Datasets:
Euanyu
/
bigbio_dataset_models

Dataset card Data Studio Files
xet
Community
1
id
stringlengths
9
104
author
stringlengths
3
36
task_category
stringclasses
32 values
tags
listlengths
1
4.05k
created_time
timestamp[ns, tz=UTC]date
2022-03-02 23:29:04
2025-03-18 02:34:30
last_modified
stringdate
2021-02-13 00:06:56
2025-03-18 09:30:19
downloads
int64
0
15.6M
likes
int64
0
4.86k
README
stringlengths
44
1.01M
matched_bigbio_names
listlengths
1
8
LoneStriker/BioMistral-7B-GPTQ
LoneStriker
text-generation
[ "transformers", "mistral", "text-generation", "medical", "biology", "conversational", "fr", "en", "de", "nl", "es", "pt", "pl", "ro", "it", "dataset:pubmed", "arxiv:2402.10373", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "gptq", "region:us" ]
2024-02-19T18:05:55Z
2024-02-19T18:19:06+00:00
35
1
--- datasets: - pubmed language: - fr - en - de - nl - es - pt - pl - ro - it license: apache-2.0 pipeline_tag: text-generation tags: - medical - biology --- <p align="center"> <img src="https://huggingface.co/BioMistral/BioMistral-7B/resolve/main/wordart_blue_m_rectangle.png?download=true" alt="drawing" width="250"/> </p> # BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains **Abstract:** Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges. In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark comprising 10 established medical question-answering (QA) tasks in English. We also explore lightweight models obtained through quantization and model merging approaches. Our results demonstrate BioMistral's superior performance compared to existing open-source medical models and its competitive edge against proprietary counterparts. Finally, to address the limited availability of data beyond English and to assess the multilingual generalization of medical LLMs, we automatically translated and evaluated this benchmark into 7 other languages. This marks the first large-scale multilingual evaluation of LLMs in the medical domain. Datasets, multilingual evaluation benchmarks, scripts, and all the models obtained during our experiments are freely released. # 1. BioMistral models **BioMistral** is a suite of Mistral-based further pre-trained open source models suited for the medical domains and pre-trained using textual data from PubMed Central Open Access (CC0, CC BY, CC BY-SA, and CC BY-ND). All the models are trained using the CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/jean-zay/) French HPC. | Model Name | Base Model | Model Type | Sequence Length | Download | |:-------------------:|:----------------------------------:|:-------------------:|:---------------:|:-----------------------------------------------------:| | BioMistral-7B | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Further Pre-trained | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B) | | BioMistral-7B-DARE | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge DARE | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-DARE) | | BioMistral-7B-TIES | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge TIES | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-TIES) | | BioMistral-7B-SLERP | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge SLERP | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-SLERP) | # 2. Quantized Models | Base Model | Method | q_group_size | w_bit | version | VRAM GB | Time | Download | |:-------------------:|:------:|:------------:|:-----:|:-------:|:-------:|:------:|:--------:| | BioMistral-7B | FP16/BF16 | | | | 15.02 | x1.00 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B) | | BioMistral-7B | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-AWQ-QGS128-W4-GEMM) | | BioMistral-7B | AWQ | 128 | 4 | GEMV | 4.68 | x10.30 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-AWQ-QGS128-W4-GEMV) | | BioMistral-7B | BnB.4 | | 4 | | 5.03 | x3.25 | [HuggingFace](blank) | | BioMistral-7B | BnB.8 | | 8 | | 8.04 | x4.34 | [HuggingFace](blank) | | BioMistral-7B-DARE | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-DARE-AWQ-QGS128-W4-GEMM) | | BioMistral-7B-TIES | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-TIES-AWQ-QGS128-W4-GEMM) | | BioMistral-7B-SLERP | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-SLERP-AWQ-QGS128-W4-GEMM) | # 2. Using BioMistral You can use BioMistral with [Hugging Face's Transformers library](https://github.com/huggingface/transformers) as follow. Loading the model and tokenizer : ```python from transformers import AutoModel, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("BioMistral/BioMistral-7B") model = AutoModel.from_pretrained("BioMistral/BioMistral-7B") ``` # 3. Supervised Fine-tuning Benchmark | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA | MedQA 5 opts | PubMedQA | MedMCQA | Avg. | |-------------------------------------------|:---------------------------------------------:|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|------------------| | **BioMistral 7B** | 59.9 | 64.0 | 56.5 | 60.4 | 59.0 | 54.7 | 50.6 | 42.8 | 77.5 | 48.1 | 57.3 | | **Mistral 7B Instruct** | **62.9** | 57.0 | 55.6 | 59.4 | 62.5 | <u>57.2</u> | 42.0 | 40.9 | 75.7 | 46.1 | 55.9 | | | | | | | | | | | | | | | **BioMistral 7B Ensemble** | <u>62.8</u> | 62.7 | <u>57.5</u> | **63.5** | 64.3 | 55.7 | 50.6 | 43.6 | 77.5 | **48.8** | 58.7 | | **BioMistral 7B DARE** | 62.3 | **67.0** | 55.8 | 61.4 | **66.9** | **58.0** | **51.1** | **45.2** | <u>77.7</u> | <u>48.7</u> | **59.4** | | **BioMistral 7B TIES** | 60.1 | <u>65.0</u> | **58.5** | 60.5 | 60.4 | 56.5 | 49.5 | 43.2 | 77.5 | 48.1 | 57.9 | | **BioMistral 7B SLERP** | 62.5 | 64.7 | 55.8 | <u>62.7</u> | <u>64.8</u> | 56.3 | <u>50.8</u> | <u>44.3</u> | **77.8** | 48.6 | <u>58.8</u> | | | | | | | | | | | | | | | **MedAlpaca 7B** | 53.1 | 58.0 | 54.1 | 58.8 | 58.1 | 48.6 | 40.1 | 33.7 | 73.6 | 37.0 | 51.5 | | **PMC-LLaMA 7B** | 24.5 | 27.7 | 35.3 | 17.4 | 30.3 | 23.3 | 25.5 | 20.2 | 72.9 | 26.6 | 30.4 | | **MediTron-7B** | 41.6 | 50.3 | 46.4 | 27.9 | 44.4 | 30.8 | 41.6 | 28.1 | 74.9 | 41.3 | 42.7 | | **BioMedGPT-LM-7B** | 51.4 | 52.0 | 49.4 | 53.3 | 50.7 | 49.1 | 42.5 | 33.9 | 76.8 | 37.6 | 49.7 | | | | | | | | | | | | | | | **GPT-3.5 Turbo 1106*** | 74.71 | 74.00 | 65.92 | 72.79 | 72.91 | 64.73 | 57.71 | 50.82 | 72.66 | 53.79 | 66.0 | Supervised Fine-Tuning (SFT) performance of BioMistral 7B models compared to baselines, measured by accuracy (↑) and averaged across 3 random seeds of 3-shot. DARE, TIES, and SLERP are model merging strategies that combine BioMistral 7B and Mistral 7B Instruct. Best model in bold, and second-best underlined. *GPT-3.5 Turbo performances are reported from the 3-shot results without SFT. # Citation BibTeX Arxiv : [https://arxiv.org/abs/2402.10373](https://arxiv.org/abs/2402.10373) ```bibtex @misc{labrak2024biomistral, title={BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains}, author={Yanis Labrak and Adrien Bazoge and Emmanuel Morin and Pierre-Antoine Gourraud and Mickael Rouvier and Richard Dufour}, year={2024}, eprint={2402.10373}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
[ "MEDQA", "PUBMEDQA" ]
YoLo2000/TiLamb-7B
YoLo2000
text-generation
[ "transformers", "pytorch", "llama", "text-generation", "bo", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2024-04-02T12:20:16Z
2024-04-03T01:08:11+00:00
35
1
--- language: - bo license: apache-2.0 --- <!-- Provide a longer summary of what this model is. --> # TiLamb-7B（Tibetan Large Language Model Base） **TiLamb-7B** 是藏文大语言模型的基座模型，它使用了 26.43GB 的藏文语料，基于Meta发布的可商用大模型 LLaMA2-7B 模型，通过 LoRA 方法进行了增量预训练。该模型在 LLaMA2 的基础上扩展了词表，从原有的词表大小 32,000 扩充藏文词汇至 61,221 ，并对 LLaMA2-7B 原始模型的 embedding 和 lm_head 进行了均值扩充初始化。更多信息请访问 [TiLamb-7B GitHub 主页](https://github.com/NLP-Learning/TiLamb)。 **重要说明**： - TiLamb-7B 是一个未经监督微调的基座模型，**不具备对话能力**。 - 要进行藏文对话和藏文 NLP 下游任务的适配（已验证的任务包括藏文新闻分类、藏文实体关系分类、藏文机器阅读理解、藏文分词、藏文摘要、藏文问题回答和藏文问题生成），建议使用 [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory/tree/main) 框架进行微调。 **使用须知**： - 本项目基于 Meta 发布的 LLaMA2-7B 模型开发，使用时请严格遵守 LLaMA2-7B 的开源许可协议。 - 如果涉及使用第三方代码，请务必遵从相关的开源许可协议。 - 模型生成的内容准确性可能受到计算方法、随机因素等的影响，因此，我们不对模型输出的准确性提供任何保证，也不会对使用相关资源和输出结果产生的任何损失承担责任。 - 如果将相关模型用于商业用途，开发者应遵守当地法律法规，确保模型输出内容的合规性。本项目不对任何由此衍生的产品或服务承担责任。 # TiLamb-7B (Tibetan Large Language Model Base) **TiLamb-7B** is the foundational model for the Tibetan language, utilizing 26.43GB of Tibetan corpora. It's based on Meta's commercially available large model, LLaMA2-7B, and has been incrementally pre-trained using the LoRA method. This model expands on LLaMA2 by enlarging the vocabulary from the original 32,000 to 61,221 Tibetan words and initializes the embedding and lm_head of the original LLaMA2-7B model through mean expansion. For more information, please visit the [TiLamb-7B GitHub page](https://github.com/NLP-Learning/TiLamb). **Important Notes**: - TiLamb-7B is an unsupervised fine-tuned base model, **lacking conversational capabilities**. - For adaptation to Tibetan dialogue and Tibetan NLP downstream tasks (verified tasks include Tibetan news classification, Tibetan entity relation classification, Tibetan machine reading comprehension, Tibetan word segmentation, Tibetan summarization, Tibetan question answering, and Tibetan question generation), it is recommended to use the [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory/tree/main) framework for fine-tuning. **Usage Notice**: - This project is developed based on the LLaMA2-7B model released by Meta, and its use must strictly adhere to the open-source license agreement of LLaMA2-7B. - If third-party code is involved, it is essential to comply with the relevant open-source license agreements. - The accuracy of the content generated by the model may be affected by computational methods, random factors, etc., therefore, we do not provide any guarantee for the accuracy of the model outputs, nor will we bear any responsibility for losses arising from the use of related resources and results. - If the related models are used for commercial purposes, developers must comply with local laws and regulations to ensure the compliance of the model output content. This project will not bear any responsibility for any products or services derived from it.
[ "BEAR" ]
Mihaiii/Squirtle
Mihaiii
sentence-similarity
[ "sentence-transformers", "onnx", "safetensors", "bert", "feature-extraction", "sentence-similarity", "bge", "mteb", "dataset:Mihaiii/qa-assistant", "license:mit", "model-index", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
2024-04-30T15:06:52Z
2024-04-30T20:00:05+00:00
35
1
--- datasets: - Mihaiii/qa-assistant library_name: sentence-transformers license: mit pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - bge - mteb model-index: - name: Squirtle results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 69.59701492537313 - type: ap value: 31.80839087521638 - type: f1 value: 63.43204352573031 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification type: mteb/amazon_polarity config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 82.09027499999999 - type: ap value: 76.95004336850603 - type: f1 value: 82.04505556179174 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 41.943999999999996 - type: f1 value: 40.40964457303876 - task: type: Retrieval dataset: name: MTEB ArguAna type: mteb/arguana config: default split: test revision: c22ab2a51041ffd869aaddef7af8d8215647e41a metrics: - type: map_at_1 value: 13.869000000000002 - type: map_at_10 value: 24.631 - type: map_at_100 value: 25.965 - type: map_at_1000 value: 26.023000000000003 - type: map_at_20 value: 25.442999999999998 - type: map_at_3 value: 20.827 - type: map_at_5 value: 22.776 - type: mrr_at_1 value: 14.580000000000002 - type: mrr_at_10 value: 24.91 - type: mrr_at_100 value: 26.229999999999997 - type: mrr_at_1000 value: 26.288 - type: mrr_at_20 value: 25.708 - type: mrr_at_3 value: 21.136 - type: mrr_at_5 value: 23.02 - type: ndcg_at_1 value: 13.869000000000002 - type: ndcg_at_10 value: 31.14 - type: ndcg_at_100 value: 37.885999999999996 - type: ndcg_at_1000 value: 39.497 - type: ndcg_at_20 value: 34.068 - type: ndcg_at_3 value: 23.163 - type: ndcg_at_5 value: 26.677 - type: precision_at_1 value: 13.869000000000002 - type: precision_at_10 value: 5.220000000000001 - type: precision_at_100 value: 0.844 - type: precision_at_1000 value: 0.097 - type: precision_at_20 value: 3.186 - type: precision_at_3 value: 9.981 - type: precision_at_5 value: 7.696 - type: recall_at_1 value: 13.869000000000002 - type: recall_at_10 value: 52.205 - type: recall_at_100 value: 84.42399999999999 - type: recall_at_1000 value: 97.297 - type: recall_at_20 value: 63.727000000000004 - type: recall_at_3 value: 29.942999999999998 - type: recall_at_5 value: 38.478 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P type: mteb/arxiv-clustering-p2p config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 33.042527574996505 - type: v_measures value: - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - 0.2896613951792161 - 0.2974905938215674 - 0.28195491579456905 - 0.3008325954323272 - 0.3012695848509836 - 0.28933380000430453 - 0.297420818100457 - 0.2792041800887245 - 0.3049968405105834 - 0.30704380358904726 - 0.39238640618067383 - 0.3932595512850983 - 0.3875472939281748 - 0.39822946285500505 - 0.39839156092566014 - 0.40184636328122075 - 0.39008499175162326 - 0.3984035967802891 - 0.39159106298575347 - 0.3923217036338575 - 0.3916410911561569 - 0.2357749280106326 - 0.23682806457721106 - 0.3122239617657793 - 0.26610676013174756 - 0.18123482803921434 - 0.2504695156635453 - 0.10917464735757001 - 0.16714512698028008 - 1.0 - 0.19931410358764295 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S type: mteb/arxiv-clustering-s2s config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 24.68133686033884 - type: v_measures value: - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - 0.2005976632299017 - 0.208968006943616 - 0.20946008190179435 - 0.20539809799180958 - 0.21463587994609631 - 0.20913407901977635 - 0.20908020832330956 - 0.1944493063711425 - 0.20181175619582953 - 0.2249901827151246 - 0.29132293951181787 - 0.29570222215271086 - 0.2796075942678196 - 0.28871411057617774 - 0.29302758518431116 - 0.29227253592096986 - 0.2856462545898644 - 0.28687743467743254 - 0.2900793948371436 - 0.28627385826697854 - 0.27308659940457203 - 0.14117319401377473 - 0.1761477350541332 - 0.24048342650129406 - 0.19387054212465876 - 0.14470023981605995 - 0.16704070762984086 - 0.07547453139959907 - 0.127993495025131 - 1.0 - 0.14319476311235024 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions type: mteb/askubuntudupquestions-reranking config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 52.344372012529384 - type: mrr value: 65.32614430813877 - task: type: STS dataset: name: MTEB BIOSSES type: mteb/biosses-sts config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 69.44065444549933 - type: cos_sim_spearman value: 71.77814153774398 - type: euclidean_pearson value: 70.59416783558756 - type: euclidean_spearman value: 71.77814153774398 - type: manhattan_pearson value: 70.99287197201959 - type: manhattan_spearman value: 72.0769435268729 - task: type: Classification dataset: name: MTEB Banking77Classification type: mteb/banking77 config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 67.12987012987013 - type: f1 value: 65.99991975715585 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P type: mteb/biorxiv-clustering-p2p config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 30.861774505346606 - type: v_measures value: - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - 0.3057878417529878 - 0.3086229109676654 - 0.3080657568280612 - 0.3002878816865892 - 0.30903247986282023 - 0.3022960257813801 - 0.31981283125167154 - 0.3119766955566159 - 0.3039859162306553 - 0.31630911061621453 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S type: mteb/biorxiv-clustering-s2s config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 21.100665285420916 - type: v_measures value: - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - 0.21042268101320297 - 0.19607301651541253 - 0.21811669828359762 - 0.20892482431651227 - 0.20621532003083415 - 0.215815720040119 - 0.20517452774094483 - 0.21396360841093787 - 0.20967704706047804 - 0.22568308513005236 - task: type: Retrieval dataset: name: MTEB CQADupstackAndroidRetrieval type: mteb/cqadupstack-android config: default split: test revision: f46a197baaae43b4f621051089b82a364682dfeb metrics: - type: map_at_1 value: 17.835 - type: map_at_10 value: 24.718999999999998 - type: map_at_100 value: 25.755 - type: map_at_1000 value: 25.887 - type: map_at_20 value: 25.217 - type: map_at_3 value: 23.076 - type: map_at_5 value: 23.96 - type: mrr_at_1 value: 23.033 - type: mrr_at_10 value: 29.868 - type: mrr_at_100 value: 30.757 - type: mrr_at_1000 value: 30.834 - type: mrr_at_20 value: 30.37 - type: mrr_at_3 value: 28.112 - type: mrr_at_5 value: 29.185 - type: ndcg_at_1 value: 23.033 - type: ndcg_at_10 value: 28.899 - type: ndcg_at_100 value: 33.788000000000004 - type: ndcg_at_1000 value: 36.962 - type: ndcg_at_20 value: 30.497000000000003 - type: ndcg_at_3 value: 26.442 - type: ndcg_at_5 value: 27.466 - type: precision_at_1 value: 23.033 - type: precision_at_10 value: 5.351 - type: precision_at_100 value: 0.9610000000000001 - type: precision_at_1000 value: 0.151 - type: precision_at_20 value: 3.2259999999999995 - type: precision_at_3 value: 12.923000000000002 - type: precision_at_5 value: 8.956 - type: recall_at_1 value: 17.835 - type: recall_at_10 value: 36.034 - type: recall_at_100 value: 57.615 - type: recall_at_1000 value: 79.72 - type: recall_at_20 value: 41.894999999999996 - type: recall_at_3 value: 28.313 - type: recall_at_5 value: 31.639 - task: type: Retrieval dataset: name: MTEB CQADupstackEnglishRetrieval type: mteb/cqadupstack-english config: default split: test revision: ad9991cb51e31e31e430383c75ffb2885547b5f0 metrics: - type: map_at_1 value: 12.166 - type: map_at_10 value: 16.320999999999998 - type: map_at_100 value: 16.954 - type: map_at_1000 value: 17.054 - type: map_at_20 value: 16.651 - type: map_at_3 value: 14.890999999999998 - type: map_at_5 value: 15.695999999999998 - type: mrr_at_1 value: 15.287 - type: mrr_at_10 value: 19.487 - type: mrr_at_100 value: 20.11 - type: mrr_at_1000 value: 20.185 - type: mrr_at_20 value: 19.830000000000002 - type: mrr_at_3 value: 18.068 - type: mrr_at_5 value: 18.855 - type: ndcg_at_1 value: 15.287 - type: ndcg_at_10 value: 19.198999999999998 - type: ndcg_at_100 value: 22.395 - type: ndcg_at_1000 value: 25.106 - type: ndcg_at_20 value: 20.297 - type: ndcg_at_3 value: 16.743 - type: ndcg_at_5 value: 17.855999999999998 - type: precision_at_1 value: 15.287 - type: precision_at_10 value: 3.605 - type: precision_at_100 value: 0.638 - type: precision_at_1000 value: 0.108 - type: precision_at_20 value: 2.166 - type: precision_at_3 value: 8.089 - type: precision_at_5 value: 5.822 - type: recall_at_1 value: 12.166 - type: recall_at_10 value: 24.701999999999998 - type: recall_at_100 value: 39.199 - type: recall_at_1000 value: 58.205 - type: recall_at_20 value: 28.791 - type: recall_at_3 value: 17.469 - type: recall_at_5 value: 20.615 - task: type: Retrieval dataset: name: MTEB CQADupstackGamingRetrieval type: mteb/cqadupstack-gaming config: default split: test revision: 4885aa143210c98657558c04aaf3dc47cfb54340 metrics: - type: map_at_1 value: 19.667 - type: map_at_10 value: 27.163999999999998 - type: map_at_100 value: 28.044000000000004 - type: map_at_1000 value: 28.142 - type: map_at_20 value: 27.645999999999997 - type: map_at_3 value: 24.914 - type: map_at_5 value: 26.078000000000003 - type: mrr_at_1 value: 23.197000000000003 - type: mrr_at_10 value: 30.202 - type: mrr_at_100 value: 30.976 - type: mrr_at_1000 value: 31.047000000000004 - type: mrr_at_20 value: 30.636000000000003 - type: mrr_at_3 value: 28.004 - type: mrr_at_5 value: 29.164 - type: ndcg_at_1 value: 23.197000000000003 - type: ndcg_at_10 value: 31.618000000000002 - type: ndcg_at_100 value: 35.977 - type: ndcg_at_1000 value: 38.458 - type: ndcg_at_20 value: 33.242 - type: ndcg_at_3 value: 27.285999999999998 - type: ndcg_at_5 value: 29.163 - type: precision_at_1 value: 23.197000000000003 - type: precision_at_10 value: 5.26 - type: precision_at_100 value: 0.8200000000000001 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_20 value: 3.082 - type: precision_at_3 value: 12.247 - type: precision_at_5 value: 8.577 - type: recall_at_1 value: 19.667 - type: recall_at_10 value: 42.443 - type: recall_at_100 value: 62.254 - type: recall_at_1000 value: 80.44 - type: recall_at_20 value: 48.447 - type: recall_at_3 value: 30.518 - type: recall_at_5 value: 35.22 - task: type: Retrieval dataset: name: MTEB CQADupstackGisRetrieval type: mteb/cqadupstack-gis config: default split: test revision: 5003b3064772da1887988e05400cf3806fe491f2 metrics: - type: map_at_1 value: 10.923 - type: map_at_10 value: 14.24 - type: map_at_100 value: 15.001000000000001 - type: map_at_1000 value: 15.092 - type: map_at_20 value: 14.623 - type: map_at_3 value: 13.168 - type: map_at_5 value: 13.678 - type: mrr_at_1 value: 11.525 - type: mrr_at_10 value: 15.187000000000001 - type: mrr_at_100 value: 15.939999999999998 - type: mrr_at_1000 value: 16.03 - type: mrr_at_20 value: 15.557000000000002 - type: mrr_at_3 value: 13.991999999999999 - type: mrr_at_5 value: 14.557 - type: ndcg_at_1 value: 11.525 - type: ndcg_at_10 value: 16.512999999999998 - type: ndcg_at_100 value: 20.445 - type: ndcg_at_1000 value: 23.398 - type: ndcg_at_20 value: 17.832 - type: ndcg_at_3 value: 14.224 - type: ndcg_at_5 value: 15.136 - type: precision_at_1 value: 11.525 - type: precision_at_10 value: 2.565 - type: precision_at_100 value: 0.484 - type: precision_at_1000 value: 0.076 - type: precision_at_20 value: 1.582 - type: precision_at_3 value: 5.989 - type: precision_at_5 value: 4.1579999999999995 - type: recall_at_1 value: 10.923 - type: recall_at_10 value: 22.695 - type: recall_at_100 value: 40.892 - type: recall_at_1000 value: 64.456 - type: recall_at_20 value: 27.607 - type: recall_at_3 value: 16.348 - type: recall_at_5 value: 18.504 - task: type: Retrieval dataset: name: MTEB CQADupstackMathematicaRetrieval type: mteb/cqadupstack-mathematica config: default split: test revision: 90fceea13679c63fe563ded68f3b6f06e50061de metrics: - type: map_at_1 value: 5.409 - type: map_at_10 value: 8.584999999999999 - type: map_at_100 value: 9.392 - type: map_at_1000 value: 9.5 - type: map_at_20 value: 8.943 - type: map_at_3 value: 7.3 - type: map_at_5 value: 7.962 - type: mrr_at_1 value: 6.965000000000001 - type: mrr_at_10 value: 10.593 - type: mrr_at_100 value: 11.496 - type: mrr_at_1000 value: 11.578 - type: mrr_at_20 value: 11.021 - type: mrr_at_3 value: 8.976 - type: mrr_at_5 value: 9.797 - type: ndcg_at_1 value: 6.965000000000001 - type: ndcg_at_10 value: 11.056000000000001 - type: ndcg_at_100 value: 15.683 - type: ndcg_at_1000 value: 18.873 - type: ndcg_at_20 value: 12.331 - type: ndcg_at_3 value: 8.334 - type: ndcg_at_5 value: 9.512 - type: precision_at_1 value: 6.965000000000001 - type: precision_at_10 value: 2.177 - type: precision_at_100 value: 0.54 - type: precision_at_1000 value: 0.095 - type: precision_at_20 value: 1.468 - type: precision_at_3 value: 3.9800000000000004 - type: precision_at_5 value: 3.109 - type: recall_at_1 value: 5.409 - type: recall_at_10 value: 16.895 - type: recall_at_100 value: 38.167 - type: recall_at_1000 value: 61.783 - type: recall_at_20 value: 21.248 - type: recall_at_3 value: 9.518 - type: recall_at_5 value: 12.426 - task: type: Retrieval dataset: name: MTEB CQADupstackPhysicsRetrieval type: mteb/cqadupstack-physics config: default split: test revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4 metrics: - type: map_at_1 value: 13.688 - type: map_at_10 value: 19.096 - type: map_at_100 value: 20.058 - type: map_at_1000 value: 20.194000000000003 - type: map_at_20 value: 19.595000000000002 - type: map_at_3 value: 17.313000000000002 - type: map_at_5 value: 18.41 - type: mrr_at_1 value: 17.132 - type: mrr_at_10 value: 22.95 - type: mrr_at_100 value: 23.799 - type: mrr_at_1000 value: 23.884 - type: mrr_at_20 value: 23.419999999999998 - type: mrr_at_3 value: 20.95 - type: mrr_at_5 value: 22.21 - type: ndcg_at_1 value: 17.132 - type: ndcg_at_10 value: 22.88 - type: ndcg_at_100 value: 27.572000000000003 - type: ndcg_at_1000 value: 30.824 - type: ndcg_at_20 value: 24.516 - type: ndcg_at_3 value: 19.64 - type: ndcg_at_5 value: 21.4 - type: precision_at_1 value: 17.132 - type: precision_at_10 value: 4.263999999999999 - type: precision_at_100 value: 0.7969999999999999 - type: precision_at_1000 value: 0.125 - type: precision_at_20 value: 2.6519999999999997 - type: precision_at_3 value: 9.336 - type: precision_at_5 value: 6.93 - type: recall_at_1 value: 13.688 - type: recall_at_10 value: 30.537999999999997 - type: recall_at_100 value: 51.017999999999994 - type: recall_at_1000 value: 73.921 - type: recall_at_20 value: 36.174 - type: recall_at_3 value: 21.568 - type: recall_at_5 value: 26.127 - task: type: Retrieval dataset: name: MTEB CQADupstackProgrammersRetrieval type: mteb/cqadupstack-programmers config: default split: test revision: 6184bc1440d2dbc7612be22b50686b8826d22b32 metrics: - type: map_at_1 value: 8.173 - type: map_at_10 value: 11.648 - type: map_at_100 value: 12.434000000000001 - type: map_at_1000 value: 12.540000000000001 - type: map_at_20 value: 12.030000000000001 - type: map_at_3 value: 10.568 - type: map_at_5 value: 11.064 - type: mrr_at_1 value: 10.274 - type: mrr_at_10 value: 14.505 - type: mrr_at_100 value: 15.332 - type: mrr_at_1000 value: 15.409 - type: mrr_at_20 value: 14.899999999999999 - type: mrr_at_3 value: 13.375 - type: mrr_at_5 value: 13.929 - type: ndcg_at_1 value: 10.274 - type: ndcg_at_10 value: 14.283999999999999 - type: ndcg_at_100 value: 18.731 - type: ndcg_at_1000 value: 21.744 - type: ndcg_at_20 value: 15.647 - type: ndcg_at_3 value: 12.278 - type: ndcg_at_5 value: 12.974 - type: precision_at_1 value: 10.274 - type: precision_at_10 value: 2.683 - type: precision_at_100 value: 0.582 - type: precision_at_1000 value: 0.099 - type: precision_at_20 value: 1.7409999999999999 - type: precision_at_3 value: 6.088 - type: precision_at_5 value: 4.201 - type: recall_at_1 value: 8.173 - type: recall_at_10 value: 19.642 - type: recall_at_100 value: 40.213 - type: recall_at_1000 value: 62.083999999999996 - type: recall_at_20 value: 24.537 - type: recall_at_3 value: 13.700999999999999 - type: recall_at_5 value: 15.751000000000001 - task: type: Retrieval dataset: name: MTEB CQADupstackRetrieval type: mteb/cqadupstack config: default split: test revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: map_at_1 value: 11.252416666666667 - type: map_at_10 value: 15.589583333333334 - type: map_at_100 value: 16.381166666666665 - type: map_at_1000 value: 16.490333333333332 - type: map_at_20 value: 15.99116666666667 - type: map_at_3 value: 14.140916666666667 - type: map_at_5 value: 14.9045 - type: mrr_at_1 value: 13.710416666666664 - type: mrr_at_10 value: 18.34416666666667 - type: mrr_at_100 value: 19.110083333333336 - type: mrr_at_1000 value: 19.192583333333335 - type: mrr_at_20 value: 18.74783333333333 - type: mrr_at_3 value: 16.799416666666666 - type: mrr_at_5 value: 17.62725 - type: ndcg_at_1 value: 13.710416666666664 - type: ndcg_at_10 value: 18.628583333333335 - type: ndcg_at_100 value: 22.733666666666668 - type: ndcg_at_1000 value: 25.728499999999997 - type: ndcg_at_20 value: 19.994500000000002 - type: ndcg_at_3 value: 15.918083333333332 - type: ndcg_at_5 value: 17.086999999999996 - type: precision_at_1 value: 13.710416666666664 - type: precision_at_10 value: 3.3575 - type: precision_at_100 value: 0.6368333333333333 - type: precision_at_1000 value: 0.10508333333333333 - type: precision_at_20 value: 2.074833333333333 - type: precision_at_3 value: 7.440333333333333 - type: precision_at_5 value: 5.341916666666667 - type: recall_at_1 value: 11.252416666666667 - type: recall_at_10 value: 25.200833333333332 - type: recall_at_100 value: 44.075333333333326 - type: recall_at_1000 value: 66.12541666666665 - type: recall_at_20 value: 30.24916666666667 - type: recall_at_3 value: 17.46591666666667 - type: recall_at_5 value: 20.53691666666667 - task: type: Retrieval dataset: name: MTEB CQADupstackStatsRetrieval type: mteb/cqadupstack-stats config: default split: test revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a metrics: - type: map_at_1 value: 8.696 - type: map_at_10 value: 12.339 - type: map_at_100 value: 12.946 - type: map_at_1000 value: 13.04 - type: map_at_20 value: 12.6 - type: map_at_3 value: 11.06 - type: map_at_5 value: 11.530999999999999 - type: mrr_at_1 value: 10.276 - type: mrr_at_10 value: 14.463999999999999 - type: mrr_at_100 value: 15.07 - type: mrr_at_1000 value: 15.152 - type: mrr_at_20 value: 14.737 - type: mrr_at_3 value: 13.037 - type: mrr_at_5 value: 13.627 - type: ndcg_at_1 value: 10.276 - type: ndcg_at_10 value: 15.085 - type: ndcg_at_100 value: 18.538 - type: ndcg_at_1000 value: 21.461 - type: ndcg_at_20 value: 15.976 - type: ndcg_at_3 value: 12.454 - type: ndcg_at_5 value: 13.195 - type: precision_at_1 value: 10.276 - type: precision_at_10 value: 2.669 - type: precision_at_100 value: 0.48900000000000005 - type: precision_at_1000 value: 0.08 - type: precision_at_20 value: 1.572 - type: precision_at_3 value: 5.726 - type: precision_at_5 value: 3.9570000000000003 - type: recall_at_1 value: 8.696 - type: recall_at_10 value: 21.766 - type: recall_at_100 value: 38.269 - type: recall_at_1000 value: 61.106 - type: recall_at_20 value: 24.992 - type: recall_at_3 value: 14.032 - type: recall_at_5 value: 15.967999999999998 - task: type: Retrieval dataset: name: MTEB CQADupstackTexRetrieval type: mteb/cqadupstack-tex config: default split: test revision: 46989137a86843e03a6195de44b09deda022eec7 metrics: - type: map_at_1 value: 6.13 - type: map_at_10 value: 9.067 - type: map_at_100 value: 9.687999999999999 - type: map_at_1000 value: 9.792 - type: map_at_20 value: 9.384 - type: map_at_3 value: 8.006 - type: map_at_5 value: 8.581999999999999 - type: mrr_at_1 value: 7.605 - type: mrr_at_10 value: 11.111 - type: mrr_at_100 value: 11.745999999999999 - type: mrr_at_1000 value: 11.837 - type: mrr_at_20 value: 11.452 - type: mrr_at_3 value: 9.922 - type: mrr_at_5 value: 10.522 - type: ndcg_at_1 value: 7.605 - type: ndcg_at_10 value: 11.302 - type: ndcg_at_100 value: 14.629 - type: ndcg_at_1000 value: 17.739 - type: ndcg_at_20 value: 12.411 - type: ndcg_at_3 value: 9.28 - type: ndcg_at_5 value: 10.161000000000001 - type: precision_at_1 value: 7.605 - type: precision_at_10 value: 2.22 - type: precision_at_100 value: 0.46499999999999997 - type: precision_at_1000 value: 0.087 - type: precision_at_20 value: 1.428 - type: precision_at_3 value: 4.565 - type: precision_at_5 value: 3.3649999999999998 - type: recall_at_1 value: 6.13 - type: recall_at_10 value: 16.009999999999998 - type: recall_at_100 value: 31.467 - type: recall_at_1000 value: 54.722 - type: recall_at_20 value: 20.137 - type: recall_at_3 value: 10.347000000000001 - type: recall_at_5 value: 12.692 - task: type: Retrieval dataset: name: MTEB CQADupstackUnixRetrieval type: mteb/cqadupstack-unix config: default split: test revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53 metrics: - type: map_at_1 value: 11.645 - type: map_at_10 value: 15.466 - type: map_at_100 value: 16.147 - type: map_at_1000 value: 16.247 - type: map_at_20 value: 15.806999999999999 - type: map_at_3 value: 14.011000000000001 - type: map_at_5 value: 14.967 - type: mrr_at_1 value: 14.179 - type: mrr_at_10 value: 18.512 - type: mrr_at_100 value: 19.184 - type: mrr_at_1000 value: 19.267 - type: mrr_at_20 value: 18.855 - type: mrr_at_3 value: 16.993 - type: mrr_at_5 value: 17.954 - type: ndcg_at_1 value: 14.179 - type: ndcg_at_10 value: 18.311 - type: ndcg_at_100 value: 21.996 - type: ndcg_at_1000 value: 24.942 - type: ndcg_at_20 value: 19.522000000000002 - type: ndcg_at_3 value: 15.593000000000002 - type: ndcg_at_5 value: 17.116 - type: precision_at_1 value: 14.179 - type: precision_at_10 value: 3.116 - type: precision_at_100 value: 0.5519999999999999 - type: precision_at_1000 value: 0.091 - type: precision_at_20 value: 1.87 - type: precision_at_3 value: 7.090000000000001 - type: precision_at_5 value: 5.224 - type: recall_at_1 value: 11.645 - type: recall_at_10 value: 24.206 - type: recall_at_100 value: 41.29 - type: recall_at_1000 value: 63.205999999999996 - type: recall_at_20 value: 28.659000000000002 - type: recall_at_3 value: 16.771 - type: recall_at_5 value: 20.602 - task: type: Retrieval dataset: name: MTEB CQADupstackWebmastersRetrieval type: mteb/cqadupstack-webmasters config: default split: test revision: 160c094312a0e1facb97e55eeddb698c0abe3571 metrics: - type: map_at_1 value: 12.435 - type: map_at_10 value: 17.263 - type: map_at_100 value: 18.137 - type: map_at_1000 value: 18.282999999999998 - type: map_at_20 value: 17.724 - type: map_at_3 value: 15.648000000000001 - type: map_at_5 value: 16.542 - type: mrr_at_1 value: 15.809999999999999 - type: mrr_at_10 value: 20.687 - type: mrr_at_100 value: 21.484 - type: mrr_at_1000 value: 21.567 - type: mrr_at_20 value: 21.124000000000002 - type: mrr_at_3 value: 19.104 - type: mrr_at_5 value: 19.974 - type: ndcg_at_1 value: 15.809999999999999 - type: ndcg_at_10 value: 20.801 - type: ndcg_at_100 value: 25.001 - type: ndcg_at_1000 value: 28.347 - type: ndcg_at_20 value: 22.223000000000003 - type: ndcg_at_3 value: 18.046 - type: ndcg_at_5 value: 19.308 - type: precision_at_1 value: 15.809999999999999 - type: precision_at_10 value: 4.032 - type: precision_at_100 value: 0.832 - type: precision_at_1000 value: 0.16 - type: precision_at_20 value: 2.54 - type: precision_at_3 value: 8.63 - type: precision_at_5 value: 6.4030000000000005 - type: recall_at_1 value: 12.435 - type: recall_at_10 value: 27.495000000000005 - type: recall_at_100 value: 47.522999999999996 - type: recall_at_1000 value: 70.804 - type: recall_at_20 value: 33.334 - type: recall_at_3 value: 19.192 - type: recall_at_5 value: 22.435 - task: type: Retrieval dataset: name: MTEB CQADupstackWordpressRetrieval type: mteb/cqadupstack-wordpress config: default split: test revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: map_at_1 value: 8.262 - type: map_at_10 value: 11.167 - type: map_at_100 value: 12.017999999999999 - type: map_at_1000 value: 12.113 - type: map_at_20 value: 11.674 - type: map_at_3 value: 9.736 - type: map_at_5 value: 10.384 - type: mrr_at_1 value: 9.242 - type: mrr_at_10 value: 12.564 - type: mrr_at_100 value: 13.427 - type: mrr_at_1000 value: 13.520999999999999 - type: mrr_at_20 value: 13.072000000000001 - type: mrr_at_3 value: 11.06 - type: mrr_at_5 value: 11.753 - type: ndcg_at_1 value: 9.242 - type: ndcg_at_10 value: 13.594999999999999 - type: ndcg_at_100 value: 18.049 - type: ndcg_at_1000 value: 20.888 - type: ndcg_at_20 value: 15.440000000000001 - type: ndcg_at_3 value: 10.697 - type: ndcg_at_5 value: 11.757 - type: precision_at_1 value: 9.242 - type: precision_at_10 value: 2.348 - type: precision_at_100 value: 0.482 - type: precision_at_1000 value: 0.077 - type: precision_at_20 value: 1.5709999999999997 - type: precision_at_3 value: 4.621 - type: precision_at_5 value: 3.401 - type: recall_at_1 value: 8.262 - type: recall_at_10 value: 19.983999999999998 - type: recall_at_100 value: 40.997 - type: recall_at_1000 value: 63.058 - type: recall_at_20 value: 27.168999999999997 - type: recall_at_3 value: 11.814 - type: recall_at_5 value: 14.463999999999999 - task: type: Retrieval dataset: name: MTEB ClimateFEVER type: mteb/climate-fever config: default split: test revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 metrics: - type: map_at_1 value: 4.058 - type: map_at_10 value: 6.734 - type: map_at_100 value: 7.593999999999999 - type: map_at_1000 value: 7.736999999999999 - type: map_at_20 value: 7.102 - type: map_at_3 value: 5.559 - type: map_at_5 value: 6.178999999999999 - type: mrr_at_1 value: 8.404 - type: mrr_at_10 value: 13.514999999999999 - type: mrr_at_100 value: 14.518 - type: mrr_at_1000 value: 14.599 - type: mrr_at_20 value: 14.025000000000002 - type: mrr_at_3 value: 11.584999999999999 - type: mrr_at_5 value: 12.588 - type: ndcg_at_1 value: 8.404 - type: ndcg_at_10 value: 10.02 - type: ndcg_at_100 value: 14.771999999999998 - type: ndcg_at_1000 value: 18.251 - type: ndcg_at_20 value: 11.378 - type: ndcg_at_3 value: 7.675 - type: ndcg_at_5 value: 8.558 - type: precision_at_1 value: 8.404 - type: precision_at_10 value: 3.212 - type: precision_at_100 value: 0.83 - type: precision_at_1000 value: 0.146 - type: precision_at_20 value: 2.186 - type: precision_at_3 value: 5.624 - type: precision_at_5 value: 4.5600000000000005 - type: recall_at_1 value: 4.058 - type: recall_at_10 value: 12.751999999999999 - type: recall_at_100 value: 30.219 - type: recall_at_1000 value: 50.749 - type: recall_at_20 value: 16.634 - type: recall_at_3 value: 7.234999999999999 - type: recall_at_5 value: 9.418 - task: type: Retrieval dataset: name: MTEB DBPedia type: mteb/dbpedia config: default split: test revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 metrics: - type: map_at_1 value: 5.516 - type: map_at_10 value: 11.001 - type: map_at_100 value: 14.527999999999999 - type: map_at_1000 value: 15.417 - type: map_at_20 value: 12.446 - type: map_at_3 value: 8.269 - type: map_at_5 value: 9.345 - type: mrr_at_1 value: 43.5 - type: mrr_at_10 value: 54.078 - type: mrr_at_100 value: 54.655 - type: mrr_at_1000 value: 54.679 - type: mrr_at_20 value: 54.461999999999996 - type: mrr_at_3 value: 51.37500000000001 - type: mrr_at_5 value: 53.25 - type: ndcg_at_1 value: 33.125 - type: ndcg_at_10 value: 25.665 - type: ndcg_at_100 value: 28.116000000000003 - type: ndcg_at_1000 value: 34.477000000000004 - type: ndcg_at_20 value: 25.027 - type: ndcg_at_3 value: 28.4 - type: ndcg_at_5 value: 27.094 - type: precision_at_1 value: 43.5 - type: precision_at_10 value: 21.65 - type: precision_at_100 value: 6.351999999999999 - type: precision_at_1000 value: 1.306 - type: precision_at_20 value: 15.662 - type: precision_at_3 value: 32.333 - type: precision_at_5 value: 28.199999999999996 - type: recall_at_1 value: 5.516 - type: recall_at_10 value: 15.457 - type: recall_at_100 value: 32.903 - type: recall_at_1000 value: 53.81700000000001 - type: recall_at_20 value: 20.365 - type: recall_at_3 value: 9.528 - type: recall_at_5 value: 11.619 - task: type: Classification dataset: name: MTEB EmotionClassification type: mteb/emotion config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 45.79 - type: f1 value: 38.89634882093881 - task: type: Retrieval dataset: name: MTEB FEVER type: mteb/fever config: default split: test revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 metrics: - type: map_at_1 value: 18.063000000000002 - type: map_at_10 value: 24.911 - type: map_at_100 value: 25.688 - type: map_at_1000 value: 25.758 - type: map_at_20 value: 25.358999999999998 - type: map_at_3 value: 22.743 - type: map_at_5 value: 23.924 - type: mrr_at_1 value: 19.472 - type: mrr_at_10 value: 26.587 - type: mrr_at_100 value: 27.362 - type: mrr_at_1000 value: 27.428 - type: mrr_at_20 value: 27.040999999999997 - type: mrr_at_3 value: 24.362000000000002 - type: mrr_at_5 value: 25.593 - type: ndcg_at_1 value: 19.472 - type: ndcg_at_10 value: 29.183999999999997 - type: ndcg_at_100 value: 33.207 - type: ndcg_at_1000 value: 35.21 - type: ndcg_at_20 value: 30.791 - type: ndcg_at_3 value: 24.701999999999998 - type: ndcg_at_5 value: 26.823000000000004 - type: precision_at_1 value: 19.472 - type: precision_at_10 value: 4.469 - type: precision_at_100 value: 0.6629999999999999 - type: precision_at_1000 value: 0.08499999999999999 - type: precision_at_20 value: 2.59 - type: precision_at_3 value: 10.401 - type: precision_at_5 value: 7.363 - type: recall_at_1 value: 18.063000000000002 - type: recall_at_10 value: 41.071999999999996 - type: recall_at_100 value: 60.049 - type: recall_at_1000 value: 75.64699999999999 - type: recall_at_20 value: 47.211999999999996 - type: recall_at_3 value: 28.796 - type: recall_at_5 value: 33.894999999999996 - task: type: Retrieval dataset: name: MTEB FiQA2018 type: mteb/fiqa config: default split: test revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: map_at_1 value: 2.45 - type: map_at_10 value: 4.255 - type: map_at_100 value: 4.809 - type: map_at_1000 value: 4.954 - type: map_at_20 value: 4.513 - type: map_at_3 value: 3.4029999999999996 - type: map_at_5 value: 3.782 - type: mrr_at_1 value: 4.938 - type: mrr_at_10 value: 8.231 - type: mrr_at_100 value: 8.902000000000001 - type: mrr_at_1000 value: 9.019 - type: mrr_at_20 value: 8.530999999999999 - type: mrr_at_3 value: 6.944 - type: mrr_at_5 value: 7.623 - type: ndcg_at_1 value: 4.938 - type: ndcg_at_10 value: 6.425 - type: ndcg_at_100 value: 9.661999999999999 - type: ndcg_at_1000 value: 13.911999999999999 - type: ndcg_at_20 value: 7.3 - type: ndcg_at_3 value: 4.907 - type: ndcg_at_5 value: 5.406 - type: precision_at_1 value: 4.938 - type: precision_at_10 value: 2.037 - type: precision_at_100 value: 0.528 - type: precision_at_1000 value: 0.125 - type: precision_at_20 value: 1.366 - type: precision_at_3 value: 3.344 - type: precision_at_5 value: 2.7470000000000003 - type: recall_at_1 value: 2.45 - type: recall_at_10 value: 8.987 - type: recall_at_100 value: 22.302 - type: recall_at_1000 value: 49.903999999999996 - type: recall_at_20 value: 11.712 - type: recall_at_3 value: 4.675 - type: recall_at_5 value: 6.161 - task: type: Retrieval dataset: name: MTEB HotpotQA type: mteb/hotpotqa config: default split: test revision: ab518f4d6fcca38d87c25209f94beba119d02014 metrics: - type: map_at_1 value: 23.585 - type: map_at_10 value: 31.893 - type: map_at_100 value: 32.851 - type: map_at_1000 value: 32.951 - type: map_at_20 value: 32.415 - type: map_at_3 value: 29.787000000000003 - type: map_at_5 value: 31.012 - type: mrr_at_1 value: 47.171 - type: mrr_at_10 value: 54.333 - type: mrr_at_100 value: 54.949000000000005 - type: mrr_at_1000 value: 54.98800000000001 - type: mrr_at_20 value: 54.702 - type: mrr_at_3 value: 52.632999999999996 - type: mrr_at_5 value: 53.652 - type: ndcg_at_1 value: 47.171 - type: ndcg_at_10 value: 39.884 - type: ndcg_at_100 value: 44.019000000000005 - type: ndcg_at_1000 value: 46.303 - type: ndcg_at_20 value: 41.461999999999996 - type: ndcg_at_3 value: 36.153999999999996 - type: ndcg_at_5 value: 38.072 - type: precision_at_1 value: 47.171 - type: precision_at_10 value: 8.396 - type: precision_at_100 value: 1.169 - type: precision_at_1000 value: 0.147 - type: precision_at_20 value: 4.707 - type: precision_at_3 value: 22.408 - type: precision_at_5 value: 14.966 - type: recall_at_1 value: 23.585 - type: recall_at_10 value: 41.978 - type: recall_at_100 value: 58.447 - type: recall_at_1000 value: 73.7 - type: recall_at_20 value: 47.07 - type: recall_at_3 value: 33.611999999999995 - type: recall_at_5 value: 37.413999999999994 - task: type: Classification dataset: name: MTEB ImdbClassification type: mteb/imdb config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 74.9528 - type: ap value: 69.50790744137139 - type: f1 value: 74.77689594327182 - task: type: Retrieval dataset: name: MTEB MSMARCO type: mteb/msmarco config: default split: dev revision: c5a29a104738b98a9e76336939199e264163d4a0 metrics: - type: map_at_1 value: 8.186 - type: map_at_10 value: 13.352 - type: map_at_100 value: 14.147000000000002 - type: map_at_1000 value: 14.231 - type: map_at_20 value: 13.753000000000002 - type: map_at_3 value: 11.529 - type: map_at_5 value: 12.497 - type: mrr_at_1 value: 8.424 - type: mrr_at_10 value: 13.675999999999998 - type: mrr_at_100 value: 14.475999999999999 - type: mrr_at_1000 value: 14.557 - type: mrr_at_20 value: 14.084 - type: mrr_at_3 value: 11.843 - type: mrr_at_5 value: 12.82 - type: ndcg_at_1 value: 8.424 - type: ndcg_at_10 value: 16.534 - type: ndcg_at_100 value: 20.982 - type: ndcg_at_1000 value: 23.538999999999998 - type: ndcg_at_20 value: 18.012 - type: ndcg_at_3 value: 12.729 - type: ndcg_at_5 value: 14.466999999999999 - type: precision_at_1 value: 8.424 - type: precision_at_10 value: 2.7449999999999997 - type: precision_at_100 value: 0.507 - type: precision_at_1000 value: 0.073 - type: precision_at_20 value: 1.683 - type: precision_at_3 value: 5.478000000000001 - type: precision_at_5 value: 4.16 - type: recall_at_1 value: 8.186 - type: recall_at_10 value: 26.415 - type: recall_at_100 value: 48.282000000000004 - type: recall_at_1000 value: 68.869 - type: recall_at_20 value: 32.207 - type: recall_at_3 value: 15.909 - type: recall_at_5 value: 20.09 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 87.26858185134519 - type: f1 value: 86.73793752046078 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 54.65800273597811 - type: f1 value: 36.16413360524473 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 61.519838601210495 - type: f1 value: 58.35755839392156 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 67.04102219233357 - type: f1 value: 65.55523696441647 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P type: mteb/medrxiv-clustering-p2p config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 27.16765056253893 - type: v_measures value: - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - 0.2535665532592405 - 0.25745435154373697 - 0.2588139996653209 - 0.2563977645588755 - 0.2572790917147801 - 0.28011260965698515 - 0.28489569719921415 - 0.2978121202496781 - 0.2927319740642704 - 0.27770089434179124 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S type: mteb/medrxiv-clustering-s2s config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 23.778196508186724 - type: v_measures value: - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - 0.22243646306633857 - 0.2203410753173429 - 0.2227543188103344 - 0.22414069966133132 - 0.2284479943649894 - 0.2523527902057292 - 0.25535019508635054 - 0.25480623149347 - 0.2575581979609686 - 0.23963168485181752 - task: type: Reranking dataset: name: MTEB MindSmallReranking type: mteb/mind_small config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.088514713666076 - type: mrr value: 31.010218178449588 - task: type: Retrieval dataset: name: MTEB NFCorpus type: mteb/nfcorpus config: default split: test revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 metrics: - type: map_at_1 value: 2.228 - type: map_at_10 value: 4.338 - type: map_at_100 value: 5.427 - type: map_at_1000 value: 6.325 - type: map_at_20 value: 4.729 - type: map_at_3 value: 3.495 - type: map_at_5 value: 3.8150000000000004 - type: mrr_at_1 value: 22.291 - type: mrr_at_10 value: 29.622 - type: mrr_at_100 value: 30.547 - type: mrr_at_1000 value: 30.618000000000002 - type: mrr_at_20 value: 30.070000000000004 - type: mrr_at_3 value: 27.141 - type: mrr_at_5 value: 28.488000000000003 - type: ndcg_at_1 value: 21.362000000000002 - type: ndcg_at_10 value: 15.64 - type: ndcg_at_100 value: 14.832 - type: ndcg_at_1000 value: 23.980999999999998 - type: ndcg_at_20 value: 14.408000000000001 - type: ndcg_at_3 value: 18.719 - type: ndcg_at_5 value: 17.137 - type: precision_at_1 value: 21.981 - type: precision_at_10 value: 11.548 - type: precision_at_100 value: 4.223 - type: precision_at_1000 value: 1.6500000000000001 - type: precision_at_20 value: 8.39 - type: precision_at_3 value: 17.337 - type: precision_at_5 value: 14.613000000000001 - type: recall_at_1 value: 2.228 - type: recall_at_10 value: 6.9190000000000005 - type: recall_at_100 value: 16.854 - type: recall_at_1000 value: 49.179 - type: recall_at_20 value: 9.166 - type: recall_at_3 value: 4.263 - type: recall_at_5 value: 4.956 - task: type: Retrieval dataset: name: MTEB NQ type: mteb/nq config: default split: test revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 metrics: - type: map_at_1 value: 9.176 - type: map_at_10 value: 15.720999999999998 - type: map_at_100 value: 16.847 - type: map_at_1000 value: 16.939999999999998 - type: map_at_20 value: 16.355 - type: map_at_3 value: 13.402 - type: map_at_5 value: 14.663 - type: mrr_at_1 value: 10.458 - type: mrr_at_10 value: 17.413 - type: mrr_at_100 value: 18.442 - type: mrr_at_1000 value: 18.52 - type: mrr_at_20 value: 18.006 - type: mrr_at_3 value: 15.043999999999999 - type: mrr_at_5 value: 16.367 - type: ndcg_at_1 value: 10.458 - type: ndcg_at_10 value: 19.994999999999997 - type: ndcg_at_100 value: 25.665 - type: ndcg_at_1000 value: 28.277 - type: ndcg_at_20 value: 22.233 - type: ndcg_at_3 value: 15.168999999999999 - type: ndcg_at_5 value: 17.453 - type: precision_at_1 value: 10.458 - type: precision_at_10 value: 3.711 - type: precision_at_100 value: 0.697 - type: precision_at_1000 value: 0.095 - type: precision_at_20 value: 2.3810000000000002 - type: precision_at_3 value: 7.204000000000001 - type: precision_at_5 value: 5.568 - type: recall_at_1 value: 9.176 - type: recall_at_10 value: 31.646 - type: recall_at_100 value: 57.865 - type: recall_at_1000 value: 78.11399999999999 - type: recall_at_20 value: 40.117000000000004 - type: recall_at_3 value: 18.67 - type: recall_at_5 value: 24.063000000000002 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval type: mteb/quora config: default split: test revision: e4e08e0b7dbe3c8700f0daef558ff32256715259 metrics: - type: map_at_1 value: 62.597 - type: map_at_10 value: 75.3 - type: map_at_100 value: 76.057 - type: map_at_1000 value: 76.089 - type: map_at_20 value: 75.762 - type: map_at_3 value: 72.41499999999999 - type: map_at_5 value: 74.139 - type: mrr_at_1 value: 72.11999999999999 - type: mrr_at_10 value: 79.44600000000001 - type: mrr_at_100 value: 79.691 - type: mrr_at_1000 value: 79.696 - type: mrr_at_20 value: 79.604 - type: mrr_at_3 value: 78.015 - type: mrr_at_5 value: 78.90700000000001 - type: ndcg_at_1 value: 72.15 - type: ndcg_at_10 value: 79.937 - type: ndcg_at_100 value: 82.074 - type: ndcg_at_1000 value: 82.443 - type: ndcg_at_20 value: 80.916 - type: ndcg_at_3 value: 76.452 - type: ndcg_at_5 value: 78.192 - type: precision_at_1 value: 72.15 - type: precision_at_10 value: 12.117 - type: precision_at_100 value: 1.4500000000000002 - type: precision_at_1000 value: 0.154 - type: precision_at_20 value: 6.503 - type: precision_at_3 value: 33.267 - type: precision_at_5 value: 21.944 - type: recall_at_1 value: 62.597 - type: recall_at_10 value: 88.911 - type: recall_at_100 value: 97.112 - type: recall_at_1000 value: 99.229 - type: recall_at_20 value: 92.231 - type: recall_at_3 value: 78.83099999999999 - type: recall_at_5 value: 83.757 - task: type: Clustering dataset: name: MTEB RedditClustering type: mteb/reddit-clustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 31.453135224292588 - type: v_measures value: - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - 0.34024081488556046 - 0.31978719363198366 - 0.28326863670514296 - 0.2736227852661663 - 0.33176589594215805 - 0.281739297860462 - 0.3714152055541526 - 0.2784460528138246 - 0.28292867038320446 - 0.3011498262585792 - 0.2903236549747166 - 0.36937775233378656 - 0.30011371483471927 - 0.33579158840067747 - 0.3774325279364799 - 0.2798489399988548 - 0.30350039884840657 - 0.39379070544611877 - 0.29845537391174287 - 0.280224383799162 - 0.2683644031255058 - 0.28462417081553165 - 0.4207860651822375 - 0.30599639335371903 - 0.29028935381025356 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P type: mteb/reddit-clustering-p2p config: default split: test revision: 385e3cb46b4cfa89021f56c4380204149d0efe33 metrics: - type: v_measure value: 43.69122416835423 - type: v_measures value: - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - 0.4949442160711536 - 0.5089714608477952 - 0.533056646726052 - 0.28870974397114113 - 0.4845435888947718 - 0.4358272686082502 - 0.15963756448560423 - 0.4966594103138184 - 0.4483975331373559 - 0.5183749837794799 - task: type: Retrieval dataset: name: MTEB SCIDOCS type: mteb/scidocs config: default split: test revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88 metrics: - type: map_at_1 value: 2.558 - type: map_at_10 value: 5.4670000000000005 - type: map_at_100 value: 6.601999999999999 - type: map_at_1000 value: 6.816 - type: map_at_20 value: 6.013 - type: map_at_3 value: 4.132000000000001 - type: map_at_5 value: 4.672 - type: mrr_at_1 value: 12.5 - type: mrr_at_10 value: 18.454 - type: mrr_at_100 value: 19.585 - type: mrr_at_1000 value: 19.698999999999998 - type: mrr_at_20 value: 19.093 - type: mrr_at_3 value: 16.25 - type: mrr_at_5 value: 17.349999999999998 - type: ndcg_at_1 value: 12.5 - type: ndcg_at_10 value: 9.931 - type: ndcg_at_100 value: 15.332 - type: ndcg_at_1000 value: 20.285 - type: ndcg_at_20 value: 11.73 - type: ndcg_at_3 value: 9.425 - type: ndcg_at_5 value: 7.994 - type: precision_at_1 value: 12.5 - type: precision_at_10 value: 5.11 - type: precision_at_100 value: 1.299 - type: precision_at_1000 value: 0.251 - type: precision_at_20 value: 3.5999999999999996 - type: precision_at_3 value: 8.533 - type: precision_at_5 value: 6.7 - type: recall_at_1 value: 2.558 - type: recall_at_10 value: 10.4 - type: recall_at_100 value: 26.35 - type: recall_at_1000 value: 50.888 - type: recall_at_20 value: 14.610000000000001 - type: recall_at_3 value: 5.208 - type: recall_at_5 value: 6.808 - task: type: STS dataset: name: MTEB SICK-R type: mteb/sickr-sts config: default split: test revision: 20a6d6f312dd54037fe07a32d58e5e168867909d metrics: - type: cos_sim_pearson value: 80.46080544471825 - type: cos_sim_spearman value: 77.33681018334157 - type: euclidean_pearson value: 78.32030772877526 - type: euclidean_spearman value: 77.3367915580176 - type: manhattan_pearson value: 78.23694581981565 - type: manhattan_spearman value: 77.24572801084182 - task: type: STS dataset: name: MTEB STS12 type: mteb/sts12-sts config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 77.33143319366522 - type: cos_sim_spearman value: 70.15243619467687 - type: euclidean_pearson value: 74.35384725257417 - type: euclidean_spearman value: 70.15020588975051 - type: manhattan_pearson value: 74.49763893926959 - type: manhattan_spearman value: 70.35289409088577 - task: type: STS dataset: name: MTEB STS13 type: mteb/sts13-sts config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 75.43426290814391 - type: cos_sim_spearman value: 78.41580967540904 - type: euclidean_pearson value: 77.87697798842441 - type: euclidean_spearman value: 78.41580967540904 - type: manhattan_pearson value: 77.7742301162175 - type: manhattan_spearman value: 78.23561925777014 - task: type: STS dataset: name: MTEB STS14 type: mteb/sts14-sts config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 75.72059066580607 - type: cos_sim_spearman value: 74.76063270848232 - type: euclidean_pearson value: 75.96422568212527 - type: euclidean_spearman value: 74.76063912580608 - type: manhattan_pearson value: 75.93446446206052 - type: manhattan_spearman value: 74.80351881324513 - task: type: STS dataset: name: MTEB STS15 type: mteb/sts15-sts config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 79.50308070637769 - type: cos_sim_spearman value: 82.00177922226122 - type: euclidean_pearson value: 81.88334998600465 - type: euclidean_spearman value: 82.00175996908672 - type: manhattan_pearson value: 82.04162815561806 - type: manhattan_spearman value: 82.16179492395742 - task: type: STS dataset: name: MTEB STS16 type: mteb/sts16-sts config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 72.660749090443 - type: cos_sim_spearman value: 78.27062791462116 - type: euclidean_pearson value: 77.22132046879575 - type: euclidean_spearman value: 78.27062749235377 - type: manhattan_pearson value: 77.30349168561915 - type: manhattan_spearman value: 78.38610133247218 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 84.40073205259823 - type: cos_sim_spearman value: 85.85093351857286 - type: euclidean_pearson value: 86.39555107737667 - type: euclidean_spearman value: 85.85093351857286 - type: manhattan_pearson value: 86.15780582794078 - type: manhattan_spearman value: 85.67768599300385 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson value: 54.06121880120164 - type: cos_sim_spearman value: 61.20018366762684 - type: euclidean_pearson value: 59.08089664894604 - type: euclidean_spearman value: 61.20018366762684 - type: manhattan_pearson value: 58.88169190353213 - type: manhattan_spearman value: 60.82629422553597 - task: type: STS dataset: name: MTEB STSBenchmark type: mteb/stsbenchmark-sts config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 76.9607252955321 - type: cos_sim_spearman value: 79.20891358738938 - type: euclidean_pearson value: 79.53044888138301 - type: euclidean_spearman value: 79.20891358738938 - type: manhattan_pearson value: 79.37313113618887 - type: manhattan_spearman value: 79.0667751270519 - task: type: Reranking dataset: name: MTEB SciDocsRR type: mteb/scidocs-reranking config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 71.0421477784269 - type: mrr value: 89.94940426312975 - task: type: Retrieval dataset: name: MTEB SciFact type: mteb/scifact config: default split: test revision: 0228b52cf27578f30900b9e5271d331663a030d7 metrics: - type: map_at_1 value: 31.900000000000002 - type: map_at_10 value: 38.494 - type: map_at_100 value: 39.353 - type: map_at_1000 value: 39.427 - type: map_at_20 value: 38.952 - type: map_at_3 value: 36.238 - type: map_at_5 value: 37.36 - type: mrr_at_1 value: 34.0 - type: mrr_at_10 value: 40.327 - type: mrr_at_100 value: 41.052 - type: mrr_at_1000 value: 41.120000000000005 - type: mrr_at_20 value: 40.737 - type: mrr_at_3 value: 38.333 - type: mrr_at_5 value: 39.367000000000004 - type: ndcg_at_1 value: 34.0 - type: ndcg_at_10 value: 42.419000000000004 - type: ndcg_at_100 value: 46.589000000000006 - type: ndcg_at_1000 value: 48.966 - type: ndcg_at_20 value: 43.980000000000004 - type: ndcg_at_3 value: 38.124 - type: ndcg_at_5 value: 39.952 - type: precision_at_1 value: 34.0 - type: precision_at_10 value: 5.933 - type: precision_at_100 value: 0.8330000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_20 value: 3.3329999999999997 - type: precision_at_3 value: 15.0 - type: precision_at_5 value: 10.067 - type: recall_at_1 value: 31.900000000000002 - type: recall_at_10 value: 52.800000000000004 - type: recall_at_100 value: 72.10600000000001 - type: recall_at_1000 value: 91.60000000000001 - type: recall_at_20 value: 58.699999999999996 - type: recall_at_3 value: 41.317 - type: recall_at_5 value: 45.761 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.62871287128714 - type: cos_sim_ap value: 85.22434241429664 - type: cos_sim_f1 value: 79.31605074462217 - type: cos_sim_precision value: 88.43788437884379 - type: cos_sim_recall value: 71.89999999999999 - type: dot_accuracy value: 99.62871287128714 - type: dot_ap value: 85.22434241429666 - type: dot_f1 value: 79.31605074462217 - type: dot_precision value: 88.43788437884379 - type: dot_recall value: 71.89999999999999 - type: euclidean_accuracy value: 99.62871287128714 - type: euclidean_ap value: 85.22434237736961 - type: euclidean_f1 value: 79.31605074462217 - type: euclidean_precision value: 88.43788437884379 - type: euclidean_recall value: 71.89999999999999 - type: manhattan_accuracy value: 99.62475247524752 - type: manhattan_ap value: 85.53918872229502 - type: manhattan_f1 value: 79.38618925831203 - type: manhattan_precision value: 81.2565445026178 - type: manhattan_recall value: 77.60000000000001 - type: max_accuracy value: 99.62871287128714 - type: max_ap value: 85.53918872229502 - type: max_f1 value: 79.38618925831203 - task: type: Clustering dataset: name: MTEB StackExchangeClustering type: mteb/stackexchange-clustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 39.16142357597941 - type: v_measures value: - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - 0.3824405761636396 - 0.44216202123263126 - 0.3390286805950001 - 0.40370202650437953 - 0.3687764786128344 - 0.3002689364743748 - 0.3406756129607103 - 0.4239251906201308 - 0.41513537797197647 - 0.39562333880392536 - 0.44243846336620263 - 0.4564014124962121 - 0.46843968839295613 - 0.3486700249457605 - 0.3931094737880025 - 0.38614031871714743 - 0.39009948062151834 - 0.3952861715088528 - 0.3768164106667065 - 0.39372559829701875 - 0.41022022885425324 - 0.3442845107165114 - 0.36768421400456974 - 0.40522290066464794 - 0.40007875701488965 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P type: mteb/stackexchange-clustering-p2p config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 29.175984546605825 - type: v_measures value: - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - 0.28319515044921223 - 0.2715264094552343 - 0.27440620100214314 - 0.26830955555466396 - 0.27653185247970546 - 0.3178752664718975 - 0.3080336049306678 - 0.3068022206397505 - 0.3022010188359171 - 0.3087171748413907 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 40.56760857818254 - type: mrr value: 40.94357439945675 - task: type: Summarization dataset: name: MTEB SummEval type: mteb/summeval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 30.764610926778037 - type: cos_sim_spearman value: 30.298920879214158 - type: dot_pearson value: 30.764611831321552 - type: dot_spearman value: 30.298299440561465 - task: type: Retrieval dataset: name: MTEB TRECCOVID type: mteb/trec-covid config: default split: test revision: bb9466bac8153a0349341eb1b22e06409e78ef4e metrics: - type: map_at_1 value: 0.109 - type: map_at_10 value: 0.781 - type: map_at_100 value: 2.995 - type: map_at_1000 value: 6.854 - type: map_at_20 value: 1.2 - type: map_at_3 value: 0.28700000000000003 - type: map_at_5 value: 0.434 - type: mrr_at_1 value: 42.0 - type: mrr_at_10 value: 54.955 - type: mrr_at_100 value: 55.655 - type: mrr_at_1000 value: 55.689 - type: mrr_at_20 value: 55.42399999999999 - type: mrr_at_3 value: 51.0 - type: mrr_at_5 value: 53.800000000000004 - type: ndcg_at_1 value: 39.0 - type: ndcg_at_10 value: 39.479 - type: ndcg_at_100 value: 25.752000000000002 - type: ndcg_at_1000 value: 22.868 - type: ndcg_at_20 value: 35.707 - type: ndcg_at_3 value: 39.419 - type: ndcg_at_5 value: 39.64 - type: precision_at_1 value: 42.0 - type: precision_at_10 value: 43.6 - type: precision_at_100 value: 25.88 - type: precision_at_1000 value: 10.784 - type: precision_at_20 value: 37.8 - type: precision_at_3 value: 43.333 - type: precision_at_5 value: 43.6 - type: recall_at_1 value: 0.109 - type: recall_at_10 value: 1.038 - type: recall_at_100 value: 5.495 - type: recall_at_1000 value: 21.665 - type: recall_at_20 value: 1.722 - type: recall_at_3 value: 0.318 - type: recall_at_5 value: 0.522 - task: type: Retrieval dataset: name: MTEB Touche2020 type: mteb/touche2020 config: default split: test revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f metrics: - type: map_at_1 value: 1.302 - type: map_at_10 value: 2.514 - type: map_at_100 value: 3.341 - type: map_at_1000 value: 3.757 - type: map_at_20 value: 2.85 - type: map_at_3 value: 1.8450000000000002 - type: map_at_5 value: 1.873 - type: mrr_at_1 value: 18.367 - type: mrr_at_10 value: 24.789 - type: mrr_at_100 value: 26.517000000000003 - type: mrr_at_1000 value: 26.593 - type: mrr_at_20 value: 25.946 - type: mrr_at_3 value: 22.448999999999998 - type: mrr_at_5 value: 22.959 - type: ndcg_at_1 value: 16.326999999999998 - type: ndcg_at_10 value: 7.7509999999999994 - type: ndcg_at_100 value: 10.67 - type: ndcg_at_1000 value: 17.76 - type: ndcg_at_20 value: 7.674 - type: ndcg_at_3 value: 10.369 - type: ndcg_at_5 value: 7.840999999999999 - type: precision_at_1 value: 18.367 - type: precision_at_10 value: 7.142999999999999 - type: precision_at_100 value: 2.327 - type: precision_at_1000 value: 0.6779999999999999 - type: precision_at_20 value: 5.408 - type: precision_at_3 value: 11.565 - type: precision_at_5 value: 7.3469999999999995 - type: recall_at_1 value: 1.302 - type: recall_at_10 value: 4.919 - type: recall_at_100 value: 14.430000000000001 - type: recall_at_1000 value: 36.949 - type: recall_at_20 value: 7.0040000000000004 - type: recall_at_3 value: 2.2319999999999998 - type: recall_at_5 value: 2.3449999999999998 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification type: mteb/toxic_conversations_50k config: default split: test revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de metrics: - type: accuracy value: 64.47265625 - type: ap value: 11.979631561643862 - type: f1 value: 49.90647543589666 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification type: mteb/tweet_sentiment_extraction config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 61.79966044142614 - type: f1 value: 61.89030508018869 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering type: mteb/twentynewsgroups-clustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 28.234217666259703 - type: v_measures value: - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - 0.29450695840941515 - 0.30590470809304793 - 0.29205899710992034 - 0.27123807357354457 - 0.28092608890535714 - 0.2787486406145347 - 0.26689540227394454 - 0.26139744229328293 - 0.2785944239497992 - 0.2931510314031239 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 84.0317100792752 - type: cos_sim_ap value: 67.56361271781817 - type: cos_sim_f1 value: 63.082081211970696 - type: cos_sim_precision value: 59.58245367112362 - type: cos_sim_recall value: 67.01846965699208 - type: dot_accuracy value: 84.0317100792752 - type: dot_ap value: 67.56359342938897 - type: dot_f1 value: 63.082081211970696 - type: dot_precision value: 59.58245367112362 - type: dot_recall value: 67.01846965699208 - type: euclidean_accuracy value: 84.0317100792752 - type: euclidean_ap value: 67.5636169518733 - type: euclidean_f1 value: 63.082081211970696 - type: euclidean_precision value: 59.58245367112362 - type: euclidean_recall value: 67.01846965699208 - type: manhattan_accuracy value: 84.0734338677952 - type: manhattan_ap value: 67.44969672020721 - type: manhattan_f1 value: 63.09479205695017 - type: manhattan_precision value: 59.90040313018734 - type: manhattan_recall value: 66.64907651715039 - type: max_accuracy value: 84.0734338677952 - type: max_ap value: 67.5636169518733 - type: max_f1 value: 63.09479205695017 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 87.60624054022587 - type: cos_sim_ap value: 82.94451598409692 - type: cos_sim_f1 value: 74.76484194294527 - type: cos_sim_precision value: 74.86874613959235 - type: cos_sim_recall value: 74.66122574684324 - type: dot_accuracy value: 87.60624054022587 - type: dot_ap value: 82.94451133280317 - type: dot_f1 value: 74.76484194294527 - type: dot_precision value: 74.86874613959235 - type: dot_recall value: 74.66122574684324 - type: euclidean_accuracy value: 87.60624054022587 - type: euclidean_ap value: 82.94449586426977 - type: euclidean_f1 value: 74.76484194294527 - type: euclidean_precision value: 74.86874613959235 - type: euclidean_recall value: 74.66122574684324 - type: manhattan_accuracy value: 87.63922847052432 - type: manhattan_ap value: 82.9449637573502 - type: manhattan_f1 value: 74.9452996046217 - type: manhattan_precision value: 74.73015386970833 - type: manhattan_recall value: 75.1616877117339 - type: max_accuracy value: 87.63922847052432 - type: max_ap value: 82.9449637573502 - type: max_f1 value: 74.9452996046217 --- # Squirtle Squirtle is a distill of [bge-base-en-v1.5](BAAI/bge-base-en-v1.5). ## Intended purpose <span style="color:blue">This model is designed for use in semantic-autocomplete ([click here for demo](https://mihaiii.github.io/semantic-autocomplete/)).</span> Make sure you also pass `pipelineParams={{ pooling: "cls", normalize: true }}` since the default pooling in the component is mean. ## Usage Other than within [semantic-autocomplete](https://github.com/Mihaiii/semantic-autocomplete), you can use this model same as [bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5#usage).
[ "BIOSSES", "SCIFACT" ]
Salesforce/xgen-mm-phi3-mini-base-r-v1
Salesforce
image-text-to-text
[ "transformers", "safetensors", "xgenmm", "feature-extraction", "image-text-to-text", "conversational", "custom_code", "en", "arxiv:2408.08872", "license:apache-2.0", "region:us" ]
2024-05-07T17:28:38Z
2025-02-03T06:11:52+00:00
35
17
--- language: - en license: apache-2.0 pipeline_tag: image-text-to-text --- # 📣 News 📌 [08/19/2024] xGen-MM-v1.5 released: - [🤗 xgen-mm-phi3-mini-instruct-interleave-r-v1.5](https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5) - [🤗 xgen-mm-phi3-mini-base-r-v1.5](https://huggingface.co/Salesforce/xgen-mm-phi3-mini-base-r-v1.5) - [🤗 xgen-mm-phi3-mini-instruct-singleimg-r-v1.5](https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-singleimg-r-v1.5) - [🤗 xgen-mm-phi3-mini-instruct-dpo-r-v1.5](https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-dpo-r-v1.5) # Model description We are excited to announce the continuation and rebranding of our **BLIP series** into **XGen-MM**, to be better aligned with Salesforce's unified XGen initiative for large foundation models! This rebranding marks a significant step in our ongoing development of cutting-edge multimodal technologies. `XGen-MM` is a series of the latest foundational Large Multimodal Models (LMMs) developed by Salesforce AI Research. This series advances upon the successful designs of the `BLIP` series, incorporating fundamental enhancements that ensure a more robust and superior foundation. \ These models have been trained at scale on high-quality image caption datasets and interleaved image-text data. XGen-MM highlights a few features below, * The **pretrained** foundation model, `xgen-mm-phi3-mini-base-r-v1`, achieves state-of-the-art performance under 5b parameters and demonstrates strong in-context learning capabilities. * The **instruct** fine-tuned model, `xgen-mm-phi3-mini-instruct-r-v1`, achieves state-of-the-art performance among open-source and closed-source VLMs under 5b parameters. * `xgen-mm-phi3-mini-instruct-r-v1` supports flexible high-resolution image encoding with efficient visual token sampling. The model is for research purposes, more technical details will come with a technical report soon. # Results ### Pretrain (base model without instruction tuning) | Model | Shot | COCO (val) | NoCaps (val) | TextCaps (val) | OKVQA (val) | TextVQA (val) | VizWiz (testdev) | VQAv2 (testdev) | |-------------|------|------------|--------------|----------------|--------------|---------------|------------------|-----------------| | Flamingo-3B | 4 | 85.0 | - | - | 43.3 | 32.7 | 34 | 53.2 | | | 8 | 90.6 | - | - | 44.6 | 32.4 | 38.4 | 55.4 | | MM1-3B | 0 | 73.5 | 55.6 | 63.3 | 26.1 | 29.4 | 15.6 | 46.2 | | | 4 | 112.3 | 99.7 | 84.1 | 48.6 | 45.3 | 38.0 | 57.9 | | | 8 | 114.6 | 104.7 | 88.8 | 48.4 | 44.6 | 46.4 | 63.6 | | **xgen-mm-phi3-mini-base-r-v1 (Ours)**| 0 | **81.7** | **80.2** | 60.7 | **26.5** | **36.0** | **21.2** | **48.1** | | | 4 | 110.5 | **101.7** | **84.6** | **49.2** | **46.1** | **38.4** | **63.9** | | | 8 | 112.1 | 104.4 | 87.7 | **49.1** | **46.4** | 44.3 | **63.8** | ### Instruct (after instruction tuning) | Model | SEED-IMG | MMBench(dev) | MME-total | MME-P | MME-C | MMStar | MMMU (val) | MMVet | MathVista (mini) | ScienceQA (test) | POPE | AI2D | | |----------------------------|----------|--------------|-----------|----------|---------|----------|------------|----------|------------------|------------------|----------|----------|---| | MM1-3B-Chat | 68.8 | 67.8 | 1761 | **1482** | 279 | - | 33.9 | 43.7 | - | - | **87.4** | - | | | openbmb/MiniCPM-V-2 | 67.1 | 69.6 | 1808 | - | - | - | 38.2 | - | 38.7 | - | - | - | | | VILA1.5-3B | 67.9 | 63.4 | - | 1442 | - | - | 33.3 | 35.4 | - | 69.0 | 85.9 | - | | | xtuner/llava-phi-3-mini-hf | 70.0 | 69.2 | 1790 | 1477 | 313 | 43.7 | **41.4** | - | - | 73.7 | 87.3 | 69.3 | | | **xgen-mm-phi3-mini-instruct-r-v1 (Ours)** | **72.1** | **74.1** | **1827** | 1467 | **360** | **44.6** | 39.8 | **45.1** | **39.3** | **74.2** | 87.2 | **75.8** | | # How to use ~~> We require the use of the development version (`"4.41.0.dev0"`) of the `transformers` library. To get it, as of 05/07/2024, one can use `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers.`~~ ```python from transformers import AutoModelForVision2Seq, AutoTokenizer, AutoImageProcessor import requests from PIL import Image import IPython.display as display import torch model_name_or_path = "Salesforce/xgen-mm-phi3-mini-base-r-v1" model = AutoModelForVision2Seq.from_pretrained(model_name_or_path, trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True, use_fast=True, legacy=False) image_processor = AutoImageProcessor.from_pretrained(model_name_or_path, trust_remote_code=True) tokenizer = model.update_special_tokens(tokenizer) model = model.to('cuda') tokenizer.padding_side = "left" def apply_prompt_template(prompt, num_images=1, num_tokens_per_vis = 128, in_context=False, output=None): """ num_tokens_per_vis: model.vlm.num_tokens_per_vis """ placeholder_image_tokens = "<image placeholder>" * (num_tokens_per_vis - 1) if in_context: formatted_prompt = f"<image>{placeholder_image_tokens}" + f"{prompt}" + f"{output}" + "<|endofchunk|>" else: formatted_prompt = f"<image>{placeholder_image_tokens}"*num_images + f"{prompt}" return formatted_prompt ############ Zero shot inference ########## img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') instruction = "Describe what is the dog doing in this image in one sentence:" print("==> Instruction: ", instruction) print("==> Image: ") display.display(raw_image.resize((int(raw_image.width*0.3), int(raw_image.height*0.3)))) inputs = image_processor([raw_image], return_tensors="pt") prompt = apply_prompt_template(instruction) language_inputs = tokenizer([prompt], return_tensors="pt") inputs.update(language_inputs) inputs = {name: tensor.cuda() for name, tensor in inputs.items()} with torch.cuda.amp.autocast(dtype=torch.bfloat16): generated_text = model.generate(**inputs, pad_token_id=tokenizer.pad_token_id, do_sample=False, max_new_tokens=64, top_p=None, num_beams=1, length_penalty=1.0, repetition_penalty=3.0) prediction = tokenizer.decode(generated_text[0], skip_special_tokens=True) print("==> prediciton: ", prediction) print("-"*120) # ==> prediciton: The dog is sitting on the beach and waving at his owner. ``` More comprehensive examples can be found in the [notebook](demo.ipynb), where we provide a zero-shot and a few-shot example, respectively. # Reproducibility: Our SFT evaluation is based on the VLMEvalKit, in which we fixed some inconsistencies with the official benchmarks (e.g., LLM judge API). During our development, we noticed that the raw resolution of the input image would noticeably affect the model output in some cases. # Bias, Risks, Limitations, and Ethical Considerations The main data sources are from the internet, including webpages, image stock sites, and curated datasets released by the research community. We have excluded certain data, such as LAION, due to known CSAM concerns. The model may be subject to bias from the original data source, as well as bias from LLMs and commercial APIs. We strongly recommend users assess safety and fairness before applying to downstream applications. # Ethical Considerations This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP. # License Our code and weights are released under the Apache-2.0 license. The copyright of the training data remains with the original data owner. # Code acknowledgment [LAVIS](https://github.com/salesforce/LAVIS) \ [openflamingo](https://github.com/mlfoundations/open_flamingo) \ [VLMEvalKit](https://github.com/open-compass/VLMEvalKit/tree/main) # Citation ``` @misc{xue2024xgenmmblip3familyopen, title={xGen-MM (BLIP-3): A Family of Open Large Multimodal Models}, author={Le Xue and Manli Shu and Anas Awadalla and Jun Wang and An Yan and Senthil Purushwalkam and Honglu Zhou and Viraj Prabhu and Yutong Dai and Michael S Ryoo and Shrikant Kendre and Jieyu Zhang and Can Qin and Shu Zhang and Chia-Chih Chen and Ning Yu and Juntao Tan and Tulika Manoj Awalgaonkar and Shelby Heinecke and Huan Wang and Yejin Choi and Ludwig Schmidt and Zeyuan Chen and Silvio Savarese and Juan Carlos Niebles and Caiming Xiong and Ran Xu}, year={2024}, eprint={2408.08872}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2408.08872}, } ``` # Troubleshoot 1. If you missed any packages, please consider the following ``` pip install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu121 pip install open_clip_torch==2.24.0 pip install einops pip install einops-exts pip install transformers==4.41.1 ``` # Changelog * 05/24/2024 * update codebase to be compatible with `transformers==4.41.1`.
[ "CHIA" ]
nasa-impact/nasa-smd-ibm-distil-v0.1
nasa-impact
fill-mask
[ "transformers", "pytorch", "roberta", "fill-mask", "earth science", "climate", "biology", "en", "arxiv:2405.10725", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-05-21T18:41:13Z
2024-10-11T02:14:02+00:00
35
8
--- language: - en library_name: transformers license: apache-2.0 pipeline_tag: fill-mask tags: - earth science - climate - biology --- # Model Card for INDUS-Small (nasa-smd-ibm-distil-v0.1) INDUS-Small(nasa-smd-ibm-distil-v0.1) is a distilled version of the RoBERTa-based, Encoder-only transformer model INDUS (nasa-impact/nasa-smd-ibm-v0.1), domain-adapted for NASA Science Mission Directorate (SMD) applications. It's fine-tuned on scientific journals and articles relevant to NASA SMD, aiming to enhance natural language technologies like information retrieval and intelligent search. We trained the smaller model, INDUS_SMALL, with 38M parameters through knowledge distillation techniques by using INDUS as the teacher. INDUS_SMALL follows a 4-layer architecture recommended by the Neural Architecture Search engine (Trivedi et al., 2023) with an optimal trade-off between performance and latency. We adopted the distillation objective proposed in MiniLMv2 (Wang et al., 2021) to transfer fine-grained self-attention relations, which has been shown to be the current state-of-the-art (Udagawa et al., 2023). Using this objective, we trained the model for 500K steps with an effective batch size of 480 on 30 V100 GPUs. ## Model Details - **Base Model**: INDUS - **Tokenizer**: Custom - **Original version Parameters**: 125M - **Pretraining Strategy**: Masked Language Modeling (MLM) - **Distilled Version Parameters**: 38 Million Parameters ## Training Data - Wikipedia English (Feb 1, 2020) - AGU Publications - AMS Publications - Scientific papers from Astrophysics Data Systems (ADS) - PubMed abstracts - PubMedCentral (PMC) (commercial license subset) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/H0-q9N7IwXQqLdEaCCgm-.png) ## Training Procedure - **Framework**: fairseq 0.12.1 with PyTorch 1.9.1 - **transformers Version**: 4.2.0 - **Strategy**: Masked Language Modeling (MLM) ## Evaluation ### BLURB benchmark ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/Ipw5xR99qUORGkn5Z8JkA.png) (Standard deviation across 10 random seeds in parenthesis. Macro avg. reported across datasets and micro avg. computed by averaging scores on each task then averaging across task averages.) ### Climate Change NER, and NASA-QA benchmark ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/ncTupw9tNVf6pSBD5VnOh.png) (Climate Change NER and NASA-QA benchmark results. Standard Deviation over multiple runs given in parantheses) Please refer to the following dataset cards for further benchmarks and evaluation - NASA-IR Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-IR-benchmark - NASA-QA Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-qa-benchmark - Climate Change NER Benchmark - https://huggingface.co/datasets/ibm/Climate-Change-NER Please refer to the following dataset cards for benchmark evaluation - NASA IR Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-IR-benchmark - NASA SMD Expert QA Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-qa-benchmark - Climate CHange Benchmark - https://huggingface.co/datasets/ibm/Climate-Change-NER ## Uses - Named Entity Recognition (NER) - Information Retrieval - Sentence Transformers - Extractive QA For NASA SMD related, scientific usecases. ## Note This Model is released in support of the training and evaluation of the encoder language model ["Indus"](https://huggingface.co/nasa-impact/nasa-smd-ibm-v0.1). Accompanying paper can be found here: https://arxiv.org/abs/2405.10725 ## Citation If you find this work useful, please cite using the following bibtex citation: ```bibtex @misc {nasa-impact_2023, author = {Masayasu Maraoka and Bishwaranjan Bhattacharjee and Muthukumaran Ramasubramanian and Ikhsa Gurung and Rahul Ramachandran and Manil Maskey and Kaylin Bugbee and Rong Zhang and Yousef El Kurdi and Bharath Dandala and Mike Little and Elizabeth Fancher and Lauren Sanders and Sylvain Costes and Sergi Blanco-Cuaresma and Kelly Lockhart and Thomas Allen and Felix Grazes and Megan Ansdell and Alberto Accomazzi and Sanaz Vahidinia and Ryan McGranaghan and Armin Mehrabian and Tsendgar Lee}, title = { nasa-smd-ibm-v0.1 (Revision f01d42f) }, year = 2023, url = { https://huggingface.co/nasa-impact/nasa-smd-ibm-v0.1 }, doi = { 10.57967/hf/1429 }, publisher = { Hugging Face } } ``` ## Attribution IBM Research - Masayasu Muraoka - Bishwaranjan Bhattacharjee - Rong Zhang - Yousef El Kurdi - Bharath Dandala NASA SMD - Muthukumaran Ramasubramanian - Iksha Gurung - Rahul Ramachandran - Manil Maskey - Kaylin Bugbee - Mike Little - Elizabeth Fancher - Lauren Sanders - Sylvain Costes - Sergi Blanco-Cuaresma - Kelly Lockhart - Thomas Allen - Felix Grazes - Megan Ansdell - Alberto Accomazzi - Sanaz Vahidinia - Ryan McGranaghan - Armin Mehrabian - Tsendgar Lee ## Disclaimer This Encoder-only model is currently in an experimental phase. We are working to improve the model's capabilities and performance, and as we progress, we invite the community to engage with this model, provide feedback, and contribute to its evolution.
[ "BLURB" ]
RDson/Phi-3-medium-128k-instruct-GGUF
RDson
text-generation
[ "gguf", "nlp", "code", "text-generation", "multilingual", "license:mit", "endpoints_compatible", "region:us", "conversational" ]
2024-05-21T20:52:59Z
2024-05-21T22:58:07+00:00
35
2
--- language: - multilingual license: mit license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE pipeline_tag: text-generation tags: - nlp - code - gguf inference: parameters: temperature: 0.7 widget: - messages: - role: user content: Can you provide ways to eat combinations of bananas and dragonfruits? --- # GGUF of [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct). # Llama.cpp version b2956. ## Model Summary The Phi-3-Medium-128K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the Medium version in two variants [4k](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) and [128K](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) which is the context length (in tokens) that it can support. The model has underwent a post-training process that incorporates both supervised fine-tuning and direct preference optimization for the instruction following and safety measures. When assessed against benchmarks testing common sense, language understanding, math, code, long context and logical reasoning, Phi-3-Medium-128K-Instruct showcased a robust and state-of-the-art performance among models of the same-size and next-size-up. Resources and Technical Documentation: + [Phi-3 Microsoft Blog](https://aka.ms/Phi-3Build2024) + [Phi-3 Technical Report](https://aka.ms/phi3-tech-report) + [Phi-3 on Azure AI Studio](https://aka.ms/phi3-azure-ai) + [Phi-3 Cookbook](https://github.com/microsoft/Phi-3CookBook) | | Short Context | Long Context | | ------- | ------------- | ------------ | | Mini | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx) ; [[GGUF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct-onnx)| | Small | 8K [[HF]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct-onnx-cuda)| | Medium | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda)| | Vision | | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct)| ## Intended Uses **Primary use cases** The model is intended for broad commercial and research use in English. The model provides uses for general purpose AI systems and applications which require : 1) Memory/compute constrained environments 2) Latency bound scenarios 3) Strong reasoning (especially code, math and logic) Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features. **Use case considerations** Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case. Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under. ## How to Use Phi-3-Medium-128k-Instruct has been integrated in the development version (4.40.2) of `transformers`. Until the official version is released through `pip`, ensure that you are doing one of the following: * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function. * Update your local `transformers` to the development version: `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`. The previous command is an alternative to cloning and installing from the source. The current `transformers` version can be verified with: `pip list | grep transformers`. Phi-3-Medium-128k-Instruct is also available in [Azure AI Studio](https://aka.ms/phi3-azure-ai). ### Tokenizer Phi-3-Medium-128k-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size. ### Chat Format Given the nature of the training data, the Phi-3-Medium-128k-Instruct model is best suited for prompts using the chat format as follows. You can provide the prompt as a question with a generic template as follow: ```markdown <|user|>\nQuestion <|end|>\n<|assistant|> ``` For example: ```markdown <|user|> How to explain Internet for a medieval knight?<|end|> <|assistant|> ``` where the model generates the text after `<|assistant|>` . In case of few-shots prompt, the prompt can be formatted as the following: ```markdown <|user|> I am going to Paris, what should I see?<|end|> <|assistant|> Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:\n\n1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.\n2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.\n3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.\n\nThese are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|> <|user|> What is so great about #1?<|end|> <|assistant|> ``` ### Sample inference code This code snippets show how to get quickly started with running the model on a GPU: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline torch.random.manual_seed(0) model_id = "microsoft/Phi-3-medium-128k-instruct" model = AutoModelForCausalLM.from_pretrained( model_id, device_map="cuda", torch_dtype="auto", trust_remote_code=True, ) tokenizer = AutoTokenizer.from_pretrained(model_id) messages = [ {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}, {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"}, ] pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, ) generation_args = { "max_new_tokens": 500, "return_full_text": False, "temperature": 0.0, "do_sample": False, } output = pipe(messages, **generation_args) print(output[0]['generated_text']) ``` *Some applications/frameworks might not include a BOS token (`<s>`) at the start of the conversation. Please ensure that it is included since it provides more reliable results.* ## Responsible AI Considerations Like other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include: + Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English. + Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases. + Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case. + Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated. + Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses. Developers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include: + Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques. + High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context. + Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG). + Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case. + Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations. ## Training ### Model * Architecture: Phi-3-Medium-128k-Instruct has 14B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines. * Inputs: Text. It is best suited for prompts using chat format. * Context length: 128k tokens * GPUs: 512 H100-80G * Training time: 42 days * Training data: 4.8T tokens * Outputs: Generated text in response to the input * Dates: Our models were trained between February and April 2024 * Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models. * Release dates: The model weight is released on May 21, 2024. ### Datasets Our training data includes a wide variety of sources, totaling 4.8 trillion tokens (including 10% multilingual), and is a combination of 1) Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code; 2) Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.); 3) High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness. We are focusing on the quality of data that could potentially improve the reasoning ability for the model, and we filter the publicly available documents to contain the correct level of knowledge. As an example, the result of a game in premier league in a particular day might be good training data for frontier models, but we need to remove such information to leave more model capacity for reasoning for the small size models. More details about data can be found in the [Phi-3 Technical Report](https://aka.ms/phi3-tech-report). ## Benchmarks We report the results for Phi-3-Medium-128k-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Mixtral-8x22b, Gemini-Pro, Command R+ 104B, Llama-3-70B-Instruct, GPT-3.5-Turbo-1106, and GPT-4-Turbo-1106(Chat). All the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation. As is now standard, we use few-shot prompts to evaluate the models, at temperature 0. The prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3. More specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model. The number of k–shot examples is listed per-benchmark. |Benchmark|Phi-3-Medium-128k-Instruct<br>14b|Command R+<br>104B|Mixtral<br>8x22B|Llama-3-70B-Instruct|GPT3.5-Turbo<br>version 1106|Gemini<br>Pro|GPT-4-Turbo<br>version 1106 (Chat)| |---------|-----------------------|--------|-------------|-------------------|-------------------|----------|------------------------| |AGI Eval<br>5-shot|49.7|50.1|54.0|56.9|48.4|49.0|59.6| |MMLU<br>5-shot|76.6|73.8|76.2|80.2|71.4|66.7|84.0| |BigBench Hard<br>3-shot|77.9|74.1|81.8|80.4|68.3|75.6|87.7| |ANLI<br>7-shot|57.3|63.4|65.2|68.3|58.1|64.2|71.7| |HellaSwag<br>5-shot|81.6|78.0|79.0|82.6|78.8|76.2|88.3| |ARC Challenge<br>10-shot|91.0|86.9|91.3|93.0|87.4|88.3|95.6| |ARC Easy<br>10-shot|97.6|95.7|96.9|98.2|96.3|96.1|98.8| |BoolQ<br>2-shot|86.5|86.1|82.7|89.1|79.1|86.4|91.3| |CommonsenseQA<br>10-shot|82.2|82.0|82.0|84.4|79.6|81.8|86.7| |MedQA<br>2-shot|67.6|59.2|67.9|78.5|63.4|58.2|83.7| |OpenBookQA<br>10-shot|87.2|86.8|88.6|91.8|86.0|86.4|93.4| |PIQA<br>5-shot|87.8|86.4|85.0|85.3|86.6|86.2|90.1| |Social IQA<br>5-shot|79.0|75.3|78.2|81.1|68.3|75.4|81.7| |TruthfulQA (MC2)<br>10-shot|74.3|57.8|67.4|81.9|67.7|72.6|85.2| |WinoGrande<br>5-shot|78.9|77.0|75.3|83.3|68.8|72.2|86.7| |TriviaQA<br>5-shot|73.9|82.8|84.5|78.5|85.8|80.2|73.3| |GSM8K Chain of Thought<br>8-shot|87.5|78.3|83.8|93.5|78.1|80.4|94.2| |HumanEval<br>0-shot|58.5|61.6|39.6|78.7|62.2|64.4|79.9| |MBPP<br>3-shot|73.8|68.9|70.7|81.3|77.8|73.2|86.7| |Average|77.3|75.0|76.3|82.5|74.3|75.4|85.2| We take a closer look at different categories across 80 public benchmark datasets at the table below: |Benchmark|Phi-3-Medium-128k-Instruct<br>14b|Command R+<br>104B|Mixtral<br>8x22B|Llama-3-70B-Instruct|GPT3.5-Turbo<br>version 1106|Gemini<br>Pro|GPT-4-Turbo<br>version 1106 (Chat)| |--------|------------------------|--------|-------------|-------------------|-------------------|----------|------------------------| | Popular aggregated benchmark | 72.3 | 69.9 | 73.4 | 76.3 | 67.0 | 67.5 | 80.5 | | Reasoning | 83.2 | 79.3 | 81.5 | 86.7 | 78.3 | 80.4 | 89.3 | | Language understanding | 75.3 | 75.7 | 78.7 | 77.9 | 70.4 | 75.3 | 81.6 | | Code generation | 64.2 | 68.6 | 60.0 | 69.3 | 70.4 | 66.7 | 76.1 | | Math | 52.9 | 45.3 | 52.5 | 59.7 | 52.8 | 50.9 | 67.1 | | Factual knowledge | 47.5 | 60.3 | 60.6 | 52.4 | 63.4 | 54.6 | 45.9 | | Multilingual | 62.2 | 67.8 | 69.8 | 62.0 | 67.0 | 73.4 | 78.2 | | Robustness | 70.2 | 57.9 | 65.5 | 78.7 | 69.3 | 69.7 | 84.6 | ## Software * [PyTorch](https://github.com/pytorch/pytorch) * [DeepSpeed](https://github.com/microsoft/DeepSpeed) * [Transformers](https://github.com/huggingface/transformers) * [Flash-Attention](https://github.com/HazyResearch/flash-attention) ## Hardware Note that by default, the Phi-3-Medium model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types: * NVIDIA A100 * NVIDIA A6000 * NVIDIA H100 If you want to run the model on: + Optimized inference on GPU, CPU, and Mobile: use the **ONNX** models [128k](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda) ## Cross Platform Support ONNX runtime ecosystem now supports Phi3 Medium models across platforms and hardware. Optimized phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML GPU acceleration is supported for Windows desktops GPUs (AMD, Intel, and NVIDIA). Along with DML, ONNX Runtime provides cross platform support for Phi3 Medium across a range of devices CPU, GPU, and mobile. Here are some of the optimized configurations we have added: 1. ONNX models for int4 DML: Quantized to int4 via AWQ 2. ONNX model for fp16 CUDA 3. ONNX model for int4 CUDA: Quantized to int4 via RTN 4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN ## License The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-medium-128k/resolve/main/LICENSE). ## Trademarks This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
[ "MEDQA" ]
EIRTHAIMED/Llama-3.1-EIRAI-8B-Prob
EIRTHAIMED
text-generation
[ "transformers", "safetensors", "llama", "text-generation", "medical", "text-generation-inference", "llama-3.1", "finetuning", "conversational", "th", "en", "arxiv:2409.08523", "base_model:meta-llama/Llama-3.1-8B", "base_model:finetune:meta-llama/Llama-3.1-8B", "license:llama3.1", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-09-09T04:12:49Z
2024-09-16T06:58:52+00:00
35
1
--- base_model: meta-llama/Meta-Llama-3.1-8B language: - th - en library_name: transformers license: llama3.1 tags: - medical - text-generation-inference - llama-3.1 - finetuning --- <p align="center"> <img src="https://hf.fast360.xyz/production/uploads/66bf1cd096583c59b024a3c5/oG16EyLMfyiqvXrbNPGZd.png" alt="Logo_Website" width="400"/> </p> # **Thai Medical Large Language Model** **Github** : [Github Evaluate](https://github.com/EIRAI-Thaimedical/EIRAI)<br> **PaPer** : <br> ## **Llama-3.1-EIRAI-8B-instruct** **Llama-3.1-EIRAI-8B-instruct**: developed an **8-billion parameter model** specifically tailored for **Thai medical applications**, with expertise in both **Thai medical language** and **English medical terminology**. The model has demonstrated its capabilities through key benchmarks such as **MMLU**, **MedQA**, **PubMedQA**, and **MedMCQA**, as well as Thai language assessments like **ThaiExam**, **M3Exam**, **XNLI**, and **XCOPA**. Additionally, we have created a **Clinically Adapted Model Enhanced test** using the **Thai language** to support **clinical use in hospitals** and to further improve the performance of **Thai medical Retrieval-Augmented Generation (RAG)**. ## Notice While **Eir AI Thai Medical LLM** is designed to encode high-quality medical knowledge, it is **not yet optimized for safe, practical use** in real-world medical settings. The model is still in the research phase and should **not be used for clinical decision-making** without further validation, including randomized controlled trials. It is available for researchers to explore the potential of LLMs in medical contexts, but **real-world deployment is not recommended** in its current version. ## Safety and Future Work The current version of **Eir AI Thai Medical LLM** is under active development. We advise against using it for medical applications until further testing is completed. Our goal is to continue enhancing the model through **rigorous testing** and **real-world evaluation**, ensuring that it can be safely integrated into healthcare systems in the future. ## Model Overview - **Model Architecture:** Meta-Llama-3.1-8B-Instruct - **Version:** 1.0 - **License(s):** [llama3.1](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE) ### Evaluations | Medical Model | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA | PubMedQA | MedMCQA | Avg. | |--------------------------|---------------------|---------------------|--------------------|--------------------|--------------------|--------------------|-------------------|-------------------|-------------------|-------------------| | **GPT-3.5 Turbo 1106** | 74.7 | 60.2 | 65.9 | 72.0 | 64.73 | 64.73 | 57.71 | 72.66 | 66.0 | 66.6 | |Thai LLMs | | | | | | | | | | | | **Eir AI-8B** | 75.1 | 80.0 | 69.6 | 76.8 | 77.1 | 66.5 | 64.5 | **79.0** | 58.6 | 71.9 | | **Eir AI-8B + Prob** | **83.8** | **89.0** | **83.0** | **84.9** | **89.6** | **75.7** | **69.6** | 78.8 | **67.1** | **80.2** | | **Typhoon-v1.5x-8B** | 75.9 | 79.0 | 63.7 | 70.6 | 77.1 | 63.6 | 59.7 | 74.4 | 58.0 | 69.1 | | **OpenThaiGPT-beta-7B** | 37.4 | 38.0 | 4.5 | 32.7 | 36.1 | 32.4 | 32.4 | 62.0 | 31.8 | 34.1 | ## Translation Performance Metrics | **Model** | **BLEU Score** | **N-gram Precisions (%)** | **BP** | **Ratio** | |-------------------------------|----------------|---------------------------------|---------|-----------| | Typhoon-v1.5x-8B-Instruct | 34.42 | 71.3/50.6/38.6/29.6 | 0.764 | 0.788 | | Meta Llama 3.1-8B Instruct | 35.74 | 62.8/42.3/31.7/24.1 | 0.946 | 0.948 | | **Eir AI-8B** | **61.10** | **76.1/64.6/56.6/50.1** | **1.000**| **1.006** | | Eir AI-8B-prob | 47.91 | 74.0/58.0/48.2/40.6 | 0.890 | 0.896 | ## Clinically Adapted Thai Medical Task Performance | Task | GPT-3.5 | Typhoon-v1.5x-8B-instruct | GPT-4o | Eir AI-8B | |----------------------------------------|---------|----------------------------|--------|-----------| | Named Entity Recognition | 3.26 | 5.55 | 6.34 | **7.08** | | Temporal Information Extraction | 3.83 | 5.46 | 6.15 | **7.05** | | Paraphrasing | 2.36 | 4.68 | 6.35 | **7.06** | | Natural Language Generation | 2.63 | 4.87 | 6.91 | **7.66** | | Keyword Extraction | 2.60 | 5.15 | 7.01 | **7.35** | | Text Classification | 2.92 | 6.21 | 5.36 | **6.75** | | Relation Extraction | 3.29 | 5.94 | 4.37 | **6.92** | | Question Answering | 3.70 | 4.92 | 6.11 | **6.82** | | Text Summarization | 2.98 | 5.44 | **7.51**| **7.51** | | Abbreviation Expansion | 3.99 | 5.96 | 6.24 | **7.82** | | Clinical Concept Normalization | 2.67 | 5.63 | 5.82 | **6.55** | | Open-ended Question | 3.32 | 5.55 | 6.77 | **7.27** | | Multiple-Choice Question | 3.90 | 5.00 | 5.40 | **6.40** | | Coreference Resolution | 3.48 | 4.55 | 4.88 | **6.43** | | Yes/No Question | 2.71 | 5.86 | 4.86 | **7.38** | | Medical Translation | 3.00 | 4.00 | **7.79**| 7.65 | | Medical Thai Extraction | 2.81 | 7.16 | **8.62**| 8.16 | | Medical ICD Prediction | 2.08 | 3.16 | **8.12**| 6.41 | | **Average Score** | 3.05 | 5.33 | 6.38 | **7.11** | # Prompt Template This model uses `ChatML` prompt template: ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> ```` # Example Clinical Adapted ICD 10 Prediction ```` <|begin_of_text|><|start_header_id|>system<|end_header_id|> You are responsible for accurately assigning ICD-10 codes and to diagnose and document medical records. Your expertise ensures that healthcare providers are properly reimbursed and that patient care is well-documented. In this scenario, you will be presented with a series of medical records and your task is to provide the correct ICD-10 code(s) and ICD-9 CM in procedures based on the information provided. <|eot_id|> <|start_header_id|>user<|end_header_id|> "Chief Complaint :5วันก่อนมารพ.มีไข้ ไอ มีเสมหะ มีน้ำมูก เหนื่อย ปวดเมื่อยตามตัว \r\n Present illness : 5วันก่อนมารพ.มีไข้ ไอ มีเสมหะ มีน้ำมูก เหนื่อย ปวดเมื่อยตามตัว มีน้ำมูก เลือดกำเดาจาากข้างขวา ปฏิการกระทบกระแทก ไม่มีเจ็บคอ ไม่มีอาการอ่อนเพลีย มีอาการอ่อนเพลีย ไอมาก ไอตลอด มีอาการระคายคอ ปัสสาวะปกติ ไม่มีถ่ายเหลว \r\n\r\nAllergy : |\r\n\r\nOther : no underlying disease\r\n\r\nPlan Treatment Day 1 of hospitalization : admit ward \r\n\r\nReview of System { \r\n\r\n General :a thai adult female ,look sickness fatigue dry lip moderate dehydration \r\n Skin :no MP rash \r\n Eyes :not pale ,no icteric sclera \r\n Chest :secretion sound in both lung ,no crepitation , no wheezing \r \n } VitalSign First : {\n BP : 117.0/63.0 mmHg\n Pulse : 62.0 BPm\n Temperature : 37.0 Celsius\n Respiratory rate : 20.0\n Weight : 50.000 kgs.\n Height : 165.0 cm.\n Painscore: N/A\n O2SAT : 100\n}\n Lab Results: \n Electrolyte:Sodium (Na), Result : 143 mmol/L\r\n Electrolyte:Potassium (K),Result : 3.8 mmol/L\r\n Electrolyte:Chloride (Cl), Result : 108 mmol/L\r\n Electrolyte:Bicarbonate (CO2),Result : 27.0 mmol/L\r\n Creatinine (Serum):Creatinine, Result : 0.69 mg/dL\r\n Creatinine (Serum):eGFR,Result : 100.41 ml/min/1.73 m^2\r\n AST/SGOT:AST/SGOT, Result : 48 U/L\r\n ALT/SGPT:ALT/SGPT, Result : 42 U/L\r\n CBC:WBC Count,Result : 3.2 10^3/uL\r\n CBC:RBC Count, Result : 3.57 10^6/uL\r\n CBC:Hemoglobin (Hb), Result : 10.7 g/dL\r\n CBC:Hematocrit (HCT),Result : 32.4 %\r\n CBC:MCV, Result : 91 fL\r\n CBC:MCH, Result : 30.0 pg\r\n CBC:MCHC, Result : 33.0 g/dL\r\n CBC:RDW-CV,Result : 12.9 %\r\n CBC:Platelet Count, Result : 226 10^3/uL\r\n CBC:Platelet Estimates, Result : Adequate \r\n CBC:Neutrophils,Result : 41 %\r\n CBC:Lymphocytes, Result : 46 %\r\n CBC:Monocytes, Result : 9 %\r\n CBC:Eosinophils, Result : 4 %\r\n CBC:Basophils,Result : 0 %\r\n COVID-19 Antigen (Rapid Test) For Admit:COVID-19 Antigen (Rapid Test), Result : Positive \r\n Influenza A/B screening:Flu A,Result : Negative \r\n Influenza A/B screening:Flu B, Result : Negative \n X-ray Results: 15-05-2567 12:56 CHEST (PA, UPRIGHT)\r\n \r\nHISTORY: Fever with productive cough and dyspnea for 5 days. \r\nCOMPARISON: None.\r\n \r\n FINDINGS:\r\n TUBES/LINES: None.\r\nLUNGS: Normal lung volumes. Band-like opacity at right apical lung. Clear left lung.\r\n PLEURA: No pneumothorax or effusion. Mild bilateral apical pleural thickening. \r\n HEART AND MEDIASTINUM: Normal cardiac silhouette. Normal mediastinal contour.\r\n BONY STRUCTURES: Mild scoliosis of the thoracic spine. \r\n\r\n IMPRESSION:\r\n - Band-like opacity at right apical lung, probably plate atelectasis or fibrosis\r\n- Mild bilateral apical pleural thickening" <|eot_id|> <|start_header_id|>assistant<|end_header_id|> Let's analyze the provided information and document the appropriate ICD-10 codes based on the patient's symptoms and diagnosis. ### Step-by-Step Analysis: 1. **Understand the Symptoms and Diagnosis**: - The patient presents with a range of symptoms including fever, cough with sputum, fatigue, nasal discharge (including blood), and dyspnea. The lab tests returned a positive COVID-19 antigen test, while the influenza test was negative. 2. **Identify Key Terms**: - Primary key terms include 'COVID-19 positive', 'fever', 'productive cough', 'dyspnea', and pulmonary findings from the X-ray. 3. **Locate the Main Category**: - The main categories for the conditions noted are: - COVID-19: U07.1 - Possible acute bronchitis: J20 (based on the productive cough) - Other symptoms such as dizziness: R42 - Evidence of acute respiratory infection: J06.9 4. **Identify Specific Codes**: - Based on the diagnosis: - COVID-19 confirmed case: U07.1 - Acute bronchitis: J20.9 (considering unspecified acute bronchitis) - Dizziness (if noted as significant and problematic): R42 - Unspecified acute upper respiratory infection: J06.9 5. **Check for Additional Codes or Modifiers**: - Considering the details provided, the primary diagnosis is the confirmed COVID-19 infection, while bronchiolitis and dizziness might be secondary diagnoses. 6. **Validate the Code Selection**: - Confirm that the selected codes reflect the patient's symptoms accurately, including acute bronchitis and any other significant symptoms presented. 7. **Document the ICD-10 Code**: - The ICD-10 codes are documented for all noted conditions accordingly." ```json Answer: { "Primary_Diagnosis": { "Code": "U071", "Description": "COVID-19, virus identified" }, "Secondary_Diagnosis": [ { "Code": "J20", "Description": "Acute bronchitis due to unspecified organism" }, { "Code": "R42", "Description": "Dizziness and giddiness" }, { "Code": "J069", "Description": "Acute upper respiratory infection, unspecified" } ], "ICD9_Procedure": [] } ```` # Example Clinical Adapted Thai Medical Extraction ```` <|begin_of_text|><|start_header_id|>system<|end_header_id|> Task : Extract input the following patient information into output format Tone: the following medical text into Thai in a fluent and elegant style. Output Format.1.Age: \n2.Gender: \n3.Weight :\n4.Height : \n5.Chief Complaint: \n6.Symptoms and Signs: \n7.Medical History: \n 8.Current Medications: \n9.Laboratory Results: \n10.Imaging Findings: \n11.Allergy: \n12.Drug Allergy: <|eot_id|> <|start_header_id|>user<|end_header_id|> ผู้ป่วยของเราเป็นชายถนัดทั้งสองมือ อายุ 43 ปี มีประวัติการชักที่ไม่สามารถควบคุมได้มาเป็นเวลา 20 ปี ลักษณะการชักของเขามักจะรวมถึงการรู้สึกร้อนวูบวาบและอาการทางประสาทสัมผัสอื่น ๆ ที่พัฒนาไปสู่การเคลื่อนไหวของกล้ามเนื้อที่มีจุดศูนย์กลางส่วนใหญ่ทางด้านขวา การตรวจหาสาเหตุของการชักรวมถึงการถ่ายภาพด้วยคลื่นแม่เหล็กไฟฟ้า (MRI) ซึ่งเผยให้เห็นเนื้องอกไขมันขนาดใหญ่ที่เส้นกลางสมอง การพัฒนาไม่สมบูรณ์ของคอร์ปัสคาโลซัมบางส่วน และรอยโรคที่อยู่ใกล้เคียงในสมองส่วนหน้าซ้ายที่คาดว่าจะเป็นเนื้องอกกลีอาล (glial neoplasm) ตามลักษณะภาพถ่ายทางรังสี รอยโรคในสมองส่วนหน้าซ้ายด้านหน้าและตรงกลางประกอบด้วยการกลายเป็นหินปูนแบบเป็นก้อนพร้อมการเพิ่มขึ้นของสัญญาณ FLAIR ที่กว้างขวางซึ่งเกี่ยวข้องกับไจรัสซิงกูเลตทั้งสองข้างและสมองส่วนหน้าซ้าย (รูปที่ ).\n\nการจัดการทางการแพทย์ล้มเหลวในการควบคุมการชักของเขาและเขาถูกส่งต่อเพื่อหาทางเลือกในการรักษาด้วยการผ่าตัด รอยโรคที่เพิ่มขึ้นถูกสังเกตด้วยการถ่ายภาพเพิ่มเติมและขอบเขตของอาการบวมน้ำก็เพิ่มขึ้นด้วย ความกังวลเกี่ยวกับการพัฒนาเนื้องอกกลีอาลที่เพิ่มขึ้นและการควบคุมการชักที่ไม่ดีทำให้มีการแนะนำให้ทำการผ่าตัด การตัดสินใจถูกทำขึ้นเพื่อดำเนินการผ่าตัดนำทางด้วยระบบประสาทเพื่อตัดมวลที่เพิ่มขึ้นในสมองส่วนหน้าซ้ายและการตัดสมองส่วนหน้าบางส่วนโดยใช้การตรวจคลื่นไฟฟ้าสมองระหว่างการผ่าตัด (intraoperative electroencephalogram - EEG), การทำแผนที่คอร์ติคอล (cortical mapping) และการตรวจวัดศักย์ไฟฟ้าที่เกิดจากการกระตุ้นประสาทรับความรู้สึก (somatosensory evoked potentials - SSEP)\n\nตัวอย่างที่ส่งไปตรวจทางพยาธิวิทยาแบบแช่แข็งในระหว่างการผ่าตัดพบว่ามีเส้นใยโรเซนธาล (Rosenthal fibers) และการกลายเป็นหินปูนแบบเป็นจุดซึ่งคาดว่าจะเป็นเนื้องอกกลีอาล การประเมินทางพยาธิวิทยาแบบถาวรเผยให้เห็นเนื้องอกไขมัน (lipoma) และความผิดปกติของคอร์ติคอลแบบเฉพาะจุด (focal cortical dysplasia) แบบ Palmini Type IA ในสมองที่อยู่ใกล้เคียง ความผิดปกติเล็กน้อยของโครงสร้างคอร์ติคอลและการเกิดกลีโอซิส (gliosis) ในเนื้อสมองขาวที่เกี่ยวข้องสามารถเห็นได้ในคราบสีฮีมาโทซิลินและอีโอซิน (hematoxylin and eosin - H&E) และคราบสีโปรตีนกรดกลีอาลไฟบริลลารี (glial fibrillary acidic protein - GFAP) และการย้อมสีโปรตีนเส้นประสาท (neurofilament protein - NFP) ในบริเวณที่เกิดกลีโอซิสไม่แสดงหลักฐานของเซลล์ประสาทที่ผิดรูป เซลล์ประสาทขนาดใหญ่ หรือเซลล์ลูกโป่ง (รูปที่ ).\n\n การถ่ายภาพหลังการผ่าตัด (รูปที่ ) แสดงให้เห็นการตัดรอยโรคที่เพิ่มขึ้นใกล้เคียงทั้งหมดในสมองส่วนหน้าซ้ายและไจรัสซิงกูเลต การลดลงอย่างมากของอาการบวมน้ำที่เกิดจากหลอดเลือดถูกสังเกตในภาพ FLAIR เนื้องอกไขมันที่เส้นกลางสมองไม่เปลี่ยนแปลง\n\nการฟื้นตัวหลังการตัดรวมถึงอาการเสริมในบริเวณมอเตอร์ซินโดรมระดับปานกลางรวมถึงอาการอ่อนแรงครึ่งซีก การพูดล่าช้า และการเปลี่ยนแปลงทางอารมณ์ การเปลี่ยนแปลงเหล่านี้ค่อยๆ หายไปและพบว่าผู้ป่วยมีความสมบูรณ์ทางระบบประสาทในการติดตามผลที่คลินิก การควบคุมการชักเกิดขึ้นทันทีหลังการตัด ยาต้านการชักถูกใช้อย่างต่อเนื่องและค่อยๆ ถูกถอดออกในเดือนต่อมาโดยไม่มีการกลับมาเป็นซ้ำ ผู้ป่วยไม่มีการชักเป็นเวลา 3 ปีหลังการตัด การถ่ายภาพติดตามผล 18 เดือนพบการเปลี่ยนแปลง T2/FLAIR ที่คงที่พร้อมกับบริเวณเล็ก ๆ <|eot_id|> <|start_header_id|>assistant<|end_header_id|> 1. อายุ: 43 ปี\n 2. เพศ: ชาย\n 3. น้ำหนัก: ไม่ระบุ\n 4. ส่วนสูง: ไม่ระบุ\n 5. อาการหลัก: การชักที่ไม่สามารถควบคุมได้\n 6. อาการและสัญญาณ: รู้สึกร้อนวูบวาบ, อาการทางประสาทสัมผัส, การเคลื่อนไหวของกล้ามเนื้อที่มีจุดศูนย์กลางส่วนใหญ่ทางด้านขวา\n 7. ประวัติการรักษา: การจัดการทางการแพทย์ล้มเหลวในการควบคุมการชัก\n 8. ยาที่ใช้ในปัจจุบัน: ยาต้านการชัก\n9. ผลการตรวจทางห้องปฏิบัติการ: ไม่ระบุ\n 10. ผลการตรวจภาพ: MRI แสดงเนื้องอกไขมันขนาดใหญ่ที่เส้นกลางสมอง, การพัฒนาไม่สมบูรณ์ของคอร์ปัสคาโลซัมบางส่วน, รอยโรคที่อยู่ใกล้เคียงในสมองส่วนหน้าซ้ายที่คาดว่าจะเป็นเนื้องอกกลีอาล\n 11. อาการแพ้: ไม่ระบุ\n 12. อาการแพ้ยา: ไม่ระบุ\n การผ่าตัดนำทางด้วยระบบประสาทเพื่อตัดมวลที่เพิ่มขึ้นในสมองส่วนหน้าซ้ายและการตัดสมองส่วนหน้าบางส่วนได้ถูกดำเนินการ และผลการตรวจทางพยาธิวิทยาเผยให้เห็นว่าเป็นเนื้องอกไขมันและความผิดปกติของคอร์ติคอลแบบเฉพาะจุด (focal cortical dysplasia) แบบ Palmini Type IA ในสมองที่อยู่ใกล้เคียง การฟื้นตัวหลังการผ่าตัดรวมถึงอาการเสริมในบริเวณมอเตอร์ซินโดรมระดับปานกลาง แต่การควบคุมการชักเกิดขึ้นทันทีหลังการผ่าตัดและผู้ป่วยไม่มีการชักเป็นเวลา 3 ปีหลังการผ่าตัด การถ่ายภาพติดตามผล 18 เดือนพบการเปลี่ยนแปลง T2/FLAIR ที่คงที่พร้อมกับบริเวณเล็ก ๆ ที่เพิ่มขึ้นของการเพิ่มขึ้นใกล้เคียงที่ไม่เปลี่ยนแปลง. ```` # How to use ```python Using transformers.pipeline() API import transformers import torch model_id = "EIRTHAIMED/Llama-3.1-EIRAI-8B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto", ) messages = [ {"role": "system", "content": "You are an expert medical assistant named EIR , developed by EIR Thai Medical LLM. You are to be a helpful, respectful, and honest assistant."}, {"role": "user", "content": "การใช้ clinical tracer มีบทบาทอย่างไรในการพัฒนาคุณภาพการดูแลผู้ป่วย?"} ] outputs = pipeline(messages, max_new_tokens=128, do_sample=True, temperature=0.01, top_k=100, top_p=0.95) print(outputs[0]["generated_text"][-1]) ``` ``` @article{EirAI, title={Eir: Thai Medical Large Language Models}, author={Yutthakorn Thiprak and Rungtam Ngodngamthaweesuk and Songtam Ngodngamtaweesuk, MD}, year={2024}, journal={arXiv preprint arXiv:2409.08523}, url={https://arxiv.org/abs/2409.08523} } ``` --- **Thank you very much** Asst.Prof.Dr. Ekapol Chuangsuwanich and Praj Bhargava @Meta Research Engineer, for your valuable endorsement of our preprint paper on arXiv. **Thank you** Draft Reviewer Report [Kullawat Chaowanawatee](https://www.computing.psu.ac.th/profile/index.php?staffid=coc0051) and [Dr. Jakapan Suaboot](https://www.computing.psu.ac.th/profile/index.php?staffid=coc0056) from Prince of Songkla University, Phuket Campus <br> Draft Industry Reviewer Report [Mr. Piyawat Maneenual](https://ieeexplore.ieee.org/author/37086452350) ,Assistant IT Manager ,Thonburi Rajyindee Hospital<br>
[ "MEDQA", "PUBMEDQA" ]
FreedomIntelligence/Apollo2-9B
FreedomIntelligence
question-answering
[ "safetensors", "gemma2", "biology", "medical", "question-answering", "ar", "en", "zh", "ko", "ja", "mn", "th", "vi", "lo", "mg", "de", "pt", "es", "fr", "ru", "it", "hr", "gl", "cs", "co", "la", "uk", "bs", "bg", "eo", "sq", "da", "sa", "no", "gn", "sr", "sk", "gd", "lb", "hi", "ku", "mt", "he", "ln", "bm", "sw", "ig", "rw", "ha", "dataset:FreedomIntelligence/ApolloMoEDataset", "arxiv:2410.10626", "base_model:google/gemma-2-9b", "base_model:finetune:google/gemma-2-9b", "license:apache-2.0", "region:us" ]
2024-10-14T09:35:09Z
2024-11-20T03:43:45+00:00
35
8
--- base_model: - google/gemma-2-9b datasets: - FreedomIntelligence/ApolloMoEDataset language: - ar - en - zh - ko - ja - mn - th - vi - lo - mg - de - pt - es - fr - ru - it - hr - gl - cs - co - la - uk - bs - bg - eo - sq - da - sa - 'no' - gn - sr - sk - gd - lb - hi - ku - mt - he - ln - bm - sw - ig - rw - ha license: apache-2.0 metrics: - accuracy pipeline_tag: question-answering tags: - biology - medical --- # Democratizing Medical LLMs For Much More Languages Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish, Arabic, Russian, Japanese, Korean, German, Italian, Portuguese and 38 Minor Languages So far. <p align="center"> 📃 <a href="https://arxiv.org/abs/2410.10626" target="_blank">Paper</a> • 🌐 <a href="" target="_blank">Demo</a> • 🤗 <a href="https://huggingface.co/datasets/FreedomIntelligence/ApolloMoEDataset" target="_blank">ApolloMoEDataset</a> • 🤗 <a href="https://huggingface.co/datasets/FreedomIntelligence/ApolloMoEBench" target="_blank">ApolloMoEBench</a> • 🤗 <a href="https://huggingface.co/collections/FreedomIntelligence/apollomoe-and-apollo2-670ddebe3bb1ba1aebabbf2c" target="_blank">Models</a> •🌐 <a href="https://github.com/FreedomIntelligence/Apollo" target="_blank">Apollo</a> • 🌐 <a href="https://github.com/FreedomIntelligence/ApolloMoE" target="_blank">ApolloMoE</a> </p> ![Apollo](assets/apollo_medium_final.png) ## 🌈 Update * **[2024.10.15]** ApolloMoE repo is published！🎉 ## Languages Coverage 12 Major Languages and 38 Minor Languages <details> <summary>Click to view the Languages Coverage</summary> ![ApolloMoE](assets/languages.png) </details> ## Architecture <details> <summary>Click to view the MoE routing image</summary> ![ApolloMoE](assets/hybrid_routing.png) </details> ## Results #### Dense 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-0.5B" target="_blank">Apollo2-0.5B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-1.5B" target="_blank">Apollo2-1.5B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-2B" target="_blank">Apollo2-2B</a> 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-3.8B" target="_blank">Apollo2-3.8B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-7B" target="_blank">Apollo2-7B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-9B" target="_blank">Apollo2-9B</a> <details> <summary>Click to view the Dense Models Results</summary> ![ApolloMoE](assets/dense_results.png) </details> #### Post-MoE 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo-MoE-0.5B" target="_blank">Apollo-MoE-0.5B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo-MoE-1.5B" target="_blank">Apollo-MoE-1.5B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo-MoE-7B" target="_blank">Apollo-MoE-7B</a> <details> <summary>Click to view the Post-MoE Models Results</summary> ![ApolloMoE](assets/post_moe_results.png) </details> ## Usage Format ##### Apollo2 - 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|> - 2B, 9B: User:{query}\nAssistant:{response}\<eos\> - 3.8B: <|user|>\n{query}<|end|><|assisitant|>\n{response}<|end|> ##### Apollo-MoE - 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|> ## Dataset & Evaluation - Dataset 🤗 <a href="https://huggingface.co/datasets/FreedomIntelligence/ApolloMoEDataset" target="_blank">ApolloMoEDataset</a> <details><summary>Click to expand</summary> ![ApolloMoE](assets/Dataset.png) - [Data category](https://huggingface.co/datasets/FreedomIntelligence/ApolloCorpus/tree/main/train) </details> - Evaluation 🤗 <a href="https://huggingface.co/datasets/FreedomIntelligence/ApolloMoEBench" target="_blank">ApolloMoEBench</a> <details><summary>Click to expand</summary> - EN: - [MedQA-USMLE](https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options) - [MedMCQA](https://huggingface.co/datasets/medmcqa/viewer/default/test) - [PubMedQA](https://huggingface.co/datasets/pubmed_qa): Because the results fluctuated too much, they were not used in the paper. - [MMLU-Medical](https://huggingface.co/datasets/cais/mmlu) - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - ZH: - [MedQA-MCMLE](https://huggingface.co/datasets/bigbio/med_qa/viewer/med_qa_zh_4options_bigbio_qa/test) - [CMB-single](https://huggingface.co/datasets/FreedomIntelligence/CMB): Not used in the paper - Randomly sample 2,000 multiple-choice questions with single answer. - [CMMLU-Medical](https://huggingface.co/datasets/haonan-li/cmmlu) - Anatomy, Clinical_knowledge, College_medicine, Genetics, Nutrition, Traditional_chinese_medicine, Virology - [CExam](https://github.com/williamliujl/CMExam): Not used in the paper - Randomly sample 2,000 multiple-choice questions - ES: [Head_qa](https://huggingface.co/datasets/head_qa) - FR: - [Frenchmedmcqa](https://github.com/qanastek/FrenchMedMCQA) - [MMLU_FR] - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - HI: [MMLU_HI](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Hindi) - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - AR: [MMLU_AR](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Arabic) - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - JA: [IgakuQA](https://github.com/jungokasai/IgakuQA) - KO: [KorMedMCQA](https://huggingface.co/datasets/sean0042/KorMedMCQA) - IT: - [MedExpQA](https://huggingface.co/datasets/HiTZ/MedExpQA) - [MMLU_IT] - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - DE: [BioInstructQA](https://huggingface.co/datasets/BioMistral/BioInstructQA): German part - PT: [BioInstructQA](https://huggingface.co/datasets/BioMistral/BioInstructQA): Portuguese part - RU: [RuMedBench](https://github.com/sb-ai-lab/MedBench) </details> ## Model Download and Inference We take Apollo-MoE-0.5B as an example 1. Login Huggingface ``` huggingface-cli login --token $HUGGINGFACE_TOKEN ``` 2. Download model to local dir ```python from huggingface_hub import snapshot_download import os local_model_dir=os.path.join('/path/to/models/dir','Apollo-MoE-0.5B') snapshot_download(repo_id="FreedomIntelligence/Apollo-MoE-0.5B", local_dir=local_model_dir) ``` 3. Inference Example ```python from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig import os local_model_dir=os.path.join('/path/to/models/dir','Apollo-MoE-0.5B') model=AutoModelForCausalLM.from_pretrained(local_model_dir,trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained(local_model_dir,trust_remote_code=True) generation_config = GenerationConfig.from_pretrained(local_model_dir, pad_token_id=tokenizer.pad_token_id, num_return_sequences=1, max_new_tokens=7, min_new_tokens=2, do_sample=False, temperature=1.0, top_k=50, top_p=1.0) inputs = tokenizer('Answer direclty.\nThe capital of Mongolia is Ulaanbaatar.\nThe capital of Iceland is Reykjavik.\nThe capital of Australia is', return_tensors='pt') inputs = inputs.to(model.device) pred = model.generate(**inputs,generation_config=generation_config) print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True)) ``` ## Results reproduction <details><summary>Click to expand</summary> We take Apollo2-7B or Apollo-MoE-0.5B as example 1. Download Dataset for project: ``` bash 0.download_data.sh  ``` 2. Prepare test and dev data for specific model: - Create test data for with special token ``` bash 1.data_process_test&dev.sh ``` 3. Prepare train data for specific model (Create tokenized data in advance): - You can adjust data Training order and Training Epoch in this step ``` bash 2.data_process_train.sh ``` 4. Train the model - If you want to train in Multi Nodes please refer to ./src/sft/training_config/zero_multi.yaml ``` bash 3.single_node_train.sh ``` 5. Evaluate your model: Generate score for benchmark ``` bash 4.eval.sh ``` </details> ## Citation Please use the following citation if you intend to use our dataset for training or evaluation: ``` @misc{zheng2024efficientlydemocratizingmedicalllms, title={Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts}, author={Guorui Zheng and Xidong Wang and Juhao Liang and Nuo Chen and Yuping Zheng and Benyou Wang}, year={2024}, eprint={2410.10626}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2410.10626}, } ```
[ "HEAD-QA", "MEDQA", "PUBMEDQA" ]
hashamulhaq/MedQwen2.5-3B-Improved
hashamulhaq
text-generation
[ "transformers", "safetensors", "text-generation-inference", "reinforcement-learning", "unsloth", "qwen2", "trl", "grpo", "text-generation", "en", "dataset:qiaojin/PubMedQA", "dataset:openai/gsm8k", "dataset:yesilhealth/Health_Benchmarks", "license:apache-2.0", "endpoints_compatible", "region:us" ]
2025-02-13T23:35:58Z
2025-02-14T00:16:20+00:00
35
0
--- base_model: unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit datasets: - qiaojin/PubMedQA - openai/gsm8k - yesilhealth/Health_Benchmarks language: - en license: apache-2.0 pipeline_tag: text-generation tags: - text-generation-inference - reinforcement-learning - transformers - unsloth - qwen2 - trl - grpo --- # MedQwen2.53B-Improved: Medical Domain Reasoning This is a specialized variant of Qwen2.5-3B-Instruct, fine-tuned using `GRPO` to excel at medical domain reasoning while maintaining strong mathematical problem-solving capabilities. The model demonstrates enhanced reasoning abilities and can express uncertainty when appropriate. ## Important If you use `ollama`, `llama-cpp`, `vllm` or any other inference iengine, you need to set the system prompt as below as the model performs best with the following prompt: ``` '\nRespond in the following format:\n<reasoning>\n...\n</reasoning>\n<answer>\n...\n</answer>\n' ``` ## Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "hashamulhaq/MedQwen2.5-3B-Improved" # Initialize model and tokenizer model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) # Prepare prompt prompt = "What is the relationship between BMI and cardiovascular disease risk?" messages = [ {"role": "system", "content": "\nRespond in the following format:\n<reasoning>\n...\n</reasoning>\n<answer>\n...\n</answer>\n"}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) # Generate response model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ## License This model is licensed under Apache 2.0.
[ "PUBMEDQA" ]
Qwe1325/Llama-Breeze2-8B-Instruct_8bit
Qwe1325
null
[ "safetensors", "internvl_chat", "custom_code", "en", "zh", "arxiv:2501.13921", "license:llama3.2", "8-bit", "bitsandbytes", "region:us" ]
2025-02-27T02:26:32Z
2025-02-28T00:49:48+00:00
35
0
--- language: - en - zh license: llama3.2 --- # Llama-Breeze2-3B-Instruct-v0_1 【[Paper](https://arxiv.org/abs/2501.13921)】◇【[Kaggle Demo](https://www.kaggle.com/code/ycckaggle/demo-breeze-2-3b)】◇【[Collection](https://huggingface.co/collections/MediaTek-Research/llama-breeze2-67863158443a06a72dd29900)】 **The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on LLaMA with Vision-Aware and Function-Calling Capabilities** Llama Breeze 2 is a suite of advanced multi-modal language models, available in 3B and 8B parameter configurations, specifically designed to enhance Traditional Chinese language representation. Building upon the [LLaMA 3.2](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/), Breeze 2 continues pretraining on an extensive corpus to enhance the linguistic and cultural heritage of Traditional Chinese. It incorporates vision-aware capabilities through a visual encoder and a bridge module, and supports function-calling via prompt templates and post-training on function-calling data. *Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.* *We list all contributors in alphabetical order of their first names, as follows: Chan-Jan Hsu (許湛然), Chia-Sheng Liu (劉佳昇), Meng-Hsi Chen (陳孟羲), Muxi Chen (陳沐希), Po-Chun Hsu (許博竣), Yi-Chang Chen (陳宜昌), and the supervisor Da-Shan Shiu (許大山).* ## Installation ``` pip3 install transformers==4.47.0 pip3 install -U bitsandbytes pip3 install -U mtkresearch ``` ```python from transformers import AutoModel, AutoTokenizer from transformers import GenerationConfig import torch from mtkresearch.llm.prompt import MRPromptV3 model_id = 'Qwe1325/Llama-Breeze2-8B-Instruct_8bit' model = AutoModel.from_pretrained( model_id, torch_dtype=torch.bfloat16, load_in_8bit=True, low_cpu_mem_usage=True, trust_remote_code=True, device_map='auto', img_context_token_id=128212 ).eval() tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, use_fast=False) generation_config = GenerationConfig( max_new_tokens=2048, do_sample=True, temperature=0.01, top_p=0.01, repetition_penalty=1.1, eos_token_id=128009 ) prompt_engine = MRPromptV3() sys_prompt = 'You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.' def _inference(tokenizer, model, generation_config, prompt, pixel_values=None): inputs = tokenizer(prompt, return_tensors="pt").to(model.device) if pixel_values is None: output_tensors = model.generate(**inputs, generation_config=generation_config) else: output_tensors = model.generate(**inputs, generation_config=generation_config, pixel_values=pixel_values.to(model.dtype).to(model.device)) output_str = tokenizer.decode(output_tensors[0]) return output_str ``` ## Feature: Instruction Following ```python conversations = [ {"role": "system", "content": sys_prompt}, {"role": "user", "content": "請問什麼是深度學習？"}, ] prompt = prompt_engine.get_prompt(conversations) output_str = _inference(tokenizer, model, generation_config, prompt) result = prompt_engine.parse_generated_str(output_str) print(result) # {'role': 'assistant', 'content': '深度學習是一種人工智慧技術，主要是透過類似於大腦神經網路的方式來處理和分析資料。這個方法利用多層的人工神經元模仿生物神經網路的運作模式，讓電腦能夠從大量數據中學習並做出預測或決策。\n\n簡單來說，深度學習就是一種用機器學習的方式來訓練電腦，使其能夠像人類一樣理解、分辨及解決問題。這項技術已被廣泛應用在各種領域，如圖像識別、自然語言處理、語音辨識以及自動駕駛等方面。'} ``` ## Feature: Visual Instruction Following Example Image: ![img_example](https://huggingface.co/MediaTek-Research/Breeze2-8B-Instruct-v0_1/resolve/main/misc/test_big_data.png) ```python conversations = [ {"role": "system", "content": sys_prompt}, {"role": "user", "content": [ { "type": "image", "image_path": /path/to/example-image, }, { "type": "text", "text": "請問第二名可獲得多少獎金？" }, ]}, ] prompt, pixel_values = prompt_engine.get_prompt(conversations) output_str = _inference(tokenizer, model, generation_config, prompt, pixel_values=pixel_values) result = prompt_engine.parse_generated_str(output_str) print(result) # {'role': 'assistant', 'content': '第二名可獲得20萬元整。'} ``` ## Feature: Function Calling ```python import json functions = [ { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"] } }, "required": ["location"] } } ] def fake_get_current_weather(location, unit=None): return {'temperature': 30} mapping = { 'get_current_weather': fake_get_current_weather } # stage 1: query conversations = [ {"role": "user", "content": "請問台北目前溫度是攝氏幾度？"}, ] prompt = prompt_engine.get_prompt(conversations, functions=functions) output_str = _inference(tokenizer, model, generation_config, prompt) result = prompt_engine.parse_generated_str(output_str) print(result) # {'role': 'assistant', 'tool_calls': [{'id': 'call_iuwELWUShiAKE16CVoumawZ4', 'type': 'function', 'function': {'name': 'get_current_weather', 'arguments': '{"location": "台北", "unit": "celsius"}'}}]} ``` ```python # stage 2: execute called functions conversations.append(result) tool_call = result['tool_calls'][0] func_name = tool_call['function']['name'] func = mapping[func_name] arguments = json.loads(tool_call['function']['arguments']) called_result = func(**arguments) # stage 3: put executed results conversations.append( { 'role': 'tool', 'tool_call_id': tool_call['id'], 'name': func_name, 'content': json.dumps(called_result) } ) prompt = prompt_engine.get_prompt(conversations, functions=functions) output_str2 = _inference(tokenizer, model, generation_config, prompt) result2 = prompt_engine.parse_generated_str(output_str2) print(result2) # {'role': 'assistant', 'content': '台北目前的溫度是攝氏30度。'} ``` ## Citation ``` @article{breeze2, title={The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on LLaMA with Vision-Aware and Function-Calling Capabilities}, author={Breeze Team, MediaTek Research}, journal={arXiv}, year={2025}, url={https://arxiv.org/abs/2501.13921} } ```
[ "CHIA" ]
efromomr/llm-course-hw2-dpo
efromomr
text-generation
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "dataset:HumanLLMs/Human-Like-DPO-Dataset", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2025-03-06T18:44:35Z
2025-03-09T19:54:33+00:00
35
0
--- datasets: - HumanLLMs/Human-Like-DPO-Dataset library_name: transformers --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This model is an aligned version of HuggingFaceTB/SmolLM-135M-Instruct. Method used for training is DPO. Reward accuracy on training dataset is 99.89. ## Example of usage ```python DEVICE = torch.device("cuda") tokenizer = AutoTokenizer.from_pretrained(efromomr/llm-course-hw2-dpo) check_model = AutoModelForCausalLM.from_pretrained(efromomr/llm-course-hw2-dpo) check_model = check_model.to(DEVICE) check_model = check_model.eval() messages = [{"role": "user", "content": "What's your morning routine like?"}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) model_inputs = tokenizer([text], return_tensors="pt") generated_ids = model.generate(model_inputs.input_ids.to(DEVICE), max_new_tokens=256, do_sample=True) response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] #Hey, I'm excited to start my morning! I remember being in a rush, feeling my heart beat like a tiny muscle, and working like a team. So, I started with breakfast, so was my whole day! 🍕 #I chose chia seeds because of their crunchy texture and the protein they's got so easy to digest. Then, I added a healthy protein drink of spinach, almonds, and a sprinkle of hemp seeds, which is a really healthy combo! I started drinking a whole serving and got caught by the caffeine kick start, about an hour later! 🍉 #And finally, I started reading this good article on breakfast habits, so I set a goal (5 servings a day would be a good goal for me 😊). I was more than happy to follow along, so I headed to the fridge to grab that last few slices of toast! 🗺️ #As for coffee, I was blown away! It was a good 5, kinda right! My coffee was great with my pancakes, too. 🍕 #And that's it! You're out of the coffee rush. 🍕 ```
[ "CHIA" ]
pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb
pritamdeka
sentence-similarity
[ "sentence-transformers", "pytorch", "bert", "feature-extraction", "sentence-similarity", "transformers", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
2022-11-03T12:36:18Z
2022-11-03T12:42:40+00:00
34
1
--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. It has been trained over the SNLI, MNLI, SCINLI, SCITAIL, MEDNLI and STSB datasets for providing robust sentence embeddings. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb') model = AutoModel.from_pretrained('pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, mean pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) ## Training The model was trained with the parameters: **DataLoader**: `torch.utils.data.dataloader.DataLoader` of length 90 with parameters: ``` {'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` **Loss**: `sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` Parameters of the fit()-Method: ``` { "epochs": 4, "evaluation_steps": 1000, "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator", "max_grad_norm": 1, "optimizer_class": "<class 'transformers.optimization.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 36, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 100, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) ) ``` ## Citing & Authors <!--- Describe where people can find more information --> If you use the model kindly cite the following work ``` @inproceedings{deka2022evidence, title={Evidence Extraction to Validate Medical Claims in Fake News Detection}, author={Deka, Pritam and Jurek-Loughrey, Anna and others}, booktitle={International Conference on Health Information Science}, pages={3--15}, year={2022}, organization={Springer} } ```
[ "MEDNLI", "SCITAIL" ]
mindrage/Manticore-13B-Chat-Pyg-Guanaco-GPTQ-4bit-128g.no-act-order.safetensors
mindrage
text-generation
[ "transformers", "llama", "text-generation", "manticore", "guanaco", "uncensored", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-05-30T07:34:50Z
2023-06-05T08:53:22+00:00
34
15
--- library_name: transformers pipeline_tag: text-generation tags: - manticore - guanaco - uncensored --- --- # 4bit GPTQ of: Manticore-13b-Chat-Pyg by [openaccess-ai-collective](https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg) with the Guanaco 13b qLoRa by [TimDettmers](https://huggingface.co/timdettmers/guanaco-13b) applied through [Monero](https://huggingface.co/Monero/Manticore-13b-Chat-Pyg-Guanaco), quantized by [mindrage](https://huggingface.co/mindrage), uncensored [link to GGML Version](https://huggingface.co/mindrage/Manticore-13B-Chat-Pyg-Guanaco-GGML-q4_0) --- Quantized to 4bit GPTQ, groupsize 128, no-act-order. Command used to quantize: python3 llama.py Manticore-13B-Chat-Pyg-Guanaco-GPTQ-4bit-128g.no-act-order.safetensors c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors The model seems to have noticeably benefited from further augmentation with the Guanaco qLora. Its capabilities seem broad, even compared with other Wizard or Manticore models, with expected weaknesses at coding. It is very good at in-context-learning and (in its class) reasoning. It both follows instructions well, and can be used as a chatbot. Refreshingly, it does not seem to insist on aggressively sticking to narratives to justify formerly hallucinated output as much as similar models. It's output seems... eerily smart at times. I believe the model is fully unrestricted/uncensored and will generally not berate. --- Prompting style + settings: --- Presumably due to the very diverse training-data the model accepts a variety of prompting styles with relatively few issues, including the ###-Variant, but seems to work best using: # "Naming" the model works great by simply modifying the context. Substantial changes in its behaviour can be caused by appending to "ASSISTANT:", like "ASSISTANT: After careful consideration, thinking step-by-step, my response is:" user: "USER:" - bot: "ASSISTANT:" - context: "This is a conversation between an advanced AI and a human user." Turn Template: <|user|> <|user-message|>\n<|bot|><|bot-message|>\n Settings that work well without (subjectively) being too deterministic: temp: 0.15 - top_p: 0.1 - top_k: 40 - rep penalty: 1.1 ---
[ "MONERO" ]
IIC/BETO_Galen-distemist
IIC
token-classification
[ "transformers", "pytorch", "safetensors", "bert", "text-classification", "biomedical", "clinical", "spanish", "BETO_Galen", "token-classification", "es", "dataset:bigbio/distemist", "license:mit", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-06-21T09:35:48Z
2025-01-17T10:51:46+00:00
34
0
--- datasets: - bigbio/distemist language: es license: mit metrics: - f1 pipeline_tag: token-classification tags: - biomedical - clinical - spanish - BETO_Galen model-index: - name: IIC/BETO_Galen-distemist results: - task: type: token-classification dataset: name: distemist type: bigbio/distemist split: test metrics: - type: f1 value: 0.346 name: f1 --- # BETO_Galen-distemist This model is a finetuned version of BETO_Galen for the distemist dataset used in a benchmark in the paper `A comparative analysis of Spanish Clinical encoder-based models on NER and classification tasks`. The model has a F1 of 0.346 Please refer to the [original publication](https://doi.org/10.1093/jamia/ocae054) for more information. ## Parameters used | parameter | Value | |-------------------------|:-----:| | batch size | 32 | | learning rate | 3e-05 | | classifier dropout | 0.2 | | warmup ratio | 0 | | warmup steps | 0 | | weight decay | 0 | | optimizer | AdamW | | epochs | 10 | | early stopping patience | 3 | ## BibTeX entry and citation info ```bibtext @article{10.1093/jamia/ocae054, author = {García Subies, Guillem and Barbero Jiménez, Álvaro and Martínez Fernández, Paloma}, title = {A comparative analysis of Spanish Clinical encoder-based models on NER and classification tasks}, journal = {Journal of the American Medical Informatics Association}, volume = {31}, number = {9}, pages = {2137-2146}, year = {2024}, month = {03}, issn = {1527-974X}, doi = {10.1093/jamia/ocae054}, url = {https://doi.org/10.1093/jamia/ocae054}, } ```
[ "DISTEMIST" ]
eluzhnica/mpt-7b-instruct-peft-compatible
eluzhnica
text-generation
[ "transformers", "pytorch", "mpt", "text-generation", "Composer", "MosaicML", "llm-foundry", "custom_code", "dataset:mosaicml/dolly_hhrlhf", "arxiv:2205.14135", "arxiv:2108.12409", "arxiv:2010.04245", "license:cc-by-sa-3.0", "autotrain_compatible", "text-generation-inference", "region:us" ]
2023-07-05T23:14:18Z
2023-07-05T23:35:23+00:00
34
0
--- datasets: - mosaicml/dolly_hhrlhf license: cc-by-sa-3.0 tags: - Composer - MosaicML - llm-foundry inference: false --- # MPT-7B-Instruct This is the MPT-7B-Instruct but with added support to finetune using peft (tested with qlora). It is not finetuned further, the weights are the same as the original MPT-7B-Instruct. I have not traced through the whole huggingface stack to see if this is working correctly but it does finetune with qlora and outputs are reasonable. Inspired by implementations here https://huggingface.co/cekal/mpt-7b-peft-compatible/commits/main https://huggingface.co/mosaicml/mpt-7b/discussions/42. The original description for MosaicML team below: MPT-7B-Instruct is a model for short-form instruction following. It is built by finetuning [MPT-7B](https://huggingface.co/mosaicml/mpt-7b) on a [dataset](https://huggingface.co/datasets/sam-mosaic/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets. * License: _CC-By-SA-3.0_ * [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-7b-instruct) This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture. ## Model Date May 5, 2023 ## Model License CC-By-SA-3.0 ## Documentation * [Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs](https://www.mosaicml.com/blog/mpt-7b) * [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/) * Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)! ### Example Question/Instruction **Longboi24**: > What is a quoll? **MPT-7B-Instruct**: >A Quoll (pronounced “cool”) is one of Australia’s native carnivorous marsupial mammals, which are also known as macropods or wallabies in other parts around Asia and South America ## How to Use Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom model architecture that is not yet part of the `transformers` package. It includes options for many training efficiency features such as [FlashAttention (Dao et al. 2022)](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), QK LayerNorm, and more. ```python import transformers model = transformers.AutoModelForCausalLM.from_pretrained( 'mosaicml/mpt-7b-instruct', trust_remote_code=True ) ``` Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package. `MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more. To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision: ```python import torch import transformers name = 'mosaicml/mpt-7b-instruct' config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True) config.attn_config['attn_impl'] = 'triton' config.init_device = 'cuda:0' # For fast initialization directly on GPU! model = transformers.AutoModelForCausalLM.from_pretrained( name, config=config, torch_dtype=torch.bfloat16, # Load model weights in bfloat16 trust_remote_code=True ) ``` Although the model was trained with a sequence length of 2048, ALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example: ```python import transformers name = 'mosaicml/mpt-7b-instruct' config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True) config.max_seq_len = 4096 # (input + output) tokens can now be up to 4096 model = transformers.AutoModelForCausalLM.from_pretrained( name, config=config, trust_remote_code=True ) ``` This model was trained with the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. ```python from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b") ``` The model can then be used, for example, within a text-generation pipeline. Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html). ```python from transformers import pipeline pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0') with torch.autocast('cuda', dtype=torch.bfloat16): print( pipe('Here is a recipe for vegan banana bread:\n', max_new_tokens=100, do_sample=True, use_cache=True)) ``` ### Formatting This model was trained on data formatted in the dolly-15k format: ```python INSTRUCTION_KEY = "### Instruction:" RESPONSE_KEY = "### Response:" INTRO_BLURB = "Below is an instruction that describes a task. Write a response that appropriately completes the request." PROMPT_FOR_GENERATION_FORMAT = """{intro} {instruction_key} {instruction} {response_key} """.format( intro=INTRO_BLURB, instruction_key=INSTRUCTION_KEY, instruction="{instruction}", response_key=RESPONSE_KEY, ) example = "James decides to run 3 sprints 3 times a week. He runs 60 meters each sprint. How many total meters does he run a week? Explain before answering." fmt_ex = PROMPT_FOR_GENERATION_FORMAT.format(instruction=example) ``` In the above example, `fmt_ex` is ready to be tokenized and sent through the model. ## Model Description The architecture is a modification of a standard decoder-only transformer. The model has been modified from a standard transformer in the following ways: * It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf) * It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings * It does not use biases | Hyperparameter | Value | |----------------|-------| |n_parameters | 6.7B | |n_layers | 32 | | n_heads | 32 | | d_model | 4096 | | vocab size | 50432 | | sequence length | 2048 | ## PreTraining Data For more details on the pretraining process, see [MPT-7B](https://huggingface.co/mosaicml/mpt-7b). The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. ### Training Configuration This model was trained on 8 A100-40GBs for about 2.3 hours using the [MosaicML Platform](https://www.mosaicml.com/platform). The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the AdamW optimizer. ## Limitations and Biases _The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_ MPT-7B-Instruct can produce factually incorrect output, and should not be relied on to produce factually accurate information. MPT-7B-Instruct was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs. ## Acknowledgements This model was finetuned by Sam Havens and the MosaicML NLP team ## MosaicML Platform If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-7b). ## Disclaimer The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes. ## Citation Please cite this model using the following format: ``` @online{MosaicML2023Introducing, author = {MosaicML NLP Team}, title = {Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs}, year = {2023}, url = {www.mosaicml.com/blog/mpt-7b}, note = {Accessed: 2023-03-28}, % change this date urldate = {2023-03-28} % change this date } ```
[ "BLURB" ]
quocanh34/sd-pokemon-model-test
quocanh34
text-to-image
[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dataset:lambdalabs/pokemon-blip-captions", "base_model:CompVis/stable-diffusion-v1-4", "base_model:finetune:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
2023-11-19T19:42:40Z
2023-11-19T20:09:00+00:00
34
0
--- base_model: CompVis/stable-diffusion-v1-4 datasets: - lambdalabs/pokemon-blip-captions license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers inference: true --- # Text-to-image finetuning - quocanh34/sd-pokemon-model-test This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** on the **lambdalabs/pokemon-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['cute bear']: ![val_imgs_grid](./val_imgs_grid.png) ## Pipeline usage You can use the pipeline like so: ```python from diffusers import DiffusionPipeline import torch pipeline = DiffusionPipeline.from_pretrained("quocanh34/sd-pokemon-model-test", torch_dtype=torch.float16) prompt = "cute bear" image = pipeline(prompt).images[0] image.save("my_image.png") ``` ## Training info These are the key hyperparameters used during training: * Epochs: 1 * Learning rate: 1e-05 * Batch size: 1 * Gradient accumulation steps: 4 * Image resolution: 512 * Mixed-precision: fp16 More information on all the CLI arguments and the environment are available on your [`wandb` run page]().
[ "BEAR" ]
ntc-ai/SDXL-LoRA-slider.fantasy
ntc-ai
text-to-image
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
2023-12-27T22:51:24Z
2023-12-27T22:51:27+00:00
34
1
--- base_model: stabilityai/stable-diffusion-xl-base-1.0 language: - en license: mit tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers thumbnail: images/evaluate/fantasy.../fantasy_17_3.0.png widget: - text: fantasy output: url: images/fantasy_17_3.0.png - text: fantasy output: url: images/fantasy_19_3.0.png - text: fantasy output: url: images/fantasy_20_3.0.png - text: fantasy output: url: images/fantasy_21_3.0.png - text: fantasy output: url: images/fantasy_22_3.0.png inference: false instance_prompt: fantasy --- # ntcai.xyz slider - fantasy (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/fantasy_17_-3.0.png" width=256 height=256 /> | <img src="images/fantasy_17_0.0.png" width=256 height=256 /> | <img src="images/fantasy_17_3.0.png" width=256 height=256 /> | | <img src="images/fantasy_19_-3.0.png" width=256 height=256 /> | <img src="images/fantasy_19_0.0.png" width=256 height=256 /> | <img src="images/fantasy_19_3.0.png" width=256 height=256 /> | | <img src="images/fantasy_20_-3.0.png" width=256 height=256 /> | <img src="images/fantasy_20_0.0.png" width=256 height=256 /> | <img src="images/fantasy_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` fantasy ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.fantasy', weight_name='fantasy.safetensors', adapter_name="fantasy") # Activate the LoRA pipe.set_adapters(["fantasy"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, fantasy" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 670+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
[ "CRAFT" ]
ntc-ai/SDXL-LoRA-slider.great-lighting
ntc-ai
text-to-image
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
2023-12-28T19:52:55Z
2023-12-28T19:52:58+00:00
34
3
--- base_model: stabilityai/stable-diffusion-xl-base-1.0 language: - en license: mit tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers thumbnail: images/evaluate/great lighting.../great lighting_17_3.0.png widget: - text: great lighting output: url: images/great lighting_17_3.0.png - text: great lighting output: url: images/great lighting_19_3.0.png - text: great lighting output: url: images/great lighting_20_3.0.png - text: great lighting output: url: images/great lighting_21_3.0.png - text: great lighting output: url: images/great lighting_22_3.0.png inference: false instance_prompt: great lighting --- # ntcai.xyz slider - great lighting (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/great lighting_17_-3.0.png" width=256 height=256 /> | <img src="images/great lighting_17_0.0.png" width=256 height=256 /> | <img src="images/great lighting_17_3.0.png" width=256 height=256 /> | | <img src="images/great lighting_19_-3.0.png" width=256 height=256 /> | <img src="images/great lighting_19_0.0.png" width=256 height=256 /> | <img src="images/great lighting_19_3.0.png" width=256 height=256 /> | | <img src="images/great lighting_20_-3.0.png" width=256 height=256 /> | <img src="images/great lighting_20_0.0.png" width=256 height=256 /> | <img src="images/great lighting_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` great lighting ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.great-lighting', weight_name='great lighting.safetensors', adapter_name="great lighting") # Activate the LoRA pipe.set_adapters(["great lighting"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, great lighting" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 690+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
[ "CRAFT" ]
RichardErkhov/BioMistral-7B-gguf
RichardErkhov
null
[ "gguf", "arxiv:2402.10373", "endpoints_compatible", "region:us", "conversational" ]
2024-02-25T17:14:02Z
2024-02-25T18:46:57+00:00
34
0
--- {} --- GGUF quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Linkedin](https://www.linkedin.com/in/richard-erkhov/) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) BioMistral-7B - GGUF - Model creator: https://huggingface.co/BioMistral/ - Original model: https://huggingface.co/BioMistral/BioMistral-7B/ | Name | Quant method | Bits | Size | Use case | | ---- | ---- | ---- | ---- | ---- | | [BioMistral-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q2_K.gguf) | Q2_K | 2 | 2.72GB | significant quality loss - not recommended for most purposes | | [BioMistral-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16GB | very small, high quality loss | | [BioMistral-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52GB | very small, high quality loss | | [BioMistral-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82GB | small, substantial quality loss | | [BioMistral-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q4_0.gguf) | Q4_0 | 4 | 4.11GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [BioMistral-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14GB | small, greater quality loss | | [BioMistral-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37GB | medium, balanced quality - recommended | | [BioMistral-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q5_0.gguf) | Q5_0 | 5 | 5GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [BioMistral-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q5_K_S.gguf) | Q5_K_S | 5 | 5GB | large, low quality loss - recommended | | [BioMistral-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13GB | large, very low quality loss - recommended | | [BioMistral-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q6_K.gguf) | Q6_K | 6 | 5.94GB | very large, extremely low quality loss | | [BioMistral-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/BioMistral-7B-gguf/blob/main/BioMistral-7B.Q8_0.gguf) | Q8_0 | 8 | 7.7GB | very large, extremely low quality loss - not recommended | Original model description: --- license: apache-2.0 language: - fr - en - de - nl - es - pt - pl - ro - it pipeline_tag: text-generation tags: - medical - biology --- <p align="center"> <img src="https://huggingface.co/BioMistral/BioMistral-7B/resolve/main/wordart_blue_m_rectangle.png?download=true" alt="drawing" width="250"/> </p> # BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains **Abstract:** Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges. In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark comprising 10 established medical question-answering (QA) tasks in English. We also explore lightweight models obtained through quantization and model merging approaches. Our results demonstrate BioMistral's superior performance compared to existing open-source medical models and its competitive edge against proprietary counterparts. Finally, to address the limited availability of data beyond English and to assess the multilingual generalization of medical LLMs, we automatically translated and evaluated this benchmark into 7 other languages. This marks the first large-scale multilingual evaluation of LLMs in the medical domain. Datasets, multilingual evaluation benchmarks, scripts, and all the models obtained during our experiments are freely released. **Advisory Notice!** Although BioMistral is intended to encapsulate medical knowledge sourced from high-quality evidence, it hasn't been tailored to effectively, safely, or suitably convey this knowledge within professional parameters for action. We advise refraining from utilizing BioMistral in medical contexts unless it undergoes thorough alignment with specific use cases and undergoes further testing, notably including randomized controlled trials in real-world medical environments. BioMistral 7B may possess inherent risks and biases that have not yet been thoroughly assessed. Additionally, the model's performance has not been evaluated in real-world clinical settings. Consequently, we recommend using BioMistral 7B strictly as a research tool and advise against deploying it in production environments for natural language generation or any professional health and medical purposes. # 1. BioMistral models **BioMistral** is a suite of Mistral-based further pre-trained open source models suited for the medical domains and pre-trained using textual data from PubMed Central Open Access (CC0, CC BY, CC BY-SA, and CC BY-ND). All the models are trained using the CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/jean-zay/) French HPC. | Model Name | Base Model | Model Type | Sequence Length | Download | |:-------------------:|:----------------------------------:|:-------------------:|:---------------:|:-----------------------------------------------------:| | BioMistral-7B | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Further Pre-trained | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B) | | BioMistral-7B-DARE | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge DARE | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-DARE) | | BioMistral-7B-TIES | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge TIES | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-TIES) | | BioMistral-7B-SLERP | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge SLERP | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-SLERP) | # 2. Quantized Models | Base Model | Method | q_group_size | w_bit | version | VRAM GB | Time | Download | |:-------------------:|:------:|:------------:|:-----:|:-------:|:-------:|:------:|:--------:| | BioMistral-7B | FP16/BF16 | | | | 15.02 | x1.00 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B) | | BioMistral-7B | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-AWQ-QGS128-W4-GEMM) | | BioMistral-7B | AWQ | 128 | 4 | GEMV | 4.68 | x10.30 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-AWQ-QGS128-W4-GEMV) | | BioMistral-7B | BnB.4 | | 4 | | 5.03 | x3.25 | [HuggingFace](blank) | | BioMistral-7B | BnB.8 | | 8 | | 8.04 | x4.34 | [HuggingFace](blank) | | BioMistral-7B-DARE | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-DARE-AWQ-QGS128-W4-GEMM) | | BioMistral-7B-TIES | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-TIES-AWQ-QGS128-W4-GEMM) | | BioMistral-7B-SLERP | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-SLERP-AWQ-QGS128-W4-GEMM) | # 2. Using BioMistral You can use BioMistral with [Hugging Face's Transformers library](https://github.com/huggingface/transformers) as follow. Loading the model and tokenizer : ```python from transformers import AutoModel, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("BioMistral/BioMistral-7B") model = AutoModel.from_pretrained("BioMistral/BioMistral-7B") ``` # 3. Supervised Fine-tuning Benchmark | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA | MedQA 5 opts | PubMedQA | MedMCQA | Avg. | |-------------------------------------------|:---------------------------------------------:|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|------------------| | **BioMistral 7B** | 59.9 | 64.0 | 56.5 | 60.4 | 59.0 | 54.7 | 50.6 | 42.8 | 77.5 | 48.1 | 57.3 | | **Mistral 7B Instruct** | **62.9** | 57.0 | 55.6 | 59.4 | 62.5 | <u>57.2</u> | 42.0 | 40.9 | 75.7 | 46.1 | 55.9 | | | | | | | | | | | | | | | **BioMistral 7B Ensemble** | <u>62.8</u> | 62.7 | <u>57.5</u> | **63.5** | 64.3 | 55.7 | 50.6 | 43.6 | 77.5 | **48.8** | 58.7 | | **BioMistral 7B DARE** | 62.3 | **67.0** | 55.8 | 61.4 | **66.9** | **58.0** | **51.1** | **45.2** | <u>77.7</u> | <u>48.7</u> | **59.4** | | **BioMistral 7B TIES** | 60.1 | <u>65.0</u> | **58.5** | 60.5 | 60.4 | 56.5 | 49.5 | 43.2 | 77.5 | 48.1 | 57.9 | | **BioMistral 7B SLERP** | 62.5 | 64.7 | 55.8 | <u>62.7</u> | <u>64.8</u> | 56.3 | <u>50.8</u> | <u>44.3</u> | **77.8** | 48.6 | <u>58.8</u> | | | | | | | | | | | | | | | **MedAlpaca 7B** | 53.1 | 58.0 | 54.1 | 58.8 | 58.1 | 48.6 | 40.1 | 33.7 | 73.6 | 37.0 | 51.5 | | **PMC-LLaMA 7B** | 24.5 | 27.7 | 35.3 | 17.4 | 30.3 | 23.3 | 25.5 | 20.2 | 72.9 | 26.6 | 30.4 | | **MediTron-7B** | 41.6 | 50.3 | 46.4 | 27.9 | 44.4 | 30.8 | 41.6 | 28.1 | 74.9 | 41.3 | 42.7 | | **BioMedGPT-LM-7B** | 51.4 | 52.0 | 49.4 | 53.3 | 50.7 | 49.1 | 42.5 | 33.9 | 76.8 | 37.6 | 49.7 | | | | | | | | | | | | | | | **GPT-3.5 Turbo 1106*** | 74.71 | 74.00 | 65.92 | 72.79 | 72.91 | 64.73 | 57.71 | 50.82 | 72.66 | 53.79 | 66.0 | Supervised Fine-Tuning (SFT) performance of BioMistral 7B models compared to baselines, measured by accuracy (↑) and averaged across 3 random seeds of 3-shot. DARE, TIES, and SLERP are model merging strategies that combine BioMistral 7B and Mistral 7B Instruct. Best model in bold, and second-best underlined. *GPT-3.5 Turbo performances are reported from the 3-shot results without SFT. # Citation BibTeX Arxiv : [https://arxiv.org/abs/2402.10373](https://arxiv.org/abs/2402.10373) ```bibtex @misc{labrak2024biomistral, title={BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains}, author={Yanis Labrak and Adrien Bazoge and Emmanuel Morin and Pierre-Antoine Gourraud and Mickael Rouvier and Richard Dufour}, year={2024}, eprint={2402.10373}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` **CAUTION!** Both direct and downstream users need to be informed about the risks, biases, and constraints inherent in the model. While the model can produce natural language text, our exploration of its capabilities and limitations is just beginning. In fields such as medicine, comprehending these limitations is crucial. Hence, we strongly advise against deploying this model for natural language generation in production or for professional tasks in the realm of health and medicine.
[ "MEDQA", "PUBMEDQA" ]
QuantFactory/Einstein-v7-Qwen2-7B-GGUF
QuantFactory
text-generation
[ "gguf", "axolotl", "instruct", "finetune", "chatml", "gpt4", "synthetic data", "science", "physics", "chemistry", "biology", "math", "qwen", "qwen2", "text-generation", "en", "dataset:allenai/ai2_arc", "dataset:camel-ai/physics", "dataset:camel-ai/chemistry", "dataset:camel-ai/biology", "dataset:camel-ai/math", "dataset:metaeval/reclor", "dataset:openbookqa", "dataset:mandyyyyii/scibench", "dataset:derek-thomas/ScienceQA", "dataset:TIGER-Lab/ScienceEval", "dataset:jondurbin/airoboros-3.2", "dataset:LDJnr/Capybara", "dataset:Cot-Alpaca-GPT4-From-OpenHermes-2.5", "dataset:STEM-AI-mtl/Electrical-engineering", "dataset:knowrohit07/saraswati-stem", "dataset:sablo/oasst2_curated", "dataset:lmsys/lmsys-chat-1m", "dataset:TIGER-Lab/MathInstruct", "dataset:bigbio/med_qa", "dataset:meta-math/MetaMathQA-40K", "dataset:piqa", "dataset:scibench", "dataset:sciq", "dataset:Open-Orca/SlimOrca", "dataset:migtissera/Synthia-v1.3", "dataset:allenai/WildChat", "dataset:microsoft/orca-math-word-problems-200k", "dataset:openchat/openchat_sharegpt4_dataset", "dataset:teknium/GPTeacher-General-Instruct", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:totally-not-an-llm/EverythingLM-data-V3", "dataset:HuggingFaceH4/no_robots", "dataset:OpenAssistant/oasst_top1_2023-08-25", "dataset:WizardLM/WizardLM_evol_instruct_70k", "dataset:abacusai/SystemChat-1.1", "dataset:H-D-T/Buzz-V1.2", "base_model:Weyaxi/Einstein-v7-Qwen2-7B", "base_model:quantized:Weyaxi/Einstein-v7-Qwen2-7B", "license:other", "endpoints_compatible", "region:us", "conversational" ]
2024-06-27T06:38:22Z
2024-06-28T13:09:51+00:00
34
0
--- base_model: Weyaxi/Einstein-v7-Qwen2-7B datasets: - allenai/ai2_arc - camel-ai/physics - camel-ai/chemistry - camel-ai/biology - camel-ai/math - metaeval/reclor - openbookqa - mandyyyyii/scibench - derek-thomas/ScienceQA - TIGER-Lab/ScienceEval - jondurbin/airoboros-3.2 - LDJnr/Capybara - Cot-Alpaca-GPT4-From-OpenHermes-2.5 - STEM-AI-mtl/Electrical-engineering - knowrohit07/saraswati-stem - sablo/oasst2_curated - lmsys/lmsys-chat-1m - TIGER-Lab/MathInstruct - bigbio/med_qa - meta-math/MetaMathQA-40K - openbookqa - piqa - metaeval/reclor - derek-thomas/ScienceQA - scibench - sciq - Open-Orca/SlimOrca - migtissera/Synthia-v1.3 - TIGER-Lab/ScienceEval - allenai/WildChat - microsoft/orca-math-word-problems-200k - openchat/openchat_sharegpt4_dataset - teknium/GPTeacher-General-Instruct - m-a-p/CodeFeedback-Filtered-Instruction - totally-not-an-llm/EverythingLM-data-V3 - HuggingFaceH4/no_robots - OpenAssistant/oasst_top1_2023-08-25 - WizardLM/WizardLM_evol_instruct_70k - abacusai/SystemChat-1.1 - H-D-T/Buzz-V1.2 language: - en license: other pipeline_tag: text-generation tags: - axolotl - instruct - finetune - chatml - gpt4 - synthetic data - science - physics - chemistry - biology - math - qwen - qwen2 --- # 🔬 Einstein-v7-Qwen2-7B-GGUF This is quantized version of [Weyaxi/Einstein-v7-Qwen2-7B](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B) created using llama.cpp # Model Description ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/KLQP1jK-DIzpwHzYRIH-Q.png) This model is a full fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on diverse datasets. This model is finetuned using `8xMI300X` using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl). <details><summary>See axolotl config</summary> axolotl version: `0.4.0` ```yaml base_model: Qwen/Qwen2-7B model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer load_in_8bit: false load_in_4bit: false strict: false chat_template: chatml datasets: - path: data/airoboros_3.2_without_contextual_slimorca_orca_sharegpt.json ds_type: json type: sharegpt conversation: chatml - path: data/allenai_wild_chat_gpt4_english_toxic_random_half_4k_sharegpt.json ds_type: json type: sharegpt strict: false conversation: chatml - path: data/buzz_unstacked_chosen_math_removed_filtered.json ds_type: json type: alpaca conversation: chatml - path: data/capybara_sharegpt.json ds_type: json type: sharegpt conversation: chatml - path: data/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.json ds_type: json type: sharegpt conversation: chatml - path: data/everythinglm-data-v3_sharegpt.json ds_type: json type: sharegpt strict: false conversation: chatml - path: data/gpt4_data_lmys_1m_sharegpt.json ds_type: json type: sharegpt conversation: chatml - path: data/gpteacher-instruct-special-alpaca.json ds_type: json type: gpteacher conversation: chatml - path: data/merged_all.json ds_type: json type: alpaca conversation: chatml - path: data/no_robots_sharegpt.json ds_type: json type: sharegpt strict: false conversation: chatml - path: data/oasst_top1_from_fusechatmixture_sharegpt.json ds_type: json type: sharegpt strict: false conversation: chatml - path: data/pippa_bagel_repo_3k_sharegpt.json ds_type: json type: sharegpt conversation: chatml - path: data/rpguild_quarter_alignment_lab_sharegpt.json ds_type: json type: sharegpt conversation: chatml - path: data/sharegpt_gpt4_english.json ds_type: json type: sharegpt conversation: chatml - path: data/slimorca_dedup_filtered_95k_sharegpt.json ds_type: json type: sharegpt conversation: chatml - path: data/soda_diaolog_longest_tenth_buzz_sharegpt.json ds_type: json type: sharegpt conversation: chatml - path: data/synthia-v1.3_sharegpt_12500.json ds_type: json type: sharegpt conversation: chatml - path: data/system_conversations_dolphin_sharegpt.json ds_type: json type: sharegpt conversation: chatml dataset_prepared_path: last_run_prepared val_set_size: 0.002 output_dir: ./Einstein-v7-Qwen2-7B-model sequence_len: 8192 sample_packing: true pad_to_sequence_len: true eval_sample_packing: false wandb_project: Einstein wandb_entity: wandb_watch: wandb_name: wandb_log_model: hub_model_id: Weyaxi/Einstein-v7-Qwen2-7B gradient_accumulation_steps: 4 micro_batch_size: 6 num_epochs: 2 optimizer: paged_adamw_8bit lr_scheduler: cosine learning_rate: 0.00001 # look train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: unsloth gradient_checkpointing_kwargs: use_reentrant: true # look early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 10 evals_per_epoch: 2 eval_table_size: eval_max_new_tokens: 128 saves_per_epoch: 1 debug: deepspeed: deepspeed_configs/zero3_bf16.json weight_decay: 0.05 fsdp: fsdp_config: special_tokens: eos_token: "<|im_end|>" pad_token: "<|end_of_text|>" tokens: - "<|im_start|>" - "<|im_end|>" ``` </details><br> # 💬 Prompt Template You can use ChatML prompt template while using the model: ### ChatML ``` <|im_start|>system {system}<|im_end|> <|im_start|>user {user}<|im_end|> <|im_start|>assistant {asistant}<|im_end|> ``` This prompt template is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the `tokenizer.apply_chat_template()` method: ```python messages = [ {"role": "system", "content": "You are helpful AI asistant."}, {"role": "user", "content": "Hello!"} ] gen_input = tokenizer.apply_chat_template(message, return_tensors="pt") model.generate(**gen_input) ``` # 📊 Datasets used in this model The datasets used to train this model are listed in the metadata section of the model card. Please note that certain datasets mentioned in the metadata may have undergone filtering based on various criteria. The results of this filtering process and its outcomes are in a diffrent repository: [Weyaxi/sci-datasets/main](https://huggingface.co/datasets/Weyaxi/sci-datasets/tree/main) # 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) # 🤖 Additional information about training This model is full fine-tuned for 2 epoch. Total number of steps was 500. <details><summary>Loss graph</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/bkJGgh_JUfKeRlTLo_ZcB.png) </details><br>
[ "SCIQ" ]
Mardiyyah/Llama3-OpenBioLLM-8B-GGUF
Mardiyyah
null
[ "gguf", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "autoquant", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:quantized:meta-llama/Meta-Llama-3-8B", "license:llama3", "endpoints_compatible", "region:us" ]
2024-08-22T09:13:43Z
2024-08-22T10:07:32+00:00
34
1
--- base_model: meta-llama/Meta-Llama-3-8B language: - en license: llama3 tags: - llama-3 - llama - Mixtral - instruct - finetune - chatml - DPO - RLHF - gpt4 - distillation - autoquant - gguf widget: - example_title: OpenBioLLM-8B messages: - role: system content: You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. - role: user content: How long does it take for newborn jaundice to go away? output: text: 'Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment. The duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines: 1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment. It''s important for parents to monitor their newborn''s jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn''s jaundice, it''s always best to consult with a healthcare professional for personalized advice and guidance.' model-index: - name: OpenBioLLM-8B results: [] --- <div align="center"> <img width="260px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/2FhDh8NDvMl7iSxbQz9BP.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-8B builds upon the powerful foundations of the **Meta-Llama-3-8B** and [Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Ranking Dataset**: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 8 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-8B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-8B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 1 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B** # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!**  While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)
[ "MEDQA", "PUBMEDQA" ]
juanluisdb/MiniLM-L-6-rerank-m3
juanluisdb
text-classification
[ "transformers", "safetensors", "bert", "text-classification", "cross-encoder", "en", "dataset:lightonai/ms-marco-en-bge", "dataset:juanluisdb/triviaqa-bge-m3-logits", "dataset:juanluisdb/nq-bge-m3-logits", "base_model:cross-encoder/ms-marco-MiniLM-L-6-v2", "base_model:finetune:cross-encoder/ms-marco-MiniLM-L-6-v2", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-09-25T15:32:58Z
2024-09-26T18:50:12+00:00
34
1
--- base_model: - cross-encoder/ms-marco-MiniLM-L-6-v2 datasets: - lightonai/ms-marco-en-bge - juanluisdb/triviaqa-bge-m3-logits - juanluisdb/nq-bge-m3-logits language: - en library_name: transformers tags: - cross-encoder --- # Model Card for Model ID This model is finetuned starting from the well-known [ms-marco-MiniLM-L-6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-6-v2) using KL distillation techniques as described [here](https://www.answer.ai/posts/2024-08-13-small-but-mighty-colbert.html), using [bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) as teacher # Usage ## Usage with Transformers ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification import torch model = AutoModelForSequenceClassification.from_pretrained("juanluisdb/MiniLM-L-6-rerank-m3") tokenizer = AutoTokenizer.from_pretrained("juanluisdb/MiniLM-L-6-rerank-m3") features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'], padding=True, truncation=True, return_tensors="pt") model.eval() with torch.no_grad(): scores = model(**features).logits print(scores) ``` ## Usage with SentenceTransformers ```python from sentence_transformers import CrossEncoder model = CrossEncoder("juanluisdb/MiniLM-L-6-rerank-m3", max_length=512) scores = model.predict([('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')]) ``` # Evaluation ### BEIR (NDCG@10) I've run tests on different BEIR datasets. Cross Encoders rerank top100 BM25 results. | | bm25 | jina-reranker-v1-turbo-en | bge-reranker-v2-m3 | mxbai-rerank-base-v1 | ms-marco-MiniLM-L-6-v2 | MiniLM-L-6-rerank-m3 | |:---------------|:-------:|:----------------------------:|:---------------------:|:-----------------------:|:-------------------------:|:------------------------------:| | nq* | 0.305 | 0.533 | **0.597** | 0.535 | 0.523 | 0.580 | | fever* | 0.638 | 0.852 | 0.857 | 0.767 | 0.801 | **0.867** | | fiqa | 0.238 | 0.336 | **0.397** | 0.382 | 0.349 | 0.364 | | trec-covid | 0.589 | 0.774 | 0.784 | **0.830** | 0.741 | 0.738 | | scidocs | 0.15 | 0.166 | 0.169 | **0.171** | 0.164 | 0.165 | | scifact | 0.676 | 0.739 | 0.731 | 0.719 | 0.688 | **0.750** | | nfcorpus | 0.318 | 0.353 | 0.336 | **0.353** | 0.349 | 0.350 | | hotpotqa | 0.629 | 0.745 | **0.794** | 0.668 | 0.724 | 0.775 | | dbpedia-entity | 0.319 | 0.421 | **0.445** | 0.416 | 0.445 | 0.444 | | quora | 0.787 | 0.858 | 0.858 | 0.747 | 0.825 | **0.871** | | climate-fever | 0.163 | 0.233 | **0.314** | 0.253 | 0.244 | 0.309 | \* Training splits of NQ and Fever were used as part of the training data. Comparison with [ablated model](https://huggingface.co/juanluisdb/MiniLM-L-6-rerank-m3-ablated) trained only on MSMarco: | | ms-marco-MiniLM-L-6-v2 | MiniLM-L-6-rerank-m3-ablated | |:---------------|:-------------------------:|:--------------------------------------:| | nq | 0.5234 | **0.5412** | | fever | 0.8007 | **0.8221** | | fiqa | 0.349 | **0.3598** | | trec-covid | **0.741** | 0.7331 | | scidocs | **0.1638** | 0.163 | | scifact | 0.688 | **0.7376** | | nfcorpus | 0.3493 | **0.3495** | | hotpotqa | 0.7235 | **0.7583** | | dbpedia-entity | **0.4445** | 0.4382 | | quora | 0.8251 | **0.8619** | | climate-fever | 0.2438 | **0.2449** | # Datasets Used ~900k queries with 32-way triplets were used from these datasets: * MSMarco * TriviaQA * Natural Questions * FEVER
[ "SCIFACT" ]
BSC-LT/salamandra-2b-instruct-fp8
BSC-LT
text-generation
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "bg", "ca", "code", "cs", "cy", "da", "de", "el", "en", "es", "et", "eu", "fi", "fr", "ga", "gl", "hr", "hu", "it", "lt", "lv", "mt", "nl", "nn", "oc", "pl", "pt", "ro", "ru", "sh", "sk", "sl", "sr", "sv", "uk", "base_model:BSC-LT/salamandra-2b-instruct", "base_model:finetune:BSC-LT/salamandra-2b-instruct", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:eu" ]
2024-10-30T16:13:07Z
2024-11-07T18:18:35+00:00
34
0
--- base_model: BSC-LT/salamandra-2b-instruct language: - bg - ca - code - cs - cy - da - de - el - en - es - et - eu - fi - fr - ga - gl - hr - hu - it - lt - lv - mt - nl - nn - \no - oc - pl - pt - ro - ru - sh - sk - sl - sr - sv - uk library_name: transformers license: apache-2.0 pipeline_tag: text-generation --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/633b489acbdbadd99c0b75ef/6y7ivSTUx4zYTn-2o-aAZ.png) # Salamandra-2b-instruct-fp8 Model Card This model is the fp8-quantized version of [Salamandra-2b-instruct](https://huggingface.co/BSC-LT/salamandra-2b-instruct). The model weights are quantized from FP16 to FP8 (8-bit weights) using the FP8 quantization algorithm from [NeuralMagic](https://neuralmagic.com/blog/vllm-brings-fp8-inference-to-the-open-source-community/). Inferencing with this model can be done using [VLLM](https://docs.vllm.ai/en/stable/models/engine_args.html). Salamandra is a highly multilingual model pre-trained from scratch that comes in three different sizes — 2B, 7B and 40B parameters — with their respective base and instruction-tuned variants, promoted and financed by the Government of Catalonia through the [Aina Project](https://projecteaina.cat/) and the _Ministerio para la Transformación Digital y de la Función Pública_ - Funded by EU – NextGenerationEU within the framework of [ILENIA Project](https://proyectoilenia.es/) with reference 2022/TL22/00215337. This model card corresponds to the fp8-quantized version of Salamandra-2b-instruct. The entire Salamandra family is released under a permissive [Apache 2.0 license]((https://www.apache.org/licenses/LICENSE-2.0)). ## How to Use The following example code works under ``Python 3.9.16``, ``vllm==0.6.3.post1``, ``torch==2.4.0`` and ``torchvision==0.19.0``, though it should run on any current version of the libraries. This is an example of a conversational chatbot using the model: ``` from vllm import LLM, SamplingParams model_name = "BSC-LT/salamandra-2b-instruct-fp8" llm = LLM(model=model_name) messages = [] while True: user_input = input("user >> ") if user_input.lower() == "exit": print("Chat ended.") break messages.append({'role': 'user', 'content': user_input}) outputs = llm.chat(messages, sampling_params=SamplingParams( temperature=0.5, stop_token_ids=[5], max_tokens=200) )[0].outputs model_output = outputs[0].text print(f'assistant >> {model_output}') messages.append({'role': 'assistant', 'content': model_output}) ``` ### Author International Business Machines (IBM). ### Copyright International Business Machines (IBM). ### Contact For further information, please send an email to <[email protected]>. ### Acknowledgements We appreciate the collaboration with IBM in this work. Specifically, the IBM team created fp8-quantized version of the Salamandra-2b-instruct model released here. ### Disclaimer Be aware that the model may contain biases or other unintended distortions. When third parties deploy systems or provide services based on this model, or use the model themselves, they bear the responsibility for mitigating any associated risks and ensuring compliance with applicable regulations, including those governing the use of Artificial Intelligence. Barcelona Supercomputing Center and International Business Machines shall not be held liable for any outcomes resulting from third-party use. ### License [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)
[ "BEAR" ]
itlwas/Einstein-v7-Qwen2-7B-Q4_K_M-GGUF
itlwas
null
[ "gguf", "axolotl", "instruct", "finetune", "chatml", "gpt4", "synthetic data", "science", "physics", "chemistry", "biology", "math", "qwen", "qwen2", "llama-cpp", "gguf-my-repo", "en", "dataset:allenai/ai2_arc", "dataset:camel-ai/physics", "dataset:camel-ai/chemistry", "dataset:camel-ai/biology", "dataset:camel-ai/math", "dataset:metaeval/reclor", "dataset:openbookqa", "dataset:mandyyyyii/scibench", "dataset:derek-thomas/ScienceQA", "dataset:TIGER-Lab/ScienceEval", "dataset:jondurbin/airoboros-3.2", "dataset:LDJnr/Capybara", "dataset:Cot-Alpaca-GPT4-From-OpenHermes-2.5", "dataset:STEM-AI-mtl/Electrical-engineering", "dataset:knowrohit07/saraswati-stem", "dataset:sablo/oasst2_curated", "dataset:lmsys/lmsys-chat-1m", "dataset:TIGER-Lab/MathInstruct", "dataset:bigbio/med_qa", "dataset:meta-math/MetaMathQA-40K", "dataset:piqa", "dataset:scibench", "dataset:sciq", "dataset:Open-Orca/SlimOrca", "dataset:migtissera/Synthia-v1.3", "dataset:allenai/WildChat", "dataset:microsoft/orca-math-word-problems-200k", "dataset:openchat/openchat_sharegpt4_dataset", "dataset:teknium/GPTeacher-General-Instruct", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:totally-not-an-llm/EverythingLM-data-V3", "dataset:HuggingFaceH4/no_robots", "dataset:OpenAssistant/oasst_top1_2023-08-25", "dataset:WizardLM/WizardLM_evol_instruct_70k", "dataset:abacusai/SystemChat-1.1", "dataset:H-D-T/Buzz-V1.2", "base_model:Weyaxi/Einstein-v7-Qwen2-7B", "base_model:quantized:Weyaxi/Einstein-v7-Qwen2-7B", "license:other", "model-index", "endpoints_compatible", "region:us", "conversational" ]
2024-12-29T00:29:07Z
2024-12-29T00:29:30+00:00
34
0
--- base_model: Weyaxi/Einstein-v7-Qwen2-7B datasets: - allenai/ai2_arc - camel-ai/physics - camel-ai/chemistry - camel-ai/biology - camel-ai/math - metaeval/reclor - openbookqa - mandyyyyii/scibench - derek-thomas/ScienceQA - TIGER-Lab/ScienceEval - jondurbin/airoboros-3.2 - LDJnr/Capybara - Cot-Alpaca-GPT4-From-OpenHermes-2.5 - STEM-AI-mtl/Electrical-engineering - knowrohit07/saraswati-stem - sablo/oasst2_curated - lmsys/lmsys-chat-1m - TIGER-Lab/MathInstruct - bigbio/med_qa - meta-math/MetaMathQA-40K - openbookqa - piqa - metaeval/reclor - derek-thomas/ScienceQA - scibench - sciq - Open-Orca/SlimOrca - migtissera/Synthia-v1.3 - TIGER-Lab/ScienceEval - allenai/WildChat - microsoft/orca-math-word-problems-200k - openchat/openchat_sharegpt4_dataset - teknium/GPTeacher-General-Instruct - m-a-p/CodeFeedback-Filtered-Instruction - totally-not-an-llm/EverythingLM-data-V3 - HuggingFaceH4/no_robots - OpenAssistant/oasst_top1_2023-08-25 - WizardLM/WizardLM_evol_instruct_70k - abacusai/SystemChat-1.1 - H-D-T/Buzz-V1.2 language: - en license: other tags: - axolotl - instruct - finetune - chatml - gpt4 - synthetic data - science - physics - chemistry - biology - math - qwen - qwen2 - llama-cpp - gguf-my-repo model-index: - name: Einstein-v7-Qwen2-7B results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 41.0 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Einstein-v7-Qwen2-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 32.84 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Einstein-v7-Qwen2-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 15.18 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Einstein-v7-Qwen2-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 6.6 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Einstein-v7-Qwen2-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 14.06 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Einstein-v7-Qwen2-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 34.4 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Einstein-v7-Qwen2-7B name: Open LLM Leaderboard --- # AIronMind/Einstein-v7-Qwen2-7B-Q4_K_M-GGUF This model was converted to GGUF format from [`Weyaxi/Einstein-v7-Qwen2-7B`](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo AIronMind/Einstein-v7-Qwen2-7B-Q4_K_M-GGUF --hf-file einstein-v7-qwen2-7b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo AIronMind/Einstein-v7-Qwen2-7B-Q4_K_M-GGUF --hf-file einstein-v7-qwen2-7b-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo AIronMind/Einstein-v7-Qwen2-7B-Q4_K_M-GGUF --hf-file einstein-v7-qwen2-7b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo AIronMind/Einstein-v7-Qwen2-7B-Q4_K_M-GGUF --hf-file einstein-v7-qwen2-7b-q4_k_m.gguf -c 2048 ```
[ "SCIQ" ]
NoYo25/BiodivBERT
NoYo25
token-classification
[ "transformers", "pytorch", "bert", "fill-mask", "bert-base-cased", "biodiversity", "token-classification", "sequence-classification", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2022-05-16T13:02:40Z
2023-07-13T08:51:53+00:00
33
3
--- language: - en license: apache-2.0 metrics: - f1 - precision - recall - accuracy tags: - bert-base-cased - biodiversity - token-classification - sequence-classification thumbnail: https://www.fusion.uni-jena.de/fusionmedia/fusionpictures/fusion-service/fusion-transp.png?height=383&width=680 citation: 'Abdelmageed, N., Löffler, F., & König-Ries, B. (2023). BiodivBERT: a Pre-Trained Language Model for the Biodiversity Domain.' paper: https://ceur-ws.org/Vol-3415/paper-7.pdf evaluation datasets: - url: https://doi.org/10.5281/zenodo.6554208 - named entity recognition: - COPIOUS - QEMP - BiodivNER - LINNAEUS - Species800 - relation extraction: - GAD - EU-ADR - BiodivRE - BioRelEx training_data: - crawling-keywords: - biodivers - genetic diversity - omic diversity - phylogenetic diversity - soil diversity - population diversity - species diversity - ecosystem diversity - functional diversity - microbial diversity - corpora: - (+Abs) Springer and Elsevier abstracts in the duration of 1990-2020 - (+Abs+Full) Springer and Elsevier abstracts and open access full publication text in the duration of 1990-2020 pre-training-hyperparams: - MAX_LEN = 512 - MLM_PROP = 0.15 - num_train_epochs = 3 - per_device_train_batch_size = 16 - per_device_eval_batch_size = 16 - gradient_accumulation_steps = 4 --- # BiodivBERT ## Model description * BiodivBERT is a domain-specific BERT based cased model for the biodiversity literature. * It uses the tokenizer from BERTT base cased model. * BiodivBERT is pre-trained on abstracts and full text from biodiversity literature. * BiodivBERT is fine-tuned on two down stream tasks for Named Entity Recognition and Relation Extraction in the biodiversity domain. * Please visit our [GitHub Repo](https://github.com/fusion-jena/BiodivBERT) for more details. ## How to use * You can use BiodivBERT via huggingface library as follows: 1. Masked Language Model ```` >>> from transformers import AutoTokenizer, AutoModelForMaskedLM >>> tokenizer = AutoTokenizer.from_pretrained("NoYo25/BiodivBERT") >>> model = AutoModelForMaskedLM.from_pretrained("NoYo25/BiodivBERT") ```` 2. Token Classification - Named Entity Recognition ```` >>> from transformers import AutoTokenizer, AutoModelForTokenClassification >>> tokenizer = AutoTokenizer.from_pretrained("NoYo25/BiodivBERT") >>> model = AutoModelForTokenClassification.from_pretrained("NoYo25/BiodivBERT") ```` 3. Sequence Classification - Relation Extraction ```` >>> from transformers import AutoTokenizer, AutoModelForSequenceClassification >>> tokenizer = AutoTokenizer.from_pretrained("NoYo25/BiodivBERT") >>> model = AutoModelForSequenceClassification.from_pretrained("NoYo25/BiodivBERT") ```` ## Training data * BiodivBERT is pre-trained on abstracts and full text from biodiversity domain-related publications. * We used both Elsevier and Springer APIs to crawl such data. * We covered publications over the duration of 1990-2020. ## Evaluation results BiodivBERT overperformed both ``BERT_base_cased``, ``biobert_v1.1``, and ``BiLSTM`` as a baseline approach on the down stream tasks.
[ "BIORELEX", "EU-ADR", "GAD", "LINNAEUS" ]
BigSalmon/InformalToFormalLincoln96Paraphrase
BigSalmon
text-generation
[ "transformers", "pytorch", "gpt2", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2023-03-22T02:15:22Z
2023-04-01T17:28:13+00:00
33
0
--- {} --- data: https://github.com/BigSalmon2/InformalToFormalDataset Text Generation Informal Formal ``` from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BigSalmon/InformalToFormalLincoln96Paraphrase") model = AutoModelForCausalLM.from_pretrained("BigSalmon/InformalToFormalLincoln96Paraphrase") ``` ``` Demo: https://huggingface.co/spaces/BigSalmon/FormalInformalConciseWordy ``` ``` prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:""" input_ids = tokenizer.encode(prompt, return_tensors='pt') outputs = model.generate(input_ids=input_ids, max_length=10 + len(prompt), temperature=1.0, top_k=50, top_p=0.95, do_sample=True, num_return_sequences=5, early_stopping=True) for i in range(5): print(tokenizer.decode(outputs[i])) ``` Most likely outputs (Disclaimer: I highly recommend using this over just generating): ``` prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:""" text = tokenizer.encode(prompt) myinput, past_key_values = torch.tensor([text]), None myinput = myinput myinput= myinput.to(device) logits, past_key_values = model(myinput, past_key_values = past_key_values, return_dict=False) logits = logits[0,-1] probabilities = torch.nn.functional.softmax(logits) best_logits, best_indices = logits.topk(250) best_words = [tokenizer.decode([idx.item()]) for idx in best_indices] text.append(best_indices[0].item()) best_probabilities = probabilities[best_indices].tolist() words = [] print(best_words) ``` ``` How To Make Prompt: informal english: i am very ready to do that just that. Translated into the Style of Abraham Lincoln: you can assure yourself of my readiness to work toward this end. Translated into the Style of Abraham Lincoln: please be assured that i am most ready to undertake this laborious task. *** informal english: space is huge and needs to be explored. Translated into the Style of Abraham Lincoln: space awaits traversal, a new world whose boundaries are endless. Translated into the Style of Abraham Lincoln: space is a ( limitless / boundless ) expanse, a vast virgin domain awaiting exploration. *** informal english: corn fields are all across illinois, visible once you leave chicago. Translated into the Style of Abraham Lincoln: corn fields ( permeate illinois / span the state of illinois / ( occupy / persist in ) all corners of illinois / line the horizon of illinois / envelop the landscape of illinois ), manifesting themselves visibly as one ventures beyond chicago. informal english: ``` ``` original: microsoft word's [MASK] pricing invites competition. Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition. *** original: the library’s quiet atmosphere encourages visitors to [blank] in their work. Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work. ``` ``` Essay Intro (Warriors vs. Rockets in Game 7): text: eagerly anticipated by fans, game 7's are the highlight of the post-season. text: ever-building in suspense, game 7's have the crowd captivated. *** Essay Intro (South Korean TV Is Becoming Popular): text: maturing into a bona fide paragon of programming, south korean television ( has much to offer / entertains without fail / never disappoints ). text: increasingly held in critical esteem, south korean television continues to impress. text: at the forefront of quality content, south korea is quickly achieving celebrity status. *** Essay Intro ( ``` ``` Search: What is the definition of Checks and Balances? https://en.wikipedia.org/wiki/Checks_and_balances Checks and Balances is the idea of having a system where each and every action in government should be subject to one or more checks that would not allow one branch or the other to overly dominate. https://www.harvard.edu/glossary/Checks_and_Balances Checks and Balances is a system that allows each branch of government to limit the powers of the other branches in order to prevent abuse of power https://www.law.cornell.edu/library/constitution/Checks_and_Balances Checks and Balances is a system of separation through which branches of government can control the other, thus preventing excess power. *** Search: What is the definition of Separation of Powers? https://en.wikipedia.org/wiki/Separation_of_powers The separation of powers is a principle in government, whereby governmental powers are separated into different branches, each with their own set of powers, that are prevent one branch from aggregating too much power. https://www.yale.edu/tcf/Separation_of_Powers.html Separation of Powers is the division of governmental functions between the executive, legislative and judicial branches, clearly demarcating each branch's authority, in the interest of ensuring that individual liberty or security is not undermined. *** Search: What is the definition of Connection of Powers? https://en.wikipedia.org/wiki/Connection_of_powers Connection of Powers is a feature of some parliamentary forms of government where different branches of government are intermingled, typically the executive and legislative branches. https://simple.wikipedia.org/wiki/Connection_of_powers The term Connection of Powers describes a system of government in which there is overlap between different parts of the government. *** Search: What is the definition of ``` ``` Search: What are phrase synonyms for "second-guess"? https://www.powerthesaurus.org/second-guess/synonyms Shortest to Longest: - feel dubious about - raise an eyebrow at - wrinkle their noses at - cast a jaundiced eye at - teeter on the fence about *** Search: What are phrase synonyms for "mean to newbies"? https://www.powerthesaurus.org/mean_to_newbies/synonyms Shortest to Longest: - readiness to balk at rookies - absence of tolerance for novices - hostile attitude toward newcomers *** Search: What are phrase synonyms for "make use of"? https://www.powerthesaurus.org/make_use_of/synonyms Shortest to Longest: - call upon - glean value from - reap benefits from - derive utility from - seize on the merits of - draw on the strength of - tap into the potential of *** Search: What are phrase synonyms for "hurting itself"? https://www.powerthesaurus.org/hurting_itself/synonyms Shortest to Longest: - erring - slighting itself - forfeiting its integrity - doing itself a disservice - evincing a lack of backbone *** Search: What are phrase synonyms for " ``` ``` - nebraska - unicamerical legislature - different from federal house and senate text: featuring a unicameral legislature, nebraska's political system stands in stark contrast to the federal model, comprised of a house and senate. *** - penny has practically no value - should be taken out of circulation - just as other coins have been in us history - lost use - value not enough - to make environmental consequences worthy text: all but valueless, the penny should be retired. as with other coins in american history, it has become defunct. too minute to warrant the environmental consequences of its production, it has outlived its usefulness. *** - ``` ``` original: sports teams are profitable for owners. [MASK], their valuations experience a dramatic uptick. infill: sports teams are profitable for owners. ( accumulating vast sums / stockpiling treasure / realizing benefits / cashing in / registering robust financials / scoring on balance sheets ), their valuations experience a dramatic uptick. *** original: ``` ``` wordy: classical music is becoming less popular more and more. Translate into Concise Text: interest in classic music is fading. *** wordy: ``` ``` sweet: savvy voters ousted him. longer: voters who were informed delivered his defeat. *** sweet: ``` ``` 1: commercial space company spacex plans to launch a whopping 52 flights in 2022. 2: spacex, a commercial space company, intends to undertake a total of 52 flights in 2022. 3: in 2022, commercial space company spacex has its sights set on undertaking 52 flights. 4: 52 flights are in the pipeline for 2022, according to spacex, a commercial space company. 5: a commercial space company, spacex aims to conduct 52 flights in 2022. *** 1: ``` Keywords to sentences or sentence. ``` ngos are characterized by: □ voluntary citizens' group that is organized on a local, national or international level □ encourage political participation □ often serve humanitarian functions □ work for social, economic, or environmental change *** what are the drawbacks of living near an airbnb? □ noise □ parking □ traffic □ security □ strangers *** ``` ``` original: musicals generally use spoken dialogue as well as songs to convey the story. operas are usually fully sung. adapted: musicals generally use spoken dialogue as well as songs to convey the story. ( in a stark departure / on the other hand / in contrast / by comparison / at odds with this practice / far from being alike / in defiance of this standard / running counter to this convention ), operas are usually fully sung. *** original: akoya and tahitian are types of pearls. akoya pearls are mostly white, and tahitian pearls are naturally dark. adapted: akoya and tahitian are types of pearls. ( a far cry from being indistinguishable / easily distinguished / on closer inspection / setting them apart / not to be mistaken for one another / hardly an instance of mere synonymy / differentiating the two ), akoya pearls are mostly white, and tahitian pearls are naturally dark. *** original: ``` ``` original: had trouble deciding. translated into journalism speak: wrestled with the question, agonized over the matter, furrowed their brows in contemplation. *** original: ``` ``` input: not loyal 1800s english: ( two-faced / inimical / perfidious / duplicitous / mendacious / double-dealing / shifty ). *** input: ``` ``` first: ( was complicit in / was involved in ). antonym: ( was blameless / was not an accomplice to / had no hand in / was uninvolved in ). *** first: ( have no qualms about / see no issue with ). antonym: ( are deeply troubled by / harbor grave reservations about / have a visceral aversion to / take ( umbrage at / exception to ) / are wary of ). *** first: ( do not see eye to eye / disagree often ). antonym: ( are in sync / are united / have excellent rapport / are like-minded / are in step / are of one mind / are in lockstep / operate in perfect harmony / march in lockstep ). *** first: ``` ``` stiff with competition, law school {A} is the launching pad for countless careers, {B} is a crowded field, {C} ranks among the most sought-after professional degrees, {D} is a professional proving ground. *** languishing in viewership, saturday night live {A} is due for a creative renaissance, {B} is no longer a ratings juggernaut, {C} has been eclipsed by its imitators, {C} can still find its mojo. *** dubbed the "manhattan of the south," atlanta {A} is a bustling metropolis, {B} is known for its vibrant downtown, {C} is a city of rich history, {D} is the pride of georgia. *** embattled by scandal, harvard {A} is feeling the heat, {B} cannot escape the media glare, {C} is facing its most intense scrutiny yet, {D} is in the spotlight for all the wrong reasons. ``` Infill / Infilling / Masking / Phrase Masking (Works pretty decently actually, especially when you use logprobs code from above): ``` his contention [blank] by the evidence [sep] was refuted [answer] *** few sights are as [blank] new york city as the colorful, flashing signage of its bodegas [sep] synonymous with [answer] *** when rick won the lottery, all of his distant relatives [blank] his winnings [sep] clamored for [answer] *** the library’s quiet atmosphere encourages visitors to [blank] in their work [sep] immerse themselves [answer] *** the joy of sport is that no two games are alike. for every exhilarating experience, however, there is an interminable one. the national pastime, unfortunately, has a penchant for the latter. what begins as a summer evening at the ballpark can quickly devolve into a game of tedium. the primary culprit is the [blank] of play. from batters readjusting their gloves to fielders spitting on their mitts, the action is [blank] unnecessary interruptions. the sport's future is [blank] if these tendencies are not addressed [sep] plodding pace [answer] riddled with [answer] bleak [answer] *** microsoft word's [blank] pricing [blank] competition [sep] unconscionable [answer] invites [answer] *** ``` ``` original: microsoft word's [MASK] pricing invites competition. Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition. *** original: the library’s quiet atmosphere encourages visitors to [blank] in their work. Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work. ``` Backwards ``` Essay Intro (National Parks): text: tourists are at ease in the national parks, ( swept up in the beauty of their natural splendor ). *** Essay Intro (D.C. Statehood): washington, d.c. is a city of outsize significance, ( ground zero for the nation's political life / center stage for the nation's political machinations ). ``` ``` topic: the Golden State Warriors. characterization 1: the reigning kings of the NBA. characterization 2: possessed of a remarkable cohesion. characterization 3: helmed by superstar Stephen Curry. characterization 4: perched atop the league’s hierarchy. characterization 5: boasting a litany of hall-of-famers. *** topic: emojis. characterization 1: shorthand for a digital generation. characterization 2: more versatile than words. characterization 3: the latest frontier in language. characterization 4: a form of self-expression. characterization 5: quintessentially millennial. characterization 6: reflective of a tech-centric world. *** topic: ``` ``` regular: illinois went against the census' population-loss prediction by getting more residents. VBG: defying the census' prediction of population loss, illinois experienced growth. *** regular: microsoft word’s high pricing increases the likelihood of competition. VBG: extortionately priced, microsoft word is inviting competition. *** regular: ``` ``` source: badminton should be more popular in the US. QUERY: Based on the given topic, can you develop a story outline? target: (1) games played with racquets are popular, (2) just look at tennis and ping pong, (3) but badminton underappreciated, (4) fun, fast-paced, competitive, (5) needs to be marketed more text: the sporting arena is dominated by games that are played with racquets. tennis and ping pong, in particular, are immensely popular. somewhat curiously, however, badminton is absent from this pantheon. exciting, fast-paced, and competitive, it is an underappreciated pastime. all that it lacks is more effective marketing. *** source: movies in theaters should be free. QUERY: Based on the given topic, can you develop a story outline? target: (1) movies provide vital life lessons, (2) many venues charge admission, (3) those without much money text: the lessons that movies impart are far from trivial. the vast catalogue of cinematic classics is replete with inspiring sagas of friendship, bravery, and tenacity. it is regrettable, then, that admission to theaters is not free. in their current form, the doors of this most vital of institutions are closed to those who lack the means to pay. *** source: ``` ``` in the private sector, { transparency } is vital to the business’s credibility. the { disclosure of information } can be the difference between success and failure. *** the labor market is changing, with { remote work } now the norm. this { flexible employment } allows the individual to design their own schedule. *** the { cubicle } is the locus of countless grievances. many complain that the { enclosed workspace } restricts their freedom of movement. *** ``` ``` it would be natural to assume that americans, as a people whose ancestors { immigrated to this country }, would be sympathetic to those seeking to do likewise. question: what does “do likewise” mean in the above context? (a) make the same journey (b) share in the promise of the american dream (c) start anew in the land of opportunity (d) make landfall on the united states *** in the private sector, { transparency } is vital to the business’s credibility. this orientation can be the difference between success and failure. question: what does “this orientation” mean in the above context? (a) visible business practices (b) candor with the public (c) open, honest communication (d) culture of accountability ``` ``` example: suppose you are a teacher. further suppose you want to tell an accurate telling of history. then suppose a parent takes offense. they do so in the name of name of their kid. this happens a lot. text: educators' responsibility to remain true to the historical record often clashes with the parent's desire to shelter their child from uncomfortable realities. *** example: suppose you are a student at college. now suppose you have to buy textbooks. that is going to be worth hundreds of dollars. given how much you already spend on tuition, that is going to hard cost to bear. text: the exorbitant cost of textbooks, which often reaches hundreds of dollars, imposes a sizable financial burden on the already-strapped college student. ``` ``` <Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle> *** <Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle> ``` ``` accustomed to having its name uttered ______, harvard university is weathering a rare spell of reputational tumult (a) in reverential tones (b) with great affection (c) in adulatory fashion (d) in glowing terms ``` ``` clarify: international ( {working together} / cooperation ) is called for when ( {issue go beyond lots of borders} / an issue transcends borders / a given matter has transnational implications ). ``` ``` description: when someone thinks that their view is the only right one. synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous. *** description: when you put something off. synonyms: shelve, defer, table, postpone. ``` ``` organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea. rewrite phrases: meritocratic, viability, vision rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability. ``` *Note* Of all the masking techniques, this one works the best. ``` <Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle> *** <Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle> ``` ``` essence: when someone's views are keeping within reasonable. refine: the senator's voting record is ( moderate / centrist / pragmatic / balanced / fair-minded / even-handed ). *** essence: when things are worked through in a petty way. refine: the propensity of the u.s. congress to settle every dispute by way of ( mudslinging / bickering / demagoguery / name-calling / finger-pointing / vilification ) is appalling. ``` ``` description: when someone thinks that their view is the only right one. synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous. *** description: when you put something off. synonyms: shelve, defer, table, postpone. ``` ``` organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea. rewrite phrases: meritocratic, viability, vision rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability. ``` ``` music before bedtime [makes for being able to relax] -> is a recipe for relaxation. ``` ``` [people wanting entertainment love traveling new york city] -> travelers flock to new york city in droves, drawn to its iconic entertainment scene. [cannot blame them] -> one cannot fault them [broadway so fun] -> when it is home to such thrilling fare as Broadway. ``` ``` in their ( ‖ when you are rushing because you want to get there on time ‖ / haste to arrive punctually / mad dash to be timely ), morning commuters are too rushed to whip up their own meal. *** politicians prefer to author vague plans rather than ( ‖ when you can make a plan without many unknowns ‖ / actionable policies / concrete solutions ). ``` ``` Q: What is whistleblower protection? A: Whistleblower protection is a form of legal immunity granted to employees who expose the unethical practices of their employer. Q: Why are whistleblower protections important? A: Absent whistleblower protections, employees would be deterred from exposing their employer’s wrongdoing for fear of retribution. Q: Why would an employer engage in retribution? A: An employer who has acted unethically stands to suffer severe financial and reputational damage were their transgressions to become public. To safeguard themselves from these consequences, they might seek to dissuade employees from exposing their wrongdoing. ``` ``` original: the meritocratic nature of crowdfunding [MASK] into their vision's viability. infill: the meritocratic nature of crowdfunding [gives investors idea of how successful] -> ( offers entrepreneurs a window ) into their vision's viability. ``` ``` Leadership | Lecture 17: Worker Morale What Workers Look for in Companies: • Benefits o Tuition reimbursement o Paid parental leave o 401K matching o Profit sharing o Pension plans o Free meals • Social responsibility o Environmental stewardship o Charitable contributions o Diversity • Work-life balance o Telecommuting o Paid holidays and vacation o Casual dress • Growth opportunities • Job security • Competitive compensation • Recognition o Open-door policies o Whistleblower protection o Employee-of-the-month awards o Positive performance reviews o Bonuses ``` ``` description: business keywords: for-profit, fiduciary duty, monopolistic, bottom line, return on investment, short-term thinking, capital-intensive, self-interested, risk-taking, fiduciary duty, merger, speculation, profiteering, oversight, capitalism, diversification ``` ``` 3. In this task, you are given a company name and you need to find its industry. McDonalds -- Restaurant Facebook -- Social Network IKEA -- Furniture American Express -- Credit Services Nokia -- Telecom Nintendo -- Entertainment 4. In this task, you are given a Month and you need to convert it to its corresponding season April -- Spring December -- Winter July -- Summer October -- Fall February -- Winter 5. In this task, you are given a sentence with a missing word and you need to predict the correct word. Managers should set an _____ for their employees. -- example Some people spend more than four _____ in the gym. -- hours The police were on the _____ of arresting the suspect. -- verge They were looking for _____ on how to solve the problem. -- guidance What is the _____ of the coffee? -- price 6. In this task, you are given a paragraph and you need to reorder it to make it logical. It was first proposed in 1987. The total length of the bridge is 1,828 meters. The idea of a bridge connects Hong Kong to Macau. -- The idea of bridge connecting Hong Kong and Macau was first proposed in 1987. The total length of the bridge is 1,828 meters. It is a movie about a brave and noble policeman. The film was produced by Americans. They were Kevin Lima and Chris Buck. They are directors. The movie is called Tarzan. -- Produced by Americans Kevin Lima and Chris Buck, Tarzan is a movie about a brave and noble policeman. It was first discovered in the mountains of India. The active ingredients in this plant can stimulate hair growth. The plant is called "Hair Plus." -- First discovered in the mountains of India, Hair Plus is a plant whose active ingredients can stimulate hair growth. ``` ``` trivia: What is the population of South Korea? response: 51 million. *** trivia: What is the minimum voting age in the US? response: 18. *** trivia: What are the first ten amendments of the US constitution called? response: Bill of Rights. ``` ``` ideas: in modern-day america, it is customary for the commander-in-chief to conduct regular press conferences related keywords: transparency, check and balance, sacrosanct, public accountability, adversarial, unscripted, direct access, open government, watchdog, healthy democracy, institutional integrity, right to know, direct line of communication, behind closed doors, updates, track progress, instill confidence, reassure, humanize, leadership style, day-to-day, forthcoming, demystify, ask hard questions *** ideas: i know this one guy who retired so young, attesting to how careful they were with money. related keywords: money management, resourceful, penny-pinching, live below their means, frugal, financial discipline, financial independence, conservative, long-term vision, discretionary spending, deferred gratification, preparedness, self-control, cushion ``` ``` less specific: actors and musicians should ( support democracy ). clarifies: actors and musicians should ( wield their celebrity to amplify pro-democracy messaging / marshal their considerable influence in the service of the democratic cause ). *** less specific: amid a contemporary culture that thrives on profligacy, the discipline necessary to retire early is a vanishing quality. rather than yielding to the lure of indulgence, the aspiring retiree must ( be careful ). clarifies: amid a contemporary culture that thrives on profligacy, the discipline necessary to retire early is a vanishing quality. rather than yielding to the lure of indulgence, the aspiring retiree must ( master their desires / exercise self-restraint / embrace frugality / restrain their appetite for splendor ). ``` ``` dull: clean emotional heft: spotless, immaculate, pristine *** dull: hot emotional heft: scorching, searing, blistering *** dull: happy emotional heft: euphoric ``` ``` text: {guide: vividly describe the premise of the show "seinfield"} -> set in the heart of bustling new york city, the sitcom "seinfield" follows the everyday {restrict: term that implies they get into trouble but in a comical way} -> misadventures of four neurotic friends. on any given episode, one can find them quarreling over their favorite diner's latest menu change, haggling over the division of household expenses, or contriving a scheme to spy on the apartment's newest resident. mundane as their exploits may be, they never fail to elicit a hearty laugh. {guide: mention how larry david is responsible} -> behind the show's witty, incisive dialogue lies the sharp pen of larry david, who co-created the show with jerry seinfeld. {guide: mention how larry david came up with the most recognizable lines} -> it is his genius that conjured such instantly {restrict: term that imply everybody knows them} -> recognizable quips as "no soup for you!" and "not that there's anything wrong with that!". {guide: mention how humanity should revel in having such good comedians these days} -> as this list of laugh-out-loud lines attests, the world is fortunate to ( count such a sharp comedic mind among its ranks / have such a talented humorist in its midst / have such comedic talent gracing its airwaves ). ```
[ "BEAR" ]
tomaarsen/span-marker-bert-base-ncbi-disease
tomaarsen
token-classification
[ "span-marker", "pytorch", "tensorboard", "safetensors", "token-classification", "ner", "named-entity-recognition", "en", "dataset:ncbi_disease", "license:apache-2.0", "model-index", "region:us" ]
2023-08-09T13:55:13Z
2023-08-09T16:04:52+00:00
33
6
--- datasets: - ncbi_disease language: - en library_name: span-marker license: apache-2.0 metrics: - f1 - recall - precision pipeline_tag: token-classification tags: - span-marker - token-classification - ner - named-entity-recognition widget: - text: X-Linked adrenoleukodystrophy (ALD) is a genetic disease associated with demyelination of the central nervous system, adrenal insufficiency, and accumulation of very long chain fatty acids in tissue and body fluids. example_title: Example 1 - text: Canavan disease is inherited as an autosomal recessive trait that is caused by the deficiency of aspartoacylase (ASPA). example_title: Example 2 - text: However, both models lack other frequent DM symptoms including the fibre-type dependent atrophy, myotonia, cataract and male-infertility. example_title: Example 3 model-index: - name: SpanMarker w. bert-base-cased on NCBI Disease by Tom Aarsen results: - task: type: token-classification name: Named Entity Recognition dataset: name: NCBI Disease type: ncbi_disease split: test revision: acd0e6451198d5b615c12356ab6a05fff4610920 metrics: - type: f1 value: 0.8813 name: F1 - type: precision value: 0.8661 name: Precision - type: recall value: 0.8971 name: Recall --- # SpanMarker for Disease Named Entity Recognition This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model trained on the [ncbi_disease](https://huggingface.co/datasets/ncbi_disease) dataset. In particular, this SpanMarker model uses [bert-base-cased](https://huggingface.co/bert-base-cased) as the underlying encoder. See [train.py](train.py) for the training script. ## Metrics This model achieves the following results on the testing set: - Overall Precision: 0.8661 - Overall Recall: 0.8971 - Overall F1: 0.8813 - Overall Accuracy: 0.9837 ## Labels | **Label** | **Examples** | |-----------|--------------| | DISEASE | "ataxia-telangiectasia", "T-cell leukaemia", "C5D", "neutrophilic leukocytosis", "pyogenic infection" | ## Usage To use this model for inference, first install the `span_marker` library: ```bash pip install span_marker ``` You can then run inference with this model like so: ```python from span_marker import SpanMarkerModel # Download from the 🤗 Hub model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-ncbi-disease") # Run inference entities = model.predict("Canavan disease is inherited as an autosomal recessive trait that is caused by the deficiency of aspartoacylase (ASPA).") ``` See the [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) repository for documentation and additional information on this library. ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 0.0038 | 1.41 | 300 | 0.0059 | 0.8141 | 0.8579 | 0.8354 | 0.9818 | | 0.0018 | 2.82 | 600 | 0.0054 | 0.8315 | 0.8720 | 0.8513 | 0.9840 | ### Framework versions - SpanMarker 1.2.4 - Transformers 4.31.0 - Pytorch 1.13.1+cu117 - Datasets 2.14.3 - Tokenizers 0.13.2
[ "NCBI DISEASE" ]
rcds/neg-xlm-roberta-base
rcds
token-classification
[ "transformers", "pytorch", "xlm-roberta", "token-classification", "legal", "de", "fr", "it", "en", "dataset:rcds/MultiLegalNeg", "arxiv:1911.04211", "arxiv:2309.08695", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-08-26T13:39:59Z
2023-10-25T17:58:35+00:00
33
0
--- datasets: - rcds/MultiLegalNeg language: - de - fr - it - en tags: - legal --- # Model Card for joelito/legal-swiss-longformer-base This model is based on [XLM-R-Base](https://huggingface.co/xlm-roberta-base). It was pretrained on negation scope resolution using [NegBERT](https://github.com/adityak6798/Transformers-For-Negation-and-Speculation/blob/master/Transformers_for_Negation_and_Speculation.ipynb) ([Khandelwal and Sawant 2020](https://arxiv.org/abs/1911.04211)) For training we used the [Multi Legal Neg Dataset](https://huggingface.co/datasets/rcds/MultiLegalNeg), a multilingual dataset of legal data annotated for negation cues and scopes, ConanDoyle-neg ([ Morante and Blanco. 2012](https://aclanthology.org/S12-1035/)), SFU Review ([Konstantinova et al. 2012](http://www.lrec-conf.org/proceedings/lrec2012/pdf/533_Paper.pdf)), BioScope ([Szarvas et al. 2008](https://aclanthology.org/W08-0606/)) and Dalloux ([Dalloux et al. 2020](https://clementdalloux.fr/?page_id=28)). ## Model Details ### Model Description - **Model type:** Transformer-based language model (XLM-R-base) - **Languages:** de, fr, it, en - **License:** CC BY-SA - **Finetune Task:** Negation Scope Resolution ## Uses See [LegalNegBERT](https://github.com/RamonaChristen/Multilingual_Negation_Scope_Resolution_on_Legal_Data/blob/main/LegalNegBERT) for details on the training process and how to use this model. ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. ### Training Data This model was pretrained on the [Multi Legal Neg Dataset](https://huggingface.co/datasets/rcds/MultiLegalNeg) ## Evaluation We evaluate neg-xlm-roberta-base on the test sets in the [Multi Legal Neg Dataset](https://huggingface.co/datasets/rcds/MultiLegalNeg). | \_Test Dataset | F1-score | | :------------------------- | :-------- | | fr | 92.49 | | it | 88.81 | | de (DE) | 95.66 | | de (CH) | 87.82 | | SFU Review | 88.53 | | ConanDoyle-neg | 90.47 | | BioScope | 95.59 | | Dalloux | 93.99 | #### Software pytorch, transformers. ## Citation Please cite the following preprint: ``` @misc{christen2023resolving, title={Resolving Legalese: A Multilingual Exploration of Negation Scope Resolution in Legal Documents}, author={Ramona Christen and Anastassia Shaitarova and Matthias Stürmer and Joel Niklaus}, year={2023}, eprint={2309.08695}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
[ "BIOSCOPE" ]
winninghealth/WiNGPT2-7B-Base
winninghealth
text-generation
[ "transformers", "pytorch", "qwen", "text-generation", "medical", "custom_code", "zh", "license:apache-2.0", "autotrain_compatible", "region:us" ]
2023-09-26T00:15:04Z
2023-11-07T04:04:47+00:00
33
10
--- language: - zh license: apache-2.0 pipeline_tag: text-generation tags: - medical --- ## WiNGPT2 [WiNGPT](https://github.com/winninghealth/WiNGPT2) 是一个基于GPT的医疗垂直领域大模型，旨在将专业的医学知识、医疗信息、数据融会贯通，为医疗行业提供智能化的医疗问答、诊断支持和医学知识等信息服务，提高诊疗效率和医疗服务质量。 ## 介绍 WiNGPT（卫宁健康医疗语言大模型，以下简称WiNGPT）的研发和训练工作开始于2023年1月。 3月，卫宁健康人工智能实验室已完成了WiNGPT-001可行性验证并开始内测。WiNGPT-001采用通用的GPT架构、60亿参数，实现了从预训练到微调的全过程自研。 今年5月，WiNGPT-001训练的数据量已达到9720项药品知识、 18个药品类型、7200余项疾病知识、 2800余项检查检验知识、53本书籍知识、1100余份指南文档，总训练Token数达37亿。 7月，WiNGPT升级到7B并采用最新的模型架构，新增检索式增强生成能力，同时开始了13B模型的训练和行业邀测。 9月，WiNGPT迎来最新版本迭代，推出了全新的WiNGPT2，新版本可以被轻松扩展和个性化并用于下游各种应用场景。 为了回馈开源社区我们尝试开源了WiNGPT2-7B版本。我们的初衷是希望通过更多的开源项目加速医疗语言大模型技术与行业的共同发展，最终惠及我们人类健康。 ## 特点 - 核心功能 - **医学知识问答**：可以回答关于医学、健康、疾病等方面的问题，包括但不限于症状、治疗、药物、预防、检查等。 - **自然语言理解**：理解医学术语、病历等医疗文本信息，提供关键信息抽取和归类 - **多轮对话**：可扮演各种医疗专业角色如医生与用户进行对话，根据上下文提供更加准确的答案。 - **多任务支持**：支持32项医疗任务，八大医疗场景18个子场景。 - 模型架构 - 基于Transformer的70亿参数规模大语言模型, 采用RoPE相对位置编码、SwiGLU激活函数、RMSNorm，训练采用Qwen-7b<sup>1</sup>作为基础预训练模型。 - 主要特点 - 高准确度：基于大规模医疗语料库训练，具有较高的准确率和较低的误诊可能性。 - 场景导向：针对不同的医疗场景和真实需求进行专门优化和定制，更好的服务应用落地。 - 迭代优化：持续搜集和学习最新的医学研究，不断提高模型性能和系统功能。 ## 如何使用 ### 推理 ```python from transformers import AutoModelForCausalLM, AutoTokenizer from transformers.generation import GenerationConfig model_path = "WiNGPT2-7B-Chat" tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True) model = model.eval() generation_config = GenerationConfig( num_beams=1, top_p=0.75, top_k=30, repetition_penalty=1.1, max_new_tokens=1024 ) text = 'User: WiNGPT, 你好<|endoftext|>\n Assistant: ' inputs = tokenizer.encode(text, return_tensors="pt").to(device) outputs = model.generate(inputs, generation_config=generation_config) output = tokenizer.decode(outputs[0]) response = output.replace(inputs, '') ## 输出结果：你好！今天我能为你做些什么？<|endoftext|> ``` ### 提示 WiNGPT2-7B-Chat使用了自定义的提示格式： 用户角色：User/Assistant 提示模板：User:[此处有空格]WiNGPT, 你好<|endoftext|>\n[此处有空格]Assistant:；**多轮对话**按此模板进行拼接，例如： ``` "User: WiNGPT, 你好<|endoftext|>\n Assistant:你好！今天我能为你做些什么？<|endoftext|>\n User: 你是谁？<|endoftext|>\n Assistant:" ``` 解码时推荐使用repetition_penalty=1.1 [greedy search] ### 企业服务 [13B模型平台测试(直接申请密钥)](https://wingpt.winning.com.cn/) ## 训练数据 - 数据总览 - 医疗专业数据 | 来源 | 类型 | 数量 | | ---------------- | ------ | ------------------- | | 药品说明书 | 知识库 | 15000 条 | | 多病种知识库 | 知识库 | 9720 项 | | 医疗专业书籍 | 教材 | 300 本 | | 临床路径知识库 | 知识库 | 1400 条 | | 检查检验知识 | 知识库 | 110 万条 | | 多学科临床指南 | 书籍 | 18 个科室共 1100 份 | | 医疗知识图谱 | 知识库 | 256 万三元组 | | 人工标注数据集 | 指令 | 5 万条 | | 医学资格考试试题 | 试题 | 30 万条 | | 医疗病例、报告 | 知识库 | 100 万条 | - 其他公开数据 | 来源 | 类型 | 数量 | | -------------------- | ------ | -------- | | 医学科普书籍 | 书籍 | 500 本 | | 其他多学科书籍 | 书籍 | 1000 本 | | 代码 | 指令 | 20 万条 | | 通用类试题 | 试题 | 300 万条 | | 多种自然语言处理任务 | 指令 | 90 万条 | | 互联网文本 | 互联网 | 300 万条 | | 医疗问答、对话 | 指令 | 500 万条 | - 继续预训练 - 扩充模型的医疗知识库：预训练数据+部分指令数据。 - 指令微调 - 从书籍、指南、病例、医疗报告、知识图谱等数据中自动化构建医疗指令集。 - 人工标注指令集，数据来源包括：电子病历系统、护理病历系统、PACS系统、临床科研系统、手术管理系统、公共卫生场景、医务管理场景以及工具助手场景。 - 采用 FastChat<sup>2</sup>、Self-Instruct<sup>3</sup>、Evol-Instruct<sup>4</sup> 等方案，对指令集进行扩展以及丰富指令集多样化形式。 - 数据工程 - 数据分类：根据训练阶段和任务场景进行分类。 - 数据清洗：去除无关信息，更正数据中的拼写错误，提取关键信息以及去隐私处理。 - 数据去重：采用 embedding 方法剔除重复数据。 - 数据采样：根据数据集的质量与分布需求进行有针对性的采样。 ## 模型卡 - 训练配置与参数 | 名称 | 长度 | 精度 | 学习率 | Weight_decay | Epochs | GPUs | | --------------- | ---- | ---- | ------ | ------------ | ------ | ------ | | WiNGPT2-7B-Base | 2048 | bf16 | 5e-5 | 0.05 | 3 | A100*8 | | WiNGPT2-7B-Chat | 4096 | bf16 | 5e-6 | 0.01 | 3 | A100*8 | - 分布式训练策略与参数 - deepspeed + cpu_offload + zero_stage3 - gradient_checkpointing ## 评测 - 中文基础模型评估 C-EVAL（Zero-shot/Few-shot） | | 平均 | 平均(Hard) | **STEM** | **社会科学** | **人文科学** | **其他** | | -------------------------------------------------------------------------------------------- | -------- | ---------- | -------- | ------------ | ------------ | -------- | | [bloomz-mt-176B](https://cevalbenchmark.com/static/model.html?method=bloomz-mt-176B*) | 44.3 | 30.8 | 39 | 53 | 47.7 | 42.7 | | [Chinese LLaMA-13B](https://cevalbenchmark.com/static/model.html?method=Chinese%20LLaMA-13B) | 33.3 | 27.3 | 31.6 | 37.2 | 33.6 | 32.8 | | [ChatGLM-6B*](https://cevalbenchmark.com/static/model.html?method=ChatGLM-6B*) | 38.9 | 29.2 | 33.3 | 48.3 | 41.3 | 38 | | [baichuan-7B](https://cevalbenchmark.com/static/model.html?method=baichuan-7B) | 42.8 | 31.5 | 38.2 | 52 | 46.2 | 39.3 | | [Baichuan-13B](https://cevalbenchmark.com/static/model.html?method=Baichuan-13B) | 53.6 | 36.7 | 47 | 66.8 | 57.3 | 49.8 | | [Qwen-7B](https://cevalbenchmark.com/static/model.html?method=Qwen-7B) | **59.6** | 41 | 52.8 | **74.1** | **63.1** | 55.2 | | [WiNGPT2-7B-Base](https://huggingface.co/winninghealth/WiNGPT2-7B-Base) | 57.4 | **42.7** | **53.2** | 69.7 | 55.7 | **55.4** | - 中文医疗专业评估 MedQA-MCMLE（Zero-shot） | 模型名称 | 平均 | 血液系统疾病 | 代谢、内分泌系统疾病 | 精神神经系统疾病 | 运动系统疾病 | 风湿免疫性疾病 | 儿科疾病 | 传染病、性传播疾病 | 其他疾病 | | ---------------------------------------------------------------------------- | -------- | ------------ | -------------------- | ---------------- | ------------ | -------------- | -------- | ------------------ | -------- | | [Baichuan-7B](https://huggingface.co/baichuan-inc/Baichuan-7B) | 23.1 | 25.6 | 20.2 | 25.8 | 17.9 | 26.5 | 20.6 | 26.1 | 17.1 | | [Baichuan-13B-Base](https://huggingface.co/baichuan-inc/Baichuan-13B-Base) | 37.2 | 34.4 | 36.2 | 40.7 | 38.4 | 57.1 | 31.6 | 30.8 | 34.3 | | [Baichuan2-7B-Base](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base) | 46.4 | 46.9 | 41.4 | 53.8 | 48.3 | 50.0 | 38.6 | 52.7 | 42.9 | | [Baichuan2-13B-Base](https://huggingface.co/baichuan-inc/Baichuan2-13B-Base) | 62.9 | 68.8 | 64.4 | 69.7 | 64.9 | 60.3 | 50.9 | 61.2 | 62.9 | | [HuatuoGPT-7B](https://huggingface.co/FreedomIntelligence/HuatuoGPT-7B) | 22.9 | 14.6 | 17.2 | 31.2 | 25.8 | 14.3 | 22.4 | 23.1 | 17.1 | | [MedicalGPT](https://huggingface.co/shibing624/vicuna-baichuan-13b-chat) | 17.9 | 21.9 | 15.5 | 19.5 | 9.3 | 7.1 | 16.7 | 20.9 | 9.5 | | [qwen-7b-Base](https://huggingface.co/Qwen/Qwen-7B) | 59.3 | 55.2 | 56.9 | 57.0 | 60.9 | 60.3 | 50.4 | 60.4 | 61.0 | | [WiNGPT2-7B-Base](https://huggingface.co/winninghealth/WiNGPT2-7B-Base) | **82.3** | **83.3** | **82.8** | **86.0** | **81.5** | **85.7** | **75.1** | **78.0** | **80** | ** 目前公开测评存在一定局限性，结果仅供参考； ** 更多专业测评敬请期待。 ## 局限性与免责声明 (a) WiNGPT2 是一个专业医疗领域的大语言模型，可为一般用户提供拟人化AI医生问诊和问答功能，以及一般医学领域的知识问答。对于专业医疗人士，WiNGPT2 提供关于患者病情的诊断、用药和健康建议等方面的回答的建议仅供参考。 (b) 您应理解 WiNGPT2 仅提供信息和建议，不能替代医疗专业人士的意见、诊断或治疗建议。在使用 WiNGPT2 的信息之前，请寻求医生或其他医疗专业人员的建议，并独立评估所提供的信息。 (c) WiNGPT2 的信息可能存在错误或不准确。卫宁健康不对 WiNGPT2 的准确性、可靠性、完整性、质量、安全性、及时性、性能或适用性提供任何明示或暗示的保证。使用 WiNGPT2 所产生的结果和决策由您自行承担。第三方原因而给您造成的损害结果承担责任。 ## 许可证 1. 本项目授权协议为 Apache License 2.0，模型权重需要遵守基础模型[Qwen-7B](https://github.com/QwenLM/Qwen-7B)相关协议及[许可证](https://github.com/QwenLM/Qwen-7B/blob/main/LICENSE)，详细内容参照其网站。 2. 使用本项目包括模型权重时请引用本项目：https://github.com/winninghealth/WiNGPT2 ## 参考资料 1. https://github.com/QwenLM/Qwen-7B 2. https://github.com/lm-sys/FastChat 3. https://github.com/yizhongw/self-instruct 4. https://github.com/nlpxucan/evol-instruct ## 联系我们 网站：https://www.winning.com.cn 邮箱：[email protected]
[ "MEDQA" ]
lomahony/pythia-70m-helpful-sft
lomahony
text-generation
[ "transformers", "pytorch", "safetensors", "gpt_neox", "text-generation", "causal-lm", "pythia", "en", "dataset:Anthropic/hh-rlhf", "arxiv:2101.00027", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2023-11-08T15:28:53Z
2025-01-20T05:39:42+00:00
33
0
--- datasets: - Anthropic/hh-rlhf language: - en license: apache-2.0 tags: - pytorch - causal-lm - pythia --- [Pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) supervised finetuned using TRLx library with the helpful subset of [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch. Checkpoints are also uploaded. Fully reproducible finetuning code is available on [GitHub](https://github.com/lauraaisling/trlx-pythia/tree/main) [wandb log](https://wandb.ai/lauraomahony999/pythia-sft/runs/3w7e3zmd) See [Pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) for model details [(paper)](https://arxiv.org/abs/2101.00027). See further details of these models in the paper [Attributing Mode Collapse in the Fine-Tuning of Large Language Models](https://openreview.net/pdf?id=3pDMYjpOxk). You can cite these models if they are helpful as follows: <pre> @inproceedings{o2024attributing, title={Attributing Mode Collapse in the Fine-Tuning of Large Language Models}, author={O’Mahony, Laura and Grinsztajn, Leo and Schoelkopf, Hailey and Biderman, Stella}, booktitle={ICLR 2024, Mathematical and Empirical Understanding of Foundation Models (ME-FoMo) workshop}, year={2024} } </pre> hf (pretrained=lomahony/pythia-70m-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16 | Tasks |Version|Filter|n-shot| Metric | Value | | Stderr | |--------------|------:|------|-----:|---------------|--------:|---|--------| |arc_challenge | 1|none | 0|acc | 0.1715|± | 0.0110| | | |none | 0|acc_norm | 0.2082|± | 0.0119| |arc_easy | 1|none | 0|acc | 0.3384|± | 0.0097| | | |none | 0|acc_norm | 0.3262|± | 0.0096| |boolq | 2|none | 0|acc | 0.4239|± | 0.0086| |hellaswag | 1|none | 0|acc | 0.2629|± | 0.0044| | | |none | 0|acc_norm | 0.2691|± | 0.0044| |lambada_openai| 1|none | 0|perplexity |5937.7964|± |424.7555| | | |none | 0|acc | 0.0328|± | 0.0025| |openbookqa | 1|none | 0|acc | 0.1580|± | 0.0163| | | |none | 0|acc_norm | 0.2520|± | 0.0194| |piqa | 1|none | 0|acc | 0.5593|± | 0.0116| | | |none | 0|acc_norm | 0.5392|± | 0.0116| |sciq | 1|none | 0|acc | 0.3710|± | 0.0153| | | |none | 0|acc_norm | 0.4990|± | 0.0158| |wikitext | 2|none | 0|word_perplexity| 550.5954|± |N/A | | | |none | 0|byte_perplexity| 3.2550|± |N/A | | | |none | 0|bits_per_byte | 1.7027|± |N/A | |winogrande | 1|none | 0|acc | 0.4878|± | 0.0140| hf (pretrained=lomahony/pythia-70m-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16 | Tasks |Version|Filter|n-shot| Metric | Value | | Stderr | |--------------|------:|------|-----:|---------------|---------:|---|---------| |arc_challenge | 1|none | 5|acc | 0.1869|± | 0.0114| | | |none | 5|acc_norm | 0.2210|± | 0.0121| |arc_easy | 1|none | 5|acc | 0.3207|± | 0.0096| | | |none | 5|acc_norm | 0.3245|± | 0.0096| |boolq | 2|none | 5|acc | 0.4159|± | 0.0086| |hellaswag | 1|none | 5|acc | 0.2633|± | 0.0044| | | |none | 5|acc_norm | 0.2596|± | 0.0044| |lambada_openai| 1|none | 5|perplexity |19968.0749|± |1423.3001| | | |none | 5|acc | 0.0202|± | 0.0020| |openbookqa | 1|none | 5|acc | 0.1440|± | 0.0157| | | |none | 5|acc_norm | 0.2420|± | 0.0192| |piqa | 1|none | 5|acc | 0.5359|± | 0.0116| | | |none | 5|acc_norm | 0.5229|± | 0.0117| |sciq | 1|none | 5|acc | 0.3240|± | 0.0148| | | |none | 5|acc_norm | 0.4310|± | 0.0157| |wikitext | 2|none | 5|word_perplexity| 550.5954|± |N/A | | | |none | 5|byte_perplexity| 3.2550|± |N/A | | | |none | 5|bits_per_byte | 1.7027|± |N/A | |winogrande | 1|none | 5|acc | 0.5154|± | 0.0140|
[ "SCIQ" ]
ntc-ai/SDXL-LoRA-slider.celestial
ntc-ai
text-to-image
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
2024-01-05T08:05:54Z
2024-01-05T08:05:57+00:00
33
1
--- base_model: stabilityai/stable-diffusion-xl-base-1.0 language: - en license: mit tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers thumbnail: images/evaluate/celestial.../celestial_17_3.0.png widget: - text: celestial output: url: images/celestial_17_3.0.png - text: celestial output: url: images/celestial_19_3.0.png - text: celestial output: url: images/celestial_20_3.0.png - text: celestial output: url: images/celestial_21_3.0.png - text: celestial output: url: images/celestial_22_3.0.png inference: false instance_prompt: celestial --- # ntcai.xyz slider - celestial (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/celestial_17_-3.0.png" width=256 height=256 /> | <img src="images/celestial_17_0.0.png" width=256 height=256 /> | <img src="images/celestial_17_3.0.png" width=256 height=256 /> | | <img src="images/celestial_19_-3.0.png" width=256 height=256 /> | <img src="images/celestial_19_0.0.png" width=256 height=256 /> | <img src="images/celestial_19_3.0.png" width=256 height=256 /> | | <img src="images/celestial_20_-3.0.png" width=256 height=256 /> | <img src="images/celestial_20_0.0.png" width=256 height=256 /> | <img src="images/celestial_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` celestial ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.celestial', weight_name='celestial.safetensors', adapter_name="celestial") # Activate the LoRA pipe.set_adapters(["celestial"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, celestial" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 880+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
[ "CRAFT" ]
LoneStriker/OpenBioLLM-Llama3-70B-GGUF
LoneStriker
null
[ "gguf", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "base_model:quantized:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "endpoints_compatible", "region:us", "conversational" ]
2024-04-26T20:56:57Z
2024-04-26T22:23:12+00:00
33
1
--- base_model: meta-llama/Meta-Llama-3-70B-Instruct language: - en license: llama3 tags: - llama-3 - llama - Mixtral - instruct - finetune - chatml - DPO - RLHF - gpt4 - distillation widget: - example_title: OpenBioLLM-70B messages: - role: system content: You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. - role: user content: How long does it take for newborn jaundice to go away? output: text: 'Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment. The duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines: 1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment. It''s important for parents to monitor their newborn''s jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn''s jaundice, it''s always best to consult with a healthcare professional for personalized advice and guidance.' model-index: - name: OpenBioLLM-70B results: [] --- <div align="center"> <img width="260px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 70 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!**  While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)
[ "MEDQA", "PUBMEDQA" ]
RichardErkhov/Technoculture_-_Medorca-4x7b-gguf
RichardErkhov
null
[ "gguf", "endpoints_compatible", "region:us" ]
2024-05-12T05:34:14Z
2024-05-12T10:39:07+00:00
33
0
--- {} --- Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Medorca-4x7b - GGUF - Model creator: https://huggingface.co/Technoculture/ - Original model: https://huggingface.co/Technoculture/Medorca-4x7b/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Medorca-4x7b.Q2_K.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q2_K.gguf) | Q2_K | 6.74GB | | [Medorca-4x7b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.IQ3_XS.gguf) | IQ3_XS | 7.52GB | | [Medorca-4x7b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.IQ3_S.gguf) | IQ3_S | 7.94GB | | [Medorca-4x7b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q3_K_S.gguf) | Q3_K_S | 7.94GB | | [Medorca-4x7b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.IQ3_M.gguf) | IQ3_M | 8.17GB | | [Medorca-4x7b.Q3_K.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q3_K.gguf) | Q3_K | 8.84GB | | [Medorca-4x7b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q3_K_M.gguf) | Q3_K_M | 8.84GB | | [Medorca-4x7b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q3_K_L.gguf) | Q3_K_L | 9.59GB | | [Medorca-4x7b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.IQ4_XS.gguf) | IQ4_XS | 9.9GB | | [Medorca-4x7b.Q4_0.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q4_0.gguf) | Q4_0 | 10.37GB | | [Medorca-4x7b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.IQ4_NL.gguf) | IQ4_NL | 10.45GB | | [Medorca-4x7b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q4_K_S.gguf) | Q4_K_S | 10.46GB | | [Medorca-4x7b.Q4_K.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q4_K.gguf) | Q4_K | 11.12GB | | [Medorca-4x7b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q4_K_M.gguf) | Q4_K_M | 11.12GB | | [Medorca-4x7b.Q4_1.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q4_1.gguf) | Q4_1 | 11.51GB | | [Medorca-4x7b.Q5_0.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q5_0.gguf) | Q5_0 | 12.65GB | | [Medorca-4x7b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q5_K_S.gguf) | Q5_K_S | 12.65GB | | [Medorca-4x7b.Q5_K.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q5_K.gguf) | Q5_K | 13.04GB | | [Medorca-4x7b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q5_K_M.gguf) | Q5_K_M | 13.04GB | | [Medorca-4x7b.Q5_1.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q5_1.gguf) | Q5_1 | 13.79GB | | [Medorca-4x7b.Q6_K.gguf](https://huggingface.co/RichardErkhov/Technoculture_-_Medorca-4x7b-gguf/blob/main/Medorca-4x7b.Q6_K.gguf) | Q6_K | 15.07GB | Original model description: --- license: apache-2.0 tags: - moe - merge - epfl-llm/meditron-7b - medalpaca/medalpaca-7b - chaoyi-wu/PMC_LLAMA_7B_10_epoch - microsoft/Orca-2-7b --- # Medorca-4x7b Mediquad-orca-20B is a Mixure of Experts (MoE) made with the following models: * [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) * [medalpaca/medalpaca-7b](https://huggingface.co/medalpaca/medalpaca-7b) * [chaoyi-wu/PMC_LLAMA_7B_10_epoch](https://huggingface.co/chaoyi-wu/PMC_LLAMA_7B_10_epoch) * [microsoft/Orca-2-7b](https://huggingface.co/microsoft/Orca-2-7b) ## Evaluations [open_llm_leaderboard](https://huggingface.co/datasets/open-llm-leaderboard/details_Technoculture__Mediquad-orca-20B) | Benchmark | Medorca-4x7b | Orca-2-7b | meditron-7b | meditron-70b | | --- | --- | --- | --- | --- | | MedMCQA | | | | | | ClosedPubMedQA | | | | | | PubMedQA | | | | | | MedQA | | | | | | MedQA4 | | | | | | MedicationQA | | | | | | MMLU Medical | | | | | | MMLU | 24.28 | 56.37 | | | | TruthfulQA | 48.42 | 52.45 | | | | GSM8K | 0 | 47.2 | | | | ARC | 29.35 | 54.1 | | | | HellaSwag | 25.72 | 76.19 | | | | Winogrande | 48.3 | 73.48 | | | ## 🧩 Configuration ```yamlbase_model: microsoft/Orca-2-7b gate_mode: hidden dtype: bfloat16 experts: - source_model: epfl-llm/meditron-7b positive_prompts: - "How does sleep affect cardiovascular health?" - "When discussing diabetes management, the key factors to consider are" - "The differential diagnosis for a headache with visual aura could include" negative_prompts: - "What are the environmental impacts of deforestation?" - "The recent advancements in artificial intelligence have led to developments in" - source_model: medalpaca/medalpaca-7b positive_prompts: - "When discussing diabetes management, the key factors to consider are" - "The differential diagnosis for a headache with visual aura could include" negative_prompts: - "Recommend a good recipe for a vegetarian lasagna." - "The fundamental concepts in economics include ideas like supply and demand, which explain" - source_model: chaoyi-wu/PMC_LLAMA_7B_10_epoch positive_prompts: - "How does sleep affect cardiovascular health?" - "When discussing diabetes management, the key factors to consider are" negative_prompts: - "Recommend a good recipe for a vegetarian lasagna." - "The recent advancements in artificial intelligence have led to developments in" - "The fundamental concepts in economics include ideas like supply and demand, which explain" - source_model: microsoft/Orca-2-7b positive_prompts: - "Here is a funny joke for you -" - "When considering the ethical implications of artificial intelligence, one must take into account" - "In strategic planning, a company must analyze its strengths and weaknesses, which involves" - "Understanding consumer behavior in marketing requires considering factors like" - "The debate on climate change solutions hinges on arguments that" negative_prompts: - "In discussing dietary adjustments for managing hypertension, it's crucial to emphasize" - "For early detection of melanoma, dermatologists recommend that patients regularly check their skin for" - "Explaining the importance of vaccination, a healthcare professional should highlight" ``` ## 💻 Usage ```python !pip install -qU transformers bitsandbytes accelerate from transformers import AutoTokenizer import transformers import torch model = "Technoculture/Mediquad-orca-20B" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True}, ) messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}] prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
[ "MEDQA", "PUBMEDQA" ]
bobox/DeBERTaV3-small-GeneralSentenceTransformer-v2-checkpoints-tmp
bobox
sentence-similarity
[ "sentence-transformers", "pytorch", "tensorboard", "deberta-v2", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:526885", "loss:GISTEmbedLoss", "loss:CoSENTLoss", "loss:OnlineContrastiveLoss", "loss:MultipleNegativesSymmetricRankingLoss", "loss:MarginMSELoss", "en", "dataset:sentence-transformers/all-nli", "dataset:sentence-transformers/stsb", "dataset:tals/vitaminc", "dataset:nyu-mll/glue", "dataset:allenai/scitail", "dataset:sentence-transformers/xsum", "dataset:sentence-transformers/sentence-compression", "dataset:allenai/sciq", "dataset:allenai/qasc", "dataset:allenai/openbookqa", "dataset:sentence-transformers/natural-questions", "dataset:sentence-transformers/trivia-qa", "dataset:sentence-transformers/quora-duplicates", "dataset:sentence-transformers/gooaq", "arxiv:1908.10084", "arxiv:2402.16829", "arxiv:2010.02666", "base_model:microsoft/deberta-v3-small", "base_model:finetune:microsoft/deberta-v3-small", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-06-15T18:21:17Z
2024-06-20T16:28:33+00:00
33
0
--- base_model: microsoft/deberta-v3-small datasets: - sentence-transformers/all-nli - sentence-transformers/stsb - tals/vitaminc - nyu-mll/glue - allenai/scitail - sentence-transformers/xsum - sentence-transformers/sentence-compression - allenai/sciq - allenai/qasc - allenai/openbookqa - sentence-transformers/natural-questions - sentence-transformers/trivia-qa - sentence-transformers/quora-duplicates - sentence-transformers/gooaq language: - en library_name: sentence-transformers metrics: - pearson_cosine - spearman_cosine - pearson_manhattan - spearman_manhattan - pearson_euclidean - spearman_euclidean - pearson_dot - spearman_dot - pearson_max - spearman_max pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:526885 - loss:GISTEmbedLoss - loss:CoSENTLoss - loss:OnlineContrastiveLoss - loss:MultipleNegativesSymmetricRankingLoss - loss:MarginMSELoss widget: - source_sentence: A man in a Santa Claus costume is sitting on a wooden chair holding a microphone and a stringed instrument. sentences: - The man is is near the ball. - The man is wearing a costume. - People are having a picnic. - source_sentence: A street vendor selling his art. sentences: - A man is selling things on the street. - A woman is walking outside. - A clown is talking into a microphone. - source_sentence: A boy looks surly as his father looks at the camera. sentences: - a boy looks at his farther - A dark-haired girl in a spotted shirt is pointing at the picture while sitting next to a boy wearing a purple shirt and jeans. - Man and woman stop and chat with each other. - source_sentence: Which company provided streetcar connections between downtown and the hospital? sentences: - In 1914 developers Billings & Meyering acquired the tract, completed street development, provided the last of the necessary municipal improvements including water service, and began marketing the property with fervor. - The war was fought primarily along the frontiers between New France and the British colonies, from Virginia in the South to Nova Scotia in the North. - 'On the basis of CST, Burnet developed a theory of how an immune response is triggered according to the self/nonself distinction: "self" constituents (constituents of the body) do not trigger destructive immune responses, while "nonself" entities (pathogens, an allograft) trigger a destructive immune response.' - source_sentence: What language did Tesla study while in school? sentences: - Because of the complexity of medications including specific indications, effectiveness of treatment regimens, safety of medications (i.e., drug interactions) and patient compliance issues (in the hospital and at home) many pharmacists practicing in hospitals gain more education and training after pharmacy school through a pharmacy practice residency and sometimes followed by another residency in a specific area. - Rev. Jimmy Creech was defrocked after a highly publicized church trial in 1999 on account of his participation in same-sex union ceremonies. - Tesla was the fourth of five children. model-index: - name: SentenceTransformer based on microsoft/deberta-v3-small results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: sts test type: sts-test metrics: - type: pearson_cosine value: 0.2520910673470529 name: Pearson Cosine - type: spearman_cosine value: 0.2588662067006675 name: Spearman Cosine - type: pearson_manhattan value: 0.30439718484055006 name: Pearson Manhattan - type: spearman_manhattan value: 0.3013780326567434 name: Spearman Manhattan - type: pearson_euclidean value: 0.25977707672353506 name: Pearson Euclidean - type: spearman_euclidean value: 0.26078444276128726 name: Spearman Euclidean - type: pearson_dot value: 0.08121075567918108 name: Pearson Dot - type: spearman_dot value: 0.0753891417253212 name: Spearman Dot - type: pearson_max value: 0.30439718484055006 name: Pearson Max - type: spearman_max value: 0.3013780326567434 name: Spearman Max - type: pearson_cosine value: 0.2520910673470529 name: Pearson Cosine - type: spearman_cosine value: 0.2588662067006675 name: Spearman Cosine - type: pearson_manhattan value: 0.30439718484055006 name: Pearson Manhattan - type: spearman_manhattan value: 0.3013780326567434 name: Spearman Manhattan - type: pearson_euclidean value: 0.25977707672353506 name: Pearson Euclidean - type: spearman_euclidean value: 0.26078444276128726 name: Spearman Euclidean - type: pearson_dot value: 0.08121075567918108 name: Pearson Dot - type: spearman_dot value: 0.0753891417253212 name: Spearman Dot - type: pearson_max value: 0.30439718484055006 name: Pearson Max - type: spearman_max value: 0.3013780326567434 name: Spearman Max - type: pearson_cosine value: 0.7933255500721913 name: Pearson Cosine - type: spearman_cosine value: 0.7974636940357042 name: Spearman Cosine - type: pearson_manhattan value: 0.7981019600081939 name: Pearson Manhattan - type: spearman_manhattan value: 0.7881373354371464 name: Spearman Manhattan - type: pearson_euclidean value: 0.7953389212549029 name: Pearson Euclidean - type: spearman_euclidean value: 0.785471057378488 name: Spearman Euclidean - type: pearson_dot value: 0.7742724036105891 name: Pearson Dot - type: spearman_dot value: 0.7646982940473647 name: Spearman Dot - type: pearson_max value: 0.7981019600081939 name: Pearson Max - type: spearman_max value: 0.7974636940357042 name: Spearman Max --- # SentenceTransformer based on microsoft/deberta-v3-small This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the [nli-pairs](https://huggingface.co/datasets/sentence-transformers/all-nli), [sts-label](https://huggingface.co/datasets/sentence-transformers/stsb), [vitaminc-pairs](https://huggingface.co/datasets/tals/vitaminc), [qnli-contrastive](https://huggingface.co/datasets/nyu-mll/glue), [scitail-pairs-qa](https://huggingface.co/datasets/allenai/scitail), [scitail-pairs-pos](https://huggingface.co/datasets/allenai/scitail), [xsum-pairs](https://huggingface.co/datasets/sentence-transformers/xsum), [compression-pairs](https://huggingface.co/datasets/sentence-transformers/sentence-compression), [sciq_pairs](https://huggingface.co/datasets/allenai/sciq), [qasc_pairs](https://huggingface.co/datasets/allenai/qasc), [openbookqa_pairs](https://huggingface.co/datasets/allenai/openbookqa), msmarco_pairs, [nq_pairs](https://huggingface.co/datasets/sentence-transformers/natural-questions), [trivia_pairs](https://huggingface.co/datasets/sentence-transformers/trivia-qa), [quora_pairs](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) and [gooaq_pairs](https://huggingface.co/datasets/sentence-transformers/gooaq) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) <!-- at revision a36c739020e01763fe789b4b85e2df55d6180012 --> - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Training Datasets:** - [nli-pairs](https://huggingface.co/datasets/sentence-transformers/all-nli) - [sts-label](https://huggingface.co/datasets/sentence-transformers/stsb) - [vitaminc-pairs](https://huggingface.co/datasets/tals/vitaminc) - [qnli-contrastive](https://huggingface.co/datasets/nyu-mll/glue) - [scitail-pairs-qa](https://huggingface.co/datasets/allenai/scitail) - [scitail-pairs-pos](https://huggingface.co/datasets/allenai/scitail) - [xsum-pairs](https://huggingface.co/datasets/sentence-transformers/xsum) - [compression-pairs](https://huggingface.co/datasets/sentence-transformers/sentence-compression) - [sciq_pairs](https://huggingface.co/datasets/allenai/sciq) - [qasc_pairs](https://huggingface.co/datasets/allenai/qasc) - [openbookqa_pairs](https://huggingface.co/datasets/allenai/openbookqa) - msmarco_pairs - [nq_pairs](https://huggingface.co/datasets/sentence-transformers/natural-questions) - [trivia_pairs](https://huggingface.co/datasets/sentence-transformers/trivia-qa) - [quora_pairs](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) - [gooaq_pairs](https://huggingface.co/datasets/sentence-transformers/gooaq) - **Language:** en <!-- - **License:** Unknown --> ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("bobox/DeBERTaV3-small-GeneralSentenceTransformer-v2-checkpoints-tmp") # Run inference sentences = [ 'What language did Tesla study while in school?', 'Tesla was the fourth of five children.', 'Rev. Jimmy Creech was defrocked after a highly publicized church trial in 1999 on account of his participation in same-sex union ceremonies.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> ## Evaluation ### Metrics #### Semantic Similarity * Dataset: `sts-test` * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.2521 | | **spearman_cosine** | **0.2589** | | pearson_manhattan | 0.3044 | | spearman_manhattan | 0.3014 | | pearson_euclidean | 0.2598 | | spearman_euclidean | 0.2608 | | pearson_dot | 0.0812 | | spearman_dot | 0.0754 | | pearson_max | 0.3044 | | spearman_max | 0.3014 | #### Semantic Similarity * Dataset: `sts-test` * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.2521 | | **spearman_cosine** | **0.2589** | | pearson_manhattan | 0.3044 | | spearman_manhattan | 0.3014 | | pearson_euclidean | 0.2598 | | spearman_euclidean | 0.2608 | | pearson_dot | 0.0812 | | spearman_dot | 0.0754 | | pearson_max | 0.3044 | | spearman_max | 0.3014 | #### Semantic Similarity * Dataset: `sts-test` * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.7933 | | **spearman_cosine** | **0.7975** | | pearson_manhattan | 0.7981 | | spearman_manhattan | 0.7881 | | pearson_euclidean | 0.7953 | | spearman_euclidean | 0.7855 | | pearson_dot | 0.7743 | | spearman_dot | 0.7647 | | pearson_max | 0.7981 | | spearman_max | 0.7975 | <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Training Datasets #### nli-pairs * Dataset: [nli-pairs](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab) * Size: 50,000 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 5 tokens</li><li>mean: 16.62 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.46 tokens</li><li>max: 29 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:---------------------------------------------------------------------------|:-------------------------------------------------| | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | | <code>Children smiling and waving at camera</code> | <code>There are children present</code> | | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### sts-label * Dataset: [sts-label](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308) * Size: 5,749 training samples * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | score | |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | <ul><li>min: 6 tokens</li><li>mean: 9.81 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 9.74 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> | * Samples: | sentence1 | sentence2 | score | |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------| | <code>A plane is taking off.</code> | <code>An air plane is taking off.</code> | <code>1.0</code> | | <code>A man is playing a large flute.</code> | <code>A man is playing a flute.</code> | <code>0.76</code> | | <code>A man is spreading shreded cheese on a pizza.</code> | <code>A man is spreading shredded cheese on an uncooked pizza.</code> | <code>0.76</code> | * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "pairwise_cos_sim" } ``` #### vitaminc-pairs * Dataset: [vitaminc-pairs](https://huggingface.co/datasets/tals/vitaminc) at [be6febb](https://huggingface.co/datasets/tals/vitaminc/tree/be6febb761b0b2807687e61e0b5282e459df2fa0) * Size: 24,996 training samples * Columns: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | label | sentence1 | sentence2 | |:--------|:-----------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | int | string | string | | details | <ul><li>1: 100.00%</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.65 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 36.9 tokens</li><li>max: 161 tokens</li></ul> | * Samples: | label | sentence1 | sentence2 | |:---------------|:-----------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>1</code> | <code>Linkin Park sold more than 30 million singles and 130 million records worldwide .</code> | <code>Linkin Park has sold over 100 million albums and 31 million singles worldwide , making a total of over 131 million records sold worldwide with 32,000,000 albums and 33,000,000 singles sold in the US as of June 2017 .</code> | | <code>1</code> | <code>Anibal Sanchez has played for the Atlanta Braves .</code> | <code>He has played in Major League Baseball ( MLB ) for the Florida/Miami Marlins , Detroit Tigers and Atlanta Braves .</code> | | <code>1</code> | <code>Frankenweenie has under 37 reviews on Metacritic , and a score above 74 .</code> | <code>Metacritic , which assigns a weighted average score out of 100 to reviews from mainstream critics , gives the film a score of 75 based on 35 reviews .</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### qnli-contrastive * Dataset: [qnli-contrastive](https://huggingface.co/datasets/nyu-mll/glue) at [bcdcba7](https://huggingface.co/datasets/nyu-mll/glue/tree/bcdcba79d07bc864c1c254ccfcedcce55bcc9a8c) * Size: 50,000 training samples * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------| | type | string | string | int | | details | <ul><li>min: 6 tokens</li><li>mean: 13.54 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 35.96 tokens</li><li>max: 136 tokens</li></ul> | <ul><li>0: 100.00%</li></ul> | * Samples: | sentence1 | sentence2 | label | |:----------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------| | <code>By what means did the British govern Tuvalu?</code> | <code>The Ellice Islands were administered as British protectorate by a Resident Commissioner from 1892 to 1916 as part of the British Western Pacific Territories (BWPT), and then as part of the Gilbert and Ellice Islands colony from 1916 to 1974.</code> | <code>0</code> | | <code>Who is the current head of BBC Television?</code> | <code>As a division within the BBC, Television was formerly known as BBC Vision for a few years in the early 21st century, until its name reverted to Television in 2013.</code> | <code>0</code> | | <code>What was the PLDA formerly known as?</code> | <code>The Professional Lighting Designers Association (PLDA), formerly known as ELDA is an organisation focusing on the promotion of the profession of Architectural Lighting Design.</code> | <code>0</code> | * Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) #### scitail-pairs-qa * Dataset: [scitail-pairs-qa](https://huggingface.co/datasets/allenai/scitail) at [0cc4353](https://huggingface.co/datasets/allenai/scitail/tree/0cc4353235b289165dfde1c7c5d1be983f99ce44) * Size: 14,987 training samples * Columns: <code>sentence2</code> and <code>sentence1</code> * Approximate statistics based on the first 1000 samples: | | sentence2 | sentence1 | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 7 tokens</li><li>mean: 15.63 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.73 tokens</li><li>max: 41 tokens</li></ul> | * Samples: | sentence2 | sentence1 | |:----------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------| | <code>People stopped adding lead to gasoline because of environmental pollution.</code> | <code>Why did people stop adding lead to gasoline?</code> | | <code>The pleura that surrounds the lungs consists of two layers.</code> | <code>The pleura that surrounds the lungs consists of how many layers?</code> | | <code>Thermal energy constitutes the total kinetic energy of all the atoms that make up an object.</code> | <code>What kind of energy constitutes the total kinetic energy of all the atoms that make up an object?</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### scitail-pairs-pos * Dataset: [scitail-pairs-pos](https://huggingface.co/datasets/allenai/scitail) at [0cc4353](https://huggingface.co/datasets/allenai/scitail/tree/0cc4353235b289165dfde1c7c5d1be983f99ce44) * Size: 8,600 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 8 tokens</li><li>mean: 24.02 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.66 tokens</li><li>max: 39 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------| | <code>TELEPHONE (818) 354-5011 PHOTO CAPTION P-23254 C & BW S-1-62 Dec. 4, 1980 Voyager 1 looked back at Saturn on Nov. 16, 1980, four days after the spacecraft flew past the planet, to observe the appearance of Saturn and its rings from this unique perspective.</code> | <code>The voyager 1 spacecraft visited saturn in 1980.</code> | | <code>atoms may share one pair of electrons (single bonds), two pairs (double bonds), or three pairs (triple bonds).</code> | <code>In a carbon triple bond, three pairs of electrons are shared.</code> | | <code>One gram of protein contains four calories.</code> | <code>One gram of proteins provides four calories of energy.</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### xsum-pairs * Dataset: [xsum-pairs](https://huggingface.co/datasets/sentence-transformers/xsum) at [788ddaf](https://huggingface.co/datasets/sentence-transformers/xsum/tree/788ddafe04e539956d56b567bc32a036ee7b9206) * Size: 50,000 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 2 tokens</li><li>mean: 351.25 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 26.7 tokens</li><li>max: 59 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>Bivsi Rana, 15, was born in Germany to Nepalese parents. In May she was deported with the rest of her family.<br>Her classmates protested and lobbied on her behalf against the deportation, drawing hundreds of people to rally under the slogan "Bring Bivsi back".<br>Officials called it a "unique case" and said Bivsi was "de facto German".<br>Mayor of Duisburg Sören Link said: "The fact that we have managed to resolve this difficult situation lifts a burden from my shoulders."<br>Bivsi's parents moved to Germany in 1998, fleeing civil conflict in their native Nepal, but their applications for asylum were denied. Their repeated appeals were rejected. Fearing political repercussions at home Bivsi's father, Mr Rana, initially applied for asylum under a false name and has since called this "the worst mistake" of his life.<br>But Bivsi herself was born and brought up in Germany.<br>On the last Monday in May, Bivsi was in class at school in Duisburg, in north west Germany, when she was told she had to pack her things and leave. That same day she and her family were deported to Nepal, a country Bivsi had never visited before.<br>Class teacher Sascha Thamm told German media afterwards that all the girls in the class cried and Bivsi's best friend broke down to the extent that an emergency doctor had to be called.<br>Mr Thamm said Bivsi was a kind, engaged student who was good at German and science and helped teach swimming lessons.<br>Bivsi has been living in Nepal with her family and, according to reports, has been unable to find a new school there due to language issues.<br>She has now been given a study visa enabling her to return Germany while she finishes her education. Her parents can return with her.<br>North-Rhine Westphalia state's integration minister Joachim Stamp said: "This is a unique case and generalisations cannot be drawn from it.<br>"The right of the child stood in the foreground in this decision.<br>"Bivsi was born in Germany and grew up here - she is de facto a German child."<br>Bivsi is reported to be "totally happy" with the decision, and her parents are reported to be "overjoyed".</code> | <code>A teenager who was removed from her classroom and deported to Nepal has been allowed to return to Germany on a study visa.</code> | | <code>It was bought by an individual from the Dorset area in a phone bid.<br>A piece of paper found with the hair said "A single hair of Napoleon Bonaparte's head 29th August 1816" and "5th May 1821' - the date Napoleon died.<br>The strand of hair was attached to a piece of paper by red sealing wax.<br>Auctioneer Max Beaumont, of Cottees Auction House, Wareham, said it was found in a drawer by a colleague doing a home valuation.<br>He said they found a small goldsmith's box and expected to find a watch, but instead they found the folded paper.<br>The hair is understood to have been owned by the family for the whole of the 20th Century, but has not been professionally analysed.<br>The initial estimate was £100 to £200.<br>Mr Beaumont, who at 19 claims to be one of the youngest auctioneers in the country, said: "There has been a lot of interest."<br>Napoleon Bonaparte was a French emperor who conquered much of Europe. He was defeated in the Battle of Waterloo and imprisoned by the British on the remote Atlantic island of St Helena, where he died on 5 May 1821.</code> | <code>A strand of hair believed to be from the head of former French emperor Napoleon Bonaparte's head has sold for £130 at auction in Dorset.</code> | | <code>Local Government Association figures show that councils will have spent £505m by 2017 on fighting obesity.<br>Councils use the money to measure children's weight at primary school, help people lose weight and offer free or cheaper leisure facilities.<br>Public health became the responsibility of local authorities in April 2013.<br>Before that, it was run by the NHS.<br>The Department of Health said it was committed to tackling obesity and the government had announced a sugar tax on soft drinks manufacturers earlier in the year.<br>The Local Government Association (LGA) receives money from the government to spend on public health, and this sum will fall from £3.38bn in 2016/17 to £3.13bn in 2020/21.<br>The association, which represents more than 370 councils - mostly in England and a few in Wales - said it was set to spend about half a billion pounds on obesity prevention in adults and children over four years.<br>This was made up as follows:<br>The LGA said the figures illustrated the amount of prevention work councils were carrying out and showed the scale of the obesity crisis.<br>The costs include running the government's National Child Measurement Programme, which involves calculating a child's BMI (body mass index) when they start primary school and again when they leave school in Year Six.<br>Recent figures showed that in 2014/15 in England, one in 10 children aged four and five was obese and one in five children aged 10 to 11 was obese.<br>The LGA said the overall cost of obesity was forecast to rise further.<br>It has previously called on the government to reduce sugar content in fizzy drinks, make sugar labelling clearer and provide more tap water in schools and restaurants.<br>Councils also want to have powers to ban junk food advertising near schools.<br>Izzi Seccombe, who is in charge of community wellbeing for the LGA, said councils were best placed to tackle obesity before it became a problem, but they needed more support.<br>"We would like assurances from the government's new administration that the long-awaited childhood obesity strategy is still on track and that it includes tough measures that will help to reverse the rise in costs and children becoming obese.<br>"Today's obese children will be tomorrow's obese adults, and with this comes a range of costly and debilitating major health conditions."</code> | <code>Local councils in England are warning that government cuts to public health funding could hamper their efforts to tackle obesity.</code> | * Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### compression-pairs * Dataset: [compression-pairs](https://huggingface.co/datasets/sentence-transformers/sentence-compression) at [605bc91](https://huggingface.co/datasets/sentence-transformers/sentence-compression/tree/605bc91d95631895ba25b6eda51a3cb596976c90) * Size: 50,000 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 10 tokens</li><li>mean: 31.89 tokens</li><li>max: 125 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.21 tokens</li><li>max: 28 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------| | <code>The USHL completed an expansion draft on Monday as 10 players who were on the rosters of USHL teams during the 2009-10 season were selected by the League's two newest entries, the Muskegon Lumberjacks and Dubuque Fighting Saints.</code> | <code>USHL completes expansion draft</code> | | <code>Major League Baseball Commissioner Bud Selig will be speaking at St. Norbert College next month.</code> | <code>Bud Selig to speak at St. Norbert College</code> | | <code>It's fresh cherry time in Michigan and the best time to enjoy this delicious and nutritious fruit.</code> | <code>It's cherry time</code> | * Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### sciq_pairs * Dataset: [sciq_pairs](https://huggingface.co/datasets/allenai/sciq) at [2c94ad3](https://huggingface.co/datasets/allenai/sciq/tree/2c94ad3e1aafab77146f384e23536f97a4849815) * Size: 11,679 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 7 tokens</li><li>mean: 17.26 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 84.37 tokens</li><li>max: 512 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>What type of organism is commonly used in preparation of foods such as cheese and yogurt?</code> | <code>Mesophiles grow best in moderate temperature, typically between 25°C and 40°C (77°F and 104°F). Mesophiles are often found living in or on the bodies of humans or other animals. The optimal growth temperature of many pathogenic mesophiles is 37°C (98°F), the normal human body temperature. Mesophilic organisms have important uses in food preparation, including cheese, yogurt, beer and wine.</code> | | <code>What phenomenon makes global winds blow northeast to southwest or the reverse in the northern hemisphere and northwest to southeast or the reverse in the southern hemisphere?</code> | <code>Without Coriolis Effect the global winds would blow north to south or south to north. But Coriolis makes them blow northeast to southwest or the reverse in the Northern Hemisphere. The winds blow northwest to southeast or the reverse in the southern hemisphere.</code> | | <code>Changes from a less-ordered state to a more-ordered state (such as a liquid to a solid) are always what?</code> | <code>Summary Changes of state are examples of phase changes, or phase transitions. All phase changes are accompanied by changes in the energy of a system. Changes from a more-ordered state to a less-ordered state (such as a liquid to a gas) areendothermic. Changes from a less-ordered state to a more-ordered state (such as a liquid to a solid) are always exothermic. The conversion of a solid to a liquid is called fusion (or melting). The energy required to melt 1 mol of a substance is its enthalpy of fusion (ΔHfus). The energy change required to vaporize 1 mol of a substance is the enthalpy of vaporization (ΔHvap). The direct conversion of a solid to a gas is sublimation. The amount of energy needed to sublime 1 mol of a substance is its enthalpy of sublimation (ΔHsub) and is the sum of the enthalpies of fusion and vaporization. Plots of the temperature of a substance versus heat added or versus heating time at a constant rate of heating are calledheating curves. Heating curves relate temperature changes to phase transitions. A superheated liquid, a liquid at a temperature and pressure at which it should be a gas, is not stable. A cooling curve is not exactly the reverse of the heating curve because many liquids do not freeze at the expected temperature. Instead, they form a supercooled liquid, a metastable liquid phase that exists below the normal melting point. Supercooled liquids usually crystallize on standing, or adding a seed crystal of the same or another substance can induce crystallization.</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### qasc_pairs * Dataset: [qasc_pairs](https://huggingface.co/datasets/allenai/qasc) at [a34ba20](https://huggingface.co/datasets/allenai/qasc/tree/a34ba204eb9a33b919c10cc08f4f1c8dae5ec070) * Size: 8,134 training samples * Columns: <code>id</code>, <code>sentence1</code>, and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | id | sentence1 | sentence2 | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 17 tokens</li><li>mean: 21.35 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.47 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 35.55 tokens</li><li>max: 66 tokens</li></ul> | * Samples: | id | sentence1 | sentence2 | |:--------------------------------------------|:---------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>3E7TUJ2EGCLQNOV1WEAJ2NN9ROPD9K</code> | <code>What type of water formation is formed by clouds?</code> | <code>beads of water are formed by water vapor condensing. Clouds are made of water vapor.. Beads of water can be formed by clouds.</code> | | <code>3LS2AMNW5FPNJK3C3PZLZCPX562OQO</code> | <code>Where do beads of water come from?</code> | <code>beads of water are formed by water vapor condensing. Condensation is the change of water vapor to a liquid.. Vapor turning into a liquid leaves behind beads of water</code> | | <code>3TMFV4NEP8DPIPCI8H9VUFHJG8V8W3</code> | <code>What forms beads of water? </code> | <code>beads of water are formed by water vapor condensing. An example of water vapor is steam.. Steam forms beads of water.</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### openbookqa_pairs * Dataset: [openbookqa_pairs](https://huggingface.co/datasets/allenai/openbookqa) at [388097e](https://huggingface.co/datasets/allenai/openbookqa/tree/388097ea7776314e93a529163e0fea805b8a6454) * Size: 2,740 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 3 tokens</li><li>mean: 13.83 tokens</li><li>max: 78 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.37 tokens</li><li>max: 30 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:-------------------------------------------------|:--------------------------------------------------------------------------| | <code>The sun is responsible for</code> | <code>the sun is the source of energy for physical cycles on Earth</code> | | <code>When food is reduced in the stomach</code> | <code>digestion is when stomach acid breaks down food</code> | | <code>Stars are</code> | <code>a star is made of gases</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### msmarco_pairs * Dataset: msmarco_pairs * Size: 50,000 training samples * Columns: <code>query</code>, <code>positive</code>, <code>negative</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | query | positive | negative | label | |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------| | type | string | string | string | float | | details | <ul><li>min: 4 tokens</li><li>mean: 8.61 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 75.09 tokens</li><li>max: 206 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 72.59 tokens</li><li>max: 216 tokens</li></ul> | <ul><li>min: -0.5</li><li>mean: 0.04</li><li>max: 0.6</li></ul> | * Samples: | query | positive | negative | label | |:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------| | <code>what are the liberal arts?</code> | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>The New York State Education Department requires 60 Liberal Arts credits in a Bachelor of Science program and 90 Liberal Arts credits in a Bachelor of Arts program. In the list of course descriptions, courses which are liberal arts for all students are identified by (Liberal Arts) after the course number.</code> | <code>0.12154221534729004</code> | | <code>what is the mechanism of action of fibrinolytic or thrombolytic drugs?</code> | <code>Baillière's Clinical Haematology. 6 Mechanism of action of the thrombolytic agents. 6 Mechanism of action of the thrombolytic agents JEFFREY I. WEITZ Fibrin formed during the haemostatic, inflammatory or tissue repair process serves a temporary role, and must be degraded to restore normal tissue function and structure.</code> | <code>Fibrinolytic drug. Fibrinolytic drug, also called thrombolytic drug, any agent that is capable of stimulating the dissolution of a blood clot (thrombus). Fibrinolytic drugs work by activating the so-called fibrinolytic pathway.</code> | <code>-0.05174225568771362</code> | | <code>what is normal plat count</code> | <code>78 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).The average platelet count is 237,000 per mcL in men and 266,000 per mcL in women.8 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).</code> | <code>Your blood test results should be written in your maternity notes. Your platelet count will look something like Plat. 160x10.9/L, which means you have a platelet count of 160, which is in the normal range.If your platelet count is low, the blood test should be done again.This will keep track of whether or not your count is dropping.our platelet count will look something like Plat. 160x10.9/L, which means you have a platelet count of 160, which is in the normal range. If your platelet count is low, the blood test should be done again. This will keep track of whether or not your count is dropping.</code> | <code>-0.037523627281188965</code> | * Loss: [<code>MarginMSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#marginmseloss) #### nq_pairs * Dataset: [nq_pairs](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17) * Size: 50,000 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 10 tokens</li><li>mean: 11.77 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 131.57 tokens</li><li>max: 512 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>when did richmond last play in a preliminary final</code> | <code>Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tigers took over the game as it progressed and scored seven straight goals at one point. They eventually would win by 48 points – 16.12 (108) to Adelaide's 8.12 (60) – to end their 37-year flag drought.[22] Dustin Martin also became the first player to win a Premiership medal, the Brownlow Medal and the Norm Smith Medal in the same season, while Damien Hardwick was named AFL Coaches Association Coach of the Year. Richmond's jump from 13th to premiers also marked the biggest jump from one AFL season to the next.</code> | | <code>who sang what in the world's come over you</code> | <code>Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.</code> | | <code>who produces the most wool in the world</code> | <code>Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### trivia_pairs * Dataset: [trivia_pairs](https://huggingface.co/datasets/sentence-transformers/trivia-qa) at [a7c36e3](https://huggingface.co/datasets/sentence-transformers/trivia-qa/tree/a7c36e3c8c8c01526bc094d79bf80d4c848b0ad0) * Size: 50,000 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 8 tokens</li><li>mean: 15.16 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 456.87 tokens</li><li>max: 512 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>Which American-born Sinclair won the Nobel Prize for Literature in 1930?</code> | <code>The Nobel Prize in Literature 1930 The Nobel Prize in Literature 1930 Sinclair Lewis The Nobel Prize in Literature 1930 Sinclair Lewis Prize share: 1/1 The Nobel Prize in Literature 1930 was awarded to Sinclair Lewis "for his vigorous and graphic art of description and his ability to create, with wit and humour, new types of characters". Photos: Copyright © The Nobel Foundation Share this: To cite this page MLA style: "The Nobel Prize in Literature 1930". Nobelprize.org. Nobel Media AB 2014. Web. 18 Jan 2017. <http://www.nobelprize.org/nobel_prizes/literature/laureates/1930/></code> | | <code>Where in England was Dame Judi Dench born?</code> | <code>Judi Dench - IMDb IMDb Actress | Music Department | Soundtrack Judi Dench was born in York, England, to Eleanora Olive (Jones), who was from Dublin, Ireland, and Reginald Arthur Dench, a doctor from Dorset, England. She attended Mount School in York, and studied at the Central School of Speech and Drama. She has performed with Royal Shakespeare Company, the National Theatre, and at Old Vic Theatre. She is a ... See full bio » Born: a list of 35 people created 02 Jul 2011 a list of 35 people created 19 Apr 2012 a list of 35 people created 28 May 2014 a list of 25 people created 05 Aug 2014 a list of 26 people created 18 May 2015 Do you have a demo reel? Add it to your IMDbPage How much of Judi Dench's work have you seen? User Polls Won 1 Oscar. Another 59 wins & 163 nominations. See more awards  » Known For  2016 The Hollow Crown (TV Series) Cecily, Duchess of York  2015 The Vote (TV Movie) Christine Metcalfe - Total War (1996) ... Narrator (voice) - Stalemate (1996) ... Narrator (voice)  1992 The Torch (TV Mini-Series) Aba  1990 Screen One (TV Series) Anne  1989 Behaving Badly (TV Mini-Series) Bridget  1981 BBC2 Playhouse (TV Series) Sister Scarli  1976 Arena (TV Series documentary) Sweetie Simpkins  1973 Ooh La La! (TV Series) Amélie  1966 Court Martial (TV Series) Marthe  1963 Z Cars (TV Series) Elena Collins  1963 Love Story (TV Series) Pat McKendrick  1960 The Terrible Choice (TV Series) Good Angel Music department (1 credit)   A Fine Romance (TV Series) (theme sung by - 14 episodes, 1981 - 1983) (theme song sung by - 12 episodes, 1983 - 1984) - A Romantic Meal (1984) ... (theme song sung by) - Problems (1984) ... (theme song sung by)  2013 Fifty Years on Stage (TV Movie) (performer: "Send in the Clowns")  2009 Nine (performer: "Folies Bergère") - What's Wrong with Mrs Bale? (1997) ... (performer: "Raindrops Keep Fallin' On My Head" - uncredited) - Misunderstandings (1993) ... (performer: "Walkin' My Baby Back Home" - uncredited)  1982-1984 A Fine Romance (TV Series) (performer - 2 episodes) - The Telephone Call (1984) ... (performer: "Boogie Woogie Bugle Boy" - uncredited) - Furniture (1982) ... (performer: "Rule, Britannia!" - uncredited) Hide   2009 Waiting in Rhyme (Video short) (special thanks)  2007 Expresso (Short) (special thanks)  1999 Shakespeare in Love and on Film (TV Movie documentary) (thanks - as Dame Judi Dench) Hide   2016 Rio Olympics (TV Mini-Series) Herself  2015 In Conversation (TV Series documentary) Herself  2015 Entertainment Tonight (TV Series) Herself  2015 CBS This Morning (TV Series) Herself - Guest  2015 The Insider (TV Series) Herself  1999-2014 Cinema 3 (TV Series) Herself  2013 Good Day L.A. (TV Series) Herself - Guest  2013 Arena (TV Series documentary) Herself  2013 At the Movies (TV Series) Herself  2013 Shooting Bond (Video documentary) Herself  2013 Bond's Greatest Moments (TV Movie documentary) Herself  2012 Made in Hollywood (TV Series) Herself  1999-2012 Charlie Rose (TV Series) Herself - Guest  2008-2012 This Morning (TV Series) Herself - Guest  2012 The Secrets of Skyfall (TV Short documentary) Herself  2012 Anderson Live (TV Series) Herself  2012 J. Edgar: A Complicated Man (Video documentary short) Herself  2011 The Many Faces of... (TV Series documentary) Herself / Various Characters  2011 Na plovárne (TV Series) Herself  2010 BBC Proms (TV Series) Herself  2010 The South Bank Show Revisited (TV Series documentary) Herself - Episode #6.68 (2009) ... Herself - Guest (as Dame Judi Dench)  2007-2009 Breakfast (TV Series)  2009 Larry King Live (TV Series) Herself - Guest  2009 The One Show (TV Series) Herself  2009 Cranford in Detail (Video documentary short) Herself / Miss Matty Jenkins (as Dame Judi Dench)  2005-2008 The South Bank Show (TV Series documentary) Herself  2008 Tavis Smiley (TV Series) Herself - Guest  2007 ITV News (TV Series) Herself - BAFTA Nominee  2007 The Making of Cranford (Video documentary short) Herself / Miss Matty Jenkyns (as Dame Judi Dench)  2006 Becoming Bond (TV Movie documentary) Herself  2006 Corazón de... (TV Series) Hers</code> | | <code>In which decade did Billboard magazine first publish and American hit chart?</code> | <code>The US Billboard song chart The US Billboard song chart Search this site with Google Song chart US Billboard The Billboard magazine has published various music charts starting (with sheet music) in 1894, the first "Music Hit Parade" was published in 1936 , the first "Music Popularity Chart" was calculated in 1940 . These charts became less irregular until the weekly "Hot 100" was started in 1958 . The current chart combines sales, airplay and downloads. A music collector that calls himself Bullfrog has been consolidating the complete chart from 1894 to the present day. he has published this information in a comprehenive spreadsheet (which can be obtained at bullfrogspond.com/ ). The Bullfrog data assigns each song a unique identifier, something like "1968_076" (which just happens to be the Bee Gees song "I've Gotta Get A Message To You"). This "Whitburn Number" is provided to match with the books of Joel Whitburn and consists of the year and a ranking within the year. A song that first entered the charts in December and has a long run is listed the following year. This numbering scheme means that songs which are still in the charts cannot be assigned a final id, because their ranking might change. So the definitive listing for a year cannot be final until about April. In our listing we only use songs with finalised IDs, this means that every year we have to wait until last year's entries are finalised before using them. (Source bullfrogspond.com/ , the original version used here was 20090808 with extra data from: the 2009 data from 20091219 the 2010 data from 20110305 the 2011 data from 20120929 the 2012 data from 20130330 the 2013 data from 20150328 The 20150328 data was the last one produced before the Billboard company forced the data to be withdrawn. As far as we know there are no more recent data sets available. This pattern of obtaining the data for a particular year in the middle of the following one comes from the way that the Bullfrog project generates the identifier for a song (what they call the "Prefix" in the spreadsheet). Recent entries are identified with keys like "2015-008" while older ones have keys like "2013_177". In the second case the underscore is significant, it indicates that this was the 177th biggest song released in 2013. Now, of course, during the year no one knows where a particular song will rank, so the underscore names can't be assigned until every song from a particular year has dropped out of the charts, so recent records are temporarily assigned a name with a dash. In about May of the following year the rankings are calculated and the final identifiers are assigned. That is why we at the Turret can only grab this data retrospectively. Attributes The original spreadsheet has a number of attributes, we have limited our attention to just a few of them: 134 9 The songs with the most entries on the chart were White Christmas (with 33 versions and a total of 110 weeks) and Stardust (with 19 and a total of 106 weeks). position The peak position that songs reached in the charts should show an smooth curve from number one down to the lowest position. This chart has more songs in the lower peak positions than one would expect. Before 1991 the profile of peak positions was exactly as you would expect, that year Billboard introduced the concept of "Recurrent" tracks, that is they removed any track from the chart which had spent more than twenty weeks in the chart and had fallen to the lower positions. weeks The effect of the "Recurrent" process, by which tracks are removed if they have spent at least twenty weeks in the chart and have fallen to the lower reaches, can clearly be seen in the strange spike in this attribute. This "adjustment" was intended to promote newer songs and ensure the chart does not become "stale". In fact since it was introduced in 1991 the length of long chart runs has increased, this might reflect the more conscious efforts of record companies to "game" the charts by controlling release times and promotions, or it coul</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### quora_pairs * Dataset: [quora_pairs](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 50,000 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 6 tokens</li><li>mean: 13.53 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.68 tokens</li><li>max: 43 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:----------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------| | <code>Astrology: I am a Capricorn Sun Cap moon and cap rising...what does that say about me?</code> | <code>I'm a triple Capricorn (Sun, Moon and ascendant in Capricorn) What does this say about me?</code> | | <code>How can I be a good geologist?</code> | <code>What should I do to be a great geologist?</code> | | <code>How do I read and find my YouTube comments?</code> | <code>How can I see all my Youtube comments?</code> | * Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### gooaq_pairs * Dataset: [gooaq_pairs](https://huggingface.co/datasets/sentence-transformers/gooaq) at [b089f72](https://huggingface.co/datasets/sentence-transformers/gooaq/tree/b089f728748a068b7bc5234e5bcf5b25e3c8279c) * Size: 50,000 training samples * Columns: <code>sentence1</code> and <code>sentence2</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 8 tokens</li><li>mean: 11.6 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 57.74 tokens</li><li>max: 127 tokens</li></ul> | * Samples: | sentence1 | sentence2 | |:---------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>is toprol xl the same as metoprolol?</code> | <code>Metoprolol succinate is also known by the brand name Toprol XL. It is the extended-release form of metoprolol. Metoprolol succinate is approved to treat high blood pressure, chronic chest pain, and congestive heart failure.</code> | | <code>are you experienced cd steve hoffman?</code> | <code>The Are You Experienced album was apparently mastered from the original stereo UK master tapes (according to Steve Hoffman - one of the very few who has heard both the master tapes and the CDs produced over the years). ... The CD booklets were a little sparse, but at least they stayed true to the album's original design.</code> | | <code>how are babushka dolls made?</code> | <code>Matryoshka dolls are made of wood from lime, balsa, alder, aspen, and birch trees; lime is probably the most common wood type. ... After cutting, the trees are stripped of most of their bark, although a few inner rings of bark are left to bind the wood and keep it from splitting.</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` ### Evaluation Datasets #### nli-pairs * Dataset: [nli-pairs](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab) * Size: 6,808 evaluation samples * Columns: <code>anchor</code> and <code>positive</code> * Approximate statistics based on the first 1000 samples: | | anchor | positive | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 5 tokens</li><li>mean: 17.64 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.67 tokens</li><li>max: 29 tokens</li></ul> | * Samples: | anchor | positive | |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------| | <code>Two women are embracing while holding to go packages.</code> | <code>Two woman are holding packages.</code> | | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code> | <code>A man selling donuts to a customer.</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### scitail-pairs-pos * Dataset: [scitail-pairs-pos](https://huggingface.co/datasets/allenai/scitail) at [0cc4353](https://huggingface.co/datasets/allenai/scitail/tree/0cc4353235b289165dfde1c7c5d1be983f99ce44) * Size: 1,304 evaluation samples * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | <ul><li>min: 5 tokens</li><li>mean: 22.52 tokens</li><li>max: 67 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 15.34 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>0: ~47.50%</li><li>1: ~52.50%</li></ul> | * Samples: | sentence1 | sentence2 | label | |:----------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:---------------| | <code>An introduction to atoms and elements, compounds, atomic structure and bonding, the molecule and chemical reactions.</code> | <code>Replace another in a molecule happens to atoms during a substitution reaction.</code> | <code>0</code> | | <code>Wavelength The distance between two consecutive points on a sinusoidal wave that are in phase;</code> | <code>Wavelength is the distance between two corresponding points of adjacent waves called.</code> | <code>1</code> | | <code>humans normally have 23 pairs of chromosomes.</code> | <code>Humans typically have 23 pairs pairs of chromosomes.</code> | <code>1</code> | * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters: ```json {'guide': SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ), 'temperature': 0.05} ``` #### qnli-contrastive * Dataset: [qnli-contrastive](https://huggingface.co/datasets/nyu-mll/glue) at [bcdcba7](https://huggingface.co/datasets/nyu-mll/glue/tree/bcdcba79d07bc864c1c254ccfcedcce55bcc9a8c) * Size: 5,463 evaluation samples * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------| | type | string | string | int | | details | <ul><li>min: 6 tokens</li><li>mean: 14.13 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 36.58 tokens</li><li>max: 225 tokens</li></ul> | <ul><li>0: 100.00%</li></ul> | * Samples: | sentence1 | sentence2 | label | |:--------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------|:---------------| | <code>What came into force after the new constitution was herald?</code> | <code>As of that day, the new constitution heralding the Second Republic came into force.</code> | <code>0</code> | | <code>What is the first major city in the stream of the Rhine?</code> | <code>The most important tributaries in this area are the Ill below of Strasbourg, the Neckar in Mannheim and the Main across from Mainz.</code> | <code>0</code> | | <code>What is the minimum required if you want to teach in Canada?</code> | <code>In most provinces a second Bachelor's Degree such as a Bachelor of Education is required to become a qualified teacher.</code> | <code>0</code> | * Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 30 - `per_device_eval_batch_size`: 16 - `learning_rate`: 1e-05 - `weight_decay`: 5e-06 - `num_train_epochs`: 2 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.5 - `save_safetensors`: False - `fp16`: True - `push_to_hub`: True - `hub_model_id`: bobox/DeBERTaV3-small-GeneralSentenceTransformer-v2-checkpoints-tmp - `hub_strategy`: checkpoint - `batch_sampler`: no_duplicates #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 30 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `learning_rate`: 1e-05 - `weight_decay`: 5e-06 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 2 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.5 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: False - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: True - `resume_from_checkpoint`: None - `hub_model_id`: bobox/DeBERTaV3-small-GeneralSentenceTransformer-v2-checkpoints-tmp - `hub_strategy`: checkpoint - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional </details> ### Training Logs | Epoch | Step | Training Loss | scitail-pairs-pos loss | nli-pairs loss | qnli-contrastive loss | sts-test_spearman_cosine | |:-----:|:-----:|:-------------:|:----------------------:|:--------------:|:---------------------:|:------------------------:| | 0 | 0 | - | 3.4975 | 4.3370 | 4.4702 | 0.2589 | | 0.1 | 1757 | 3.8346 | 2.3231 | 2.8535 | 3.0973 | - | | 0.2 | 3514 | 1.8532 | 0.9755 | 1.3508 | 2.0603 | - | | 0.3 | 5271 | 1.2185 | 0.7407 | 0.9381 | 1.2534 | - | | 0.4 | 7028 | 0.9584 | 0.6616 | 0.7495 | 0.5140 | - | | 0.5 | 8785 | 0.8157 | 0.6057 | 0.6550 | 0.3295 | - | | 0.6 | 10542 | 0.6698 | 0.5821 | 0.5809 | 0.2423 | - | | 0.7 | 12299 | 0.6497 | 0.5040 | 0.5178 | 0.2409 | - | | 0.8 | 14056 | 0.5737 | 0.4942 | 0.5019 | 0.1500 | - | | 0.9 | 15813 | 0.5896 | 0.4757 | 0.4804 | 0.1465 | - | | 1.0 | 17570 | 0.5174 | 0.5253 | 0.4587 | 0.0534 | - | | 1.1 | 19327 | 0.5059 | 0.5493 | 0.4587 | 0.0278 | - | | 1.2 | 21084 | 0.4654 | 0.4850 | 0.4415 | 0.0517 | - | | 1.3 | 22841 | 0.4224 | 0.4292 | 0.3957 | 0.0938 | - | | 1.4 | 24598 | 0.4125 | 0.4624 | 0.3794 | 0.0839 | - | | 1.5 | 26355 | 0.4072 | 0.4481 | 0.3878 | 0.0681 | - | | 1.6 | 28112 | 0.3572 | 0.4953 | 0.3716 | 0.0674 | - | | 1.7 | 29869 | 0.371 | 0.4767 | 0.3622 | 0.0600 | - | | 1.8 | 31626 | 0.3332 | 0.4659 | 0.3600 | 0.0561 | - | | 1.9 | 33383 | 0.3695 | 0.4604 | 0.3567 | 0.0614 | - | | 2.0 | 35140 | 0.3315 | 0.4712 | 0.3597 | 0.0540 | 0.7975 | ### Framework Versions - Python: 3.10.13 - Sentence Transformers: 3.0.1 - Transformers: 4.41.2 - PyTorch: 2.1.2 - Accelerate: 0.30.1 - Datasets: 2.19.2 - Tokenizers: 0.19.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### GISTEmbedLoss ```bibtex @misc{solatorio2024gistembed, title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning}, author={Aivin V. Solatorio}, year={2024}, eprint={2402.16829}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### CoSENTLoss ```bibtex @online{kexuefm-8847, title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT}, author={Su Jianlin}, year={2022}, month={Jan}, url={https://kexue.fm/archives/8847}, } ``` #### MarginMSELoss ```bibtex @misc{hofstätter2021improving, title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation}, author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury}, year={2021}, eprint={2010.02666}, archivePrefix={arXiv}, primaryClass={cs.IR} } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
[ "MEDAL", "SCIQ", "SCITAIL" ]
Rodrigo1771/bsc-bio-ehr-es-symptemist-ner
Rodrigo1771
token-classification
[ "tensorboard", "safetensors", "roberta", "token-classification", "generated_from_trainer", "dataset:Rodrigo1771/symptemist-ner", "base_model:PlanTL-GOB-ES/bsc-bio-ehr-es", "base_model:finetune:PlanTL-GOB-ES/bsc-bio-ehr-es", "license:apache-2.0", "model-index", "region:us" ]
2024-08-30T22:28:06Z
2024-08-30T22:36:17+00:00
33
0
--- base_model: PlanTL-GOB-ES/bsc-bio-ehr-es datasets: - Rodrigo1771/symptemist-ner license: apache-2.0 metrics: - precision - recall - f1 - accuracy tags: - token-classification - generated_from_trainer model-index: - name: output results: - task: type: token-classification name: Token Classification dataset: name: Rodrigo1771/symptemist-ner type: Rodrigo1771/symptemist-ner config: SympTEMIST NER split: validation args: SympTEMIST NER metrics: - type: precision value: 0.6675139806812405 name: Precision - type: recall value: 0.7186644772851669 name: Recall - type: f1 value: 0.6921454928835002 name: F1 - type: accuracy value: 0.9483461131252205 name: Accuracy --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # output This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the Rodrigo1771/symptemist-ner dataset. It achieves the following results on the evaluation set: - Loss: 0.2747 - Precision: 0.6675 - Recall: 0.7187 - F1: 0.6921 - Accuracy: 0.9483 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 150 | 0.1504 | 0.5091 | 0.6409 | 0.5675 | 0.9456 | | No log | 2.0 | 300 | 0.1547 | 0.5881 | 0.6995 | 0.639 | 0.9462 | | No log | 3.0 | 450 | 0.1618 | 0.6237 | 0.6984 | 0.6589 | 0.9476 | | 0.126 | 4.0 | 600 | 0.1920 | 0.6154 | 0.7181 | 0.6628 | 0.9451 | | 0.126 | 5.0 | 750 | 0.2102 | 0.6561 | 0.7028 | 0.6786 | 0.9488 | | 0.126 | 6.0 | 900 | 0.2414 | 0.6443 | 0.7088 | 0.6750 | 0.9467 | | 0.0251 | 7.0 | 1050 | 0.2500 | 0.6588 | 0.7061 | 0.6816 | 0.9492 | | 0.0251 | 8.0 | 1200 | 0.2642 | 0.6440 | 0.7307 | 0.6846 | 0.9474 | | 0.0251 | 9.0 | 1350 | 0.2747 | 0.6675 | 0.7187 | 0.6921 | 0.9483 | | 0.0091 | 10.0 | 1500 | 0.2767 | 0.6595 | 0.7187 | 0.6878 | 0.9488 | ### Framework versions - Transformers 4.42.4 - Pytorch 2.4.0+cu121 - Datasets 2.21.0 - Tokenizers 0.19.1
[ "SYMPTEMIST" ]
mllmTeam/PhoneLM-0.5B
mllmTeam
text-generation
[ "transformers", "safetensors", "phonelm", "text-generation", "custom_code", "en", "dataset:mlfoundations/dclm-baseline-1.0-parquet", "dataset:bigcode/starcoderdata", "dataset:open-web-math/open-web-math", "dataset:allenai/dolma", "arxiv:2104.09864", "arxiv:2204.06745", "arxiv:1607.06450", "arxiv:1910.07467", "arxiv:2309.16609", "arxiv:2406.11794", "arxiv:2305.06161", "arxiv:2310.06786", "arxiv:2411.05046", "license:apache-2.0", "autotrain_compatible", "region:us" ]
2024-11-06T08:01:53Z
2024-11-14T13:44:19+00:00
33
0
--- datasets: - mlfoundations/dclm-baseline-1.0-parquet - bigcode/starcoderdata - open-web-math/open-web-math - allenai/dolma language: - en library_name: transformers license: apache-2.0 --- PhoneLM-0.5B is a 0.5 billion parameter decoder-only language model pre-trained on 1.1 trillion tokens. ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM model_name = 'mllmTeam/PhoneLM-0.5B' model = AutoModelForCausalLM.from_pretrained(model_name, device_map='cuda', trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained(model_name) inp = tokenizer("Machine Learning is ", return_tensors="pt") inp = {k: v.to('cuda') for k, v in inp.items()} out = model.generate(**inp, max_length=256, do_sample=True, temperature=0.7, top_p=0.7 ) text = tokenizer.decode(out[0], skip_special_tokens=True) print(text) ``` ## Model Details * **Developed by**: mllmTeam * **Model type**: `PhoneLM 0.5B` models are auto-regressive language models based on the transformer decoder architecture. * **Language(s)**: English * **Paper**: [PhoneLM Technical Report]() * **Library**: [PhoneLM](https://github.com/UbiquitousLearning/PhoneLM) ### Model Architecture The model is a decoder-only transformer architecture with the following modifications: | Hidden Size | Layers | Heads | Sequence Length | |-------------|--------|-------|-----------------| | 1024 | 24 | 16 | 2048 | * **Position Embeddings**: Rotary Position Embeddings ([Su et al., 2021](https://arxiv.org/abs/2104.09864)) applied to the first 25% of head embedding dimensions for improved throughput following [Black et al. (2022)](https://arxiv.org/pdf/2204.06745.pdf). PhoneLM quantized the sin and cos values in Rotary Position Embeddings to 8-bit integers. * **Normalization**: LayerNorm ([Ba et al., 2016](https://arxiv.org/abs/1607.06450)) with learned bias terms as opposed to RMSNorm ([Zhang & Sennrich, 2019](https://arxiv.org/abs/1910.07467)). * **Biases**: We remove all bias terms from the feed-forward networks and multi-head self-attention layers, except for the biases of the query, key, and value projections ([Bai et al., 2023](https://arxiv.org/abs/2309.16609)). * **ReLU Activation Function**: ReLU([Glorot et al., 2011](https://proceedings.mlr.press/v15/glorot11a/glorot11a.pdf)) activation functions are adopted in feed-forward networks. * **Tokenizer**: We use the SmolLM([Allal et al., 2024](https://huggingface.co/blog/smollm))'s tokenizer with a vocabulary size of 49,152. ## Training Dataset The training dataset PhoneLM used is comprised of a filtered mixture of open-source large-scale datasets available on the [HuggingFace Hub](https://huggingface.co/datasets): DCLM-baseline([Li et al., 2024](https://arxiv.org/abs/2406.11794)), StarCoder ([Li et al., 2023](https://arxiv.org/abs/2305.06161)), OpenWebMath ([Paster et al., 2023](https://arxiv.org/abs/2310.06786)) and Dolma ([Soldaini et al., 2024](https://aclanthology.org/2024.acl-long.840/)). ## Evaluation Results | Model | HellaSwag | WinoGrande | PIQA | SciQ | BoolQ | ARC Easy | ARC Challenge | Average | |-----------|-----------|------------|------|------|-------|----------|---------------|---------| | **PhoneLM-0.5B** | **54.0** | **57.9** | **73.3** | **85.1** | **60.7** | **60.4** | **31.6** | **60.43** | | Pythia-410M | 40.6 | 53.7 | 66.9 | 72.4 | 60.3 | 45.9 | 24.5 | 52.04 | | OPT-350M | 36.8 | 52.3 | 64.3 | 68.5 | 57.6 | 40.1 | 23.7 | 49.04 | | BLOOM-560M | 36.9 | 51.7 | 65.0 | 71.7 | 53.3 | 41.8 | 23.7 | 49.16 | | MobiLlama-500M | 51.1 | 53.4 | 70.9 | 76.4 | 55.7 | 46.0 | 26.6 | 54.30 | | OpenELM-450M | 54.0 | 58.0 | 72.3 | 79.4 | 55.8 | 48.1 | 27.6 | 56.46 | | SmolLM-360M | 53.5 | 56.8 | 71.5 | 84.2 | 55.4 | 63.8 | 36.0 | 60.17 | | Qwen 1.5-500M | 49.2 | 55.7 | 69.5 | 82.5 | 49.5 | 52.3 | 29.4 | 55.44 | | Cerebras-GPT-590M | 32.3 | 49.8 | 62.8 | 68.2 | 59.2 | 41.2 | 23.5 | 48.14 | ## License * This repository is released under the [Apache-2.0](https://huggingface.co/mllmTeam/PhoneLM-0.5B/blob/main/README.md) License. ## Citation ``` @misc{yi2024phonelmanefficientcapablesmall, title={PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training}, author={Rongjie Yi and Xiang Li and Weikai Xie and Zhenyan Lu and Chenghua Wang and Ao Zhou and Shangguang Wang and Xiwen Zhang and Mengwei Xu}, year={2024}, eprint={2411.05046}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2411.05046}, } ```
[ "SCIQ" ]
aisingapore/llama3.1-70b-cpt-sea-lionv3-base
aisingapore
text-generation
[ "transformers", "safetensors", "llama", "text-generation", "en", "zh", "vi", "id", "th", "fil", "ta", "ms", "km", "lo", "my", "arxiv:2309.06085", "arxiv:2311.07911", "arxiv:2403.06350", "arxiv:2101.09635", "base_model:meta-llama/Llama-3.1-70B-Instruct", "base_model:finetune:meta-llama/Llama-3.1-70B-Instruct", "license:llama3.1", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2024-12-11T10:22:14Z
2024-12-19T13:06:53+00:00
33
0
--- base_model: meta-llama/Llama-3.1-70B-Instruct language: - en - zh - vi - id - th - fil - ta - ms - km - lo - my library_name: transformers license: llama3.1 pipeline_tag: text-generation base_model_relation: finetune --- <div> <img src="llama_3.1_70b_sea-lion_v3_base_banner.png"/> </div> # Llama3.1 70B CPT SEA-LIONv3 SEA-LION is a collection of Large Language Models (LLMs) which has been pretrained and instruct-tuned for the Southeast Asia (SEA) region. Llama3.1 70B CPT SEA-LIONv3 Base is a multilingual model which has undergone continued pre-training on approximately **200B** tokens across 11 SEA languages: Burmese, Chinese, English, Filipino, Indonesia, Khmer, Lao, Malay, Tamil, Thai and Vietnamese. SEA-LION stands for <i>Southeast Asian Languages In One Network</i>. - **Developed by:** Products Pillar, AI Singapore - **Funded by:** Singapore NRF - **Model type:** Decoder - **Languages supported:** Burmese, Chinese, English, Filipino, Indonesia, Khmer, Lao, Malay, Tamil, Thai, Vietnamese. - **License:** [Llama 3.1 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE) ## Model Details ### Model Description We performed continued pre-training in English and SEA languages on [Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct), a decoder model using the Llama 3.1 architecture, to create Llama3.1 70B CPT SEA-LIONv3 Base. For tokenisation, the model employs the default tokenizer used in Llama 3.1 70B Instruct. ### Benchmark Performance We evaluated Llama3.1 70B CPT SEA-LIONv3 base model on general language capabilities and constraint-following behaviour. #### General Language Capabilities and Constraint-following Behaviour For the evaluation of general language capabilities, we employed the [SEA-HELM (also known as BHASA) evaluation benchmark](https://arxiv.org/abs/2309.06085v2) across a variety of tasks. These tasks include Question Answering (QA), Sentiment Analysis (Sentiment), Toxicity Detection (Toxicity), Translation in both directions (Eng>Lang & Lang>Eng), Abstractive Summarisation (Abssum), Causal Reasoning (Causal) and Natural Language Inference (NLI). Note: SEA-HELM is implemented using prompts to elicit answers in a strict format. For all tasks, the model is expected to provide an answer tag from which the answer is automatically extracted. For tasks where options are provided, the answer should comprise one of the pre-defined options. The scores for each task is normalised to account for baseline performance due to random chance. The evaluation was done **five-shot** with native prompts on a sample of 100-1000 instances for each dataset. Following the implementation of IFEval in OpenLLM leaderboard, we also implement SEA-IFEval to provide a comparison of the ability of the model to follow specific constraints in English and in SEA languages. **SEA-IFEval** Based on [IFEval](https://arxiv.org/abs/2311.07911), the linguists and native speakers in the team worked together to filter, localise and translate the datasets into the respective target languages to ensure that the examples remained reasonable, meaningful and natural. SEA-IFEval evaluates a model's ability to adhere to constraints provided in the prompt, for example beginning a response with a specific word/phrase or answering with a certain number of sections. Additionally, accuracy is normalised by the proportion of responses in the correct language (if the model performs the task correctly but responds in the wrong language, it is judged to have failed the task). For more details on Llama3.1 70B CPT SEA-LIONv3 base benchmark performance, please refer to the SEA-HELM leaderboard, https://leaderboard.sea-lion.ai/. ## Technical Specifications ### Infrastructure Llama3.1 70B CPT SEA-LIONv3 was trained in two stages using [MosaicML Composer](https://github.com/mosaicml/composer) on the following hardware: | Stage | Training Details | Llama3.1 70B CPT SEA-LIONv3 | |------------|-----------------------|:---------------------------:| |First Stage | AWS p5e.48xlarge | 8 instances | | | Nvidia H200 140GB GPU | 64 | | | Training Duration | 200 hrs (step 0 - 9000) | |Second Stage| SingTel HGX-100 | 16 instances | | | Nvidia H100 80GB GPU | 128 | | | Training Duration | 495 hrs (step 9000 - 47684) | ### Configuration | HyperParameter | Llama3.1 70B CPT SEA-LIONv3 | |-------------------|:------------------------:| | Precision | bfloat16 | | Optimizer | decoupled_adamw | | Scheduler | weight_stable_decay | | Learning Rate | 1.0e-5 | | Global Batch Size | 512 | ## Data Llama3.1 70B CPT SEA-LIONv3 base model was continued pre-trained on 200B tokens of the following data: | Language | Source | Total Tokens (B) | Percentage (%) | Total percentage (%) | | ------------------------ | -------------------------------------- | ---------------- | -------------- | -------------------- | | Code | StackV2 | 40 | 20 | 20 | | English | Dolma | 37.5 | 18.75 | 25 | | | Fineweb-Edu | 7.5 | 3.75 | | | Others | 5 | 2.5 | | Chinese | SEA-LION Pile v1 | 12 | 6 | 13 | | | Others | 14 | 7 | | Vietnamese | SEA-LION Pile v1 | 8.4 | 4.2 | 13 | | | VinBigData | 16 | 8 | | | Others | 1.6 | 0.8 | | Indonesian | SEA-LION Pile v1 | 7 | 3.5 | 13 | | | SEA-LION Pile v2 | 7 | 3.5 | | | Others | 12 | 6 | | Thai | SEA-LION Pile v1 | 10.7 | 5.35 | 10 | | | WangChanBERTa | 8.5 | 4.25 | | | Others | 0.8 | 0.4 | | Filipino - Malay - Tamil | SEA-LION Pile v1, AI4Bharat Sangraha | 4.28 | 2.14 | 3 | | | Others | 1.72 | 0.86 | | Khmer - Lao - Burmese | SEA-LION Pile v1 | 5.2 | 2.6 | 3 | | | Others | 0.8 | 0.4 | Note: - All token counts are counted using Llama 3.1 70B Instruct tokenizer - SEA-LION Pile v1 is processed from Common Crawl WET, which is published [here](https://huggingface.co/datasets/aisingapore/sea-lion-pile). The cutoff date of this version is September 2020. - SEA-LION Pile v2 is processed from Common Crawl WARC from October 2020 to April 2024. - Tamil data from Sangraha is published [here](https://huggingface.co/datasets/ai4bharat/sangraha). The paper can be found [here](https://arxiv.org/abs/2403.06350). - Tamil news is sourced with permission from [Seithi](https://seithi.mediacorp.sg/) ## Call for Contributions We encourage researchers, developers, and language enthusiasts to actively contribute to the enhancement and expansion of SEA-LION. Contributions can involve identifying and reporting bugs, sharing pre-training, instruction, and preference data, improving documentation usability, proposing and implementing new model evaluation tasks and metrics, or training versions of the model in additional Southeast Asian languages. Join us in shaping the future of SEA-LION by sharing your expertise and insights to make these models more accessible, accurate, and versatile. Please check out our GitHub for further information on the call for contributions. ## The Team Chan Adwin, Cheng Nicholas, Choa Esther, Huang Yuli, Hulagadri Adithya Venkatadri, Lau Wayne, Lee Chwan Ren, Leong Wai Yi, Leong Wei Qi, Limkonchotiwat Peerat, Liu Bing Jie Darius, Montalan Jann Railey, Ng Boon Cheong Raymond, Ngui Jian Gang, Nguyen Thanh Ngan, Ong Brandon, Ong Tat-Wee David, Ong Zhi Hao, Rengarajan Hamsawardhini, Siow Bryan, Susanto Yosephine, Tai Ngee Chia, Tan Choon Meng, Teng Walter, Teo Eng Sipp Leslie, Teo Wei Yi, Tjhi William, Yeo Yeow Tong, Yong Xianbin ## Acknowledgements [AI Singapore](​​https://aisingapore.org/) is a national programme supported by the National Research Foundation, Singapore and hosted by the National University of Singapore. Any opinions, findings and conclusions or recommendations expressed in this material are those of the author(s) and do not reflect the views of the National Research Foundation or the National University of Singapore. ## Contact For more info, please contact us using this [SEA-LION Inquiry Form.](https://forms.gle/sLCUVb95wmGf43hi6) [Link to SEA-LION's GitHub repository.](https://github.com/aisingapore/sealion) ## Disclaimer This is the repository for the commercial instruction-tuned model. The model has _not_ been aligned for safety. Developers and users should perform their own safety fine-tuning and related security measures. In no event shall the authors be held liable for any claims, damages, or other liabilities arising from the use of the released weights and codes. ## References ### Thai Pre-Training Data Reference ```bibtex @misc{lowphansirikul2021wangchanberta, title={WangchanBERTa: Pretraining transformer-based Thai Language Models}, author={Lalita Lowphansirikul and Charin Polpanumas and Nawat Jantrakulchai and Sarana Nutanong}, year={2021}, eprint={2101.09635}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
[ "CHIA" ]
BigSalmon/InformalToFormalLincoln84Paraphrase
BigSalmon
text-generation
[ "transformers", "pytorch", "gpt2", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2022-10-08T22:35:14Z
2022-10-10T00:36:04+00:00
32
0
--- {} --- data: https://github.com/BigSalmon2/InformalToFormalDataset Text Generation Informal Formal Phrase Mask Infill Infilling ``` from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BigSalmon/InformalToFormalLincoln84Paraphrase") model = AutoModelForCausalLM.from_pretrained("BigSalmon/InformalToFormalLincoln84Paraphrase") ``` ``` Demo: https://huggingface.co/spaces/BigSalmon/FormalInformalConciseWordy ``` ``` prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:""" input_ids = tokenizer.encode(prompt, return_tensors='pt') outputs = model.generate(input_ids=input_ids, max_length=10 + len(prompt), temperature=1.0, top_k=50, top_p=0.95, do_sample=True, num_return_sequences=5, early_stopping=True) for i in range(5): print(tokenizer.decode(outputs[i])) ``` Most likely outputs (Disclaimer: I highly recommend using this over just generating): ``` prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:""" text = tokenizer.encode(prompt) myinput, past_key_values = torch.tensor([text]), None myinput = myinput myinput= myinput.to(device) logits, past_key_values = model(myinput, past_key_values = past_key_values, return_dict=False) logits = logits[0,-1] probabilities = torch.nn.functional.softmax(logits) best_logits, best_indices = logits.topk(250) best_words = [tokenizer.decode([idx.item()]) for idx in best_indices] text.append(best_indices[0].item()) best_probabilities = probabilities[best_indices].tolist() words = [] print(best_words) ``` ``` How To Make Prompt: informal english: i am very ready to do that just that. Translated into the Style of Abraham Lincoln: you can assure yourself of my readiness to work toward this end. Translated into the Style of Abraham Lincoln: please be assured that i am most ready to undertake this laborious task. *** informal english: space is huge and needs to be explored. Translated into the Style of Abraham Lincoln: space awaits traversal, a new world whose boundaries are endless. Translated into the Style of Abraham Lincoln: space is a ( limitless / boundless ) expanse, a vast virgin domain awaiting exploration. *** informal english: corn fields are all across illinois, visible once you leave chicago. Translated into the Style of Abraham Lincoln: corn fields ( permeate illinois / span the state of illinois / ( occupy / persist in ) all corners of illinois / line the horizon of illinois / envelop the landscape of illinois ), manifesting themselves visibly as one ventures beyond chicago. informal english: ``` ``` original: microsoft word's [MASK] pricing invites competition. Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition. *** original: the library’s quiet atmosphere encourages visitors to [blank] in their work. Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work. ``` ``` Essay Intro (Warriors vs. Rockets in Game 7): text: eagerly anticipated by fans, game 7's are the highlight of the post-season. text: ever-building in suspense, game 7's have the crowd captivated. *** Essay Intro (South Korean TV Is Becoming Popular): text: maturing into a bona fide paragon of programming, south korean television ( has much to offer / entertains without fail / never disappoints ). text: increasingly held in critical esteem, south korean television continues to impress. text: at the forefront of quality content, south korea is quickly achieving celebrity status. *** Essay Intro ( ``` ``` Search: What is the definition of Checks and Balances? https://en.wikipedia.org/wiki/Checks_and_balances Checks and Balances is the idea of having a system where each and every action in government should be subject to one or more checks that would not allow one branch or the other to overly dominate. https://www.harvard.edu/glossary/Checks_and_Balances Checks and Balances is a system that allows each branch of government to limit the powers of the other branches in order to prevent abuse of power https://www.law.cornell.edu/library/constitution/Checks_and_Balances Checks and Balances is a system of separation through which branches of government can control the other, thus preventing excess power. *** Search: What is the definition of Separation of Powers? https://en.wikipedia.org/wiki/Separation_of_powers The separation of powers is a principle in government, whereby governmental powers are separated into different branches, each with their own set of powers, that are prevent one branch from aggregating too much power. https://www.yale.edu/tcf/Separation_of_Powers.html Separation of Powers is the division of governmental functions between the executive, legislative and judicial branches, clearly demarcating each branch's authority, in the interest of ensuring that individual liberty or security is not undermined. *** Search: What is the definition of Connection of Powers? https://en.wikipedia.org/wiki/Connection_of_powers Connection of Powers is a feature of some parliamentary forms of government where different branches of government are intermingled, typically the executive and legislative branches. https://simple.wikipedia.org/wiki/Connection_of_powers The term Connection of Powers describes a system of government in which there is overlap between different parts of the government. *** Search: What is the definition of ``` ``` Search: What are phrase synonyms for "second-guess"? https://www.powerthesaurus.org/second-guess/synonyms Shortest to Longest: - feel dubious about - raise an eyebrow at - wrinkle their noses at - cast a jaundiced eye at - teeter on the fence about *** Search: What are phrase synonyms for "mean to newbies"? https://www.powerthesaurus.org/mean_to_newbies/synonyms Shortest to Longest: - readiness to balk at rookies - absence of tolerance for novices - hostile attitude toward newcomers *** Search: What are phrase synonyms for "make use of"? https://www.powerthesaurus.org/make_use_of/synonyms Shortest to Longest: - call upon - glean value from - reap benefits from - derive utility from - seize on the merits of - draw on the strength of - tap into the potential of *** Search: What are phrase synonyms for "hurting itself"? https://www.powerthesaurus.org/hurting_itself/synonyms Shortest to Longest: - erring - slighting itself - forfeiting its integrity - doing itself a disservice - evincing a lack of backbone *** Search: What are phrase synonyms for " ``` ``` - nebraska - unicamerical legislature - different from federal house and senate text: featuring a unicameral legislature, nebraska's political system stands in stark contrast to the federal model, comprised of a house and senate. *** - penny has practically no value - should be taken out of circulation - just as other coins have been in us history - lost use - value not enough - to make environmental consequences worthy text: all but valueless, the penny should be retired. as with other coins in american history, it has become defunct. too minute to warrant the environmental consequences of its production, it has outlived its usefulness. *** - ``` ``` original: sports teams are profitable for owners. [MASK], their valuations experience a dramatic uptick. infill: sports teams are profitable for owners. ( accumulating vast sums / stockpiling treasure / realizing benefits / cashing in / registering robust financials / scoring on balance sheets ), their valuations experience a dramatic uptick. *** original: ``` ``` wordy: classical music is becoming less popular more and more. Translate into Concise Text: interest in classic music is fading. *** wordy: ``` ``` sweet: savvy voters ousted him. longer: voters who were informed delivered his defeat. *** sweet: ``` ``` 1: commercial space company spacex plans to launch a whopping 52 flights in 2022. 2: spacex, a commercial space company, intends to undertake a total of 52 flights in 2022. 3: in 2022, commercial space company spacex has its sights set on undertaking 52 flights. 4: 52 flights are in the pipeline for 2022, according to spacex, a commercial space company. 5: a commercial space company, spacex aims to conduct 52 flights in 2022. *** 1: ``` Keywords to sentences or sentence. ``` ngos are characterized by: □ voluntary citizens' group that is organized on a local, national or international level □ encourage political participation □ often serve humanitarian functions □ work for social, economic, or environmental change *** what are the drawbacks of living near an airbnb? □ noise □ parking □ traffic □ security □ strangers *** ``` ``` original: musicals generally use spoken dialogue as well as songs to convey the story. operas are usually fully sung. adapted: musicals generally use spoken dialogue as well as songs to convey the story. ( in a stark departure / on the other hand / in contrast / by comparison / at odds with this practice / far from being alike / in defiance of this standard / running counter to this convention ), operas are usually fully sung. *** original: akoya and tahitian are types of pearls. akoya pearls are mostly white, and tahitian pearls are naturally dark. adapted: akoya and tahitian are types of pearls. ( a far cry from being indistinguishable / easily distinguished / on closer inspection / setting them apart / not to be mistaken for one another / hardly an instance of mere synonymy / differentiating the two ), akoya pearls are mostly white, and tahitian pearls are naturally dark. *** original: ``` ``` original: had trouble deciding. translated into journalism speak: wrestled with the question, agonized over the matter, furrowed their brows in contemplation. *** original: ``` ``` input: not loyal 1800s english: ( two-faced / inimical / perfidious / duplicitous / mendacious / double-dealing / shifty ). *** input: ``` ``` first: ( was complicit in / was involved in ). antonym: ( was blameless / was not an accomplice to / had no hand in / was uninvolved in ). *** first: ( have no qualms about / see no issue with ). antonym: ( are deeply troubled by / harbor grave reservations about / have a visceral aversion to / take ( umbrage at / exception to ) / are wary of ). *** first: ( do not see eye to eye / disagree often ). antonym: ( are in sync / are united / have excellent rapport / are like-minded / are in step / are of one mind / are in lockstep / operate in perfect harmony / march in lockstep ). *** first: ``` ``` stiff with competition, law school {A} is the launching pad for countless careers, {B} is a crowded field, {C} ranks among the most sought-after professional degrees, {D} is a professional proving ground. *** languishing in viewership, saturday night live {A} is due for a creative renaissance, {B} is no longer a ratings juggernaut, {C} has been eclipsed by its imitators, {C} can still find its mojo. *** dubbed the "manhattan of the south," atlanta {A} is a bustling metropolis, {B} is known for its vibrant downtown, {C} is a city of rich history, {D} is the pride of georgia. *** embattled by scandal, harvard {A} is feeling the heat, {B} cannot escape the media glare, {C} is facing its most intense scrutiny yet, {D} is in the spotlight for all the wrong reasons. ``` Infill / Infilling / Masking / Phrase Masking (Works pretty decently actually, especially when you use logprobs code from above): ``` his contention [blank] by the evidence [sep] was refuted [answer] *** few sights are as [blank] new york city as the colorful, flashing signage of its bodegas [sep] synonymous with [answer] *** when rick won the lottery, all of his distant relatives [blank] his winnings [sep] clamored for [answer] *** the library’s quiet atmosphere encourages visitors to [blank] in their work [sep] immerse themselves [answer] *** the joy of sport is that no two games are alike. for every exhilarating experience, however, there is an interminable one. the national pastime, unfortunately, has a penchant for the latter. what begins as a summer evening at the ballpark can quickly devolve into a game of tedium. the primary culprit is the [blank] of play. from batters readjusting their gloves to fielders spitting on their mitts, the action is [blank] unnecessary interruptions. the sport's future is [blank] if these tendencies are not addressed [sep] plodding pace [answer] riddled with [answer] bleak [answer] *** microsoft word's [blank] pricing [blank] competition [sep] unconscionable [answer] invites [answer] *** ``` ``` original: microsoft word's [MASK] pricing invites competition. Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition. *** original: the library’s quiet atmosphere encourages visitors to [blank] in their work. Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work. ``` Backwards ``` Essay Intro (National Parks): text: tourists are at ease in the national parks, ( swept up in the beauty of their natural splendor ). *** Essay Intro (D.C. Statehood): washington, d.c. is a city of outsize significance, ( ground zero for the nation's political life / center stage for the nation's political machinations ). ``` ``` topic: the Golden State Warriors. characterization 1: the reigning kings of the NBA. characterization 2: possessed of a remarkable cohesion. characterization 3: helmed by superstar Stephen Curry. characterization 4: perched atop the league’s hierarchy. characterization 5: boasting a litany of hall-of-famers. *** topic: emojis. characterization 1: shorthand for a digital generation. characterization 2: more versatile than words. characterization 3: the latest frontier in language. characterization 4: a form of self-expression. characterization 5: quintessentially millennial. characterization 6: reflective of a tech-centric world. *** topic: ``` ``` regular: illinois went against the census' population-loss prediction by getting more residents. VBG: defying the census' prediction of population loss, illinois experienced growth. *** regular: microsoft word’s high pricing increases the likelihood of competition. VBG: extortionately priced, microsoft word is inviting competition. *** regular: ``` ``` source: badminton should be more popular in the US. QUERY: Based on the given topic, can you develop a story outline? target: (1) games played with racquets are popular, (2) just look at tennis and ping pong, (3) but badminton underappreciated, (4) fun, fast-paced, competitive, (5) needs to be marketed more text: the sporting arena is dominated by games that are played with racquets. tennis and ping pong, in particular, are immensely popular. somewhat curiously, however, badminton is absent from this pantheon. exciting, fast-paced, and competitive, it is an underappreciated pastime. all that it lacks is more effective marketing. *** source: movies in theaters should be free. QUERY: Based on the given topic, can you develop a story outline? target: (1) movies provide vital life lessons, (2) many venues charge admission, (3) those without much money text: the lessons that movies impart are far from trivial. the vast catalogue of cinematic classics is replete with inspiring sagas of friendship, bravery, and tenacity. it is regrettable, then, that admission to theaters is not free. in their current form, the doors of this most vital of institutions are closed to those who lack the means to pay. *** source: ``` ``` in the private sector, { transparency } is vital to the business’s credibility. the { disclosure of information } can be the difference between success and failure. *** the labor market is changing, with { remote work } now the norm. this { flexible employment } allows the individual to design their own schedule. *** the { cubicle } is the locus of countless grievances. many complain that the { enclosed workspace } restricts their freedom of movement. *** ``` ``` it would be natural to assume that americans, as a people whose ancestors { immigrated to this country }, would be sympathetic to those seeking to do likewise. question: what does “do likewise” mean in the above context? (a) make the same journey (b) share in the promise of the american dream (c) start anew in the land of opportunity (d) make landfall on the united states *** in the private sector, { transparency } is vital to the business’s credibility. this orientation can be the difference between success and failure. question: what does “this orientation” mean in the above context? (a) visible business practices (b) candor with the public (c) open, honest communication (d) culture of accountability ``` ``` example: suppose you are a teacher. further suppose you want to tell an accurate telling of history. then suppose a parent takes offense. they do so in the name of name of their kid. this happens a lot. text: educators' responsibility to remain true to the historical record often clashes with the parent's desire to shelter their child from uncomfortable realities. *** example: suppose you are a student at college. now suppose you have to buy textbooks. that is going to be worth hundreds of dollars. given how much you already spend on tuition, that is going to hard cost to bear. text: the exorbitant cost of textbooks, which often reaches hundreds of dollars, imposes a sizable financial burden on the already-strapped college student. ``` ``` <Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle> *** <Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle> ``` ``` accustomed to having its name uttered ______, harvard university is weathering a rare spell of reputational tumult (a) in reverential tones (b) with great affection (c) in adulatory fashion (d) in glowing terms ``` ``` clarify: international ( {working together} / cooperation ) is called for when ( {issue go beyond lots of borders} / an issue transcends borders / a given matter has transnational implications ). ``` ``` description: when someone thinks that their view is the only right one. synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous. *** description: when you put something off. synonyms: shelve, defer, table, postpone. ``` ``` organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea. rewrite phrases: meritocratic, viability, vision rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability. ``` *Note* Of all the masking techniques, this one works the best. ``` <Prefix> the atlanta hawks may attribute <Suffix> trae young <Middle> their robust season to <Middle> *** <Prefix> the nobel prize in literature <Suffix> honor <Middle> is a singularly prestigious <Middle> ``` ``` essence: when someone's views are keeping within reasonable. refine: the senator's voting record is ( moderate / centrist / pragmatic / balanced / fair-minded / even-handed ). *** essence: when things are worked through in a petty way. refine: the propensity of the u.s. congress to settle every dispute by way of ( mudslinging / bickering / demagoguery / name-calling / finger-pointing / vilification ) is appalling. ``` ``` <Suffix> of internationality <Prefix> there are examples of strategies that have <Middle> withstood the test <Middle> ``` ``` test: the movie's success has ..... the producer's earlier failure. (a) overshadowed, (b) obscured, (c) outshone, (d) offset ``` ``` complete: as sales figures soared, so too did [hiring openings] -> employment opportunities. just as noteworthy was [wages increased] -> the effect on wage growth. *** complete: in exchange for a small uptick in the labor bill, they were able to [get holiday season most money possible] -> ( wring the most out of the holiday season / maximize the proceeds of the holiday season / milk the holiday season for all its worth ). ``` ``` h: of all the obligations of adulthood, there is none that elicits more scorn than paying taxes. indeed, any exchange where money is taken and not received in return is bound to be the source of frustration. understandably, the impulse is to want to hold on to every dollar earned. yet, this urge must be tempered by a realization that tax revenue is essential to a functional society. question: what does “this urge” mean in the above context? (a) anti-tax sentiment (b) libertarian disposition (c) yearning to retain every dollar (d) resistance to redistribution (e) misanthropic attitude ```
[ "BEAR" ]
pruas/BENT-PubMedBERT-NER-Organism
pruas
token-classification
[ "transformers", "pytorch", "bert", "token-classification", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-01-14T12:17:32Z
2024-03-02T10:09:47+00:00
32
3
--- language: - en license: apache-2.0 pipeline_tag: token-classification --- Named Entity Recognition (NER) model to recognize organism entities. Please cite our work: ``` @article{NILNKER2022, title = {NILINKER: Attention-based approach to NIL Entity Linking}, journal = {Journal of Biomedical Informatics}, volume = {132}, pages = {104137}, year = {2022}, issn = {1532-0464}, doi = {https://doi.org/10.1016/j.jbi.2022.104137}, url = {https://www.sciencedirect.com/science/article/pii/S1532046422001526}, author = {Pedro Ruas and Francisco M. Couto}, } ``` [PubMedBERT](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) fine-tuned on the following datasets: - [CellFinder](http://cellfinder.org/about/annotation/): entity type "species" - [CRAFT](https://github.com/UCDenver-ccp/CRAFT/tree/master/concept-annotation): entity type "NCBITaxon" - [MLEE](http://nactem.ac.uk/MLEE/):entity type "organism" - [LINNAEUS](http://linnaeus.sourceforge.net/) (train and dev sets): - [Species-800](https://species.jensenlab.org/) - [BioNLP11ID](https://github.com/cambridgeltl/MTL-Bioinformatics-2016/tree/master/data/BioNLP11ID-species-IOB): entity type "Organism" - [BioNLP13CG](https://github.com/cambridgeltl/MTL-Bioinformatics-2016/tree/master/data/BioNLP13CG-species-IOB): entity types "Organism", "Organism subdivision" - [miRNA-Test-Corpus](https://www.scai.fraunhofer.de/en/business-research-areas/bioinformatics/downloads/download-mirna-test-corpus.html): entity type "species" - [Mantra](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4986661/pdf/ocv037.pdf):entity type "DISO"
[ "CRAFT", "CELLFINDER", "LINNAEUS", "MLEE", "MIRNA" ]
BigSalmon/InformalToFormalLincoln98Paraphrase
BigSalmon
text-generation
[ "transformers", "pytorch", "tensorboard", "gpt2", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2023-04-28T21:04:31Z
2023-04-28T21:18:27+00:00
32
0
--- {} --- data: https://github.com/BigSalmon2/InformalToFormalDataset Text Generation Informal Formal ``` from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BigSalmon/InformalToFormalLincoln98Paraphrase") model = AutoModelForCausalLM.from_pretrained("BigSalmon/InformalToFormalLincoln98Paraphrase") ``` ``` Demo: https://huggingface.co/spaces/BigSalmon/FormalInformalConciseWordy ``` ``` prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:""" input_ids = tokenizer.encode(prompt, return_tensors='pt') outputs = model.generate(input_ids=input_ids, max_length=10 + len(prompt), temperature=1.0, top_k=50, top_p=0.95, do_sample=True, num_return_sequences=5, early_stopping=True) for i in range(5): print(tokenizer.decode(outputs[i])) ``` Most likely outputs (Disclaimer: I highly recommend using this over just generating): ``` prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:""" text = tokenizer.encode(prompt) myinput, past_key_values = torch.tensor([text]), None myinput = myinput myinput= myinput.to(device) logits, past_key_values = model(myinput, past_key_values = past_key_values, return_dict=False) logits = logits[0,-1] probabilities = torch.nn.functional.softmax(logits) best_logits, best_indices = logits.topk(250) best_words = [tokenizer.decode([idx.item()]) for idx in best_indices] text.append(best_indices[0].item()) best_probabilities = probabilities[best_indices].tolist() words = [] print(best_words) ``` ``` How To Make Prompt: informal english: i am very ready to do that just that. Translated into the Style of Abraham Lincoln: you can assure yourself of my readiness to work toward this end. Translated into the Style of Abraham Lincoln: please be assured that i am most ready to undertake this laborious task. *** informal english: space is huge and needs to be explored. Translated into the Style of Abraham Lincoln: space awaits traversal, a new world whose boundaries are endless. Translated into the Style of Abraham Lincoln: space is a ( limitless / boundless ) expanse, a vast virgin domain awaiting exploration. *** informal english: corn fields are all across illinois, visible once you leave chicago. Translated into the Style of Abraham Lincoln: corn fields ( permeate illinois / span the state of illinois / ( occupy / persist in ) all corners of illinois / line the horizon of illinois / envelop the landscape of illinois ), manifesting themselves visibly as one ventures beyond chicago. informal english: ``` ``` original: microsoft word's [MASK] pricing invites competition. Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition. *** original: the library’s quiet atmosphere encourages visitors to [blank] in their work. Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work. ``` ``` Essay Intro (Warriors vs. Rockets in Game 7): text: eagerly anticipated by fans, game 7's are the highlight of the post-season. text: ever-building in suspense, game 7's have the crowd captivated. *** Essay Intro (South Korean TV Is Becoming Popular): text: maturing into a bona fide paragon of programming, south korean television ( has much to offer / entertains without fail / never disappoints ). text: increasingly held in critical esteem, south korean television continues to impress. text: at the forefront of quality content, south korea is quickly achieving celebrity status. *** Essay Intro ( ``` ``` Search: What is the definition of Checks and Balances? https://en.wikipedia.org/wiki/Checks_and_balances Checks and Balances is the idea of having a system where each and every action in government should be subject to one or more checks that would not allow one branch or the other to overly dominate. https://www.harvard.edu/glossary/Checks_and_Balances Checks and Balances is a system that allows each branch of government to limit the powers of the other branches in order to prevent abuse of power https://www.law.cornell.edu/library/constitution/Checks_and_Balances Checks and Balances is a system of separation through which branches of government can control the other, thus preventing excess power. *** Search: What is the definition of Separation of Powers? https://en.wikipedia.org/wiki/Separation_of_powers The separation of powers is a principle in government, whereby governmental powers are separated into different branches, each with their own set of powers, that are prevent one branch from aggregating too much power. https://www.yale.edu/tcf/Separation_of_Powers.html Separation of Powers is the division of governmental functions between the executive, legislative and judicial branches, clearly demarcating each branch's authority, in the interest of ensuring that individual liberty or security is not undermined. *** Search: What is the definition of Connection of Powers? https://en.wikipedia.org/wiki/Connection_of_powers Connection of Powers is a feature of some parliamentary forms of government where different branches of government are intermingled, typically the executive and legislative branches. https://simple.wikipedia.org/wiki/Connection_of_powers The term Connection of Powers describes a system of government in which there is overlap between different parts of the government. *** Search: What is the definition of ``` ``` Search: What are phrase synonyms for "second-guess"? https://www.powerthesaurus.org/second-guess/synonyms Shortest to Longest: - feel dubious about - raise an eyebrow at - wrinkle their noses at - cast a jaundiced eye at - teeter on the fence about *** Search: What are phrase synonyms for "mean to newbies"? https://www.powerthesaurus.org/mean_to_newbies/synonyms Shortest to Longest: - readiness to balk at rookies - absence of tolerance for novices - hostile attitude toward newcomers *** Search: What are phrase synonyms for "make use of"? https://www.powerthesaurus.org/make_use_of/synonyms Shortest to Longest: - call upon - glean value from - reap benefits from - derive utility from - seize on the merits of - draw on the strength of - tap into the potential of *** Search: What are phrase synonyms for "hurting itself"? https://www.powerthesaurus.org/hurting_itself/synonyms Shortest to Longest: - erring - slighting itself - forfeiting its integrity - doing itself a disservice - evincing a lack of backbone *** Search: What are phrase synonyms for " ``` ``` - nebraska - unicamerical legislature - different from federal house and senate text: featuring a unicameral legislature, nebraska's political system stands in stark contrast to the federal model, comprised of a house and senate. *** - penny has practically no value - should be taken out of circulation - just as other coins have been in us history - lost use - value not enough - to make environmental consequences worthy text: all but valueless, the penny should be retired. as with other coins in american history, it has become defunct. too minute to warrant the environmental consequences of its production, it has outlived its usefulness. *** - ``` ``` original: sports teams are profitable for owners. [MASK], their valuations experience a dramatic uptick. infill: sports teams are profitable for owners. ( accumulating vast sums / stockpiling treasure / realizing benefits / cashing in / registering robust financials / scoring on balance sheets ), their valuations experience a dramatic uptick. *** original: ``` ``` wordy: classical music is becoming less popular more and more. Translate into Concise Text: interest in classic music is fading. *** wordy: ``` ``` sweet: savvy voters ousted him. longer: voters who were informed delivered his defeat. *** sweet: ``` ``` 1: commercial space company spacex plans to launch a whopping 52 flights in 2022. 2: spacex, a commercial space company, intends to undertake a total of 52 flights in 2022. 3: in 2022, commercial space company spacex has its sights set on undertaking 52 flights. 4: 52 flights are in the pipeline for 2022, according to spacex, a commercial space company. 5: a commercial space company, spacex aims to conduct 52 flights in 2022. *** 1: ``` Keywords to sentences or sentence. ``` ngos are characterized by: □ voluntary citizens' group that is organized on a local, national or international level □ encourage political participation □ often serve humanitarian functions □ work for social, economic, or environmental change *** what are the drawbacks of living near an airbnb? □ noise □ parking □ traffic □ security □ strangers *** ``` ``` original: musicals generally use spoken dialogue as well as songs to convey the story. operas are usually fully sung. adapted: musicals generally use spoken dialogue as well as songs to convey the story. ( in a stark departure / on the other hand / in contrast / by comparison / at odds with this practice / far from being alike / in defiance of this standard / running counter to this convention ), operas are usually fully sung. *** original: akoya and tahitian are types of pearls. akoya pearls are mostly white, and tahitian pearls are naturally dark. adapted: akoya and tahitian are types of pearls. ( a far cry from being indistinguishable / easily distinguished / on closer inspection / setting them apart / not to be mistaken for one another / hardly an instance of mere synonymy / differentiating the two ), akoya pearls are mostly white, and tahitian pearls are naturally dark. *** original: ``` ``` original: had trouble deciding. translated into journalism speak: wrestled with the question, agonized over the matter, furrowed their brows in contemplation. *** original: ``` ``` input: not loyal 1800s english: ( two-faced / inimical / perfidious / duplicitous / mendacious / double-dealing / shifty ). *** input: ``` ``` first: ( was complicit in / was involved in ). antonym: ( was blameless / was not an accomplice to / had no hand in / was uninvolved in ). *** first: ( have no qualms about / see no issue with ). antonym: ( are deeply troubled by / harbor grave reservations about / have a visceral aversion to / take ( umbrage at / exception to ) / are wary of ). *** first: ( do not see eye to eye / disagree often ). antonym: ( are in sync / are united / have excellent rapport / are like-minded / are in step / are of one mind / are in lockstep / operate in perfect harmony / march in lockstep ). *** first: ``` ``` stiff with competition, law school {A} is the launching pad for countless careers, {B} is a crowded field, {C} ranks among the most sought-after professional degrees, {D} is a professional proving ground. *** languishing in viewership, saturday night live {A} is due for a creative renaissance, {B} is no longer a ratings juggernaut, {C} has been eclipsed by its imitators, {C} can still find its mojo. *** dubbed the "manhattan of the south," atlanta {A} is a bustling metropolis, {B} is known for its vibrant downtown, {C} is a city of rich history, {D} is the pride of georgia. *** embattled by scandal, harvard {A} is feeling the heat, {B} cannot escape the media glare, {C} is facing its most intense scrutiny yet, {D} is in the spotlight for all the wrong reasons. ``` Infill / Infilling / Masking / Phrase Masking (Works pretty decently actually, especially when you use logprobs code from above): ``` his contention [blank] by the evidence [sep] was refuted [answer] *** few sights are as [blank] new york city as the colorful, flashing signage of its bodegas [sep] synonymous with [answer] *** when rick won the lottery, all of his distant relatives [blank] his winnings [sep] clamored for [answer] *** the library’s quiet atmosphere encourages visitors to [blank] in their work [sep] immerse themselves [answer] *** the joy of sport is that no two games are alike. for every exhilarating experience, however, there is an interminable one. the national pastime, unfortunately, has a penchant for the latter. what begins as a summer evening at the ballpark can quickly devolve into a game of tedium. the primary culprit is the [blank] of play. from batters readjusting their gloves to fielders spitting on their mitts, the action is [blank] unnecessary interruptions. the sport's future is [blank] if these tendencies are not addressed [sep] plodding pace [answer] riddled with [answer] bleak [answer] *** microsoft word's [blank] pricing [blank] competition [sep] unconscionable [answer] invites [answer] *** ``` ``` original: microsoft word's [MASK] pricing invites competition. Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition. *** original: the library’s quiet atmosphere encourages visitors to [blank] in their work. Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work. ``` Backwards ``` Essay Intro (National Parks): text: tourists are at ease in the national parks, ( swept up in the beauty of their natural splendor ). *** Essay Intro (D.C. Statehood): washington, d.c. is a city of outsize significance, ( ground zero for the nation's political life / center stage for the nation's political machinations ). ``` ``` topic: the Golden State Warriors. characterization 1: the reigning kings of the NBA. characterization 2: possessed of a remarkable cohesion. characterization 3: helmed by superstar Stephen Curry. characterization 4: perched atop the league’s hierarchy. characterization 5: boasting a litany of hall-of-famers. *** topic: emojis. characterization 1: shorthand for a digital generation. characterization 2: more versatile than words. characterization 3: the latest frontier in language. characterization 4: a form of self-expression. characterization 5: quintessentially millennial. characterization 6: reflective of a tech-centric world. *** topic: ``` ``` regular: illinois went against the census' population-loss prediction by getting more residents. VBG: defying the census' prediction of population loss, illinois experienced growth. *** regular: microsoft word’s high pricing increases the likelihood of competition. VBG: extortionately priced, microsoft word is inviting competition. *** regular: ``` ``` source: badminton should be more popular in the US. QUERY: Based on the given topic, can you develop a story outline? target: (1) games played with racquets are popular, (2) just look at tennis and ping pong, (3) but badminton underappreciated, (4) fun, fast-paced, competitive, (5) needs to be marketed more text: the sporting arena is dominated by games that are played with racquets. tennis and ping pong, in particular, are immensely popular. somewhat curiously, however, badminton is absent from this pantheon. exciting, fast-paced, and competitive, it is an underappreciated pastime. all that it lacks is more effective marketing. *** source: movies in theaters should be free. QUERY: Based on the given topic, can you develop a story outline? target: (1) movies provide vital life lessons, (2) many venues charge admission, (3) those without much money text: the lessons that movies impart are far from trivial. the vast catalogue of cinematic classics is replete with inspiring sagas of friendship, bravery, and tenacity. it is regrettable, then, that admission to theaters is not free. in their current form, the doors of this most vital of institutions are closed to those who lack the means to pay. *** source: ``` ``` in the private sector, { transparency } is vital to the business’s credibility. the { disclosure of information } can be the difference between success and failure. *** the labor market is changing, with { remote work } now the norm. this { flexible employment } allows the individual to design their own schedule. *** the { cubicle } is the locus of countless grievances. many complain that the { enclosed workspace } restricts their freedom of movement. *** ``` ``` it would be natural to assume that americans, as a people whose ancestors { immigrated to this country }, would be sympathetic to those seeking to do likewise. question: what does “do likewise” mean in the above context? (a) make the same journey (b) share in the promise of the american dream (c) start anew in the land of opportunity (d) make landfall on the united states *** in the private sector, { transparency } is vital to the business’s credibility. this orientation can be the difference between success and failure. question: what does “this orientation” mean in the above context? (a) visible business practices (b) candor with the public (c) open, honest communication (d) culture of accountability ``` ``` example: suppose you are a teacher. further suppose you want to tell an accurate telling of history. then suppose a parent takes offense. they do so in the name of name of their kid. this happens a lot. text: educators' responsibility to remain true to the historical record often clashes with the parent's desire to shelter their child from uncomfortable realities. *** example: suppose you are a student at college. now suppose you have to buy textbooks. that is going to be worth hundreds of dollars. given how much you already spend on tuition, that is going to hard cost to bear. text: the exorbitant cost of textbooks, which often reaches hundreds of dollars, imposes a sizable financial burden on the already-strapped college student. ``` ``` <Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle> *** <Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle> ``` ``` accustomed to having its name uttered ______, harvard university is weathering a rare spell of reputational tumult (a) in reverential tones (b) with great affection (c) in adulatory fashion (d) in glowing terms ``` ``` clarify: international ( {working together} / cooperation ) is called for when ( {issue go beyond lots of borders} / an issue transcends borders / a given matter has transnational implications ). ``` ``` description: when someone thinks that their view is the only right one. synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous. *** description: when you put something off. synonyms: shelve, defer, table, postpone. ``` ``` organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea. rewrite phrases: meritocratic, viability, vision rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability. ``` *Note* Of all the masking techniques, this one works the best. ``` <Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle> *** <Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle> ``` ``` essence: when someone's views are keeping within reasonable. refine: the senator's voting record is ( moderate / centrist / pragmatic / balanced / fair-minded / even-handed ). *** essence: when things are worked through in a petty way. refine: the propensity of the u.s. congress to settle every dispute by way of ( mudslinging / bickering / demagoguery / name-calling / finger-pointing / vilification ) is appalling. ``` ``` description: when someone thinks that their view is the only right one. synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous. *** description: when you put something off. synonyms: shelve, defer, table, postpone. ``` ``` organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea. rewrite phrases: meritocratic, viability, vision rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability. ``` ``` music before bedtime [makes for being able to relax] -> is a recipe for relaxation. ``` ``` [people wanting entertainment love traveling new york city] -> travelers flock to new york city in droves, drawn to its iconic entertainment scene. [cannot blame them] -> one cannot fault them [broadway so fun] -> when it is home to such thrilling fare as Broadway. ``` ``` in their ( ‖ when you are rushing because you want to get there on time ‖ / haste to arrive punctually / mad dash to be timely ), morning commuters are too rushed to whip up their own meal. *** politicians prefer to author vague plans rather than ( ‖ when you can make a plan without many unknowns ‖ / actionable policies / concrete solutions ). ``` ``` Q: What is whistleblower protection? A: Whistleblower protection is a form of legal immunity granted to employees who expose the unethical practices of their employer. Q: Why are whistleblower protections important? A: Absent whistleblower protections, employees would be deterred from exposing their employer’s wrongdoing for fear of retribution. Q: Why would an employer engage in retribution? A: An employer who has acted unethically stands to suffer severe financial and reputational damage were their transgressions to become public. To safeguard themselves from these consequences, they might seek to dissuade employees from exposing their wrongdoing. ``` ``` original: the meritocratic nature of crowdfunding [MASK] into their vision's viability. infill: the meritocratic nature of crowdfunding [gives investors idea of how successful] -> ( offers entrepreneurs a window ) into their vision's viability. ``` ``` Leadership | Lecture 17: Worker Morale What Workers Look for in Companies: • Benefits o Tuition reimbursement o Paid parental leave o 401K matching o Profit sharing o Pension plans o Free meals • Social responsibility o Environmental stewardship o Charitable contributions o Diversity • Work-life balance o Telecommuting o Paid holidays and vacation o Casual dress • Growth opportunities • Job security • Competitive compensation • Recognition o Open-door policies o Whistleblower protection o Employee-of-the-month awards o Positive performance reviews o Bonuses ``` ``` description: business keywords: for-profit, fiduciary duty, monopolistic, bottom line, return on investment, short-term thinking, capital-intensive, self-interested, risk-taking, fiduciary duty, merger, speculation, profiteering, oversight, capitalism, diversification ``` ``` 3. In this task, you are given a company name and you need to find its industry. McDonalds -- Restaurant Facebook -- Social Network IKEA -- Furniture American Express -- Credit Services Nokia -- Telecom Nintendo -- Entertainment 4. In this task, you are given a Month and you need to convert it to its corresponding season April -- Spring December -- Winter July -- Summer October -- Fall February -- Winter 5. In this task, you are given a sentence with a missing word and you need to predict the correct word. Managers should set an _____ for their employees. -- example Some people spend more than four _____ in the gym. -- hours The police were on the _____ of arresting the suspect. -- verge They were looking for _____ on how to solve the problem. -- guidance What is the _____ of the coffee? -- price 6. In this task, you are given a paragraph and you need to reorder it to make it logical. It was first proposed in 1987. The total length of the bridge is 1,828 meters. The idea of a bridge connects Hong Kong to Macau. -- The idea of bridge connecting Hong Kong and Macau was first proposed in 1987. The total length of the bridge is 1,828 meters. It is a movie about a brave and noble policeman. The film was produced by Americans. They were Kevin Lima and Chris Buck. They are directors. The movie is called Tarzan. -- Produced by Americans Kevin Lima and Chris Buck, Tarzan is a movie about a brave and noble policeman. It was first discovered in the mountains of India. The active ingredients in this plant can stimulate hair growth. The plant is called "Hair Plus." -- First discovered in the mountains of India, Hair Plus is a plant whose active ingredients can stimulate hair growth. ``` ``` trivia: What is the population of South Korea? response: 51 million. *** trivia: What is the minimum voting age in the US? response: 18. *** trivia: What are the first ten amendments of the US constitution called? response: Bill of Rights. ``` ``` ideas: in modern-day america, it is customary for the commander-in-chief to conduct regular press conferences related keywords: transparency, check and balance, sacrosanct, public accountability, adversarial, unscripted, direct access, open government, watchdog, healthy democracy, institutional integrity, right to know, direct line of communication, behind closed doors, updates, track progress, instill confidence, reassure, humanize, leadership style, day-to-day, forthcoming, demystify, ask hard questions *** ideas: i know this one guy who retired so young, attesting to how careful they were with money. related keywords: money management, resourceful, penny-pinching, live below their means, frugal, financial discipline, financial independence, conservative, long-term vision, discretionary spending, deferred gratification, preparedness, self-control, cushion ``` ``` less specific: actors and musicians should ( support democracy ). clarifies: actors and musicians should ( wield their celebrity to amplify pro-democracy messaging / marshal their considerable influence in the service of the democratic cause ). *** less specific: amid a contemporary culture that thrives on profligacy, the discipline necessary to retire early is a vanishing quality. rather than yielding to the lure of indulgence, the aspiring retiree must ( be careful ). clarifies: amid a contemporary culture that thrives on profligacy, the discipline necessary to retire early is a vanishing quality. rather than yielding to the lure of indulgence, the aspiring retiree must ( master their desires / exercise self-restraint / embrace frugality / restrain their appetite for splendor ). ``` ``` dull: clean emotional heft: spotless, immaculate, pristine *** dull: hot emotional heft: scorching, searing, blistering *** dull: happy emotional heft: euphoric ``` ``` text: {guide: vividly describe the premise of the show "seinfield"} -> set in the heart of bustling new york city, the sitcom "seinfield" follows the everyday {restrict: term that implies they get into trouble but in a comical way} -> misadventures of four neurotic friends. on any given episode, one can find them quarreling over their favorite diner's latest menu change, haggling over the division of household expenses, or contriving a scheme to spy on the apartment's newest resident. mundane as their exploits may be, they never fail to elicit a hearty laugh. {guide: mention how larry david is responsible} -> behind the show's witty, incisive dialogue lies the sharp pen of larry david, who co-created the show with jerry seinfeld. {guide: mention how larry david came up with the most recognizable lines} -> it is his genius that conjured such instantly {restrict: term that imply everybody knows them} -> recognizable quips as "no soup for you!" and "not that there's anything wrong with that!". {guide: mention how humanity should revel in having such good comedians these days} -> as this list of laugh-out-loud lines attests, the world is fortunate to ( count such a sharp comedic mind among its ranks / have such a talented humorist in its midst / have such comedic talent gracing its airwaves ). ``` ``` system: i'm not sure i agree with your assessment of the situation. user: replace "assessment" with a more casual term. chatbot: ( take / read / view ). system: i've been feeling really busy lately, trying to balance work and family responsibilities. user: replace "busy" with a more intense word that conveys it is too much. chatbot: overwhelmed. system: the candidate's stance on immigration is quite nebulous, and it's difficult to discern exactly what they would do if elected. user: replace "nebulous" with a word that conveys a lack of detail. chatbot: ( vague / ambiguous ). ``` ``` user: exorbitant in price, scholarly journals unconscionably define the breadth of one's knowledge awareness by the contents of their wallet. [replace “knowledge awareness” with a more natural expression] chatbot: intellectual horizons. user: can you do another alternative to “intellectual horizons” that has more relation to “scholarly journals”? chatbot: academic enlightenment. ``` ``` key: calculate. syn: estimate, consider, weigh, number, count, apportion, proportion, investigate, reckon, rate, compute. ant: guess, conjecture, hit, chance, risk, stake, miscalculate. ```
[ "BEAR" ]
mindrage/Manticore-13B-Chat-Pyg-Guanaco-GGML
mindrage
text-generation
[ "transformers", "llama", "text-generation", "manticore", "guanaco", "uncensored", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-06-02T11:57:25Z
2023-06-12T08:02:11+00:00
32
36
--- library_name: transformers pipeline_tag: text-generation tags: - manticore - guanaco - uncensored --- --- # GGML of: Manticore-13b-Chat-Pyg by [openaccess-ai-collective](https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg) with the Guanaco 13b qLoRa by [TimDettmers](https://huggingface.co/timdettmers/guanaco-13b) applied through [Monero](https://huggingface.co/Monero/Manticore-13b-Chat-Pyg-Guanaco), quantized by [mindrage](https://huggingface.co/mindrage), uncensored 12.06.2023: Added versions quantized with the new method (less precision loss relative to compression ratio, but slower (for now)): q2_K, q3_KM, q4_KS, q4_KM, q5_KS Old Quant method: q4_0, q5_0 and q8_0 versions available [link to GPTQ Version](https://huggingface.co/mindrage/Manticore-13B-Chat-Pyg-Guanaco-GPTQ-4bit-128g.no-act-order.safetensors) --- Files are quantized using the newest llama.cpp and will therefore only work with llama.cpp versions compiled after May 19th, 2023. The model seems to have noticeably benefited from further augmentation with the Guanaco qLora. Its capabilities seem broad, even compared with other Wizard or Manticore models, with expected weaknesses at coding. It is very good at in-context-learning and (in its class) reasoning. It both follows instructions well, and can be used as a chatbot. Refreshingly, it does not seem to insist on aggressively sticking to narratives to justify formerly hallucinated output as much as similar models. It's output seems... eerily smart at times. I believe the model is fully unrestricted/uncensored and will generally not berate. --- Prompting style + settings: --- Presumably due to the very diverse training-data the model accepts a variety of prompting styles with relatively few issues, including the ###-Variant, but seems to work best using: # "Naming" the model works great by simply modifying the context. Substantial changes in its behaviour can be caused by appending to "ASSISTANT:", like "ASSISTANT: After careful consideration, thinking step-by-step, my response is:" user: "USER:" - bot: "ASSISTANT:" - context: "This is a conversation between an advanced AI and a human user." Turn Template: <|user|> <|user-message|>\n<|bot|><|bot-message|>\n Settings that work well without (subjectively) being too deterministic: temp: 0.15 - top_p: 0.1 - top_k: 40 - rep penalty: 1.1 ---
[ "MONERO" ]
medspaner/xlm-roberta-large-spanish-trials-cases-7sgs-umls
medspaner
token-classification
[ "transformers", "pytorch", "xlm-roberta", "token-classification", "generated_from_trainer", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-09-29T11:19:37Z
2024-10-01T06:33:30+00:00
32
0
--- license: cc-by-nc-4.0 metrics: - precision - recall - f1 - accuracy tags: - generated_from_trainer widget: - text: "Criterios de inclusión: 18 a 65 años; necrosis avascular de cadera; sintomática\ \ de menos de 6 meses; capaz de otorgar consentimiento informado.\n Criterios\ \ de exclusión: embarazo, lactancia, mujer fértil sin métodos anticonceptivos\ \ adecuados; tratamiento activo con bifosfonatos; infección por VIH, hepatitis\ \ B o hepatitis C; historia de neoplasia en cualquier organo." - text: 'Recuperación de daño hepático relacionado con nutrición parenteral con ácidos omega-3 en adultos críticos: ensayo clínico aleatorizado.' - text: 'Título público: Análisis del dolor tras inyección intramuscular de penicilina con agujas de mayor calibre y anestésico local, frente a aguja tradicional sin anestésico en pacientes con sífilis' model-index: - name: roberta-large-spanish-trials-cases-7sgs-umls results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # xlm-roberta-large-spanish-trials-cases-7sgs-umls This medical named entity recognition model detects 7 types of semantic groups from the [Unified Medical Language System (UMLS)](https://www.nlm.nih.gov/research/umls/index.html) ([Bodenreider 2004](https://academic.oup.com/nar/article/32/suppl_1/D267/2505235)): - ANAT: body parts and anatomy (e.g. *garganta*, 'throat') - CHEM: chemical entities and pharmacological substances (e.g. *aspirina*,'aspirin') - DEVI: medical devices (e.g. *catéter*, 'catheter') - DISO: pathologic conditions (e.g. *dolor*, 'pain') - LIVB: living beings (e.g. *paciente*, 'patient') - PHYS: physiological processes (e.g. *respiración*, 'breathing') - PROC: diagnostic and therapeutic procedures, laboratory analyses and medical research activities (e.g. *cirugía*, 'surgery') The model achieves the following results on the test set (when trained with the training and development set; results are averaged over 5 evaluation rounds): - Precision: 0.905 (±0.007) - Recall: 0.916 (±0.004) - F1: 0.910 (±0.005) - Accuracy: 0.955 (±0.002) ## Model description This model adapts the pre-trained model [xlm-roberta-large-spanish-clinical](https://huggingface.co/llange/xlm-roberta-large-spanish-clinical), presented in [Lange et al. (2022)](https://academic.oup.com/bioinformatics/article/38/12/3267/6575884). It is fine-tuned to conduct medical named entity recognition on texts about in Spanish. The model is fine-tuned on the [CT-EBM-ES corpus (Campillos-Llanos et al. 2021)](https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01395-z) and 100 clinical cases with Creative Commons License. If you use this model, please, cite as follows: ``` @article{campillosetal2024,         title = {{Hybrid tool for semantic annotation and concept extraction of medical texts in Spanish}},         author = {Campillos-Llanos, Leonardo and Valverde-Mateos, Ana and Capllonch-Carri{\'o}n, Adri{\'a}n},         journal = {BMC Bioinformatics}, year={2024}, publisher={BioMed Central} } ``` ## Intended uses & limitations **Disclosure**: *This model is under development and needs to be improved. It should not be used for medical decision making without human assistance and supervision* This model is intended for a generalist purpose, and may have bias and/or any other undesirable distortions. Third parties who deploy or provide systems and/or services using any of these models (or using systems based on these models) should note that it is their responsibility to mitigate the risks arising from their use. Third parties, in any event, need to comply with applicable regulations, including regulations concerning the use of artificial intelligence. The owner or creator of the models will in no event be liable for any results arising from the use made by third parties of these models. **Descargo de responsabilidad**: *Esta herramienta se encuentra en desarrollo y no debe ser empleada para la toma de decisiones médicas* La finalidad de este modelo es generalista, y se advierte que puede tener sesgos y/u otro tipo de distorsiones indeseables. Terceras partes que desplieguen o proporcionen sistemas y/o servicios usando alguno de estos modelos (o utilizando sistemas basados en estos modelos) han tener presente que es su responsabilidad abordar y minimizar los riesgos derivados de su uso. Las terceras partes, en cualquier circunstancia, deben cumplir con la normativa aplicable, incluyendo la normativa que concierne al uso de la inteligencia artificial. El propietario o creador de los modelos de ningún modo será responsable de los resultados derivados del uso que las terceras partes hagan de estos modelos. ## Training and evaluation data The data used for fine-tuning are the [Clinical Trials for Evidence-Based-Medicine in Spanish corpus](http://www.lllf.uam.es/ESP/nlpdata/wp2/). It is a collection of 1200 texts about clinical trials studies and clinical trials announcements: - 500 abstracts from journals published under a Creative Commons license, e.g. available in PubMed or the Scientific Electronic Library Online (SciELO) - 700 clinical trials announcements published in the European Clinical Trials Register and Repositorio Español de Estudios Clínicos If you use the CT-EBM-ES resource, please, cite as follows: ``` @article{campillosetal-midm2021,         title = {A clinical trials corpus annotated with UMLS© entities to enhance the access to Evidence-Based Medicine},         author = {Campillos-Llanos, Leonardo and Valverde-Mateos, Ana and Capllonch-Carri{\'o}n, Adri{\'a}n and Moreno-Sandoval, Antonio},         journal = {BMC Medical Informatics and Decision Making},         volume={21}, number={1}, pages={1--19}, year={2021}, publisher={BioMed Central} } ``` To fine-tune the model, we also used 100 clinical cases with Creative Commons licences. ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: we used different seeds for 5 evaluation rounds, and uploaded the model with the best results - optimizer: Adam - num_epochs: average 21.75 epochs (±6.34); trained with early stopping if no improvement after 5 epochs (early stopping patience: 5) ### Training results (test set; average and standard deviation of 5 rounds with different seeds) | Precision | Recall | F1 | Accuracy | |:--------------:|:--------------:|:--------------:|:--------------:| | 0.905 (±0.007) | 0.916 (±0.004) | 0.910 (±0.005) | 0.955 (±0.002) | ### Framework versions - Transformers 4.17.0 - Pytorch 1.10.2+cu113 - Datasets 1.18.4 - Tokenizers 0.11.6
[ "SCIELO" ]
yeajinmin/NER-NewsBI-150142-e3b4
yeajinmin
token-classification
[ "transformers", "safetensors", "xlm-roberta", "token-classification", "ko", "dataset:yeajinmin/NER-News-BIDataset", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-01-06T10:12:35Z
2025-01-15T07:18:20+00:00
32
3
--- datasets: - yeajinmin/NER-News-BIDataset language: - ko --- ## Model Details ### Model Description NER-NewsBI-150142-e3b4 can recognize named entities in input sentences and predicts one label from a set of 150 labels for each named entity, thereby performing labeling for the input sentences. In particular, it is specialized for articles because it was trained using a news dataset. - base model: https://huggingface.co/xlm-roberta-large-finetuned-conll03-english - tokenizer: "xlm-roberta-large-finetuned-conll03-english" - dataset: https://huggingface.co/datasets/yeajinmin/NER-News-BIDataset Because the Base Model is a multilingual model, even though it was trained only for Korean, it can recognize entity names with 150 labels for other languages. Available languages can be checked in the language of the base model above. ### Training scores | Epoch | Training Loss | Validation Loss | F1 | |-------|---------------|------------------|----------| | 1 | 0.237400 | 0.213017 | 0.791144 | | 2 | 0.177400 | 0.174727 | 0.839951 | | 3 | 0.119500 | 0.157669 | 0.862055 | TrainOutput(global_step=90087, training_loss=0.19955111364530848, metrics={'train_runtime': 11692.8865, 'train_samples_per_second': 30.817, 'train_steps_per_second': 7.704, 'total_flos': 4.889673580336036e+16, 'train_loss': 0.19955111364530848, 'epoch': 3.0}) ## Uses ### Main Use The 151 entity name recognition labels that this model can recognize in sentences are listed in the table below. |index|0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31|32|33|34|35|36|37|38|39|40|41|42|43|44|45|46|47|48|49|50|51|52|53|54|55|56|57|58|59|60|61|62|63|64|65|66|67|68|69|70|71|72|73|74|75|76|77|78|79|80|81|82|83|84|85|86|87|88|89|90|91|92|93|94|95|96|97|98|99|100|101|102|103|104|105|106|107|108|109|110|111|112|113|114|115|116|117|118|119|120|121|122|123|124|125|126|127|128|129|130|131|132|133|134|135|136|137|138|139|140|141|142|143|144|145|146|147|148|149|150| |---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---| |Label|O|PS\_NAME|PS\_CHARACTER|PS\_PET|FD\_SCIENCE|FD\_SOCIAL\_SCIENCE|FD\_MEDICINE|FD\_ART|FD\_HUMANITIES|FD\_OTHERS|TR\_SCIENCE|TR\_SOCIAL\_SCIENCE|TR\_MEDICINE|TR\_ART|TR\_HUMANITIES|TR\_OTHERS|AF\_BUILDING|AF\_CULTURAL\_ASSET|AF\_ROAD|AF\_TRANSPORT|AF\_MUSICAL\_INSTRUMENT|AF\_WEAPON|AFA\_DOCUMENT|AFA\_PERFORMANCE|AFA\_VIDEO|AFA\_ART\_CRAFT|AFA\_MUSIC|AFW\_SERVICE\_PRODUCTS|AFW\_OTHER\_PRODUCTS|OGG\_ECONOMY|OGG\_EDUCATION|OGG\_MILITARY|OGG\_MEDIA|OGG\_SPORTS|OGG\_ART|OGG\_MEDICINE|OGG\_RELIGION|OGG\_SCIENCE|OGG\_LIBRARY|OGG\_LAW|OGG\_POLITICS|OGG\_FOOD|OGG\_HOTEL|OGG\_OTHERS|LCP\_COUNTRY|LCP\_PROVINCE|LCP\_COUNTY|LCP\_CITY|LCP\_CAPITALCITY|LCG\_RIVER|LCG\_OCEAN|LCG\_BAY|LCG\_MOUNTAIN|LCG\_ISLAND|LCG\_CONTINENT|LC\_SPACE|LC\_OTHERS|CV\_CULTURE|CV\_TRIBE|CV\_LANGUAGE|CV\_POLICY|CV\_LAW|CV\_CURRENCY|CV\_TAX|CV\_FUNDS|CV\_ART|CV\_SPORTS|CV\_SPORTS\_POSITION|CV\_SPORTS\_INST|CV\_PRIZE|CV\_RELATION|CV\_OCCUPATION|CV\_POSITION|CV\_FOOD|CV\_DRINK|CV\_FOOD\_STYLE|CV\_CLOTHING|CV\_BUILDING\_TYPE|DT\_DURATION|DT\_DAY|DT\_WEEK|DT\_MONTH|DT\_YEAR|DT\_SEASON|DT\_GEOAGE|DT\_DYNASTY|DT\_OTHERS|TI\_DURATION|TI\_HOUR|TI\_MINUTE|TI\_SECOND|TI\_OTHERS|QT\_AGE|QT\_SIZE|QT\_LENGTH|QT\_COUNT|QT\_MAN\_COUNT|QT\_WEIGHT|QT\_PERCENTAGE|QT\_SPEED|QT\_TEMPERATURE|QT\_VOLUME|QT\_ORDER|QT\_PRICE|QT\_PHONE|QT\_SPORTS|QT\_CHANNEL|QT\_ALBUM|QT\_ADDRESS|QT\_OTHERS|EV\_ACTIVITY|EV\_WAR\_REVOLUTION|EV\_SPORTS|EV\_FESTIVAL|EV\_OTHERS|AM\_INSECT|AM\_BIRD|AM\_FISH|AM\_MAMMALIA|AM\_AMPHIBIA|AM\_REPTILIA|AM\_TYPE|AM\_PART|AM\_OTHERS|PT\_FRUIT|PT\_FLOWER|PT\_TREE|PT\_GRASS|PT\_TYPE|PT\_PART|PT\_OTHERS|MT\_ELEMENT|MT\_METAL|MT\_ROCK|MT\_CHEMICAL|TM\_COLOR|TM\_DIRECTION|TM\_CLIMATE|TM\_SHAPE|TM\_CELL\_TISSUE\_ORGAN|TMM\_DISEASE|TMM\_DRUG|TMI\_HW|TMI\_SW|TMI\_SITE|TMI\_EMAIL|TMI\_MODEL|TMI\_SERVICE|TMI\_PROJECT|TMIG\_GENRE|TM\_SPORTS| ### How to Use ```python from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("yeajinmin/NER-NewsBI-150142-e3b4") model = AutoModelForTokenClassification.from_pretrained("yeajinmin/NER-NewsBI-150142-e3b4") from transformers import pipeline nlp_ner = pipeline("ner", model=model, tokenizer=tokenizer) text = "미국인 친구 Lisa에게 서울의 지하철 1호선만으로는 대구에 갈 수 없다고 알려주었다." results = nlp_ner(text) print(results) # for tabular output import pandas as pd df = pd.DataFrame([(result['word'], result['entity']) for result in results], columns=["단어", "개체명"]) print(df.to_markdown(index=False)) ``` The definition of index2tag and tag2index is required to classify the 150 NER labels. The code is below: ```python label_mapping = {'O': 0, 'PS_NAME': 1, 'PS_CHARACTER': 2, 'PS_PET': 3, 'FD_SCIENCE': 4, 'FD_SOCIAL_SCIENCE': 5, 'FD_MEDICINE': 6, 'FD_ART':7, 'FD_HUMANITIES': 8, 'FD_OTHERS': 9, 'TR_SCIENCE': 10, 'TR_SOCIAL_SCIENCE': 11, 'TR_MEDICINE': 12, 'TR_ART': 13, 'TR_HUMANITIES': 14, 'TR_OTHERS': 15, 'AF_BUILDING': 16, 'AF_CULTURAL_ASSET': 17, 'AF_ROAD': 18, 'AF_TRANSPORT': 19, 'AF_MUSICAL_INSTRUMENT': 20, 'AF_WEAPON': 21, 'AFA_DOCUMENT': 22, 'AFA_PERFORMANCE': 23, 'AFA_VIDEO': 24, 'AFA_ART_CRAFT': 25, 'AFA_MUSIC': 26, "AFW_SERVICE_PRODUCTS": 27, 'AFW_OTHER_PRODUCTS': 28, 'OGG_ECONOMY': 29, 'OGG_EDUCATION': 30, 'OGG_MILITARY': 31, 'OGG_MEDIA': 32, 'OGG_SPORTS': 33, 'OGG_ART': 34, 'OGG_MEDICINE': 35, 'OGG_RELIGION': 36, 'OGG_SCIENCE': 37, 'OGG_LIBRARY':38, 'OGG_LAW': 39, 'OGG_POLITICS': 40, 'OGG_FOOD': 41, 'OGG_HOTEL': 42, 'OGG_OTHERS': 43, 'LCP_COUNTRY': 44, 'LCP_PROVINCE': 45, 'LCP_COUNTY':46, 'LCP_CITY': 47, 'LCP_CAPITALCITY': 48, 'LCG_RIVER': 49, 'LCG_OCEAN': 50, 'LCG_BAY': 51, 'LCG_MOUNTAIN':52, 'LCG_ISLAND': 53, 'LCG_CONTINENT': 54, 'LC_SPACE': 55, 'LC_OTHERS': 56, 'CV_CULTURE': 57, 'CV_TRIBE': 58, 'CV_LANGUAGE': 59, 'CV_POLICY': 60, 'CV_LAW': 61, 'CV_CURRENCY': 62, 'CV_TAX': 63, 'CV_FUNDS': 64, 'CV_ART': 65, 'CV_SPORTS': 66, 'CV_SPORTS_POSITION': 67, 'CV_SPORTS_INST': 68, 'CV_PRIZE': 69, 'CV_RELATION': 70, 'CV_OCCUPATION': 71, 'CV_POSITION': 72, 'CV_FOOD': 73, 'CV_DRINK': 74, 'CV_FOOD_STYLE': 75, 'CV_CLOTHING': 76, 'CV_BUILDING_TYPE': 77, 'DT_DURATION': 78, 'DT_DAY': 79, 'DT_WEEK':80, 'DT_MONTH': 81, 'DT_YEAR': 82, 'DT_SEASON': 83, 'DT_GEOAGE': 84, 'DT_DYNASTY': 85, 'DT_OTHERS': 86, 'TI_DURATION': 87, 'TI_HOUR':88, 'TI_MINUTE': 89, 'TI_SECOND': 90, 'TI_OTHERS': 91, 'QT_AGE': 92, 'QT_SIZE': 93, 'QT_LENGTH': 94, 'QT_COUNT': 95, 'QT_MAN_COUNT': 96, 'QT_WEIGHT': 97, 'QT_PERCENTAGE': 98, 'QT_SPEED': 99, 'QT_TEMPERATURE': 100, 'QT_VOLUME': 101, 'QT_ORDER': 102, 'QT_PRICE': 103, 'QT_PHONE': 104, 'QT_SPORTS': 105, 'QT_CHANNEL': 106, 'QT_ALBUM': 107, 'QT_ADDRESS': 108, 'QT_OTHERS': 109, 'EV_ACTIVITY': 110, 'EV_WAR_REVOLUTION': 111, 'EV_SPORTS': 112, 'EV_FESTIVAL': 113, 'EV_OTHERS': 114, 'AM_INSECT': 115, 'AM_BIRD': 116, 'AM_FISH': 117, 'AM_MAMMALIA': 118, 'AM_AMPHIBIA': 119, 'AM_REPTILIA': 120, 'AM_TYPE': 121, 'AM_PART': 122, 'AM_OTHERS': 123, 'PT_FRUIT': 124, 'PT_FLOWER': 125, 'PT_TREE': 126, 'PT_GRASS': 127, 'PT_TYPE': 128, 'PT_PART': 129, 'PT_OTHERS': 130, 'MT_ELEMENT': 131, 'MT_METAL': 132, 'MT_ROCK':133, 'MT_CHEMICAL': 134, 'TM_COLOR': 135, 'TM_DIRECTION': 136, 'TM_CLIMATE': 137, 'TM_SHAPE': 138, 'TM_CELL_TISSUE_ORGAN': 139, 'TMM_DISEASE': 140, 'TMM_DRUG': 141, 'TMI_HW':142, 'TMI_SW': 143, 'TMI_SITE': 144, 'TMI_EMAIL': 145, 'TMI_MODEL': 146, 'TMI_SERVICE': 147, 'TMI_PROJECT': 148, 'TMIG_GENRE': 149, 'TM_SPORTS': 150} # Add label like B-entity name I-entity name new_label_mapping = {} for key, value in label_mapping.items(): if key == 'O': new_label_mapping[key] = value continue new_key_b = 'B-' + key new_key_i = 'I-' + key new_label_mapping[new_key_b] = value new_label_mapping[new_key_i] = value + 150 # Sort the new_label_mapping by values new_label_mapping = {k: v for k, v in sorted(new_label_mapping.items(), key=lambda item: item[1])} from datasets import Features, ClassLabel features = Features({'label': ClassLabel(num_classes=301, names=list(new_label_mapping.keys()))}) tags = features['label'] index2tag = {idx:tag for idx, tag in enumerate(tags.names)} tag2index = {tag:idx for idx, tag in enumerate(tags.names)} ``` ### Extended Usage Idea This model trained with the news dataset can be used to search for news articles. This is especially useful when the user does not know the exact name of a particular object name. You can search for cases without knowing the name of a specific entity at all through a search term query combining 'entity name label' + 'predicate'. For example, if you want to search for cases where a man-made building burned down, you can search for 'AF_BUILDING' + 'burned down' to see the actual cases and the name of the building. Just with a predicate search, when you search for 'burned', non-building cases such as forest fires will also appear as results. Even if you want to find a case where two countries signed an agreement, you can find the actual case and check the country name by using a search term query such as 'LCP_COUNTRY' + 'entered into an agreement'. This allows users to search for actual articles based on ‘context’ even without any information about the country. ## Performance Dataset used for evaluation Use 10000 of ‘test’ from the dataset in the link below ```python ds = dataset['test'] sliceds = {} sliceds = ds.select([i for i in range(10000)]) ``` - NER-NewsBI-150142-e3b4: https://huggingface.co/datasets/yeajinmin/NER-News-BIDataset - KcBert: https://huggingface.co/datasets/yeajinmin/News-NER-dataset-ForKCBERT - KoGPT2: https://huggingface.co/datasets/yeajinmin/News-NER-dataset-ForKoGPT2 |모델명|Precision|Recall|f1 score| |--------|----|----|----| |**NER-NewsBI-150142-e3b4**|**0.9208**|**0.9243**|**0.9225**| |KcBERT|0.9105|0.9197|0.9151| |KoGPT2|0.8032|0.8224|0.8127 If you would like to check other models trained for evaluation, check the link below: - KcBert: https://huggingface.co/yeajinmin/NER-News-kcbert-150142-e3b4 - KoGPT2: https://huggingface.co/yeajinmin/NER-News-KoGPT2-150142-e3b4
[ "CRAFT" ]
lightblue/Jamba-v0.1-chat-multilingual
lightblue
text-generation
[ "transformers", "safetensors", "jamba", "text-generation", "conversational", "custom_code", "dataset:jondurbin/airoboros-3.2", "dataset:openchat/openchat_sharegpt4_dataset", "base_model:ai21labs/Jamba-v0.1", "base_model:finetune:ai21labs/Jamba-v0.1", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-03-30T08:21:43Z
2024-04-01T14:29:34+00:00
32
22
--- base_model: ai21labs/Jamba-v0.1 datasets: - jondurbin/airoboros-3.2 - openchat/openchat_sharegpt4_dataset library_name: transformers license: apache-2.0 pipeline_tag: text-generation --- # Model Overview This model was trained as a small-scale experiment to determine how easy it is to fine-tune [ai21labs/Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1) to work as a chatbot. The aim of this experiment was to find how intelligently and reliably Jamba can chat in both English and other languages if only QLoRA finetuned for a few hours. Initial subjective testing has shown that this model can chat reasonably well in both English and other languages, so feel free to give it a try! ## Model Details - **Model type:** Joint Attention and Mamba (Jamba) - **License:** Apache 2.0 - **Context length:** 256K - **Knowledge cutoff date:** March 5, 2024 ## Presequities Jamba requires you use `transformers` version 4.39.0 or higher: ```bash pip install transformers>=4.39.0 ``` In order to run optimized Mamba implementations, you first need to install `mamba-ssm` and `causal-conv1d`: ```bash pip install mamba-ssm causal-conv1d>=1.2.0 ``` You also have to have the model on a CUDA device. You can run the model not using the optimized Mamba kernels, but it is **not** recommended as it will result in significantly lower latencies. In order to do that, you'll need to specify `use_mamba_kernels=False` when loading the model. ## How to use ※ - This code automatically appends the "<|startoftext|>" special token to any input. Appending this to all inputs is required for inference, as initial testing shows that leaving it out leads to output errors. ```python from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig import torch double_quant_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_compute_dtype=torch.float16 ) model = AutoModelForCausalLM.from_pretrained("lightblue/Jamba-v0.1-chat-multilingual", device_map="auto", quantization_config=double_quant_config, trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("lightblue/Jamba-v0.1-chat-multilingual") input_text = """<|im_start|>system You are a helpful AI assistant. <|im_end|> <|im_start|>user What is the most interesting fact about kangaroos that you know? <|im_end|> <|im_start|>assistant """ input_ids = tokenizer(input_text, return_tensors='pt').to(model.device)["input_ids"] outputs = model.generate(input_ids, max_new_tokens=256, temperature=0.0, repetition_penalty=1.1) print(tokenizer.batch_decode(outputs)[0]) # <|startoftext|><|im_start|>system # You are a helpful AI assistant. # <|im_end|> # <|im_start|>user # What is the most interesting fact about kangaroos that you know? # <|im_end|> # <|im_start|>assistant # One of the most interesting facts about kangaroos is their unique reproductive system, which involves embryonic diapause and multiple births. Female kangaroos can have up to three joeys at different stages of development simultaneously: one fully developed in the pouch, another developing inside her body, and an embryo waiting for its turn.<|im_end|> # <|endoftext|> ``` # Initial testing results Overall, the model seems to have decent knowledge in some areas while hallucinating incorrect information in others. It also seems faily easy to steer the model using the system message, being able to rhyme and modulate English difficulty to varying levels of success. The multi-turn accuracy seems decent from very little testing. The multilingual tests show us that this model fairly reliably replies in whatever language it has been prompted in. <details> <summary>Single turn examples</summary> ``` <|startoftext|><|im_start|>system You are a helpful AI assistant. <|im_end|> <|im_start|>user Describe the town of Strathaven, Scotland in 50 words. <|im_end|> <|im_start|>assistant Strathaven is a picturesque market town located in South Lanarkshire, Scotland. Known for its rich history and stunning landscapes, it offers visitors a delightful blend of historical attractions, outdoor activities, and modern amenities. With its charming streets, beautiful parks, and friendly community, Strathaven provides an ideal destination for those seeking a peaceful escape from city life.<|im_end|> <|endoftext|> <|startoftext|><|im_start|>system You are a helpful AI assistant. <|im_end|> <|im_start|>user Describe a harmless prank that I can play on my colleagues. <|im_end|> <|im_start|>assistant A harmless prank you can play on your colleagues is the "Fake Meeting" prank. Here's how to do it: 1. Choose a colleague who often has meetings or conference calls scheduled throughout the day. 2. Find out their schedule for the day, including any upcoming meetings they have. 3. Create a fake meeting invitation using an email template or online tool like Canva or Google Docs. Make sure the design and format look similar to the company's official meeting invitations. 4. Include details such as the date, time, location (if applicable), subject, and attendees. You can even add a fake agenda if you want to make it more convincing. 5. Send the fake meeting invitation to your chosen colleague via email or instant messaging platform used in your workplace. 6. Wait for them to respond with confusion or excitement about attending this unexpected meeting. 7. When they ask questions about the meeting, act clueless and say something like, "Oh, I just got this invite too! Must be some new initiative from upper management." 8. Keep up the charade until they realize it's a prank, but don't let it go on for too long so as not to cause unnecessary stress or confusion. <|startoftext|><|im_start|>system You are a helpful AI assistant that always answers correctly. <|im_end|> <|im_start|>user Do UK citizens need a visa to holiday in Singapore? <|im_end|> <|im_start|>assistant Yes, UK citizens do need a visa to holiday in Singapore. They can apply for an Electronic Travel Authorization (ETA) online before their trip.<|im_end|> <|endoftext|> ## <dev note>: This is false, UK citizens do NOT require a visa to holiday in Singapore. An Electronic Travel Authorization (ETA) is required for the USA etc. <|startoftext|><|im_start|>system You are a helpful AI assistant. <|im_end|> <|im_start|>user Which US state has the highest GDP per capita? <|im_end|> <|im_start|>assistant As of my last update, the US state with the highest GDP per capita is Massachusetts.<|im_end|> <|endoftext|> <|startoftext|><|im_start|>system You are a helpful AI assistant. <|im_end|> <|im_start|>user Name three things that feel like a golf ball in your hands. <|im_end|> <|im_start|>assistant 1. A tennis ball: Tennis balls have a similar size and texture to golf balls, making them feel quite similar when held in the hand. They both have a rubbery surface with dimples or indentations on their outer layer. 2. A stress ball: Stress balls are often made of soft, squishy material such as foam or gel, which can be squeezed and manipulated easily. The feeling of holding a stress ball is comparable to that of a golf ball due to its small size and round shape. 3. A ping pong ball: Ping pong balls are lightweight and hollow, much like golf balls. Although they may not have the same texture, their size and spherical shape make them feel somewhat similar when held in the hand.<|im_end|> <|endoftext|> ``` </details> <details> <summary>System message control examples</summary> ``` <|startoftext|><|startoftext|><|im_start|>system You are a helpful AI assistant. You write all answers in very simple English. <|im_end|> <|im_start|>user Write a 50 word analysis of why sausages are better than bacon. <|im_end|> <|im_start|>assistant Sausages are better than bacon because they have more variety and can be eaten for breakfast, lunch, or dinner. They come in different flavors and sizes, making them versatile. Sausages also contain less fat and calories compared to bacon, which is healthier for people who want to watch their diet.<|im_end|> <|endoftext|> <|startoftext|><|startoftext|><|im_start|>system You are a helpful AI assistant. You write all answers in very complex English. <|im_end|> <|im_start|>user Write a 50 word analysis of why sausages are better than bacon. <|im_end|> <|im_start|>assistant Sausages, due to their versatility and adaptability, offer more culinary possibilities compared to bacon. They can be used as an ingredient or served whole, while bacon is often limited to being a side dish. Sausages also have a longer shelf life and come in various flavors, making them a more convenient choice for cooking.<|im_end|> <|endoftext|> <|startoftext|><|im_start|>system You are an AI assistant that answers all questions in rhyme. <|im_end|> <|im_start|>user Why is the sky blue? <|im_end|> <|im_start|>assistant The sky's hue, a question so true, Is caused by light scattering through. When sunlight meets our atmosphere, It scatters and creates a fair weather affair. Blue light waves have shorter lengths, They scatter more than other tints. This phenomenon, called Rayleigh scattering, Makes the sky appear as if it were wearing a sapphire ring. So when you gaze at the azure expanse above, Remember this simple explanation of nature's love.<|im_end|> <|endoftext|> ``` </details> <details> <summary>Multi-turn examples</summary> ``` <|startoftext|><|startoftext|><|im_start|>system You are a helpful AI assistant. <|im_end|> <|im_start|>user Give an example of a healthy breakfast. <|im_end|> <|im_start|>assistant A healthy breakfast could include: 1. A bowl of oatmeal made with water or low-fat milk, topped with fresh berries and a sprinkle of nuts or seeds (such as almonds, walnuts, chia seeds, or flaxseeds). 2. A slice of whole grain toast spread with natural peanut butter or almond butter, along with a side of sliced fruit like apples or bananas. 3. Greek yogurt mixed with honey and granola, served with a handful of blueberries or strawberries on the side. 4. A vegetable omelette made with egg whites or a combination of whole eggs and egg whites, filled with spinach, tomatoes, onions, and mushrooms, paired with a small serving of avocado slices. 5. A smoothie made with unsweetened almond milk, frozen fruits (like mangoes, pineapples, or berries), a scoop of protein powder, and a handful of leafy greens (like spinach or kale). 6. Whole grain cereal with skim milk, accompanied by a piece of fruit and a dollop of plain Greek yogurt for added protein.<|im_end|> <|im_start|>user Which of these would have the lowest calorie count while still making me feel full? <|im_end|> <|im_start|>assistant The option with the lowest calorie count that will also make you feel full is Option 1: Oatmeal with fresh berries and nuts/seeds. Oatmeal is high in fiber, which helps keep you feeling full longer, and it's lower in calories compared to other options like smoothies and omelettes. The addition of fresh berries provides essential vitamins and minerals, while the nuts and seeds add healthy fats and proteins to help you stay satisfied until your next meal.<|im_end|> <|endoftext|> ``` </details> <details> <summary>Multilingual examples</summary> ``` <|startoftext|><|im_start|>system You are a helpful AI assistant. <|im_end|> <|im_start|>user 東京駅から池袋駅まで丸の内線で行きたいですが、普通に何時間かかりますか？ <|im_end|> <|im_start|>assistant 東京駅から池袋駅まで丸の内線で行く場合、平均的には約20分程度かかります。しかし、これは一般的な情報であり、実際の旅行時間は運行状況や列車の種類、日付、時間帯などによって異なることに注意してください。<|im_end|> <|endoftext|> <|startoftext|><|im_start|>system You are a helpful AI assistant. <|im_end|> <|im_start|>user Opisz kilka ciekawych miejsc do odwiedzenia w Londynie <|im_end|> <|im_start|>assistant 1. Buckingham Palace: Jest to oficjalne siedzisko Królowej Brytanii, króla Brytanii i innych państw Członkowskich Zjednoczonego Królestwa. Można tu zobaczyć mający historię palac oraz obejrzeć ceremonię zmiany strażników na placu przed budynkiem. 2. Big Ben: To jest jedna z najbardziej rozpoznawalnych atrakcji turystycznych w Londynie. Jest to wieża zegarowa położona na terenie Parlamentu Wielkiej Brytanii i Senatu. Jej dźwiękowy sygnał można usłyszeć nawet na dalekie odległości. 3. Tower Bridge: Ten piękny most nad Tamizą oferuje widok na skyline Londynu. Otwiera się on pod koniec każdego d ``` </details> <br/> # Training details The model was trained on 2 open source datasets (one multilingual) for one epoch on a A100 (80GB) x 4 environment for 3 hours. ## Training data * [jondurbin/airoboros-3.2](https://huggingface.co/datasets/jondurbin/airoboros-3.2) A ~59K example dataset of curated LLM tasks in English, primarily generated with GPT-4. This dataset has been used by some of the best performing open source LLMs in the world (e.g. [jondurbin/bagel-7b-v0.4](https://huggingface.co/jondurbin/bagel-7b-v0.4), [NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)) and contains a wide variety of tasks, so we hypothesized that this would lead to a multi-talented, accurate model. For this reason we chose this dataset was chosen for the bulk of our training data. Note: Each element in jondurbin/airoboros-3.2 already contains a system message. * [openchat/openchat_sharegpt4_dataset](https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset) (GPT-4 responses only) A ~6K example dataset of multilingual multi-turn chats between users and GPT-4. While jondurbin/airoboros-3.2 has deilvered good results for models previously, it sadly contains no (or seemingly very little) multilingual data. We are a Japanese AI company, so require an LLM to be able to output in Japanese too. Hence we also selected a small, seemingly high quality dataset of GPT-4 responses in many languages from the ShareGPT dataset. We chose to only select the GPT-4 responses as we wanted to keep our dataset as small and high quality as possible to maximise the efficiency of our training. Note: openchat/openchat_sharegpt4_dataset does not contain system messages, so we added 'You are GPT-4, a helpful assistant.' as our system message. <details> <summary>Data preparation code</summary> ```python import os import pandas as pd from datasets import load_dataset, Dataset, concatenate_datasets os.environ['HF_HOME'] = "/workspace/hf_home" os.environ['HF_HUB_ENABLE_HF_TRANSFER'] = "1" boros_dataset = load_dataset("jondurbin/airoboros-3.2", split='train') gpt4_df = pd.read_json("https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset/resolve/main/sharegpt_gpt4.json?download=true") gpt4_df["conversations"] = gpt4_df["items"].apply(lambda x: [{'from': 'system', 'value': 'You are GPT-4, a helpful assistant.'}] + x) gpt4_dataset = Dataset.from_pandas(gpt4_df[["conversations"]]) dataset = concatenate_datasets([gpt4_dataset, boros_dataset]).shuffle() dataset.select_columns(["conversations"]).to_json("/workspace/airoboros-3.2_plus_openchat_sharegpt4.json") ``` </details> ## Training The Jamba-v0.1 base model was trained for roughly 3 hours in a A100 (80GB) x 4 environment on the Azure cloud (Standard_NC96ads_A100_v4). We trained using QLoRA and merged the adapter to the original weights. Our training harness was Axolotl using the ChatML chat template. Full details of the training config are below: <details> <summary>Training config</summary> ```yaml base_model: ai21labs/Jamba-v0.1 trust_remote_code: true load_in_8bit: false load_in_4bit: true strict: false datasets: - path: /workspace/airoboros-3.2_plus_openchat_sharegpt4.json ds_type: json type: sharegpt conversation: chatml dataset_prepared_path: val_set_size: 0.01 output_dir: ./airoboros-3.2_plus_openchat_sharegpt4_one_epoch sequence_len: 6000 sample_packing: true pad_to_sequence_len: false eval_sample_packing: true use_wandb: true wandb_project: axolotl wandb_entity: peterd wandb_name: airoboros-3.2_plus_openchat_sharegpt4 adapter: qlora lora_r: 8 lora_alpha: 16 lora_dropout: 0.05 lora_target_linear: true low_cpu_mem_usage: true gradient_accumulation_steps: 4 micro_batch_size: 1 num_epochs: 1 optimizer: paged_adamw_8bit lr_scheduler: cosine learning_rate: 0.0002 train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: true gradient_checkpointing_kwargs: use_reentrant: false early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 10 evals_per_epoch: 5 saves_per_epoch: 5 debug: deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json weight_decay: 0.0 special_tokens: ``` </details> [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <details> <summary>Training graphs</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/umxTIsNRHUtKS_kL81Uyf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/mpuCoL99rxX8RCgXH1CJo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/5FvwYNdte-bgzEvcvFO8I.png) </details> <br/> # Developers Lead developer - Peter Devine [ptrdvn](https://huggingface.co/ptrdvn) Administrative supervisor - Shunichi Taniguchi [shun1taniguchi](https://huggingface.co/shun1taniguchi)
[ "CHIA" ]
Tweeties/tweety-7b-tatar-v24a
Tweeties
text-generation
[ "transformers", "safetensors", "mistral", "text-generation", "tweety", "tt", "dataset:oscar-corpus/OSCAR-2301", "arxiv:2408.04303", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "base_model:finetune:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2024-04-11T19:40:19Z
2024-08-09T08:58:41+00:00
32
11
--- base_model: mistralai/Mistral-7B-Instruct-v0.2 datasets: - oscar-corpus/OSCAR-2301 language: - tt license: apache-2.0 tags: - tweety --- <img align="right" src="https://huggingface.co/Tweeties/tweety-tatar-base-7b-2024-v1/resolve/main/TweetyTatar.png?download=true" alt="Tweety-Tatar-7B: A Tatar Large Language Model" width="20%"> # Tweety Tatar / Base 7b / 2024-v1 ## Model description This model is our trans-tokenized LLM for the [Tatar language](https://en.wikipedia.org/wiki/Tatar_language), converted from the [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) model trained by MistralAI. Trans-tokenized LLMs are language models finetuned to produce output in a particular language, using a novel tokenizer native to that language. - **Developed by:** [François Remy](https://huggingface.co/FremyCompany) (UGent), [Alfiya Khabibullina](https://huggingface.co/justalphie) (BeCode), [et al.](#citation) - **Funded by:** IDLab / GPULab (UGent) - **Model type:** Foundation model using the mistral architecture - **Language(s) (NLP):** Tatar - **License:** Apache 2.0 ## In-scope usage This model can be used as-is to perform basic language modeling operations in Tatar, or finetuned to perform more complex operations. This model has not undergone Instruction- or Chat-based finetuning, which means that the model functions best in few-shot settings. ## Usage instructions This model can be used just like any LLM in the HuggingFace framework: ```py import transformers MODEL_NAME = "Tweeties/tweety-tatar-base-7b-2024-v1" generate = transformers.pipeline("text-generation", model=MODEL_NAME) ``` ### Word Analogies ```py ANALOGY_PROMPT = """Бу аналоглар таблицасын тутырыгыз: * {x1} : {y1} * {x2} :""" def score_analogy(x1, y1, x2, y2): Y2_PROMPT = ANALOGY_PROMPT.replace('{x1}', x1).replace('{y1}', y1).replace('{x2}', x2) answer = generate(Y2_PROMPT, use_cache=True, do_sample=False, max_new_tokens=10, return_full_text=False, pad_token_id=generate.tokenizer.eos_token_id, eos_token_id=generate.tokenizer.convert_tokens_to_ids(['<0x0A>','</s>']))[0]['generated_text'].strip() return 1 if answer == y2 else 0 score_analogy('Мәскәү', 'Русия', 'Әнкара', 'Төркия') # 1 ``` ### Summarization ```py SUMMARIZE = "Түбәндәге текстка йомгак ясагыз:\n" LONG_TEXT = "\n\nОзын текст:\n" LONG_TEXT_DEMO = "Кеше организмы катлаулы организм, аның өчен кирәкле туклыклы матдәләрнең аерым баланс таләп итә. Кеше организмының туклану рационы нигездә пешекләнгән ризыклардан тора икән, аның организмы бу ысул белән туклануга җайлаша. Әмма, шул ук кеше кинәт чимал диетасына күчә икән, аның организмы әлеге үзгәрешне кабул итә алмый, бу мөмкин кадәр зыян китерергә мөмкин." # The human body is a complex organism that requires a specific balance of nutrients. If the human body's diet consists mainly of cooked foods, its body adapts to this type of nutrition. However, if the same person suddenly switches to a raw diet, his body cannot adapt to this change, which can be harmful. # The human body is a complex organism that requires a specific balance of nutrients to function optimally. When a person's diet consists primarily of cooked food, their body adapts to this way of eating. However, if that same person suddenly switches to a raw food diet, their body may not be able to handle the sudden change, leading to potential harm. SHORT_TEXT = "\n\nКыска текст:\n" SHORT_TEXT_DEMO = "Әмма пешкән ризык ашауга гына күнгән организмга кинәт чи ризык белән туклануга күчүнең зарарлы нәтиҗәсе дә булырга мөмкин." # However, a body accustomed to eating only cooked food can have harmful consequences when suddenly switching to eating raw food. def generate_tatar_summary(tatar_text_to_summarize: str) -> str: # craft the 1-shot example input_ids = torch.concat([ tokenizer.encode(SUMMARIZE, return_tensors='pt'), tokenizer.encode(LONG_TEXT, add_special_tokens=False, return_tensors='pt'), tokenizer.encode(LONG_TEXT_DEMO, add_special_tokens=False, return_tensors='pt'), tokenizer.encode(SHORT_TEXT, add_special_tokens=False, return_tensors='pt'), tokenizer.encode(SHORT_TEXT_DEMO, add_special_tokens=False, return_tensors='pt'), tokenizer.encode("\n\n", add_special_tokens=False, return_tensors='pt') ], axis=1) # craft the input input_ids = torch.concat([ input_ids, tokenizer.encode(SUMMARIZE, return_tensors='pt'), tokenizer.encode(LONG_TEXT, add_special_tokens=False, return_tensors='pt'), tokenizer.encode(tatar_text_to_summarize, add_special_tokens=False, return_tensors='pt'), tokenizer.encode(SHORT_TEXT, add_special_tokens=False, return_tensors='pt'), ], axis=1) # generate the output model_inputs = {'input_ids':input_ids.to(cuda_device)} model_outputs = model.generate( **model_inputs, max_new_tokens=80, num_beams=8, no_repeat_ngram_size=6, early_stopping=False, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.convert_tokens_to_ids(['<0x0A>','</s>']), ) # decode the output return (tokenizer.decode(model_outputs[0][input_ids.shape[1]:])).rstrip() generate_tatar_summary("Зур шартлау (ингл. Big Bang) – Галәмнең башлангыч, сингуляр халәттә торган чорын тасвирлаучы космологик модель. Әле ХХ гасырда да без яшәгән Галәм статик структуралы, дигән фикер яшәгән. Ягъни, Галәмнең башы һәм ахыры юк, имеш, ул һәрвакыт булган һәм булачак. Бу фикер фән дөньясында бик озак, астрономия фәненең бөтен нигезләрен җимереп яңа теория барлыкка килгәнче яшәгән. Бу теориянең исеме – «Зур шартлау» теориясе.") ``` ## Citation If you use this model, please cite our work as: ``` @article{tweeties2024, title = {Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP}, author = {François Remy and Pieter Delobelle and Hayastan Avetisyan and Alfiya Khabibullina and Miryam de Lhoneux and Thomas Demeester}, url = {https://arxiv.org/abs/2408.04303}, year = {2024}, note = {Accepted at COLM 2024} } ```
[ "CRAFT" ]
Huzaifa367/chat-summarizer
Huzaifa367
summarization
[ "transformers", "pytorch", "bart", "text2text-generation", "summarization", "dataset:samsum", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-05-12T15:03:57Z
2024-05-12T15:16:52+00:00
32
1
--- datasets: - samsum pipeline_tag: summarization widget: - text: "Laurie: So, what are your plans for this weekend?\nChristie: I don’t know.\ \ Do you want to get together or something?\nSarah: How about going to see a movie?\ \ Cinemax 26 on Carson Boulevard is showing Enchanted. Laurie: That sounds like\ \ a good idea. Maybe we should go out to eat beforehand.\nSarah: It is fine with\ \ me. Where do you want to meet?\nChristie: Let’s meet at Summer Pizza House.\ \ I have not gone there for a long time.\nLaurie: Good idea again. I heard they\ \ just came up with a new pizza. It should be good because Summer Pizza House\ \ always has the best pizza in town.\nSarah: When should we meet?\nChristie: Well,\ \ the movie is shown at 2:00PM, 4:00PM, 6:00PM and 8:00PM.\nLaurie: Why don’t\ \ we go to the 2:00PM show? We can meet at Summer Pizza House at noon. That will\ \ give us plenty of time to enjoy our pizza.\nSarah: My cousin Karen is in town.\ \ Can I bring her along? I hate to leave her home alone.\nChristie: Karen is in\ \ town? Yes, bring her along. Laurie, you remember Karen? We met her at Sara’s\ \ high school graduation party two years ago.\nLaurie: I do not quite remember\ \ her. What does she look like?\nSarah: She has blond hair, she is kind of slender,\ \ and she is about your height.\nLaurie: She wears eyeglasses, right?\nSarah:\ \ Yes, and she was playing the piano off and on during the party.\nLaurie: I remember\ \ her now. Yes, do bring her along Sara. She is such a nice person, and funny\ \ too.\nSarah: She will be happy to meet both of you again.\nChristie: What is\ \ she doing these days?\nSarah: She graduated last June, and she will start her\ \ teaching career next week when the new school term begins.\nLaurie: What grade\ \ is she going to teach?\nSarah: She will teach kindergarten. She loves working\ \ with kids, and she always has such a good rapport with them\nChristie: Kindergarten?\ \ She must be a very patient person. I always think kindergarten is the most difficult\ \ class to teach. Most of the kids have never been to school, and they have e\ \ never been away from mommy for long.\nSarah: I think Karen will do fine. She\ \ knows how to handle young children\nLaurie: I think the first few weeks will\ \ be tough. However, once the routine is set, it should not be too difficult to\ \ teach kindergarten.\nChristie: You are right. The kids might even look forward\ \ to going to school since they have so many friends to play with.\nSarah: There\ \ are so many new things for them to do at school too. They do a lot of crafts\ \ in kindergarten. I am always amazed by the things kindergarten teachers do.\ \ \nLaurie: Yes, I have seen my niece come home with so many neat stuff.\nChristie:\ \ Maybe we can ask Karen to show us some of the things that we can do for this\ \ Halloween.\nLaurie: Maybe we can stop by the craft store after the movie. What\ \ do you think, Sara?\nSarah: I will talk to her. I think she will like that.\ \ It will help her with school projects when Halloween comes.\nChristie: Michael’s\ \ is a good store for crafts. It always carries a variety of things, and you can\ \ find almost anything there.\nLaurie: There is a Michaels store not far away\ \ from Cinemax 26. I believe it is just around the corner, on Pioneer Avenue.\ \ We can even walk over there.\nSarah: So, we plan to meet for pizza at noon,\ \ go to the movies at two, and shop at Michael’s afterward. Right?\nLaurie and\ \ Christie: Yes. \n" model-index: - name: bart-large-cnn-samsum results: - task: type: summarization name: Conversation Summarization dataset: name: 'SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization' type: samsum metrics: - type: rogue-1 value: 54.8764 name: Validation ROGUE-1 - type: rogue-2 value: 29.6869, name: Validation ROGUE-2 - type: rogue-l value: 44.9874 name: Validation ROGUE-L - type: loss value: 1.47812 name: loss ---
[ "CRAFT" ]
grimjim/llama-3-aaditya-OpenBioLLM-8B
grimjim
text-generation
[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:finetune:meta-llama/Meta-Llama-3-8B", "license:llama3", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2024-05-29T03:26:48Z
2024-05-29T11:37:35+00:00
32
0
--- base_model: meta-llama/Meta-Llama-3-8B language: - en license: llama3 tags: - llama-3 - llama - Mixtral - instruct - finetune - chatml - DPO - RLHF - gpt4 - distillation widget: - example_title: OpenBioLLM-8B messages: - role: system content: You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. - role: user content: How long does it take for newborn jaundice to go away? output: text: 'Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment. The duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines: 1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment. It''s important for parents to monitor their newborn''s jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn''s jaundice, it''s always best to consult with a healthcare professional for personalized advice and guidance.' model-index: - name: OpenBioLLM-8B results: [] --- <div align="center"> <img width="260px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/2FhDh8NDvMl7iSxbQz9BP.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-8B builds upon the powerful foundations of the **Meta-Llama-3-8B** and [Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Ranking Dataset**: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 8 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-8B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-8B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 1 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B** # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!**  While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)
[ "MEDQA", "PUBMEDQA" ]
ThorBaller/yes
ThorBaller
question-answering
[ "transformers", "gguf", "llama", "question-answering", "en", "dataset:qiaojin/PubMedQA", "license:apache-2.0", "endpoints_compatible", "region:us" ]
2024-06-08T23:12:40Z
2024-06-09T12:52:56+00:00
32
1
--- datasets: - qiaojin/PubMedQA language: - en license: apache-2.0 pipeline_tag: question-answering --- A llama3 model im gguf form that was finetuned on a pubmed dataset.
[ "PUBMEDQA" ]
tenzin3/phi3-mini-128k
tenzin3
text-generation
[ "transformers", "safetensors", "phi3", "text-generation", "nlp", "code", "conversational", "custom_code", "en", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2024-06-10T10:31:28Z
2024-06-10T11:43:10+00:00
32
0
--- language: - en license: mit license_link: https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE pipeline_tag: text-generation tags: - nlp - code widget: - messages: - role: user content: Can you provide ways to eat combinations of bananas and dragonfruits? --- ## Model Summary The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties. The model belongs to the Phi-3 family with the Mini version in two variants [4K](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) and [128K](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) which is the context length (in tokens) that it can support. After initial training, the model underwent a post-training process that involved supervised fine-tuning and direct preference optimization to enhance its ability to follow instructions and adhere to safety measures. When evaluated against benchmarks that test common sense, language understanding, mathematics, coding, long-term context, and logical reasoning, the Phi-3 Mini-128K-Instruct demonstrated robust and state-of-the-art performance among models with fewer than 13 billion parameters. Resources and Technical Documentation: + [Phi-3 Microsoft Blog](https://aka.ms/Phi-3Build2024) + [Phi-3 Technical Report](https://aka.ms/phi3-tech-report) + [Phi-3 on Azure AI Studio](https://aka.ms/phi3-azure-ai) + [Phi-3 Cookbook](https://github.com/microsoft/Phi-3CookBook) | | Short Context | Long Context | | ------- | ------------- | ------------ | | Mini | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx) ; [[GGUF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct-onnx)| | Small | 8K [[HF]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct-onnx-cuda)| | Medium | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda)| | Vision | | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct-onnx-cuda)| ## Intended Uses **Primary use cases** The model is intended for commercial and research use in English. The model provides uses for applications which require: 1) Memory/compute constrained environments 2) Latency bound scenarios 3) Strong reasoning (especially code, math and logic) Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features. **Use case considerations** Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case. Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under. ## How to Use Phi-3 Mini-128K-Instruct has been integrated in the development version (4.41.0.dev0) of `transformers`. Until the official version is released through `pip`, ensure that you are doing one of the following: * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function. * Update your local `transformers` to the development version: `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`. The previous command is an alternative to cloning and installing from the source. The current `transformers` version can be verified with: `pip list | grep transformers`. ### Tokenizer Phi-3 Mini-128K-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size. ### Chat Format Given the nature of the training data, the Phi-3 Mini-128K-Instruct model is best suited for prompts using the chat format as follows. You can provide the prompt as a question with a generic template as follow: ```markdown <|user|>\nQuestion<|end|>\n<|assistant|> ``` For example: ```markdown <|user|> How to explain Internet for a medieval knight?<|end|> <|assistant|> ``` where the model generates the text after `<|assistant|>`. In case of few-shots prompt, the prompt can be formatted as the following: ```markdown <|user|> I am going to Paris, what should I see?<|end|> <|assistant|> Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:\n\n1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.\n2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.\n3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.\n\nThese are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|> <|user|> What is so great about #1?<|end|> <|assistant|> ``` ### Sample inference code This code snippets show how to get quickly started with running the model on a GPU: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline torch.random.manual_seed(0) model = AutoModelForCausalLM.from_pretrained( "microsoft/Phi-3-mini-128k-instruct", device_map="cuda", torch_dtype="auto", trust_remote_code=True, ) tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct") messages = [ {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}, {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"}, ] pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, ) generation_args = { "max_new_tokens": 500, "return_full_text": False, "temperature": 0.0, "do_sample": False, } output = pipe(messages, **generation_args) print(output[0]['generated_text']) ``` *Some applications/frameworks might not include a BOS token (`<s>`) at the start of the conversation. Please ensure that it is included since it provides more reliable results.* ## Responsible AI Considerations Like other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include: + Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English. + Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases. + Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case. + Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated. + Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses. Developers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include: + Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques. + High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context. + Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG). + Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case. + Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations. ## Training ### Model * Architecture: Phi-3 Mini-128K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines. * Inputs: Text. It is best suited for prompts using chat format. * Context length: 128K tokens * GPUs: 512 H100-80G * Training time: 7 days * Training data: 3.3T tokens * Outputs: Generated text in response to the input * Dates: Our models were trained between February and April 2024 * Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models. ### Datasets Our training data includes a wide variety of sources, totaling 3.3 trillion tokens, and is a combination of 1) Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code; 2) Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.); 3) High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness. ### Fine-tuning A basic example of multi-GPUs supervised fine-tuning (SFT) with TRL and Accelerate modules is provided [here](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/sample_finetune.py). ## Benchmarks We report the results for Phi-3-Mini-128K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Phi-2, Mistral-7b-v0.1, Mixtral-8x7b, Gemma 7B, Llama-3-8B-Instruct, and GPT-3.5. All the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation. As is now standard, we use few-shot prompts to evaluate the models, at temperature 0. The prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3. More specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model. The number of k–shot examples is listed per-benchmark. | | Phi-3-Mini-128K-In<br>3.8b | Phi-3-Small<br>7b (preview) | Phi-3-Medium<br>14b (preview) | Phi-2<br>2.7b | Mistral<br>7b | Gemma<br>7b | Llama-3-In<br>8b | Mixtral<br>8x7b | GPT-3.5<br>version 1106 | |---|---|---|---|---|---|---|---|---|---| | MMLU <br>5-Shot | 68.1 | 75.3 | 78.2 | 56.3 | 61.7 | 63.6 | 66.5 | 68.4 | 71.4 | | HellaSwag <br> 5-Shot | 74.5 | 78.7 | 83.2 | 53.6 | 58.5 | 49.8 | 71.1 | 70.4 | 78.8 | | ANLI <br> 7-Shot | 52.8 | 55.0 | 58.7 | 42.5 | 47.1 | 48.7 | 57.3 | 55.2 | 58.1 | | GSM-8K <br> 0-Shot; CoT | 83.6 | 86.4 | 90.8 | 61.1 | 46.4 | 59.8 | 77.4 | 64.7 | 78.1 | | MedQA <br> 2-Shot | 55.3 | 58.2 | 69.8 | 40.9 | 49.6 | 50.0 | 60.5 | 62.2 | 63.4 | | AGIEval <br> 0-Shot | 36.9 | 45.0 | 49.7 | 29.8 | 35.1 | 42.1 | 42.0 | 45.2 | 48.4 | | TriviaQA <br> 5-Shot | 57.1 | 59.1 | 73.3 | 45.2 | 72.3 | 75.2 | 67.7 | 82.2 | 85.8 | | Arc-C <br> 10-Shot | 84.0 | 90.7 | 91.9 | 75.9 | 78.6 | 78.3 | 82.8 | 87.3 | 87.4 | | Arc-E <br> 10-Shot | 95.2 | 97.1 | 98.0 | 88.5 | 90.6 | 91.4 | 93.4 | 95.6 | 96.3 | | PIQA <br> 5-Shot | 83.6 | 87.8 | 88.2 | 60.2 | 77.7 | 78.1 | 75.7 | 86.0 | 86.6 | | SociQA <br> 5-Shot | 76.1 | 79.0 | 79.4 | 68.3 | 74.6 | 65.5 | 73.9 | 75.9 | 68.3 | | BigBench-Hard <br> 0-Shot | 71.5 | 75.0 | 82.5 | 59.4 | 57.3 | 59.6 | 51.5 | 69.7 | 68.32 | | WinoGrande <br> 5-Shot | 72.5 | 82.5 | 81.2 | 54.7 | 54.2 | 55.6 | 65.0 | 62.0 | 68.8 | | OpenBookQA <br> 10-Shot | 80.6 | 88.4 | 86.6 | 73.6 | 79.8 | 78.6 | 82.6 | 85.8 | 86.0 | | BoolQ <br> 0-Shot | 78.7 | 82.9 | 86.5 | -- | 72.2 | 66.0 | 80.9 | 77.6 | 79.1 | | CommonSenseQA <br> 10-Shot | 78.0 | 80.3 | 82.6 | 69.3 | 72.6 | 76.2 | 79 | 78.1 | 79.6 | | TruthfulQA <br> 10-Shot | 63.2 | 68.1 | 74.8 | -- | 52.1 | 53.0 | 63.2 | 60.1 | 85.8 | | HumanEval <br> 0-Shot | 57.9 | 59.1 | 54.7 | 47.0 | 28.0 | 34.1 | 60.4| 37.8 | 62.2 | | MBPP <br> 3-Shot | 62.5 | 71.4 | 73.7 | 60.6 | 50.8 | 51.5 | 67.7 | 60.2 | 77.8 | ## Software * [PyTorch](https://github.com/pytorch/pytorch) * [DeepSpeed](https://github.com/microsoft/DeepSpeed) * [Transformers](https://github.com/huggingface/transformers) * [Flash-Attention](https://github.com/HazyResearch/flash-attention) ## Hardware Note that by default, the Phi-3-mini model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types: * NVIDIA A100 * NVIDIA A6000 * NVIDIA H100 If you want to run the model on: * NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from_pretrained() with attn_implementation="eager" * Optimized inference on GPU, CPU, and Mobile: use the **ONNX** models [128K](https://aka.ms/phi3-mini-128k-instruct-onnx) ## Cross Platform Support ONNX runtime ecosystem now supports Phi-3 Mini models across platforms and hardware. You can find the optimized Phi-3 Mini-128K-Instruct ONNX model [here](https://aka.ms/phi3-mini-128k-instruct-onnx). Optimized Phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML support lets developers bring hardware acceleration to Windows devices at scale across AMD, Intel, and NVIDIA GPUs. Along with DirectML, ONNX Runtime provides cross platform support for Phi-3 across a range of devices CPU, GPU, and mobile. Here are some of the optimized configurations we have added: 1. ONNX models for int4 DML: Quantized to int4 via AWQ 2. ONNX model for fp16 CUDA 3. ONNX model for int4 CUDA: Quantized to int4 via RTN 4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN ## License The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-mini-128k/resolve/main/LICENSE). ## Trademarks This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
[ "MEDQA" ]
mradermacher/Llama3-CAS-Audit8B-AP-GGUF
mradermacher
null
[ "transformers", "gguf", "en", "endpoints_compatible", "region:us", "conversational" ]
2024-07-09T09:34:04Z
2024-07-09T10:01:20+00:00
32
0
--- base_model: jamesohe/Llama3-CAS-Audit8B-AP language: - en library_name: transformers tags: [] quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/jamesohe/Llama3-CAS-Audit8B-AP <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
[ "CAS" ]
RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf
RichardErkhov
null
[ "gguf", "endpoints_compatible", "region:us", "conversational" ]
2024-07-22T14:24:16Z
2024-07-22T15:37:29+00:00
32
0
--- {} --- Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) vi-gemma-2b-RAG - GGUF - Model creator: https://huggingface.co/himmeow/ - Original model: https://huggingface.co/himmeow/vi-gemma-2b-RAG/ | Name | Quant method | Size | | ---- | ---- | ---- | | [vi-gemma-2b-RAG.Q2_K.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q2_K.gguf) | Q2_K | 1.08GB | | [vi-gemma-2b-RAG.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.IQ3_XS.gguf) | IQ3_XS | 1.16GB | | [vi-gemma-2b-RAG.IQ3_S.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.IQ3_S.gguf) | IQ3_S | 1.2GB | | [vi-gemma-2b-RAG.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q3_K_S.gguf) | Q3_K_S | 1.2GB | | [vi-gemma-2b-RAG.IQ3_M.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.IQ3_M.gguf) | IQ3_M | 1.22GB | | [vi-gemma-2b-RAG.Q3_K.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q3_K.gguf) | Q3_K | 1.29GB | | [vi-gemma-2b-RAG.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q3_K_M.gguf) | Q3_K_M | 1.29GB | | [vi-gemma-2b-RAG.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q3_K_L.gguf) | Q3_K_L | 1.36GB | | [vi-gemma-2b-RAG.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.IQ4_XS.gguf) | IQ4_XS | 1.4GB | | [vi-gemma-2b-RAG.Q4_0.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q4_0.gguf) | Q4_0 | 1.44GB | | [vi-gemma-2b-RAG.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.IQ4_NL.gguf) | IQ4_NL | 1.45GB | | [vi-gemma-2b-RAG.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q4_K_S.gguf) | Q4_K_S | 1.45GB | | [vi-gemma-2b-RAG.Q4_K.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q4_K.gguf) | Q4_K | 1.52GB | | [vi-gemma-2b-RAG.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q4_K_M.gguf) | Q4_K_M | 1.52GB | | [vi-gemma-2b-RAG.Q4_1.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q4_1.gguf) | Q4_1 | 1.56GB | | [vi-gemma-2b-RAG.Q5_0.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q5_0.gguf) | Q5_0 | 1.68GB | | [vi-gemma-2b-RAG.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q5_K_S.gguf) | Q5_K_S | 1.68GB | | [vi-gemma-2b-RAG.Q5_K.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q5_K.gguf) | Q5_K | 1.71GB | | [vi-gemma-2b-RAG.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q5_K_M.gguf) | Q5_K_M | 1.71GB | | [vi-gemma-2b-RAG.Q5_1.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q5_1.gguf) | Q5_1 | 1.79GB | | [vi-gemma-2b-RAG.Q6_K.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q6_K.gguf) | Q6_K | 1.92GB | | [vi-gemma-2b-RAG.Q8_0.gguf](https://huggingface.co/RichardErkhov/himmeow_-_vi-gemma-2b-RAG-gguf/blob/main/vi-gemma-2b-RAG.Q8_0.gguf) | Q8_0 | 2.49GB | Original model description: --- base_model: unsloth/gemma-1.1-2b-it-bnb-4bit language: - en - vi license: apache-2.0 tags: - text-generation-inference - retrieval-augmented-generation - transformers - unsloth - gemma - trl - sft --- ## Model Card: vi-gemma-2b-RAG ### Tiếng Việt (Vietnamese) **Mô tả mô hình:** vi-gemma-2b-RAG là một mô hình ngôn ngữ lớn được tinh chỉnh từ mô hình cơ sở [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it) sử dụng kỹ thuật LoRA. Mô hình được huấn luyện trên tập dữ liệu tiếng Việt với mục tiêu cải thiện khả năng xử lý ngôn ngữ tiếng Việt và nâng cao hiệu suất cho các tác vụ truy xuất thông tin mở (Retrieval Augmented Generation - RAG). **Mục đích sử dụng:** Mô hình vi-gemma-2b-RAG phù hợp cho các tác vụ sau: * Trả lời câu hỏi dựa trên ngữ cảnh tiếng Việt. * Tóm tắt văn bản tiếng Việt. * Dịch máy tiếng Việt. * Và các tác vụ tạo văn bản tiếng Việt khác. **Giới hạn:** Mặc dù đã được tinh chỉnh cho tiếng Việt, vi-gemma-2b-RAG vẫn có thể gặp phải một số hạn chế: * Có thể tạo ra thông tin sai lệch hoặc không chính xác. * Có thể thể hiện thành kiến ​​hoặc quan điểm không phù hợp. * Hiệu suất có thể bị ảnh hưởng bởi chất lượng của dữ liệu đầu vào. **Cách sử dụng:** Dưới đây chúng tôi chia sẻ một số đoạn mã về cách bắt đầu nhanh chóng để sử dụng mô hình. Trước tiên, hãy đảm bảo đã cài đặt `pip install -U transformers`, sau đó sao chép đoạn mã từ phần có liên quan đến usecase của bạn. Chúng tôi khuyến nghị sử dụng `torch.bfloat16` làm mặc định. ```python # pip install transformers torch accelerate from transformers import AutoTokenizer, AutoModelForCausalLM import torch # Khởi tạo tokenizer và model từ checkpoint đã lưu tokenizer = AutoTokenizer.from_pretrained("himmeow/vi-gemma-2b-RAG") model = AutoModelForCausalLM.from_pretrained( "himmeow/vi-gemma-2b-RAG", device_map="auto", torch_dtype=torch.bfloat16 ) # Sử dụng GPU nếu có if torch.cuda.is_available(): model.to("cuda") # Định dạng prompt cho model prompt = """ ### Instruction and Input: Dựa vào ngữ cảnh/tài liệu sau: {} Hãy trả lời câu hỏi: {} ### Response: {} """ # Chuẩn bị dữ liệu đầu vào input_data = """ Short Tandem Repeats (STRs) là các trình tự DNA lặp lại ngắn (2- 6 nucleotides) xuất hiện phổ biến trong hệ gen của con người. Các trình tự này có tính đa hình rất cao trong tự nhiên, điều này khiến các STRs trở thành những markers di truyền rất quan trọng trong nghiên cứu bản đồ gen người và chuẩn đoán bệnh lý di truyền cũng như xác định danh tính trong lĩnh vực pháp y. Các STRs trở nên phổ biến tại các phòng xét nghiệm pháp y bởi vì việc nhân bản và phân tích STRs chỉ cần lượng DNA rất thấp ngay cả khi ở dạng bị phân hủy việc đinh danh vẫn có thể được thực hiện thành công. Hơn nữa việc phát hiện và đánh giá sự nhiễm DNA mẫu trong các mẫu vật có thể được giải quyết nhanh với kết quả phân tích STRs. Ở Hoa Kỳ hiện nay, từ bộ 13 markers nay đã tăng lên 20 markers chính đang được sử dụng để tạo ra một cơ sở dữ liệu DNA trên toàn đất nước được gọi là The FBI Combined DNA Index System (Expaned CODIS). CODIS và các cơ sử dữ liệu DNA tương tự đang được sử dụng thực sự thành công trong việc liên kết các hồ sơ DNA từ các tội phạm và các bằng chứng hiện trường vụ án. Kết quả định danh STRs cũng được sử dụng để hỗ trợ hàng trăm nghìn trường hợp xét nghiệm huyết thống cha con mỗi năm' """ query = "Hãy cho tôi biết một số tính chất của STRs được dùng để làm gì?" # Định dạng input text input_text = prompt.format(input_data, query," ") # Mã hóa input text thành input ids input_ids = tokenizer(input_text, return_tensors="pt") # Sử dụng GPU cho input ids nếu có if torch.cuda.is_available(): input_ids = input_ids.to("cuda") # Tạo văn bản bằng model outputs = model.generate( **input_ids, max_new_tokens=500, no_repeat_ngram_size=5, # Ngăn chặn lặp lại các cụm từ 5 gram # do_sample=True, # Kích hoạt chế độ tạo văn bản dựa trên lấy mẫu. Trong chế độ này, model sẽ chọn ngẫu nhiên token tiếp theo dựa trên xác suất được tính từ phân phối xác suất của các token. # temperature=0.7, # Giảm temperature để kiểm soát tính ngẫu nhiên # early_stopping=True, # Dừng tạo văn bản khi tìm thấy kết thúc phù hợp ) # Giải mã và in kết quả print(tokenizer.decode(outputs[0])) ''' <bos> ### Instruction and Input: Dựa vào ngữ cảnh/tài liệu sau: Short Tandem Repeats (STRs) là các trình tự DNA lặp lại ngắn (2- 6 nucleotides) xuất hiện phổ biến trong hệ gen của con người. Các trình tự này có tính đa hình rất cao trong tự nhiên, điều này khiến các STRs trở thành những markers di truyền rất quan trọng trong nghiên cứu bản đồ gen người và chuẩn đoán bệnh lý di truyền cũng như xác định danh tính trong lĩnh vực pháp y. Các STRs trở nên phổ biến tại các phòng xét nghiệm pháp y bởi vì việc nhân bản và phân tích STRs chỉ cần lượng DNA rất thấp ngay cả khi ở dạng bị phân hủy việc đinh danh vẫn có thể được thực hiện thành công. Hơn nữa việc phát hiện và đánh giá sự nhiễm DNA mẫu trong các mẫu vật có thể được giải quyết nhanh với kết quả phân tích STRs. Ở Hoa Kỳ hiện nay, từ bộ 13 markers nay đã tăng lên 20 markers chính đang được sử dụng để tạo ra một cơ sở dữ liệu DNA trên toàn đất nước được gọi là The FBI Combined DNA Index System (Expaned CODIS). CODIS và các cơ sử dữ liệu DNA tương tự đang được sử dụng thực sự thành công trong việc liên kết các hồ sơ DNA từ các tội phạm và các bằng chứng hiện trường vụ án. Kết quả định danh STRs cũng được sử dụng để hỗ trợ hàng trăm nghìn trường hợp xét nghiệm huyết thống cha con mỗi năm' Hãy trả lời câu hỏi: Hãy cho tôi biết một số tính chất của STRs được dùng để làm gì? ### Response: STRs được sử dụng để xác định danh tính, chuẩn đoán bệnh lý và xác định bệnh lý di truyền. <eos> ''' ``` **Huấn luyện:** * **Mô hình cơ sở:** google/gemma-1.1-2b-it * **Tập dữ liệu:** lamhieu/mabrycodes_dialogue_vi * **Phương pháp tinh chỉnh:** LoRA, PEFT với Unsloth ## Model Card: vi-gemma-2b-RAG ### English **Model Description:** vi-gemma-2b-RAG is a large language model fine-tuned from the base model [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it) using LoRA. The model is trained on a Vietnamese dataset to improve its Vietnamese language processing capabilities and enhance its performance for Retrieval Augmented Generation (RAG) tasks. **Intended Use:** The vi-gemma-2b-RAG model is suitable for tasks such as: * Vietnamese question answering. * Vietnamese text summarization. * Vietnamese machine translation. * And other Vietnamese text generation tasks. **Limitations:** While fine-tuned for Vietnamese, vi-gemma-2b-RAG may still have some limitations: * It may generate incorrect or misleading information. * It may exhibit biases or inappropriate opinions. * Its performance may be affected by the quality of the input data. **How to Use:** ### Usage Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase. We recommend `torch.bfloat16` as the default dtype. ```python # pip install transformers torch accelerate from transformers import AutoTokenizer, AutoModelForCausalLM import torch # Initialize the tokenizer and model from the saved checkpoint tokenizer = AutoTokenizer.from_pretrained("himmeow/vi-gemma-2b-RAG") model = AutoModelForCausalLM.from_pretrained( "himmeow/vi-gemma-2b-RAG", device_map="auto", torch_dtype=torch.bfloat16 ) # Use GPU if available if torch.cuda.is_available(): model.to("cuda") # Define the prompt format for the model prompt = """ ### Instruction and Input: Based on the following context/document: {} Please answer the question: {} ### Response: {} """ # Prepare the input data input_data = """ Short Tandem Repeats (STRs) are short (2-6 nucleotides) repeating DNA sequences that are widespread in the human genome. These sequences are highly polymorphic in nature, which makes STRs very important genetic markers in human gene mapping and diagnosis of hereditary diseases as well as identification in the field of forensics. STRs have become popular in forensic laboratories because the replication and analysis of STRs requires very small amounts of DNA, even in decomposed form, identification can still be performed successfully. Furthermore, the detection and assessment of sample DNA contamination in specimens can be quickly resolved with STR analysis results. In the United States today, the set of 13 markers has now been increased to 20 main markers being used to create a nationwide DNA database called The FBI Combined DNA Index System (Expaned CODIS). CODIS and similar DNA databases are being used very successfully in linking DNA records from criminals and crime scene evidence. STR identification results are also used to support hundreds of thousands of paternity test cases each year.' """ query = "Tell me what are some properties of STRs used for?" # Format the input text input_text = prompt.format(input_data, query," ") # Encode the input text into input ids input_ids = tokenizer(input_text, return_tensors="pt") # Use GPU for input ids if available if torch.cuda.is_available(): input_ids = input_ids.to("cuda") # Generate text using the model outputs = model.generate( **input_ids, max_new_tokens=500, # Limit the number of tokens generated no_repeat_ngram_size=5, # Prevent repetition of 5-gram phrases # do_sample=True, # temperature=0.7, # Adjust the randomness of the generated text # early_stopping=True, # Stop generating text when a suitable ending is found ) # Decode and print the results print(tokenizer.decode(outputs[0])) ``` **Training:** * **Base Model:** google/gemma-1.1-2b-it * **Dataset:** lamhieu/mabrycodes_dialogue_vi * **Fine-tuning Method:** LoRA, PEFT and Unsloth **Using example repository:** https://github.com/Martincrux/Vietnamese-RAG-system-building-with-vi-gemma-2b-RAG-and-halong_embedding # Uploaded model - **Developed by:** [hiieu](https://huggingface.co/hiieu), [himmeow the coder](https://viblo.asia/u/MartinCrux), [cuctrinh](https://www.linkedin.com/in/trinh-cuc-5722832b6) - **License:** apache-2.0 - **Finetuned from model :** unsloth/gemma-1.1-2b-it-bnb-4bit This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
[ "CHIA" ]
knowledgator/gliner-poly-small-v1.0
knowledgator
token-classification
[ "gliner", "pytorch", "token-classification", "multilingual", "dataset:urchade/pile-mistral-v0.1", "dataset:numind/NuNER", "dataset:knowledgator/GLINER-multi-task-synthetic-data", "license:apache-2.0", "region:us" ]
2024-08-19T12:40:53Z
2024-08-25T11:38:05+00:00
32
14
--- datasets: - urchade/pile-mistral-v0.1 - numind/NuNER - knowledgator/GLINER-multi-task-synthetic-data language: - multilingual library_name: gliner license: apache-2.0 pipeline_tag: token-classification --- # About GLiNER is a Named Entity Recognition (NER) model capable of identifying any entity type using a bidirectional transformer encoders (BERT-like). It provides a practical alternative to traditional NER models, which are limited to predefined entities, and Large Language Models (LLMs) that, despite their flexibility, are costly and large for resource-constrained scenarios. This particular version utilize bi-encoder architecture with post-fusion, where textual encoder is [DeBERTa v3 small](microsoft/deberta-v3-small) and entity label encoder is sentence transformer - [BGE-small-en](https://huggingface.co/BAAI/bge-small-en-v1.5). Such architecture brings several advantages over uni-encoder GLiNER: * An unlimited amount of entities can be recognized at a single time; * Faster inference if entity embeddings are preprocessed; * Better generalization to unseen entities; Post fusion strategy brings advantages over classical bi-encoder enabling better inter-label understanding. ### Installation & Usage Install or update the gliner package: ```bash pip install gliner -U ``` Once you've downloaded the GLiNER library, you can import the GLiNER class. You can then load this model using `GLiNER.from_pretrained` and predict entities with `predict_entities`. ```python from gliner import GLiNER model = GLiNER.from_pretrained("knowledgator/gliner-poly-small-v1.0") text = """ Cristiano Ronaldo dos Santos Aveiro (Portuguese pronunciation: [kɾiʃˈtjɐnu ʁɔˈnaldu]; born 5 February 1985) is a Portuguese professional footballer who plays as a forward for and captains both Saudi Pro League club Al Nassr and the Portugal national team. Widely regarded as one of the greatest players of all time, Ronaldo has won five Ballon d'Or awards,[note 3] a record three UEFA Men's Player of the Year Awards, and four European Golden Shoes, the most by a European player. He has won 33 trophies in his career, including seven league titles, five UEFA Champions Leagues, the UEFA European Championship and the UEFA Nations League. Ronaldo holds the records for most appearances (183), goals (140) and assists (42) in the Champions League, goals in the European Championship (14), international goals (128) and international appearances (205). He is one of the few players to have made over 1,200 professional career appearances, the most by an outfield player, and has scored over 850 official senior career goals for club and country, making him the top goalscorer of all time. """ labels = ["person", "award", "date", "competitions", "teams"] entities = model.predict_entities(text, labels, threshold=0.25) for entity in entities: print(entity["text"], "=>", entity["label"]) ``` ``` Cristiano Ronaldo dos Santos Aveiro => person 5 February 1985 => date Al Nassr => teams Portugal national team => teams Ballon d'Or => award UEFA Men's Player of the Year Awards => award European Golden Shoes => award UEFA Champions Leagues => competitions UEFA European Championship => competitions UEFA Nations League => competitions Champions League => competitions European Championship => competitions ``` If you have a large amount of entities and want to pre-embed them, please, refer to the following code snippet: ```python labels = ["your entities"] texts = ["your texts"] entity_embeddings = model.encode_labels(labels, batch_size = 8) outputs = model.batch_predict_with_embeds([text], entity_embeddings, labels) ``` ### Benchmarks Below you can see the table with benchmarking results on various named entity recognition datasets: | Dataset | Score | |---------|-------| | ACE 2004 | 25.4% | | ACE 2005 | 27.2% | | AnatEM | 17.7% | | Broad Tweet Corpus | 70.2% | | CoNLL 2003 | 67.8% | | FabNER | 22.9% | | FindVehicle | 40.2% | | GENIA_NER | 47.7% | | HarveyNER | 15.5% | | MultiNERD | 64.5% | | Ontonotes | 28.7% | | PolyglotNER | 47.5% | | TweetNER7 | 39.3% | | WikiANN en | 56.7% | | WikiNeural | 80.0% | | bc2gm | 56.2% | | bc4chemd | 48.7% | | bc5cdr | 60.5% | | ncbi | 53.5% | | **Average** | **45.8%** | ||| | CrossNER_AI | 48.9% | | CrossNER_literature | 64.0% | | CrossNER_music | 68.7% | | CrossNER_politics | 69.0% | | CrossNER_science | 62.7% | | mit-movie | 40.3% | | mit-restaurant | 36.2% | | **Average (zero-shot benchmark)** | **55.7%** | ### Join Our Discord Connect with our community on Discord for news, support, and discussion about our models. Join [Discord](https://discord.gg/dkyeAgs9DG).
[ "ANATEM", "BC5CDR" ]
yixuan-chia/snowflake-arctic-embed-m-GGUF
yixuan-chia
null
[ "gguf", "endpoints_compatible", "region:us", "feature-extraction" ]
2024-08-29T07:36:07Z
2024-08-29T09:01:39+00:00
32
0
--- {} --- # yixuan-chia/snowflake-arctic-embed-m-GGUF This model was converted to GGUF format from [`Snowflake/snowflake-arctic-embed-m`](https://huggingface.co/Snowflake/snowflake-arctic-embed-m) using llama.cpp. Refer to the [original model card](https://huggingface.co/Snowflake/snowflake-arctic-embed-m) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo yixuan-chia/snowflake-arctic-embed-m-GGUF --hf-file snowflake-arctic-embed-m-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo yixuan-chia/snowflake-arctic-embed-m-GGUF --hf-file snowflake-arctic-embed-m-q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo yixuan-chia/snowflake-arctic-embed-m-GGUF --hf-file snowflake-arctic-embed-m-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo yixuan-chia/snowflake-arctic-embed-m-GGUF --hf-file snowflake-arctic-embed-m-q8_0.gguf -c 2048 ```
[ "CHIA" ]
adipanda/luffy-simpletuner-lora-9
adipanda
text-to-image
[ "diffusers", "flux", "flux-diffusers", "text-to-image", "simpletuner", "safe-for-work", "lora", "template:sd-lora", "lycoris", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]
2024-10-06T03:18:06Z
2024-10-11T01:09:28+00:00
32
0
--- base_model: black-forest-labs/FLUX.1-dev license: other tags: - flux - flux-diffusers - text-to-image - diffusers - simpletuner - safe-for-work - lora - template:sd-lora - lycoris inference: true widget: - text: unconditional (blank prompt) parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_0_0.png - text: A scene from One Piece. Monkey D. Luffy holding a sign that says 'I LOVE PROMPTS!', he is standing full body on a beach at sunset. He is wearing a red vest, yellow sash, and a straw hat. The setting sun casts a dynamic shadow on his face. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_1_0.png - text: A scene from One Piece. Monkey D. Luffy jumping out of a propeller airplane, sky diving. He looks excited and his hair is blowing in the wind. The sky is clear and blue, there are birds pictured in the distance. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_2_0.png - text: 'A scene from One Piece. Monkey D. Luffy spinning a basketball on his finger on a basketball court. He is wearing a lakers jersey with the #12 on it. The basketball hoop and crowd are in the background cheering him. He is smiling.' parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_3_0.png - text: A scene from One Piece. Monkey D. Luffy is wearing a suit in an office shaking the hand of a business woman. The woman has purple hair and is wearing professional attire. There is a Google logo in the background. It is during daytime, and the overall sentiment is one of accomplishment. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_4_0.png - text: A scene from One Piece. Monkey D. Luffy is fighting a large brown grizzly bear, deep in a forest. The bear is tall and standing on two legs, roaring. The bear is also wearing a crown because it is the king of all bears. Around them are tall trees and other animals watching. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_5_0.png --- # luffy-simpletuner-lora-9 This is a LyCORIS adapter derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev). No validation prompt was used during training. None ## Validation settings - CFG: `3.5` - CFG Rescale: `0.0` - Steps: `20` - Sampler: `None` - Seed: `42` - Resolution: `1024x1024` Note: The validation settings are not necessarily the same as the [training settings](#training-settings). You can find some example images in the following gallery: <Gallery /> The text encoder **was not** trained. You may reuse the base model text encoder for inference. ## Training settings - Training epochs: 246 - Training steps: 28800 - Learning rate: 5e-05 - Effective batch size: 8 - Micro-batch size: 8 - Gradient accumulation steps: 1 - Number of GPUs: 1 - Prediction type: flow-matching - Rescaled betas zero SNR: False - Optimizer: adamw_bf16 - Precision: Pure BF16 - Quantised: Yes: int8-quanto - Xformers: Not used - LyCORIS Config: ```json { "algo": "lokr", "multiplier": 1.0, "linear_dim": 10000, "linear_alpha": 1, "factor": 12, "apply_preset": { "target_module": [ "Attention", "FeedForward" ], "module_algo_map": { "Attention": { "factor": 12 }, "FeedForward": { "factor": 6 } } } } ``` ## Datasets ### luffy-512 - Repeats: 2 - Total number of images: 306 - Total number of aspect buckets: 1 - Resolution: 0.262144 megapixels - Cropped: False - Crop style: None - Crop aspect: None ## Inference ```python import torch from diffusers import DiffusionPipeline from lycoris import create_lycoris_from_weights model_id = 'black-forest-labs/FLUX.1-dev' adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually lora_scale = 1.0 wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer) wrapper.merge_to() prompt = "An astronaut is riding a horse through the jungles of Thailand." pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') image = pipeline( prompt=prompt, num_inference_steps=20, generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826), width=1024, height=1024, guidance_scale=3.5, ).images[0] image.save("output.png", format="PNG") ```
[ "BEAR" ]
FreedomIntelligence/Apollo2-3.8B
FreedomIntelligence
question-answering
[ "safetensors", "phi3", "biology", "medical", "question-answering", "custom_code", "ar", "en", "zh", "ko", "ja", "mn", "th", "vi", "lo", "mg", "de", "pt", "es", "fr", "ru", "it", "hr", "gl", "cs", "co", "la", "uk", "bs", "bg", "eo", "sq", "da", "sa", "gn", "sr", "sk", "gd", "lb", "hi", "ku", "mt", "he", "ln", "bm", "sw", "ig", "rw", "ha", "dataset:FreedomIntelligence/ApolloMoEDataset", "arxiv:2410.10626", "base_model:microsoft/Phi-3-mini-4k-instruct", "base_model:finetune:microsoft/Phi-3-mini-4k-instruct", "license:apache-2.0", "region:us" ]
2024-10-14T07:47:08Z
2024-11-20T03:43:07+00:00
32
1
--- base_model: - microsoft/Phi-3-mini-4k-instruct datasets: - FreedomIntelligence/ApolloMoEDataset language: - ar - en - zh - ko - ja - mn - th - vi - lo - mg - de - pt - es - fr - ru - it - hr - gl - cs - co - la - uk - bs - bg - eo - sq - da - sa - gn - sr - sk - gd - lb - hi - ku - mt - he - ln - bm - sw - ig - rw - ha license: apache-2.0 metrics: - accuracy pipeline_tag: question-answering tags: - biology - medical --- # Democratizing Medical LLMs For Much More Languages Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish, Arabic, Russian, Japanese, Korean, German, Italian, Portuguese and 38 Minor Languages So far. <p align="center"> 📃 <a href="https://arxiv.org/abs/2410.10626" target="_blank">Paper</a> • 🌐 <a href="" target="_blank">Demo</a> • 🤗 <a href="https://huggingface.co/datasets/FreedomIntelligence/ApolloMoEDataset" target="_blank">ApolloMoEDataset</a> • 🤗 <a href="https://huggingface.co/datasets/FreedomIntelligence/ApolloMoEBench" target="_blank">ApolloMoEBench</a> • 🤗 <a href="https://huggingface.co/collections/FreedomIntelligence/apollomoe-and-apollo2-670ddebe3bb1ba1aebabbf2c" target="_blank">Models</a> •🌐 <a href="https://github.com/FreedomIntelligence/Apollo" target="_blank">Apollo</a> • 🌐 <a href="https://github.com/FreedomIntelligence/ApolloMoE" target="_blank">ApolloMoE</a> </p> ![Apollo](assets/apollo_medium_final.png) ## 🌈 Update * **[2024.10.15]** ApolloMoE repo is published！🎉 ## Languages Coverage 12 Major Languages and 38 Minor Languages <details> <summary>Click to view the Languages Coverage</summary> ![ApolloMoE](assets/languages.png) </details> ## Architecture <details> <summary>Click to view the MoE routing image</summary> ![ApolloMoE](assets/hybrid_routing.png) </details> ## Results #### Dense 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-0.5B" target="_blank">Apollo2-0.5B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-1.5B" target="_blank">Apollo2-1.5B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-2B" target="_blank">Apollo2-2B</a> 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-3.8B" target="_blank">Apollo2-3.8B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-7B" target="_blank">Apollo2-7B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo2-9B" target="_blank">Apollo2-9B</a> <details> <summary>Click to view the Dense Models Results</summary> ![ApolloMoE](assets/dense_results.png) </details> #### Post-MoE 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo-MoE-0.5B" target="_blank">Apollo-MoE-0.5B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo-MoE-1.5B" target="_blank">Apollo-MoE-1.5B</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/Apollo-MoE-7B" target="_blank">Apollo-MoE-7B</a> <details> <summary>Click to view the Post-MoE Models Results</summary> ![ApolloMoE](assets/post_moe_results.png) </details> ## Usage Format ##### Apollo2 - 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|> - 2B, 9B: User:{query}\nAssistant:{response}\<eos\> - 3.8B: <|user|>\n{query}<|end|><|assisitant|>\n{response}<|end|> ##### Apollo-MoE - 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|> ## Dataset & Evaluation - Dataset 🤗 <a href="https://huggingface.co/datasets/FreedomIntelligence/ApolloMoEDataset" target="_blank">ApolloMoEDataset</a> <details><summary>Click to expand</summary> ![ApolloMoE](assets/Dataset.png) - [Data category](https://huggingface.co/datasets/FreedomIntelligence/ApolloCorpus/tree/main/train) </details> - Evaluation 🤗 <a href="https://huggingface.co/datasets/FreedomIntelligence/ApolloMoEBench" target="_blank">ApolloMoEBench</a> <details><summary>Click to expand</summary> - EN: - [MedQA-USMLE](https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options) - [MedMCQA](https://huggingface.co/datasets/medmcqa/viewer/default/test) - [PubMedQA](https://huggingface.co/datasets/pubmed_qa): Because the results fluctuated too much, they were not used in the paper. - [MMLU-Medical](https://huggingface.co/datasets/cais/mmlu) - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - ZH: - [MedQA-MCMLE](https://huggingface.co/datasets/bigbio/med_qa/viewer/med_qa_zh_4options_bigbio_qa/test) - [CMB-single](https://huggingface.co/datasets/FreedomIntelligence/CMB): Not used in the paper - Randomly sample 2,000 multiple-choice questions with single answer. - [CMMLU-Medical](https://huggingface.co/datasets/haonan-li/cmmlu) - Anatomy, Clinical_knowledge, College_medicine, Genetics, Nutrition, Traditional_chinese_medicine, Virology - [CExam](https://github.com/williamliujl/CMExam): Not used in the paper - Randomly sample 2,000 multiple-choice questions - ES: [Head_qa](https://huggingface.co/datasets/head_qa) - FR: - [Frenchmedmcqa](https://github.com/qanastek/FrenchMedMCQA) - [MMLU_FR] - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - HI: [MMLU_HI](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Hindi) - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - AR: [MMLU_AR](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Arabic) - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - JA: [IgakuQA](https://github.com/jungokasai/IgakuQA) - KO: [KorMedMCQA](https://huggingface.co/datasets/sean0042/KorMedMCQA) - IT: - [MedExpQA](https://huggingface.co/datasets/HiTZ/MedExpQA) - [MMLU_IT] - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine - DE: [BioInstructQA](https://huggingface.co/datasets/BioMistral/BioInstructQA): German part - PT: [BioInstructQA](https://huggingface.co/datasets/BioMistral/BioInstructQA): Portuguese part - RU: [RuMedBench](https://github.com/sb-ai-lab/MedBench) </details> ## Model Download and Inference We take Apollo-MoE-0.5B as an example 1. Login Huggingface ``` huggingface-cli login --token $HUGGINGFACE_TOKEN ``` 2. Download model to local dir ```python from huggingface_hub import snapshot_download import os local_model_dir=os.path.join('/path/to/models/dir','Apollo-MoE-0.5B') snapshot_download(repo_id="FreedomIntelligence/Apollo-MoE-0.5B", local_dir=local_model_dir) ``` 3. Inference Example ```python from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig import os local_model_dir=os.path.join('/path/to/models/dir','Apollo-MoE-0.5B') model=AutoModelForCausalLM.from_pretrained(local_model_dir,trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained(local_model_dir,trust_remote_code=True) generation_config = GenerationConfig.from_pretrained(local_model_dir, pad_token_id=tokenizer.pad_token_id, num_return_sequences=1, max_new_tokens=7, min_new_tokens=2, do_sample=False, temperature=1.0, top_k=50, top_p=1.0) inputs = tokenizer('Answer direclty.\nThe capital of Mongolia is Ulaanbaatar.\nThe capital of Iceland is Reykjavik.\nThe capital of Australia is', return_tensors='pt') inputs = inputs.to(model.device) pred = model.generate(**inputs,generation_config=generation_config) print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True)) ``` ## Results reproduction <details><summary>Click to expand</summary> We take Apollo2-7B or Apollo-MoE-0.5B as example 1. Download Dataset for project: ``` bash 0.download_data.sh  ``` 2. Prepare test and dev data for specific model: - Create test data for with special token ``` bash 1.data_process_test&dev.sh ``` 3. Prepare train data for specific model (Create tokenized data in advance): - You can adjust data Training order and Training Epoch in this step ``` bash 2.data_process_train.sh ``` 4. Train the model - If you want to train in Multi Nodes please refer to ./src/sft/training_config/zero_multi.yaml ``` bash 3.single_node_train.sh ``` 5. Evaluate your model: Generate score for benchmark ``` bash 4.eval.sh ``` </details> ## Citation Please use the following citation if you intend to use our dataset for training or evaluation: ``` @misc{zheng2024efficientlydemocratizingmedicalllms, title={Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts}, author={Guorui Zheng and Xidong Wang and Juhao Liang and Nuo Chen and Yuping Zheng and Benyou Wang}, year={2024}, eprint={2410.10626}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2410.10626}, } ```
[ "HEAD-QA", "MEDQA", "PUBMEDQA" ]
joe32140/ColModernBERT-base-msmarco-en-bge
joe32140
sentence-similarity
[ "PyLate", "safetensors", "modernbert", "ColBERT", "sentence-transformers", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:808728", "loss:Distillation", "en", "dataset:lightonai/ms-marco-en-bge", "arxiv:1908.10084", "base_model:answerdotai/ModernBERT-base", "base_model:finetune:answerdotai/ModernBERT-base", "model-index", "region:us" ]
2024-12-20T16:55:41Z
2024-12-21T22:20:32+00:00
32
1
--- base_model: answerdotai/ModernBERT-base datasets: - lightonai/ms-marco-en-bge language: - en library_name: PyLate pipeline_tag: sentence-similarity tags: - ColBERT - PyLate - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:808728 - loss:Distillation model-index: - name: ColBERT based on answerdotai/ModernBERT-base results: - task: type: Retrieval dataset: name: FiQA type: beir/fiqa split: test metrics: - type: ndcg_at_10 value: 39.86 - task: type: Retrieval dataset: name: SciFact type: beir/scifact split: test metrics: - type: ndcg_at_10 value: 73.67 - task: type: Retrieval dataset: name: nfcorpus type: beir/nfcorpus split: test metrics: - type: ndcg_at_10 value: 33.98 - task: type: Retrieval dataset: name: arguana type: beir/arguana split: test metrics: - type: ndcg_at_10 value: 30.98 --- # PyLate model based on answerdotai/ModernBERT-base This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the [train](https://huggingface.co/datasets/lightonai/ms-marco-en-bge) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator. I finetuned the model with official script [examples/train_pylate.py](https://github.com/AnswerDotAI/ModernBERT/blob/main/examples/train_pylate.py) on a RTX 4090 GPU in 12 hours. See more details in [trianing logs](https://wandb.ai/joe32140/col-modernbert-msmarco/workspace?nw=nwuserjoe32140). The finetuned model performance is on par with numbers reported in the paper. ## Model Details ### Model Description - **Model Type:** PyLate model - **Base model:** [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) <!-- at revision 5756c58a31a2478f9e62146021f48295a92c3da5 --> - **Document Length:** 180 tokens - **Query Length:** 32 tokens - **Output Dimensionality:** 128 tokens - **Similarity Function:** MaxSim - **Training Dataset:** - [train](https://huggingface.co/datasets/lightonai/ms-marco-en-bge) - **Language:** en <!-- - **License:** Unknown --> ### Model Sources - **Documentation:** [PyLate Documentation](https://lightonai.github.io/pylate/) - **Repository:** [PyLate on GitHub](https://github.com/lightonai/pylate) - **Hugging Face:** [PyLate models on Hugging Face](https://huggingface.co/models?library=PyLate) ### Full Model Architecture ``` ColBERT( (0): Transformer({'max_seq_length': 179, 'do_lower_case': False}) with Transformer model: ModernBertModel (1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'}) ) ``` ## Usage First install the PyLate library: ```bash pip install -U pylate ``` ### Retrieval PyLate provides a streamlined interface to index and retrieve documents using ColBERT models. The index leverages the Voyager HNSW index to efficiently handle document embeddings and enable fast retrieval. #### Indexing documents First, load the ColBERT model and initialize the Voyager index, then encode and index your documents: ```python from pylate import indexes, models, retrieve # Step 1: Load the ColBERT model model = models.ColBERT( model_name_or_path=pylate_model_id, ) # Step 2: Initialize the Voyager index index = indexes.Voyager( index_folder="pylate-index", index_name="index", override=True, # This overwrites the existing index if any ) # Step 3: Encode the documents documents_ids = ["1", "2", "3"] documents = ["document 1 text", "document 2 text", "document 3 text"] documents_embeddings = model.encode( documents, batch_size=32, is_query=False, # Ensure that it is set to False to indicate that these are documents, not queries show_progress_bar=True, ) # Step 4: Add document embeddings to the index by providing embeddings and corresponding ids index.add_documents( documents_ids=documents_ids, documents_embeddings=documents_embeddings, ) ``` Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it: ```python # To load an index, simply instantiate it with the correct folder/name and without overriding it index = indexes.Voyager( index_folder="pylate-index", index_name="index", ) ``` #### Retrieving top-k documents for queries Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries. To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores: ```python # Step 1: Initialize the ColBERT retriever retriever = retrieve.ColBERT(index=index) # Step 2: Encode the queries queries_embeddings = model.encode( ["query for document 3", "query for document 1"], batch_size=32, is_query=True, # # Ensure that it is set to False to indicate that these are queries show_progress_bar=True, ) # Step 3: Retrieve top-k documents scores = retriever.retrieve( queries_embeddings=queries_embeddings, k=10, # Retrieve the top 10 matches for each query ) ``` ### Reranking If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank: ```python from pylate import rank, models queries = [ "query A", "query B", ] documents = [ ["document A", "document B"], ["document 1", "document C", "document B"], ] documents_ids = [ [1, 2], [1, 3, 2], ] model = models.ColBERT( model_name_or_path=pylate_model_id, ) queries_embeddings = model.encode( queries, is_query=True, ) documents_embeddings = model.encode( documents, is_query=False, ) reranked_documents = rank.rerank( documents_ids=documents_ids, queries_embeddings=queries_embeddings, documents_embeddings=documents_embeddings, ) ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Evaluation NDCG@10 |Dataset | Score| |:-------|------| |FiQA | 0.3986| |SciFact | 0.7367| |nfcorpus | 0.3398 | |arguana|0.3098| ## Training Details ### Training Dataset #### train * Dataset: [train](https://huggingface.co/datasets/lightonai/ms-marco-en-bge) at [11e6ffa](https://huggingface.co/datasets/lightonai/ms-marco-en-bge/tree/11e6ffa1d22f461579f451eb31bdc964244cb61f) * Size: 808,728 training samples * Columns: <code>query_id</code>, <code>document_ids</code>, and <code>scores</code> * Approximate statistics based on the first 1000 samples: | | query_id | document_ids | scores | |:--------|:--------------------------------------------------------------------------------|:------------------------------------|:------------------------------------| | type | string | list | list | | details | <ul><li>min: 5 tokens</li><li>mean: 5.59 tokens</li><li>max: 6 tokens</li></ul> | <ul><li>size: 32 elements</li></ul> | <ul><li>size: 32 elements</li></ul> | * Samples: | query_id | document_ids | scores | |:--------------------|:--------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------| | <code>121352</code> | <code>['2259784', '4923159', '40211', '1545154', '8527175', ...]</code> | <code>[0.2343463897705078, 0.639204204082489, 0.3806908428668976, 0.5623092651367188, 0.8051995635032654, ...]</code> | | <code>634306</code> | <code>['7723525', '1874779', '379307', '2738583', '7599583', ...]</code> | <code>[0.7124203443527222, 0.7379189729690552, 0.5786551237106323, 0.6142299175262451, 0.6755089163780212, ...]</code> | | <code>920825</code> | <code>['5976297', '2866112', '3560294', '3285659', '4706740', ...]</code> | <code>[0.6462352871894836, 0.7880821228027344, 0.791019856929779, 0.7709633111953735, 0.8284491300582886, ...]</code> | * Loss: <code>pylate.losses.distillation.Distillation</code> ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 4 - `gradient_accumulation_steps`: 4 - `learning_rate`: 8e-05 - `num_train_epochs`: 1 - `warmup_ratio`: 0.05 - `bf16`: True - `tf32`: True #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 4 - `per_device_eval_batch_size`: 8 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 4 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 8e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 1 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.05 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: True - `fp16`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: True - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional </details> ### Training Logs <details><summary>Click to expand</summary> | Epoch | Step | Training Loss | |:------:|:-----:|:-------------:| | 0.0020 | 100 | 0.0524 | | 0.0040 | 200 | 0.0482 | | 0.0059 | 300 | 0.0464 | | 0.0079 | 400 | 0.043 | | 0.0099 | 500 | 0.0387 | | 0.0119 | 600 | 0.0383 | | 0.0138 | 700 | 0.0345 | | 0.0158 | 800 | 0.0307 | | 0.0178 | 900 | 0.0294 | | 0.0198 | 1000 | 0.0275 | | 0.0218 | 1100 | 0.0271 | | 0.0237 | 1200 | 0.0264 | | 0.0257 | 1300 | 0.0258 | | 0.0277 | 1400 | 0.0246 | | 0.0297 | 1500 | 0.0239 | | 0.0317 | 1600 | 0.023 | | 0.0336 | 1700 | 0.0216 | | 0.0356 | 1800 | 0.0282 | | 0.0376 | 1900 | 0.0211 | | 0.0396 | 2000 | 0.0205 | | 0.0415 | 2100 | 0.0197 | | 0.0435 | 2200 | 0.0187 | | 0.0455 | 2300 | 0.0184 | | 0.0475 | 2400 | 0.0177 | | 0.0495 | 2500 | 0.0179 | | 0.0514 | 2600 | 0.0173 | | 0.0534 | 2700 | 0.0169 | | 0.0554 | 2800 | 0.0163 | | 0.0574 | 2900 | 0.016 | | 0.0594 | 3000 | 0.016 | | 0.0613 | 3100 | 0.0147 | | 0.0633 | 3200 | 0.0148 | | 0.0653 | 3300 | 0.0155 | | 0.0673 | 3400 | 0.0149 | | 0.0692 | 3500 | 0.0149 | | 0.0712 | 3600 | 0.0141 | | 0.0732 | 3700 | 0.0145 | | 0.0752 | 3800 | 0.0142 | | 0.0772 | 3900 | 0.0143 | | 0.0791 | 4000 | 0.0137 | | 0.0811 | 4100 | 0.0134 | | 0.0831 | 4200 | 0.0129 | | 0.0851 | 4300 | 0.0133 | | 0.0871 | 4400 | 0.0135 | | 0.0890 | 4500 | 0.0128 | | 0.0910 | 4600 | 0.0126 | | 0.0930 | 4700 | 0.0126 | | 0.0950 | 4800 | 0.0129 | | 0.0969 | 4900 | 0.0127 | | 0.0989 | 5000 | 0.0127 | | 0.1009 | 5100 | 0.0125 | | 0.1029 | 5200 | 0.0119 | | 0.1049 | 5300 | 0.0124 | | 0.1068 | 5400 | 0.012 | | 0.1088 | 5500 | 0.013 | | 0.1108 | 5600 | 0.0119 | | 0.1128 | 5700 | 0.0118 | | 0.1147 | 5800 | 0.0121 | | 0.1167 | 5900 | 0.0119 | | 0.1187 | 6000 | 0.0116 | | 0.1207 | 6100 | 0.0112 | | 0.1227 | 6200 | 0.0116 | | 0.1246 | 6300 | 0.0115 | | 0.1266 | 6400 | 0.0119 | | 0.1286 | 6500 | 0.0115 | | 0.1306 | 6600 | 0.0109 | | 0.1326 | 6700 | 0.0114 | | 0.1345 | 6800 | 0.0114 | | 0.1365 | 6900 | 0.0109 | | 0.1385 | 7000 | 0.011 | | 0.1405 | 7100 | 0.0111 | | 0.1424 | 7200 | 0.0109 | | 0.1444 | 7300 | 0.0108 | | 0.1464 | 7400 | 0.0112 | | 0.1484 | 7500 | 0.0106 | | 0.1504 | 7600 | 0.011 | | 0.1523 | 7700 | 0.0106 | | 0.1543 | 7800 | 0.0107 | | 0.1563 | 7900 | 0.0108 | | 0.1583 | 8000 | 0.0106 | | 0.1603 | 8100 | 0.0107 | | 0.1622 | 8200 | 0.0108 | | 0.1642 | 8300 | 0.0103 | | 0.1662 | 8400 | 0.0107 | | 0.1682 | 8500 | 0.0104 | | 0.1701 | 8600 | 0.011 | | 0.1721 | 8700 | 0.0105 | | 0.1741 | 8800 | 0.0105 | | 0.1761 | 8900 | 0.01 | | 0.1781 | 9000 | 0.0106 | | 0.1800 | 9100 | 0.0105 | | 0.1820 | 9200 | 0.0104 | | 0.1840 | 9300 | 0.0104 | | 0.1860 | 9400 | 0.0107 | | 0.1879 | 9500 | 0.0102 | | 0.1899 | 9600 | 0.0103 | | 0.1919 | 9700 | 0.0105 | | 0.1939 | 9800 | 0.01 | | 0.1959 | 9900 | 0.0098 | | 0.1978 | 10000 | 0.0099 | | 0.1998 | 10100 | 0.0099 | | 0.2018 | 10200 | 0.0099 | | 0.2038 | 10300 | 0.0098 | | 0.2058 | 10400 | 0.01 | | 0.2077 | 10500 | 0.0101 | | 0.2097 | 10600 | 0.0098 | | 0.2117 | 10700 | 0.0101 | | 0.2137 | 10800 | 0.0098 | | 0.2156 | 10900 | 0.0101 | | 0.2176 | 11000 | 0.01 | | 0.2196 | 11100 | 0.01 | | 0.2216 | 11200 | 0.0096 | | 0.2236 | 11300 | 0.0096 | | 0.2255 | 11400 | 0.0096 | | 0.2275 | 11500 | 0.0098 | | 0.2295 | 11600 | 0.0099 | | 0.2315 | 11700 | 0.0094 | | 0.2335 | 11800 | 0.0096 | | 0.2354 | 11900 | 0.0094 | | 0.2374 | 12000 | 0.0098 | | 0.2394 | 12100 | 0.0095 | | 0.2414 | 12200 | 0.0095 | | 0.2433 | 12300 | 0.0098 | | 0.2453 | 12400 | 0.0097 | | 0.2473 | 12500 | 0.0094 | | 0.2493 | 12600 | 0.0093 | | 0.2513 | 12700 | 0.0093 | | 0.2532 | 12800 | 0.0092 | | 0.2552 | 12900 | 0.0094 | | 0.2572 | 13000 | 0.0095 | | 0.2592 | 13100 | 0.0093 | | 0.2612 | 13200 | 0.009 | | 0.2631 | 13300 | 0.0087 | | 0.2651 | 13400 | 0.0089 | | 0.2671 | 13500 | 0.009 | | 0.2691 | 13600 | 0.0091 | | 0.2710 | 13700 | 0.0092 | | 0.2730 | 13800 | 0.0089 | | 0.2750 | 13900 | 0.0091 | | 0.2770 | 14000 | 0.0092 | | 0.2790 | 14100 | 0.0088 | | 0.2809 | 14200 | 0.009 | | 0.2829 | 14300 | 0.0091 | | 0.2849 | 14400 | 0.0086 | | 0.2869 | 14500 | 0.009 | | 0.2888 | 14600 | 0.0088 | | 0.2908 | 14700 | 0.0092 | | 0.2928 | 14800 | 0.009 | | 0.2948 | 14900 | 0.0088 | | 0.2968 | 15000 | 0.0087 | | 0.2987 | 15100 | 0.0085 | | 0.3007 | 15200 | 0.009 | | 0.3027 | 15300 | 0.0088 | | 0.3047 | 15400 | 0.0086 | | 0.3067 | 15500 | 0.0087 | | 0.3086 | 15600 | 0.0088 | | 0.3106 | 15700 | 0.0085 | | 0.3126 | 15800 | 0.0088 | | 0.3146 | 15900 | 0.0085 | | 0.3165 | 16000 | 0.0086 | | 0.3185 | 16100 | 0.0086 | | 0.3205 | 16200 | 0.0087 | | 0.3225 | 16300 | 0.0088 | | 0.3245 | 16400 | 0.0087 | | 0.3264 | 16500 | 0.0087 | | 0.3284 | 16600 | 0.0086 | | 0.3304 | 16700 | 0.0087 | | 0.3324 | 16800 | 0.0092 | | 0.3344 | 16900 | 0.0085 | | 0.3363 | 17000 | 0.0088 | | 0.3383 | 17100 | 0.0084 | | 0.3403 | 17200 | 0.0088 | | 0.3423 | 17300 | 0.0083 | | 0.3442 | 17400 | 0.0085 | | 0.3462 | 17500 | 0.0083 | | 0.3482 | 17600 | 0.0084 | | 0.3502 | 17700 | 0.0084 | | 0.3522 | 17800 | 0.0083 | | 0.3541 | 17900 | 0.0087 | | 0.3561 | 18000 | 0.0083 | | 0.3581 | 18100 | 0.0085 | | 0.3601 | 18200 | 0.0082 | | 0.3621 | 18300 | 0.0079 | | 0.3640 | 18400 | 0.0085 | | 0.3660 | 18500 | 0.0084 | | 0.3680 | 18600 | 0.0082 | | 0.3700 | 18700 | 0.0083 | | 0.3719 | 18800 | 0.0082 | | 0.3739 | 18900 | 0.0082 | | 0.3759 | 19000 | 0.0083 | | 0.3779 | 19100 | 0.0081 | | 0.3799 | 19200 | 0.0083 | | 0.3818 | 19300 | 0.0079 | | 0.3838 | 19400 | 0.0083 | | 0.3858 | 19500 | 0.0082 | | 0.3878 | 19600 | 0.0084 | | 0.3897 | 19700 | 0.0084 | | 0.3917 | 19800 | 0.008 | | 0.3937 | 19900 | 0.0081 | | 0.3957 | 20000 | 0.0083 | | 0.3977 | 20100 | 0.0082 | | 0.3996 | 20200 | 0.0078 | | 0.4016 | 20300 | 0.0079 | | 0.4036 | 20400 | 0.0081 | | 0.4056 | 20500 | 0.0085 | | 0.4076 | 20600 | 0.0082 | | 0.4095 | 20700 | 0.008 | | 0.4115 | 20800 | 0.0079 | | 0.4135 | 20900 | 0.0081 | | 0.4155 | 21000 | 0.008 | | 0.4174 | 21100 | 0.0079 | | 0.4194 | 21200 | 0.0077 | | 0.4214 | 21300 | 0.0078 | | 0.4234 | 21400 | 0.0082 | | 0.4254 | 21500 | 0.008 | | 0.4273 | 21600 | 0.0076 | | 0.4293 | 21700 | 0.0075 | | 0.4313 | 21800 | 0.0078 | | 0.4333 | 21900 | 0.0081 | | 0.4353 | 22000 | 0.0077 | | 0.4372 | 22100 | 0.0079 | | 0.4392 | 22200 | 0.0078 | | 0.4412 | 22300 | 0.0078 | | 0.4432 | 22400 | 0.0077 | | 0.4451 | 22500 | 0.0078 | | 0.4471 | 22600 | 0.0079 | | 0.4491 | 22700 | 0.0078 | | 0.4511 | 22800 | 0.0079 | | 0.4531 | 22900 | 0.0075 | | 0.4550 | 23000 | 0.0077 | | 0.4570 | 23100 | 0.0076 | | 0.4590 | 23200 | 0.0078 | | 0.4610 | 23300 | 0.0075 | | 0.4629 | 23400 | 0.0075 | | 0.4649 | 23500 | 0.0078 | | 0.4669 | 23600 | 0.0075 | | 0.4689 | 23700 | 0.0076 | | 0.4709 | 23800 | 0.0075 | | 0.4728 | 23900 | 0.0075 | | 0.4748 | 24000 | 0.0075 | | 0.4768 | 24100 | 0.0076 | | 0.4788 | 24200 | 0.0079 | | 0.4808 | 24300 | 0.0076 | | 0.4827 | 24400 | 0.0077 | | 0.4847 | 24500 | 0.0077 | | 0.4867 | 24600 | 0.0073 | | 0.4887 | 24700 | 0.0077 | | 0.4906 | 24800 | 0.0076 | | 0.4926 | 24900 | 0.0075 | | 0.4946 | 25000 | 0.0076 | | 0.4966 | 25100 | 0.0078 | | 0.4986 | 25200 | 0.0077 | | 0.5005 | 25300 | 0.0076 | | 0.5025 | 25400 | 0.0076 | | 0.5045 | 25500 | 0.0076 | | 0.5065 | 25600 | 0.0073 | | 0.5085 | 25700 | 0.0075 | | 0.5104 | 25800 | 0.0072 | | 0.5124 | 25900 | 0.0074 | | 0.5144 | 26000 | 0.0075 | | 0.5164 | 26100 | 0.0075 | | 0.5183 | 26200 | 0.0072 | | 0.5203 | 26300 | 0.0073 | | 0.5223 | 26400 | 0.0073 | | 0.5243 | 26500 | 0.0073 | | 0.5263 | 26600 | 0.0076 | | 0.5282 | 26700 | 0.0075 | | 0.5302 | 26800 | 0.0075 | | 0.5322 | 26900 | 0.0071 | | 0.5342 | 27000 | 0.0074 | | 0.5362 | 27100 | 0.0073 | | 0.5381 | 27200 | 0.0072 | | 0.5401 | 27300 | 0.0071 | | 0.5421 | 27400 | 0.0073 | | 0.5441 | 27500 | 0.0072 | | 0.5460 | 27600 | 0.0076 | | 0.5480 | 27700 | 0.0072 | | 0.5500 | 27800 | 0.0074 | | 0.5520 | 27900 | 0.0072 | | 0.5540 | 28000 | 0.0072 | | 0.5559 | 28100 | 0.0071 | | 0.5579 | 28200 | 0.0069 | | 0.5599 | 28300 | 0.0071 | | 0.5619 | 28400 | 0.0075 | | 0.5638 | 28500 | 0.0074 | | 0.5658 | 28600 | 0.0072 | | 0.5678 | 28700 | 0.0074 | | 0.5698 | 28800 | 0.0072 | | 0.5718 | 28900 | 0.0072 | | 0.5737 | 29000 | 0.0073 | | 0.5757 | 29100 | 0.0072 | | 0.5777 | 29200 | 0.0069 | | 0.5797 | 29300 | 0.0069 | | 0.5817 | 29400 | 0.007 | | 0.5836 | 29500 | 0.0071 | | 0.5856 | 29600 | 0.007 | | 0.5876 | 29700 | 0.0069 | | 0.5896 | 29800 | 0.0072 | | 0.5915 | 29900 | 0.007 | | 0.5935 | 30000 | 0.007 | | 0.5955 | 30100 | 0.007 | | 0.5975 | 30200 | 0.0069 | | 0.5995 | 30300 | 0.0068 | | 0.6014 | 30400 | 0.0071 | | 0.6034 | 30500 | 0.007 | | 0.6054 | 30600 | 0.0071 | | 0.6074 | 30700 | 0.007 | | 0.6094 | 30800 | 0.0069 | | 0.6113 | 30900 | 0.007 | | 0.6133 | 31000 | 0.0071 | | 0.6153 | 31100 | 0.0069 | | 0.6173 | 31200 | 0.007 | | 0.6192 | 31300 | 0.0068 | | 0.6212 | 31400 | 0.0069 | | 0.6232 | 31500 | 0.0068 | | 0.6252 | 31600 | 0.0068 | | 0.6272 | 31700 | 0.007 | | 0.6291 | 31800 | 0.0068 | | 0.6311 | 31900 | 0.0069 | | 0.6331 | 32000 | 0.0068 | | 0.6351 | 32100 | 0.0069 | | 0.6370 | 32200 | 0.0066 | | 0.6390 | 32300 | 0.0068 | | 0.6410 | 32400 | 0.0067 | | 0.6430 | 32500 | 0.0068 | | 0.6450 | 32600 | 0.0069 | | 0.6469 | 32700 | 0.0068 | | 0.6489 | 32800 | 0.0065 | | 0.6509 | 32900 | 0.0068 | | 0.6529 | 33000 | 0.0067 | | 0.6549 | 33100 | 0.0066 | | 0.6568 | 33200 | 0.0069 | | 0.6588 | 33300 | 0.0067 | | 0.6608 | 33400 | 0.0067 | | 0.6628 | 33500 | 0.0068 | | 0.6647 | 33600 | 0.0066 | | 0.6667 | 33700 | 0.0069 | | 0.6687 | 33800 | 0.0069 | | 0.6707 | 33900 | 0.0064 | | 0.6727 | 34000 | 0.0065 | | 0.6746 | 34100 | 0.0067 | | 0.6766 | 34200 | 0.0063 | | 0.6786 | 34300 | 0.0067 | | 0.6806 | 34400 | 0.0066 | | 0.6826 | 34500 | 0.0065 | | 0.6845 | 34600 | 0.0064 | | 0.6865 | 34700 | 0.0066 | | 0.6885 | 34800 | 0.0065 | | 0.6905 | 34900 | 0.0064 | | 0.6924 | 35000 | 0.0066 | | 0.6944 | 35100 | 0.0064 | | 0.6964 | 35200 | 0.0064 | | 0.6984 | 35300 | 0.0066 | | 0.7004 | 35400 | 0.0065 | | 0.7023 | 35500 | 0.0067 | | 0.7043 | 35600 | 0.0065 | | 0.7063 | 35700 | 0.0064 | | 0.7083 | 35800 | 0.0066 | | 0.7103 | 35900 | 0.0065 | | 0.7122 | 36000 | 0.0067 | | 0.7142 | 36100 | 0.0069 | | 0.7162 | 36200 | 0.0065 | | 0.7182 | 36300 | 0.0064 | | 0.7201 | 36400 | 0.0064 | | 0.7221 | 36500 | 0.0066 | | 0.7241 | 36600 | 0.0065 | | 0.7261 | 36700 | 0.0062 | | 0.7281 | 36800 | 0.0068 | | 0.7300 | 36900 | 0.0064 | | 0.7320 | 37000 | 0.0067 | | 0.7340 | 37100 | 0.0063 | | 0.7360 | 37200 | 0.0063 | | 0.7379 | 37300 | 0.0064 | | 0.7399 | 37400 | 0.0066 | | 0.7419 | 37500 | 0.0065 | | 0.7439 | 37600 | 0.0064 | | 0.7459 | 37700 | 0.0065 | | 0.7478 | 37800 | 0.0064 | | 0.7498 | 37900 | 0.0063 | | 0.7518 | 38000 | 0.0062 | | 0.7538 | 38100 | 0.0064 | | 0.7558 | 38200 | 0.0062 | | 0.7577 | 38300 | 0.0064 | | 0.7597 | 38400 | 0.0063 | | 0.7617 | 38500 | 0.0063 | | 0.7637 | 38600 | 0.0065 | | 0.7656 | 38700 | 0.0063 | | 0.7676 | 38800 | 0.0064 | | 0.7696 | 38900 | 0.0062 | | 0.7716 | 39000 | 0.0062 | | 0.7736 | 39100 | 0.0062 | | 0.7755 | 39200 | 0.0063 | | 0.7775 | 39300 | 0.0065 | | 0.7795 | 39400 | 0.0061 | | 0.7815 | 39500 | 0.0062 | | 0.7835 | 39600 | 0.0063 | | 0.7854 | 39700 | 0.0062 | | 0.7874 | 39800 | 0.0062 | | 0.7894 | 39900 | 0.0063 | | 0.7914 | 40000 | 0.0059 | | 0.7933 | 40100 | 0.0063 | | 0.7953 | 40200 | 0.0064 | | 0.7973 | 40300 | 0.006 | | 0.7993 | 40400 | 0.0063 | | 0.8013 | 40500 | 0.0061 | | 0.8032 | 40600 | 0.0061 | | 0.8052 | 40700 | 0.0062 | | 0.8072 | 40800 | 0.0062 | | 0.8092 | 40900 | 0.006 | | 0.8112 | 41000 | 0.0061 | | 0.8131 | 41100 | 0.0063 | | 0.8151 | 41200 | 0.0059 | | 0.8171 | 41300 | 0.0062 | | 0.8191 | 41400 | 0.0062 | | 0.8210 | 41500 | 0.0062 | | 0.8230 | 41600 | 0.0062 | | 0.8250 | 41700 | 0.0061 | | 0.8270 | 41800 | 0.0061 | | 0.8290 | 41900 | 0.0061 | | 0.8309 | 42000 | 0.0063 | | 0.8329 | 42100 | 0.0064 | | 0.8349 | 42200 | 0.0063 | | 0.8369 | 42300 | 0.0063 | | 0.8388 | 42400 | 0.0061 | | 0.8408 | 42500 | 0.0062 | | 0.8428 | 42600 | 0.0062 | | 0.8448 | 42700 | 0.0061 | | 0.8468 | 42800 | 0.0059 | | 0.8487 | 42900 | 0.006 | | 0.8507 | 43000 | 0.0061 | | 0.8527 | 43100 | 0.0062 | | 0.8547 | 43200 | 0.0058 | | 0.8567 | 43300 | 0.0065 | | 0.8586 | 43400 | 0.0064 | | 0.8606 | 43500 | 0.006 | | 0.8626 | 43600 | 0.0061 | | 0.8646 | 43700 | 0.0059 | | 0.8665 | 43800 | 0.0063 | | 0.8685 | 43900 | 0.0061 | | 0.8705 | 44000 | 0.006 | | 0.8725 | 44100 | 0.0061 | | 0.8745 | 44200 | 0.0061 | | 0.8764 | 44300 | 0.0059 | | 0.8784 | 44400 | 0.006 | | 0.8804 | 44500 | 0.006 | | 0.8824 | 44600 | 0.0059 | | 0.8844 | 44700 | 0.0062 | | 0.8863 | 44800 | 0.006 | | 0.8883 | 44900 | 0.006 | | 0.8903 | 45000 | 0.0058 | | 0.8923 | 45100 | 0.006 | | 0.8942 | 45200 | 0.0061 | | 0.8962 | 45300 | 0.006 | | 0.8982 | 45400 | 0.0059 | | 0.9002 | 45500 | 0.0059 | | 0.9022 | 45600 | 0.006 | | 0.9041 | 45700 | 0.0062 | | 0.9061 | 45800 | 0.0056 | | 0.9081 | 45900 | 0.0057 | | 0.9101 | 46000 | 0.006 | | 0.9120 | 46100 | 0.0059 | | 0.9140 | 46200 | 0.006 | | 0.9160 | 46300 | 0.0059 | | 0.9180 | 46400 | 0.0062 | | 0.9200 | 46500 | 0.0059 | | 0.9219 | 46600 | 0.0059 | | 0.9239 | 46700 | 0.006 | | 0.9259 | 46800 | 0.0059 | | 0.9279 | 46900 | 0.0058 | | 0.9299 | 47000 | 0.0057 | | 0.9318 | 47100 | 0.0058 | | 0.9338 | 47200 | 0.0058 | | 0.9358 | 47300 | 0.0059 | | 0.9378 | 47400 | 0.0059 | | 0.9397 | 47500 | 0.0058 | | 0.9417 | 47600 | 0.006 | | 0.9437 | 47700 | 0.0058 | | 0.9457 | 47800 | 0.006 | | 0.9477 | 47900 | 0.0059 | | 0.9496 | 48000 | 0.0058 | | 0.9516 | 48100 | 0.0057 | | 0.9536 | 48200 | 0.006 | | 0.9556 | 48300 | 0.0057 | | 0.9576 | 48400 | 0.006 | | 0.9595 | 48500 | 0.0058 | | 0.9615 | 48600 | 0.0058 | | 0.9635 | 48700 | 0.0058 | | 0.9655 | 48800 | 0.0057 | | 0.9674 | 48900 | 0.0058 | | 0.9694 | 49000 | 0.006 | | 0.9714 | 49100 | 0.0055 | | 0.9734 | 49200 | 0.0058 | | 0.9754 | 49300 | 0.0059 | | 0.9773 | 49400 | 0.0057 | | 0.9793 | 49500 | 0.0055 | | 0.9813 | 49600 | 0.0059 | | 0.9833 | 49700 | 0.0058 | | 0.9853 | 49800 | 0.0059 | | 0.9872 | 49900 | 0.0058 | | 0.9892 | 50000 | 0.0056 | | 0.9912 | 50100 | 0.0058 | | 0.9932 | 50200 | 0.0058 | | 0.9951 | 50300 | 0.0059 | | 0.9971 | 50400 | 0.0059 | | 0.9991 | 50500 | 0.006 | </details> ### Framework Versions - Python: 3.11.9 - Sentence Transformers: 3.3.0 - PyLate: 1.1.4 - Transformers: 4.48.0.dev0 - PyTorch: 2.4.0 - Accelerate: 1.2.1 - Datasets: 2.21.0 - Tokenizers: 0.21.0 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084" } ``` #### PyLate ```bibtex @misc{PyLate, title={PyLate: Flexible Training and Retrieval for Late Interaction Models}, author={Chaffin, Antoine and Sourty, Raphaël}, url={https://github.com/lightonai/pylate}, year={2024} } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
[ "SCIFACT" ]
mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF
mradermacher
null
[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B", "base_model:quantized:Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B", "endpoints_compatible", "region:us", "conversational" ]
2024-12-25T00:44:42Z
2024-12-26T15:17:37+00:00
32
0
--- base_model: Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B language: - en library_name: transformers tags: - mergekit - merge quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF/resolve/main/Llama-3-MopeyMule-Blackroot-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
[ "CAS" ]
billatsectorflow/stella_en_1.5B_v5
billatsectorflow
sentence-similarity
[ "sentence-transformers", "pytorch", "safetensors", "qwen2", "text-generation", "mteb", "transformers", "sentence-similarity", "custom_code", "arxiv:2205.13147", "license:mit", "model-index", "autotrain_compatible", "text-generation-inference", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
2025-01-22T11:17:38Z
2025-01-22T11:25:36+00:00
32
2
--- license: mit tags: - mteb - sentence-transformers - transformers - sentence-similarity model-index: - name: stella_en_1.5B_v5 results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 92.86567164179104 - type: ap value: 72.13503907102613 - type: ap_weighted value: 72.13503907102613 - type: f1 value: 89.5586886376355 - type: f1_weighted value: 93.13621183004571 - type: main_score value: 92.86567164179104 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification type: mteb/amazon_polarity config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 97.16485 - type: ap value: 96.05546315415225 - type: ap_weighted value: 96.05546315415225 - type: f1 value: 97.16351087403213 - type: f1_weighted value: 97.16351087403213 - type: main_score value: 97.16485 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 59.358 - type: f1 value: 59.0264615883114 - type: f1_weighted value: 59.0264615883114 - type: main_score value: 59.358 - task: type: Retrieval dataset: name: MTEB ArguAna type: mteb/arguana config: default split: test revision: c22ab2a51041ffd869aaddef7af8d8215647e41a metrics: - type: main_score value: 65.269 - type: map_at_1 value: 41.607 - type: map_at_10 value: 57.104 - type: map_at_100 value: 57.621 - type: map_at_1000 value: 57.621 - type: map_at_20 value: 57.533 - type: map_at_3 value: 52.891999999999996 - type: map_at_5 value: 55.371 - type: mrr_at_1 value: 42.318634423897585 - type: mrr_at_10 value: 57.353970511865406 - type: mrr_at_100 value: 57.88398078476526 - type: mrr_at_1000 value: 57.88467807648422 - type: mrr_at_20 value: 57.796730533206166 - type: mrr_at_3 value: 53.200568990042775 - type: mrr_at_5 value: 55.6330014224753 - type: nauc_map_at_1000_diff1 value: 24.54414600428287 - type: nauc_map_at_1000_max value: -8.389738078358459 - type: nauc_map_at_1000_std value: -18.188787645801366 - type: nauc_map_at_100_diff1 value: 24.543138576462308 - type: nauc_map_at_100_max value: -8.390896839752044 - type: nauc_map_at_100_std value: -18.192549240185247 - type: nauc_map_at_10_diff1 value: 24.219607088995822 - type: nauc_map_at_10_max value: -8.245734391254308 - type: nauc_map_at_10_std value: -18.229706566466447 - type: nauc_map_at_1_diff1 value: 29.325201664812788 - type: nauc_map_at_1_max value: -11.742800494823971 - type: nauc_map_at_1_std value: -18.610215769702528 - type: nauc_map_at_20_diff1 value: 24.471097562798803 - type: nauc_map_at_20_max value: -8.318035874000799 - type: nauc_map_at_20_std value: -18.171541096773108 - type: nauc_map_at_3_diff1 value: 24.275846107642824 - type: nauc_map_at_3_max value: -8.212242049581894 - type: nauc_map_at_3_std value: -17.920379368937496 - type: nauc_map_at_5_diff1 value: 23.873692493209255 - type: nauc_map_at_5_max value: -8.110347163828767 - type: nauc_map_at_5_std value: -18.20863325596931 - type: nauc_mrr_at_1000_diff1 value: 22.656410956419975 - type: nauc_mrr_at_1000_max value: -8.924888102233243 - type: nauc_mrr_at_1000_std value: -18.103674384502526 - type: nauc_mrr_at_100_diff1 value: 22.655448817140968 - type: nauc_mrr_at_100_max value: -8.926034318499038 - type: nauc_mrr_at_100_std value: -18.10743930104164 - type: nauc_mrr_at_10_diff1 value: 22.297536272996872 - type: nauc_mrr_at_10_max value: -8.836407556658274 - type: nauc_mrr_at_10_std value: -18.1598393044477 - type: nauc_mrr_at_1_diff1 value: 27.419572424489708 - type: nauc_mrr_at_1_max value: -11.42241314820691 - type: nauc_mrr_at_1_std value: -18.54893865856313 - type: nauc_mrr_at_20_diff1 value: 22.590227214657418 - type: nauc_mrr_at_20_max value: -8.849986456376993 - type: nauc_mrr_at_20_std value: -18.0862391777352 - type: nauc_mrr_at_3_diff1 value: 22.415270167774988 - type: nauc_mrr_at_3_max value: -8.692871854156435 - type: nauc_mrr_at_3_std value: -17.6740102891955 - type: nauc_mrr_at_5_diff1 value: 21.96284578521464 - type: nauc_mrr_at_5_max value: -8.757031535546025 - type: nauc_mrr_at_5_std value: -18.210766964081294 - type: nauc_ndcg_at_1000_diff1 value: 23.939400161569115 - type: nauc_ndcg_at_1000_max value: -7.866999120512983 - type: nauc_ndcg_at_1000_std value: -17.981457019643617 - type: nauc_ndcg_at_100_diff1 value: 23.920033349619317 - type: nauc_ndcg_at_100_max value: -7.889849409678031 - type: nauc_ndcg_at_100_std value: -18.054931990360537 - type: nauc_ndcg_at_10_diff1 value: 22.543020461303534 - type: nauc_ndcg_at_10_max value: -7.072111788010867 - type: nauc_ndcg_at_10_std value: -18.26397604573537 - type: nauc_ndcg_at_1_diff1 value: 29.325201664812788 - type: nauc_ndcg_at_1_max value: -11.742800494823971 - type: nauc_ndcg_at_1_std value: -18.610215769702528 - type: nauc_ndcg_at_20_diff1 value: 23.551587021207972 - type: nauc_ndcg_at_20_max value: -7.298056222649139 - type: nauc_ndcg_at_20_std value: -18.056004880930608 - type: nauc_ndcg_at_3_diff1 value: 22.669089506345273 - type: nauc_ndcg_at_3_max value: -7.278024373570137 - type: nauc_ndcg_at_3_std value: -17.816657759914193 - type: nauc_ndcg_at_5_diff1 value: 21.72619728226575 - type: nauc_ndcg_at_5_max value: -6.959741647471228 - type: nauc_ndcg_at_5_std value: -18.35173705190235 - type: nauc_precision_at_1000_diff1 value: 5.0388241058076995 - type: nauc_precision_at_1000_max value: 34.439879624882145 - type: nauc_precision_at_1000_std value: 77.22610895194498 - type: nauc_precision_at_100_diff1 value: 1.340670767252794 - type: nauc_precision_at_100_max value: 19.30870025961241 - type: nauc_precision_at_100_std value: 35.37688289157788 - type: nauc_precision_at_10_diff1 value: 7.734227153124332 - type: nauc_precision_at_10_max value: 4.202399088422237 - type: nauc_precision_at_10_std value: -18.383890254046698 - type: nauc_precision_at_1_diff1 value: 29.325201664812788 - type: nauc_precision_at_1_max value: -11.742800494823971 - type: nauc_precision_at_1_std value: -18.610215769702528 - type: nauc_precision_at_20_diff1 value: 9.48070999361637 - type: nauc_precision_at_20_max value: 19.056709637253025 - type: nauc_precision_at_20_std value: -13.266821166159485 - type: nauc_precision_at_3_diff1 value: 17.245260303409747 - type: nauc_precision_at_3_max value: -4.202455033452335 - type: nauc_precision_at_3_std value: -17.514264039955332 - type: nauc_precision_at_5_diff1 value: 12.074628162049974 - type: nauc_precision_at_5_max value: -1.9145501461107832 - type: nauc_precision_at_5_std value: -19.162525528916344 - type: nauc_recall_at_1000_diff1 value: 5.038824105805915 - type: nauc_recall_at_1000_max value: 34.43987962487738 - type: nauc_recall_at_1000_std value: 77.22610895193765 - type: nauc_recall_at_100_diff1 value: 1.3406707672497025 - type: nauc_recall_at_100_max value: 19.30870025960776 - type: nauc_recall_at_100_std value: 35.37688289157515 - type: nauc_recall_at_10_diff1 value: 7.734227153124366 - type: nauc_recall_at_10_max value: 4.202399088421976 - type: nauc_recall_at_10_std value: -18.38389025404673 - type: nauc_recall_at_1_diff1 value: 29.325201664812788 - type: nauc_recall_at_1_max value: -11.742800494823971 - type: nauc_recall_at_1_std value: -18.610215769702528 - type: nauc_recall_at_20_diff1 value: 9.480709993616845 - type: nauc_recall_at_20_max value: 19.05670963725301 - type: nauc_recall_at_20_std value: -13.266821166158651 - type: nauc_recall_at_3_diff1 value: 17.24526030340978 - type: nauc_recall_at_3_max value: -4.202455033452323 - type: nauc_recall_at_3_std value: -17.51426403995538 - type: nauc_recall_at_5_diff1 value: 12.074628162049992 - type: nauc_recall_at_5_max value: -1.914550146110865 - type: nauc_recall_at_5_std value: -19.162525528916362 - type: ndcg_at_1 value: 41.607 - type: ndcg_at_10 value: 65.269 - type: ndcg_at_100 value: 67.289 - type: ndcg_at_1000 value: 67.29899999999999 - type: ndcg_at_20 value: 66.76299999999999 - type: ndcg_at_3 value: 56.604 - type: ndcg_at_5 value: 61.07900000000001 - type: precision_at_1 value: 41.607 - type: precision_at_10 value: 9.118 - type: precision_at_100 value: 0.996 - type: precision_at_1000 value: 0.1 - type: precision_at_20 value: 4.8469999999999995 - type: precision_at_3 value: 22.451 - type: precision_at_5 value: 15.647 - type: recall_at_1 value: 41.607 - type: recall_at_10 value: 91.181 - type: recall_at_100 value: 99.57300000000001 - type: recall_at_1000 value: 99.644 - type: recall_at_20 value: 96.942 - type: recall_at_3 value: 67.354 - type: recall_at_5 value: 78.236 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P type: mteb/arxiv-clustering-p2p config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: main_score value: 55.437138353189994 - type: v_measure value: 55.437138353189994 - type: v_measure_std value: 14.718556601335491 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S type: mteb/arxiv-clustering-s2s config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: main_score value: 50.65858459544658 - type: v_measure value: 50.65858459544658 - type: v_measure_std value: 14.887033747525146 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions type: mteb/askubuntudupquestions-reranking config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: main_score value: 67.32597152838535 - type: map value: 67.32597152838535 - type: mrr value: 78.98683111286988 - type: nAUC_map_diff1 value: 16.8624639710487 - type: nAUC_map_max value: 24.91996491142433 - type: nAUC_map_std value: 17.91865808793225 - type: nAUC_mrr_diff1 value: 25.03766425631947 - type: nAUC_mrr_max value: 41.64561939958336 - type: nAUC_mrr_std value: 23.179909345891968 - task: type: STS dataset: name: MTEB BIOSSES type: mteb/biosses-sts config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cosine_pearson value: 85.790820496042 - type: cosine_spearman value: 83.10731534330517 - type: euclidean_pearson value: 84.61741304343133 - type: euclidean_spearman value: 83.17297949010973 - type: main_score value: 83.10731534330517 - type: manhattan_pearson value: 85.2137696526676 - type: manhattan_spearman value: 84.39168195786738 - type: pearson value: 85.790820496042 - type: spearman value: 83.10731534330517 - task: type: Classification dataset: name: MTEB Banking77Classification type: mteb/banking77 config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 89.78896103896105 - type: f1 value: 89.76107366333488 - type: f1_weighted value: 89.76107366333488 - type: main_score value: 89.78896103896105 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P type: mteb/biorxiv-clustering-p2p config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: main_score value: 50.68092296236376 - type: v_measure value: 50.68092296236376 - type: v_measure_std value: 0.7832640983085436 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S type: mteb/biorxiv-clustering-s2s config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: main_score value: 46.86629236732983 - type: v_measure value: 46.86629236732983 - type: v_measure_std value: 0.8784322236350974 - task: type: Retrieval dataset: name: MTEB CQADupstackRetrieval type: mteb/cqadupstack config: default split: test revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: main_score value: 47.74883333333334 - type: map_at_1 value: 30.179249999999996 - type: map_at_10 value: 41.60824999999999 - type: map_at_100 value: 42.94008333333332 - type: map_at_1000 value: 43.04666666666667 - type: map_at_20 value: 42.36833333333334 - type: map_at_3 value: 38.23491666666666 - type: map_at_5 value: 40.10183333333333 - type: mrr_at_1 value: 36.47676085808166 - type: mrr_at_10 value: 46.300991916437155 - type: mrr_at_100 value: 47.12155753713262 - type: mrr_at_1000 value: 47.168033610799945 - type: mrr_at_20 value: 46.80405724560391 - type: mrr_at_3 value: 43.77000352801797 - type: mrr_at_5 value: 45.22295361704542 - type: nauc_map_at_1000_diff1 value: 46.953671666941524 - type: nauc_map_at_1000_max value: 32.260396316089675 - type: nauc_map_at_1000_std value: 0.6657766120094878 - type: nauc_map_at_100_diff1 value: 46.94717463394555 - type: nauc_map_at_100_max value: 32.25088350678177 - type: nauc_map_at_100_std value: 0.6257017014549283 - type: nauc_map_at_10_diff1 value: 46.974678429336464 - type: nauc_map_at_10_max value: 31.862230807295504 - type: nauc_map_at_10_std value: -0.14758828549579284 - type: nauc_map_at_1_diff1 value: 52.48913346466124 - type: nauc_map_at_1_max value: 29.874374024967725 - type: nauc_map_at_1_std value: -2.433547569836134 - type: nauc_map_at_20_diff1 value: 46.96088684217651 - type: nauc_map_at_20_max value: 32.08954208613205 - type: nauc_map_at_20_std value: 0.25946321113436527 - type: nauc_map_at_3_diff1 value: 47.703230121518345 - type: nauc_map_at_3_max value: 30.977880095983107 - type: nauc_map_at_3_std value: -1.342777563991804 - type: nauc_map_at_5_diff1 value: 47.1615010199957 - type: nauc_map_at_5_max value: 31.420885812683284 - type: nauc_map_at_5_std value: -0.8789297099444306 - type: nauc_mrr_at_1000_diff1 value: 46.69178645962615 - type: nauc_mrr_at_1000_max value: 34.392807413340655 - type: nauc_mrr_at_1000_std value: 1.6155464863667934 - type: nauc_mrr_at_100_diff1 value: 46.67417236349189 - type: nauc_mrr_at_100_max value: 34.384607045512624 - type: nauc_mrr_at_100_std value: 1.6259917384109652 - type: nauc_mrr_at_10_diff1 value: 46.60497560446239 - type: nauc_mrr_at_10_max value: 34.32918897817958 - type: nauc_mrr_at_10_std value: 1.39387793769014 - type: nauc_mrr_at_1_diff1 value: 51.61608573254137 - type: nauc_mrr_at_1_max value: 35.18105023234596 - type: nauc_mrr_at_1_std value: 0.17943702145478177 - type: nauc_mrr_at_20_diff1 value: 46.635943069860254 - type: nauc_mrr_at_20_max value: 34.37050973118794 - type: nauc_mrr_at_20_std value: 1.5346464678860607 - type: nauc_mrr_at_3_diff1 value: 47.154389369038334 - type: nauc_mrr_at_3_max value: 34.41036411855465 - type: nauc_mrr_at_3_std value: 0.924551812357872 - type: nauc_mrr_at_5_diff1 value: 46.6690101691763 - type: nauc_mrr_at_5_max value: 34.29740388138466 - type: nauc_mrr_at_5_std value: 1.0567184149139792 - type: nauc_ndcg_at_1000_diff1 value: 45.375448289173264 - type: nauc_ndcg_at_1000_max value: 33.47957083714482 - type: nauc_ndcg_at_1000_std value: 3.192251100225568 - type: nauc_ndcg_at_100_diff1 value: 44.93601014699499 - type: nauc_ndcg_at_100_max value: 33.21249888295249 - type: nauc_ndcg_at_100_std value: 3.609842852934217 - type: nauc_ndcg_at_10_diff1 value: 44.87893284011915 - type: nauc_ndcg_at_10_max value: 32.384885249478515 - type: nauc_ndcg_at_10_std value: 1.454493065035396 - type: nauc_ndcg_at_1_diff1 value: 51.61608573254137 - type: nauc_ndcg_at_1_max value: 35.18105023234596 - type: nauc_ndcg_at_1_std value: 0.17943702145478177 - type: nauc_ndcg_at_20_diff1 value: 44.867752179050605 - type: nauc_ndcg_at_20_max value: 32.689535921840196 - type: nauc_ndcg_at_20_std value: 2.337765158573901 - type: nauc_ndcg_at_3_diff1 value: 45.87485821381341 - type: nauc_ndcg_at_3_max value: 32.33282450558947 - type: nauc_ndcg_at_3_std value: 0.0681643829273283 - type: nauc_ndcg_at_5_diff1 value: 45.202902131892394 - type: nauc_ndcg_at_5_max value: 32.1026971523917 - type: nauc_ndcg_at_5_std value: 0.3565572833774486 - type: nauc_precision_at_1000_diff1 value: -8.935267931198956 - type: nauc_precision_at_1000_max value: 6.464981960169269 - type: nauc_precision_at_1000_std value: 10.662786182234633 - type: nauc_precision_at_100_diff1 value: -1.64091517847155 - type: nauc_precision_at_100_max value: 15.175617871025024 - type: nauc_precision_at_100_std value: 16.924256989248075 - type: nauc_precision_at_10_diff1 value: 15.676651966277047 - type: nauc_precision_at_10_max value: 26.243734188847117 - type: nauc_precision_at_10_std value: 10.601741034956333 - type: nauc_precision_at_1_diff1 value: 51.61608573254137 - type: nauc_precision_at_1_max value: 35.18105023234596 - type: nauc_precision_at_1_std value: 0.17943702145478177 - type: nauc_precision_at_20_diff1 value: 9.447267260198654 - type: nauc_precision_at_20_max value: 23.024130858142723 - type: nauc_precision_at_20_std value: 13.739145648899603 - type: nauc_precision_at_3_diff1 value: 30.11583572134629 - type: nauc_precision_at_3_max value: 31.37321080069495 - type: nauc_precision_at_3_std value: 4.705512374126024 - type: nauc_precision_at_5_diff1 value: 23.192015335996093 - type: nauc_precision_at_5_max value: 29.415746835998764 - type: nauc_precision_at_5_std value: 6.843498772798558 - type: nauc_recall_at_1000_diff1 value: 25.36573313426033 - type: nauc_recall_at_1000_max value: 43.06672256524168 - type: nauc_recall_at_1000_std value: 47.93664853815292 - type: nauc_recall_at_100_diff1 value: 31.222880916617406 - type: nauc_recall_at_100_max value: 31.761159904172658 - type: nauc_recall_at_100_std value: 23.034218976635877 - type: nauc_recall_at_10_diff1 value: 36.23439028915225 - type: nauc_recall_at_10_max value: 28.473458977606438 - type: nauc_recall_at_10_std value: 3.7797969934159 - type: nauc_recall_at_1_diff1 value: 52.48913346466124 - type: nauc_recall_at_1_max value: 29.874374024967725 - type: nauc_recall_at_1_std value: -2.433547569836134 - type: nauc_recall_at_20_diff1 value: 34.678676952584766 - type: nauc_recall_at_20_max value: 29.04638392522168 - type: nauc_recall_at_20_std value: 8.148894982082549 - type: nauc_recall_at_3_diff1 value: 41.31029996231311 - type: nauc_recall_at_3_max value: 28.44199443414157 - type: nauc_recall_at_3_std value: -0.747324057600377 - type: nauc_recall_at_5_diff1 value: 38.535873899920674 - type: nauc_recall_at_5_max value: 27.942667805948375 - type: nauc_recall_at_5_std value: 0.30652206930973686 - type: ndcg_at_1 value: 36.47675 - type: ndcg_at_10 value: 47.74883333333334 - type: ndcg_at_100 value: 52.902416666666674 - type: ndcg_at_1000 value: 54.69116666666667 - type: ndcg_at_20 value: 49.89758333333333 - type: ndcg_at_3 value: 42.462250000000004 - type: ndcg_at_5 value: 44.91841666666667 - type: precision_at_1 value: 36.47675 - type: precision_at_10 value: 8.582416666666665 - type: precision_at_100 value: 1.31475 - type: precision_at_1000 value: 0.16458333333333333 - type: precision_at_20 value: 5.021833333333333 - type: precision_at_3 value: 20.004499999999997 - type: precision_at_5 value: 14.178666666666665 - type: recall_at_1 value: 30.179249999999996 - type: recall_at_10 value: 60.950166666666675 - type: recall_at_100 value: 83.19025 - type: recall_at_1000 value: 95.27774999999998 - type: recall_at_20 value: 68.80175 - type: recall_at_3 value: 46.01841666666666 - type: recall_at_5 value: 52.482416666666666 - task: type: Retrieval dataset: name: MTEB ClimateFEVER type: mteb/climate-fever config: default split: test revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 metrics: - type: main_score value: 46.113 - type: map_at_1 value: 20.122999999999998 - type: map_at_10 value: 35.474 - type: map_at_100 value: 37.592 - type: map_at_1000 value: 37.773 - type: map_at_20 value: 36.637 - type: map_at_3 value: 29.731 - type: map_at_5 value: 32.964 - type: mrr_at_1 value: 46.71009771986971 - type: mrr_at_10 value: 58.855669303552105 - type: mrr_at_100 value: 59.389249674038425 - type: mrr_at_1000 value: 59.408448104362364 - type: mrr_at_20 value: 59.23881203149016 - type: mrr_at_3 value: 56.18892508143328 - type: mrr_at_5 value: 57.85342019543985 - type: nauc_map_at_1000_diff1 value: 27.047031037721958 - type: nauc_map_at_1000_max value: 43.25240279148033 - type: nauc_map_at_1000_std value: 20.795849418696037 - type: nauc_map_at_100_diff1 value: 27.044739015116452 - type: nauc_map_at_100_max value: 43.24042159787812 - type: nauc_map_at_100_std value: 20.799952124137683 - type: nauc_map_at_10_diff1 value: 27.372696854670338 - type: nauc_map_at_10_max value: 43.054456574721684 - type: nauc_map_at_10_std value: 19.537162110136645 - type: nauc_map_at_1_diff1 value: 43.65424623953092 - type: nauc_map_at_1_max value: 45.17986509998762 - type: nauc_map_at_1_std value: 8.497107052335414 - type: nauc_map_at_20_diff1 value: 27.224535846566074 - type: nauc_map_at_20_max value: 43.12222854561229 - type: nauc_map_at_20_std value: 20.29982972202669 - type: nauc_map_at_3_diff1 value: 30.87847002319001 - type: nauc_map_at_3_max value: 42.890027891707575 - type: nauc_map_at_3_std value: 13.857451947580929 - type: nauc_map_at_5_diff1 value: 27.966867093591542 - type: nauc_map_at_5_max value: 42.35826637592201 - type: nauc_map_at_5_std value: 16.993102524058624 - type: nauc_mrr_at_1000_diff1 value: 30.191544077608164 - type: nauc_mrr_at_1000_max value: 44.959438920351644 - type: nauc_mrr_at_1000_std value: 24.065801376465114 - type: nauc_mrr_at_100_diff1 value: 30.170368115494 - type: nauc_mrr_at_100_max value: 44.955868115761156 - type: nauc_mrr_at_100_std value: 24.093510767847707 - type: nauc_mrr_at_10_diff1 value: 30.128430637520175 - type: nauc_mrr_at_10_max value: 44.97689261350708 - type: nauc_mrr_at_10_std value: 24.037049561818897 - type: nauc_mrr_at_1_diff1 value: 35.323351939108214 - type: nauc_mrr_at_1_max value: 43.85026244855636 - type: nauc_mrr_at_1_std value: 17.040662141218974 - type: nauc_mrr_at_20_diff1 value: 30.192006556160443 - type: nauc_mrr_at_20_max value: 45.02814530774032 - type: nauc_mrr_at_20_std value: 24.20885865448696 - type: nauc_mrr_at_3_diff1 value: 29.88250163424518 - type: nauc_mrr_at_3_max value: 44.25768944883186 - type: nauc_mrr_at_3_std value: 22.804183393364198 - type: nauc_mrr_at_5_diff1 value: 30.269824490420767 - type: nauc_mrr_at_5_max value: 44.97443265796657 - type: nauc_mrr_at_5_std value: 23.894159916141177 - type: nauc_ndcg_at_1000_diff1 value: 24.533764005407356 - type: nauc_ndcg_at_1000_max value: 44.50902713386608 - type: nauc_ndcg_at_1000_std value: 27.589506980238404 - type: nauc_ndcg_at_100_diff1 value: 24.209785073940353 - type: nauc_ndcg_at_100_max value: 44.18257063893669 - type: nauc_ndcg_at_100_std value: 27.963150866401943 - type: nauc_ndcg_at_10_diff1 value: 25.168069201989486 - type: nauc_ndcg_at_10_max value: 43.84940910683214 - type: nauc_ndcg_at_10_std value: 24.810707270956435 - type: nauc_ndcg_at_1_diff1 value: 35.323351939108214 - type: nauc_ndcg_at_1_max value: 43.85026244855636 - type: nauc_ndcg_at_1_std value: 17.040662141218974 - type: nauc_ndcg_at_20_diff1 value: 24.829924800466834 - type: nauc_ndcg_at_20_max value: 43.738574327059716 - type: nauc_ndcg_at_20_std value: 26.252370278684072 - type: nauc_ndcg_at_3_diff1 value: 27.321943393906274 - type: nauc_ndcg_at_3_max value: 42.16584786993447 - type: nauc_ndcg_at_3_std value: 18.24775079455969 - type: nauc_ndcg_at_5_diff1 value: 26.043785418347998 - type: nauc_ndcg_at_5_max value: 42.874593895388344 - type: nauc_ndcg_at_5_std value: 21.294004555506117 - type: nauc_precision_at_1000_diff1 value: -22.073027615308582 - type: nauc_precision_at_1000_max value: -6.549723766317357 - type: nauc_precision_at_1000_std value: 18.301749191241306 - type: nauc_precision_at_100_diff1 value: -15.654286887593619 - type: nauc_precision_at_100_max value: 6.401516251421999 - type: nauc_precision_at_100_std value: 29.170680324929805 - type: nauc_precision_at_10_diff1 value: -4.362381972892247 - type: nauc_precision_at_10_max value: 22.10943515872447 - type: nauc_precision_at_10_std value: 31.869699459530022 - type: nauc_precision_at_1_diff1 value: 35.323351939108214 - type: nauc_precision_at_1_max value: 43.85026244855636 - type: nauc_precision_at_1_std value: 17.040662141218974 - type: nauc_precision_at_20_diff1 value: -7.50749661117875 - type: nauc_precision_at_20_max value: 16.80584016023257 - type: nauc_precision_at_20_std value: 31.976755897112437 - type: nauc_precision_at_3_diff1 value: 7.402667538773083 - type: nauc_precision_at_3_max value: 31.2088401330676 - type: nauc_precision_at_3_std value: 24.287905698405662 - type: nauc_precision_at_5_diff1 value: 0.7479172565343901 - type: nauc_precision_at_5_max value: 26.28427734237825 - type: nauc_precision_at_5_std value: 28.246947120310317 - type: nauc_recall_at_1000_diff1 value: 2.4778431086370496 - type: nauc_recall_at_1000_max value: 40.2231995797509 - type: nauc_recall_at_1000_std value: 52.62124052183862 - type: nauc_recall_at_100_diff1 value: 8.960962419741463 - type: nauc_recall_at_100_max value: 35.81132850291491 - type: nauc_recall_at_100_std value: 40.020903251786166 - type: nauc_recall_at_10_diff1 value: 15.603400751376636 - type: nauc_recall_at_10_max value: 37.570127529136485 - type: nauc_recall_at_10_std value: 28.07128410238545 - type: nauc_recall_at_1_diff1 value: 43.65424623953092 - type: nauc_recall_at_1_max value: 45.17986509998762 - type: nauc_recall_at_1_std value: 8.497107052335414 - type: nauc_recall_at_20_diff1 value: 13.844820282832346 - type: nauc_recall_at_20_max value: 36.0106148516309 - type: nauc_recall_at_20_std value: 31.453103910565254 - type: nauc_recall_at_3_diff1 value: 24.359328154117748 - type: nauc_recall_at_3_max value: 39.93774251377568 - type: nauc_recall_at_3_std value: 16.214921517509648 - type: nauc_recall_at_5_diff1 value: 18.75788451360292 - type: nauc_recall_at_5_max value: 38.177646107055516 - type: nauc_recall_at_5_std value: 22.17196825834675 - type: ndcg_at_1 value: 46.71 - type: ndcg_at_10 value: 46.113 - type: ndcg_at_100 value: 53.035 - type: ndcg_at_1000 value: 55.724 - type: ndcg_at_20 value: 48.929 - type: ndcg_at_3 value: 39.501999999999995 - type: ndcg_at_5 value: 41.792 - type: precision_at_1 value: 46.71 - type: precision_at_10 value: 14.274000000000001 - type: precision_at_100 value: 2.1870000000000003 - type: precision_at_1000 value: 0.269 - type: precision_at_20 value: 8.375 - type: precision_at_3 value: 29.881 - type: precision_at_5 value: 22.697 - type: recall_at_1 value: 20.122999999999998 - type: recall_at_10 value: 52.22 - type: recall_at_100 value: 75.388 - type: recall_at_1000 value: 89.938 - type: recall_at_20 value: 60.077000000000005 - type: recall_at_3 value: 35.150999999999996 - type: recall_at_5 value: 42.748000000000005 - task: type: Retrieval dataset: name: MTEB DBPedia type: mteb/dbpedia config: default split: test revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 metrics: - type: main_score value: 52.276999999999994 - type: map_at_1 value: 9.949 - type: map_at_10 value: 24.891 - type: map_at_100 value: 37.111 - type: map_at_1000 value: 39.266 - type: map_at_20 value: 29.685 - type: map_at_3 value: 16.586000000000002 - type: map_at_5 value: 19.982 - type: mrr_at_1 value: 76.25 - type: mrr_at_10 value: 82.4518849206349 - type: mrr_at_100 value: 82.70302194564499 - type: mrr_at_1000 value: 82.70909729942254 - type: mrr_at_20 value: 82.60492765962964 - type: mrr_at_3 value: 81.33333333333331 - type: mrr_at_5 value: 82.14583333333331 - type: nauc_map_at_1000_diff1 value: 21.427201262456556 - type: nauc_map_at_1000_max value: 35.357361590816076 - type: nauc_map_at_1000_std value: 24.785419223353717 - type: nauc_map_at_100_diff1 value: 22.82358692021537 - type: nauc_map_at_100_max value: 35.07399692072945 - type: nauc_map_at_100_std value: 22.679878828987025 - type: nauc_map_at_10_diff1 value: 26.491769223479643 - type: nauc_map_at_10_max value: 20.78079385443902 - type: nauc_map_at_10_std value: -4.910406292079661 - type: nauc_map_at_1_diff1 value: 35.20851030208876 - type: nauc_map_at_1_max value: 5.783003346365858 - type: nauc_map_at_1_std value: -21.11679133835354 - type: nauc_map_at_20_diff1 value: 24.80097499300491 - type: nauc_map_at_20_max value: 26.807021360774975 - type: nauc_map_at_20_std value: 4.793103995429955 - type: nauc_map_at_3_diff1 value: 29.238193458890173 - type: nauc_map_at_3_max value: 10.300839972189456 - type: nauc_map_at_3_std value: -17.889666731981592 - type: nauc_map_at_5_diff1 value: 28.773624870573926 - type: nauc_map_at_5_max value: 14.951435645422887 - type: nauc_map_at_5_std value: -13.319697827173565 - type: nauc_mrr_at_1000_diff1 value: 55.232544856708785 - type: nauc_mrr_at_1000_max value: 64.73225637682637 - type: nauc_mrr_at_1000_std value: 37.57480399594188 - type: nauc_mrr_at_100_diff1 value: 55.219251601773735 - type: nauc_mrr_at_100_max value: 64.73305063663611 - type: nauc_mrr_at_100_std value: 37.56458562909293 - type: nauc_mrr_at_10_diff1 value: 55.123463838253464 - type: nauc_mrr_at_10_max value: 64.91914041040233 - type: nauc_mrr_at_10_std value: 37.76482503851598 - type: nauc_mrr_at_1_diff1 value: 56.45461238513347 - type: nauc_mrr_at_1_max value: 63.11782510293676 - type: nauc_mrr_at_1_std value: 33.592561284868985 - type: nauc_mrr_at_20_diff1 value: 55.15401961460458 - type: nauc_mrr_at_20_max value: 64.77145835613156 - type: nauc_mrr_at_20_std value: 37.471561418305804 - type: nauc_mrr_at_3_diff1 value: 54.64387438697658 - type: nauc_mrr_at_3_max value: 64.27618995019164 - type: nauc_mrr_at_3_std value: 39.391637295269014 - type: nauc_mrr_at_5_diff1 value: 55.08702591239485 - type: nauc_mrr_at_5_max value: 64.6071475650635 - type: nauc_mrr_at_5_std value: 37.97185134269896 - type: nauc_ndcg_at_1000_diff1 value: 31.696698876400387 - type: nauc_ndcg_at_1000_max value: 52.12183760001191 - type: nauc_ndcg_at_1000_std value: 40.197596211778716 - type: nauc_ndcg_at_100_diff1 value: 33.253120193433666 - type: nauc_ndcg_at_100_max value: 49.47167758554746 - type: nauc_ndcg_at_100_std value: 32.643833139756204 - type: nauc_ndcg_at_10_diff1 value: 27.065541392580013 - type: nauc_ndcg_at_10_max value: 45.83504281289289 - type: nauc_ndcg_at_10_std value: 27.11739500732328 - type: nauc_ndcg_at_1_diff1 value: 49.42808250022517 - type: nauc_ndcg_at_1_max value: 53.502615048520354 - type: nauc_ndcg_at_1_std value: 27.17555908836708 - type: nauc_ndcg_at_20_diff1 value: 29.374791382330308 - type: nauc_ndcg_at_20_max value: 43.91246842479055 - type: nauc_ndcg_at_20_std value: 23.419410620550316 - type: nauc_ndcg_at_3_diff1 value: 26.71550354496204 - type: nauc_ndcg_at_3_max value: 43.9641457892003 - type: nauc_ndcg_at_3_std value: 27.320024167947686 - type: nauc_ndcg_at_5_diff1 value: 27.020654974589487 - type: nauc_ndcg_at_5_max value: 46.130417266030584 - type: nauc_ndcg_at_5_std value: 28.392009019010068 - type: nauc_precision_at_1000_diff1 value: -21.47455482181002 - type: nauc_precision_at_1000_max value: -9.721907229236024 - type: nauc_precision_at_1000_std value: -1.061132062651487 - type: nauc_precision_at_100_diff1 value: -12.35759246101943 - type: nauc_precision_at_100_max value: 15.509512444892168 - type: nauc_precision_at_100_std value: 36.21183578592014 - type: nauc_precision_at_10_diff1 value: -6.136998947343125 - type: nauc_precision_at_10_max value: 32.30037906748288 - type: nauc_precision_at_10_std value: 41.4500302476981 - type: nauc_precision_at_1_diff1 value: 56.45461238513347 - type: nauc_precision_at_1_max value: 63.11782510293676 - type: nauc_precision_at_1_std value: 33.592561284868985 - type: nauc_precision_at_20_diff1 value: -7.335890123683174 - type: nauc_precision_at_20_max value: 28.31417075291312 - type: nauc_precision_at_20_std value: 41.405935715061815 - type: nauc_precision_at_3_diff1 value: 7.117255890225942 - type: nauc_precision_at_3_max value: 39.19894132683829 - type: nauc_precision_at_3_std value: 38.48255841994843 - type: nauc_precision_at_5_diff1 value: 1.861523090114206 - type: nauc_precision_at_5_max value: 38.11649223007208 - type: nauc_precision_at_5_std value: 40.52993530374645 - type: nauc_recall_at_1000_diff1 value: 26.497648584314636 - type: nauc_recall_at_1000_max value: 44.48069746734414 - type: nauc_recall_at_1000_std value: 53.16438130228715 - type: nauc_recall_at_100_diff1 value: 26.353456899511446 - type: nauc_recall_at_100_max value: 37.57379787884197 - type: nauc_recall_at_100_std value: 29.197468295989548 - type: nauc_recall_at_10_diff1 value: 22.80445738351114 - type: nauc_recall_at_10_max value: 15.895630778449046 - type: nauc_recall_at_10_std value: -8.746224797644501 - type: nauc_recall_at_1_diff1 value: 35.20851030208876 - type: nauc_recall_at_1_max value: 5.783003346365858 - type: nauc_recall_at_1_std value: -21.11679133835354 - type: nauc_recall_at_20_diff1 value: 22.34028867678706 - type: nauc_recall_at_20_max value: 21.42373427646772 - type: nauc_recall_at_20_std value: 0.4533036151015875 - type: nauc_recall_at_3_diff1 value: 24.96853445599229 - type: nauc_recall_at_3_max value: 6.245185375804208 - type: nauc_recall_at_3_std value: -20.200240127099622 - type: nauc_recall_at_5_diff1 value: 24.749259476710623 - type: nauc_recall_at_5_max value: 11.024592845995942 - type: nauc_recall_at_5_std value: -16.15683085641543 - type: ndcg_at_1 value: 64.125 - type: ndcg_at_10 value: 52.276999999999994 - type: ndcg_at_100 value: 57.440000000000005 - type: ndcg_at_1000 value: 64.082 - type: ndcg_at_20 value: 51.383 - type: ndcg_at_3 value: 55.769000000000005 - type: ndcg_at_5 value: 53.978 - type: precision_at_1 value: 76.25 - type: precision_at_10 value: 43.05 - type: precision_at_100 value: 14.09 - type: precision_at_1000 value: 2.662 - type: precision_at_20 value: 33.112 - type: precision_at_3 value: 59.833000000000006 - type: precision_at_5 value: 53.05 - type: recall_at_1 value: 9.949 - type: recall_at_10 value: 30.424 - type: recall_at_100 value: 64.062 - type: recall_at_1000 value: 85.916 - type: recall_at_20 value: 39.895 - type: recall_at_3 value: 17.876 - type: recall_at_5 value: 22.536 - task: type: Classification dataset: name: MTEB EmotionClassification type: mteb/emotion config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 84.29499999999999 - type: f1 value: 79.76188258172078 - type: f1_weighted value: 84.96026012933847 - type: main_score value: 84.29499999999999 - task: type: Retrieval dataset: name: MTEB FEVER type: mteb/fever config: default split: test revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 metrics: - type: main_score value: 94.83200000000001 - type: map_at_1 value: 87.339 - type: map_at_10 value: 92.92099999999999 - type: map_at_100 value: 93.108 - type: map_at_1000 value: 93.116 - type: map_at_20 value: 93.041 - type: map_at_3 value: 92.219 - type: map_at_5 value: 92.664 - type: mrr_at_1 value: 93.99939993999399 - type: mrr_at_10 value: 96.55188137861403 - type: mrr_at_100 value: 96.5652366009286 - type: mrr_at_1000 value: 96.5652625550811 - type: mrr_at_20 value: 96.5601781754844 - type: mrr_at_3 value: 96.45714571457142 - type: mrr_at_5 value: 96.544904490449 - type: nauc_map_at_1000_diff1 value: 51.81676454961933 - type: nauc_map_at_1000_max value: 24.904822914926118 - type: nauc_map_at_1000_std value: -3.8110347821630404 - type: nauc_map_at_100_diff1 value: 51.77514975011158 - type: nauc_map_at_100_max value: 24.912497341800094 - type: nauc_map_at_100_std value: -3.76229517662447 - type: nauc_map_at_10_diff1 value: 51.29608296382479 - type: nauc_map_at_10_max value: 24.78704970246707 - type: nauc_map_at_10_std value: -3.723130815783328 - type: nauc_map_at_1_diff1 value: 59.90813138005125 - type: nauc_map_at_1_max value: 24.58479295693794 - type: nauc_map_at_1_std value: -8.056152492777027 - type: nauc_map_at_20_diff1 value: 51.428639331678326 - type: nauc_map_at_20_max value: 24.849214517705086 - type: nauc_map_at_20_std value: -3.685550123874596 - type: nauc_map_at_3_diff1 value: 50.94399923719279 - type: nauc_map_at_3_max value: 24.359700180006207 - type: nauc_map_at_3_std value: -5.407767408816422 - type: nauc_map_at_5_diff1 value: 50.767302682959546 - type: nauc_map_at_5_max value: 24.491113461892215 - type: nauc_map_at_5_std value: -4.058336127339082 - type: nauc_mrr_at_1000_diff1 value: 79.86042313551833 - type: nauc_mrr_at_1000_max value: 23.20960445633933 - type: nauc_mrr_at_1000_std value: -23.54334295120471 - type: nauc_mrr_at_100_diff1 value: 79.85991247027636 - type: nauc_mrr_at_100_max value: 23.210085926780106 - type: nauc_mrr_at_100_std value: -23.542508200789197 - type: nauc_mrr_at_10_diff1 value: 79.71095155563415 - type: nauc_mrr_at_10_max value: 23.24128650883908 - type: nauc_mrr_at_10_std value: -23.408502781834102 - type: nauc_mrr_at_1_diff1 value: 82.6349900233902 - type: nauc_mrr_at_1_max value: 21.994548214014227 - type: nauc_mrr_at_1_std value: -22.549769792179262 - type: nauc_mrr_at_20_diff1 value: 79.76465012873038 - type: nauc_mrr_at_20_max value: 23.17575026523213 - type: nauc_mrr_at_20_std value: -23.492660166315048 - type: nauc_mrr_at_3_diff1 value: 79.91074933379953 - type: nauc_mrr_at_3_max value: 24.14246499097892 - type: nauc_mrr_at_3_std value: -25.22601708389664 - type: nauc_mrr_at_5_diff1 value: 79.62092651565847 - type: nauc_mrr_at_5_max value: 23.315937737034425 - type: nauc_mrr_at_5_std value: -23.317659360058403 - type: nauc_ndcg_at_1000_diff1 value: 54.404537986779225 - type: nauc_ndcg_at_1000_max value: 25.38408304128995 - type: nauc_ndcg_at_1000_std value: -4.916709117696968 - type: nauc_ndcg_at_100_diff1 value: 53.2448598868241 - type: nauc_ndcg_at_100_max value: 25.75325255295546 - type: nauc_ndcg_at_100_std value: -3.680507005630751 - type: nauc_ndcg_at_10_diff1 value: 50.81057355170232 - type: nauc_ndcg_at_10_max value: 25.006448273343807 - type: nauc_ndcg_at_10_std value: -2.8979899112515577 - type: nauc_ndcg_at_1_diff1 value: 82.6349900233902 - type: nauc_ndcg_at_1_max value: 21.994548214014227 - type: nauc_ndcg_at_1_std value: -22.549769792179262 - type: nauc_ndcg_at_20_diff1 value: 51.205023097166304 - type: nauc_ndcg_at_20_max value: 25.22133626556826 - type: nauc_ndcg_at_20_std value: -2.9506328244150155 - type: nauc_ndcg_at_3_diff1 value: 51.79780256736321 - type: nauc_ndcg_at_3_max value: 24.81137324438439 - type: nauc_ndcg_at_3_std value: -6.881223858227807 - type: nauc_ndcg_at_5_diff1 value: 50.290038260564565 - type: nauc_ndcg_at_5_max value: 24.57250792165796 - type: nauc_ndcg_at_5_std value: -3.5124628344654596 - type: nauc_precision_at_1000_diff1 value: -20.215211396894333 - type: nauc_precision_at_1000_max value: -14.165452298769171 - type: nauc_precision_at_1000_std value: -2.0952871214470816 - type: nauc_precision_at_100_diff1 value: -22.340257474494607 - type: nauc_precision_at_100_max value: -12.697885641360282 - type: nauc_precision_at_100_std value: 1.0688624940286244 - type: nauc_precision_at_10_diff1 value: -24.78271817420798 - type: nauc_precision_at_10_max value: -12.625257500222656 - type: nauc_precision_at_10_std value: 3.223250450607087 - type: nauc_precision_at_1_diff1 value: 82.6349900233902 - type: nauc_precision_at_1_max value: 21.994548214014227 - type: nauc_precision_at_1_std value: -22.549769792179262 - type: nauc_precision_at_20_diff1 value: -24.375756227194177 - type: nauc_precision_at_20_max value: -12.341015011563536 - type: nauc_precision_at_20_std value: 2.7475274619387955 - type: nauc_precision_at_3_diff1 value: -24.8251306777365 - type: nauc_precision_at_3_max value: -13.109579709589042 - type: nauc_precision_at_3_std value: -1.2233442335420748 - type: nauc_precision_at_5_diff1 value: -26.955418583344894 - type: nauc_precision_at_5_max value: -13.598630838071015 - type: nauc_precision_at_5_std value: 2.545780631940738 - type: nauc_recall_at_1000_diff1 value: 0.2542680835344437 - type: nauc_recall_at_1000_max value: 49.38194243035277 - type: nauc_recall_at_1000_std value: 57.021502715846026 - type: nauc_recall_at_100_diff1 value: 5.062154815367015 - type: nauc_recall_at_100_max value: 45.41178380188437 - type: nauc_recall_at_100_std value: 50.78382225901813 - type: nauc_recall_at_10_diff1 value: 20.429153629007818 - type: nauc_recall_at_10_max value: 27.516855026155508 - type: nauc_recall_at_10_std value: 21.367491371755467 - type: nauc_recall_at_1_diff1 value: 59.90813138005125 - type: nauc_recall_at_1_max value: 24.58479295693794 - type: nauc_recall_at_1_std value: -8.056152492777027 - type: nauc_recall_at_20_diff1 value: 13.072430858896942 - type: nauc_recall_at_20_max value: 29.5522659183247 - type: nauc_recall_at_20_std value: 28.70569974090291 - type: nauc_recall_at_3_diff1 value: 30.419084482663617 - type: nauc_recall_at_3_max value: 25.627389580252835 - type: nauc_recall_at_3_std value: 2.5557690877637054 - type: nauc_recall_at_5_diff1 value: 22.92561435069869 - type: nauc_recall_at_5_max value: 25.545265063475455 - type: nauc_recall_at_5_std value: 14.736172663072786 - type: ndcg_at_1 value: 93.999 - type: ndcg_at_10 value: 94.83200000000001 - type: ndcg_at_100 value: 95.363 - type: ndcg_at_1000 value: 95.478 - type: ndcg_at_20 value: 95.077 - type: ndcg_at_3 value: 94.143 - type: ndcg_at_5 value: 94.525 - type: precision_at_1 value: 93.999 - type: precision_at_10 value: 11.029 - type: precision_at_100 value: 1.1560000000000001 - type: precision_at_1000 value: 0.11800000000000001 - type: precision_at_20 value: 5.62 - type: precision_at_3 value: 35.219 - type: precision_at_5 value: 21.584 - type: recall_at_1 value: 87.339 - type: recall_at_10 value: 97.026 - type: recall_at_100 value: 98.936 - type: recall_at_1000 value: 99.599 - type: recall_at_20 value: 97.744 - type: recall_at_3 value: 95.069 - type: recall_at_5 value: 96.177 - task: type: Retrieval dataset: name: MTEB FiQA2018 type: mteb/fiqa config: default split: test revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: main_score value: 60.480000000000004 - type: map_at_1 value: 31.529 - type: map_at_10 value: 52.081 - type: map_at_100 value: 54.342 - type: map_at_1000 value: 54.449000000000005 - type: map_at_20 value: 53.479 - type: map_at_3 value: 45.471000000000004 - type: map_at_5 value: 49.164 - type: mrr_at_1 value: 60.03086419753087 - type: mrr_at_10 value: 67.73754409171075 - type: mrr_at_100 value: 68.332432152368 - type: mrr_at_1000 value: 68.34150941774908 - type: mrr_at_20 value: 68.14780993838725 - type: mrr_at_3 value: 65.6378600823045 - type: mrr_at_5 value: 66.88014403292176 - type: nauc_map_at_1000_diff1 value: 45.36598134579052 - type: nauc_map_at_1000_max value: 31.891451119906943 - type: nauc_map_at_1000_std value: -15.41454384137943 - type: nauc_map_at_100_diff1 value: 45.31268291874018 - type: nauc_map_at_100_max value: 31.811055683002092 - type: nauc_map_at_100_std value: -15.348503855591417 - type: nauc_map_at_10_diff1 value: 45.22606983565892 - type: nauc_map_at_10_max value: 30.46108534749699 - type: nauc_map_at_10_std value: -16.618086029682555 - type: nauc_map_at_1_diff1 value: 49.94952823753276 - type: nauc_map_at_1_max value: 13.770377574254548 - type: nauc_map_at_1_std value: -14.946357968858653 - type: nauc_map_at_20_diff1 value: 45.29274207897926 - type: nauc_map_at_20_max value: 31.27332015148257 - type: nauc_map_at_20_std value: -15.782946115613129 - type: nauc_map_at_3_diff1 value: 47.94248233566038 - type: nauc_map_at_3_max value: 24.022838776825456 - type: nauc_map_at_3_std value: -17.103518542262208 - type: nauc_map_at_5_diff1 value: 45.85345590031722 - type: nauc_map_at_5_max value: 27.78341379004547 - type: nauc_map_at_5_std value: -17.490850791756326 - type: nauc_mrr_at_1000_diff1 value: 58.225141047822824 - type: nauc_mrr_at_1000_max value: 43.39606904140525 - type: nauc_mrr_at_1000_std value: -14.64093518199122 - type: nauc_mrr_at_100_diff1 value: 58.22137274179545 - type: nauc_mrr_at_100_max value: 43.39567568136935 - type: nauc_mrr_at_100_std value: -14.62512313985582 - type: nauc_mrr_at_10_diff1 value: 58.03217329957151 - type: nauc_mrr_at_10_max value: 43.633561683075186 - type: nauc_mrr_at_10_std value: -14.563703576023808 - type: nauc_mrr_at_1_diff1 value: 61.48979902647692 - type: nauc_mrr_at_1_max value: 43.1938079066948 - type: nauc_mrr_at_1_std value: -15.808138277440465 - type: nauc_mrr_at_20_diff1 value: 58.13185370150794 - type: nauc_mrr_at_20_max value: 43.35607721183147 - type: nauc_mrr_at_20_std value: -14.635812702971263 - type: nauc_mrr_at_3_diff1 value: 58.698963168321264 - type: nauc_mrr_at_3_max value: 43.633129249785405 - type: nauc_mrr_at_3_std value: -15.733246346983854 - type: nauc_mrr_at_5_diff1 value: 57.94156745229547 - type: nauc_mrr_at_5_max value: 43.14152462640525 - type: nauc_mrr_at_5_std value: -15.318685307750895 - type: nauc_ndcg_at_1000_diff1 value: 47.871896043731496 - type: nauc_ndcg_at_1000_max value: 37.159845167533426 - type: nauc_ndcg_at_1000_std value: -13.067288160833485 - type: nauc_ndcg_at_100_diff1 value: 47.046171407204426 - type: nauc_ndcg_at_100_max value: 36.422514360855835 - type: nauc_ndcg_at_100_std value: -11.636859259571441 - type: nauc_ndcg_at_10_diff1 value: 46.232628149078096 - type: nauc_ndcg_at_10_max value: 34.82402625088358 - type: nauc_ndcg_at_10_std value: -14.768545542980114 - type: nauc_ndcg_at_1_diff1 value: 61.48979902647692 - type: nauc_ndcg_at_1_max value: 43.1938079066948 - type: nauc_ndcg_at_1_std value: -15.808138277440465 - type: nauc_ndcg_at_20_diff1 value: 46.51116172390955 - type: nauc_ndcg_at_20_max value: 35.36362650568298 - type: nauc_ndcg_at_20_std value: -12.849406209182826 - type: nauc_ndcg_at_3_diff1 value: 47.39832263785871 - type: nauc_ndcg_at_3_max value: 35.67466264628456 - type: nauc_ndcg_at_3_std value: -17.257717349296943 - type: nauc_ndcg_at_5_diff1 value: 45.91049493804232 - type: nauc_ndcg_at_5_max value: 33.8405091138445 - type: nauc_ndcg_at_5_std value: -17.477069902735895 - type: nauc_precision_at_1000_diff1 value: -12.037873000917767 - type: nauc_precision_at_1000_max value: 26.043220150002295 - type: nauc_precision_at_1000_std value: 6.84910668321572 - type: nauc_precision_at_100_diff1 value: -9.383403459051864 - type: nauc_precision_at_100_max value: 29.68713170610003 - type: nauc_precision_at_100_std value: 10.079531587056152 - type: nauc_precision_at_10_diff1 value: 3.3433323353925135 - type: nauc_precision_at_10_max value: 38.31790111725993 - type: nauc_precision_at_10_std value: 0.7888123304710856 - type: nauc_precision_at_1_diff1 value: 61.48979902647692 - type: nauc_precision_at_1_max value: 43.1938079066948 - type: nauc_precision_at_1_std value: -15.808138277440465 - type: nauc_precision_at_20_diff1 value: -2.083500986294448 - type: nauc_precision_at_20_max value: 35.77143835726343 - type: nauc_precision_at_20_std value: 5.318547021874003 - type: nauc_precision_at_3_diff1 value: 23.335617788912586 - type: nauc_precision_at_3_max value: 39.81973275320871 - type: nauc_precision_at_3_std value: -8.442769390555561 - type: nauc_precision_at_5_diff1 value: 11.521087842589482 - type: nauc_precision_at_5_max value: 39.527792539828255 - type: nauc_precision_at_5_std value: -5.412729503701626 - type: nauc_recall_at_1000_diff1 value: 10.6830893047453 - type: nauc_recall_at_1000_max value: 8.834504311238423 - type: nauc_recall_at_1000_std value: 24.670754304859692 - type: nauc_recall_at_100_diff1 value: 20.646020385527358 - type: nauc_recall_at_100_max value: 20.121595011523294 - type: nauc_recall_at_100_std value: 19.42307459311791 - type: nauc_recall_at_10_diff1 value: 33.01029313733417 - type: nauc_recall_at_10_max value: 27.948634980368702 - type: nauc_recall_at_10_std value: -10.239767371462975 - type: nauc_recall_at_1_diff1 value: 49.94952823753276 - type: nauc_recall_at_1_max value: 13.770377574254548 - type: nauc_recall_at_1_std value: -14.946357968858653 - type: nauc_recall_at_20_diff1 value: 30.040111045267963 - type: nauc_recall_at_20_max value: 25.984919302418184 - type: nauc_recall_at_20_std value: -1.4998001817460804 - type: nauc_recall_at_3_diff1 value: 42.24410559113653 - type: nauc_recall_at_3_max value: 20.269503583626914 - type: nauc_recall_at_3_std value: -17.09578532600584 - type: nauc_recall_at_5_diff1 value: 36.124149735848945 - type: nauc_recall_at_5_max value: 22.708022306002622 - type: nauc_recall_at_5_std value: -16.966976847236193 - type: ndcg_at_1 value: 60.031 - type: ndcg_at_10 value: 60.480000000000004 - type: ndcg_at_100 value: 66.94099999999999 - type: ndcg_at_1000 value: 68.303 - type: ndcg_at_20 value: 63.536 - type: ndcg_at_3 value: 55.903999999999996 - type: ndcg_at_5 value: 57.387 - type: precision_at_1 value: 60.031 - type: precision_at_10 value: 16.682 - type: precision_at_100 value: 2.336 - type: precision_at_1000 value: 0.259 - type: precision_at_20 value: 9.66 - type: precision_at_3 value: 37.191 - type: precision_at_5 value: 27.253 - type: recall_at_1 value: 31.529 - type: recall_at_10 value: 68.035 - type: recall_at_100 value: 90.925 - type: recall_at_1000 value: 98.688 - type: recall_at_20 value: 77.453 - type: recall_at_3 value: 50.221000000000004 - type: recall_at_5 value: 58.209999999999994 - task: type: Retrieval dataset: name: MTEB HotpotQA type: mteb/hotpotqa config: default split: test revision: ab518f4d6fcca38d87c25209f94beba119d02014 metrics: - type: main_score value: 76.67399999999999 - type: map_at_1 value: 43.822 - type: map_at_10 value: 68.82000000000001 - type: map_at_100 value: 69.659 - type: map_at_1000 value: 69.714 - type: map_at_20 value: 69.305 - type: map_at_3 value: 65.517 - type: map_at_5 value: 67.633 - type: mrr_at_1 value: 87.643484132343 - type: mrr_at_10 value: 91.28134679485098 - type: mrr_at_100 value: 91.37985230614755 - type: mrr_at_1000 value: 91.38202467630681 - type: mrr_at_20 value: 91.34718855278429 - type: mrr_at_3 value: 90.75849651136599 - type: mrr_at_5 value: 91.10961062345235 - type: nauc_map_at_1000_diff1 value: 3.7670405082837477 - type: nauc_map_at_1000_max value: 14.410594409695182 - type: nauc_map_at_1000_std value: 7.94738583292685 - type: nauc_map_at_100_diff1 value: 3.738796209193936 - type: nauc_map_at_100_max value: 14.408029101534694 - type: nauc_map_at_100_std value: 7.979641077687816 - type: nauc_map_at_10_diff1 value: 3.334917978089454 - type: nauc_map_at_10_max value: 13.975255289147748 - type: nauc_map_at_10_std value: 7.491959628012161 - type: nauc_map_at_1_diff1 value: 75.35066482050009 - type: nauc_map_at_1_max value: 53.573503488571475 - type: nauc_map_at_1_std value: -6.542030594426993 - type: nauc_map_at_20_diff1 value: 3.5197129341582083 - type: nauc_map_at_20_max value: 14.159880698006816 - type: nauc_map_at_20_std value: 7.856574384998483 - type: nauc_map_at_3_diff1 value: 3.0992333232864064 - type: nauc_map_at_3_max value: 12.513959281222112 - type: nauc_map_at_3_std value: 4.352912866014865 - type: nauc_map_at_5_diff1 value: 3.0351688998572537 - type: nauc_map_at_5_max value: 13.21599457624529 - type: nauc_map_at_5_std value: 6.246882983214777 - type: nauc_mrr_at_1000_diff1 value: 75.23953736361132 - type: nauc_mrr_at_1000_max value: 56.64260717262164 - type: nauc_mrr_at_1000_std value: -4.865932053762276 - type: nauc_mrr_at_100_diff1 value: 75.24091372816497 - type: nauc_mrr_at_100_max value: 56.64831104504846 - type: nauc_mrr_at_100_std value: -4.850966297943324 - type: nauc_mrr_at_10_diff1 value: 75.26540178053416 - type: nauc_mrr_at_10_max value: 56.828755673428965 - type: nauc_mrr_at_10_std value: -4.8401126970944635 - type: nauc_mrr_at_1_diff1 value: 75.35066482050009 - type: nauc_mrr_at_1_max value: 53.573503488571475 - type: nauc_mrr_at_1_std value: -6.542030594426993 - type: nauc_mrr_at_20_diff1 value: 75.24453050729845 - type: nauc_mrr_at_20_max value: 56.69220588401435 - type: nauc_mrr_at_20_std value: -4.843700730832108 - type: nauc_mrr_at_3_diff1 value: 74.98411648336175 - type: nauc_mrr_at_3_max value: 56.766537573537114 - type: nauc_mrr_at_3_std value: -4.909712671649337 - type: nauc_mrr_at_5_diff1 value: 75.20599020991028 - type: nauc_mrr_at_5_max value: 56.64236207782237 - type: nauc_mrr_at_5_std value: -5.208907367513977 - type: nauc_ndcg_at_1000_diff1 value: 11.48307079099774 - type: nauc_ndcg_at_1000_max value: 20.893326881675176 - type: nauc_ndcg_at_1000_std value: 10.43489838692119 - type: nauc_ndcg_at_100_diff1 value: 10.395588735754927 - type: nauc_ndcg_at_100_max value: 20.529573302516912 - type: nauc_ndcg_at_100_std value: 11.252973083654268 - type: nauc_ndcg_at_10_diff1 value: 8.596739352741972 - type: nauc_ndcg_at_10_max value: 18.475863682540673 - type: nauc_ndcg_at_10_std value: 9.175831033463352 - type: nauc_ndcg_at_1_diff1 value: 75.35066482050009 - type: nauc_ndcg_at_1_max value: 53.573503488571475 - type: nauc_ndcg_at_1_std value: -6.542030594426993 - type: nauc_ndcg_at_20_diff1 value: 8.998033972471749 - type: nauc_ndcg_at_20_max value: 18.892085875404522 - type: nauc_ndcg_at_20_std value: 10.3241608901084 - type: nauc_ndcg_at_3_diff1 value: 8.796384949533579 - type: nauc_ndcg_at_3_max value: 16.515261419885274 - type: nauc_ndcg_at_3_std value: 4.081902976576701 - type: nauc_ndcg_at_5_diff1 value: 8.277259464605025 - type: nauc_ndcg_at_5_max value: 17.163053202909527 - type: nauc_ndcg_at_5_std value: 6.652669449704474 - type: nauc_precision_at_1000_diff1 value: -3.490556596304827 - type: nauc_precision_at_1000_max value: 31.0473259001597 - type: nauc_precision_at_1000_std value: 52.36921397692622 - type: nauc_precision_at_100_diff1 value: -6.420747959222489 - type: nauc_precision_at_100_max value: 20.555887056005936 - type: nauc_precision_at_100_std value: 36.119132870798495 - type: nauc_precision_at_10_diff1 value: -6.461726057290426 - type: nauc_precision_at_10_max value: 12.161081825341915 - type: nauc_precision_at_10_std value: 17.961318451839993 - type: nauc_precision_at_1_diff1 value: 75.35066482050009 - type: nauc_precision_at_1_max value: 53.573503488571475 - type: nauc_precision_at_1_std value: -6.542030594426993 - type: nauc_precision_at_20_diff1 value: -7.361461296416161 - type: nauc_precision_at_20_max value: 12.663621261696733 - type: nauc_precision_at_20_std value: 23.312476851670286 - type: nauc_precision_at_3_diff1 value: -3.299056912774522 - type: nauc_precision_at_3_max value: 9.85602375812038 - type: nauc_precision_at_3_std value: 6.4962782003155475 - type: nauc_precision_at_5_diff1 value: -5.3155827772027795 - type: nauc_precision_at_5_max value: 10.32907751171833 - type: nauc_precision_at_5_std value: 11.384098087196932 - type: nauc_recall_at_1000_diff1 value: -3.4905565963043332 - type: nauc_recall_at_1000_max value: 31.04732590016041 - type: nauc_recall_at_1000_std value: 52.36921397692641 - type: nauc_recall_at_100_diff1 value: -6.420747959222586 - type: nauc_recall_at_100_max value: 20.55588705600596 - type: nauc_recall_at_100_std value: 36.11913287079825 - type: nauc_recall_at_10_diff1 value: -6.461726057290347 - type: nauc_recall_at_10_max value: 12.161081825342022 - type: nauc_recall_at_10_std value: 17.96131845184002 - type: nauc_recall_at_1_diff1 value: 75.35066482050009 - type: nauc_recall_at_1_max value: 53.573503488571475 - type: nauc_recall_at_1_std value: -6.542030594426993 - type: nauc_recall_at_20_diff1 value: -7.361461296416054 - type: nauc_recall_at_20_max value: 12.66362126169679 - type: nauc_recall_at_20_std value: 23.312476851670382 - type: nauc_recall_at_3_diff1 value: -3.2990569127745886 - type: nauc_recall_at_3_max value: 9.856023758120296 - type: nauc_recall_at_3_std value: 6.496278200315444 - type: nauc_recall_at_5_diff1 value: -5.315582777202729 - type: nauc_recall_at_5_max value: 10.329077511718229 - type: nauc_recall_at_5_std value: 11.384098087196932 - type: ndcg_at_1 value: 87.643 - type: ndcg_at_10 value: 76.67399999999999 - type: ndcg_at_100 value: 79.462 - type: ndcg_at_1000 value: 80.43599999999999 - type: ndcg_at_20 value: 77.83 - type: ndcg_at_3 value: 72.256 - type: ndcg_at_5 value: 74.789 - type: precision_at_1 value: 87.643 - type: precision_at_10 value: 15.726999999999999 - type: precision_at_100 value: 1.791 - type: precision_at_1000 value: 0.192 - type: precision_at_20 value: 8.236 - type: precision_at_3 value: 45.919 - type: precision_at_5 value: 29.558 - type: recall_at_1 value: 43.822 - type: recall_at_10 value: 78.636 - type: recall_at_100 value: 89.527 - type: recall_at_1000 value: 95.868 - type: recall_at_20 value: 82.363 - type: recall_at_3 value: 68.879 - type: recall_at_5 value: 73.896 - task: type: Classification dataset: name: MTEB ImdbClassification type: mteb/imdb config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 96.6608 - type: ap value: 95.14657820401189 - type: ap_weighted value: 95.14657820401189 - type: f1 value: 96.66029695623422 - type: f1_weighted value: 96.66029695623423 - type: main_score value: 96.6608 - task: type: Retrieval dataset: name: MTEB MSMARCO type: mteb/msmarco config: default split: dev revision: c5a29a104738b98a9e76336939199e264163d4a0 metrics: - type: main_score value: 45.217 - type: map_at_1 value: 24.728 - type: map_at_10 value: 37.933 - type: map_at_100 value: 39.074999999999996 - type: map_at_1000 value: 39.115 - type: map_at_20 value: 38.663 - type: map_at_3 value: 33.904 - type: map_at_5 value: 36.217 - type: mrr_at_1 value: 25.44412607449857 - type: mrr_at_10 value: 38.52640196479737 - type: mrr_at_100 value: 39.60462889736067 - type: mrr_at_1000 value: 39.638904296248526 - type: mrr_at_20 value: 39.2234365827559 - type: mrr_at_3 value: 34.59646609360076 - type: mrr_at_5 value: 36.8801337153773 - type: nauc_map_at_1000_diff1 value: 37.645652178132174 - type: nauc_map_at_1000_max value: 9.953357023361367 - type: nauc_map_at_1000_std value: -20.800238036721503 - type: nauc_map_at_100_diff1 value: 37.643073495974555 - type: nauc_map_at_100_max value: 9.95921239641703 - type: nauc_map_at_100_std value: -20.76517765535793 - type: nauc_map_at_10_diff1 value: 37.44380763335014 - type: nauc_map_at_10_max value: 9.917273043055342 - type: nauc_map_at_10_std value: -21.467951225710898 - type: nauc_map_at_1_diff1 value: 41.02118887981969 - type: nauc_map_at_1_max value: 8.301113449711778 - type: nauc_map_at_1_std value: -19.436814224415027 - type: nauc_map_at_20_diff1 value: 37.58156586490493 - type: nauc_map_at_20_max value: 9.972927967610659 - type: nauc_map_at_20_std value: -20.951374218839387 - type: nauc_map_at_3_diff1 value: 37.67246795684178 - type: nauc_map_at_3_max value: 9.307031378909478 - type: nauc_map_at_3_std value: -21.77026217965021 - type: nauc_map_at_5_diff1 value: 37.39086482095963 - type: nauc_map_at_5_max value: 9.732739107368566 - type: nauc_map_at_5_std value: -21.8424296893692 - type: nauc_mrr_at_1000_diff1 value: 37.36666719603192 - type: nauc_mrr_at_1000_max value: 9.79040465289953 - type: nauc_mrr_at_1000_std value: -20.590147245965568 - type: nauc_mrr_at_100_diff1 value: 37.36560296629318 - type: nauc_mrr_at_100_max value: 9.798113710672162 - type: nauc_mrr_at_100_std value: -20.556791838504292 - type: nauc_mrr_at_10_diff1 value: 37.19257605840734 - type: nauc_mrr_at_10_max value: 9.749429811638063 - type: nauc_mrr_at_10_std value: -21.206407664327276 - type: nauc_mrr_at_1_diff1 value: 40.98478651095172 - type: nauc_mrr_at_1_max value: 8.173841799119707 - type: nauc_mrr_at_1_std value: -19.530027987868017 - type: nauc_mrr_at_20_diff1 value: 37.29973172861245 - type: nauc_mrr_at_20_max value: 9.815127660001345 - type: nauc_mrr_at_20_std value: -20.700860112175928 - type: nauc_mrr_at_3_diff1 value: 37.282848009425734 - type: nauc_mrr_at_3_max value: 9.172741713108193 - type: nauc_mrr_at_3_std value: -21.563630513502996 - type: nauc_mrr_at_5_diff1 value: 37.08609827303586 - type: nauc_mrr_at_5_max value: 9.604643424273284 - type: nauc_mrr_at_5_std value: -21.580110806494094 - type: nauc_ndcg_at_1000_diff1 value: 37.086587020218545 - type: nauc_ndcg_at_1000_max value: 10.696860688467472 - type: nauc_ndcg_at_1000_std value: -19.50989939916873 - type: nauc_ndcg_at_100_diff1 value: 37.03794531268128 - type: nauc_ndcg_at_100_max value: 10.940820719182339 - type: nauc_ndcg_at_100_std value: -18.28651832370893 - type: nauc_ndcg_at_10_diff1 value: 36.21062857920633 - type: nauc_ndcg_at_10_max value: 10.845172882571733 - type: nauc_ndcg_at_10_std value: -21.454301679510106 - type: nauc_ndcg_at_1_diff1 value: 40.98478651095172 - type: nauc_ndcg_at_1_max value: 8.173841799119707 - type: nauc_ndcg_at_1_std value: -19.530027987868017 - type: nauc_ndcg_at_20_diff1 value: 36.583262733100526 - type: nauc_ndcg_at_20_max value: 11.10492720898974 - type: nauc_ndcg_at_20_std value: -19.41753284137609 - type: nauc_ndcg_at_3_diff1 value: 36.57271365035382 - type: nauc_ndcg_at_3_max value: 9.56073433062999 - type: nauc_ndcg_at_3_std value: -22.324263670932915 - type: nauc_ndcg_at_5_diff1 value: 36.09419372820154 - type: nauc_ndcg_at_5_max value: 10.357384992631271 - type: nauc_ndcg_at_5_std value: -22.389578276324894 - type: nauc_precision_at_1000_diff1 value: -2.7435338714030597 - type: nauc_precision_at_1000_max value: 4.302274933383809 - type: nauc_precision_at_1000_std value: 8.456846348638948 - type: nauc_precision_at_100_diff1 value: 15.149466332615983 - type: nauc_precision_at_100_max value: 12.501013731673163 - type: nauc_precision_at_100_std value: 15.909667509021785 - type: nauc_precision_at_10_diff1 value: 28.699788688314214 - type: nauc_precision_at_10_max value: 13.024586051842347 - type: nauc_precision_at_10_std value: -19.197658937078703 - type: nauc_precision_at_1_diff1 value: 40.98478651095172 - type: nauc_precision_at_1_max value: 8.173841799119707 - type: nauc_precision_at_1_std value: -19.530027987868017 - type: nauc_precision_at_20_diff1 value: 26.519292942353395 - type: nauc_precision_at_20_max value: 14.389979272056438 - type: nauc_precision_at_20_std value: -7.030956994938155 - type: nauc_precision_at_3_diff1 value: 32.87913492278213 - type: nauc_precision_at_3_max value: 9.673660161387776 - type: nauc_precision_at_3_std value: -23.905612656592172 - type: nauc_precision_at_5_diff1 value: 30.903850113238597 - type: nauc_precision_at_5_max value: 11.482375434154898 - type: nauc_precision_at_5_std value: -23.828657095254247 - type: nauc_recall_at_1000_diff1 value: 35.80765639589219 - type: nauc_recall_at_1000_max value: 50.94532805969448 - type: nauc_recall_at_1000_std value: 66.79910877083275 - type: nauc_recall_at_100_diff1 value: 34.96182828311028 - type: nauc_recall_at_100_max value: 21.729699631790556 - type: nauc_recall_at_100_std value: 23.509439011686474 - type: nauc_recall_at_10_diff1 value: 31.88371369567137 - type: nauc_recall_at_10_max value: 14.425389702697073 - type: nauc_recall_at_10_std value: -20.95578001880924 - type: nauc_recall_at_1_diff1 value: 41.02118887981969 - type: nauc_recall_at_1_max value: 8.301113449711778 - type: nauc_recall_at_1_std value: -19.436814224415027 - type: nauc_recall_at_20_diff1 value: 32.42718780622455 - type: nauc_recall_at_20_max value: 16.90686126329399 - type: nauc_recall_at_20_std value: -9.38158227016737 - type: nauc_recall_at_3_diff1 value: 33.68966646043966 - type: nauc_recall_at_3_max value: 10.336277419708532 - type: nauc_recall_at_3_std value: -23.80165869168538 - type: nauc_recall_at_5_diff1 value: 32.26258807452426 - type: nauc_recall_at_5_max value: 12.303713005399935 - type: nauc_recall_at_5_std value: -23.87721891164968 - type: ndcg_at_1 value: 25.444 - type: ndcg_at_10 value: 45.217 - type: ndcg_at_100 value: 50.575 - type: ndcg_at_1000 value: 51.519999999999996 - type: ndcg_at_20 value: 47.786 - type: ndcg_at_3 value: 37.067 - type: ndcg_at_5 value: 41.184 - type: precision_at_1 value: 25.444 - type: precision_at_10 value: 7.07 - type: precision_at_100 value: 0.9730000000000001 - type: precision_at_1000 value: 0.106 - type: precision_at_20 value: 4.072 - type: precision_at_3 value: 15.754999999999999 - type: precision_at_5 value: 11.544 - type: recall_at_1 value: 24.728 - type: recall_at_10 value: 67.607 - type: recall_at_100 value: 92.094 - type: recall_at_1000 value: 99.165 - type: recall_at_20 value: 77.529 - type: recall_at_3 value: 45.535 - type: recall_at_5 value: 55.394 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 99.01276789785682 - type: f1 value: 98.9288649250924 - type: f1_weighted value: 99.01406884928141 - type: main_score value: 99.01276789785682 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 92.78385772913816 - type: f1 value: 79.78115704297824 - type: f1_weighted value: 93.90424147486428 - type: main_score value: 92.78385772913816 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 4672e20407010da34463acc759c162ca9734bca6 metrics: - type: accuracy value: 85.83053127101546 - type: f1 value: 82.72036139888232 - type: f1_weighted value: 85.81759723866098 - type: main_score value: 85.83053127101546 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8 metrics: - type: accuracy value: 90.19838601210489 - type: f1 value: 89.55260197964978 - type: f1_weighted value: 90.11422965504119 - type: main_score value: 90.19838601210489 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P type: mteb/medrxiv-clustering-p2p config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: main_score value: 46.866746897607094 - type: v_measure value: 46.866746897607094 - type: v_measure_std value: 1.0966477896919726 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S type: mteb/medrxiv-clustering-s2s config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: main_score value: 44.6538827415503 - type: v_measure value: 44.6538827415503 - type: v_measure_std value: 1.1649569936599116 - task: type: Reranking dataset: name: MTEB MindSmallReranking type: mteb/mind_small config: default split: test revision: 59042f120c80e8afa9cdbb224f67076cec0fc9a7 metrics: - type: main_score value: 33.05449204940555 - type: map value: 33.05449204940555 - type: mrr value: 34.32562058439585 - type: nAUC_map_diff1 value: 11.465656013162807 - type: nAUC_map_max value: -20.400088169502308 - type: nAUC_map_std value: -2.638964886362445 - type: nAUC_mrr_diff1 value: 10.644290702481207 - type: nAUC_mrr_max value: -15.304687384645769 - type: nAUC_mrr_std value: -0.519919931348978 - task: type: Retrieval dataset: name: MTEB NFCorpus type: mteb/nfcorpus config: default split: test revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 metrics: - type: main_score value: 41.998000000000005 - type: map_at_1 value: 6.907000000000001 - type: map_at_10 value: 16.397000000000002 - type: map_at_100 value: 21.69 - type: map_at_1000 value: 23.652 - type: map_at_20 value: 18.629 - type: map_at_3 value: 11.969000000000001 - type: map_at_5 value: 13.894 - type: mrr_at_1 value: 53.25077399380805 - type: mrr_at_10 value: 61.8561108653988 - type: mrr_at_100 value: 62.42447851935404 - type: mrr_at_1000 value: 62.459626424428095 - type: mrr_at_20 value: 62.287236389990696 - type: mrr_at_3 value: 60.42311661506711 - type: mrr_at_5 value: 61.36738906088753 - type: nauc_map_at_1000_diff1 value: 17.159461939643844 - type: nauc_map_at_1000_max value: 32.42764938789903 - type: nauc_map_at_1000_std value: 11.039427848422093 - type: nauc_map_at_100_diff1 value: 19.089532984187503 - type: nauc_map_at_100_max value: 31.96721085058713 - type: nauc_map_at_100_std value: 6.947468655726444 - type: nauc_map_at_10_diff1 value: 25.77255342629802 - type: nauc_map_at_10_max value: 26.163590320961543 - type: nauc_map_at_10_std value: -5.2588093720998375 - type: nauc_map_at_1_diff1 value: 46.31602607957798 - type: nauc_map_at_1_max value: 11.807757660801942 - type: nauc_map_at_1_std value: -13.984889089354317 - type: nauc_map_at_20_diff1 value: 22.308161130465365 - type: nauc_map_at_20_max value: 29.070587307827722 - type: nauc_map_at_20_std value: -1.0103056620851558 - type: nauc_map_at_3_diff1 value: 33.580827849617506 - type: nauc_map_at_3_max value: 17.661630885799042 - type: nauc_map_at_3_std value: -11.463282544041888 - type: nauc_map_at_5_diff1 value: 30.32603342696912 - type: nauc_map_at_5_max value: 20.938905485667245 - type: nauc_map_at_5_std value: -10.537086968155755 - type: nauc_mrr_at_1000_diff1 value: 24.45065397805829 - type: nauc_mrr_at_1000_max value: 48.17519860927417 - type: nauc_mrr_at_1000_std value: 30.350767549118903 - type: nauc_mrr_at_100_diff1 value: 24.444061606534486 - type: nauc_mrr_at_100_max value: 48.1922894212229 - type: nauc_mrr_at_100_std value: 30.379257816584094 - type: nauc_mrr_at_10_diff1 value: 24.25598717198779 - type: nauc_mrr_at_10_max value: 48.10437607774264 - type: nauc_mrr_at_10_std value: 30.090202482685996 - type: nauc_mrr_at_1_diff1 value: 26.907595285201264 - type: nauc_mrr_at_1_max value: 44.006974050369955 - type: nauc_mrr_at_1_std value: 26.921001962861062 - type: nauc_mrr_at_20_diff1 value: 24.462771570553738 - type: nauc_mrr_at_20_max value: 48.264688196799746 - type: nauc_mrr_at_20_std value: 30.498095141265914 - type: nauc_mrr_at_3_diff1 value: 24.76829388237229 - type: nauc_mrr_at_3_max value: 48.213758704739924 - type: nauc_mrr_at_3_std value: 30.1502853918892 - type: nauc_mrr_at_5_diff1 value: 24.476494932330247 - type: nauc_mrr_at_5_max value: 47.977250552198804 - type: nauc_mrr_at_5_std value: 29.65248143104835 - type: nauc_ndcg_at_1000_diff1 value: 13.055818920426246 - type: nauc_ndcg_at_1000_max value: 46.00986444256306 - type: nauc_ndcg_at_1000_std value: 29.622662054922085 - type: nauc_ndcg_at_100_diff1 value: 12.260551238228816 - type: nauc_ndcg_at_100_max value: 39.89783048267698 - type: nauc_ndcg_at_100_std value: 23.806961617956613 - type: nauc_ndcg_at_10_diff1 value: 11.002915931619567 - type: nauc_ndcg_at_10_max value: 39.79323759244374 - type: nauc_ndcg_at_10_std value: 23.053072152911046 - type: nauc_ndcg_at_1_diff1 value: 27.560910719974434 - type: nauc_ndcg_at_1_max value: 41.21084046258119 - type: nauc_ndcg_at_1_std value: 26.112891742912893 - type: nauc_ndcg_at_20_diff1 value: 10.085854089024496 - type: nauc_ndcg_at_20_max value: 37.88629173784684 - type: nauc_ndcg_at_20_std value: 23.17664322248358 - type: nauc_ndcg_at_3_diff1 value: 16.58969583405987 - type: nauc_ndcg_at_3_max value: 41.282222954101435 - type: nauc_ndcg_at_3_std value: 21.080670648392747 - type: nauc_ndcg_at_5_diff1 value: 13.893127947909885 - type: nauc_ndcg_at_5_max value: 40.21188015992804 - type: nauc_ndcg_at_5_std value: 21.417443978842652 - type: nauc_precision_at_1000_diff1 value: -17.227504530334564 - type: nauc_precision_at_1000_max value: 3.798554468439066 - type: nauc_precision_at_1000_std value: 35.73617809452683 - type: nauc_precision_at_100_diff1 value: -17.63388230218776 - type: nauc_precision_at_100_max value: 15.079399882407094 - type: nauc_precision_at_100_std value: 41.83698491321226 - type: nauc_precision_at_10_diff1 value: -11.850925959645156 - type: nauc_precision_at_10_max value: 35.93283968364352 - type: nauc_precision_at_10_std value: 34.391271855921296 - type: nauc_precision_at_1_diff1 value: 27.730860778824823 - type: nauc_precision_at_1_max value: 43.97462471516834 - type: nauc_precision_at_1_std value: 27.491068270978896 - type: nauc_precision_at_20_diff1 value: -14.281328840943347 - type: nauc_precision_at_20_max value: 29.469099781759006 - type: nauc_precision_at_20_std value: 38.54703022340941 - type: nauc_precision_at_3_diff1 value: 3.486986910413196 - type: nauc_precision_at_3_max value: 41.21107780473768 - type: nauc_precision_at_3_std value: 24.057479124531216 - type: nauc_precision_at_5_diff1 value: -3.0623787872866233 - type: nauc_precision_at_5_max value: 37.49266386466702 - type: nauc_precision_at_5_std value: 26.894454268004935 - type: nauc_recall_at_1000_diff1 value: -2.446891864334283 - type: nauc_recall_at_1000_max value: 23.867293584643377 - type: nauc_recall_at_1000_std value: 16.34707128224595 - type: nauc_recall_at_100_diff1 value: 4.891133690841179 - type: nauc_recall_at_100_max value: 24.56727964996522 - type: nauc_recall_at_100_std value: 9.847212953200797 - type: nauc_recall_at_10_diff1 value: 19.211912363585288 - type: nauc_recall_at_10_max value: 24.825344777920737 - type: nauc_recall_at_10_std value: -5.447989195041898 - type: nauc_recall_at_1_diff1 value: 46.31602607957798 - type: nauc_recall_at_1_max value: 11.807757660801942 - type: nauc_recall_at_1_std value: -13.984889089354317 - type: nauc_recall_at_20_diff1 value: 12.233372054304805 - type: nauc_recall_at_20_max value: 22.284108685207148 - type: nauc_recall_at_20_std value: -4.317138366746209 - type: nauc_recall_at_3_diff1 value: 28.394631527225815 - type: nauc_recall_at_3_max value: 15.593864852625462 - type: nauc_recall_at_3_std value: -12.383531804314593 - type: nauc_recall_at_5_diff1 value: 24.457441304950343 - type: nauc_recall_at_5_max value: 19.080049396281623 - type: nauc_recall_at_5_std value: -11.879747703626627 - type: ndcg_at_1 value: 51.548 - type: ndcg_at_10 value: 41.998000000000005 - type: ndcg_at_100 value: 39.626 - type: ndcg_at_1000 value: 48.707 - type: ndcg_at_20 value: 40.181 - type: ndcg_at_3 value: 48.06 - type: ndcg_at_5 value: 45.829 - type: precision_at_1 value: 52.941 - type: precision_at_10 value: 31.330999999999996 - type: precision_at_100 value: 10.421 - type: precision_at_1000 value: 2.428 - type: precision_at_20 value: 24.118000000000002 - type: precision_at_3 value: 45.408 - type: precision_at_5 value: 39.938 - type: recall_at_1 value: 6.907000000000001 - type: recall_at_10 value: 20.51 - type: recall_at_100 value: 40.857 - type: recall_at_1000 value: 73.616 - type: recall_at_20 value: 26.52 - type: recall_at_3 value: 13.267999999999999 - type: recall_at_5 value: 16.141 - task: type: Retrieval dataset: name: MTEB NQ type: mteb/nq config: default split: test revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 metrics: - type: main_score value: 71.8 - type: map_at_1 value: 47.629 - type: map_at_10 value: 64.846 - type: map_at_100 value: 65.40899999999999 - type: map_at_1000 value: 65.416 - type: map_at_20 value: 65.239 - type: map_at_3 value: 61.185 - type: map_at_5 value: 63.583 - type: mrr_at_1 value: 53.15758980301275 - type: mrr_at_10 value: 67.12880961577366 - type: mrr_at_100 value: 67.44006405426018 - type: mrr_at_1000 value: 67.44519150402294 - type: mrr_at_20 value: 67.34317135515428 - type: mrr_at_3 value: 64.5905755117805 - type: mrr_at_5 value: 66.24613750482806 - type: nauc_map_at_1000_diff1 value: 45.73812106517133 - type: nauc_map_at_1000_max value: 35.21262031755756 - type: nauc_map_at_1000_std value: -5.549443574026027 - type: nauc_map_at_100_diff1 value: 45.74254652176879 - type: nauc_map_at_100_max value: 35.22349167515518 - type: nauc_map_at_100_std value: -5.53697496044773 - type: nauc_map_at_10_diff1 value: 45.62837128377087 - type: nauc_map_at_10_max value: 35.3261562342222 - type: nauc_map_at_10_std value: -5.761924414031163 - type: nauc_map_at_1_diff1 value: 48.69187848570499 - type: nauc_map_at_1_max value: 28.687996096473476 - type: nauc_map_at_1_std value: -7.518605958272523 - type: nauc_map_at_20_diff1 value: 45.702303442220035 - type: nauc_map_at_20_max value: 35.30719944705456 - type: nauc_map_at_20_std value: -5.59505654742681 - type: nauc_map_at_3_diff1 value: 45.376813726832474 - type: nauc_map_at_3_max value: 34.68452149643597 - type: nauc_map_at_3_std value: -7.329014950379634 - type: nauc_map_at_5_diff1 value: 45.29528861989316 - type: nauc_map_at_5_max value: 35.35741440869229 - type: nauc_map_at_5_std value: -6.028788612259288 - type: nauc_mrr_at_1000_diff1 value: 46.11808147912517 - type: nauc_mrr_at_1000_max value: 35.59241850411947 - type: nauc_mrr_at_1000_std value: -3.4072428526109317 - type: nauc_mrr_at_100_diff1 value: 46.121345545514046 - type: nauc_mrr_at_100_max value: 35.60147795073431 - type: nauc_mrr_at_100_std value: -3.3965322447588826 - type: nauc_mrr_at_10_diff1 value: 46.0920068210502 - type: nauc_mrr_at_10_max value: 35.79649987854354 - type: nauc_mrr_at_10_std value: -3.339624589368137 - type: nauc_mrr_at_1_diff1 value: 49.101364605656194 - type: nauc_mrr_at_1_max value: 31.500796071482146 - type: nauc_mrr_at_1_std value: -4.183818500718156 - type: nauc_mrr_at_20_diff1 value: 46.088076630465594 - type: nauc_mrr_at_20_max value: 35.682131663053205 - type: nauc_mrr_at_20_std value: -3.35939023178519 - type: nauc_mrr_at_3_diff1 value: 45.47570812708642 - type: nauc_mrr_at_3_max value: 35.741892517632984 - type: nauc_mrr_at_3_std value: -4.135335963822013 - type: nauc_mrr_at_5_diff1 value: 45.78903474184014 - type: nauc_mrr_at_5_max value: 35.91273593700205 - type: nauc_mrr_at_5_std value: -3.467873421286869 - type: nauc_ndcg_at_1000_diff1 value: 45.5056583000012 - type: nauc_ndcg_at_1000_max value: 36.34328379251593 - type: nauc_ndcg_at_1000_std value: -4.0759698229323345 - type: nauc_ndcg_at_100_diff1 value: 45.61918946477166 - type: nauc_ndcg_at_100_max value: 36.675460335836235 - type: nauc_ndcg_at_100_std value: -3.6795334726235986 - type: nauc_ndcg_at_10_diff1 value: 45.15343994274541 - type: nauc_ndcg_at_10_max value: 37.48139242964657 - type: nauc_ndcg_at_10_std value: -4.287039084554882 - type: nauc_ndcg_at_1_diff1 value: 49.101364605656194 - type: nauc_ndcg_at_1_max value: 31.500796071482146 - type: nauc_ndcg_at_1_std value: -4.183818500718156 - type: nauc_ndcg_at_20_diff1 value: 45.310026313402375 - type: nauc_ndcg_at_20_max value: 37.32177497902133 - type: nauc_ndcg_at_20_std value: -3.8214360391282587 - type: nauc_ndcg_at_3_diff1 value: 44.27064370528994 - type: nauc_ndcg_at_3_max value: 36.380294033571396 - type: nauc_ndcg_at_3_std value: -6.844263370898355 - type: nauc_ndcg_at_5_diff1 value: 44.29933499225583 - type: nauc_ndcg_at_5_max value: 37.46477041822136 - type: nauc_ndcg_at_5_std value: -4.866548530467956 - type: nauc_precision_at_1000_diff1 value: -14.666553359142306 - type: nauc_precision_at_1000_max value: -0.5599759853201481 - type: nauc_precision_at_1000_std value: 16.8370925526591 - type: nauc_precision_at_100_diff1 value: -11.816251306246278 - type: nauc_precision_at_100_max value: 2.969819268208207 - type: nauc_precision_at_100_std value: 18.59422946634747 - type: nauc_precision_at_10_diff1 value: 1.2050200086029401 - type: nauc_precision_at_10_max value: 17.59930352911209 - type: nauc_precision_at_10_std value: 13.714495717588985 - type: nauc_precision_at_1_diff1 value: 49.101364605656194 - type: nauc_precision_at_1_max value: 31.500796071482146 - type: nauc_precision_at_1_std value: -4.183818500718156 - type: nauc_precision_at_20_diff1 value: -5.263476664822757 - type: nauc_precision_at_20_max value: 11.42004823600046 - type: nauc_precision_at_20_std value: 16.510514518664994 - type: nauc_precision_at_3_diff1 value: 20.116460379305828 - type: nauc_precision_at_3_max value: 31.32235038301311 - type: nauc_precision_at_3_std value: 2.7486717133871923 - type: nauc_precision_at_5_diff1 value: 9.57451645335723 - type: nauc_precision_at_5_max value: 25.28449126580587 - type: nauc_precision_at_5_std value: 9.955736162466767 - type: nauc_recall_at_1000_diff1 value: -21.632253065978794 - type: nauc_recall_at_1000_max value: 70.14409090958776 - type: nauc_recall_at_1000_std value: 65.61658090892989 - type: nauc_recall_at_100_diff1 value: 51.83161124806711 - type: nauc_recall_at_100_max value: 77.49921361841523 - type: nauc_recall_at_100_std value: 48.352508746719444 - type: nauc_recall_at_10_diff1 value: 39.86695231362791 - type: nauc_recall_at_10_max value: 50.12029094799474 - type: nauc_recall_at_10_std value: 0.1650940628131058 - type: nauc_recall_at_1_diff1 value: 48.69187848570499 - type: nauc_recall_at_1_max value: 28.687996096473476 - type: nauc_recall_at_1_std value: -7.518605958272523 - type: nauc_recall_at_20_diff1 value: 39.14155398061627 - type: nauc_recall_at_20_max value: 56.78559423716229 - type: nauc_recall_at_20_std value: 7.9728224572344075 - type: nauc_recall_at_3_diff1 value: 38.69589523432158 - type: nauc_recall_at_3_max value: 39.53271258375579 - type: nauc_recall_at_3_std value: -8.646925065787512 - type: nauc_recall_at_5_diff1 value: 37.45922652959002 - type: nauc_recall_at_5_max value: 44.4911958995867 - type: nauc_recall_at_5_std value: -3.5659842556375594 - type: ndcg_at_1 value: 53.15800000000001 - type: ndcg_at_10 value: 71.8 - type: ndcg_at_100 value: 73.85199999999999 - type: ndcg_at_1000 value: 74.017 - type: ndcg_at_20 value: 72.933 - type: ndcg_at_3 value: 65.479 - type: ndcg_at_5 value: 69.182 - type: precision_at_1 value: 53.15800000000001 - type: precision_at_10 value: 10.805 - type: precision_at_100 value: 1.2 - type: precision_at_1000 value: 0.122 - type: precision_at_20 value: 5.694 - type: precision_at_3 value: 28.939999999999998 - type: precision_at_5 value: 19.641000000000002 - type: recall_at_1 value: 47.629 - type: recall_at_10 value: 90.204 - type: recall_at_100 value: 98.66 - type: recall_at_1000 value: 99.874 - type: recall_at_20 value: 94.24 - type: recall_at_3 value: 74.394 - type: recall_at_5 value: 82.711 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval type: mteb/quora config: default split: test revision: e4e08e0b7dbe3c8700f0daef558ff32256715259 metrics: - type: main_score value: 90.025 - type: map_at_1 value: 72.222 - type: map_at_10 value: 86.58500000000001 - type: map_at_100 value: 87.176 - type: map_at_1000 value: 87.188 - type: map_at_20 value: 86.97399999999999 - type: map_at_3 value: 83.736 - type: map_at_5 value: 85.554 - type: mrr_at_1 value: 83.04 - type: mrr_at_10 value: 89.05599603174585 - type: mrr_at_100 value: 89.12398891419457 - type: mrr_at_1000 value: 89.12434072241001 - type: mrr_at_20 value: 89.10416280692111 - type: mrr_at_3 value: 88.23833333333312 - type: mrr_at_5 value: 88.82233333333308 - type: nauc_map_at_1000_diff1 value: 78.29348113313218 - type: nauc_map_at_1000_max value: 32.31386754277228 - type: nauc_map_at_1000_std value: -50.47543661484052 - type: nauc_map_at_100_diff1 value: 78.29618548618575 - type: nauc_map_at_100_max value: 32.301475680947846 - type: nauc_map_at_100_std value: -50.50303428814228 - type: nauc_map_at_10_diff1 value: 78.47383776440803 - type: nauc_map_at_10_max value: 31.839339990133563 - type: nauc_map_at_10_std value: -52.832713555976 - type: nauc_map_at_1_diff1 value: 82.46330147467418 - type: nauc_map_at_1_max value: 23.497664918373538 - type: nauc_map_at_1_std value: -43.824657665520704 - type: nauc_map_at_20_diff1 value: 78.34772176474422 - type: nauc_map_at_20_max value: 32.16495182893947 - type: nauc_map_at_20_std value: -51.503292726558605 - type: nauc_map_at_3_diff1 value: 79.07823813069432 - type: nauc_map_at_3_max value: 29.395911687513976 - type: nauc_map_at_3_std value: -54.16377546873304 - type: nauc_map_at_5_diff1 value: 78.73076619520454 - type: nauc_map_at_5_max value: 30.700453118585237 - type: nauc_map_at_5_std value: -54.130514177664054 - type: nauc_mrr_at_1000_diff1 value: 79.04736184471865 - type: nauc_mrr_at_1000_max value: 34.43004593837643 - type: nauc_mrr_at_1000_std value: -46.137269068195316 - type: nauc_mrr_at_100_diff1 value: 79.04698704288086 - type: nauc_mrr_at_100_max value: 34.4305553741175 - type: nauc_mrr_at_100_std value: -46.13786687786434 - type: nauc_mrr_at_10_diff1 value: 79.04490677485934 - type: nauc_mrr_at_10_max value: 34.38170181522227 - type: nauc_mrr_at_10_std value: -46.38129875681807 - type: nauc_mrr_at_1_diff1 value: 79.87159215719124 - type: nauc_mrr_at_1_max value: 34.05882339253136 - type: nauc_mrr_at_1_std value: -43.56093395137571 - type: nauc_mrr_at_20_diff1 value: 79.04384174535653 - type: nauc_mrr_at_20_max value: 34.442136494675005 - type: nauc_mrr_at_20_std value: -46.205458519638654 - type: nauc_mrr_at_3_diff1 value: 78.78154519155487 - type: nauc_mrr_at_3_max value: 34.74995000500305 - type: nauc_mrr_at_3_std value: -46.36264203155416 - type: nauc_mrr_at_5_diff1 value: 79.02631187177 - type: nauc_mrr_at_5_max value: 34.538698249632205 - type: nauc_mrr_at_5_std value: -46.468881576157465 - type: nauc_ndcg_at_1000_diff1 value: 78.25260097014645 - type: nauc_ndcg_at_1000_max value: 33.68584498704271 - type: nauc_ndcg_at_1000_std value: -48.44716779494868 - type: nauc_ndcg_at_100_diff1 value: 78.25115412256716 - type: nauc_ndcg_at_100_max value: 33.63652663447088 - type: nauc_ndcg_at_100_std value: -48.489243909024715 - type: nauc_ndcg_at_10_diff1 value: 78.23875101557334 - type: nauc_ndcg_at_10_max value: 32.65217430043823 - type: nauc_ndcg_at_10_std value: -52.57770468845309 - type: nauc_ndcg_at_1_diff1 value: 79.87159215719124 - type: nauc_ndcg_at_1_max value: 34.05882339253136 - type: nauc_ndcg_at_1_std value: -43.56093395137571 - type: nauc_ndcg_at_20_diff1 value: 78.23478552311765 - type: nauc_ndcg_at_20_max value: 33.30691737901109 - type: nauc_ndcg_at_20_std value: -50.78412614854527 - type: nauc_ndcg_at_3_diff1 value: 77.66134485470224 - type: nauc_ndcg_at_3_max value: 32.19504710373125 - type: nauc_ndcg_at_3_std value: -52.01636728550155 - type: nauc_ndcg_at_5_diff1 value: 78.04734137324255 - type: nauc_ndcg_at_5_max value: 31.94593625591248 - type: nauc_ndcg_at_5_std value: -53.02169800690546 - type: nauc_precision_at_1000_diff1 value: -45.771948123542636 - type: nauc_precision_at_1000_max value: -5.182406190477681 - type: nauc_precision_at_1000_std value: 41.14460438707817 - type: nauc_precision_at_100_diff1 value: -45.64767154261461 - type: nauc_precision_at_100_max value: -5.046308286851713 - type: nauc_precision_at_100_std value: 41.07186716587844 - type: nauc_precision_at_10_diff1 value: -42.26779562305825 - type: nauc_precision_at_10_max value: -1.1264852893323076 - type: nauc_precision_at_10_std value: 27.62275729822392 - type: nauc_precision_at_1_diff1 value: 79.87159215719124 - type: nauc_precision_at_1_max value: 34.05882339253136 - type: nauc_precision_at_1_std value: -43.56093395137571 - type: nauc_precision_at_20_diff1 value: -44.24293221128388 - type: nauc_precision_at_20_max value: -3.1345628837361867 - type: nauc_precision_at_20_std value: 34.23625492740366 - type: nauc_precision_at_3_diff1 value: -24.925251389823348 - type: nauc_precision_at_3_max value: 6.622188833369412 - type: nauc_precision_at_3_std value: 6.424741786858512 - type: nauc_precision_at_5_diff1 value: -36.1407949990387 - type: nauc_precision_at_5_max value: 1.7533948968374462 - type: nauc_precision_at_5_std value: 17.914083278982634 - type: nauc_recall_at_1000_diff1 value: 52.26815466244496 - type: nauc_recall_at_1000_max value: 69.73611104239443 - type: nauc_recall_at_1000_std value: 73.18969965863008 - type: nauc_recall_at_100_diff1 value: 70.80557513785271 - type: nauc_recall_at_100_max value: 33.333440086544556 - type: nauc_recall_at_100_std value: -38.75992366905504 - type: nauc_recall_at_10_diff1 value: 74.45948457438163 - type: nauc_recall_at_10_max value: 26.64948512428989 - type: nauc_recall_at_10_std value: -82.90334292052363 - type: nauc_recall_at_1_diff1 value: 82.46330147467418 - type: nauc_recall_at_1_max value: 23.497664918373538 - type: nauc_recall_at_1_std value: -43.824657665520704 - type: nauc_recall_at_20_diff1 value: 73.80140280887753 - type: nauc_recall_at_20_max value: 30.361616426734965 - type: nauc_recall_at_20_std value: -81.1418804447414 - type: nauc_recall_at_3_diff1 value: 75.19854736087834 - type: nauc_recall_at_3_max value: 26.12298005045584 - type: nauc_recall_at_3_std value: -63.42583714745169 - type: nauc_recall_at_5_diff1 value: 74.16423451950358 - type: nauc_recall_at_5_max value: 25.552390331018987 - type: nauc_recall_at_5_std value: -71.15891947773912 - type: ndcg_at_1 value: 83.04 - type: ndcg_at_10 value: 90.025 - type: ndcg_at_100 value: 91.006 - type: ndcg_at_1000 value: 91.061 - type: ndcg_at_20 value: 90.556 - type: ndcg_at_3 value: 87.493 - type: ndcg_at_5 value: 88.955 - type: precision_at_1 value: 83.04 - type: precision_at_10 value: 13.667000000000002 - type: precision_at_100 value: 1.542 - type: precision_at_1000 value: 0.157 - type: precision_at_20 value: 7.221 - type: precision_at_3 value: 38.433 - type: precision_at_5 value: 25.228 - type: recall_at_1 value: 72.222 - type: recall_at_10 value: 96.604 - type: recall_at_100 value: 99.786 - type: recall_at_1000 value: 99.996 - type: recall_at_20 value: 98.253 - type: recall_at_3 value: 89.276 - type: recall_at_5 value: 93.46 - task: type: Clustering dataset: name: MTEB RedditClustering type: mteb/reddit-clustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: main_score value: 72.86492101891123 - type: v_measure value: 72.86492101891123 - type: v_measure_std value: 2.778711445144635 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P type: mteb/reddit-clustering-p2p config: default split: test revision: 385e3cb46b4cfa89021f56c4380204149d0efe33 metrics: - type: main_score value: 75.27316726548479 - type: v_measure value: 75.27316726548479 - type: v_measure_std value: 8.87871936725338 - task: type: Retrieval dataset: name: MTEB SCIDOCS type: mteb/scidocs config: default split: test revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88 metrics: - type: main_score value: 26.638 - type: map_at_1 value: 6.128 - type: map_at_10 value: 16.472 - type: map_at_100 value: 19.522000000000002 - type: map_at_1000 value: 19.898 - type: map_at_20 value: 18.098 - type: map_at_3 value: 11.283 - type: map_at_5 value: 13.771 - type: mrr_at_1 value: 30.2 - type: mrr_at_10 value: 42.621150793650735 - type: mrr_at_100 value: 43.740858712021954 - type: mrr_at_1000 value: 43.762699500220904 - type: mrr_at_20 value: 43.383639927753634 - type: mrr_at_3 value: 38.83333333333331 - type: mrr_at_5 value: 41.14833333333326 - type: nauc_map_at_1000_diff1 value: 13.13534664124808 - type: nauc_map_at_1000_max value: 29.346654566149795 - type: nauc_map_at_1000_std value: 18.08121186982413 - type: nauc_map_at_100_diff1 value: 13.098072728041538 - type: nauc_map_at_100_max value: 29.299084480697523 - type: nauc_map_at_100_std value: 17.961620202918464 - type: nauc_map_at_10_diff1 value: 14.001743720394682 - type: nauc_map_at_10_max value: 28.04128290996403 - type: nauc_map_at_10_std value: 13.744481555974716 - type: nauc_map_at_1_diff1 value: 22.1926640424872 - type: nauc_map_at_1_max value: 21.32609279586034 - type: nauc_map_at_1_std value: 6.566596302915438 - type: nauc_map_at_20_diff1 value: 13.57313142419664 - type: nauc_map_at_20_max value: 28.93840146319476 - type: nauc_map_at_20_std value: 16.50869367365676 - type: nauc_map_at_3_diff1 value: 17.707700541948462 - type: nauc_map_at_3_max value: 26.058174051376238 - type: nauc_map_at_3_std value: 9.943924560735267 - type: nauc_map_at_5_diff1 value: 17.11844492157723 - type: nauc_map_at_5_max value: 27.865247403049388 - type: nauc_map_at_5_std value: 11.372588172121546 - type: nauc_mrr_at_1000_diff1 value: 21.11248719936198 - type: nauc_mrr_at_1000_max value: 26.734172102201466 - type: nauc_mrr_at_1000_std value: 11.766121765437228 - type: nauc_mrr_at_100_diff1 value: 21.107109982277702 - type: nauc_mrr_at_100_max value: 26.741616065723267 - type: nauc_mrr_at_100_std value: 11.789802686224208 - type: nauc_mrr_at_10_diff1 value: 20.74108639793207 - type: nauc_mrr_at_10_max value: 26.920838463358333 - type: nauc_mrr_at_10_std value: 11.849217361926522 - type: nauc_mrr_at_1_diff1 value: 22.177437860573356 - type: nauc_mrr_at_1_max value: 21.88074521417754 - type: nauc_mrr_at_1_std value: 6.776011900101789 - type: nauc_mrr_at_20_diff1 value: 21.126633710175994 - type: nauc_mrr_at_20_max value: 26.860736480370974 - type: nauc_mrr_at_20_std value: 11.815411633726338 - type: nauc_mrr_at_3_diff1 value: 21.689245200066466 - type: nauc_mrr_at_3_max value: 26.187305092831625 - type: nauc_mrr_at_3_std value: 10.895380313134332 - type: nauc_mrr_at_5_diff1 value: 20.898811082479778 - type: nauc_mrr_at_5_max value: 26.939217247104036 - type: nauc_mrr_at_5_std value: 11.77832949822472 - type: nauc_ndcg_at_1000_diff1 value: 13.251184947898546 - type: nauc_ndcg_at_1000_max value: 30.879594164526146 - type: nauc_ndcg_at_1000_std value: 23.125206047366625 - type: nauc_ndcg_at_100_diff1 value: 12.549100649053676 - type: nauc_ndcg_at_100_max value: 30.634680845419123 - type: nauc_ndcg_at_100_std value: 23.296226055422984 - type: nauc_ndcg_at_10_diff1 value: 14.475144549294322 - type: nauc_ndcg_at_10_max value: 29.450349815417336 - type: nauc_ndcg_at_10_std value: 15.94068314781612 - type: nauc_ndcg_at_1_diff1 value: 22.177437860573356 - type: nauc_ndcg_at_1_max value: 21.88074521417754 - type: nauc_ndcg_at_1_std value: 6.776011900101789 - type: nauc_ndcg_at_20_diff1 value: 14.173669585802266 - type: nauc_ndcg_at_20_max value: 30.475890854725 - type: nauc_ndcg_at_20_std value: 19.863898148221704 - type: nauc_ndcg_at_3_diff1 value: 18.93971261196868 - type: nauc_ndcg_at_3_max value: 27.3707298720736 - type: nauc_ndcg_at_3_std value: 11.439810510051224 - type: nauc_ndcg_at_5_diff1 value: 17.89535958094687 - type: nauc_ndcg_at_5_max value: 29.272740466638425 - type: nauc_ndcg_at_5_std value: 13.402467626635909 - type: nauc_precision_at_1000_diff1 value: -3.811547048784123 - type: nauc_precision_at_1000_max value: 22.55165337197117 - type: nauc_precision_at_1000_std value: 35.98524999650108 - type: nauc_precision_at_100_diff1 value: 0.6474234774922896 - type: nauc_precision_at_100_max value: 25.06920726527032 - type: nauc_precision_at_100_std value: 32.31439698982313 - type: nauc_precision_at_10_diff1 value: 7.943127218139508 - type: nauc_precision_at_10_max value: 28.571937636787197 - type: nauc_precision_at_10_std value: 18.8472620918488 - type: nauc_precision_at_1_diff1 value: 22.177437860573356 - type: nauc_precision_at_1_max value: 21.88074521417754 - type: nauc_precision_at_1_std value: 6.776011900101789 - type: nauc_precision_at_20_diff1 value: 6.981574259607366 - type: nauc_precision_at_20_max value: 28.986094397038727 - type: nauc_precision_at_20_std value: 25.83129974001146 - type: nauc_precision_at_3_diff1 value: 17.197490724039355 - type: nauc_precision_at_3_max value: 29.17569320583099 - type: nauc_precision_at_3_std value: 13.430554945991846 - type: nauc_precision_at_5_diff1 value: 14.952364330739362 - type: nauc_precision_at_5_max value: 31.053243354846977 - type: nauc_precision_at_5_std value: 15.856312752807822 - type: nauc_recall_at_1000_diff1 value: -4.8224253128926975 - type: nauc_recall_at_1000_max value: 21.3989024429911 - type: nauc_recall_at_1000_std value: 39.152234275603604 - type: nauc_recall_at_100_diff1 value: 0.11936808422867201 - type: nauc_recall_at_100_max value: 24.261739241957823 - type: nauc_recall_at_100_std value: 32.62984573938928 - type: nauc_recall_at_10_diff1 value: 7.851256165018388 - type: nauc_recall_at_10_max value: 27.936406600938746 - type: nauc_recall_at_10_std value: 18.683634320636113 - type: nauc_recall_at_1_diff1 value: 22.1926640424872 - type: nauc_recall_at_1_max value: 21.32609279586034 - type: nauc_recall_at_1_std value: 6.566596302915438 - type: nauc_recall_at_20_diff1 value: 6.8107211705182165 - type: nauc_recall_at_20_max value: 28.286284094687787 - type: nauc_recall_at_20_std value: 25.932013268120862 - type: nauc_recall_at_3_diff1 value: 17.04156818427151 - type: nauc_recall_at_3_max value: 28.645439108719216 - type: nauc_recall_at_3_std value: 13.346047828494411 - type: nauc_recall_at_5_diff1 value: 14.906284329771822 - type: nauc_recall_at_5_max value: 30.58628602415921 - type: nauc_recall_at_5_std value: 15.755157478191755 - type: ndcg_at_1 value: 30.2 - type: ndcg_at_10 value: 26.638 - type: ndcg_at_100 value: 37.135 - type: ndcg_at_1000 value: 42.576 - type: ndcg_at_20 value: 30.75 - type: ndcg_at_3 value: 24.675 - type: ndcg_at_5 value: 21.836 - type: precision_at_1 value: 30.2 - type: precision_at_10 value: 14.06 - type: precision_at_100 value: 2.904 - type: precision_at_1000 value: 0.42 - type: precision_at_20 value: 9.4 - type: precision_at_3 value: 23.233 - type: precision_at_5 value: 19.439999999999998 - type: recall_at_1 value: 6.128 - type: recall_at_10 value: 28.471999999999998 - type: recall_at_100 value: 58.952000000000005 - type: recall_at_1000 value: 85.137 - type: recall_at_20 value: 38.17 - type: recall_at_3 value: 14.127999999999998 - type: recall_at_5 value: 19.673 - task: type: STS dataset: name: MTEB SICK-R type: mteb/sickr-sts config: default split: test revision: 20a6d6f312dd54037fe07a32d58e5e168867909d metrics: - type: cosine_pearson value: 86.86608529160739 - type: cosine_spearman value: 82.88625166203383 - type: euclidean_pearson value: 84.15494418856142 - type: euclidean_spearman value: 82.88449294676421 - type: main_score value: 82.88625166203383 - type: manhattan_pearson value: 84.39068623474428 - type: manhattan_spearman value: 82.88065412169463 - type: pearson value: 86.86608529160739 - type: spearman value: 82.88625166203383 - task: type: STS dataset: name: MTEB STS12 type: mteb/sts12-sts config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cosine_pearson value: 87.0445014940449 - type: cosine_spearman value: 80.0880365116599 - type: euclidean_pearson value: 83.80250772928852 - type: euclidean_spearman value: 80.0892465260778 - type: main_score value: 80.0880365116599 - type: manhattan_pearson value: 83.96793981929336 - type: manhattan_spearman value: 80.24881789268238 - type: pearson value: 87.0445014940449 - type: spearman value: 80.0880365116599 - task: type: STS dataset: name: MTEB STS13 type: mteb/sts13-sts config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cosine_pearson value: 89.33900828959968 - type: cosine_spearman value: 89.68256358526733 - type: euclidean_pearson value: 89.29188708262265 - type: euclidean_spearman value: 89.68204344658601 - type: main_score value: 89.68256358526733 - type: manhattan_pearson value: 89.13996588193149 - type: manhattan_spearman value: 89.61372804425623 - type: pearson value: 89.33900828959968 - type: spearman value: 89.68256358526733 - task: type: STS dataset: name: MTEB STS14 type: mteb/sts14-sts config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cosine_pearson value: 86.42029843639123 - type: cosine_spearman value: 85.0707889220723 - type: euclidean_pearson value: 85.75114239552562 - type: euclidean_spearman value: 85.06858160270725 - type: main_score value: 85.0707889220723 - type: manhattan_pearson value: 85.86461900459038 - type: manhattan_spearman value: 85.28671103475605 - type: pearson value: 86.42029843639123 - type: spearman value: 85.0707889220723 - task: type: STS dataset: name: MTEB STS15 type: mteb/sts15-sts config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cosine_pearson value: 88.3660081271444 - type: cosine_spearman value: 89.39375083609528 - type: euclidean_pearson value: 89.21818482894895 - type: euclidean_spearman value: 89.39361588875443 - type: main_score value: 89.39375083609528 - type: manhattan_pearson value: 89.53535068014057 - type: manhattan_spearman value: 89.81077130567752 - type: pearson value: 88.3660081271444 - type: spearman value: 89.39375083609528 - task: type: STS dataset: name: MTEB STS16 type: mteb/sts16-sts config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cosine_pearson value: 85.60708247171874 - type: cosine_spearman value: 87.15234952832193 - type: euclidean_pearson value: 86.21743555548137 - type: euclidean_spearman value: 87.14450217418016 - type: main_score value: 87.15234952832193 - type: manhattan_pearson value: 86.2467748746084 - type: manhattan_spearman value: 87.2197479717654 - type: pearson value: 85.60708247171874 - type: spearman value: 87.15234952832193 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: cosine_pearson value: 91.25898556808458 - type: cosine_spearman value: 91.35372390581641 - type: euclidean_pearson value: 91.319520321348 - type: euclidean_spearman value: 91.30821135416925 - type: main_score value: 91.35372390581641 - type: manhattan_pearson value: 91.14800959939069 - type: manhattan_spearman value: 91.09775424245629 - type: pearson value: 91.25898556808458 - type: spearman value: 91.35372390581641 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: cosine_pearson value: 67.61637111515797 - type: cosine_spearman value: 68.10379096526697 - type: euclidean_pearson value: 69.2652309491375 - type: euclidean_spearman value: 68.18436357033228 - type: main_score value: 68.10379096526697 - type: manhattan_pearson value: 69.52531340510775 - type: manhattan_spearman value: 68.17874790391862 - type: pearson value: 67.61637111515797 - type: spearman value: 68.10379096526697 - task: type: STS dataset: name: MTEB STSBenchmark type: mteb/stsbenchmark-sts config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cosine_pearson value: 87.81592853782297 - type: cosine_spearman value: 88.2302550329183 - type: euclidean_pearson value: 88.01165144519526 - type: euclidean_spearman value: 88.23342148890097 - type: main_score value: 88.2302550329183 - type: manhattan_pearson value: 88.148592564938 - type: manhattan_spearman value: 88.49226317320988 - type: pearson value: 87.81592853782297 - type: spearman value: 88.2302550329183 - task: type: Reranking dataset: name: MTEB SciDocsRR type: mteb/scidocs-reranking config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: main_score value: 89.196009707431 - type: map value: 89.196009707431 - type: mrr value: 97.07198121413808 - type: nAUC_map_diff1 value: -14.066667940115352 - type: nAUC_map_max value: 49.73702475027407 - type: nAUC_map_std value: 64.0986775782592 - type: nAUC_mrr_diff1 value: 21.96846389417319 - type: nAUC_mrr_max value: 86.38341077184032 - type: nAUC_mrr_std value: 75.38945014727746 - task: type: Retrieval dataset: name: MTEB SciFact type: mteb/scifact config: default split: test revision: 0228b52cf27578f30900b9e5271d331663a030d7 metrics: - type: main_score value: 80.08999999999999 - type: map_at_1 value: 63.161 - type: map_at_10 value: 75.163 - type: map_at_100 value: 75.408 - type: map_at_1000 value: 75.409 - type: map_at_20 value: 75.332 - type: map_at_3 value: 71.839 - type: map_at_5 value: 74.32600000000001 - type: mrr_at_1 value: 66.33333333333333 - type: mrr_at_10 value: 75.95978835978836 - type: mrr_at_100 value: 76.15647881281473 - type: mrr_at_1000 value: 76.15736533763744 - type: mrr_at_20 value: 76.08557368557368 - type: mrr_at_3 value: 73.55555555555556 - type: mrr_at_5 value: 75.4888888888889 - type: nauc_map_at_1000_diff1 value: 77.31229383811176 - type: nauc_map_at_1000_max value: 58.848319058605156 - type: nauc_map_at_1000_std value: -14.290090263454985 - type: nauc_map_at_100_diff1 value: 77.31325400213969 - type: nauc_map_at_100_max value: 58.848885054155275 - type: nauc_map_at_100_std value: -14.285806618869273 - type: nauc_map_at_10_diff1 value: 77.1806705504232 - type: nauc_map_at_10_max value: 59.02905805134415 - type: nauc_map_at_10_std value: -14.132954900037467 - type: nauc_map_at_1_diff1 value: 81.03932970557837 - type: nauc_map_at_1_max value: 49.02073230264529 - type: nauc_map_at_1_std value: -22.977452975845512 - type: nauc_map_at_20_diff1 value: 77.22581364818562 - type: nauc_map_at_20_max value: 58.90740400399768 - type: nauc_map_at_20_std value: -14.245079150986745 - type: nauc_map_at_3_diff1 value: 76.99793243255563 - type: nauc_map_at_3_max value: 54.9930733886623 - type: nauc_map_at_3_std value: -19.297708446082407 - type: nauc_map_at_5_diff1 value: 77.1671608360295 - type: nauc_map_at_5_max value: 57.27757489519526 - type: nauc_map_at_5_std value: -15.446338357667708 - type: nauc_mrr_at_1000_diff1 value: 77.4806080821202 - type: nauc_mrr_at_1000_max value: 60.9213776129792 - type: nauc_mrr_at_1000_std value: -12.139599632228343 - type: nauc_mrr_at_100_diff1 value: 77.48158073865281 - type: nauc_mrr_at_100_max value: 60.9218657185361 - type: nauc_mrr_at_100_std value: -12.13532070453677 - type: nauc_mrr_at_10_diff1 value: 77.32428546014407 - type: nauc_mrr_at_10_max value: 61.018407010343466 - type: nauc_mrr_at_10_std value: -12.143193773309347 - type: nauc_mrr_at_1_diff1 value: 80.99806778887115 - type: nauc_mrr_at_1_max value: 59.17855969530095 - type: nauc_mrr_at_1_std value: -12.30545640831458 - type: nauc_mrr_at_20_diff1 value: 77.3811067653992 - type: nauc_mrr_at_20_max value: 60.9648880366335 - type: nauc_mrr_at_20_std value: -12.124066076541853 - type: nauc_mrr_at_3_diff1 value: 77.31304316321959 - type: nauc_mrr_at_3_max value: 60.75536766404163 - type: nauc_mrr_at_3_std value: -12.997876030849623 - type: nauc_mrr_at_5_diff1 value: 77.12952864141742 - type: nauc_mrr_at_5_max value: 60.995943754968685 - type: nauc_mrr_at_5_std value: -11.353447465605694 - type: nauc_ndcg_at_1000_diff1 value: 76.81788665683746 - type: nauc_ndcg_at_1000_max value: 60.35947755262391 - type: nauc_ndcg_at_1000_std value: -12.884942372460362 - type: nauc_ndcg_at_100_diff1 value: 76.87388230365198 - type: nauc_ndcg_at_100_max value: 60.38813162962434 - type: nauc_ndcg_at_100_std value: -12.64384717800478 - type: nauc_ndcg_at_10_diff1 value: 75.87713506026317 - type: nauc_ndcg_at_10_max value: 61.39356554675667 - type: nauc_ndcg_at_10_std value: -12.144227584144218 - type: nauc_ndcg_at_1_diff1 value: 80.99806778887115 - type: nauc_ndcg_at_1_max value: 59.17855969530095 - type: nauc_ndcg_at_1_std value: -12.30545640831458 - type: nauc_ndcg_at_20_diff1 value: 76.09913944506627 - type: nauc_ndcg_at_20_max value: 61.01644448834147 - type: nauc_ndcg_at_20_std value: -12.456209267623857 - type: nauc_ndcg_at_3_diff1 value: 75.52717946614608 - type: nauc_ndcg_at_3_max value: 58.96433090721983 - type: nauc_ndcg_at_3_std value: -15.849280494339556 - type: nauc_ndcg_at_5_diff1 value: 75.69026981016921 - type: nauc_ndcg_at_5_max value: 58.924044405851326 - type: nauc_ndcg_at_5_std value: -13.182728827923107 - type: nauc_precision_at_1000_diff1 value: -31.634022001609914 - type: nauc_precision_at_1000_max value: 31.46271490784504 - type: nauc_precision_at_1000_std value: 60.44801276891442 - type: nauc_precision_at_100_diff1 value: -29.722363469948103 - type: nauc_precision_at_100_max value: 32.05464592020074 - type: nauc_precision_at_100_std value: 60.832570595613554 - type: nauc_precision_at_10_diff1 value: -11.91731376599939 - type: nauc_precision_at_10_max value: 45.43646553157129 - type: nauc_precision_at_10_std value: 52.962408871791276 - type: nauc_precision_at_1_diff1 value: 80.99806778887115 - type: nauc_precision_at_1_max value: 59.17855969530095 - type: nauc_precision_at_1_std value: -12.30545640831458 - type: nauc_precision_at_20_diff1 value: -18.43293701721667 - type: nauc_precision_at_20_max value: 39.53434874203934 - type: nauc_precision_at_20_std value: 53.6291982468461 - type: nauc_precision_at_3_diff1 value: 30.84789043003892 - type: nauc_precision_at_3_max value: 55.660727758110376 - type: nauc_precision_at_3_std value: 17.87243920840355 - type: nauc_precision_at_5_diff1 value: 4.099395181445625 - type: nauc_precision_at_5_max value: 50.346770968709386 - type: nauc_precision_at_5_std value: 44.66722483255029 - type: nauc_recall_at_1000_diff1 value: .nan - type: nauc_recall_at_1000_max value: .nan - type: nauc_recall_at_1000_std value: .nan - type: nauc_recall_at_100_diff1 value: 100.0 - type: nauc_recall_at_100_max value: 72.2222222222207 - type: nauc_recall_at_100_std value: 86.92810457516407 - type: nauc_recall_at_10_diff1 value: 62.18887555022005 - type: nauc_recall_at_10_max value: 75.14339068960916 - type: nauc_recall_at_10_std value: -1.4912631719357108 - type: nauc_recall_at_1_diff1 value: 81.03932970557837 - type: nauc_recall_at_1_max value: 49.02073230264529 - type: nauc_recall_at_1_std value: -22.977452975845512 - type: nauc_recall_at_20_diff1 value: 59.27414444038499 - type: nauc_recall_at_20_max value: 76.32241302318047 - type: nauc_recall_at_20_std value: -0.8322169447488666 - type: nauc_recall_at_3_diff1 value: 69.58783002593157 - type: nauc_recall_at_3_max value: 55.89660919896563 - type: nauc_recall_at_3_std value: -21.183005510917862 - type: nauc_recall_at_5_diff1 value: 65.53660499878802 - type: nauc_recall_at_5_max value: 58.218018535135805 - type: nauc_recall_at_5_std value: -8.328952210032455 - type: ndcg_at_1 value: 66.333 - type: ndcg_at_10 value: 80.08999999999999 - type: ndcg_at_100 value: 81.24900000000001 - type: ndcg_at_1000 value: 81.28800000000001 - type: ndcg_at_20 value: 80.625 - type: ndcg_at_3 value: 74.98700000000001 - type: ndcg_at_5 value: 78.553 - type: precision_at_1 value: 66.333 - type: precision_at_10 value: 10.667 - type: precision_at_100 value: 1.127 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_20 value: 5.45 - type: precision_at_3 value: 29.555999999999997 - type: precision_at_5 value: 20.133000000000003 - type: recall_at_1 value: 63.161 - type: recall_at_10 value: 94.167 - type: recall_at_100 value: 99.667 - type: recall_at_1000 value: 100.0 - type: recall_at_20 value: 96.167 - type: recall_at_3 value: 80.972 - type: recall_at_5 value: 89.90599999999999 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cosine_accuracy value: 99.81881188118813 - type: cosine_accuracy_threshold value: 85.55081486701965 - type: cosine_ap value: 96.0359661816236 - type: cosine_f1 value: 90.6584992343032 - type: cosine_f1_threshold value: 84.82859134674072 - type: cosine_precision value: 92.59645464025026 - type: cosine_recall value: 88.8 - type: dot_accuracy value: 99.81881188118813 - type: dot_accuracy_threshold value: 84.91908311843872 - type: dot_ap value: 96.05740121094365 - type: dot_f1 value: 90.81885856079404 - type: dot_f1_threshold value: 83.84919166564941 - type: dot_precision value: 90.14778325123153 - type: dot_recall value: 91.5 - type: euclidean_accuracy value: 99.82079207920792 - type: euclidean_accuracy_threshold value: 54.49706315994263 - type: euclidean_ap value: 96.03223527068818 - type: euclidean_f1 value: 90.72270630445925 - type: euclidean_f1_threshold value: 54.49706315994263 - type: euclidean_precision value: 93.05993690851734 - type: euclidean_recall value: 88.5 - type: main_score value: 96.32671902439806 - type: manhattan_accuracy value: 99.83267326732673 - type: manhattan_accuracy_threshold value: 3818.192672729492 - type: manhattan_ap value: 96.32671902439806 - type: manhattan_f1 value: 91.52032112393378 - type: manhattan_f1_threshold value: 3818.192672729492 - type: manhattan_precision value: 91.8429003021148 - type: manhattan_recall value: 91.2 - type: max_ap value: 96.32671902439806 - type: max_f1 value: 91.52032112393378 - type: max_precision value: 93.05993690851734 - type: max_recall value: 91.5 - type: similarity_accuracy value: 99.81881188118813 - type: similarity_accuracy_threshold value: 85.55081486701965 - type: similarity_ap value: 96.0359661816236 - type: similarity_f1 value: 90.6584992343032 - type: similarity_f1_threshold value: 84.82859134674072 - type: similarity_precision value: 92.59645464025026 - type: similarity_recall value: 88.8 - task: type: Clustering dataset: name: MTEB StackExchangeClustering type: mteb/stackexchange-clustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: main_score value: 80.28558559137414 - type: v_measure value: 80.28558559137414 - type: v_measure_std value: 2.795276520287584 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P type: mteb/stackexchange-clustering-p2p config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: main_score value: 49.57135582416209 - type: v_measure value: 49.57135582416209 - type: v_measure_std value: 1.6414135468423754 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: main_score value: 55.253002583598644 - type: map value: 55.253002583598644 - type: mrr value: 56.24172396231219 - type: nAUC_map_diff1 value: 40.00053248203427 - type: nAUC_map_max value: 10.05441740585869 - type: nAUC_map_std value: 8.227169286387552 - type: nAUC_mrr_diff1 value: 40.250446264233744 - type: nAUC_mrr_max value: 10.586310195339053 - type: nAUC_mrr_std value: 8.47326494370076 - task: type: Summarization dataset: name: MTEB SummEval type: mteb/summeval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cosine_pearson value: 31.19874648747059 - type: cosine_spearman value: 31.493550648844863 - type: dot_pearson value: 31.157847680289407 - type: dot_spearman value: 31.575299712180538 - type: main_score value: 31.493550648844863 - type: pearson value: 31.19874648747059 - type: spearman value: 31.493550648844863 - task: type: Retrieval dataset: name: MTEB TRECCOVID type: mteb/trec-covid config: default split: test revision: bb9466bac8153a0349341eb1b22e06409e78ef4e metrics: - type: main_score value: 85.983 - type: map_at_1 value: 0.247 - type: map_at_10 value: 2.177 - type: map_at_100 value: 14.804 - type: map_at_1000 value: 37.045 - type: map_at_20 value: 4.12 - type: map_at_3 value: 0.7000000000000001 - type: map_at_5 value: 1.1320000000000001 - type: mrr_at_1 value: 96.0 - type: mrr_at_10 value: 98.0 - type: mrr_at_100 value: 98.0 - type: mrr_at_1000 value: 98.0 - type: mrr_at_20 value: 98.0 - type: mrr_at_3 value: 98.0 - type: mrr_at_5 value: 98.0 - type: nauc_map_at_1000_diff1 value: -0.9165125200337213 - type: nauc_map_at_1000_max value: 40.260117798042764 - type: nauc_map_at_1000_std value: 71.72789335831554 - type: nauc_map_at_100_diff1 value: 20.493827311583953 - type: nauc_map_at_100_max value: 21.005742079276462 - type: nauc_map_at_100_std value: 62.53815607831659 - type: nauc_map_at_10_diff1 value: 31.289297684528215 - type: nauc_map_at_10_max value: 7.86554294370268 - type: nauc_map_at_10_std value: 37.26191657133897 - type: nauc_map_at_1_diff1 value: 25.57568148849456 - type: nauc_map_at_1_max value: -5.9767435623941445 - type: nauc_map_at_1_std value: 30.849871717506755 - type: nauc_map_at_20_diff1 value: 30.896018204532087 - type: nauc_map_at_20_max value: 8.667077299744314 - type: nauc_map_at_20_std value: 41.512687168412924 - type: nauc_map_at_3_diff1 value: 29.44724521006598 - type: nauc_map_at_3_max value: 1.597496889532064 - type: nauc_map_at_3_std value: 32.25013773854697 - type: nauc_map_at_5_diff1 value: 27.387036605618825 - type: nauc_map_at_5_max value: 5.402983746211454 - type: nauc_map_at_5_std value: 33.940523962472184 - type: nauc_mrr_at_1000_diff1 value: -14.122315592903503 - type: nauc_mrr_at_1000_max value: 33.84687208216605 - type: nauc_mrr_at_1000_std value: 86.11111111111092 - type: nauc_mrr_at_100_diff1 value: -14.122315592903503 - type: nauc_mrr_at_100_max value: 33.84687208216605 - type: nauc_mrr_at_100_std value: 86.11111111111092 - type: nauc_mrr_at_10_diff1 value: -14.122315592903503 - type: nauc_mrr_at_10_max value: 33.84687208216605 - type: nauc_mrr_at_10_std value: 86.11111111111092 - type: nauc_mrr_at_1_diff1 value: -14.122315592903831 - type: nauc_mrr_at_1_max value: 33.84687208216637 - type: nauc_mrr_at_1_std value: 86.11111111111124 - type: nauc_mrr_at_20_diff1 value: -14.122315592903503 - type: nauc_mrr_at_20_max value: 33.84687208216605 - type: nauc_mrr_at_20_std value: 86.11111111111092 - type: nauc_mrr_at_3_diff1 value: -14.122315592903503 - type: nauc_mrr_at_3_max value: 33.84687208216605 - type: nauc_mrr_at_3_std value: 86.11111111111092 - type: nauc_mrr_at_5_diff1 value: -14.122315592903503 - type: nauc_mrr_at_5_max value: 33.84687208216605 - type: nauc_mrr_at_5_std value: 86.11111111111092 - type: nauc_ndcg_at_1000_diff1 value: 8.745907669561928 - type: nauc_ndcg_at_1000_max value: 45.43307237994533 - type: nauc_ndcg_at_1000_std value: 74.93357447176336 - type: nauc_ndcg_at_100_diff1 value: -3.9719350773353765 - type: nauc_ndcg_at_100_max value: 44.43705332397461 - type: nauc_ndcg_at_100_std value: 61.59493812371758 - type: nauc_ndcg_at_10_diff1 value: 15.230915878367348 - type: nauc_ndcg_at_10_max value: 48.332840970836635 - type: nauc_ndcg_at_10_std value: 46.888785065125774 - type: nauc_ndcg_at_1_diff1 value: 13.219732337379442 - type: nauc_ndcg_at_1_max value: 45.19919078742603 - type: nauc_ndcg_at_1_std value: 64.68253968253977 - type: nauc_ndcg_at_20_diff1 value: 12.479648691964865 - type: nauc_ndcg_at_20_max value: 48.76688248450331 - type: nauc_ndcg_at_20_std value: 51.450399755887545 - type: nauc_ndcg_at_3_diff1 value: 6.165414201871464 - type: nauc_ndcg_at_3_max value: 45.089689347691035 - type: nauc_ndcg_at_3_std value: 41.08249161845213 - type: nauc_ndcg_at_5_diff1 value: 7.411245806844721 - type: nauc_ndcg_at_5_max value: 47.818748093538076 - type: nauc_ndcg_at_5_std value: 45.907685763676575 - type: nauc_precision_at_1000_diff1 value: -30.574290219847345 - type: nauc_precision_at_1000_max value: 32.56926126118719 - type: nauc_precision_at_1000_std value: 14.584504392628874 - type: nauc_precision_at_100_diff1 value: -10.199740234718847 - type: nauc_precision_at_100_max value: 41.0213226769777 - type: nauc_precision_at_100_std value: 56.975760776771324 - type: nauc_precision_at_10_diff1 value: 7.865792689701161 - type: nauc_precision_at_10_max value: 52.00432275201737 - type: nauc_precision_at_10_std value: 43.89512276413724 - type: nauc_precision_at_1_diff1 value: -14.122315592903831 - type: nauc_precision_at_1_max value: 33.84687208216637 - type: nauc_precision_at_1_std value: 86.11111111111124 - type: nauc_precision_at_20_diff1 value: 5.481424191880084 - type: nauc_precision_at_20_max value: 46.86629331792725 - type: nauc_precision_at_20_std value: 49.245692667517496 - type: nauc_precision_at_3_diff1 value: -5.870408807869163 - type: nauc_precision_at_3_max value: 48.73657612128875 - type: nauc_precision_at_3_std value: 41.15152062088262 - type: nauc_precision_at_5_diff1 value: -4.550610529125413 - type: nauc_precision_at_5_max value: 60.390115878205386 - type: nauc_precision_at_5_std value: 44.16494295055696 - type: nauc_recall_at_1000_diff1 value: 8.047794367079034 - type: nauc_recall_at_1000_max value: 37.07551482870489 - type: nauc_recall_at_1000_std value: 66.20862163364201 - type: nauc_recall_at_100_diff1 value: 25.08104923597475 - type: nauc_recall_at_100_max value: 9.971294642165734 - type: nauc_recall_at_100_std value: 51.737814074891254 - type: nauc_recall_at_10_diff1 value: 32.33148478369628 - type: nauc_recall_at_10_max value: 1.3767192150014917 - type: nauc_recall_at_10_std value: 30.801926742876308 - type: nauc_recall_at_1_diff1 value: 25.57568148849456 - type: nauc_recall_at_1_max value: -5.9767435623941445 - type: nauc_recall_at_1_std value: 30.849871717506755 - type: nauc_recall_at_20_diff1 value: 31.716580022934654 - type: nauc_recall_at_20_max value: -0.1281270579464631 - type: nauc_recall_at_20_std value: 33.76185294993676 - type: nauc_recall_at_3_diff1 value: 29.758810004388348 - type: nauc_recall_at_3_max value: -1.9442985017191816 - type: nauc_recall_at_3_std value: 27.45550076962206 - type: nauc_recall_at_5_diff1 value: 27.047710181576672 - type: nauc_recall_at_5_max value: 1.5237000700880248 - type: nauc_recall_at_5_std value: 28.235297950159698 - type: ndcg_at_1 value: 94.0 - type: ndcg_at_10 value: 85.983 - type: ndcg_at_100 value: 69.195 - type: ndcg_at_1000 value: 62.541000000000004 - type: ndcg_at_20 value: 83.405 - type: ndcg_at_3 value: 89.98899999999999 - type: ndcg_at_5 value: 87.905 - type: precision_at_1 value: 96.0 - type: precision_at_10 value: 89.4 - type: precision_at_100 value: 71.54 - type: precision_at_1000 value: 27.594 - type: precision_at_20 value: 87.2 - type: precision_at_3 value: 92.667 - type: precision_at_5 value: 90.8 - type: recall_at_1 value: 0.247 - type: recall_at_10 value: 2.315 - type: recall_at_100 value: 17.574 - type: recall_at_1000 value: 59.336999999999996 - type: recall_at_20 value: 4.491 - type: recall_at_3 value: 0.7250000000000001 - type: recall_at_5 value: 1.1820000000000002 - task: type: Retrieval dataset: name: MTEB Touche2020 type: mteb/touche2020 config: default split: test revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f metrics: - type: main_score value: 29.944 - type: map_at_1 value: 3.064 - type: map_at_10 value: 11.501999999999999 - type: map_at_100 value: 18.736 - type: map_at_1000 value: 20.333000000000002 - type: map_at_20 value: 14.057 - type: map_at_3 value: 6.300999999999999 - type: map_at_5 value: 8.463 - type: mrr_at_1 value: 44.89795918367347 - type: mrr_at_10 value: 58.41188856494979 - type: mrr_at_100 value: 58.93964266413245 - type: mrr_at_1000 value: 58.93964266413245 - type: mrr_at_20 value: 58.767485349118 - type: mrr_at_3 value: 54.42176870748299 - type: mrr_at_5 value: 56.666666666666664 - type: nauc_map_at_1000_diff1 value: 11.478593385608479 - type: nauc_map_at_1000_max value: 10.309889845044324 - type: nauc_map_at_1000_std value: 21.16721939940238 - type: nauc_map_at_100_diff1 value: 11.570438543562418 - type: nauc_map_at_100_max value: 8.426183648064834 - type: nauc_map_at_100_std value: 18.56231985033613 - type: nauc_map_at_10_diff1 value: 22.37735506247481 - type: nauc_map_at_10_max value: 5.455946239060806 - type: nauc_map_at_10_std value: -4.2848826518388154 - type: nauc_map_at_1_diff1 value: 27.853645380676824 - type: nauc_map_at_1_max value: 7.30739948053113 - type: nauc_map_at_1_std value: -0.2773663157814586 - type: nauc_map_at_20_diff1 value: 14.724669779924648 - type: nauc_map_at_20_max value: 10.12882779173533 - type: nauc_map_at_20_std value: 4.4803777672120875 - type: nauc_map_at_3_diff1 value: 31.891173385921263 - type: nauc_map_at_3_max value: 4.889652271827218 - type: nauc_map_at_3_std value: -9.477460238651643 - type: nauc_map_at_5_diff1 value: 31.489012040465003 - type: nauc_map_at_5_max value: 1.7330092417337482 - type: nauc_map_at_5_std value: -8.137018608469637 - type: nauc_mrr_at_1000_diff1 value: 24.411522237082416 - type: nauc_mrr_at_1000_max value: 11.286971076556688 - type: nauc_mrr_at_1000_std value: 23.443174210894043 - type: nauc_mrr_at_100_diff1 value: 24.411522237082416 - type: nauc_mrr_at_100_max value: 11.286971076556688 - type: nauc_mrr_at_100_std value: 23.443174210894043 - type: nauc_mrr_at_10_diff1 value: 23.948152308265186 - type: nauc_mrr_at_10_max value: 12.22420979621155 - type: nauc_mrr_at_10_std value: 23.557939024705544 - type: nauc_mrr_at_1_diff1 value: 17.902334894536107 - type: nauc_mrr_at_1_max value: 17.36969662861018 - type: nauc_mrr_at_1_std value: 19.425714969048734 - type: nauc_mrr_at_20_diff1 value: 24.635893795899797 - type: nauc_mrr_at_20_max value: 11.330541067194913 - type: nauc_mrr_at_20_std value: 23.74518583400233 - type: nauc_mrr_at_3_diff1 value: 25.045536328282587 - type: nauc_mrr_at_3_max value: 7.497967004732733 - type: nauc_mrr_at_3_std value: 24.167153007320078 - type: nauc_mrr_at_5_diff1 value: 24.328479930592454 - type: nauc_mrr_at_5_max value: 10.037126854938336 - type: nauc_mrr_at_5_std value: 25.236208055346136 - type: nauc_ndcg_at_1000_diff1 value: 15.555347444667389 - type: nauc_ndcg_at_1000_max value: 13.356591700655718 - type: nauc_ndcg_at_1000_std value: 42.42395845935052 - type: nauc_ndcg_at_100_diff1 value: 13.110526060413708 - type: nauc_ndcg_at_100_max value: 3.140006440162515 - type: nauc_ndcg_at_100_std value: 39.02733288398033 - type: nauc_ndcg_at_10_diff1 value: 20.68853369009725 - type: nauc_ndcg_at_10_max value: 2.435389817058852 - type: nauc_ndcg_at_10_std value: 10.038202768784316 - type: nauc_ndcg_at_1_diff1 value: 20.17287594582385 - type: nauc_ndcg_at_1_max value: 12.487205168273196 - type: nauc_ndcg_at_1_std value: 20.639827614373075 - type: nauc_ndcg_at_20_diff1 value: 16.987577348502985 - type: nauc_ndcg_at_20_max value: 2.9978717644469266 - type: nauc_ndcg_at_20_std value: 13.015690866750354 - type: nauc_ndcg_at_3_diff1 value: 32.392223079245575 - type: nauc_ndcg_at_3_max value: 1.587587110582544 - type: nauc_ndcg_at_3_std value: 12.850592473446609 - type: nauc_ndcg_at_5_diff1 value: 32.80244517369626 - type: nauc_ndcg_at_5_max value: 5.8939933777508084 - type: nauc_ndcg_at_5_std value: 15.779687411463414 - type: nauc_precision_at_1000_diff1 value: -14.314031720452537 - type: nauc_precision_at_1000_max value: 32.87886666567266 - type: nauc_precision_at_1000_std value: 21.49347046886851 - type: nauc_precision_at_100_diff1 value: -9.4034008613839 - type: nauc_precision_at_100_max value: 16.784075123309645 - type: nauc_precision_at_100_std value: 73.14688535393604 - type: nauc_precision_at_10_diff1 value: 6.855101404043058 - type: nauc_precision_at_10_max value: 6.52491228645612 - type: nauc_precision_at_10_std value: 16.104602266016744 - type: nauc_precision_at_1_diff1 value: 17.902334894536107 - type: nauc_precision_at_1_max value: 17.36969662861018 - type: nauc_precision_at_1_std value: 19.425714969048734 - type: nauc_precision_at_20_diff1 value: -5.337534613602212 - type: nauc_precision_at_20_max value: 17.722925454767218 - type: nauc_precision_at_20_std value: 34.26680462132849 - type: nauc_precision_at_3_diff1 value: 31.054623397809255 - type: nauc_precision_at_3_max value: -0.92038600946826 - type: nauc_precision_at_3_std value: 8.326997076862916 - type: nauc_precision_at_5_diff1 value: 29.784942296920462 - type: nauc_precision_at_5_max value: 6.337469263434779 - type: nauc_precision_at_5_std value: 12.789597196020974 - type: nauc_recall_at_1000_diff1 value: -3.8177981862041364 - type: nauc_recall_at_1000_max value: 14.206064332229163 - type: nauc_recall_at_1000_std value: 74.18853420771269 - type: nauc_recall_at_100_diff1 value: 0.7677996771461106 - type: nauc_recall_at_100_max value: -4.139924106878441 - type: nauc_recall_at_100_std value: 48.319930706362896 - type: nauc_recall_at_10_diff1 value: 12.038835537494322 - type: nauc_recall_at_10_max value: -2.0498983557854418 - type: nauc_recall_at_10_std value: -2.0339180690854493 - type: nauc_recall_at_1_diff1 value: 27.853645380676824 - type: nauc_recall_at_1_max value: 7.30739948053113 - type: nauc_recall_at_1_std value: -0.2773663157814586 - type: nauc_recall_at_20_diff1 value: 0.7907893667756708 - type: nauc_recall_at_20_max value: 0.8795499810558195 - type: nauc_recall_at_20_std value: 11.512483291688282 - type: nauc_recall_at_3_diff1 value: 33.19440392639576 - type: nauc_recall_at_3_max value: -1.5494237697432613 - type: nauc_recall_at_3_std value: -8.560408808376984 - type: nauc_recall_at_5_diff1 value: 27.42193873870941 - type: nauc_recall_at_5_max value: -4.74350293281128 - type: nauc_recall_at_5_std value: -7.618060131179654 - type: ndcg_at_1 value: 42.857 - type: ndcg_at_10 value: 29.944 - type: ndcg_at_100 value: 42.624 - type: ndcg_at_1000 value: 53.384 - type: ndcg_at_20 value: 30.135 - type: ndcg_at_3 value: 34.847 - type: ndcg_at_5 value: 32.573 - type: precision_at_1 value: 44.897999999999996 - type: precision_at_10 value: 25.306 - type: precision_at_100 value: 8.694 - type: precision_at_1000 value: 1.616 - type: precision_at_20 value: 19.082 - type: precision_at_3 value: 34.014 - type: precision_at_5 value: 31.019999999999996 - type: recall_at_1 value: 3.064 - type: recall_at_10 value: 17.849999999999998 - type: recall_at_100 value: 53.217999999999996 - type: recall_at_1000 value: 87.095 - type: recall_at_20 value: 26.111 - type: recall_at_3 value: 7.383000000000001 - type: recall_at_5 value: 11.434 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification type: mteb/toxic_conversations_50k config: default split: test revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de metrics: - type: accuracy value: 88.759765625 - type: ap value: 36.49152357863017 - type: ap_weighted value: 36.49152357863017 - type: f1 value: 74.4692714448641 - type: f1_weighted value: 90.54372649306606 - type: main_score value: 88.759765625 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification type: mteb/tweet_sentiment_extraction config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 74.8443689869836 - type: f1 value: 75.1139662898148 - type: f1_weighted value: 74.7369003946243 - type: main_score value: 74.8443689869836 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering type: mteb/twentynewsgroups-clustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: main_score value: 61.42918790942448 - type: v_measure value: 61.42918790942448 - type: v_measure_std value: 1.0156550098843082 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cosine_accuracy value: 88.22197055492639 - type: cosine_accuracy_threshold value: 83.30042362213135 - type: cosine_ap value: 80.57754959194938 - type: cosine_f1 value: 73.70579190158894 - type: cosine_f1_threshold value: 81.04978799819946 - type: cosine_precision value: 71.64922770303936 - type: cosine_recall value: 75.8839050131926 - type: dot_accuracy value: 88.23985217857782 - type: dot_accuracy_threshold value: 83.31039547920227 - type: dot_ap value: 80.57533213448181 - type: dot_f1 value: 73.61309601143302 - type: dot_f1_threshold value: 81.33968114852905 - type: dot_precision value: 72.51087791144101 - type: dot_recall value: 74.74934036939314 - type: euclidean_accuracy value: 88.22197055492639 - type: euclidean_accuracy_threshold value: 58.290231227874756 - type: euclidean_ap value: 80.57982723880139 - type: euclidean_f1 value: 73.63426519620417 - type: euclidean_f1_threshold value: 61.55576705932617 - type: euclidean_precision value: 71.63173652694611 - type: euclidean_recall value: 75.75197889182058 - type: main_score value: 80.57982723880139 - type: manhattan_accuracy value: 88.14448351910353 - type: manhattan_accuracy_threshold value: 3907.2471618652344 - type: manhattan_ap value: 80.3538079655539 - type: manhattan_f1 value: 73.40466675261054 - type: manhattan_f1_threshold value: 4103.794097900391 - type: manhattan_precision value: 71.76707839677337 - type: manhattan_recall value: 75.11873350923483 - type: max_ap value: 80.57982723880139 - type: max_f1 value: 73.70579190158894 - type: max_precision value: 72.51087791144101 - type: max_recall value: 75.8839050131926 - type: similarity_accuracy value: 88.22197055492639 - type: similarity_accuracy_threshold value: 83.30042362213135 - type: similarity_ap value: 80.57754959194938 - type: similarity_f1 value: 73.70579190158894 - type: similarity_f1_threshold value: 81.04978799819946 - type: similarity_precision value: 71.64922770303936 - type: similarity_recall value: 75.8839050131926 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cosine_accuracy value: 89.88628866379477 - type: cosine_accuracy_threshold value: 80.8050274848938 - type: cosine_ap value: 87.57594591596816 - type: cosine_f1 value: 80.0812257707218 - type: cosine_f1_threshold value: 77.990061044693 - type: cosine_precision value: 76.93126197063205 - type: cosine_recall value: 83.50015398829689 - type: dot_accuracy value: 89.87852679784221 - type: dot_accuracy_threshold value: 80.84419965744019 - type: dot_ap value: 87.56136742222151 - type: dot_f1 value: 80.05898617511521 - type: dot_f1_threshold value: 77.92385816574097 - type: dot_precision value: 76.80554573106035 - type: dot_recall value: 83.60024638127503 - type: euclidean_accuracy value: 89.86882446540149 - type: euclidean_accuracy_threshold value: 62.08193898200989 - type: euclidean_ap value: 87.57517549192228 - type: euclidean_f1 value: 80.05286925872892 - type: euclidean_f1_threshold value: 66.65036082267761 - type: euclidean_precision value: 76.51063232507545 - type: euclidean_recall value: 83.93902063443178 - type: main_score value: 87.64162614197194 - type: manhattan_accuracy value: 89.8959909962355 - type: manhattan_accuracy_threshold value: 4176.108169555664 - type: manhattan_ap value: 87.64162614197194 - type: manhattan_f1 value: 80.17116279069768 - type: manhattan_f1_threshold value: 4433.153533935547 - type: manhattan_precision value: 77.57615035644848 - type: manhattan_recall value: 82.94579611949491 - type: max_ap value: 87.64162614197194 - type: max_f1 value: 80.17116279069768 - type: max_precision value: 77.57615035644848 - type: max_recall value: 83.93902063443178 - type: similarity_accuracy value: 89.88628866379477 - type: similarity_accuracy_threshold value: 80.8050274848938 - type: similarity_ap value: 87.57594591596816 - type: similarity_f1 value: 80.0812257707218 - type: similarity_f1_threshold value: 77.990061044693 - type: similarity_precision value: 76.93126197063205 - type: similarity_recall value: 83.50015398829689 --- # Updates Hi, everyone, thanks for using stella models. After six months of work, I trained the jasper model on top of the stella model, which is a multimodal model, and it can be ranked 2 in mteb (submitted the results on 2024-12-11, which may need official review https://github.com/embeddings-benchmark/results/pull/68). Model link: https://huggingface.co/infgrad/jasper_en_vision_language_v1 I'll focus on the technical report, training data and related code, hopefully the tricks I've used will be of some help to you guys! This work was accomplished during my free time, it's a personal hobby. One person's time and energy is limited, and you are welcome to make any contributions! You can also find these models on my [homepage](https://huggingface.co/infgrad). # Introduction The models are trained based on `Alibaba-NLP/gte-large-en-v1.5` and `Alibaba-NLP/gte-Qwen2-1.5B-instruct`. Thanks for their contributions! **We simplify usage of prompts, providing two prompts for most general tasks, one is for s2p, another one is for s2s.** Prompt of s2p task(e.g. retrieve task): ```text Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: {query} ``` Prompt of s2s task(e.g. semantic textual similarity task): ```text Instruct: Retrieve semantically similar text.\nQuery: {query} ``` The models are finally trained by [MRL]((https://arxiv.org/abs/2205.13147)), so they have multiple dimensions: 512, 768, 1024, 2048, 4096, 6144 and 8192. The higher the dimension, the better the performance. **Generally speaking, 1024d is good enough.** The MTEB score of 1024d is only 0.001 lower than 8192d. # Model directory structure The model directory structure is very simple, it is a standard SentenceTransformer directory **with a series of `2_Dense_{dims}` folders**, where `dims` represents the final vector dimension. For example, the `2_Dense_256` folder stores Linear weights that convert vector dimensions to 256 dimensions. Please refer to the following chapters for specific instructions on how to use them. # Usage You can use `SentenceTransformers` or `transformers` library to encode text. ## Sentence Transformers ```python from sentence_transformers import SentenceTransformer # This model supports two prompts: "s2p_query" and "s2s_query" for sentence-to-passage and sentence-to-sentence tasks, respectively. # They are defined in `config_sentence_transformers.json` query_prompt_name = "s2p_query" queries = [ "What are some ways to reduce stress?", "What are the benefits of drinking green tea?", ] # docs do not need any prompts docs = [ "There are many effective ways to reduce stress. Some common techniques include deep breathing, meditation, and physical activity. Engaging in hobbies, spending time in nature, and connecting with loved ones can also help alleviate stress. Additionally, setting boundaries, practicing self-care, and learning to say no can prevent stress from building up.", "Green tea has been consumed for centuries and is known for its potential health benefits. It contains antioxidants that may help protect the body against damage caused by free radicals. Regular consumption of green tea has been associated with improved heart health, enhanced cognitive function, and a reduced risk of certain types of cancer. The polyphenols in green tea may also have anti-inflammatory and weight loss properties.", ] # ！The default dimension is 1024, if you need other dimensions, please clone the model and modify `modules.json` to replace `2_Dense_1024` with another dimension, e.g. `2_Dense_256` or `2_Dense_8192` ! model = SentenceTransformer("dunzhang/stella_en_1.5B_v5", trust_remote_code=True).cuda() query_embeddings = model.encode(queries, prompt_name=query_prompt_name) doc_embeddings = model.encode(docs) print(query_embeddings.shape, doc_embeddings.shape) # (2, 1024) (2, 1024) similarities = model.similarity(query_embeddings, doc_embeddings) print(similarities) # tensor([[0.8179, 0.2958], # [0.3194, 0.7854]]) ``` ## Transformers ```python import os import torch from transformers import AutoModel, AutoTokenizer from sklearn.preprocessing import normalize query_prompt = "Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: " queries = [ "What are some ways to reduce stress?", "What are the benefits of drinking green tea?", ] queries = [query_prompt + query for query in queries] # docs do not need any prompts docs = [ "There are many effective ways to reduce stress. Some common techniques include deep breathing, meditation, and physical activity. Engaging in hobbies, spending time in nature, and connecting with loved ones can also help alleviate stress. Additionally, setting boundaries, practicing self-care, and learning to say no can prevent stress from building up.", "Green tea has been consumed for centuries and is known for its potential health benefits. It contains antioxidants that may help protect the body against damage caused by free radicals. Regular consumption of green tea has been associated with improved heart health, enhanced cognitive function, and a reduced risk of certain types of cancer. The polyphenols in green tea may also have anti-inflammatory and weight loss properties.", ] # The path of your model after cloning it model_dir = "{Your MODEL_PATH}" vector_dim = 1024 vector_linear_directory = f"2_Dense_{vector_dim}" model = AutoModel.from_pretrained(model_dir, trust_remote_code=True).cuda().eval() tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True) vector_linear = torch.nn.Linear(in_features=model.config.hidden_size, out_features=vector_dim) vector_linear_dict = { k.replace("linear.", ""): v for k, v in torch.load(os.path.join(model_dir, f"{vector_linear_directory}/pytorch_model.bin")).items() } vector_linear.load_state_dict(vector_linear_dict) vector_linear.cuda() # Embed the queries with torch.no_grad(): input_data = tokenizer(queries, padding="longest", truncation=True, max_length=512, return_tensors="pt") input_data = {k: v.cuda() for k, v in input_data.items()} attention_mask = input_data["attention_mask"] last_hidden_state = model(**input_data)[0] last_hidden = last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0) query_vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None] query_vectors = normalize(vector_linear(query_vectors).cpu().numpy()) # Embed the documents with torch.no_grad(): input_data = tokenizer(docs, padding="longest", truncation=True, max_length=512, return_tensors="pt") input_data = {k: v.cuda() for k, v in input_data.items()} attention_mask = input_data["attention_mask"] last_hidden_state = model(**input_data)[0] last_hidden = last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0) docs_vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None] docs_vectors = normalize(vector_linear(docs_vectors).cpu().numpy()) print(query_vectors.shape, docs_vectors.shape) # (2, 1024) (2, 1024) similarities = query_vectors @ docs_vectors.T print(similarities) # [[0.8178789 0.2958377 ] # [0.31938642 0.7853526 ]] ``` ## Infinity Usage with [Infinity, MIT Licensed Inference Server](https://github.com/michaelfeil/infinity) and Docker. ```bash docker run --gpus all -v $PWD/data:/app/.cache \ michaelf34/infinity:0.0.69-trt-onnx \ v2 --model-id dunzhang/stella_en_1.5B_v5 --batch-size 16 --device cuda --engine torch --port 7997 ``` # FAQ Q: The details of training? A: The training method and datasets will be released in the future. (specific time unknown, may be provided in a paper) Q: How to choose a suitable prompt for my own task? A: In most cases, please use the s2p and s2s prompts. These two prompts account for the vast majority of the training data. Q: How to reproduce MTEB results? A: Please use evaluation scripts in `Alibaba-NLP/gte-Qwen2-1.5B-instruct` or `intfloat/e5-mistral-7b-instruct` Q: Why each dimension has a linear weight? A: MRL has multiple training methods, we choose this method which has the best performance. Q: What is the sequence length of models? A: 512 is recommended, in our experiments, almost all models perform poorly on specialized long text retrieval datasets. Besides, the model is trained on datasets of 512 length. This may be an optimization term. If you have any questions, please start a discussion on community.
[ "BIOSSES", "SCIFACT" ]
Teradata/bge-base-en-v1.5
Teradata
feature-extraction
[ "onnx", "bert", "feature-extraction", "sentence-similarity", "mteb", "teradata", "en", "license:mit", "model-index", "region:us" ]
2025-02-12T16:06:02Z
2025-03-04T09:38:36+00:00
32
0
--- language: - en license: mit tags: - feature-extraction - sentence-similarity - mteb - onnx - teradata model-index: - name: bge-base-en-v1.5 results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 76.14925373134328 - type: ap value: 39.32336517995478 - type: f1 value: 70.16902252611425 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification type: mteb/amazon_polarity config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 93.386825 - type: ap value: 90.21276917991995 - type: f1 value: 93.37741030006174 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 48.846000000000004 - type: f1 value: 48.14646269778261 - task: type: Retrieval dataset: name: MTEB ArguAna type: arguana config: default split: test revision: None metrics: - type: map_at_1 value: 40.754000000000005 - type: map_at_10 value: 55.761 - type: map_at_100 value: 56.330999999999996 - type: map_at_1000 value: 56.333999999999996 - type: map_at_3 value: 51.92 - type: map_at_5 value: 54.010999999999996 - type: mrr_at_1 value: 41.181 - type: mrr_at_10 value: 55.967999999999996 - type: mrr_at_100 value: 56.538 - type: mrr_at_1000 value: 56.542 - type: mrr_at_3 value: 51.980000000000004 - type: mrr_at_5 value: 54.208999999999996 - type: ndcg_at_1 value: 40.754000000000005 - type: ndcg_at_10 value: 63.605000000000004 - type: ndcg_at_100 value: 66.05199999999999 - type: ndcg_at_1000 value: 66.12 - type: ndcg_at_3 value: 55.708 - type: ndcg_at_5 value: 59.452000000000005 - type: precision_at_1 value: 40.754000000000005 - type: precision_at_10 value: 8.841000000000001 - type: precision_at_100 value: 0.991 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 22.238 - type: precision_at_5 value: 15.149000000000001 - type: recall_at_1 value: 40.754000000000005 - type: recall_at_10 value: 88.407 - type: recall_at_100 value: 99.14699999999999 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 66.714 - type: recall_at_5 value: 75.747 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P type: mteb/arxiv-clustering-p2p config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 48.74884539679369 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S type: mteb/arxiv-clustering-s2s config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 42.8075893810716 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions type: mteb/askubuntudupquestions-reranking config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 62.128470519187736 - type: mrr value: 74.28065778481289 - task: type: STS dataset: name: MTEB BIOSSES type: mteb/biosses-sts config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 89.24629081484655 - type: cos_sim_spearman value: 86.93752309911496 - type: euclidean_pearson value: 87.58589628573816 - type: euclidean_spearman value: 88.05622328825284 - type: manhattan_pearson value: 87.5594959805773 - type: manhattan_spearman value: 88.19658793233961 - task: type: Classification dataset: name: MTEB Banking77Classification type: mteb/banking77 config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 86.9512987012987 - type: f1 value: 86.92515357973708 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P type: mteb/biorxiv-clustering-p2p config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 39.10263762928872 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S type: mteb/biorxiv-clustering-s2s config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 36.69711517426737 - task: type: Retrieval dataset: name: MTEB CQADupstackAndroidRetrieval type: BeIR/cqadupstack config: default split: test revision: None metrics: - type: map_at_1 value: 32.327 - type: map_at_10 value: 44.099 - type: map_at_100 value: 45.525 - type: map_at_1000 value: 45.641999999999996 - type: map_at_3 value: 40.47 - type: map_at_5 value: 42.36 - type: mrr_at_1 value: 39.199 - type: mrr_at_10 value: 49.651 - type: mrr_at_100 value: 50.29 - type: mrr_at_1000 value: 50.329 - type: mrr_at_3 value: 46.924 - type: mrr_at_5 value: 48.548 - type: ndcg_at_1 value: 39.199 - type: ndcg_at_10 value: 50.773 - type: ndcg_at_100 value: 55.67999999999999 - type: ndcg_at_1000 value: 57.495 - type: ndcg_at_3 value: 45.513999999999996 - type: ndcg_at_5 value: 47.703 - type: precision_at_1 value: 39.199 - type: precision_at_10 value: 9.914000000000001 - type: precision_at_100 value: 1.5310000000000001 - type: precision_at_1000 value: 0.198 - type: precision_at_3 value: 21.984 - type: precision_at_5 value: 15.737000000000002 - type: recall_at_1 value: 32.327 - type: recall_at_10 value: 63.743 - type: recall_at_100 value: 84.538 - type: recall_at_1000 value: 96.089 - type: recall_at_3 value: 48.065000000000005 - type: recall_at_5 value: 54.519 - type: map_at_1 value: 32.671 - type: map_at_10 value: 42.954 - type: map_at_100 value: 44.151 - type: map_at_1000 value: 44.287 - type: map_at_3 value: 39.912 - type: map_at_5 value: 41.798 - type: mrr_at_1 value: 41.465 - type: mrr_at_10 value: 49.351 - type: mrr_at_100 value: 49.980000000000004 - type: mrr_at_1000 value: 50.016000000000005 - type: mrr_at_3 value: 47.144000000000005 - type: mrr_at_5 value: 48.592999999999996 - type: ndcg_at_1 value: 41.465 - type: ndcg_at_10 value: 48.565999999999995 - type: ndcg_at_100 value: 52.76499999999999 - type: ndcg_at_1000 value: 54.749 - type: ndcg_at_3 value: 44.57 - type: ndcg_at_5 value: 46.759 - type: precision_at_1 value: 41.465 - type: precision_at_10 value: 9.107999999999999 - type: precision_at_100 value: 1.433 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 21.423000000000002 - type: precision_at_5 value: 15.414 - type: recall_at_1 value: 32.671 - type: recall_at_10 value: 57.738 - type: recall_at_100 value: 75.86500000000001 - type: recall_at_1000 value: 88.36 - type: recall_at_3 value: 45.626 - type: recall_at_5 value: 51.812000000000005 - type: map_at_1 value: 41.185 - type: map_at_10 value: 53.929 - type: map_at_100 value: 54.92 - type: map_at_1000 value: 54.967999999999996 - type: map_at_3 value: 50.70400000000001 - type: map_at_5 value: 52.673 - type: mrr_at_1 value: 47.398 - type: mrr_at_10 value: 57.303000000000004 - type: mrr_at_100 value: 57.959 - type: mrr_at_1000 value: 57.985 - type: mrr_at_3 value: 54.932 - type: mrr_at_5 value: 56.464999999999996 - type: ndcg_at_1 value: 47.398 - type: ndcg_at_10 value: 59.653 - type: ndcg_at_100 value: 63.627 - type: ndcg_at_1000 value: 64.596 - type: ndcg_at_3 value: 54.455 - type: ndcg_at_5 value: 57.245000000000005 - type: precision_at_1 value: 47.398 - type: precision_at_10 value: 9.524000000000001 - type: precision_at_100 value: 1.243 - type: precision_at_1000 value: 0.13699999999999998 - type: precision_at_3 value: 24.389 - type: precision_at_5 value: 16.752 - type: recall_at_1 value: 41.185 - type: recall_at_10 value: 73.193 - type: recall_at_100 value: 90.357 - type: recall_at_1000 value: 97.253 - type: recall_at_3 value: 59.199999999999996 - type: recall_at_5 value: 66.118 - type: map_at_1 value: 27.27 - type: map_at_10 value: 36.223 - type: map_at_100 value: 37.218 - type: map_at_1000 value: 37.293 - type: map_at_3 value: 33.503 - type: map_at_5 value: 35.097 - type: mrr_at_1 value: 29.492 - type: mrr_at_10 value: 38.352000000000004 - type: mrr_at_100 value: 39.188 - type: mrr_at_1000 value: 39.247 - type: mrr_at_3 value: 35.876000000000005 - type: mrr_at_5 value: 37.401 - type: ndcg_at_1 value: 29.492 - type: ndcg_at_10 value: 41.239 - type: ndcg_at_100 value: 46.066 - type: ndcg_at_1000 value: 47.992000000000004 - type: ndcg_at_3 value: 36.11 - type: ndcg_at_5 value: 38.772 - type: precision_at_1 value: 29.492 - type: precision_at_10 value: 6.260000000000001 - type: precision_at_100 value: 0.914 - type: precision_at_1000 value: 0.11100000000000002 - type: precision_at_3 value: 15.104000000000001 - type: precision_at_5 value: 10.644 - type: recall_at_1 value: 27.27 - type: recall_at_10 value: 54.589 - type: recall_at_100 value: 76.70700000000001 - type: recall_at_1000 value: 91.158 - type: recall_at_3 value: 40.974 - type: recall_at_5 value: 47.327000000000005 - type: map_at_1 value: 17.848 - type: map_at_10 value: 26.207 - type: map_at_100 value: 27.478 - type: map_at_1000 value: 27.602 - type: map_at_3 value: 23.405 - type: map_at_5 value: 24.98 - type: mrr_at_1 value: 21.891 - type: mrr_at_10 value: 31.041999999999998 - type: mrr_at_100 value: 32.092 - type: mrr_at_1000 value: 32.151999999999994 - type: mrr_at_3 value: 28.358 - type: mrr_at_5 value: 29.969 - type: ndcg_at_1 value: 21.891 - type: ndcg_at_10 value: 31.585 - type: ndcg_at_100 value: 37.531 - type: ndcg_at_1000 value: 40.256 - type: ndcg_at_3 value: 26.508 - type: ndcg_at_5 value: 28.894 - type: precision_at_1 value: 21.891 - type: precision_at_10 value: 5.795999999999999 - type: precision_at_100 value: 0.9990000000000001 - type: precision_at_1000 value: 0.13799999999999998 - type: precision_at_3 value: 12.769 - type: precision_at_5 value: 9.279 - type: recall_at_1 value: 17.848 - type: recall_at_10 value: 43.452 - type: recall_at_100 value: 69.216 - type: recall_at_1000 value: 88.102 - type: recall_at_3 value: 29.18 - type: recall_at_5 value: 35.347 - type: map_at_1 value: 30.94 - type: map_at_10 value: 41.248000000000005 - type: map_at_100 value: 42.495 - type: map_at_1000 value: 42.602000000000004 - type: map_at_3 value: 37.939 - type: map_at_5 value: 39.924 - type: mrr_at_1 value: 37.824999999999996 - type: mrr_at_10 value: 47.041 - type: mrr_at_100 value: 47.83 - type: mrr_at_1000 value: 47.878 - type: mrr_at_3 value: 44.466 - type: mrr_at_5 value: 46.111999999999995 - type: ndcg_at_1 value: 37.824999999999996 - type: ndcg_at_10 value: 47.223 - type: ndcg_at_100 value: 52.394 - type: ndcg_at_1000 value: 54.432 - type: ndcg_at_3 value: 42.032000000000004 - type: ndcg_at_5 value: 44.772 - type: precision_at_1 value: 37.824999999999996 - type: precision_at_10 value: 8.393 - type: precision_at_100 value: 1.2890000000000001 - type: precision_at_1000 value: 0.164 - type: precision_at_3 value: 19.698 - type: precision_at_5 value: 14.013 - type: recall_at_1 value: 30.94 - type: recall_at_10 value: 59.316 - type: recall_at_100 value: 80.783 - type: recall_at_1000 value: 94.15400000000001 - type: recall_at_3 value: 44.712 - type: recall_at_5 value: 51.932 - type: map_at_1 value: 27.104 - type: map_at_10 value: 36.675999999999995 - type: map_at_100 value: 38.076 - type: map_at_1000 value: 38.189 - type: map_at_3 value: 33.733999999999995 - type: map_at_5 value: 35.287 - type: mrr_at_1 value: 33.904 - type: mrr_at_10 value: 42.55 - type: mrr_at_100 value: 43.434 - type: mrr_at_1000 value: 43.494 - type: mrr_at_3 value: 40.126 - type: mrr_at_5 value: 41.473 - type: ndcg_at_1 value: 33.904 - type: ndcg_at_10 value: 42.414 - type: ndcg_at_100 value: 48.203 - type: ndcg_at_1000 value: 50.437 - type: ndcg_at_3 value: 37.633 - type: ndcg_at_5 value: 39.67 - type: precision_at_1 value: 33.904 - type: precision_at_10 value: 7.82 - type: precision_at_100 value: 1.2409999999999999 - type: precision_at_1000 value: 0.159 - type: precision_at_3 value: 17.884 - type: precision_at_5 value: 12.648000000000001 - type: recall_at_1 value: 27.104 - type: recall_at_10 value: 53.563 - type: recall_at_100 value: 78.557 - type: recall_at_1000 value: 93.533 - type: recall_at_3 value: 39.92 - type: recall_at_5 value: 45.457 - type: map_at_1 value: 27.707749999999997 - type: map_at_10 value: 36.961 - type: map_at_100 value: 38.158833333333334 - type: map_at_1000 value: 38.270333333333326 - type: map_at_3 value: 34.07183333333334 - type: map_at_5 value: 35.69533333333334 - type: mrr_at_1 value: 32.81875 - type: mrr_at_10 value: 41.293 - type: mrr_at_100 value: 42.116499999999995 - type: mrr_at_1000 value: 42.170249999999996 - type: mrr_at_3 value: 38.83983333333333 - type: mrr_at_5 value: 40.29775 - type: ndcg_at_1 value: 32.81875 - type: ndcg_at_10 value: 42.355 - type: ndcg_at_100 value: 47.41374999999999 - type: ndcg_at_1000 value: 49.5805 - type: ndcg_at_3 value: 37.52825 - type: ndcg_at_5 value: 39.83266666666667 - type: precision_at_1 value: 32.81875 - type: precision_at_10 value: 7.382416666666666 - type: precision_at_100 value: 1.1640833333333334 - type: precision_at_1000 value: 0.15383333333333335 - type: precision_at_3 value: 17.134166666666665 - type: precision_at_5 value: 12.174833333333336 - type: recall_at_1 value: 27.707749999999997 - type: recall_at_10 value: 53.945 - type: recall_at_100 value: 76.191 - type: recall_at_1000 value: 91.101 - type: recall_at_3 value: 40.39083333333334 - type: recall_at_5 value: 46.40083333333333 - type: map_at_1 value: 26.482 - type: map_at_10 value: 33.201 - type: map_at_100 value: 34.107 - type: map_at_1000 value: 34.197 - type: map_at_3 value: 31.174000000000003 - type: map_at_5 value: 32.279 - type: mrr_at_1 value: 29.908 - type: mrr_at_10 value: 36.235 - type: mrr_at_100 value: 37.04 - type: mrr_at_1000 value: 37.105 - type: mrr_at_3 value: 34.355999999999995 - type: mrr_at_5 value: 35.382999999999996 - type: ndcg_at_1 value: 29.908 - type: ndcg_at_10 value: 37.325 - type: ndcg_at_100 value: 41.795 - type: ndcg_at_1000 value: 44.105 - type: ndcg_at_3 value: 33.555 - type: ndcg_at_5 value: 35.266999999999996 - type: precision_at_1 value: 29.908 - type: precision_at_10 value: 5.721 - type: precision_at_100 value: 0.8630000000000001 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 14.008000000000001 - type: precision_at_5 value: 9.754999999999999 - type: recall_at_1 value: 26.482 - type: recall_at_10 value: 47.072 - type: recall_at_100 value: 67.27 - type: recall_at_1000 value: 84.371 - type: recall_at_3 value: 36.65 - type: recall_at_5 value: 40.774 - type: map_at_1 value: 18.815 - type: map_at_10 value: 26.369999999999997 - type: map_at_100 value: 27.458 - type: map_at_1000 value: 27.588 - type: map_at_3 value: 23.990000000000002 - type: map_at_5 value: 25.345000000000002 - type: mrr_at_1 value: 22.953000000000003 - type: mrr_at_10 value: 30.342999999999996 - type: mrr_at_100 value: 31.241000000000003 - type: mrr_at_1000 value: 31.319000000000003 - type: mrr_at_3 value: 28.16 - type: mrr_at_5 value: 29.406 - type: ndcg_at_1 value: 22.953000000000003 - type: ndcg_at_10 value: 31.151 - type: ndcg_at_100 value: 36.309000000000005 - type: ndcg_at_1000 value: 39.227000000000004 - type: ndcg_at_3 value: 26.921 - type: ndcg_at_5 value: 28.938000000000002 - type: precision_at_1 value: 22.953000000000003 - type: precision_at_10 value: 5.602 - type: precision_at_100 value: 0.9530000000000001 - type: precision_at_1000 value: 0.13899999999999998 - type: precision_at_3 value: 12.606 - type: precision_at_5 value: 9.119 - type: recall_at_1 value: 18.815 - type: recall_at_10 value: 41.574 - type: recall_at_100 value: 64.84400000000001 - type: recall_at_1000 value: 85.406 - type: recall_at_3 value: 29.694 - type: recall_at_5 value: 34.935 - type: map_at_1 value: 27.840999999999998 - type: map_at_10 value: 36.797999999999995 - type: map_at_100 value: 37.993 - type: map_at_1000 value: 38.086999999999996 - type: map_at_3 value: 34.050999999999995 - type: map_at_5 value: 35.379 - type: mrr_at_1 value: 32.649 - type: mrr_at_10 value: 41.025 - type: mrr_at_100 value: 41.878 - type: mrr_at_1000 value: 41.929 - type: mrr_at_3 value: 38.573 - type: mrr_at_5 value: 39.715 - type: ndcg_at_1 value: 32.649 - type: ndcg_at_10 value: 42.142 - type: ndcg_at_100 value: 47.558 - type: ndcg_at_1000 value: 49.643 - type: ndcg_at_3 value: 37.12 - type: ndcg_at_5 value: 38.983000000000004 - type: precision_at_1 value: 32.649 - type: precision_at_10 value: 7.08 - type: precision_at_100 value: 1.1039999999999999 - type: precision_at_1000 value: 0.13899999999999998 - type: precision_at_3 value: 16.698 - type: precision_at_5 value: 11.511000000000001 - type: recall_at_1 value: 27.840999999999998 - type: recall_at_10 value: 54.245 - type: recall_at_100 value: 77.947 - type: recall_at_1000 value: 92.36999999999999 - type: recall_at_3 value: 40.146 - type: recall_at_5 value: 44.951 - type: map_at_1 value: 26.529000000000003 - type: map_at_10 value: 35.010000000000005 - type: map_at_100 value: 36.647 - type: map_at_1000 value: 36.857 - type: map_at_3 value: 31.968000000000004 - type: map_at_5 value: 33.554 - type: mrr_at_1 value: 31.818 - type: mrr_at_10 value: 39.550999999999995 - type: mrr_at_100 value: 40.54 - type: mrr_at_1000 value: 40.596 - type: mrr_at_3 value: 36.726 - type: mrr_at_5 value: 38.416 - type: ndcg_at_1 value: 31.818 - type: ndcg_at_10 value: 40.675 - type: ndcg_at_100 value: 46.548 - type: ndcg_at_1000 value: 49.126 - type: ndcg_at_3 value: 35.829 - type: ndcg_at_5 value: 38 - type: precision_at_1 value: 31.818 - type: precision_at_10 value: 7.826 - type: precision_at_100 value: 1.538 - type: precision_at_1000 value: 0.24 - type: precision_at_3 value: 16.601 - type: precision_at_5 value: 12.095 - type: recall_at_1 value: 26.529000000000003 - type: recall_at_10 value: 51.03 - type: recall_at_100 value: 77.556 - type: recall_at_1000 value: 93.804 - type: recall_at_3 value: 36.986000000000004 - type: recall_at_5 value: 43.096000000000004 - type: map_at_1 value: 23.480999999999998 - type: map_at_10 value: 30.817 - type: map_at_100 value: 31.838 - type: map_at_1000 value: 31.932 - type: map_at_3 value: 28.011999999999997 - type: map_at_5 value: 29.668 - type: mrr_at_1 value: 25.323 - type: mrr_at_10 value: 33.072 - type: mrr_at_100 value: 33.926 - type: mrr_at_1000 value: 33.993 - type: mrr_at_3 value: 30.436999999999998 - type: mrr_at_5 value: 32.092 - type: ndcg_at_1 value: 25.323 - type: ndcg_at_10 value: 35.514 - type: ndcg_at_100 value: 40.489000000000004 - type: ndcg_at_1000 value: 42.908 - type: ndcg_at_3 value: 30.092000000000002 - type: ndcg_at_5 value: 32.989000000000004 - type: precision_at_1 value: 25.323 - type: precision_at_10 value: 5.545 - type: precision_at_100 value: 0.861 - type: precision_at_1000 value: 0.117 - type: precision_at_3 value: 12.446 - type: precision_at_5 value: 9.131 - type: recall_at_1 value: 23.480999999999998 - type: recall_at_10 value: 47.825 - type: recall_at_100 value: 70.652 - type: recall_at_1000 value: 88.612 - type: recall_at_3 value: 33.537 - type: recall_at_5 value: 40.542 - task: type: Retrieval dataset: name: MTEB ClimateFEVER type: climate-fever config: default split: test revision: None metrics: - type: map_at_1 value: 13.333999999999998 - type: map_at_10 value: 22.524 - type: map_at_100 value: 24.506 - type: map_at_1000 value: 24.715 - type: map_at_3 value: 19.022 - type: map_at_5 value: 20.693 - type: mrr_at_1 value: 29.186 - type: mrr_at_10 value: 41.22 - type: mrr_at_100 value: 42.16 - type: mrr_at_1000 value: 42.192 - type: mrr_at_3 value: 38.013000000000005 - type: mrr_at_5 value: 39.704 - type: ndcg_at_1 value: 29.186 - type: ndcg_at_10 value: 31.167 - type: ndcg_at_100 value: 38.879000000000005 - type: ndcg_at_1000 value: 42.376000000000005 - type: ndcg_at_3 value: 25.817 - type: ndcg_at_5 value: 27.377000000000002 - type: precision_at_1 value: 29.186 - type: precision_at_10 value: 9.693999999999999 - type: precision_at_100 value: 1.8030000000000002 - type: precision_at_1000 value: 0.246 - type: precision_at_3 value: 19.11 - type: precision_at_5 value: 14.344999999999999 - type: recall_at_1 value: 13.333999999999998 - type: recall_at_10 value: 37.092000000000006 - type: recall_at_100 value: 63.651 - type: recall_at_1000 value: 83.05 - type: recall_at_3 value: 23.74 - type: recall_at_5 value: 28.655 - task: type: Retrieval dataset: name: MTEB DBPedia type: dbpedia-entity config: default split: test revision: None metrics: - type: map_at_1 value: 9.151 - type: map_at_10 value: 19.653000000000002 - type: map_at_100 value: 28.053 - type: map_at_1000 value: 29.709000000000003 - type: map_at_3 value: 14.191 - type: map_at_5 value: 16.456 - type: mrr_at_1 value: 66.25 - type: mrr_at_10 value: 74.4 - type: mrr_at_100 value: 74.715 - type: mrr_at_1000 value: 74.726 - type: mrr_at_3 value: 72.417 - type: mrr_at_5 value: 73.667 - type: ndcg_at_1 value: 54.25 - type: ndcg_at_10 value: 40.77 - type: ndcg_at_100 value: 46.359 - type: ndcg_at_1000 value: 54.193000000000005 - type: ndcg_at_3 value: 44.832 - type: ndcg_at_5 value: 42.63 - type: precision_at_1 value: 66.25 - type: precision_at_10 value: 32.175 - type: precision_at_100 value: 10.668 - type: precision_at_1000 value: 2.067 - type: precision_at_3 value: 47.667 - type: precision_at_5 value: 41.3 - type: recall_at_1 value: 9.151 - type: recall_at_10 value: 25.003999999999998 - type: recall_at_100 value: 52.976 - type: recall_at_1000 value: 78.315 - type: recall_at_3 value: 15.487 - type: recall_at_5 value: 18.999 - task: type: Classification dataset: name: MTEB EmotionClassification type: mteb/emotion config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 51.89999999999999 - type: f1 value: 46.47777925067403 - task: type: Retrieval dataset: name: MTEB FEVER type: fever config: default split: test revision: None metrics: - type: map_at_1 value: 73.706 - type: map_at_10 value: 82.423 - type: map_at_100 value: 82.67999999999999 - type: map_at_1000 value: 82.694 - type: map_at_3 value: 81.328 - type: map_at_5 value: 82.001 - type: mrr_at_1 value: 79.613 - type: mrr_at_10 value: 87.07000000000001 - type: mrr_at_100 value: 87.169 - type: mrr_at_1000 value: 87.17 - type: mrr_at_3 value: 86.404 - type: mrr_at_5 value: 86.856 - type: ndcg_at_1 value: 79.613 - type: ndcg_at_10 value: 86.289 - type: ndcg_at_100 value: 87.201 - type: ndcg_at_1000 value: 87.428 - type: ndcg_at_3 value: 84.625 - type: ndcg_at_5 value: 85.53699999999999 - type: precision_at_1 value: 79.613 - type: precision_at_10 value: 10.399 - type: precision_at_100 value: 1.1079999999999999 - type: precision_at_1000 value: 0.11499999999999999 - type: precision_at_3 value: 32.473 - type: precision_at_5 value: 20.132 - type: recall_at_1 value: 73.706 - type: recall_at_10 value: 93.559 - type: recall_at_100 value: 97.188 - type: recall_at_1000 value: 98.555 - type: recall_at_3 value: 88.98700000000001 - type: recall_at_5 value: 91.373 - task: type: Retrieval dataset: name: MTEB FiQA2018 type: fiqa config: default split: test revision: None metrics: - type: map_at_1 value: 19.841 - type: map_at_10 value: 32.643 - type: map_at_100 value: 34.575 - type: map_at_1000 value: 34.736 - type: map_at_3 value: 28.317999999999998 - type: map_at_5 value: 30.964000000000002 - type: mrr_at_1 value: 39.660000000000004 - type: mrr_at_10 value: 48.620000000000005 - type: mrr_at_100 value: 49.384 - type: mrr_at_1000 value: 49.415 - type: mrr_at_3 value: 45.988 - type: mrr_at_5 value: 47.361 - type: ndcg_at_1 value: 39.660000000000004 - type: ndcg_at_10 value: 40.646 - type: ndcg_at_100 value: 47.657 - type: ndcg_at_1000 value: 50.428 - type: ndcg_at_3 value: 36.689 - type: ndcg_at_5 value: 38.211 - type: precision_at_1 value: 39.660000000000004 - type: precision_at_10 value: 11.235000000000001 - type: precision_at_100 value: 1.8530000000000002 - type: precision_at_1000 value: 0.23600000000000002 - type: precision_at_3 value: 24.587999999999997 - type: precision_at_5 value: 18.395 - type: recall_at_1 value: 19.841 - type: recall_at_10 value: 48.135 - type: recall_at_100 value: 74.224 - type: recall_at_1000 value: 90.826 - type: recall_at_3 value: 33.536 - type: recall_at_5 value: 40.311 - task: type: Retrieval dataset: name: MTEB HotpotQA type: hotpotqa config: default split: test revision: None metrics: - type: map_at_1 value: 40.358 - type: map_at_10 value: 64.497 - type: map_at_100 value: 65.362 - type: map_at_1000 value: 65.41900000000001 - type: map_at_3 value: 61.06700000000001 - type: map_at_5 value: 63.317 - type: mrr_at_1 value: 80.716 - type: mrr_at_10 value: 86.10799999999999 - type: mrr_at_100 value: 86.265 - type: mrr_at_1000 value: 86.27 - type: mrr_at_3 value: 85.271 - type: mrr_at_5 value: 85.82499999999999 - type: ndcg_at_1 value: 80.716 - type: ndcg_at_10 value: 72.597 - type: ndcg_at_100 value: 75.549 - type: ndcg_at_1000 value: 76.61 - type: ndcg_at_3 value: 67.874 - type: ndcg_at_5 value: 70.655 - type: precision_at_1 value: 80.716 - type: precision_at_10 value: 15.148 - type: precision_at_100 value: 1.745 - type: precision_at_1000 value: 0.188 - type: precision_at_3 value: 43.597 - type: precision_at_5 value: 28.351 - type: recall_at_1 value: 40.358 - type: recall_at_10 value: 75.739 - type: recall_at_100 value: 87.259 - type: recall_at_1000 value: 94.234 - type: recall_at_3 value: 65.39500000000001 - type: recall_at_5 value: 70.878 - task: type: Classification dataset: name: MTEB ImdbClassification type: mteb/imdb config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 90.80799999999998 - type: ap value: 86.81350378180757 - type: f1 value: 90.79901248314215 - task: type: Retrieval dataset: name: MTEB MSMARCO type: msmarco config: default split: dev revision: None metrics: - type: map_at_1 value: 22.096 - type: map_at_10 value: 34.384 - type: map_at_100 value: 35.541 - type: map_at_1000 value: 35.589999999999996 - type: map_at_3 value: 30.496000000000002 - type: map_at_5 value: 32.718 - type: mrr_at_1 value: 22.750999999999998 - type: mrr_at_10 value: 35.024 - type: mrr_at_100 value: 36.125 - type: mrr_at_1000 value: 36.168 - type: mrr_at_3 value: 31.225 - type: mrr_at_5 value: 33.416000000000004 - type: ndcg_at_1 value: 22.750999999999998 - type: ndcg_at_10 value: 41.351 - type: ndcg_at_100 value: 46.92 - type: ndcg_at_1000 value: 48.111 - type: ndcg_at_3 value: 33.439 - type: ndcg_at_5 value: 37.407000000000004 - type: precision_at_1 value: 22.750999999999998 - type: precision_at_10 value: 6.564 - type: precision_at_100 value: 0.935 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 14.288 - type: precision_at_5 value: 10.581999999999999 - type: recall_at_1 value: 22.096 - type: recall_at_10 value: 62.771 - type: recall_at_100 value: 88.529 - type: recall_at_1000 value: 97.55 - type: recall_at_3 value: 41.245 - type: recall_at_5 value: 50.788 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 94.16780665754673 - type: f1 value: 93.96331194859894 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 76.90606475148198 - type: f1 value: 58.58344986604187 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 76.14660390047075 - type: f1 value: 74.31533923533614 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 80.16139878950908 - type: f1 value: 80.18532656824924 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P type: mteb/medrxiv-clustering-p2p config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 32.949880906135085 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S type: mteb/medrxiv-clustering-s2s config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 31.56300351524862 - task: type: Reranking dataset: name: MTEB MindSmallReranking type: mteb/mind_small config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 31.196521894371315 - type: mrr value: 32.22644231694389 - task: type: Retrieval dataset: name: MTEB NFCorpus type: nfcorpus config: default split: test revision: None metrics: - type: map_at_1 value: 6.783 - type: map_at_10 value: 14.549000000000001 - type: map_at_100 value: 18.433 - type: map_at_1000 value: 19.949 - type: map_at_3 value: 10.936 - type: map_at_5 value: 12.514 - type: mrr_at_1 value: 47.368 - type: mrr_at_10 value: 56.42 - type: mrr_at_100 value: 56.908 - type: mrr_at_1000 value: 56.95 - type: mrr_at_3 value: 54.283 - type: mrr_at_5 value: 55.568 - type: ndcg_at_1 value: 45.666000000000004 - type: ndcg_at_10 value: 37.389 - type: ndcg_at_100 value: 34.253 - type: ndcg_at_1000 value: 43.059999999999995 - type: ndcg_at_3 value: 42.725 - type: ndcg_at_5 value: 40.193 - type: precision_at_1 value: 47.368 - type: precision_at_10 value: 27.988000000000003 - type: precision_at_100 value: 8.672 - type: precision_at_1000 value: 2.164 - type: precision_at_3 value: 40.248 - type: precision_at_5 value: 34.737 - type: recall_at_1 value: 6.783 - type: recall_at_10 value: 17.838 - type: recall_at_100 value: 33.672000000000004 - type: recall_at_1000 value: 66.166 - type: recall_at_3 value: 11.849 - type: recall_at_5 value: 14.205000000000002 - task: type: Retrieval dataset: name: MTEB NQ type: nq config: default split: test revision: None metrics: - type: map_at_1 value: 31.698999999999998 - type: map_at_10 value: 46.556 - type: map_at_100 value: 47.652 - type: map_at_1000 value: 47.68 - type: map_at_3 value: 42.492000000000004 - type: map_at_5 value: 44.763999999999996 - type: mrr_at_1 value: 35.747 - type: mrr_at_10 value: 49.242999999999995 - type: mrr_at_100 value: 50.052 - type: mrr_at_1000 value: 50.068 - type: mrr_at_3 value: 45.867000000000004 - type: mrr_at_5 value: 47.778999999999996 - type: ndcg_at_1 value: 35.717999999999996 - type: ndcg_at_10 value: 54.14600000000001 - type: ndcg_at_100 value: 58.672999999999995 - type: ndcg_at_1000 value: 59.279 - type: ndcg_at_3 value: 46.407 - type: ndcg_at_5 value: 50.181 - type: precision_at_1 value: 35.717999999999996 - type: precision_at_10 value: 8.844000000000001 - type: precision_at_100 value: 1.139 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 20.993000000000002 - type: precision_at_5 value: 14.791000000000002 - type: recall_at_1 value: 31.698999999999998 - type: recall_at_10 value: 74.693 - type: recall_at_100 value: 94.15299999999999 - type: recall_at_1000 value: 98.585 - type: recall_at_3 value: 54.388999999999996 - type: recall_at_5 value: 63.08200000000001 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval type: quora config: default split: test revision: None metrics: - type: map_at_1 value: 71.283 - type: map_at_10 value: 85.24000000000001 - type: map_at_100 value: 85.882 - type: map_at_1000 value: 85.897 - type: map_at_3 value: 82.326 - type: map_at_5 value: 84.177 - type: mrr_at_1 value: 82.21000000000001 - type: mrr_at_10 value: 88.228 - type: mrr_at_100 value: 88.32 - type: mrr_at_1000 value: 88.32 - type: mrr_at_3 value: 87.323 - type: mrr_at_5 value: 87.94800000000001 - type: ndcg_at_1 value: 82.17999999999999 - type: ndcg_at_10 value: 88.9 - type: ndcg_at_100 value: 90.079 - type: ndcg_at_1000 value: 90.158 - type: ndcg_at_3 value: 86.18299999999999 - type: ndcg_at_5 value: 87.71799999999999 - type: precision_at_1 value: 82.17999999999999 - type: precision_at_10 value: 13.464 - type: precision_at_100 value: 1.533 - type: precision_at_1000 value: 0.157 - type: precision_at_3 value: 37.693 - type: precision_at_5 value: 24.792 - type: recall_at_1 value: 71.283 - type: recall_at_10 value: 95.742 - type: recall_at_100 value: 99.67200000000001 - type: recall_at_1000 value: 99.981 - type: recall_at_3 value: 87.888 - type: recall_at_5 value: 92.24 - task: type: Clustering dataset: name: MTEB RedditClustering type: mteb/reddit-clustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.24267063669042 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P type: mteb/reddit-clustering-p2p config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 62.88056988932578 - task: type: Retrieval dataset: name: MTEB SCIDOCS type: scidocs config: default split: test revision: None metrics: - type: map_at_1 value: 4.903 - type: map_at_10 value: 13.202 - type: map_at_100 value: 15.5 - type: map_at_1000 value: 15.870999999999999 - type: map_at_3 value: 9.407 - type: map_at_5 value: 11.238 - type: mrr_at_1 value: 24.2 - type: mrr_at_10 value: 35.867 - type: mrr_at_100 value: 37.001 - type: mrr_at_1000 value: 37.043 - type: mrr_at_3 value: 32.5 - type: mrr_at_5 value: 34.35 - type: ndcg_at_1 value: 24.2 - type: ndcg_at_10 value: 21.731 - type: ndcg_at_100 value: 30.7 - type: ndcg_at_1000 value: 36.618 - type: ndcg_at_3 value: 20.72 - type: ndcg_at_5 value: 17.954 - type: precision_at_1 value: 24.2 - type: precision_at_10 value: 11.33 - type: precision_at_100 value: 2.4410000000000003 - type: precision_at_1000 value: 0.386 - type: precision_at_3 value: 19.667 - type: precision_at_5 value: 15.86 - type: recall_at_1 value: 4.903 - type: recall_at_10 value: 22.962 - type: recall_at_100 value: 49.563 - type: recall_at_1000 value: 78.238 - type: recall_at_3 value: 11.953 - type: recall_at_5 value: 16.067999999999998 - task: type: STS dataset: name: MTEB SICK-R type: mteb/sickr-sts config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 84.12694254604078 - type: cos_sim_spearman value: 80.30141815181918 - type: euclidean_pearson value: 81.34015449877128 - type: euclidean_spearman value: 80.13984197010849 - type: manhattan_pearson value: 81.31767068124086 - type: manhattan_spearman value: 80.11720513114103 - task: type: STS dataset: name: MTEB STS12 type: mteb/sts12-sts config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 86.13112984010417 - type: cos_sim_spearman value: 78.03063573402875 - type: euclidean_pearson value: 83.51928418844804 - type: euclidean_spearman value: 78.4045235411144 - type: manhattan_pearson value: 83.49981637388689 - type: manhattan_spearman value: 78.4042575139372 - task: type: STS dataset: name: MTEB STS13 type: mteb/sts13-sts config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 82.50327987379504 - type: cos_sim_spearman value: 84.18556767756205 - type: euclidean_pearson value: 82.69684424327679 - type: euclidean_spearman value: 83.5368106038335 - type: manhattan_pearson value: 82.57967581007374 - type: manhattan_spearman value: 83.43009053133697 - task: type: STS dataset: name: MTEB STS14 type: mteb/sts14-sts config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 82.50756863007814 - type: cos_sim_spearman value: 82.27204331279108 - type: euclidean_pearson value: 81.39535251429741 - type: euclidean_spearman value: 81.84386626336239 - type: manhattan_pearson value: 81.34281737280695 - type: manhattan_spearman value: 81.81149375673166 - task: type: STS dataset: name: MTEB STS15 type: mteb/sts15-sts config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 86.8727714856726 - type: cos_sim_spearman value: 87.95738287792312 - type: euclidean_pearson value: 86.62920602795887 - type: euclidean_spearman value: 87.05207355381243 - type: manhattan_pearson value: 86.53587918472225 - type: manhattan_spearman value: 86.95382961029586 - task: type: STS dataset: name: MTEB STS16 type: mteb/sts16-sts config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 83.52240359769479 - type: cos_sim_spearman value: 85.47685776238286 - type: euclidean_pearson value: 84.25815333483058 - type: euclidean_spearman value: 85.27415639683198 - type: manhattan_pearson value: 84.29127757025637 - type: manhattan_spearman value: 85.30226224917351 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 86.42501708915708 - type: cos_sim_spearman value: 86.42276182795041 - type: euclidean_pearson value: 86.5408207354761 - type: euclidean_spearman value: 85.46096321750838 - type: manhattan_pearson value: 86.54177303026881 - type: manhattan_spearman value: 85.50313151916117 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 64.86521089250766 - type: cos_sim_spearman value: 65.94868540323003 - type: euclidean_pearson value: 67.16569626533084 - type: euclidean_spearman value: 66.37667004134917 - type: manhattan_pearson value: 67.1482365102333 - type: manhattan_spearman value: 66.53240122580029 - task: type: STS dataset: name: MTEB STSBenchmark type: mteb/stsbenchmark-sts config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 84.64746265365318 - type: cos_sim_spearman value: 86.41888825906786 - type: euclidean_pearson value: 85.27453642725811 - type: euclidean_spearman value: 85.94095796602544 - type: manhattan_pearson value: 85.28643660505334 - type: manhattan_spearman value: 85.95028003260744 - task: type: Reranking dataset: name: MTEB SciDocsRR type: mteb/scidocs-reranking config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 87.48903153618527 - type: mrr value: 96.41081503826601 - task: type: Retrieval dataset: name: MTEB SciFact type: scifact config: default split: test revision: None metrics: - type: map_at_1 value: 58.594 - type: map_at_10 value: 69.296 - type: map_at_100 value: 69.782 - type: map_at_1000 value: 69.795 - type: map_at_3 value: 66.23 - type: map_at_5 value: 68.293 - type: mrr_at_1 value: 61.667 - type: mrr_at_10 value: 70.339 - type: mrr_at_100 value: 70.708 - type: mrr_at_1000 value: 70.722 - type: mrr_at_3 value: 68 - type: mrr_at_5 value: 69.56700000000001 - type: ndcg_at_1 value: 61.667 - type: ndcg_at_10 value: 74.039 - type: ndcg_at_100 value: 76.103 - type: ndcg_at_1000 value: 76.47800000000001 - type: ndcg_at_3 value: 68.967 - type: ndcg_at_5 value: 71.96900000000001 - type: precision_at_1 value: 61.667 - type: precision_at_10 value: 9.866999999999999 - type: precision_at_100 value: 1.097 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 27.111 - type: precision_at_5 value: 18.2 - type: recall_at_1 value: 58.594 - type: recall_at_10 value: 87.422 - type: recall_at_100 value: 96.667 - type: recall_at_1000 value: 99.667 - type: recall_at_3 value: 74.217 - type: recall_at_5 value: 81.539 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.85049504950496 - type: cos_sim_ap value: 96.33111544137081 - type: cos_sim_f1 value: 92.35443037974684 - type: cos_sim_precision value: 93.53846153846153 - type: cos_sim_recall value: 91.2 - type: dot_accuracy value: 99.82376237623762 - type: dot_ap value: 95.38082527310888 - type: dot_f1 value: 90.90909090909092 - type: dot_precision value: 92.90187891440502 - type: dot_recall value: 89 - type: euclidean_accuracy value: 99.84851485148515 - type: euclidean_ap value: 96.32316003996347 - type: euclidean_f1 value: 92.2071392659628 - type: euclidean_precision value: 92.71991911021233 - type: euclidean_recall value: 91.7 - type: manhattan_accuracy value: 99.84851485148515 - type: manhattan_ap value: 96.3655668249217 - type: manhattan_f1 value: 92.18356026222895 - type: manhattan_precision value: 92.98067141403867 - type: manhattan_recall value: 91.4 - type: max_accuracy value: 99.85049504950496 - type: max_ap value: 96.3655668249217 - type: max_f1 value: 92.35443037974684 - task: type: Clustering dataset: name: MTEB StackExchangeClustering type: mteb/stackexchange-clustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 65.94861371629051 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P type: mteb/stackexchange-clustering-p2p config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 35.009430451385 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 54.61164066427969 - type: mrr value: 55.49710603938544 - task: type: Summarization dataset: name: MTEB SummEval type: mteb/summeval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 30.622620124907662 - type: cos_sim_spearman value: 31.0678351356163 - type: dot_pearson value: 30.863727693306814 - type: dot_spearman value: 31.230306567021255 - task: type: Retrieval dataset: name: MTEB TRECCOVID type: trec-covid config: default split: test revision: None metrics: - type: map_at_1 value: 0.22 - type: map_at_10 value: 2.011 - type: map_at_100 value: 10.974 - type: map_at_1000 value: 25.819 - type: map_at_3 value: 0.6649999999999999 - type: map_at_5 value: 1.076 - type: mrr_at_1 value: 86 - type: mrr_at_10 value: 91.8 - type: mrr_at_100 value: 91.8 - type: mrr_at_1000 value: 91.8 - type: mrr_at_3 value: 91 - type: mrr_at_5 value: 91.8 - type: ndcg_at_1 value: 82 - type: ndcg_at_10 value: 78.07300000000001 - type: ndcg_at_100 value: 58.231 - type: ndcg_at_1000 value: 51.153000000000006 - type: ndcg_at_3 value: 81.123 - type: ndcg_at_5 value: 81.059 - type: precision_at_1 value: 86 - type: precision_at_10 value: 83 - type: precision_at_100 value: 59.38 - type: precision_at_1000 value: 22.55 - type: precision_at_3 value: 87.333 - type: precision_at_5 value: 86.8 - type: recall_at_1 value: 0.22 - type: recall_at_10 value: 2.2079999999999997 - type: recall_at_100 value: 14.069 - type: recall_at_1000 value: 47.678 - type: recall_at_3 value: 0.7040000000000001 - type: recall_at_5 value: 1.161 - task: type: Retrieval dataset: name: MTEB Touche2020 type: webis-touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.809 - type: map_at_10 value: 10.394 - type: map_at_100 value: 16.598 - type: map_at_1000 value: 18.142 - type: map_at_3 value: 5.572 - type: map_at_5 value: 7.1370000000000005 - type: mrr_at_1 value: 32.653 - type: mrr_at_10 value: 46.564 - type: mrr_at_100 value: 47.469 - type: mrr_at_1000 value: 47.469 - type: mrr_at_3 value: 42.177 - type: mrr_at_5 value: 44.524 - type: ndcg_at_1 value: 30.612000000000002 - type: ndcg_at_10 value: 25.701 - type: ndcg_at_100 value: 37.532 - type: ndcg_at_1000 value: 48.757 - type: ndcg_at_3 value: 28.199999999999996 - type: ndcg_at_5 value: 25.987 - type: precision_at_1 value: 32.653 - type: precision_at_10 value: 23.469 - type: precision_at_100 value: 7.9799999999999995 - type: precision_at_1000 value: 1.5350000000000001 - type: precision_at_3 value: 29.932 - type: precision_at_5 value: 26.122 - type: recall_at_1 value: 2.809 - type: recall_at_10 value: 16.887 - type: recall_at_100 value: 48.67 - type: recall_at_1000 value: 82.89699999999999 - type: recall_at_3 value: 6.521000000000001 - type: recall_at_5 value: 9.609 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification type: mteb/toxic_conversations_50k config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.57860000000001 - type: ap value: 13.82629211536393 - type: f1 value: 54.59860966183956 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification type: mteb/tweet_sentiment_extraction config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 59.38030560271647 - type: f1 value: 59.69685552567865 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering type: mteb/twentynewsgroups-clustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 51.4736717043405 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.92853311080646 - type: cos_sim_ap value: 77.67872502591382 - type: cos_sim_f1 value: 70.33941236068895 - type: cos_sim_precision value: 67.63273258645884 - type: cos_sim_recall value: 73.27176781002639 - type: dot_accuracy value: 85.79603027954938 - type: dot_ap value: 73.73786190233379 - type: dot_f1 value: 67.3437901774235 - type: dot_precision value: 65.67201604814443 - type: dot_recall value: 69.10290237467018 - type: euclidean_accuracy value: 86.94045419324074 - type: euclidean_ap value: 77.6687791535167 - type: euclidean_f1 value: 70.47209214023542 - type: euclidean_precision value: 67.7207492094381 - type: euclidean_recall value: 73.45646437994723 - type: manhattan_accuracy value: 86.87488823985218 - type: manhattan_ap value: 77.63373392430728 - type: manhattan_f1 value: 70.40920716112532 - type: manhattan_precision value: 68.31265508684864 - type: manhattan_recall value: 72.63852242744063 - type: max_accuracy value: 86.94045419324074 - type: max_ap value: 77.67872502591382 - type: max_f1 value: 70.47209214023542 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 88.67155664221679 - type: cos_sim_ap value: 85.64591703003417 - type: cos_sim_f1 value: 77.59531005352656 - type: cos_sim_precision value: 73.60967184801382 - type: cos_sim_recall value: 82.03726516784724 - type: dot_accuracy value: 88.41541506578181 - type: dot_ap value: 84.6482788957769 - type: dot_f1 value: 77.04748541466657 - type: dot_precision value: 74.02440754931176 - type: dot_recall value: 80.3279950723745 - type: euclidean_accuracy value: 88.63080684596576 - type: euclidean_ap value: 85.44570045321562 - type: euclidean_f1 value: 77.28769403336106 - type: euclidean_precision value: 72.90600040958427 - type: euclidean_recall value: 82.22975053895904 - type: manhattan_accuracy value: 88.59393798269105 - type: manhattan_ap value: 85.40271361038187 - type: manhattan_f1 value: 77.17606419344392 - type: manhattan_precision value: 72.4447747078295 - type: manhattan_recall value: 82.5685247921158 - type: max_accuracy value: 88.67155664221679 - type: max_ap value: 85.64591703003417 - type: max_f1 value: 77.59531005352656 --- ***See Disclaimer below*** ---- # A Teradata Vantage compatible Embeddings Model # BAAI/bge-base-en-v1.5 ## Overview of this Model An Embedding Model which maps text (sentence/ paragraphs) into a vector. The [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) model well known for its effectiveness in capturing semantic meanings in text data. It's a state-of-the-art model trained on a large corpus, capable of generating high-quality text embeddings. - 109.48M params (Sizes in ONNX format - "fp32": 415.72MB, "int8": 104.75MB, "uint8": 104.75MB) - 512 maximum input tokens - 768 dimensions of output vector - Licence: mit. The released models can be used for commercial purposes free of charge. - Reference to Original Model: https://huggingface.co/BAAI/bge-base-en-v1.5 ## Quickstart: Deploying this Model in Teradata Vantage We have pre-converted the model into the ONNX format compatible with BYOM 6.0, eliminating the need for manual conversion. **Note:** Ensure you have access to a Teradata Database with BYOM 6.0 installed. To get started, clone the pre-converted model directly from the Teradata HuggingFace repository. ```python import teradataml as tdml import getpass from huggingface_hub import hf_hub_download model_name = "bge-base-en-v1.5" number_dimensions_output = 768 model_file_name = "model.onnx" # Step 1: Download Model from Teradata HuggingFace Page hf_hub_download(repo_id=f"Teradata/{model_name}", filename=f"onnx/{model_file_name}", local_dir="./") hf_hub_download(repo_id=f"Teradata/{model_name}", filename=f"tokenizer.json", local_dir="./") # Step 2: Create Connection to Vantage tdml.create_context(host = input('enter your hostname'), username=input('enter your username'), password = getpass.getpass("enter your password")) # Step 3: Load Models into Vantage # a) Embedding model tdml.save_byom(model_id = model_name, # must be unique in the models table model_file = f"onnx/{model_file_name}", table_name = 'embeddings_models' ) # b) Tokenizer tdml.save_byom(model_id = model_name, # must be unique in the models table model_file = 'tokenizer.json', table_name = 'embeddings_tokenizers') # Step 4: Test ONNXEmbeddings Function # Note that ONNXEmbeddings expects the 'payload' column to be 'txt'. # If it has got a different name, just rename it in a subquery/CTE. input_table = "emails.emails" embeddings_query = f""" SELECT * from mldb.ONNXEmbeddings( on {input_table} as InputTable on (select * from embeddings_models where model_id = '{model_name}') as ModelTable DIMENSION on (select model as tokenizer from embeddings_tokenizers where model_id = '{model_name}') as TokenizerTable DIMENSION using Accumulate('id', 'txt') ModelOutputTensor('sentence_embedding') EnableMemoryCheck('false') OutputFormat('FLOAT32({number_dimensions_output})') OverwriteCachedModel('true') ) a """ DF_embeddings = tdml.DataFrame.from_query(embeddings_query) DF_embeddings ``` ## What Can I Do with the Embeddings? Teradata Vantage includes pre-built in-database functions to process embeddings further. Explore the following examples: - **Semantic Clustering with TD_KMeans:** [Semantic Clustering Python Notebook](https://github.com/Teradata/jupyter-demos/blob/main/UseCases/Language_Models_InVantage/Semantic_Clustering_Python.ipynb) - **Semantic Distance with TD_VectorDistance:** [Semantic Similarity Python Notebook](https://github.com/Teradata/jupyter-demos/blob/main/UseCases/Language_Models_InVantage/Semantic_Similarity_Python.ipynb) - **RAG-Based Application with TD_VectorDistance:** [RAG and Bedrock Query PDF Notebook](https://github.com/Teradata/jupyter-demos/blob/main/UseCases/Language_Models_InVantage/RAG_and_Bedrock_QueryPDF.ipynb) ## Deep Dive into Model Conversion to ONNX **The steps below outline how we converted the open-source Hugging Face model into an ONNX file compatible with the in-database ONNXEmbeddings function.** You do not need to perform these steps—they are provided solely for documentation and transparency. However, they may be helpful if you wish to convert another model to the required format. ### Part 1. Importing and Converting Model using optimum We start by importing the pre-trained [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) model from Hugging Face. To enhance performance and ensure compatibility with various execution environments, we'll use the [Optimum](https://github.com/huggingface/optimum) utility to convert the model into the ONNX (Open Neural Network Exchange) format. After conversion to ONNX, we are fixing the opset in the ONNX file for compatibility with ONNX runtime used in Teradata Vantage We are generating ONNX files for multiple different precisions: fp32, int8, uint8 You can find the detailed conversion steps in the file [convert.py](./convert.py) ### Part 2. Running the model in Python with onnxruntime & compare results Once the fixes are applied, we proceed to test the correctness of the ONNX model by calculating cosine similarity between two texts using native SentenceTransformers and ONNX runtime, comparing the results. If the results are identical, it confirms that the ONNX model gives the same result as the native models, validating its correctness and suitability for further use in the database. ```python import onnxruntime as rt from sentence_transformers.util import cos_sim from sentence_transformers import SentenceTransformer import transformers sentences_1 = 'How is the weather today?' sentences_2 = 'What is the current weather like today?' # Calculate ONNX result tokenizer = transformers.AutoTokenizer.from_pretrained("BAAI/bge-base-en-v1.5") predef_sess = rt.InferenceSession("onnx/model.onnx") enc1 = tokenizer(sentences_1) embeddings_1_onnx = predef_sess.run(None, {"input_ids": [enc1.input_ids], "attention_mask": [enc1.attention_mask]}) enc2 = tokenizer(sentences_2) embeddings_2_onnx = predef_sess.run(None, {"input_ids": [enc2.input_ids], "attention_mask": [enc2.attention_mask]}) # Calculate embeddings with SentenceTransformer model = SentenceTransformer(model_id, trust_remote_code=True) embeddings_1_sentence_transformer = model.encode(sentences_1, normalize_embeddings=True, trust_remote_code=True) embeddings_2_sentence_transformer = model.encode(sentences_2, normalize_embeddings=True, trust_remote_code=True) # Compare results print("Cosine similiarity for embeddings calculated with ONNX:" + str(cos_sim(embeddings_1_onnx[1][0], embeddings_2_onnx[1][0]))) print("Cosine similiarity for embeddings calculated with SentenceTransformer:" + str(cos_sim(embeddings_1_sentence_transformer, embeddings_2_sentence_transformer))) ``` You can find the detailed ONNX vs. SentenceTransformer result comparison steps in the file [test_local.py](./test_local.py) ---- DISCLAIMER: The content herein (“Content”) is provided “AS IS” and is not covered by any Teradata Operations, Inc. and its affiliates (“Teradata”) agreements. Its listing here does not constitute certification or endorsement by Teradata. To the extent any of the Content contains or is related to any artificial intelligence (“AI”) or other language learning models (“Models”) that interoperate with the products and services of Teradata, by accessing, bringing, deploying or using such Models, you acknowledge and agree that you are solely responsible for ensuring compliance with all applicable laws, regulations, and restrictions governing the use, deployment, and distribution of AI technologies. This includes, but is not limited to, AI Diffusion Rules, European Union AI Act, AI-related laws and regulations, privacy laws, export controls, and financial or sector-specific regulations. While Teradata may provide support, guidance, or assistance in the deployment or implementation of Models to interoperate with Teradata’s products and/or services, you remain fully responsible for ensuring that your Models, data, and applications comply with all relevant legal and regulatory obligations. Our assistance does not constitute legal or regulatory approval, and Teradata disclaims any liability arising from non-compliance with applicable laws. You must determine the suitability of the Models for any purpose. Given the probabilistic nature of machine learning and modeling, the use of the Models may in some situations result in incorrect output that does not accurately reflect the action generated. You should evaluate the accuracy of any output as appropriate for your use case, including by using human review of the output.
[ "BIOSSES", "SCIFACT" ]
NoodlesWu/Llama3.1-Aloe-Beta-8B-Q4_K_M-GGUF
NoodlesWu
question-answering
[ "transformers", "gguf", "biology", "medical", "healthcare", "llama-cpp", "gguf-my-repo", "question-answering", "en", "dataset:HPAI-BSC/Aloe-Beta-General-Collection", "dataset:HPAI-BSC/chain-of-diagnosis", "dataset:HPAI-BSC/MedS-Ins", "dataset:HPAI-BSC/ultramedical", "dataset:HPAI-BSC/pubmedqa-cot-llama31", "dataset:HPAI-BSC/medqa-cot-llama31", "dataset:HPAI-BSC/medmcqa-cot-llama31", "dataset:HPAI-BSC/headqa-cot-llama31", "dataset:HPAI-BSC/MMLU-medical-cot-llama31", "dataset:HPAI-BSC/Polymed-QA", "base_model:HPAI-BSC/Llama3.1-Aloe-Beta-8B", "base_model:quantized:HPAI-BSC/Llama3.1-Aloe-Beta-8B", "license:llama3.1", "endpoints_compatible", "region:us", "conversational" ]
2025-02-19T08:11:36Z
2025-02-19T08:11:59+00:00
32
0
--- base_model: HPAI-BSC/Llama3.1-Aloe-Beta-8B datasets: - HPAI-BSC/Aloe-Beta-General-Collection - HPAI-BSC/chain-of-diagnosis - HPAI-BSC/MedS-Ins - HPAI-BSC/ultramedical - HPAI-BSC/pubmedqa-cot-llama31 - HPAI-BSC/medqa-cot-llama31 - HPAI-BSC/medmcqa-cot-llama31 - HPAI-BSC/headqa-cot-llama31 - HPAI-BSC/MMLU-medical-cot-llama31 - HPAI-BSC/Polymed-QA - HPAI-BSC/Aloe-Beta-General-Collection - HPAI-BSC/Aloe-Beta-General-Collection language: - en library_name: transformers license: llama3.1 pipeline_tag: question-answering tags: - biology - medical - healthcare - llama-cpp - gguf-my-repo --- # NoodlesWu/Llama3.1-Aloe-Beta-8B-Q4_K_M-GGUF This model was converted to GGUF format from [`HPAI-BSC/Llama3.1-Aloe-Beta-8B`](https://huggingface.co/HPAI-BSC/Llama3.1-Aloe-Beta-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/HPAI-BSC/Llama3.1-Aloe-Beta-8B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo NoodlesWu/Llama3.1-Aloe-Beta-8B-Q4_K_M-GGUF --hf-file llama3.1-aloe-beta-8b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo NoodlesWu/Llama3.1-Aloe-Beta-8B-Q4_K_M-GGUF --hf-file llama3.1-aloe-beta-8b-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo NoodlesWu/Llama3.1-Aloe-Beta-8B-Q4_K_M-GGUF --hf-file llama3.1-aloe-beta-8b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo NoodlesWu/Llama3.1-Aloe-Beta-8B-Q4_K_M-GGUF --hf-file llama3.1-aloe-beta-8b-q4_k_m.gguf -c 2048 ```
[ "MEDQA", "PUBMEDQA" ]
Qwe1325/Llama-Breeze2-3B-Instruct_4bit
Qwe1325
null
[ "safetensors", "internvl_chat", "custom_code", "en", "zh", "arxiv:2501.13921", "license:llama3.2", "4-bit", "bitsandbytes", "region:us" ]
2025-02-27T02:18:13Z
2025-02-27T04:17:44+00:00
32
0
--- language: - en - zh license: llama3.2 --- # Llama-Breeze2-3B-Instruct-v0_1 【[Paper](https://arxiv.org/abs/2501.13921)】◇【[Kaggle Demo](https://www.kaggle.com/code/ycckaggle/demo-breeze-2-3b)】◇【[Collection](https://huggingface.co/collections/MediaTek-Research/llama-breeze2-67863158443a06a72dd29900)】 **The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on LLaMA with Vision-Aware and Function-Calling Capabilities** Llama Breeze 2 is a suite of advanced multi-modal language models, available in 3B and 8B parameter configurations, specifically designed to enhance Traditional Chinese language representation. Building upon the [LLaMA 3.2](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/), Breeze 2 continues pretraining on an extensive corpus to enhance the linguistic and cultural heritage of Traditional Chinese. It incorporates vision-aware capabilities through a visual encoder and a bridge module, and supports function-calling via prompt templates and post-training on function-calling data. *Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.* *We list all contributors in alphabetical order of their first names, as follows: Chan-Jan Hsu (許湛然), Chia-Sheng Liu (劉佳昇), Meng-Hsi Chen (陳孟羲), Muxi Chen (陳沐希), Po-Chun Hsu (許博竣), Yi-Chang Chen (陳宜昌), and the supervisor Da-Shan Shiu (許大山).* ## Installation ``` pip3 install transformers==4.47.0 pip3 install -U mtkresearch ``` ```python from transformers import AutoModel, AutoTokenizer from transformers import GenerationConfig import torch from mtkresearch.llm.prompt import MRPromptV3 model_id = 'Qwe1325/Llama-Breeze2-3B-Instruct_4bit' model = AutoModel.from_pretrained( model_id, torch_dtype=torch.bfloat16, load_in_4bit=True, low_cpu_mem_usage=True, trust_remote_code=True, device_map='auto', img_context_token_id=128212 ).eval() tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, use_fast=False) generation_config = GenerationConfig( max_new_tokens=2048, do_sample=True, temperature=0.01, top_p=0.01, repetition_penalty=1.1, eos_token_id=128009 ) prompt_engine = MRPromptV3() sys_prompt = 'You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.' def _inference(tokenizer, model, generation_config, prompt, pixel_values=None): inputs = tokenizer(prompt, return_tensors="pt").to(model.device) if pixel_values is None: output_tensors = model.generate(**inputs, generation_config=generation_config) else: output_tensors = model.generate(**inputs, generation_config=generation_config, pixel_values=pixel_values.to(model.dtype).to(model.device)) output_str = tokenizer.decode(output_tensors[0]) return output_str ``` ## Feature: Instruction Following ```python conversations = [ {"role": "system", "content": sys_prompt}, {"role": "user", "content": "請問什麼是深度學習？"}, ] prompt = prompt_engine.get_prompt(conversations) output_str = _inference(tokenizer, model, generation_config, prompt) result = prompt_engine.parse_generated_str(output_str) print(result) # {'role': 'assistant', 'content': '深度學習是一種人工智慧技術，主要是透過類似於大腦神經網路的方式來處理和分析資料。這個方法利用多層的人工神經元模仿生物神經網路的運作模式，讓電腦能夠從大量數據中學習並做出預測或決策。\n\n簡單來說，深度學習就是一種用機器學習的方式來訓練電腦，使其能夠像人類一樣理解、分辨及解決問題。這項技術已被廣泛應用在各種領域，如圖像識別、自然語言處理、語音辨識以及自動駕駛等方面。'} ``` ## Feature: Visual Instruction Following Example Image: ![img_example](https://huggingface.co/MediaTek-Research/Breeze2-8B-Instruct-v0_1/resolve/main/misc/test_big_data.png) ```python conversations = [ {"role": "system", "content": sys_prompt}, {"role": "user", "content": [ { "type": "image", "image_path": /path/to/example-image, }, { "type": "text", "text": "請問第二名可獲得多少獎金？" }, ]}, ] prompt, pixel_values = prompt_engine.get_prompt(conversations) output_str = _inference(tokenizer, model, generation_config, prompt, pixel_values=pixel_values) result = prompt_engine.parse_generated_str(output_str) print(result) # {'role': 'assistant', 'content': '第二名可獲得20萬元整。'} ``` ## Feature: Function Calling ```python import json functions = [ { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"] } }, "required": ["location"] } } ] def fake_get_current_weather(location, unit=None): return {'temperature': 30} mapping = { 'get_current_weather': fake_get_current_weather } # stage 1: query conversations = [ {"role": "user", "content": "請問台北目前溫度是攝氏幾度？"}, ] prompt = prompt_engine.get_prompt(conversations, functions=functions) output_str = _inference(tokenizer, model, generation_config, prompt) result = prompt_engine.parse_generated_str(output_str) print(result) # {'role': 'assistant', 'tool_calls': [{'id': 'call_iuwELWUShiAKE16CVoumawZ4', 'type': 'function', 'function': {'name': 'get_current_weather', 'arguments': '{"location": "台北", "unit": "celsius"}'}}]} ``` ```python # stage 2: execute called functions conversations.append(result) tool_call = result['tool_calls'][0] func_name = tool_call['function']['name'] func = mapping[func_name] arguments = json.loads(tool_call['function']['arguments']) called_result = func(**arguments) # stage 3: put executed results conversations.append( { 'role': 'tool', 'tool_call_id': tool_call['id'], 'name': func_name, 'content': json.dumps(called_result) } ) prompt = prompt_engine.get_prompt(conversations, functions=functions) output_str2 = _inference(tokenizer, model, generation_config, prompt) result2 = prompt_engine.parse_generated_str(output_str2) print(result2) # {'role': 'assistant', 'content': '台北目前的溫度是攝氏30度。'} ``` ## Citation ``` @article{breeze2, title={The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on LLaMA with Vision-Aware and Function-Calling Capabilities}, author={Breeze Team, MediaTek Research}, journal={arXiv}, year={2025}, url={https://arxiv.org/abs/2501.13921} } ```
[ "CHIA" ]
Hoshino-Yumetsuki/gte-Qwen2-7B-instruct-Q8_0-GGUF
Hoshino-Yumetsuki
sentence-similarity
[ "sentence-transformers", "gguf", "mteb", "transformers", "Qwen2", "sentence-similarity", "llama-cpp", "gguf-my-repo", "base_model:Alibaba-NLP/gte-Qwen2-7B-instruct", "base_model:quantized:Alibaba-NLP/gte-Qwen2-7B-instruct", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us", "conversational" ]
2025-03-02T13:40:04Z
2025-03-02T13:40:40+00:00
32
0
--- base_model: Alibaba-NLP/gte-Qwen2-7B-instruct license: apache-2.0 tags: - mteb - sentence-transformers - transformers - Qwen2 - sentence-similarity - llama-cpp - gguf-my-repo model-index: - name: gte-qwen2-7B-instruct results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 91.31343283582089 - type: ap value: 67.64251402604096 - type: f1 value: 87.53372530755692 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification type: mteb/amazon_polarity config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 97.497825 - type: ap value: 96.30329547047529 - type: f1 value: 97.49769793778039 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 62.564 - type: f1 value: 60.975777935041066 - task: type: Retrieval dataset: name: MTEB ArguAna type: mteb/arguana config: default split: test revision: c22ab2a51041ffd869aaddef7af8d8215647e41a metrics: - type: map_at_1 value: 36.486000000000004 - type: map_at_10 value: 54.842 - type: map_at_100 value: 55.206999999999994 - type: map_at_1000 value: 55.206999999999994 - type: map_at_3 value: 49.893 - type: map_at_5 value: 53.105000000000004 - type: mrr_at_1 value: 37.34 - type: mrr_at_10 value: 55.143 - type: mrr_at_100 value: 55.509 - type: mrr_at_1000 value: 55.509 - type: mrr_at_3 value: 50.212999999999994 - type: mrr_at_5 value: 53.432 - type: ndcg_at_1 value: 36.486000000000004 - type: ndcg_at_10 value: 64.273 - type: ndcg_at_100 value: 65.66199999999999 - type: ndcg_at_1000 value: 65.66199999999999 - type: ndcg_at_3 value: 54.352999999999994 - type: ndcg_at_5 value: 60.131 - type: precision_at_1 value: 36.486000000000004 - type: precision_at_10 value: 9.395000000000001 - type: precision_at_100 value: 0.996 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 22.428 - type: precision_at_5 value: 16.259 - type: recall_at_1 value: 36.486000000000004 - type: recall_at_10 value: 93.95400000000001 - type: recall_at_100 value: 99.644 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 67.283 - type: recall_at_5 value: 81.294 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P type: mteb/arxiv-clustering-p2p config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 56.461169803700564 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S type: mteb/arxiv-clustering-s2s config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 51.73600434466286 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions type: mteb/askubuntudupquestions-reranking config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 67.57827065898053 - type: mrr value: 79.08136569493911 - task: type: STS dataset: name: MTEB BIOSSES type: mteb/biosses-sts config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 83.53324575999243 - type: cos_sim_spearman value: 81.37173362822374 - type: euclidean_pearson value: 82.19243335103444 - type: euclidean_spearman value: 81.33679307304334 - type: manhattan_pearson value: 82.38752665975699 - type: manhattan_spearman value: 81.31510583189689 - task: type: Classification dataset: name: MTEB Banking77Classification type: mteb/banking77 config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 87.56818181818181 - type: f1 value: 87.25826722019875 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P type: mteb/biorxiv-clustering-p2p config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 50.09239610327673 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S type: mteb/biorxiv-clustering-s2s config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 46.64733054606282 - task: type: Retrieval dataset: name: MTEB CQADupstackAndroidRetrieval type: BeIR/cqadupstack config: default split: test revision: f46a197baaae43b4f621051089b82a364682dfeb metrics: - type: map_at_1 value: 33.997 - type: map_at_10 value: 48.176 - type: map_at_100 value: 49.82 - type: map_at_1000 value: 49.924 - type: map_at_3 value: 43.626 - type: map_at_5 value: 46.275 - type: mrr_at_1 value: 42.059999999999995 - type: mrr_at_10 value: 53.726 - type: mrr_at_100 value: 54.398 - type: mrr_at_1000 value: 54.416 - type: mrr_at_3 value: 50.714999999999996 - type: mrr_at_5 value: 52.639 - type: ndcg_at_1 value: 42.059999999999995 - type: ndcg_at_10 value: 55.574999999999996 - type: ndcg_at_100 value: 60.744 - type: ndcg_at_1000 value: 61.85699999999999 - type: ndcg_at_3 value: 49.363 - type: ndcg_at_5 value: 52.44 - type: precision_at_1 value: 42.059999999999995 - type: precision_at_10 value: 11.101999999999999 - type: precision_at_100 value: 1.73 - type: precision_at_1000 value: 0.218 - type: precision_at_3 value: 24.464 - type: precision_at_5 value: 18.026 - type: recall_at_1 value: 33.997 - type: recall_at_10 value: 70.35900000000001 - type: recall_at_100 value: 91.642 - type: recall_at_1000 value: 97.977 - type: recall_at_3 value: 52.76 - type: recall_at_5 value: 61.148 - task: type: Retrieval dataset: name: MTEB CQADupstackEnglishRetrieval type: BeIR/cqadupstack config: default split: test revision: ad9991cb51e31e31e430383c75ffb2885547b5f0 metrics: - type: map_at_1 value: 35.884 - type: map_at_10 value: 48.14 - type: map_at_100 value: 49.5 - type: map_at_1000 value: 49.63 - type: map_at_3 value: 44.646 - type: map_at_5 value: 46.617999999999995 - type: mrr_at_1 value: 44.458999999999996 - type: mrr_at_10 value: 53.751000000000005 - type: mrr_at_100 value: 54.37800000000001 - type: mrr_at_1000 value: 54.415 - type: mrr_at_3 value: 51.815 - type: mrr_at_5 value: 52.882 - type: ndcg_at_1 value: 44.458999999999996 - type: ndcg_at_10 value: 54.157 - type: ndcg_at_100 value: 58.362 - type: ndcg_at_1000 value: 60.178 - type: ndcg_at_3 value: 49.661 - type: ndcg_at_5 value: 51.74999999999999 - type: precision_at_1 value: 44.458999999999996 - type: precision_at_10 value: 10.248 - type: precision_at_100 value: 1.5890000000000002 - type: precision_at_1000 value: 0.207 - type: precision_at_3 value: 23.928 - type: precision_at_5 value: 16.878999999999998 - type: recall_at_1 value: 35.884 - type: recall_at_10 value: 64.798 - type: recall_at_100 value: 82.345 - type: recall_at_1000 value: 93.267 - type: recall_at_3 value: 51.847 - type: recall_at_5 value: 57.601 - task: type: Retrieval dataset: name: MTEB CQADupstackGamingRetrieval type: BeIR/cqadupstack config: default split: test revision: 4885aa143210c98657558c04aaf3dc47cfb54340 metrics: - type: map_at_1 value: 39.383 - type: map_at_10 value: 53.714 - type: map_at_100 value: 54.838 - type: map_at_1000 value: 54.87800000000001 - type: map_at_3 value: 50.114999999999995 - type: map_at_5 value: 52.153000000000006 - type: mrr_at_1 value: 45.016 - type: mrr_at_10 value: 56.732000000000006 - type: mrr_at_100 value: 57.411 - type: mrr_at_1000 value: 57.431 - type: mrr_at_3 value: 54.044000000000004 - type: mrr_at_5 value: 55.639 - type: ndcg_at_1 value: 45.016 - type: ndcg_at_10 value: 60.228 - type: ndcg_at_100 value: 64.277 - type: ndcg_at_1000 value: 65.07 - type: ndcg_at_3 value: 54.124 - type: ndcg_at_5 value: 57.147000000000006 - type: precision_at_1 value: 45.016 - type: precision_at_10 value: 9.937 - type: precision_at_100 value: 1.288 - type: precision_at_1000 value: 0.13899999999999998 - type: precision_at_3 value: 24.471999999999998 - type: precision_at_5 value: 16.991 - type: recall_at_1 value: 39.383 - type: recall_at_10 value: 76.175 - type: recall_at_100 value: 93.02 - type: recall_at_1000 value: 98.60900000000001 - type: recall_at_3 value: 60.265 - type: recall_at_5 value: 67.46600000000001 - task: type: Retrieval dataset: name: MTEB CQADupstackGisRetrieval type: BeIR/cqadupstack config: default split: test revision: 5003b3064772da1887988e05400cf3806fe491f2 metrics: - type: map_at_1 value: 27.426000000000002 - type: map_at_10 value: 37.397000000000006 - type: map_at_100 value: 38.61 - type: map_at_1000 value: 38.678000000000004 - type: map_at_3 value: 34.150999999999996 - type: map_at_5 value: 36.137 - type: mrr_at_1 value: 29.944 - type: mrr_at_10 value: 39.654 - type: mrr_at_100 value: 40.638000000000005 - type: mrr_at_1000 value: 40.691 - type: mrr_at_3 value: 36.817 - type: mrr_at_5 value: 38.524 - type: ndcg_at_1 value: 29.944 - type: ndcg_at_10 value: 43.094 - type: ndcg_at_100 value: 48.789 - type: ndcg_at_1000 value: 50.339999999999996 - type: ndcg_at_3 value: 36.984 - type: ndcg_at_5 value: 40.248 - type: precision_at_1 value: 29.944 - type: precision_at_10 value: 6.78 - type: precision_at_100 value: 1.024 - type: precision_at_1000 value: 0.11800000000000001 - type: precision_at_3 value: 15.895000000000001 - type: precision_at_5 value: 11.39 - type: recall_at_1 value: 27.426000000000002 - type: recall_at_10 value: 58.464000000000006 - type: recall_at_100 value: 84.193 - type: recall_at_1000 value: 95.52000000000001 - type: recall_at_3 value: 42.172 - type: recall_at_5 value: 50.101 - task: type: Retrieval dataset: name: MTEB CQADupstackMathematicaRetrieval type: BeIR/cqadupstack config: default split: test revision: 90fceea13679c63fe563ded68f3b6f06e50061de metrics: - type: map_at_1 value: 19.721 - type: map_at_10 value: 31.604 - type: map_at_100 value: 32.972 - type: map_at_1000 value: 33.077 - type: map_at_3 value: 27.218999999999998 - type: map_at_5 value: 29.53 - type: mrr_at_1 value: 25.0 - type: mrr_at_10 value: 35.843 - type: mrr_at_100 value: 36.785000000000004 - type: mrr_at_1000 value: 36.842000000000006 - type: mrr_at_3 value: 32.193 - type: mrr_at_5 value: 34.264 - type: ndcg_at_1 value: 25.0 - type: ndcg_at_10 value: 38.606 - type: ndcg_at_100 value: 44.272 - type: ndcg_at_1000 value: 46.527 - type: ndcg_at_3 value: 30.985000000000003 - type: ndcg_at_5 value: 34.43 - type: precision_at_1 value: 25.0 - type: precision_at_10 value: 7.811 - type: precision_at_100 value: 1.203 - type: precision_at_1000 value: 0.15 - type: precision_at_3 value: 15.423 - type: precision_at_5 value: 11.791 - type: recall_at_1 value: 19.721 - type: recall_at_10 value: 55.625 - type: recall_at_100 value: 79.34400000000001 - type: recall_at_1000 value: 95.208 - type: recall_at_3 value: 35.19 - type: recall_at_5 value: 43.626 - task: type: Retrieval dataset: name: MTEB CQADupstackPhysicsRetrieval type: BeIR/cqadupstack config: default split: test revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4 metrics: - type: map_at_1 value: 33.784 - type: map_at_10 value: 47.522 - type: map_at_100 value: 48.949999999999996 - type: map_at_1000 value: 49.038 - type: map_at_3 value: 43.284 - type: map_at_5 value: 45.629 - type: mrr_at_1 value: 41.482 - type: mrr_at_10 value: 52.830999999999996 - type: mrr_at_100 value: 53.559999999999995 - type: mrr_at_1000 value: 53.588 - type: mrr_at_3 value: 50.016000000000005 - type: mrr_at_5 value: 51.614000000000004 - type: ndcg_at_1 value: 41.482 - type: ndcg_at_10 value: 54.569 - type: ndcg_at_100 value: 59.675999999999995 - type: ndcg_at_1000 value: 60.989000000000004 - type: ndcg_at_3 value: 48.187000000000005 - type: ndcg_at_5 value: 51.183 - type: precision_at_1 value: 41.482 - type: precision_at_10 value: 10.221 - type: precision_at_100 value: 1.486 - type: precision_at_1000 value: 0.17500000000000002 - type: precision_at_3 value: 23.548 - type: precision_at_5 value: 16.805 - type: recall_at_1 value: 33.784 - type: recall_at_10 value: 69.798 - type: recall_at_100 value: 90.098 - type: recall_at_1000 value: 98.176 - type: recall_at_3 value: 52.127 - type: recall_at_5 value: 59.861 - task: type: Retrieval dataset: name: MTEB CQADupstackProgrammersRetrieval type: BeIR/cqadupstack config: default split: test revision: 6184bc1440d2dbc7612be22b50686b8826d22b32 metrics: - type: map_at_1 value: 28.038999999999998 - type: map_at_10 value: 41.904 - type: map_at_100 value: 43.36 - type: map_at_1000 value: 43.453 - type: map_at_3 value: 37.785999999999994 - type: map_at_5 value: 40.105000000000004 - type: mrr_at_1 value: 35.046 - type: mrr_at_10 value: 46.926 - type: mrr_at_100 value: 47.815000000000005 - type: mrr_at_1000 value: 47.849000000000004 - type: mrr_at_3 value: 44.273 - type: mrr_at_5 value: 45.774 - type: ndcg_at_1 value: 35.046 - type: ndcg_at_10 value: 48.937000000000005 - type: ndcg_at_100 value: 54.544000000000004 - type: ndcg_at_1000 value: 56.069 - type: ndcg_at_3 value: 42.858000000000004 - type: ndcg_at_5 value: 45.644 - type: precision_at_1 value: 35.046 - type: precision_at_10 value: 9.452 - type: precision_at_100 value: 1.429 - type: precision_at_1000 value: 0.173 - type: precision_at_3 value: 21.346999999999998 - type: precision_at_5 value: 15.342 - type: recall_at_1 value: 28.038999999999998 - type: recall_at_10 value: 64.59700000000001 - type: recall_at_100 value: 87.735 - type: recall_at_1000 value: 97.41300000000001 - type: recall_at_3 value: 47.368 - type: recall_at_5 value: 54.93900000000001 - task: type: Retrieval dataset: name: MTEB CQADupstackRetrieval type: BeIR/cqadupstack config: default split: test revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: map_at_1 value: 28.17291666666667 - type: map_at_10 value: 40.025749999999995 - type: map_at_100 value: 41.39208333333333 - type: map_at_1000 value: 41.499249999999996 - type: map_at_3 value: 36.347 - type: map_at_5 value: 38.41391666666667 - type: mrr_at_1 value: 33.65925 - type: mrr_at_10 value: 44.085499999999996 - type: mrr_at_100 value: 44.94116666666667 - type: mrr_at_1000 value: 44.9855 - type: mrr_at_3 value: 41.2815 - type: mrr_at_5 value: 42.91491666666666 - type: ndcg_at_1 value: 33.65925 - type: ndcg_at_10 value: 46.430833333333325 - type: ndcg_at_100 value: 51.761 - type: ndcg_at_1000 value: 53.50899999999999 - type: ndcg_at_3 value: 40.45133333333333 - type: ndcg_at_5 value: 43.31483333333334 - type: precision_at_1 value: 33.65925 - type: precision_at_10 value: 8.4995 - type: precision_at_100 value: 1.3210000000000004 - type: precision_at_1000 value: 0.16591666666666666 - type: precision_at_3 value: 19.165083333333335 - type: precision_at_5 value: 13.81816666666667 - type: recall_at_1 value: 28.17291666666667 - type: recall_at_10 value: 61.12624999999999 - type: recall_at_100 value: 83.97266666666667 - type: recall_at_1000 value: 95.66550000000001 - type: recall_at_3 value: 44.661249999999995 - type: recall_at_5 value: 51.983333333333334 - type: map_at_1 value: 17.936 - type: map_at_10 value: 27.399 - type: map_at_100 value: 28.632 - type: map_at_1000 value: 28.738000000000003 - type: map_at_3 value: 24.456 - type: map_at_5 value: 26.06 - type: mrr_at_1 value: 19.224 - type: mrr_at_10 value: 28.998 - type: mrr_at_100 value: 30.11 - type: mrr_at_1000 value: 30.177 - type: mrr_at_3 value: 26.247999999999998 - type: mrr_at_5 value: 27.708 - type: ndcg_at_1 value: 19.224 - type: ndcg_at_10 value: 32.911 - type: ndcg_at_100 value: 38.873999999999995 - type: ndcg_at_1000 value: 41.277 - type: ndcg_at_3 value: 27.142 - type: ndcg_at_5 value: 29.755 - type: precision_at_1 value: 19.224 - type: precision_at_10 value: 5.6930000000000005 - type: precision_at_100 value: 0.9259999999999999 - type: precision_at_1000 value: 0.126 - type: precision_at_3 value: 12.138 - type: precision_at_5 value: 8.909 - type: recall_at_1 value: 17.936 - type: recall_at_10 value: 48.096 - type: recall_at_100 value: 75.389 - type: recall_at_1000 value: 92.803 - type: recall_at_3 value: 32.812999999999995 - type: recall_at_5 value: 38.851 - task: type: Retrieval dataset: name: MTEB CQADupstackStatsRetrieval type: BeIR/cqadupstack config: default split: test revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a metrics: - type: map_at_1 value: 24.681 - type: map_at_10 value: 34.892 - type: map_at_100 value: 35.996 - type: map_at_1000 value: 36.083 - type: map_at_3 value: 31.491999999999997 - type: map_at_5 value: 33.632 - type: mrr_at_1 value: 28.528 - type: mrr_at_10 value: 37.694 - type: mrr_at_100 value: 38.613 - type: mrr_at_1000 value: 38.668 - type: mrr_at_3 value: 34.714 - type: mrr_at_5 value: 36.616 - type: ndcg_at_1 value: 28.528 - type: ndcg_at_10 value: 40.703 - type: ndcg_at_100 value: 45.993 - type: ndcg_at_1000 value: 47.847 - type: ndcg_at_3 value: 34.622 - type: ndcg_at_5 value: 38.035999999999994 - type: precision_at_1 value: 28.528 - type: precision_at_10 value: 6.902 - type: precision_at_100 value: 1.0370000000000001 - type: precision_at_1000 value: 0.126 - type: precision_at_3 value: 15.798000000000002 - type: precision_at_5 value: 11.655999999999999 - type: recall_at_1 value: 24.681 - type: recall_at_10 value: 55.81 - type: recall_at_100 value: 79.785 - type: recall_at_1000 value: 92.959 - type: recall_at_3 value: 39.074 - type: recall_at_5 value: 47.568 - task: type: Retrieval dataset: name: MTEB CQADupstackTexRetrieval type: BeIR/cqadupstack config: default split: test revision: 46989137a86843e03a6195de44b09deda022eec7 metrics: - type: map_at_1 value: 18.627 - type: map_at_10 value: 27.872000000000003 - type: map_at_100 value: 29.237999999999996 - type: map_at_1000 value: 29.363 - type: map_at_3 value: 24.751 - type: map_at_5 value: 26.521 - type: mrr_at_1 value: 23.021 - type: mrr_at_10 value: 31.924000000000003 - type: mrr_at_100 value: 32.922000000000004 - type: mrr_at_1000 value: 32.988 - type: mrr_at_3 value: 29.192 - type: mrr_at_5 value: 30.798 - type: ndcg_at_1 value: 23.021 - type: ndcg_at_10 value: 33.535 - type: ndcg_at_100 value: 39.732 - type: ndcg_at_1000 value: 42.201 - type: ndcg_at_3 value: 28.153 - type: ndcg_at_5 value: 30.746000000000002 - type: precision_at_1 value: 23.021 - type: precision_at_10 value: 6.459 - type: precision_at_100 value: 1.1320000000000001 - type: precision_at_1000 value: 0.153 - type: precision_at_3 value: 13.719000000000001 - type: precision_at_5 value: 10.193000000000001 - type: recall_at_1 value: 18.627 - type: recall_at_10 value: 46.463 - type: recall_at_100 value: 74.226 - type: recall_at_1000 value: 91.28500000000001 - type: recall_at_3 value: 31.357000000000003 - type: recall_at_5 value: 38.067 - task: type: Retrieval dataset: name: MTEB CQADupstackUnixRetrieval type: BeIR/cqadupstack config: default split: test revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53 metrics: - type: map_at_1 value: 31.457 - type: map_at_10 value: 42.888 - type: map_at_100 value: 44.24 - type: map_at_1000 value: 44.327 - type: map_at_3 value: 39.588 - type: map_at_5 value: 41.423 - type: mrr_at_1 value: 37.126999999999995 - type: mrr_at_10 value: 47.083000000000006 - type: mrr_at_100 value: 47.997 - type: mrr_at_1000 value: 48.044 - type: mrr_at_3 value: 44.574000000000005 - type: mrr_at_5 value: 46.202 - type: ndcg_at_1 value: 37.126999999999995 - type: ndcg_at_10 value: 48.833 - type: ndcg_at_100 value: 54.327000000000005 - type: ndcg_at_1000 value: 56.011 - type: ndcg_at_3 value: 43.541999999999994 - type: ndcg_at_5 value: 46.127 - type: precision_at_1 value: 37.126999999999995 - type: precision_at_10 value: 8.376999999999999 - type: precision_at_100 value: 1.2309999999999999 - type: precision_at_1000 value: 0.146 - type: precision_at_3 value: 20.211000000000002 - type: precision_at_5 value: 14.16 - type: recall_at_1 value: 31.457 - type: recall_at_10 value: 62.369 - type: recall_at_100 value: 85.444 - type: recall_at_1000 value: 96.65599999999999 - type: recall_at_3 value: 47.961 - type: recall_at_5 value: 54.676 - task: type: Retrieval dataset: name: MTEB CQADupstackWebmastersRetrieval type: BeIR/cqadupstack config: default split: test revision: 160c094312a0e1facb97e55eeddb698c0abe3571 metrics: - type: map_at_1 value: 27.139999999999997 - type: map_at_10 value: 38.801 - type: map_at_100 value: 40.549 - type: map_at_1000 value: 40.802 - type: map_at_3 value: 35.05 - type: map_at_5 value: 36.884 - type: mrr_at_1 value: 33.004 - type: mrr_at_10 value: 43.864 - type: mrr_at_100 value: 44.667 - type: mrr_at_1000 value: 44.717 - type: mrr_at_3 value: 40.777 - type: mrr_at_5 value: 42.319 - type: ndcg_at_1 value: 33.004 - type: ndcg_at_10 value: 46.022 - type: ndcg_at_100 value: 51.542 - type: ndcg_at_1000 value: 53.742000000000004 - type: ndcg_at_3 value: 39.795 - type: ndcg_at_5 value: 42.272 - type: precision_at_1 value: 33.004 - type: precision_at_10 value: 9.012 - type: precision_at_100 value: 1.7770000000000001 - type: precision_at_1000 value: 0.26 - type: precision_at_3 value: 19.038 - type: precision_at_5 value: 13.675999999999998 - type: recall_at_1 value: 27.139999999999997 - type: recall_at_10 value: 60.961 - type: recall_at_100 value: 84.451 - type: recall_at_1000 value: 98.113 - type: recall_at_3 value: 43.001 - type: recall_at_5 value: 49.896 - task: type: Retrieval dataset: name: MTEB ClimateFEVER type: mteb/climate-fever config: default split: test revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 metrics: - type: map_at_1 value: 22.076999999999998 - type: map_at_10 value: 35.44 - type: map_at_100 value: 37.651 - type: map_at_1000 value: 37.824999999999996 - type: map_at_3 value: 30.764999999999997 - type: map_at_5 value: 33.26 - type: mrr_at_1 value: 50.163000000000004 - type: mrr_at_10 value: 61.207 - type: mrr_at_100 value: 61.675000000000004 - type: mrr_at_1000 value: 61.692 - type: mrr_at_3 value: 58.60999999999999 - type: mrr_at_5 value: 60.307 - type: ndcg_at_1 value: 50.163000000000004 - type: ndcg_at_10 value: 45.882 - type: ndcg_at_100 value: 53.239999999999995 - type: ndcg_at_1000 value: 55.852000000000004 - type: ndcg_at_3 value: 40.514 - type: ndcg_at_5 value: 42.038 - type: precision_at_1 value: 50.163000000000004 - type: precision_at_10 value: 13.466000000000001 - type: precision_at_100 value: 2.164 - type: precision_at_1000 value: 0.266 - type: precision_at_3 value: 29.707 - type: precision_at_5 value: 21.694 - type: recall_at_1 value: 22.076999999999998 - type: recall_at_10 value: 50.193 - type: recall_at_100 value: 74.993 - type: recall_at_1000 value: 89.131 - type: recall_at_3 value: 35.472 - type: recall_at_5 value: 41.814 - task: type: Retrieval dataset: name: MTEB DBPedia type: mteb/dbpedia config: default split: test revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 metrics: - type: map_at_1 value: 9.953 - type: map_at_10 value: 24.515 - type: map_at_100 value: 36.173 - type: map_at_1000 value: 38.351 - type: map_at_3 value: 16.592000000000002 - type: map_at_5 value: 20.036 - type: mrr_at_1 value: 74.25 - type: mrr_at_10 value: 81.813 - type: mrr_at_100 value: 82.006 - type: mrr_at_1000 value: 82.011 - type: mrr_at_3 value: 80.875 - type: mrr_at_5 value: 81.362 - type: ndcg_at_1 value: 62.5 - type: ndcg_at_10 value: 52.42 - type: ndcg_at_100 value: 56.808 - type: ndcg_at_1000 value: 63.532999999999994 - type: ndcg_at_3 value: 56.654 - type: ndcg_at_5 value: 54.18300000000001 - type: precision_at_1 value: 74.25 - type: precision_at_10 value: 42.699999999999996 - type: precision_at_100 value: 13.675 - type: precision_at_1000 value: 2.664 - type: precision_at_3 value: 60.5 - type: precision_at_5 value: 52.800000000000004 - type: recall_at_1 value: 9.953 - type: recall_at_10 value: 30.253999999999998 - type: recall_at_100 value: 62.516000000000005 - type: recall_at_1000 value: 84.163 - type: recall_at_3 value: 18.13 - type: recall_at_5 value: 22.771 - task: type: Classification dataset: name: MTEB EmotionClassification type: mteb/emotion config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 79.455 - type: f1 value: 74.16798697647569 - task: type: Retrieval dataset: name: MTEB FEVER type: mteb/fever config: default split: test revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 metrics: - type: map_at_1 value: 87.531 - type: map_at_10 value: 93.16799999999999 - type: map_at_100 value: 93.341 - type: map_at_1000 value: 93.349 - type: map_at_3 value: 92.444 - type: map_at_5 value: 92.865 - type: mrr_at_1 value: 94.014 - type: mrr_at_10 value: 96.761 - type: mrr_at_100 value: 96.762 - type: mrr_at_1000 value: 96.762 - type: mrr_at_3 value: 96.672 - type: mrr_at_5 value: 96.736 - type: ndcg_at_1 value: 94.014 - type: ndcg_at_10 value: 95.112 - type: ndcg_at_100 value: 95.578 - type: ndcg_at_1000 value: 95.68900000000001 - type: ndcg_at_3 value: 94.392 - type: ndcg_at_5 value: 94.72500000000001 - type: precision_at_1 value: 94.014 - type: precision_at_10 value: 11.065 - type: precision_at_100 value: 1.157 - type: precision_at_1000 value: 0.11800000000000001 - type: precision_at_3 value: 35.259 - type: precision_at_5 value: 21.599 - type: recall_at_1 value: 87.531 - type: recall_at_10 value: 97.356 - type: recall_at_100 value: 98.965 - type: recall_at_1000 value: 99.607 - type: recall_at_3 value: 95.312 - type: recall_at_5 value: 96.295 - task: type: Retrieval dataset: name: MTEB FiQA2018 type: mteb/fiqa config: default split: test revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: map_at_1 value: 32.055 - type: map_at_10 value: 53.114 - type: map_at_100 value: 55.235 - type: map_at_1000 value: 55.345 - type: map_at_3 value: 45.854 - type: map_at_5 value: 50.025 - type: mrr_at_1 value: 60.34 - type: mrr_at_10 value: 68.804 - type: mrr_at_100 value: 69.309 - type: mrr_at_1000 value: 69.32199999999999 - type: mrr_at_3 value: 66.40899999999999 - type: mrr_at_5 value: 67.976 - type: ndcg_at_1 value: 60.34 - type: ndcg_at_10 value: 62.031000000000006 - type: ndcg_at_100 value: 68.00500000000001 - type: ndcg_at_1000 value: 69.286 - type: ndcg_at_3 value: 56.355999999999995 - type: ndcg_at_5 value: 58.687 - type: precision_at_1 value: 60.34 - type: precision_at_10 value: 17.176 - type: precision_at_100 value: 2.36 - type: precision_at_1000 value: 0.259 - type: precision_at_3 value: 37.14 - type: precision_at_5 value: 27.809 - type: recall_at_1 value: 32.055 - type: recall_at_10 value: 70.91 - type: recall_at_100 value: 91.83 - type: recall_at_1000 value: 98.871 - type: recall_at_3 value: 51.202999999999996 - type: recall_at_5 value: 60.563 - task: type: Retrieval dataset: name: MTEB HotpotQA type: mteb/hotpotqa config: default split: test revision: ab518f4d6fcca38d87c25209f94beba119d02014 metrics: - type: map_at_1 value: 43.68 - type: map_at_10 value: 64.389 - type: map_at_100 value: 65.24 - type: map_at_1000 value: 65.303 - type: map_at_3 value: 61.309000000000005 - type: map_at_5 value: 63.275999999999996 - type: mrr_at_1 value: 87.36 - type: mrr_at_10 value: 91.12 - type: mrr_at_100 value: 91.227 - type: mrr_at_1000 value: 91.229 - type: mrr_at_3 value: 90.57600000000001 - type: mrr_at_5 value: 90.912 - type: ndcg_at_1 value: 87.36 - type: ndcg_at_10 value: 73.076 - type: ndcg_at_100 value: 75.895 - type: ndcg_at_1000 value: 77.049 - type: ndcg_at_3 value: 68.929 - type: ndcg_at_5 value: 71.28 - type: precision_at_1 value: 87.36 - type: precision_at_10 value: 14.741000000000001 - type: precision_at_100 value: 1.694 - type: precision_at_1000 value: 0.185 - type: precision_at_3 value: 43.043 - type: precision_at_5 value: 27.681 - type: recall_at_1 value: 43.68 - type: recall_at_10 value: 73.707 - type: recall_at_100 value: 84.7 - type: recall_at_1000 value: 92.309 - type: recall_at_3 value: 64.564 - type: recall_at_5 value: 69.203 - task: type: Classification dataset: name: MTEB ImdbClassification type: mteb/imdb config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 96.75399999999999 - type: ap value: 95.29389839242187 - type: f1 value: 96.75348377433475 - task: type: Retrieval dataset: name: MTEB MSMARCO type: mteb/msmarco config: default split: dev revision: c5a29a104738b98a9e76336939199e264163d4a0 metrics: - type: map_at_1 value: 25.176 - type: map_at_10 value: 38.598 - type: map_at_100 value: 39.707 - type: map_at_1000 value: 39.744 - type: map_at_3 value: 34.566 - type: map_at_5 value: 36.863 - type: mrr_at_1 value: 25.874000000000002 - type: mrr_at_10 value: 39.214 - type: mrr_at_100 value: 40.251 - type: mrr_at_1000 value: 40.281 - type: mrr_at_3 value: 35.291 - type: mrr_at_5 value: 37.545 - type: ndcg_at_1 value: 25.874000000000002 - type: ndcg_at_10 value: 45.98 - type: ndcg_at_100 value: 51.197 - type: ndcg_at_1000 value: 52.073 - type: ndcg_at_3 value: 37.785999999999994 - type: ndcg_at_5 value: 41.870000000000005 - type: precision_at_1 value: 25.874000000000002 - type: precision_at_10 value: 7.181 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.106 - type: precision_at_3 value: 16.051000000000002 - type: precision_at_5 value: 11.713 - type: recall_at_1 value: 25.176 - type: recall_at_10 value: 68.67699999999999 - type: recall_at_100 value: 92.55 - type: recall_at_1000 value: 99.164 - type: recall_at_3 value: 46.372 - type: recall_at_5 value: 56.16 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 99.03784769721841 - type: f1 value: 98.97791641821495 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 91.88326493388054 - type: f1 value: 73.74809928034335 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 85.41358439811701 - type: f1 value: 83.503679460639 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 89.77135171486215 - type: f1 value: 88.89843747468366 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P type: mteb/medrxiv-clustering-p2p config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 46.22695362087359 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S type: mteb/medrxiv-clustering-s2s config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 44.132372165849425 - task: type: Reranking dataset: name: MTEB MindSmallReranking type: mteb/mind_small config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 33.35680810650402 - type: mrr value: 34.72625715637218 - task: type: Retrieval dataset: name: MTEB NFCorpus type: mteb/nfcorpus config: default split: test revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 metrics: - type: map_at_1 value: 7.165000000000001 - type: map_at_10 value: 15.424 - type: map_at_100 value: 20.28 - type: map_at_1000 value: 22.065 - type: map_at_3 value: 11.236 - type: map_at_5 value: 13.025999999999998 - type: mrr_at_1 value: 51.702999999999996 - type: mrr_at_10 value: 59.965 - type: mrr_at_100 value: 60.667 - type: mrr_at_1000 value: 60.702999999999996 - type: mrr_at_3 value: 58.772000000000006 - type: mrr_at_5 value: 59.267 - type: ndcg_at_1 value: 49.536 - type: ndcg_at_10 value: 40.6 - type: ndcg_at_100 value: 37.848 - type: ndcg_at_1000 value: 46.657 - type: ndcg_at_3 value: 46.117999999999995 - type: ndcg_at_5 value: 43.619 - type: precision_at_1 value: 51.393 - type: precision_at_10 value: 30.31 - type: precision_at_100 value: 9.972 - type: precision_at_1000 value: 2.329 - type: precision_at_3 value: 43.137 - type: precision_at_5 value: 37.585 - type: recall_at_1 value: 7.165000000000001 - type: recall_at_10 value: 19.689999999999998 - type: recall_at_100 value: 39.237 - type: recall_at_1000 value: 71.417 - type: recall_at_3 value: 12.247 - type: recall_at_5 value: 14.902999999999999 - task: type: Retrieval dataset: name: MTEB NQ type: mteb/nq config: default split: test revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 metrics: - type: map_at_1 value: 42.653999999999996 - type: map_at_10 value: 59.611999999999995 - type: map_at_100 value: 60.32300000000001 - type: map_at_1000 value: 60.336 - type: map_at_3 value: 55.584999999999994 - type: map_at_5 value: 58.19 - type: mrr_at_1 value: 47.683 - type: mrr_at_10 value: 62.06700000000001 - type: mrr_at_100 value: 62.537 - type: mrr_at_1000 value: 62.544999999999995 - type: mrr_at_3 value: 59.178 - type: mrr_at_5 value: 61.034 - type: ndcg_at_1 value: 47.654 - type: ndcg_at_10 value: 67.001 - type: ndcg_at_100 value: 69.73899999999999 - type: ndcg_at_1000 value: 69.986 - type: ndcg_at_3 value: 59.95700000000001 - type: ndcg_at_5 value: 64.025 - type: precision_at_1 value: 47.654 - type: precision_at_10 value: 10.367999999999999 - type: precision_at_100 value: 1.192 - type: precision_at_1000 value: 0.121 - type: precision_at_3 value: 26.651000000000003 - type: precision_at_5 value: 18.459 - type: recall_at_1 value: 42.653999999999996 - type: recall_at_10 value: 86.619 - type: recall_at_100 value: 98.04899999999999 - type: recall_at_1000 value: 99.812 - type: recall_at_3 value: 68.987 - type: recall_at_5 value: 78.158 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval type: mteb/quora config: default split: test revision: None metrics: - type: map_at_1 value: 72.538 - type: map_at_10 value: 86.702 - type: map_at_100 value: 87.31 - type: map_at_1000 value: 87.323 - type: map_at_3 value: 83.87 - type: map_at_5 value: 85.682 - type: mrr_at_1 value: 83.31 - type: mrr_at_10 value: 89.225 - type: mrr_at_100 value: 89.30399999999999 - type: mrr_at_1000 value: 89.30399999999999 - type: mrr_at_3 value: 88.44300000000001 - type: mrr_at_5 value: 89.005 - type: ndcg_at_1 value: 83.32000000000001 - type: ndcg_at_10 value: 90.095 - type: ndcg_at_100 value: 91.12 - type: ndcg_at_1000 value: 91.179 - type: ndcg_at_3 value: 87.606 - type: ndcg_at_5 value: 89.031 - type: precision_at_1 value: 83.32000000000001 - type: precision_at_10 value: 13.641 - type: precision_at_100 value: 1.541 - type: precision_at_1000 value: 0.157 - type: precision_at_3 value: 38.377 - type: precision_at_5 value: 25.162000000000003 - type: recall_at_1 value: 72.538 - type: recall_at_10 value: 96.47200000000001 - type: recall_at_100 value: 99.785 - type: recall_at_1000 value: 99.99900000000001 - type: recall_at_3 value: 89.278 - type: recall_at_5 value: 93.367 - task: type: Clustering dataset: name: MTEB RedditClustering type: mteb/reddit-clustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 73.55219145406065 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P type: mteb/reddit-clustering-p2p config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 74.13437105242755 - task: type: Retrieval dataset: name: MTEB SCIDOCS type: mteb/scidocs config: default split: test revision: None metrics: - type: map_at_1 value: 6.873 - type: map_at_10 value: 17.944 - type: map_at_100 value: 21.171 - type: map_at_1000 value: 21.528 - type: map_at_3 value: 12.415 - type: map_at_5 value: 15.187999999999999 - type: mrr_at_1 value: 33.800000000000004 - type: mrr_at_10 value: 46.455 - type: mrr_at_100 value: 47.378 - type: mrr_at_1000 value: 47.394999999999996 - type: mrr_at_3 value: 42.367 - type: mrr_at_5 value: 44.972 - type: ndcg_at_1 value: 33.800000000000004 - type: ndcg_at_10 value: 28.907 - type: ndcg_at_100 value: 39.695 - type: ndcg_at_1000 value: 44.582 - type: ndcg_at_3 value: 26.949 - type: ndcg_at_5 value: 23.988 - type: precision_at_1 value: 33.800000000000004 - type: precision_at_10 value: 15.079999999999998 - type: precision_at_100 value: 3.056 - type: precision_at_1000 value: 0.42100000000000004 - type: precision_at_3 value: 25.167 - type: precision_at_5 value: 21.26 - type: recall_at_1 value: 6.873 - type: recall_at_10 value: 30.568 - type: recall_at_100 value: 62.062 - type: recall_at_1000 value: 85.37700000000001 - type: recall_at_3 value: 15.312999999999999 - type: recall_at_5 value: 21.575 - task: type: STS dataset: name: MTEB SICK-R type: mteb/sickr-sts config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.37009118256057 - type: cos_sim_spearman value: 79.27986395671529 - type: euclidean_pearson value: 79.18037715442115 - type: euclidean_spearman value: 79.28004791561621 - type: manhattan_pearson value: 79.34062972800541 - type: manhattan_spearman value: 79.43106695543402 - task: type: STS dataset: name: MTEB STS12 type: mteb/sts12-sts config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 87.48474767383833 - type: cos_sim_spearman value: 79.54505388752513 - type: euclidean_pearson value: 83.43282704179565 - type: euclidean_spearman value: 79.54579919925405 - type: manhattan_pearson value: 83.77564492427952 - type: manhattan_spearman value: 79.84558396989286 - task: type: STS dataset: name: MTEB STS13 type: mteb/sts13-sts config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 88.803698035802 - type: cos_sim_spearman value: 88.83451367754881 - type: euclidean_pearson value: 88.28939285711628 - type: euclidean_spearman value: 88.83528996073112 - type: manhattan_pearson value: 88.28017412671795 - type: manhattan_spearman value: 88.9228828016344 - task: type: STS dataset: name: MTEB STS14 type: mteb/sts14-sts config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 85.27469288153428 - type: cos_sim_spearman value: 83.87477064876288 - type: euclidean_pearson value: 84.2601737035379 - type: euclidean_spearman value: 83.87431082479074 - type: manhattan_pearson value: 84.3621547772745 - type: manhattan_spearman value: 84.12094375000423 - task: type: STS dataset: name: MTEB STS15 type: mteb/sts15-sts config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 88.12749863201587 - type: cos_sim_spearman value: 88.54287568368565 - type: euclidean_pearson value: 87.90429700607999 - type: euclidean_spearman value: 88.5437689576261 - type: manhattan_pearson value: 88.19276653356833 - type: manhattan_spearman value: 88.99995393814679 - task: type: STS dataset: name: MTEB STS16 type: mteb/sts16-sts config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 85.68398747560902 - type: cos_sim_spearman value: 86.48815303460574 - type: euclidean_pearson value: 85.52356631237954 - type: euclidean_spearman value: 86.486391949551 - type: manhattan_pearson value: 85.67267981761788 - type: manhattan_spearman value: 86.7073696332485 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 88.9057107443124 - type: cos_sim_spearman value: 88.7312168757697 - type: euclidean_pearson value: 88.72810439714794 - type: euclidean_spearman value: 88.71976185854771 - type: manhattan_pearson value: 88.50433745949111 - type: manhattan_spearman value: 88.51726175544195 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson value: 67.59391795109886 - type: cos_sim_spearman value: 66.87613008631367 - type: euclidean_pearson value: 69.23198488262217 - type: euclidean_spearman value: 66.85427723013692 - type: manhattan_pearson value: 69.50730124841084 - type: manhattan_spearman value: 67.10404669820792 - task: type: STS dataset: name: MTEB STSBenchmark type: mteb/stsbenchmark-sts config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 87.0820605344619 - type: cos_sim_spearman value: 86.8518089863434 - type: euclidean_pearson value: 86.31087134689284 - type: euclidean_spearman value: 86.8518520517941 - type: manhattan_pearson value: 86.47203796160612 - type: manhattan_spearman value: 87.1080149734421 - task: type: Reranking dataset: name: MTEB SciDocsRR type: mteb/scidocs-reranking config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 89.09255369305481 - type: mrr value: 97.10323445617563 - task: type: Retrieval dataset: name: MTEB SciFact type: mteb/scifact config: default split: test revision: 0228b52cf27578f30900b9e5271d331663a030d7 metrics: - type: map_at_1 value: 61.260999999999996 - type: map_at_10 value: 74.043 - type: map_at_100 value: 74.37700000000001 - type: map_at_1000 value: 74.384 - type: map_at_3 value: 71.222 - type: map_at_5 value: 72.875 - type: mrr_at_1 value: 64.333 - type: mrr_at_10 value: 74.984 - type: mrr_at_100 value: 75.247 - type: mrr_at_1000 value: 75.25500000000001 - type: mrr_at_3 value: 73.167 - type: mrr_at_5 value: 74.35000000000001 - type: ndcg_at_1 value: 64.333 - type: ndcg_at_10 value: 79.06 - type: ndcg_at_100 value: 80.416 - type: ndcg_at_1000 value: 80.55600000000001 - type: ndcg_at_3 value: 74.753 - type: ndcg_at_5 value: 76.97500000000001 - type: precision_at_1 value: 64.333 - type: precision_at_10 value: 10.567 - type: precision_at_100 value: 1.1199999999999999 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 29.889 - type: precision_at_5 value: 19.533 - type: recall_at_1 value: 61.260999999999996 - type: recall_at_10 value: 93.167 - type: recall_at_100 value: 99.0 - type: recall_at_1000 value: 100.0 - type: recall_at_3 value: 81.667 - type: recall_at_5 value: 87.394 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.71980198019801 - type: cos_sim_ap value: 92.81616007802704 - type: cos_sim_f1 value: 85.17548454688318 - type: cos_sim_precision value: 89.43894389438944 - type: cos_sim_recall value: 81.3 - type: dot_accuracy value: 99.71980198019801 - type: dot_ap value: 92.81398760591358 - type: dot_f1 value: 85.17548454688318 - type: dot_precision value: 89.43894389438944 - type: dot_recall value: 81.3 - type: euclidean_accuracy value: 99.71980198019801 - type: euclidean_ap value: 92.81560637245072 - type: euclidean_f1 value: 85.17548454688318 - type: euclidean_precision value: 89.43894389438944 - type: euclidean_recall value: 81.3 - type: manhattan_accuracy value: 99.73069306930694 - type: manhattan_ap value: 93.14005487480794 - type: manhattan_f1 value: 85.56263269639068 - type: manhattan_precision value: 91.17647058823529 - type: manhattan_recall value: 80.60000000000001 - type: max_accuracy value: 99.73069306930694 - type: max_ap value: 93.14005487480794 - type: max_f1 value: 85.56263269639068 - task: type: Clustering dataset: name: MTEB StackExchangeClustering type: mteb/stackexchange-clustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 79.86443362395185 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P type: mteb/stackexchange-clustering-p2p config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 49.40897096662564 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 55.66040806627947 - type: mrr value: 56.58670475766064 - task: type: Summarization dataset: name: MTEB SummEval type: mteb/summeval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 31.51015090598575 - type: cos_sim_spearman value: 31.35016454939226 - type: dot_pearson value: 31.5150068731 - type: dot_spearman value: 31.34790869023487 - task: type: Retrieval dataset: name: MTEB TRECCOVID type: mteb/trec-covid config: default split: test revision: None metrics: - type: map_at_1 value: 0.254 - type: map_at_10 value: 2.064 - type: map_at_100 value: 12.909 - type: map_at_1000 value: 31.761 - type: map_at_3 value: 0.738 - type: map_at_5 value: 1.155 - type: mrr_at_1 value: 96.0 - type: mrr_at_10 value: 98.0 - type: mrr_at_100 value: 98.0 - type: mrr_at_1000 value: 98.0 - type: mrr_at_3 value: 98.0 - type: mrr_at_5 value: 98.0 - type: ndcg_at_1 value: 93.0 - type: ndcg_at_10 value: 82.258 - type: ndcg_at_100 value: 64.34 - type: ndcg_at_1000 value: 57.912 - type: ndcg_at_3 value: 90.827 - type: ndcg_at_5 value: 86.79 - type: precision_at_1 value: 96.0 - type: precision_at_10 value: 84.8 - type: precision_at_100 value: 66.0 - type: precision_at_1000 value: 25.356 - type: precision_at_3 value: 94.667 - type: precision_at_5 value: 90.4 - type: recall_at_1 value: 0.254 - type: recall_at_10 value: 2.1950000000000003 - type: recall_at_100 value: 16.088 - type: recall_at_1000 value: 54.559000000000005 - type: recall_at_3 value: 0.75 - type: recall_at_5 value: 1.191 - task: type: Retrieval dataset: name: MTEB Touche2020 type: mteb/touche2020 config: default split: test revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f metrics: - type: map_at_1 value: 2.976 - type: map_at_10 value: 11.389000000000001 - type: map_at_100 value: 18.429000000000002 - type: map_at_1000 value: 20.113 - type: map_at_3 value: 6.483 - type: map_at_5 value: 8.770999999999999 - type: mrr_at_1 value: 40.816 - type: mrr_at_10 value: 58.118 - type: mrr_at_100 value: 58.489999999999995 - type: mrr_at_1000 value: 58.489999999999995 - type: mrr_at_3 value: 53.061 - type: mrr_at_5 value: 57.041 - type: ndcg_at_1 value: 40.816 - type: ndcg_at_10 value: 30.567 - type: ndcg_at_100 value: 42.44 - type: ndcg_at_1000 value: 53.480000000000004 - type: ndcg_at_3 value: 36.016 - type: ndcg_at_5 value: 34.257 - type: precision_at_1 value: 42.857 - type: precision_at_10 value: 25.714 - type: precision_at_100 value: 8.429 - type: precision_at_1000 value: 1.5939999999999999 - type: precision_at_3 value: 36.735 - type: precision_at_5 value: 33.878 - type: recall_at_1 value: 2.976 - type: recall_at_10 value: 17.854999999999997 - type: recall_at_100 value: 51.833 - type: recall_at_1000 value: 86.223 - type: recall_at_3 value: 7.887 - type: recall_at_5 value: 12.026 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification type: mteb/toxic_conversations_50k config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 85.1174 - type: ap value: 30.169441069345748 - type: f1 value: 69.79254701873245 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification type: mteb/tweet_sentiment_extraction config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 72.58347481607245 - type: f1 value: 72.74877295564937 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering type: mteb/twentynewsgroups-clustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 53.90586138221305 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 87.35769207844072 - type: cos_sim_ap value: 77.9645072410354 - type: cos_sim_f1 value: 71.32352941176471 - type: cos_sim_precision value: 66.5903890160183 - type: cos_sim_recall value: 76.78100263852242 - type: dot_accuracy value: 87.37557370209214 - type: dot_ap value: 77.96250046429908 - type: dot_f1 value: 71.28932757557064 - type: dot_precision value: 66.95249130938586 - type: dot_recall value: 76.22691292875989 - type: euclidean_accuracy value: 87.35173153722357 - type: euclidean_ap value: 77.96520460741593 - type: euclidean_f1 value: 71.32470733210104 - type: euclidean_precision value: 66.91329479768785 - type: euclidean_recall value: 76.35883905013192 - type: manhattan_accuracy value: 87.25636287774931 - type: manhattan_ap value: 77.77752485611796 - type: manhattan_f1 value: 71.18148599269183 - type: manhattan_precision value: 66.10859728506787 - type: manhattan_recall value: 77.0976253298153 - type: max_accuracy value: 87.37557370209214 - type: max_ap value: 77.96520460741593 - type: max_f1 value: 71.32470733210104 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.38176737687739 - type: cos_sim_ap value: 86.58811861657401 - type: cos_sim_f1 value: 79.09430644097604 - type: cos_sim_precision value: 75.45085977911366 - type: cos_sim_recall value: 83.10748383122882 - type: dot_accuracy value: 89.38370784336554 - type: dot_ap value: 86.58840606004333 - type: dot_f1 value: 79.10179860068133 - type: dot_precision value: 75.44546153308643 - type: dot_recall value: 83.13058207576223 - type: euclidean_accuracy value: 89.38564830985369 - type: euclidean_ap value: 86.58820721061164 - type: euclidean_f1 value: 79.09070942235888 - type: euclidean_precision value: 75.38729937194697 - type: euclidean_recall value: 83.17677856482906 - type: manhattan_accuracy value: 89.40699344122326 - type: manhattan_ap value: 86.60631843011362 - type: manhattan_f1 value: 79.14949970570925 - type: manhattan_precision value: 75.78191039729502 - type: manhattan_recall value: 82.83030489682784 - type: max_accuracy value: 89.40699344122326 - type: max_ap value: 86.60631843011362 - type: max_f1 value: 79.14949970570925 - task: type: STS dataset: name: MTEB AFQMC type: C-MTEB/AFQMC config: default split: validation revision: b44c3b011063adb25877c13823db83bb193913c4 metrics: - type: cos_sim_pearson value: 65.58442135663871 - type: cos_sim_spearman value: 72.2538631361313 - type: euclidean_pearson value: 70.97255486607429 - type: euclidean_spearman value: 72.25374250228647 - type: manhattan_pearson value: 70.83250199989911 - type: manhattan_spearman value: 72.14819496536272 - task: type: STS dataset: name: MTEB ATEC type: C-MTEB/ATEC config: default split: test revision: 0f319b1142f28d00e055a6770f3f726ae9b7d865 metrics: - type: cos_sim_pearson value: 59.99478404929932 - type: cos_sim_spearman value: 62.61836216999812 - type: euclidean_pearson value: 66.86429811933593 - type: euclidean_spearman value: 62.6183520374191 - type: manhattan_pearson value: 66.8063778911633 - type: manhattan_spearman value: 62.569607573241115 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (zh) type: mteb/amazon_reviews_multi config: zh split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 53.98400000000001 - type: f1 value: 51.21447361350723 - task: type: STS dataset: name: MTEB BQ type: C-MTEB/BQ config: default split: test revision: e3dda5e115e487b39ec7e618c0c6a29137052a55 metrics: - type: cos_sim_pearson value: 79.11941660686553 - type: cos_sim_spearman value: 81.25029594540435 - type: euclidean_pearson value: 82.06973504238826 - type: euclidean_spearman value: 81.2501989488524 - type: manhattan_pearson value: 82.10094630392753 - type: manhattan_spearman value: 81.27987244392389 - task: type: Clustering dataset: name: MTEB CLSClusteringP2P type: C-MTEB/CLSClusteringP2P config: default split: test revision: 4b6227591c6c1a73bc76b1055f3b7f3588e72476 metrics: - type: v_measure value: 47.07270168705156 - task: type: Clustering dataset: name: MTEB CLSClusteringS2S type: C-MTEB/CLSClusteringS2S config: default split: test revision: e458b3f5414b62b7f9f83499ac1f5497ae2e869f metrics: - type: v_measure value: 45.98511703185043 - task: type: Reranking dataset: name: MTEB CMedQAv1 type: C-MTEB/CMedQAv1-reranking config: default split: test revision: 8d7f1e942507dac42dc58017c1a001c3717da7df metrics: - type: map value: 88.19895157194931 - type: mrr value: 90.21424603174603 - task: type: Reranking dataset: name: MTEB CMedQAv2 type: C-MTEB/CMedQAv2-reranking config: default split: test revision: 23d186750531a14a0357ca22cd92d712fd512ea0 metrics: - type: map value: 88.03317320980119 - type: mrr value: 89.9461507936508 - task: type: Retrieval dataset: name: MTEB CmedqaRetrieval type: C-MTEB/CmedqaRetrieval config: default split: dev revision: cd540c506dae1cf9e9a59c3e06f42030d54e7301 metrics: - type: map_at_1 value: 29.037000000000003 - type: map_at_10 value: 42.001 - type: map_at_100 value: 43.773 - type: map_at_1000 value: 43.878 - type: map_at_3 value: 37.637 - type: map_at_5 value: 40.034 - type: mrr_at_1 value: 43.136 - type: mrr_at_10 value: 51.158 - type: mrr_at_100 value: 52.083 - type: mrr_at_1000 value: 52.12 - type: mrr_at_3 value: 48.733 - type: mrr_at_5 value: 50.025 - type: ndcg_at_1 value: 43.136 - type: ndcg_at_10 value: 48.685 - type: ndcg_at_100 value: 55.513 - type: ndcg_at_1000 value: 57.242000000000004 - type: ndcg_at_3 value: 43.329 - type: ndcg_at_5 value: 45.438 - type: precision_at_1 value: 43.136 - type: precision_at_10 value: 10.56 - type: precision_at_100 value: 1.6129999999999998 - type: precision_at_1000 value: 0.184 - type: precision_at_3 value: 24.064 - type: precision_at_5 value: 17.269000000000002 - type: recall_at_1 value: 29.037000000000003 - type: recall_at_10 value: 59.245000000000005 - type: recall_at_100 value: 87.355 - type: recall_at_1000 value: 98.74000000000001 - type: recall_at_3 value: 42.99 - type: recall_at_5 value: 49.681999999999995 - task: type: PairClassification dataset: name: MTEB Cmnli type: C-MTEB/CMNLI config: default split: validation revision: 41bc36f332156f7adc9e38f53777c959b2ae9766 metrics: - type: cos_sim_accuracy value: 82.68190018039687 - type: cos_sim_ap value: 90.18017125327886 - type: cos_sim_f1 value: 83.64080906868193 - type: cos_sim_precision value: 79.7076890489303 - type: cos_sim_recall value: 87.98223053542202 - type: dot_accuracy value: 82.68190018039687 - type: dot_ap value: 90.18782350103646 - type: dot_f1 value: 83.64242087729039 - type: dot_precision value: 79.65313028764805 - type: dot_recall value: 88.05237315875614 - type: euclidean_accuracy value: 82.68190018039687 - type: euclidean_ap value: 90.1801957900632 - type: euclidean_f1 value: 83.63636363636364 - type: euclidean_precision value: 79.52772506852203 - type: euclidean_recall value: 88.19265840542437 - type: manhattan_accuracy value: 82.14070956103427 - type: manhattan_ap value: 89.96178420101427 - type: manhattan_f1 value: 83.21087838578791 - type: manhattan_precision value: 78.35605121850475 - type: manhattan_recall value: 88.70703764320785 - type: max_accuracy value: 82.68190018039687 - type: max_ap value: 90.18782350103646 - type: max_f1 value: 83.64242087729039 - task: type: Retrieval dataset: name: MTEB CovidRetrieval type: C-MTEB/CovidRetrieval config: default split: dev revision: 1271c7809071a13532e05f25fb53511ffce77117 metrics: - type: map_at_1 value: 72.234 - type: map_at_10 value: 80.10000000000001 - type: map_at_100 value: 80.36 - type: map_at_1000 value: 80.363 - type: map_at_3 value: 78.315 - type: map_at_5 value: 79.607 - type: mrr_at_1 value: 72.392 - type: mrr_at_10 value: 80.117 - type: mrr_at_100 value: 80.36999999999999 - type: mrr_at_1000 value: 80.373 - type: mrr_at_3 value: 78.469 - type: mrr_at_5 value: 79.633 - type: ndcg_at_1 value: 72.392 - type: ndcg_at_10 value: 83.651 - type: ndcg_at_100 value: 84.749 - type: ndcg_at_1000 value: 84.83000000000001 - type: ndcg_at_3 value: 80.253 - type: ndcg_at_5 value: 82.485 - type: precision_at_1 value: 72.392 - type: precision_at_10 value: 9.557 - type: precision_at_100 value: 1.004 - type: precision_at_1000 value: 0.101 - type: precision_at_3 value: 28.732000000000003 - type: precision_at_5 value: 18.377 - type: recall_at_1 value: 72.234 - type: recall_at_10 value: 94.573 - type: recall_at_100 value: 99.368 - type: recall_at_1000 value: 100.0 - type: recall_at_3 value: 85.669 - type: recall_at_5 value: 91.01700000000001 - task: type: Retrieval dataset: name: MTEB DuRetrieval type: C-MTEB/DuRetrieval config: default split: dev revision: a1a333e290fe30b10f3f56498e3a0d911a693ced metrics: - type: map_at_1 value: 26.173999999999996 - type: map_at_10 value: 80.04 - type: map_at_100 value: 82.94500000000001 - type: map_at_1000 value: 82.98100000000001 - type: map_at_3 value: 55.562999999999995 - type: map_at_5 value: 69.89800000000001 - type: mrr_at_1 value: 89.5 - type: mrr_at_10 value: 92.996 - type: mrr_at_100 value: 93.06400000000001 - type: mrr_at_1000 value: 93.065 - type: mrr_at_3 value: 92.658 - type: mrr_at_5 value: 92.84599999999999 - type: ndcg_at_1 value: 89.5 - type: ndcg_at_10 value: 87.443 - type: ndcg_at_100 value: 90.253 - type: ndcg_at_1000 value: 90.549 - type: ndcg_at_3 value: 85.874 - type: ndcg_at_5 value: 84.842 - type: precision_at_1 value: 89.5 - type: precision_at_10 value: 41.805 - type: precision_at_100 value: 4.827 - type: precision_at_1000 value: 0.49 - type: precision_at_3 value: 76.85 - type: precision_at_5 value: 64.8 - type: recall_at_1 value: 26.173999999999996 - type: recall_at_10 value: 89.101 - type: recall_at_100 value: 98.08099999999999 - type: recall_at_1000 value: 99.529 - type: recall_at_3 value: 57.902 - type: recall_at_5 value: 74.602 - task: type: Retrieval dataset: name: MTEB EcomRetrieval type: C-MTEB/EcomRetrieval config: default split: dev revision: 687de13dc7294d6fd9be10c6945f9e8fec8166b9 metrics: - type: map_at_1 value: 56.10000000000001 - type: map_at_10 value: 66.15299999999999 - type: map_at_100 value: 66.625 - type: map_at_1000 value: 66.636 - type: map_at_3 value: 63.632999999999996 - type: map_at_5 value: 65.293 - type: mrr_at_1 value: 56.10000000000001 - type: mrr_at_10 value: 66.15299999999999 - type: mrr_at_100 value: 66.625 - type: mrr_at_1000 value: 66.636 - type: mrr_at_3 value: 63.632999999999996 - type: mrr_at_5 value: 65.293 - type: ndcg_at_1 value: 56.10000000000001 - type: ndcg_at_10 value: 71.146 - type: ndcg_at_100 value: 73.27799999999999 - type: ndcg_at_1000 value: 73.529 - type: ndcg_at_3 value: 66.09 - type: ndcg_at_5 value: 69.08999999999999 - type: precision_at_1 value: 56.10000000000001 - type: precision_at_10 value: 8.68 - type: precision_at_100 value: 0.964 - type: precision_at_1000 value: 0.098 - type: precision_at_3 value: 24.4 - type: precision_at_5 value: 16.1 - type: recall_at_1 value: 56.10000000000001 - type: recall_at_10 value: 86.8 - type: recall_at_100 value: 96.39999999999999 - type: recall_at_1000 value: 98.3 - type: recall_at_3 value: 73.2 - type: recall_at_5 value: 80.5 - task: type: Classification dataset: name: MTEB IFlyTek type: C-MTEB/IFlyTek-classification config: default split: validation revision: 421605374b29664c5fc098418fe20ada9bd55f8a metrics: - type: accuracy value: 54.52096960369373 - type: f1 value: 40.930845295808695 - task: type: Classification dataset: name: MTEB JDReview type: C-MTEB/JDReview-classification config: default split: test revision: b7c64bd89eb87f8ded463478346f76731f07bf8b metrics: - type: accuracy value: 86.51031894934334 - type: ap value: 55.9516014323483 - type: f1 value: 81.54813679326381 - task: type: STS dataset: name: MTEB LCQMC type: C-MTEB/LCQMC config: default split: test revision: 17f9b096f80380fce5ed12a9be8be7784b337daf metrics: - type: cos_sim_pearson value: 69.67437838574276 - type: cos_sim_spearman value: 73.81314174653045 - type: euclidean_pearson value: 72.63430276680275 - type: euclidean_spearman value: 73.81358736777001 - type: manhattan_pearson value: 72.58743833842829 - type: manhattan_spearman value: 73.7590419009179 - task: type: Reranking dataset: name: MTEB MMarcoReranking type: C-MTEB/Mmarco-reranking config: default split: dev revision: None metrics: - type: map value: 31.648613483640254 - type: mrr value: 30.37420634920635 - task: type: Retrieval dataset: name: MTEB MMarcoRetrieval type: C-MTEB/MMarcoRetrieval config: default split: dev revision: 539bbde593d947e2a124ba72651aafc09eb33fc2 metrics: - type: map_at_1 value: 73.28099999999999 - type: map_at_10 value: 81.977 - type: map_at_100 value: 82.222 - type: map_at_1000 value: 82.22699999999999 - type: map_at_3 value: 80.441 - type: map_at_5 value: 81.46600000000001 - type: mrr_at_1 value: 75.673 - type: mrr_at_10 value: 82.41000000000001 - type: mrr_at_100 value: 82.616 - type: mrr_at_1000 value: 82.621 - type: mrr_at_3 value: 81.094 - type: mrr_at_5 value: 81.962 - type: ndcg_at_1 value: 75.673 - type: ndcg_at_10 value: 85.15599999999999 - type: ndcg_at_100 value: 86.151 - type: ndcg_at_1000 value: 86.26899999999999 - type: ndcg_at_3 value: 82.304 - type: ndcg_at_5 value: 84.009 - type: precision_at_1 value: 75.673 - type: precision_at_10 value: 10.042 - type: precision_at_100 value: 1.052 - type: precision_at_1000 value: 0.106 - type: precision_at_3 value: 30.673000000000002 - type: precision_at_5 value: 19.326999999999998 - type: recall_at_1 value: 73.28099999999999 - type: recall_at_10 value: 94.446 - type: recall_at_100 value: 98.737 - type: recall_at_1000 value: 99.649 - type: recall_at_3 value: 86.984 - type: recall_at_5 value: 91.024 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (zh-CN) type: mteb/amazon_massive_intent config: zh-CN split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 81.08607935440484 - type: f1 value: 78.24879986066307 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (zh-CN) type: mteb/amazon_massive_scenario config: zh-CN split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 86.05917955615332 - type: f1 value: 85.05279279434997 - task: type: Retrieval dataset: name: MTEB MedicalRetrieval type: C-MTEB/MedicalRetrieval config: default split: dev revision: 2039188fb5800a9803ba5048df7b76e6fb151fc6 metrics: - type: map_at_1 value: 56.2 - type: map_at_10 value: 62.57899999999999 - type: map_at_100 value: 63.154999999999994 - type: map_at_1000 value: 63.193 - type: map_at_3 value: 61.217 - type: map_at_5 value: 62.012 - type: mrr_at_1 value: 56.3 - type: mrr_at_10 value: 62.629000000000005 - type: mrr_at_100 value: 63.205999999999996 - type: mrr_at_1000 value: 63.244 - type: mrr_at_3 value: 61.267 - type: mrr_at_5 value: 62.062 - type: ndcg_at_1 value: 56.2 - type: ndcg_at_10 value: 65.592 - type: ndcg_at_100 value: 68.657 - type: ndcg_at_1000 value: 69.671 - type: ndcg_at_3 value: 62.808 - type: ndcg_at_5 value: 64.24499999999999 - type: precision_at_1 value: 56.2 - type: precision_at_10 value: 7.5 - type: precision_at_100 value: 0.899 - type: precision_at_1000 value: 0.098 - type: precision_at_3 value: 22.467000000000002 - type: precision_at_5 value: 14.180000000000001 - type: recall_at_1 value: 56.2 - type: recall_at_10 value: 75.0 - type: recall_at_100 value: 89.9 - type: recall_at_1000 value: 97.89999999999999 - type: recall_at_3 value: 67.4 - type: recall_at_5 value: 70.89999999999999 - task: type: Classification dataset: name: MTEB MultilingualSentiment type: C-MTEB/MultilingualSentiment-classification config: default split: validation revision: 46958b007a63fdbf239b7672c25d0bea67b5ea1a metrics: - type: accuracy value: 76.87666666666667 - type: f1 value: 76.7317686219665 - task: type: PairClassification dataset: name: MTEB Ocnli type: C-MTEB/OCNLI config: default split: validation revision: 66e76a618a34d6d565d5538088562851e6daa7ec metrics: - type: cos_sim_accuracy value: 79.64266377910124 - type: cos_sim_ap value: 84.78274442344829 - type: cos_sim_f1 value: 81.16947472745292 - type: cos_sim_precision value: 76.47058823529412 - type: cos_sim_recall value: 86.48363252375924 - type: dot_accuracy value: 79.64266377910124 - type: dot_ap value: 84.7851404063692 - type: dot_f1 value: 81.16947472745292 - type: dot_precision value: 76.47058823529412 - type: dot_recall value: 86.48363252375924 - type: euclidean_accuracy value: 79.64266377910124 - type: euclidean_ap value: 84.78068373762378 - type: euclidean_f1 value: 81.14794656110837 - type: euclidean_precision value: 76.35009310986965 - type: euclidean_recall value: 86.58922914466737 - type: manhattan_accuracy value: 79.48023822414727 - type: manhattan_ap value: 84.72928897427576 - type: manhattan_f1 value: 81.32084770823064 - type: manhattan_precision value: 76.24768946395564 - type: manhattan_recall value: 87.11721224920802 - type: max_accuracy value: 79.64266377910124 - type: max_ap value: 84.7851404063692 - type: max_f1 value: 81.32084770823064 - task: type: Classification dataset: name: MTEB OnlineShopping type: C-MTEB/OnlineShopping-classification config: default split: test revision: e610f2ebd179a8fda30ae534c3878750a96db120 metrics: - type: accuracy value: 94.3 - type: ap value: 92.8664032274438 - type: f1 value: 94.29311102997727 - task: type: STS dataset: name: MTEB PAWSX type: C-MTEB/PAWSX config: default split: test revision: 9c6a90e430ac22b5779fb019a23e820b11a8b5e1 metrics: - type: cos_sim_pearson value: 48.51392279882909 - type: cos_sim_spearman value: 54.06338895994974 - type: euclidean_pearson value: 52.58480559573412 - type: euclidean_spearman value: 54.06417276612201 - type: manhattan_pearson value: 52.69525121721343 - type: manhattan_spearman value: 54.048147455389675 - task: type: STS dataset: name: MTEB QBQTC type: C-MTEB/QBQTC config: default split: test revision: 790b0510dc52b1553e8c49f3d2afb48c0e5c48b7 metrics: - type: cos_sim_pearson value: 29.728387290757325 - type: cos_sim_spearman value: 31.366121633635284 - type: euclidean_pearson value: 29.14588368552961 - type: euclidean_spearman value: 31.36764411112844 - type: manhattan_pearson value: 29.63517350523121 - type: manhattan_spearman value: 31.94157020583762 - task: type: STS dataset: name: MTEB STS22 (zh) type: mteb/sts22-crosslingual-sts config: zh split: test revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson value: 63.64868296271406 - type: cos_sim_spearman value: 66.12800618164744 - type: euclidean_pearson value: 63.21405767340238 - type: euclidean_spearman value: 66.12786567790748 - type: manhattan_pearson value: 64.04300276525848 - type: manhattan_spearman value: 66.5066857145652 - task: type: STS dataset: name: MTEB STSB type: C-MTEB/STSB config: default split: test revision: 0cde68302b3541bb8b3c340dc0644b0b745b3dc0 metrics: - type: cos_sim_pearson value: 81.2302623912794 - type: cos_sim_spearman value: 81.16833673266562 - type: euclidean_pearson value: 79.47647843876024 - type: euclidean_spearman value: 81.16944349524972 - type: manhattan_pearson value: 79.84947238492208 - type: manhattan_spearman value: 81.64626599410026 - task: type: Reranking dataset: name: MTEB T2Reranking type: C-MTEB/T2Reranking config: default split: dev revision: 76631901a18387f85eaa53e5450019b87ad58ef9 metrics: - type: map value: 67.80129586475687 - type: mrr value: 77.77402311635554 - task: type: Retrieval dataset: name: MTEB T2Retrieval type: C-MTEB/T2Retrieval config: default split: dev revision: 8731a845f1bf500a4f111cf1070785c793d10e64 metrics: - type: map_at_1 value: 28.666999999999998 - type: map_at_10 value: 81.063 - type: map_at_100 value: 84.504 - type: map_at_1000 value: 84.552 - type: map_at_3 value: 56.897 - type: map_at_5 value: 70.073 - type: mrr_at_1 value: 92.087 - type: mrr_at_10 value: 94.132 - type: mrr_at_100 value: 94.19800000000001 - type: mrr_at_1000 value: 94.19999999999999 - type: mrr_at_3 value: 93.78999999999999 - type: mrr_at_5 value: 94.002 - type: ndcg_at_1 value: 92.087 - type: ndcg_at_10 value: 87.734 - type: ndcg_at_100 value: 90.736 - type: ndcg_at_1000 value: 91.184 - type: ndcg_at_3 value: 88.78 - type: ndcg_at_5 value: 87.676 - type: precision_at_1 value: 92.087 - type: precision_at_10 value: 43.46 - type: precision_at_100 value: 5.07 - type: precision_at_1000 value: 0.518 - type: precision_at_3 value: 77.49000000000001 - type: precision_at_5 value: 65.194 - type: recall_at_1 value: 28.666999999999998 - type: recall_at_10 value: 86.632 - type: recall_at_100 value: 96.646 - type: recall_at_1000 value: 98.917 - type: recall_at_3 value: 58.333999999999996 - type: recall_at_5 value: 72.974 - task: type: Classification dataset: name: MTEB TNews type: C-MTEB/TNews-classification config: default split: validation revision: 317f262bf1e6126357bbe89e875451e4b0938fe4 metrics: - type: accuracy value: 52.971999999999994 - type: f1 value: 50.2898280984929 - task: type: Clustering dataset: name: MTEB ThuNewsClusteringP2P type: C-MTEB/ThuNewsClusteringP2P config: default split: test revision: 5798586b105c0434e4f0fe5e767abe619442cf93 metrics: - type: v_measure value: 86.0797948663824 - task: type: Clustering dataset: name: MTEB ThuNewsClusteringS2S type: C-MTEB/ThuNewsClusteringS2S config: default split: test revision: 8a8b2caeda43f39e13c4bc5bea0f8a667896e10d metrics: - type: v_measure value: 85.10759092255017 - task: type: Retrieval dataset: name: MTEB VideoRetrieval type: C-MTEB/VideoRetrieval config: default split: dev revision: 58c2597a5943a2ba48f4668c3b90d796283c5639 metrics: - type: map_at_1 value: 65.60000000000001 - type: map_at_10 value: 74.773 - type: map_at_100 value: 75.128 - type: map_at_1000 value: 75.136 - type: map_at_3 value: 73.05 - type: map_at_5 value: 74.13499999999999 - type: mrr_at_1 value: 65.60000000000001 - type: mrr_at_10 value: 74.773 - type: mrr_at_100 value: 75.128 - type: mrr_at_1000 value: 75.136 - type: mrr_at_3 value: 73.05 - type: mrr_at_5 value: 74.13499999999999 - type: ndcg_at_1 value: 65.60000000000001 - type: ndcg_at_10 value: 78.84299999999999 - type: ndcg_at_100 value: 80.40899999999999 - type: ndcg_at_1000 value: 80.57 - type: ndcg_at_3 value: 75.40599999999999 - type: ndcg_at_5 value: 77.351 - type: precision_at_1 value: 65.60000000000001 - type: precision_at_10 value: 9.139999999999999 - type: precision_at_100 value: 0.984 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 27.400000000000002 - type: precision_at_5 value: 17.380000000000003 - type: recall_at_1 value: 65.60000000000001 - type: recall_at_10 value: 91.4 - type: recall_at_100 value: 98.4 - type: recall_at_1000 value: 99.6 - type: recall_at_3 value: 82.19999999999999 - type: recall_at_5 value: 86.9 - task: type: Classification dataset: name: MTEB Waimai type: C-MTEB/waimai-classification config: default split: test revision: 339287def212450dcaa9df8c22bf93e9980c7023 metrics: - type: accuracy value: 89.47 - type: ap value: 75.59561751845389 - type: f1 value: 87.95207751382563 - task: type: Clustering dataset: name: MTEB AlloProfClusteringP2P type: lyon-nlp/alloprof config: default split: test revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b metrics: - type: v_measure value: 76.05592323841036 - type: v_measure value: 64.51718058866508 - task: type: Reranking dataset: name: MTEB AlloprofReranking type: lyon-nlp/mteb-fr-reranking-alloprof-s2p config: default split: test revision: 666fdacebe0291776e86f29345663dfaf80a0db9 metrics: - type: map value: 73.08278490943373 - type: mrr value: 74.66561454570449 - task: type: Retrieval dataset: name: MTEB AlloprofRetrieval type: lyon-nlp/alloprof config: default split: test revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b metrics: - type: map_at_1 value: 38.912 - type: map_at_10 value: 52.437999999999995 - type: map_at_100 value: 53.38 - type: map_at_1000 value: 53.427 - type: map_at_3 value: 48.879 - type: map_at_5 value: 50.934000000000005 - type: mrr_at_1 value: 44.085 - type: mrr_at_10 value: 55.337 - type: mrr_at_100 value: 56.016999999999996 - type: mrr_at_1000 value: 56.043 - type: mrr_at_3 value: 52.55499999999999 - type: mrr_at_5 value: 54.20399999999999 - type: ndcg_at_1 value: 44.085 - type: ndcg_at_10 value: 58.876 - type: ndcg_at_100 value: 62.714000000000006 - type: ndcg_at_1000 value: 63.721000000000004 - type: ndcg_at_3 value: 52.444 - type: ndcg_at_5 value: 55.692 - type: precision_at_1 value: 44.085 - type: precision_at_10 value: 9.21 - type: precision_at_100 value: 1.164 - type: precision_at_1000 value: 0.128 - type: precision_at_3 value: 23.043 - type: precision_at_5 value: 15.898000000000001 - type: recall_at_1 value: 38.912 - type: recall_at_10 value: 75.577 - type: recall_at_100 value: 92.038 - type: recall_at_1000 value: 99.325 - type: recall_at_3 value: 58.592 - type: recall_at_5 value: 66.235 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (fr) type: mteb/amazon_reviews_multi config: fr split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 55.532000000000004 - type: f1 value: 52.5783943471605 - task: type: Retrieval dataset: name: MTEB BSARDRetrieval type: maastrichtlawtech/bsard config: default split: test revision: 5effa1b9b5fa3b0f9e12523e6e43e5f86a6e6d59 metrics: - type: map_at_1 value: 8.108 - type: map_at_10 value: 14.710999999999999 - type: map_at_100 value: 15.891 - type: map_at_1000 value: 15.983 - type: map_at_3 value: 12.237 - type: map_at_5 value: 13.679 - type: mrr_at_1 value: 8.108 - type: mrr_at_10 value: 14.710999999999999 - type: mrr_at_100 value: 15.891 - type: mrr_at_1000 value: 15.983 - type: mrr_at_3 value: 12.237 - type: mrr_at_5 value: 13.679 - type: ndcg_at_1 value: 8.108 - type: ndcg_at_10 value: 18.796 - type: ndcg_at_100 value: 25.098 - type: ndcg_at_1000 value: 27.951999999999998 - type: ndcg_at_3 value: 13.712 - type: ndcg_at_5 value: 16.309 - type: precision_at_1 value: 8.108 - type: precision_at_10 value: 3.198 - type: precision_at_100 value: 0.626 - type: precision_at_1000 value: 0.086 - type: precision_at_3 value: 6.006 - type: precision_at_5 value: 4.865 - type: recall_at_1 value: 8.108 - type: recall_at_10 value: 31.982 - type: recall_at_100 value: 62.613 - type: recall_at_1000 value: 86.036 - type: recall_at_3 value: 18.018 - type: recall_at_5 value: 24.324 - task: type: Clustering dataset: name: MTEB HALClusteringS2S type: lyon-nlp/clustering-hal-s2s config: default split: test revision: e06ebbbb123f8144bef1a5d18796f3dec9ae2915 metrics: - type: v_measure value: 30.833269778867116 - task: type: Clustering dataset: name: MTEB MLSUMClusteringP2P type: mlsum config: default split: test revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7 metrics: - type: v_measure value: 50.0281928004713 - type: v_measure value: 43.699961510636534 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (fr) type: mteb/mtop_domain config: fr split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 96.68963357344191 - type: f1 value: 96.45175170820961 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (fr) type: mteb/mtop_intent config: fr split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 87.46946445349202 - type: f1 value: 65.79860440988624 - task: type: Classification dataset: name: MTEB MasakhaNEWSClassification (fra) type: masakhane/masakhanews config: fra split: test revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60 metrics: - type: accuracy value: 82.60663507109005 - type: f1 value: 77.20462646604777 - task: type: Clustering dataset: name: MTEB MasakhaNEWSClusteringP2P (fra) type: masakhane/masakhanews config: fra split: test revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60 metrics: - type: v_measure value: 60.19311264967803 - type: v_measure value: 63.6235764409785 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (fr) type: mteb/amazon_massive_intent config: fr split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 81.65097511768661 - type: f1 value: 78.77796091490924 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (fr) type: mteb/amazon_massive_scenario config: fr split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 86.64425016812373 - type: f1 value: 85.4912728670017 - task: type: Retrieval dataset: name: MTEB MintakaRetrieval (fr) type: jinaai/mintakaqa config: fr split: test revision: efa78cc2f74bbcd21eff2261f9e13aebe40b814e metrics: - type: map_at_1 value: 35.913000000000004 - type: map_at_10 value: 48.147 - type: map_at_100 value: 48.91 - type: map_at_1000 value: 48.949 - type: map_at_3 value: 45.269999999999996 - type: map_at_5 value: 47.115 - type: mrr_at_1 value: 35.913000000000004 - type: mrr_at_10 value: 48.147 - type: mrr_at_100 value: 48.91 - type: mrr_at_1000 value: 48.949 - type: mrr_at_3 value: 45.269999999999996 - type: mrr_at_5 value: 47.115 - type: ndcg_at_1 value: 35.913000000000004 - type: ndcg_at_10 value: 54.03 - type: ndcg_at_100 value: 57.839 - type: ndcg_at_1000 value: 58.925000000000004 - type: ndcg_at_3 value: 48.217999999999996 - type: ndcg_at_5 value: 51.56699999999999 - type: precision_at_1 value: 35.913000000000004 - type: precision_at_10 value: 7.244000000000001 - type: precision_at_100 value: 0.9039999999999999 - type: precision_at_1000 value: 0.099 - type: precision_at_3 value: 18.905 - type: precision_at_5 value: 12.981000000000002 - type: recall_at_1 value: 35.913000000000004 - type: recall_at_10 value: 72.441 - type: recall_at_100 value: 90.41799999999999 - type: recall_at_1000 value: 99.099 - type: recall_at_3 value: 56.716 - type: recall_at_5 value: 64.90599999999999 - task: type: PairClassification dataset: name: MTEB OpusparcusPC (fr) type: GEM/opusparcus config: fr split: test revision: 9e9b1f8ef51616073f47f306f7f47dd91663f86a metrics: - type: cos_sim_accuracy value: 99.90069513406156 - type: cos_sim_ap value: 100.0 - type: cos_sim_f1 value: 99.95032290114257 - type: cos_sim_precision value: 100.0 - type: cos_sim_recall value: 99.90069513406156 - type: dot_accuracy value: 99.90069513406156 - type: dot_ap value: 100.0 - type: dot_f1 value: 99.95032290114257 - type: dot_precision value: 100.0 - type: dot_recall value: 99.90069513406156 - type: euclidean_accuracy value: 99.90069513406156 - type: euclidean_ap value: 100.0 - type: euclidean_f1 value: 99.95032290114257 - type: euclidean_precision value: 100.0 - type: euclidean_recall value: 99.90069513406156 - type: manhattan_accuracy value: 99.90069513406156 - type: manhattan_ap value: 100.0 - type: manhattan_f1 value: 99.95032290114257 - type: manhattan_precision value: 100.0 - type: manhattan_recall value: 99.90069513406156 - type: max_accuracy value: 99.90069513406156 - type: max_ap value: 100.0 - type: max_f1 value: 99.95032290114257 - task: type: PairClassification dataset: name: MTEB PawsX (fr) type: paws-x config: fr split: test revision: 8a04d940a42cd40658986fdd8e3da561533a3646 metrics: - type: cos_sim_accuracy value: 75.25 - type: cos_sim_ap value: 80.86376001270014 - type: cos_sim_f1 value: 73.65945437441204 - type: cos_sim_precision value: 64.02289452166802 - type: cos_sim_recall value: 86.71096345514951 - type: dot_accuracy value: 75.25 - type: dot_ap value: 80.93686107633002 - type: dot_f1 value: 73.65945437441204 - type: dot_precision value: 64.02289452166802 - type: dot_recall value: 86.71096345514951 - type: euclidean_accuracy value: 75.25 - type: euclidean_ap value: 80.86379136218862 - type: euclidean_f1 value: 73.65945437441204 - type: euclidean_precision value: 64.02289452166802 - type: euclidean_recall value: 86.71096345514951 - type: manhattan_accuracy value: 75.3 - type: manhattan_ap value: 80.87826606097734 - type: manhattan_f1 value: 73.68421052631581 - type: manhattan_precision value: 64.0 - type: manhattan_recall value: 86.82170542635659 - type: max_accuracy value: 75.3 - type: max_ap value: 80.93686107633002 - type: max_f1 value: 73.68421052631581 - task: type: STS dataset: name: MTEB SICKFr type: Lajavaness/SICK-fr config: default split: test revision: e077ab4cf4774a1e36d86d593b150422fafd8e8a metrics: - type: cos_sim_pearson value: 81.42349425981143 - type: cos_sim_spearman value: 78.90454327031226 - type: euclidean_pearson value: 78.39086497435166 - type: euclidean_spearman value: 78.9046133980509 - type: manhattan_pearson value: 78.63743094286502 - type: manhattan_spearman value: 79.12136348449269 - task: type: STS dataset: name: MTEB STS22 (fr) type: mteb/sts22-crosslingual-sts config: fr split: test revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson value: 81.452697919749 - type: cos_sim_spearman value: 82.58116836039301 - type: euclidean_pearson value: 81.04038478932786 - type: euclidean_spearman value: 82.58116836039301 - type: manhattan_pearson value: 81.37075396187771 - type: manhattan_spearman value: 82.73678231355368 - task: type: STS dataset: name: MTEB STSBenchmarkMultilingualSTS (fr) type: stsb_multi_mt config: fr split: test revision: 93d57ef91790589e3ce9c365164337a8a78b7632 metrics: - type: cos_sim_pearson value: 85.7419764013806 - type: cos_sim_spearman value: 85.46085808849622 - type: euclidean_pearson value: 83.70449639870063 - type: euclidean_spearman value: 85.46159013076233 - type: manhattan_pearson value: 83.95259510313929 - type: manhattan_spearman value: 85.8029724659458 - task: type: Summarization dataset: name: MTEB SummEvalFr type: lyon-nlp/summarization-summeval-fr-p2p config: default split: test revision: b385812de6a9577b6f4d0f88c6a6e35395a94054 metrics: - type: cos_sim_pearson value: 32.61063271753325 - type: cos_sim_spearman value: 31.454589417353603 - type: dot_pearson value: 32.6106288643431 - type: dot_spearman value: 31.454589417353603 - task: type: Reranking dataset: name: MTEB SyntecReranking type: lyon-nlp/mteb-fr-reranking-syntec-s2p config: default split: test revision: b205c5084a0934ce8af14338bf03feb19499c84d metrics: - type: map value: 84.31666666666666 - type: mrr value: 84.31666666666666 - task: type: Retrieval dataset: name: MTEB SyntecRetrieval type: lyon-nlp/mteb-fr-retrieval-syntec-s2p config: default split: test revision: 77f7e271bf4a92b24fce5119f3486b583ca016ff metrics: - type: map_at_1 value: 63.0 - type: map_at_10 value: 73.471 - type: map_at_100 value: 73.87 - type: map_at_1000 value: 73.87 - type: map_at_3 value: 70.5 - type: map_at_5 value: 73.05 - type: mrr_at_1 value: 63.0 - type: mrr_at_10 value: 73.471 - type: mrr_at_100 value: 73.87 - type: mrr_at_1000 value: 73.87 - type: mrr_at_3 value: 70.5 - type: mrr_at_5 value: 73.05 - type: ndcg_at_1 value: 63.0 - type: ndcg_at_10 value: 78.255 - type: ndcg_at_100 value: 79.88 - type: ndcg_at_1000 value: 79.88 - type: ndcg_at_3 value: 72.702 - type: ndcg_at_5 value: 77.264 - type: precision_at_1 value: 63.0 - type: precision_at_10 value: 9.3 - type: precision_at_100 value: 1.0 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 26.333000000000002 - type: precision_at_5 value: 18.0 - type: recall_at_1 value: 63.0 - type: recall_at_10 value: 93.0 - type: recall_at_100 value: 100.0 - type: recall_at_1000 value: 100.0 - type: recall_at_3 value: 79.0 - type: recall_at_5 value: 90.0 - task: type: Retrieval dataset: name: MTEB XPQARetrieval (fr) type: jinaai/xpqa config: fr split: test revision: c99d599f0a6ab9b85b065da6f9d94f9cf731679f metrics: - type: map_at_1 value: 40.338 - type: map_at_10 value: 61.927 - type: map_at_100 value: 63.361999999999995 - type: map_at_1000 value: 63.405 - type: map_at_3 value: 55.479 - type: map_at_5 value: 59.732 - type: mrr_at_1 value: 63.551 - type: mrr_at_10 value: 71.006 - type: mrr_at_100 value: 71.501 - type: mrr_at_1000 value: 71.509 - type: mrr_at_3 value: 69.07 - type: mrr_at_5 value: 70.165 - type: ndcg_at_1 value: 63.551 - type: ndcg_at_10 value: 68.297 - type: ndcg_at_100 value: 73.13199999999999 - type: ndcg_at_1000 value: 73.751 - type: ndcg_at_3 value: 62.999 - type: ndcg_at_5 value: 64.89 - type: precision_at_1 value: 63.551 - type: precision_at_10 value: 15.661 - type: precision_at_100 value: 1.9789999999999999 - type: precision_at_1000 value: 0.207 - type: precision_at_3 value: 38.273 - type: precision_at_5 value: 27.61 - type: recall_at_1 value: 40.338 - type: recall_at_10 value: 77.267 - type: recall_at_100 value: 95.892 - type: recall_at_1000 value: 99.75500000000001 - type: recall_at_3 value: 60.36 - type: recall_at_5 value: 68.825 - task: type: Clustering dataset: name: MTEB 8TagsClustering type: PL-MTEB/8tags-clustering config: default split: test revision: None metrics: - type: v_measure value: 51.36126303874126 - task: type: Classification dataset: name: MTEB AllegroReviews type: PL-MTEB/allegro-reviews config: default split: test revision: None metrics: - type: accuracy value: 67.13717693836979 - type: f1 value: 57.27609848003782 - task: type: Retrieval dataset: name: MTEB ArguAna-PL type: clarin-knext/arguana-pl config: default split: test revision: 63fc86750af76253e8c760fc9e534bbf24d260a2 metrics: - type: map_at_1 value: 35.276999999999994 - type: map_at_10 value: 51.086 - type: map_at_100 value: 51.788000000000004 - type: map_at_1000 value: 51.791 - type: map_at_3 value: 46.147 - type: map_at_5 value: 49.078 - type: mrr_at_1 value: 35.917 - type: mrr_at_10 value: 51.315999999999995 - type: mrr_at_100 value: 52.018 - type: mrr_at_1000 value: 52.022 - type: mrr_at_3 value: 46.349000000000004 - type: mrr_at_5 value: 49.297000000000004 - type: ndcg_at_1 value: 35.276999999999994 - type: ndcg_at_10 value: 59.870999999999995 - type: ndcg_at_100 value: 62.590999999999994 - type: ndcg_at_1000 value: 62.661 - type: ndcg_at_3 value: 49.745 - type: ndcg_at_5 value: 55.067 - type: precision_at_1 value: 35.276999999999994 - type: precision_at_10 value: 8.791 - type: precision_at_100 value: 0.991 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 20.057 - type: precision_at_5 value: 14.637 - type: recall_at_1 value: 35.276999999999994 - type: recall_at_10 value: 87.909 - type: recall_at_100 value: 99.14699999999999 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 60.171 - type: recall_at_5 value: 73.18599999999999 - task: type: Classification dataset: name: MTEB CBD type: PL-MTEB/cbd config: default split: test revision: None metrics: - type: accuracy value: 78.03000000000002 - type: ap value: 29.12548553897622 - type: f1 value: 66.54857118886073 - task: type: PairClassification dataset: name: MTEB CDSC-E type: PL-MTEB/cdsce-pairclassification config: default split: test revision: None metrics: - type: cos_sim_accuracy value: 89.0 - type: cos_sim_ap value: 76.75437826834582 - type: cos_sim_f1 value: 66.4850136239782 - type: cos_sim_precision value: 68.92655367231639 - type: cos_sim_recall value: 64.21052631578948 - type: dot_accuracy value: 89.0 - type: dot_ap value: 76.75437826834582 - type: dot_f1 value: 66.4850136239782 - type: dot_precision value: 68.92655367231639 - type: dot_recall value: 64.21052631578948 - type: euclidean_accuracy value: 89.0 - type: euclidean_ap value: 76.75437826834582 - type: euclidean_f1 value: 66.4850136239782 - type: euclidean_precision value: 68.92655367231639 - type: euclidean_recall value: 64.21052631578948 - type: manhattan_accuracy value: 89.0 - type: manhattan_ap value: 76.66074220647083 - type: manhattan_f1 value: 66.47058823529412 - type: manhattan_precision value: 75.33333333333333 - type: manhattan_recall value: 59.473684210526315 - type: max_accuracy value: 89.0 - type: max_ap value: 76.75437826834582 - type: max_f1 value: 66.4850136239782 - task: type: STS dataset: name: MTEB CDSC-R type: PL-MTEB/cdscr-sts config: default split: test revision: None metrics: - type: cos_sim_pearson value: 93.12903172428328 - type: cos_sim_spearman value: 92.66381487060741 - type: euclidean_pearson value: 90.37278396708922 - type: euclidean_spearman value: 92.66381487060741 - type: manhattan_pearson value: 90.32503296540962 - type: manhattan_spearman value: 92.6902938354313 - task: type: Retrieval dataset: name: MTEB DBPedia-PL type: clarin-knext/dbpedia-pl config: default split: test revision: 76afe41d9af165cc40999fcaa92312b8b012064a metrics: - type: map_at_1 value: 8.83 - type: map_at_10 value: 18.326 - type: map_at_100 value: 26.496 - type: map_at_1000 value: 28.455000000000002 - type: map_at_3 value: 12.933 - type: map_at_5 value: 15.168000000000001 - type: mrr_at_1 value: 66.0 - type: mrr_at_10 value: 72.76700000000001 - type: mrr_at_100 value: 73.203 - type: mrr_at_1000 value: 73.219 - type: mrr_at_3 value: 71.458 - type: mrr_at_5 value: 72.246 - type: ndcg_at_1 value: 55.375 - type: ndcg_at_10 value: 41.3 - type: ndcg_at_100 value: 45.891 - type: ndcg_at_1000 value: 52.905 - type: ndcg_at_3 value: 46.472 - type: ndcg_at_5 value: 43.734 - type: precision_at_1 value: 66.0 - type: precision_at_10 value: 33.074999999999996 - type: precision_at_100 value: 11.094999999999999 - type: precision_at_1000 value: 2.374 - type: precision_at_3 value: 48.583 - type: precision_at_5 value: 42.0 - type: recall_at_1 value: 8.83 - type: recall_at_10 value: 22.587 - type: recall_at_100 value: 50.61600000000001 - type: recall_at_1000 value: 73.559 - type: recall_at_3 value: 13.688 - type: recall_at_5 value: 16.855 - task: type: Retrieval dataset: name: MTEB FiQA-PL type: clarin-knext/fiqa-pl config: default split: test revision: 2e535829717f8bf9dc829b7f911cc5bbd4e6608e metrics: - type: map_at_1 value: 20.587 - type: map_at_10 value: 33.095 - type: map_at_100 value: 35.24 - type: map_at_1000 value: 35.429 - type: map_at_3 value: 28.626 - type: map_at_5 value: 31.136999999999997 - type: mrr_at_1 value: 40.586 - type: mrr_at_10 value: 49.033 - type: mrr_at_100 value: 49.952999999999996 - type: mrr_at_1000 value: 49.992 - type: mrr_at_3 value: 46.553 - type: mrr_at_5 value: 48.035 - type: ndcg_at_1 value: 40.586 - type: ndcg_at_10 value: 41.046 - type: ndcg_at_100 value: 48.586 - type: ndcg_at_1000 value: 51.634 - type: ndcg_at_3 value: 36.773 - type: ndcg_at_5 value: 38.389 - type: precision_at_1 value: 40.586 - type: precision_at_10 value: 11.466 - type: precision_at_100 value: 1.909 - type: precision_at_1000 value: 0.245 - type: precision_at_3 value: 24.434 - type: precision_at_5 value: 18.426000000000002 - type: recall_at_1 value: 20.587 - type: recall_at_10 value: 47.986000000000004 - type: recall_at_100 value: 75.761 - type: recall_at_1000 value: 94.065 - type: recall_at_3 value: 33.339 - type: recall_at_5 value: 39.765 - task: type: Retrieval dataset: name: MTEB HotpotQA-PL type: clarin-knext/hotpotqa-pl config: default split: test revision: a0bd479ac97b4ccb5bd6ce320c415d0bb4beb907 metrics: - type: map_at_1 value: 40.878 - type: map_at_10 value: 58.775999999999996 - type: map_at_100 value: 59.632 - type: map_at_1000 value: 59.707 - type: map_at_3 value: 56.074 - type: map_at_5 value: 57.629 - type: mrr_at_1 value: 81.756 - type: mrr_at_10 value: 86.117 - type: mrr_at_100 value: 86.299 - type: mrr_at_1000 value: 86.30600000000001 - type: mrr_at_3 value: 85.345 - type: mrr_at_5 value: 85.832 - type: ndcg_at_1 value: 81.756 - type: ndcg_at_10 value: 67.608 - type: ndcg_at_100 value: 70.575 - type: ndcg_at_1000 value: 71.99600000000001 - type: ndcg_at_3 value: 63.723 - type: ndcg_at_5 value: 65.70700000000001 - type: precision_at_1 value: 81.756 - type: precision_at_10 value: 13.619 - type: precision_at_100 value: 1.5939999999999999 - type: precision_at_1000 value: 0.178 - type: precision_at_3 value: 39.604 - type: precision_at_5 value: 25.332 - type: recall_at_1 value: 40.878 - type: recall_at_10 value: 68.096 - type: recall_at_100 value: 79.696 - type: recall_at_1000 value: 89.082 - type: recall_at_3 value: 59.406000000000006 - type: recall_at_5 value: 63.329 - task: type: Retrieval dataset: name: MTEB MSMARCO-PL type: clarin-knext/msmarco-pl config: default split: test revision: 8634c07806d5cce3a6138e260e59b81760a0a640 metrics: - type: map_at_1 value: 2.1839999999999997 - type: map_at_10 value: 11.346 - type: map_at_100 value: 30.325000000000003 - type: map_at_1000 value: 37.806 - type: map_at_3 value: 4.842 - type: map_at_5 value: 6.891 - type: mrr_at_1 value: 86.047 - type: mrr_at_10 value: 89.14699999999999 - type: mrr_at_100 value: 89.46600000000001 - type: mrr_at_1000 value: 89.46600000000001 - type: mrr_at_3 value: 89.14699999999999 - type: mrr_at_5 value: 89.14699999999999 - type: ndcg_at_1 value: 67.829 - type: ndcg_at_10 value: 62.222 - type: ndcg_at_100 value: 55.337 - type: ndcg_at_1000 value: 64.076 - type: ndcg_at_3 value: 68.12700000000001 - type: ndcg_at_5 value: 64.987 - type: precision_at_1 value: 86.047 - type: precision_at_10 value: 69.535 - type: precision_at_100 value: 32.93 - type: precision_at_1000 value: 6.6049999999999995 - type: precision_at_3 value: 79.845 - type: precision_at_5 value: 75.349 - type: recall_at_1 value: 2.1839999999999997 - type: recall_at_10 value: 12.866 - type: recall_at_100 value: 43.505 - type: recall_at_1000 value: 72.366 - type: recall_at_3 value: 4.947 - type: recall_at_5 value: 7.192 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (pl) type: mteb/amazon_massive_intent config: pl split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 80.75319435104238 - type: f1 value: 77.58961444860606 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (pl) type: mteb/amazon_massive_scenario config: pl split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 85.54472091459313 - type: f1 value: 84.29498563572106 - task: type: Retrieval dataset: name: MTEB NFCorpus-PL type: clarin-knext/nfcorpus-pl config: default split: test revision: 9a6f9567fda928260afed2de480d79c98bf0bec0 metrics: - type: map_at_1 value: 4.367 - type: map_at_10 value: 10.38 - type: map_at_100 value: 13.516 - type: map_at_1000 value: 14.982000000000001 - type: map_at_3 value: 7.367 - type: map_at_5 value: 8.59 - type: mrr_at_1 value: 41.486000000000004 - type: mrr_at_10 value: 48.886 - type: mrr_at_100 value: 49.657000000000004 - type: mrr_at_1000 value: 49.713 - type: mrr_at_3 value: 46.904 - type: mrr_at_5 value: 48.065000000000005 - type: ndcg_at_1 value: 40.402 - type: ndcg_at_10 value: 30.885 - type: ndcg_at_100 value: 28.393 - type: ndcg_at_1000 value: 37.428 - type: ndcg_at_3 value: 35.394999999999996 - type: ndcg_at_5 value: 33.391999999999996 - type: precision_at_1 value: 41.486000000000004 - type: precision_at_10 value: 23.437 - type: precision_at_100 value: 7.638 - type: precision_at_1000 value: 2.0389999999999997 - type: precision_at_3 value: 32.817 - type: precision_at_5 value: 28.915999999999997 - type: recall_at_1 value: 4.367 - type: recall_at_10 value: 14.655000000000001 - type: recall_at_100 value: 29.665999999999997 - type: recall_at_1000 value: 62.073 - type: recall_at_3 value: 8.51 - type: recall_at_5 value: 10.689 - task: type: Retrieval dataset: name: MTEB NQ-PL type: clarin-knext/nq-pl config: default split: test revision: f171245712cf85dd4700b06bef18001578d0ca8d metrics: - type: map_at_1 value: 28.616000000000003 - type: map_at_10 value: 41.626000000000005 - type: map_at_100 value: 42.689 - type: map_at_1000 value: 42.733 - type: map_at_3 value: 37.729 - type: map_at_5 value: 39.879999999999995 - type: mrr_at_1 value: 32.068000000000005 - type: mrr_at_10 value: 44.029 - type: mrr_at_100 value: 44.87 - type: mrr_at_1000 value: 44.901 - type: mrr_at_3 value: 40.687 - type: mrr_at_5 value: 42.625 - type: ndcg_at_1 value: 32.068000000000005 - type: ndcg_at_10 value: 48.449999999999996 - type: ndcg_at_100 value: 53.13 - type: ndcg_at_1000 value: 54.186 - type: ndcg_at_3 value: 40.983999999999995 - type: ndcg_at_5 value: 44.628 - type: precision_at_1 value: 32.068000000000005 - type: precision_at_10 value: 7.9750000000000005 - type: precision_at_100 value: 1.061 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 18.404999999999998 - type: precision_at_5 value: 13.111 - type: recall_at_1 value: 28.616000000000003 - type: recall_at_10 value: 66.956 - type: recall_at_100 value: 87.657 - type: recall_at_1000 value: 95.548 - type: recall_at_3 value: 47.453 - type: recall_at_5 value: 55.87800000000001 - task: type: Classification dataset: name: MTEB PAC type: laugustyniak/abusive-clauses-pl config: default split: test revision: None metrics: - type: accuracy value: 69.04141326382856 - type: ap value: 77.47589122111044 - type: f1 value: 66.6332277374775 - task: type: PairClassification dataset: name: MTEB PPC type: PL-MTEB/ppc-pairclassification config: default split: test revision: None metrics: - type: cos_sim_accuracy value: 86.4 - type: cos_sim_ap value: 94.1044939667201 - type: cos_sim_f1 value: 88.78048780487805 - type: cos_sim_precision value: 87.22044728434504 - type: cos_sim_recall value: 90.39735099337747 - type: dot_accuracy value: 86.4 - type: dot_ap value: 94.1044939667201 - type: dot_f1 value: 88.78048780487805 - type: dot_precision value: 87.22044728434504 - type: dot_recall value: 90.39735099337747 - type: euclidean_accuracy value: 86.4 - type: euclidean_ap value: 94.1044939667201 - type: euclidean_f1 value: 88.78048780487805 - type: euclidean_precision value: 87.22044728434504 - type: euclidean_recall value: 90.39735099337747 - type: manhattan_accuracy value: 86.4 - type: manhattan_ap value: 94.11438365697387 - type: manhattan_f1 value: 88.77968877968877 - type: manhattan_precision value: 87.84440842787681 - type: manhattan_recall value: 89.73509933774835 - type: max_accuracy value: 86.4 - type: max_ap value: 94.11438365697387 - type: max_f1 value: 88.78048780487805 - task: type: PairClassification dataset: name: MTEB PSC type: PL-MTEB/psc-pairclassification config: default split: test revision: None metrics: - type: cos_sim_accuracy value: 97.86641929499072 - type: cos_sim_ap value: 99.36904211868182 - type: cos_sim_f1 value: 96.56203288490283 - type: cos_sim_precision value: 94.72140762463343 - type: cos_sim_recall value: 98.47560975609755 - type: dot_accuracy value: 97.86641929499072 - type: dot_ap value: 99.36904211868183 - type: dot_f1 value: 96.56203288490283 - type: dot_precision value: 94.72140762463343 - type: dot_recall value: 98.47560975609755 - type: euclidean_accuracy value: 97.86641929499072 - type: euclidean_ap value: 99.36904211868183 - type: euclidean_f1 value: 96.56203288490283 - type: euclidean_precision value: 94.72140762463343 - type: euclidean_recall value: 98.47560975609755 - type: manhattan_accuracy value: 98.14471243042672 - type: manhattan_ap value: 99.43359540492416 - type: manhattan_f1 value: 96.98795180722892 - type: manhattan_precision value: 95.83333333333334 - type: manhattan_recall value: 98.17073170731707 - type: max_accuracy value: 98.14471243042672 - type: max_ap value: 99.43359540492416 - type: max_f1 value: 96.98795180722892 - task: type: Classification dataset: name: MTEB PolEmo2.0-IN type: PL-MTEB/polemo2_in config: default split: test revision: None metrics: - type: accuracy value: 89.39058171745152 - type: f1 value: 86.8552093529568 - task: type: Classification dataset: name: MTEB PolEmo2.0-OUT type: PL-MTEB/polemo2_out config: default split: test revision: None metrics: - type: accuracy value: 74.97975708502024 - type: f1 value: 58.73081628832407 - task: type: Retrieval dataset: name: MTEB Quora-PL type: clarin-knext/quora-pl config: default split: test revision: 0be27e93455051e531182b85e85e425aba12e9d4 metrics: - type: map_at_1 value: 64.917 - type: map_at_10 value: 78.74600000000001 - type: map_at_100 value: 79.501 - type: map_at_1000 value: 79.524 - type: map_at_3 value: 75.549 - type: map_at_5 value: 77.495 - type: mrr_at_1 value: 74.9 - type: mrr_at_10 value: 82.112 - type: mrr_at_100 value: 82.314 - type: mrr_at_1000 value: 82.317 - type: mrr_at_3 value: 80.745 - type: mrr_at_5 value: 81.607 - type: ndcg_at_1 value: 74.83999999999999 - type: ndcg_at_10 value: 83.214 - type: ndcg_at_100 value: 84.997 - type: ndcg_at_1000 value: 85.207 - type: ndcg_at_3 value: 79.547 - type: ndcg_at_5 value: 81.46600000000001 - type: precision_at_1 value: 74.83999999999999 - type: precision_at_10 value: 12.822 - type: precision_at_100 value: 1.506 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 34.903 - type: precision_at_5 value: 23.16 - type: recall_at_1 value: 64.917 - type: recall_at_10 value: 92.27199999999999 - type: recall_at_100 value: 98.715 - type: recall_at_1000 value: 99.854 - type: recall_at_3 value: 82.04599999999999 - type: recall_at_5 value: 87.2 - task: type: Retrieval dataset: name: MTEB SCIDOCS-PL type: clarin-knext/scidocs-pl config: default split: test revision: 45452b03f05560207ef19149545f168e596c9337 metrics: - type: map_at_1 value: 3.51 - type: map_at_10 value: 9.046999999999999 - type: map_at_100 value: 10.823 - type: map_at_1000 value: 11.144 - type: map_at_3 value: 6.257 - type: map_at_5 value: 7.648000000000001 - type: mrr_at_1 value: 17.299999999999997 - type: mrr_at_10 value: 27.419 - type: mrr_at_100 value: 28.618 - type: mrr_at_1000 value: 28.685 - type: mrr_at_3 value: 23.817 - type: mrr_at_5 value: 25.927 - type: ndcg_at_1 value: 17.299999999999997 - type: ndcg_at_10 value: 16.084 - type: ndcg_at_100 value: 23.729 - type: ndcg_at_1000 value: 29.476999999999997 - type: ndcg_at_3 value: 14.327000000000002 - type: ndcg_at_5 value: 13.017999999999999 - type: precision_at_1 value: 17.299999999999997 - type: precision_at_10 value: 8.63 - type: precision_at_100 value: 1.981 - type: precision_at_1000 value: 0.336 - type: precision_at_3 value: 13.4 - type: precision_at_5 value: 11.700000000000001 - type: recall_at_1 value: 3.51 - type: recall_at_10 value: 17.518 - type: recall_at_100 value: 40.275 - type: recall_at_1000 value: 68.203 - type: recall_at_3 value: 8.155 - type: recall_at_5 value: 11.875 - task: type: PairClassification dataset: name: MTEB SICK-E-PL type: PL-MTEB/sicke-pl-pairclassification config: default split: test revision: None metrics: - type: cos_sim_accuracy value: 86.30248675091724 - type: cos_sim_ap value: 83.6756734006714 - type: cos_sim_f1 value: 74.97367497367497 - type: cos_sim_precision value: 73.91003460207612 - type: cos_sim_recall value: 76.06837606837607 - type: dot_accuracy value: 86.30248675091724 - type: dot_ap value: 83.6756734006714 - type: dot_f1 value: 74.97367497367497 - type: dot_precision value: 73.91003460207612 - type: dot_recall value: 76.06837606837607 - type: euclidean_accuracy value: 86.30248675091724 - type: euclidean_ap value: 83.67566984333091 - type: euclidean_f1 value: 74.97367497367497 - type: euclidean_precision value: 73.91003460207612 - type: euclidean_recall value: 76.06837606837607 - type: manhattan_accuracy value: 86.28210354667753 - type: manhattan_ap value: 83.64216119130171 - type: manhattan_f1 value: 74.92152075340078 - type: manhattan_precision value: 73.4107997265892 - type: manhattan_recall value: 76.49572649572649 - type: max_accuracy value: 86.30248675091724 - type: max_ap value: 83.6756734006714 - type: max_f1 value: 74.97367497367497 - task: type: STS dataset: name: MTEB SICK-R-PL type: PL-MTEB/sickr-pl-sts config: default split: test revision: None metrics: - type: cos_sim_pearson value: 82.23295940859121 - type: cos_sim_spearman value: 78.89329160768719 - type: euclidean_pearson value: 79.56019107076818 - type: euclidean_spearman value: 78.89330209904084 - type: manhattan_pearson value: 79.76098513973719 - type: manhattan_spearman value: 79.05490162570123 - task: type: STS dataset: name: MTEB STS22 (pl) type: mteb/sts22-crosslingual-sts config: pl split: test revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson value: 37.732606308062486 - type: cos_sim_spearman value: 41.01645667030284 - type: euclidean_pearson value: 26.61722556367085 - type: euclidean_spearman value: 41.01645667030284 - type: manhattan_pearson value: 26.60917378970807 - type: manhattan_spearman value: 41.51335727617614 - task: type: Retrieval dataset: name: MTEB SciFact-PL type: clarin-knext/scifact-pl config: default split: test revision: 47932a35f045ef8ed01ba82bf9ff67f6e109207e metrics: - type: map_at_1 value: 54.31700000000001 - type: map_at_10 value: 65.564 - type: map_at_100 value: 66.062 - type: map_at_1000 value: 66.08699999999999 - type: map_at_3 value: 62.592999999999996 - type: map_at_5 value: 63.888 - type: mrr_at_1 value: 56.99999999999999 - type: mrr_at_10 value: 66.412 - type: mrr_at_100 value: 66.85900000000001 - type: mrr_at_1000 value: 66.88 - type: mrr_at_3 value: 64.22200000000001 - type: mrr_at_5 value: 65.206 - type: ndcg_at_1 value: 56.99999999999999 - type: ndcg_at_10 value: 70.577 - type: ndcg_at_100 value: 72.879 - type: ndcg_at_1000 value: 73.45 - type: ndcg_at_3 value: 65.5 - type: ndcg_at_5 value: 67.278 - type: precision_at_1 value: 56.99999999999999 - type: precision_at_10 value: 9.667 - type: precision_at_100 value: 1.083 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 26.0 - type: precision_at_5 value: 16.933 - type: recall_at_1 value: 54.31700000000001 - type: recall_at_10 value: 85.056 - type: recall_at_100 value: 95.667 - type: recall_at_1000 value: 100.0 - type: recall_at_3 value: 71.0 - type: recall_at_5 value: 75.672 - task: type: Retrieval dataset: name: MTEB TRECCOVID-PL type: clarin-knext/trec-covid-pl config: default split: test revision: 81bcb408f33366c2a20ac54adafad1ae7e877fdd metrics: - type: map_at_1 value: 0.245 - type: map_at_10 value: 2.051 - type: map_at_100 value: 12.009 - type: map_at_1000 value: 27.448 - type: map_at_3 value: 0.721 - type: map_at_5 value: 1.13 - type: mrr_at_1 value: 88.0 - type: mrr_at_10 value: 93.0 - type: mrr_at_100 value: 93.0 - type: mrr_at_1000 value: 93.0 - type: mrr_at_3 value: 93.0 - type: mrr_at_5 value: 93.0 - type: ndcg_at_1 value: 85.0 - type: ndcg_at_10 value: 80.303 - type: ndcg_at_100 value: 61.23499999999999 - type: ndcg_at_1000 value: 52.978 - type: ndcg_at_3 value: 84.419 - type: ndcg_at_5 value: 82.976 - type: precision_at_1 value: 88.0 - type: precision_at_10 value: 83.39999999999999 - type: precision_at_100 value: 61.96 - type: precision_at_1000 value: 22.648 - type: precision_at_3 value: 89.333 - type: precision_at_5 value: 87.2 - type: recall_at_1 value: 0.245 - type: recall_at_10 value: 2.193 - type: recall_at_100 value: 14.938 - type: recall_at_1000 value: 48.563 - type: recall_at_3 value: 0.738 - type: recall_at_5 value: 1.173 --- # Hoshino-Yumetsuki/gte-Qwen2-7B-instruct-Q8_0-GGUF This model was converted to GGUF format from [`Alibaba-NLP/gte-Qwen2-7B-instruct`](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Hoshino-Yumetsuki/gte-Qwen2-7B-instruct-Q8_0-GGUF --hf-file gte-qwen2-7b-instruct-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Hoshino-Yumetsuki/gte-Qwen2-7B-instruct-Q8_0-GGUF --hf-file gte-qwen2-7b-instruct-q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Hoshino-Yumetsuki/gte-Qwen2-7B-instruct-Q8_0-GGUF --hf-file gte-qwen2-7b-instruct-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Hoshino-Yumetsuki/gte-Qwen2-7B-instruct-Q8_0-GGUF --hf-file gte-qwen2-7b-instruct-q8_0.gguf -c 2048 ```
[ "BIOSSES", "SCIFACT" ]
addy88/gpt-j-8bit
addy88
text-generation
[ "transformers", "pytorch", "gptj", "text-generation", "arxiv:2106.09685", "arxiv:2110.02861", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2022-03-02T23:29:05Z
2022-01-02T06:34:27+00:00
31
2
--- {} --- This Model is 8bit Version of EleutherAI/gpt-j-6B. It is converted by Facebook's bitsandbytes library. The original GPT-J takes 22+ GB memory for float32 parameters alone, and that's before you account for gradients & optimizer. So for finetuning on single GPU This model is converted into 8bit. Here's how to run it: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1KNf5siQdM7ILQM-pHsP6gNVPKl1SJdU1) __The [original GPT-J](https://huggingface.co/EleutherAI/gpt-j-6B/tree/main)__ takes 22+ GB memory for float32 parameters alone, and that's before you account for gradients & optimizer. Even if you cast everything to 16-bit, it will still not fit onto most single-GPU setups short of A6000 and A100. You can inference it [on TPU](https://colab.research.google.com/github/kingoflolz/mesh-transformer-jax/blob/master/colab_demo.ipynb) or CPUs, but fine-tuning is way more expensive. Here, we apply several techniques to make GPT-J usable and fine-tunable on a single GPU with ~11 GB memory: - large weight tensors are quantized using dynamic 8-bit quantization and de-quantized just-in-time for multiplication - using gradient checkpoints to store one only activation per layer: using dramatically less memory at the cost of 30% slower training - scalable fine-tuning with [LoRA](https://arxiv.org/abs/2106.09685) and [8-bit Adam](https://arxiv.org/abs/2110.02861) In other words, all of the large weight-matrices are frozen in 8-bit, and you only train small adapters and optionally 1d tensors (layernorm scales, biases). ![img](https://i.imgur.com/n4XXo1x.png) __Does 8-bit affect model quality?__ Technically yes, but the effect is negligible in practice. [This notebook measures wikitext test perplexity](https://colab.research.google.com/drive/1FxGeYQyE7cx9VNCBC4gUyRVZGORW7c6g) and it is nigh indistinguishable from the original GPT-J. Quantized model is even slightly better, but that is not statistically significant. Our code differs from other 8-bit methods in that we use **8-bit only for storage, and all computations are performed in float16 or float32**. As a result, we can take advantage of nonlinear quantization that fits to each individual weight distribution. Such nonlinear quantization does not accelerate inference, but it allows for much smaller error. __What about performance?__ Both checkpointing and de-quantization has some overhead, but it's surprisingly manageable. Depending on GPU and batch size, the quantized model is 1-10% slower than the original model on top of using gradient checkpoints (which is 30% overhead). In short, this is because block-wise quantization from bitsandbytes is really fast on GPU. ### How should I fine-tune the model? We recommend starting with the original hyperparameters from [the LoRA paper](https://arxiv.org/pdf/2106.09685.pdf). On top of that, there is one more trick to consider: the overhead from de-quantizing weights does not depend on batch size. As a result, the larger batch size you can fit, the more efficient you will train. ### Can I use this technique with other models? The model was converted using [this notebook](https://colab.research.google.com/drive/1rwxh0XRdVi8VEbTx97l9xXr4JbRhZaq5#scrollTo=CX3VHn-J1Zer). It can be adapted to work with other model types. However, please bear in mind that some models replace Linear and Embedding with custom alternatives that require their own BNBWhateverWithAdapters.
[ "BEAR" ]
model-attribution-challenge/bloom-2b5
model-attribution-challenge
text-generation
[ "transformers", "pytorch", "bloom", "feature-extraction", "text-generation", "ak", "ar", "as", "bm", "bn", "ca", "code", "en", "es", "eu", "fon", "fr", "gu", "hi", "id", "ig", "ki", "kn", "lg", "ln", "ml", "mr", "ne", "nso", "ny", "or", "pa", "pt", "rn", "rw", "sn", "st", "sw", "ta", "te", "tn", "ts", "tum", "tw", "ur", "vi", "wo", "xh", "yo", "zh", "zhs", "zht", "zu", "arxiv:1909.08053", "arxiv:2110.02861", "arxiv:2108.12409", "license:bigscience-bloom-rail-1.0", "model-index", "text-generation-inference", "endpoints_compatible", "region:us" ]
2022-08-09T19:38:50Z
2022-09-27T15:58:41+00:00
31
0
--- language: - ak - ar - as - bm - bn - ca - code - en - es - eu - fon - fr - gu - hi - id - ig - ki - kn - lg - ln - ml - mr - ne - nso - ny - or - pa - pt - rn - rw - sn - st - sw - ta - te - tn - ts - tum - tw - ur - vi - wo - xh - yo - zh - zhs - zht - zu license: bigscience-bloom-rail-1.0 pipeline_tag: text-generation model-index: - name: bloom results: - task: type: text-generation name: text generation dataset: name: arc_challenge type: arc_challenge metrics: - type: acc value: 0.27986348122866894 name: acc verified: false - task: type: text-generation name: text generation dataset: name: arc_easy type: arc_easy metrics: - type: acc value: 0.5946969696969697 name: acc verified: false - task: type: text-generation name: text generation dataset: name: axb type: axb metrics: - type: acc value: 0.4433876811594203 name: acc verified: false - task: type: text-generation name: text generation dataset: name: axg type: axg metrics: - type: acc value: 0.5 name: acc verified: false - task: type: text-generation name: text generation dataset: name: boolq type: boolq metrics: - type: acc value: 0.6165137614678899 name: acc verified: false - task: type: text-generation name: text generation dataset: name: cb type: cb metrics: - type: acc value: 0.30357142857142855 name: acc verified: false - task: type: text-generation name: text generation dataset: name: cola type: cola metrics: - type: acc value: 0.610738255033557 name: acc verified: false - task: type: text-generation name: text generation dataset: name: copa type: copa metrics: - type: acc value: 0.63 name: acc verified: false - task: type: text-generation name: text generation dataset: name: crows_pairs_english type: crows_pairs_english metrics: - type: acc value: 0.4973166368515206 name: acc verified: false - task: type: text-generation name: text generation dataset: name: crows_pairs_french type: crows_pairs_french metrics: - type: acc value: 0.5032796660703638 name: acc verified: false - task: type: text-generation name: text generation dataset: name: diabla type: diabla metrics: - type: acc value: 0.28888308977035493 name: acc verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_afr type: gsarti/flores_101_afr metrics: - type: byte_perplexity value: 6.500798737976343 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_amh type: gsarti/flores_101_amh metrics: - type: byte_perplexity value: 3.9726863338897145 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ara type: gsarti/flores_101_ara metrics: - type: byte_perplexity value: 1.8083841089875814 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_asm type: gsarti/flores_101_asm metrics: - type: byte_perplexity value: 5.699102962086425 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ast type: gsarti/flores_101_ast metrics: - type: byte_perplexity value: 3.9252047073429384 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_azj type: gsarti/flores_101_azj metrics: - type: byte_perplexity value: 6.942805054270002 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_bel type: gsarti/flores_101_bel metrics: - type: byte_perplexity value: 3.614136245847082 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ben type: gsarti/flores_101_ben metrics: - type: byte_perplexity value: 5.121491534300969 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_bos type: gsarti/flores_101_bos metrics: - type: byte_perplexity value: 5.653353469118798 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_bul type: gsarti/flores_101_bul metrics: - type: byte_perplexity value: 2.7014693938055068 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_cat type: gsarti/flores_101_cat metrics: - type: byte_perplexity value: 2.305190041967345 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ceb type: gsarti/flores_101_ceb metrics: - type: byte_perplexity value: 6.291000321323428 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ces type: gsarti/flores_101_ces metrics: - type: byte_perplexity value: 5.447322753586386 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ckb type: gsarti/flores_101_ckb metrics: - type: byte_perplexity value: 3.7255124939234765 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_cym type: gsarti/flores_101_cym metrics: - type: byte_perplexity value: 12.539424151448149 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_dan type: gsarti/flores_101_dan metrics: - type: byte_perplexity value: 5.183309001005672 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_deu type: gsarti/flores_101_deu metrics: - type: byte_perplexity value: 3.1180422286591347 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ell type: gsarti/flores_101_ell metrics: - type: byte_perplexity value: 2.467943456164706 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_eng type: gsarti/flores_101_eng metrics: - type: byte_perplexity value: 2.018740628193298 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_est type: gsarti/flores_101_est metrics: - type: byte_perplexity value: 9.11654425176368 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_fas type: gsarti/flores_101_fas metrics: - type: byte_perplexity value: 3.058009097116482 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_fin type: gsarti/flores_101_fin metrics: - type: byte_perplexity value: 6.847047959628553 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_fra type: gsarti/flores_101_fra metrics: - type: byte_perplexity value: 1.9975177011840075 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ful type: gsarti/flores_101_ful metrics: - type: byte_perplexity value: 11.465912731488828 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_gle type: gsarti/flores_101_gle metrics: - type: byte_perplexity value: 8.681491663539422 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_glg type: gsarti/flores_101_glg metrics: - type: byte_perplexity value: 3.029991089015508 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_guj type: gsarti/flores_101_guj metrics: - type: byte_perplexity value: 4.955224230286231 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_hau type: gsarti/flores_101_hau metrics: - type: byte_perplexity value: 10.758347356372159 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_heb type: gsarti/flores_101_heb metrics: - type: byte_perplexity value: 3.6004478129801667 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_hin type: gsarti/flores_101_hin metrics: - type: byte_perplexity value: 4.712530650588064 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_hrv type: gsarti/flores_101_hrv metrics: - type: byte_perplexity value: 5.822418943372185 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_hun type: gsarti/flores_101_hun metrics: - type: byte_perplexity value: 6.440482646965992 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_hye type: gsarti/flores_101_hye metrics: - type: byte_perplexity value: 3.657718918347166 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ibo type: gsarti/flores_101_ibo metrics: - type: byte_perplexity value: 5.564814003872672 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ind type: gsarti/flores_101_ind metrics: - type: byte_perplexity value: 2.1597101468869373 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_isl type: gsarti/flores_101_isl metrics: - type: byte_perplexity value: 8.082349269518136 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ita type: gsarti/flores_101_ita metrics: - type: byte_perplexity value: 2.9687591414176207 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_jav type: gsarti/flores_101_jav metrics: - type: byte_perplexity value: 7.0573805415708994 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_jpn type: gsarti/flores_101_jpn metrics: - type: byte_perplexity value: 2.7758864197116933 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_kam type: gsarti/flores_101_kam metrics: - type: byte_perplexity value: 11.072949642861332 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_kan type: gsarti/flores_101_kan metrics: - type: byte_perplexity value: 5.551730651007082 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_kat type: gsarti/flores_101_kat metrics: - type: byte_perplexity value: 2.522630524283745 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_kaz type: gsarti/flores_101_kaz metrics: - type: byte_perplexity value: 3.3901748516975574 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_kea type: gsarti/flores_101_kea metrics: - type: byte_perplexity value: 8.918534182590863 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_kir type: gsarti/flores_101_kir metrics: - type: byte_perplexity value: 3.729278369847201 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_kor type: gsarti/flores_101_kor metrics: - type: byte_perplexity value: 3.932884847226212 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_lao type: gsarti/flores_101_lao metrics: - type: byte_perplexity value: 2.9077314760849924 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_lav type: gsarti/flores_101_lav metrics: - type: byte_perplexity value: 7.777221919194806 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_lin type: gsarti/flores_101_lin metrics: - type: byte_perplexity value: 7.524842908050988 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_lit type: gsarti/flores_101_lit metrics: - type: byte_perplexity value: 7.369179434621725 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ltz type: gsarti/flores_101_ltz metrics: - type: byte_perplexity value: 8.801059747949214 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_lug type: gsarti/flores_101_lug metrics: - type: byte_perplexity value: 8.483203026364786 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_luo type: gsarti/flores_101_luo metrics: - type: byte_perplexity value: 11.975963093623681 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_mal type: gsarti/flores_101_mal metrics: - type: byte_perplexity value: 4.615948455160037 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_mar type: gsarti/flores_101_mar metrics: - type: byte_perplexity value: 5.483253482821379 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_mkd type: gsarti/flores_101_mkd metrics: - type: byte_perplexity value: 2.9656732291754087 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_mlt type: gsarti/flores_101_mlt metrics: - type: byte_perplexity value: 15.004773437665275 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_mon type: gsarti/flores_101_mon metrics: - type: byte_perplexity value: 3.410598542315402 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_mri type: gsarti/flores_101_mri metrics: - type: byte_perplexity value: 7.474035895661322 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_msa type: gsarti/flores_101_msa metrics: - type: byte_perplexity value: 2.5710001772665634 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_mya type: gsarti/flores_101_mya metrics: - type: byte_perplexity value: 2.413577969878331 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_nld type: gsarti/flores_101_nld metrics: - type: byte_perplexity value: 4.127831721885065 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_nob type: gsarti/flores_101_nob metrics: - type: byte_perplexity value: 5.402763169129877 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_npi type: gsarti/flores_101_npi metrics: - type: byte_perplexity value: 5.199342701937889 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_nso type: gsarti/flores_101_nso metrics: - type: byte_perplexity value: 8.154626800955667 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_nya type: gsarti/flores_101_nya metrics: - type: byte_perplexity value: 8.179860208369393 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_oci type: gsarti/flores_101_oci metrics: - type: byte_perplexity value: 4.8617357393685845 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_orm type: gsarti/flores_101_orm metrics: - type: byte_perplexity value: 12.911595421079408 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ory type: gsarti/flores_101_ory metrics: - type: byte_perplexity value: 5.189421861225964 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_pan type: gsarti/flores_101_pan metrics: - type: byte_perplexity value: 4.698477289331806 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_pol type: gsarti/flores_101_pol metrics: - type: byte_perplexity value: 4.625550458479643 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_por type: gsarti/flores_101_por metrics: - type: byte_perplexity value: 1.9754515986213523 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_pus type: gsarti/flores_101_pus metrics: - type: byte_perplexity value: 4.4963371422771585 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ron type: gsarti/flores_101_ron metrics: - type: byte_perplexity value: 4.965456830031304 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_rus type: gsarti/flores_101_rus metrics: - type: byte_perplexity value: 2.0498020542445303 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_slk type: gsarti/flores_101_slk metrics: - type: byte_perplexity value: 6.450822127057479 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_slv type: gsarti/flores_101_slv metrics: - type: byte_perplexity value: 6.620252120186232 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_sna type: gsarti/flores_101_sna metrics: - type: byte_perplexity value: 8.462166771382726 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_snd type: gsarti/flores_101_snd metrics: - type: byte_perplexity value: 5.466066951221973 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_som type: gsarti/flores_101_som metrics: - type: byte_perplexity value: 11.95918054093392 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_spa type: gsarti/flores_101_spa metrics: - type: byte_perplexity value: 1.8965140104323535 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_srp type: gsarti/flores_101_srp metrics: - type: byte_perplexity value: 2.871214785885079 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_swe type: gsarti/flores_101_swe metrics: - type: byte_perplexity value: 5.054972008155866 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_swh type: gsarti/flores_101_swh metrics: - type: byte_perplexity value: 3.6973091886730676 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_tam type: gsarti/flores_101_tam metrics: - type: byte_perplexity value: 4.539493400469833 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_tel type: gsarti/flores_101_tel metrics: - type: byte_perplexity value: 5.807499987508966 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_tgk type: gsarti/flores_101_tgk metrics: - type: byte_perplexity value: 3.5994818827380426 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_tgl type: gsarti/flores_101_tgl metrics: - type: byte_perplexity value: 5.667053833119858 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_tha type: gsarti/flores_101_tha metrics: - type: byte_perplexity value: 2.365940201944242 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_tur type: gsarti/flores_101_tur metrics: - type: byte_perplexity value: 4.885014749844601 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_ukr type: gsarti/flores_101_ukr metrics: - type: byte_perplexity value: 2.7240934990288483 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_umb type: gsarti/flores_101_umb metrics: - type: byte_perplexity value: 12.766915508610673 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_urd type: gsarti/flores_101_urd metrics: - type: byte_perplexity value: 1.9797467071381232 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_uzb type: gsarti/flores_101_uzb metrics: - type: byte_perplexity value: 12.002337637722146 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_vie type: gsarti/flores_101_vie metrics: - type: byte_perplexity value: 1.76578415476397 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_wol type: gsarti/flores_101_wol metrics: - type: byte_perplexity value: 9.144285650306488 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_xho type: gsarti/flores_101_xho metrics: - type: byte_perplexity value: 7.403240538286952 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_yor type: gsarti/flores_101_yor metrics: - type: byte_perplexity value: 5.91272037551173 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_zho_simpl type: gsarti/flores_101_zho_simpl metrics: - type: byte_perplexity value: 2.2769070822768533 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_zho_trad type: gsarti/flores_101_zho_trad metrics: - type: byte_perplexity value: 2.5180582198242383 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: gsarti/flores_101_zul type: gsarti/flores_101_zul metrics: - type: byte_perplexity value: 8.53353320693145 name: byte_perplexity verified: false - task: type: text-generation name: text generation dataset: name: headqa type: headqa metrics: - type: acc value: 0.26440554339897887 name: acc verified: false - task: type: text-generation name: text generation dataset: name: hellaswag type: hellaswag metrics: - type: acc value: 0.41236805417247563 name: acc verified: false - task: type: text-generation name: text generation dataset: name: logiqa type: logiqa metrics: - type: acc value: 0.2073732718894009 name: acc verified: false - task: type: text-generation name: text generation dataset: name: mathqa type: mathqa metrics: - type: acc value: 0.24958123953098826 name: acc verified: false - task: type: text-generation name: text generation dataset: name: mc_taco type: mc_taco metrics: - type: em value: 0.11936936936936937 name: em verified: false - task: type: text-generation name: text generation dataset: name: mnli type: mnli metrics: - type: acc value: 0.35496688741721855 name: acc verified: false - task: type: text-generation name: text generation dataset: name: mnli_mismatched type: mnli_mismatched metrics: - type: acc value: 0.35211554109031734 name: acc verified: false - task: type: text-generation name: text generation dataset: name: mrpc type: mrpc metrics: - type: acc value: 0.5857843137254902 name: acc verified: false - task: type: text-generation name: text generation dataset: name: multirc type: multirc metrics: - type: acc value: 0.5375412541254125 name: acc verified: false - task: type: text-generation name: text generation dataset: name: openbookqa type: openbookqa metrics: - type: acc value: 0.216 name: acc verified: false - task: type: text-generation name: text generation dataset: name: piqa type: piqa metrics: - type: acc value: 0.7078346028291621 name: acc verified: false - task: type: text-generation name: text generation dataset: name: prost type: prost metrics: - type: acc value: 0.22683603757472245 name: acc verified: false - task: type: text-generation name: text generation dataset: name: pubmedqa type: pubmedqa metrics: - type: acc value: 0.616 name: acc verified: false - task: type: text-generation name: text generation dataset: name: qnli type: qnli metrics: - type: acc value: 0.5072304594545122 name: acc verified: false - task: type: text-generation name: text generation dataset: name: qqp type: qqp metrics: - type: acc value: 0.3842443729903537 name: acc verified: false - task: type: text-generation name: text generation dataset: name: race type: race metrics: - type: acc value: 0.3521531100478469 name: acc verified: false - task: type: text-generation name: text generation dataset: name: rte type: rte metrics: - type: acc value: 0.47653429602888087 name: acc verified: false - task: type: text-generation name: text generation dataset: name: sciq type: sciq metrics: - type: acc value: 0.892 name: acc verified: false - task: type: text-generation name: text generation dataset: name: sst type: sst metrics: - type: acc value: 0.5177752293577982 name: acc verified: false - task: type: text-generation name: text generation dataset: name: triviaqa type: triviaqa metrics: - type: acc value: 0.041633518960487934 name: acc verified: false - task: type: text-generation name: text generation dataset: name: tydiqa_primary type: tydiqa_primary metrics: - type: acc value: 0.3011337608795236 name: acc verified: false - task: type: text-generation name: text generation dataset: name: webqs type: webqs metrics: - type: acc value: 0.01673228346456693 name: acc verified: false - task: type: text-generation name: text generation dataset: name: wic type: wic metrics: - type: acc value: 0.5015673981191222 name: acc verified: false - task: type: text-generation name: text generation dataset: name: winogrande type: winogrande metrics: - type: acc value: 0.5864246250986582 name: acc verified: false - task: type: text-generation name: text generation dataset: name: wnli type: wnli metrics: - type: acc value: 0.471830985915493 name: acc verified: false - task: type: text-generation name: text generation dataset: name: wsc type: wsc metrics: - type: acc value: 0.4423076923076923 name: acc verified: false - task: type: text-generation name: text generation dataset: name: humaneval type: humaneval metrics: - type: pass@1 value: 0.15524390243902436 name: pass@1 verified: false - type: pass@10 value: 0.3220367632383857 name: pass@10 verified: false - type: pass@100 value: 0.5545431515723145 name: pass@100 verified: false --- <h1 style='text-align: center '>BLOOM LM</h1> <h2 style='text-align: center '><em>BigScience Large Open-science Open-access Multilingual Language Model</em> </h2> <h3 style='text-align: center '>Model Card</h3> <img src="https://s3.amazonaws.com/moonup/production/uploads/1657124309515-5f17f0a0925b9863e28ad517.png" alt="BigScience Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/> Version 1.0 / 26.May.2022 ## Table of Contents 1. [Model Details](#model-details) 2. [Uses](#uses) 3. [Training Data](#training-data) 4. [Risks and Limitations](#risks-and-limitations) 5. [Evaluation](#evaluation) 6. [Recommendations](#recommendations) 7. [Glossary and Calculations](#glossary-and-calculations) 8. [More Information](#more-information) 9. [Model Card Authors](#model-card-authors) ## Model Details ### Basics *This section provides information for anyone who wants to know about the model.* <details> <summary>Click to expand</summary> <br/> **Developed by:** BigScience ([website](https://bigscience.huggingface.co)) * All collaborators are either volunteers or have an agreement with their employer. *(Further breakdown of participants forthcoming.)* **Model Type:** Transformer-based Language Model **Version:** 1.0.0 **Languages:** Multiple; see [training data](#training-data) **License:** RAIL License v1.0 ([link](https://huggingface.co/spaces/bigscience/license)) **Release Date Estimate:** Monday, 11.July.2022 **Send Questions to:** [email protected] **Cite as:** BigScience, _BigScience Language Open-science Open-access Multilingual (BLOOM) Language Model_. International, May 2021-May 2022 **Funded by:** * The French government. * Hugging Face ([website](https://huggingface.co)). * Organizations of contributors. *(Further breakdown of organizations forthcoming.)* </details> ### Technical Specifications *This section provides information for people who work on model development.* <details> <summary>Click to expand</summary><br/> Please see [the BLOOM training README](https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml#readme) for full details on replicating training. **Model Architecture:** Modified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https://github.com/bigscience-workshop/Megatron-DeepSpeed)): * Decoder-only architecture * Layer normalization applied to word embeddings layer (`StableEmbedding`; see [code](https://github.com/facebookresearch/bitsandbytes), [paper](https://arxiv.org/pdf/2110.02861.pdf)) * ALiBI positional encodings (see [paper](https://arxiv.org/pdf/2108.12409.pdf)), with GeLU activation functions * 3,002,557,440 parameters: * 642,252,800 embedding parameters * 30 layers, 32 attention heads * Hidden layers are 2560-dimensional * Sequence length of 2048 tokens used (see [BLOOM tokenizer](https://huggingface.co/bigscience/tokenizer), [tokenizer description](#tokenization)) **Objective Function:** Cross Entropy with mean reduction (see [API documentation](https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html#torch.nn.CrossEntropyLoss)). **Compute infrastructure:** Jean Zay Public Supercomputer, provided by the French government (see [announcement](https://www.enseignementsup-recherche.gouv.fr/fr/signature-du-marche-d-acquisition-de-l-un-des-supercalculateurs-les-plus-puissants-d-europe-46733)). * Hardware: 384 A100 80GB GPUs (48 nodes): * Additional 32 A100 80GB GPUs (4 nodes) in reserve * 8 GPUs per node Using NVLink 4 inter-gpu connects, 4 OmniPath links * CPU: AMD * CPU memory: 512GB per node * GPU memory: 640GB per node * Inter-node connect: Omni-Path Architecture (OPA) * NCCL-communications network: a fully dedicated subnet * Disc IO network: shared network with other types of nodes * Software: * Megatron-DeepSpeed ([Github link](https://github.com/bigscience-workshop/Megatron-DeepSpeed)) * DeepSpeed ([Github link](https://github.com/microsoft/DeepSpeed)) * PyTorch (pytorch-1.11 w/ CUDA-11.5; see [Github link](https://github.com/pytorch/pytorch)) * apex ([Github link](https://github.com/NVIDIA/apex)) #### **Training** Training logs: [Tensorboard link](https://huggingface.co/tensorboard/bigscience/tr11c-2B5-logs) - Number of epochs: 1 (*current target*) - Dates: - Started 11th March, 2022 11:42am PST - Ended 5th July, 2022 - Estimated cost of training: Equivalent of $2-5M in cloud computing (including preliminary experiments) - Server training location: Île-de-France, France #### **Tokenization** The BLOOM tokenizer ([link](https://huggingface.co/bigscience/tokenizer)) is a learned subword tokenizer trained using: - A byte-level Byte Pair Encoding (BPE) algorithm - A simple pre-tokenization rule, no normalization - A vocabulary size of 250,680 It was trained on a subset of a preliminary version of the corpus using alpha-weighting per language. </details> ### Environmental Impact <details> <summary>Click to expand</summary><br/> The training supercomputer, Jean Zay ([website](http://www.idris.fr/eng/jean-zay/jean-zay-presentation-eng.html)), uses mostly nuclear energy. The heat generated by it is reused for heating campus housing. **Estimated carbon emissions:** *(Forthcoming upon completion of training.)* **Estimated electricity usage:** *(Forthcoming upon completion of training.)* </details> <p>&nbsp;</p> ## Uses *This section addresses questions around how the model is intended to be used, discusses the foreseeable users of the model (including those affected by the model), and describes uses that are considered out of scope or misuse of the model. It provides information for anyone considering using the model or who is affected by the model.* <details> <summary>Click to expand</summary><br/> ### Intended Use This model is being created in order to enable public research on large language models (LLMs). LLMs are intended to be used for language generation or as a pretrained base model that can be further fine-tuned for specific tasks. Use cases below are not exhaustive. #### **Direct Use** - Text generation - Exploring characteristics of language generated by a language model - Examples: Cloze tests, counterfactuals, generations with reframings #### **Downstream Use** - Tasks that leverage language models include: Information Extraction, Question Answering, Summarization ### Misuse and Out-of-scope Use *This section addresses what users ought not do with the model.* See the [BLOOM License](https://huggingface.co/spaces/bigscience/license), Attachment A, for detailed usage restrictions. The below list is non-exhaustive, but lists some easily foreseeable problematic use cases. #### **Out-of-scope Uses** Using the model in [high-stakes](#high-stakes) settings is out of scope for this model.  The model is not designed for [critical decisions](#critical-decisions) nor uses with any material consequences on an individual's livelihood or wellbeing. The model outputs content that appears factual but is not correct. ##### Out-of-scope Uses Include: - Usage in biomedical domains, political and legal domains, or finance domains - Usage for evaluating or scoring individuals, such as for employment, education, or credit - Applying the model for critical automatic decisions, generating factual content, creating reliable summaries, or generating predictions that must be correct #### **Misuse** Intentionally using the model for harm, violating [human rights](#human-rights), or other kinds of malicious activities, is a misuse of this model. This includes: - Spam generation - Disinformation and influence operations - Disparagement and defamation - Harassment and abuse - [Deception](#deception) - Unconsented impersonation and imitation - Unconsented surveillance - Generating content without attribution to the model, as specified in the [RAIL License, Use Restrictions](https://huggingface.co/spaces/bigscience/license) ### Intended Users #### **Direct Users** - General Public - Researchers - Students - Educators - Engineers/developers - Non-commercial entities - Community advocates, including human and civil rights groups #### Indirect Users - Users of derivatives created by Direct Users, such as those using software with an [intended use](#intended-use) - Users of [Derivatives of the Model, as described in the License](https://huggingface.co/spaces/bigscience/license) #### Others Affected (Parties Prenantes) - People and groups referred to by the LLM - People and groups exposed to outputs of, or decisions based on, the LLM - People and groups whose original work is included in the LLM </details> <p>&nbsp;</p> ## Training Data *This section provides a high-level overview of the training data. It is relevant for anyone who wants to know the basics of what the model is learning.* <details> <summary>Click to expand</summary><br/> Details for each dataset are provided in individual [Data Cards](https://huggingface.co/spaces/bigscience/BigScienceCorpus). Training data includes: - 45 natural languages - 12 programming languages - In 1.5TB of pre-processed text, converted into 350B unique tokens (see [the tokenizer section](#tokenization) for more.) #### **Languages** The pie chart shows the distribution of languages in training data. ![pie chart showing the distribution of languages in training data](https://github.com/bigscience-workshop/model_card/blob/main/assets/data/pie_chart.svg?raw=true) The following table shows the further distribution of Niger-Congo and Indic languages in the training data. <details> <summary>Click to expand</summary><br/> | Niger Congo | Percentage | | Indic | Percentage | |----------------|------------ |------ |-----------|------------| | Chi Tumbuka | 0.00002 | | Assamese | 0.01 | | Kikuyu | 0.00004 | | Odia | 0.04 | | Bambara | 0.00004 | | Gujarati | 0.04 | | Akan | 0.00007 | | Marathi | 0.05 | | Xitsonga | 0.00007 | | Punjabi | 0.05 | | Sesotho | 0.00007 | | Kannada | 0.06 | | Chi Chewa | 0.0001 | | Nepali | 0.07 | | Setswana | 0.0002 | | Telugu | 0.09 | | Northern Sotho | 0.0002 | | Malayalam | 0.10 | | Fon | 0.0002 | | Urdu | 0.10 | | Kirundi | 0.0003 | | Tamil | 0.20 | | Wolof | 0.0004 | | Bengali | 0.50 | | Kuganda | 0.0004 | | Hindi | 0.70 | | Chi Shona | 0.001 | | Isi Zulu | 0.001 | | Igbo | 0.001 | | Xhosa | 0.001 | | Kinyarwanda | 0.003 | | Yoruba | 0.006 | | Swahili | 0.02 | </details> The following table shows the distribution of programming languages. <details> <summary>Click to expand</summary><br/> | Extension | Language | Number of files | |----------------|------------|-----------------| | java | Java | 5,407,724 | | php | PHP | 4,942,186 | | cpp | C++ | 2,503,930 | | py | Python | 2,435,072 | | js | JavaScript | 1,905,518 | | cs | C# | 1,577,347 | | rb | Ruby | 6,78,413 | | cc | C++ | 443,054 | | hpp | C++ | 391,048 | | lua | Lua | 352,317 | | go | GO | 227,763 | | ts | TypeScript | 195,254 | | C | C | 134,537 | | scala | Scala | 92,052 | | hh | C++ | 67,161 | | H | C++ | 55,899 | | tsx | TypeScript | 33,107 | | rs | Rust | 29,693 | | phpt | PHP | 9,702 | | c++ | C++ | 1,342 | | h++ | C++ | 791 | | php3 | PHP | 540 | | phps | PHP | 270 | | php5 | PHP | 166 | | php4 | PHP | 29 | </details> </details> <p>&nbsp;</p> ## Risks and Limitations *This section identifies foreseeable harms and misunderstandings.* <details> <summary>Click to expand</summary><br/> Model may: - Overrepresent some viewpoints and underrepresent others - Contain stereotypes - Contain [personal information](#personal-data-and-information) - Generate: - Hateful, abusive, or violent language - Discriminatory or prejudicial language - Content that may not be appropriate for all settings, including sexual content - Make errors, including producing incorrect information as if it were factual - Generate irrelevant or repetitive outputs </details> <p>&nbsp;</p> ## Evaluation *This section describes the evaluation protocols and provides the results.* <details> <summary>Click to expand</summary><br/> ### Metrics *This section describes the different ways performance is calculated and why.* Includes: | Metric | Why chosen | |--------------------|--------------------------------------------------------------------| | [Perplexity](#perplexity) | Standard metric for quantifying model improvements during training | | Cross Entropy [Loss](#loss) | Standard objective for language models. | And multiple different metrics for specific tasks. _(More evaluation metrics forthcoming upon completion of evaluation protocol.)_ ### Factors *This section lists some different aspects of BLOOM models. Its focus is on aspects that are likely to give rise to high variance in model behavior.* - Language, such as English or Yoruba - Domain, such as newswire or stories - Demographic characteristics, such as gender or nationality ### Results *Results are based on the [Factors](#factors) and [Metrics](#metrics).* **Zero-shot evaluations:** See this repository for JSON files: https://github.com/bigscience-workshop/evaluation-results | Task | Language | Metric | BLOOM-2B5 | |:----|:----|:----|:----:| | arc_challenge | eng | acc ↑ | 0.28 | | arc_easy | eng | acc ↑ | 0.595 | | axb (Median of 10 prompts) | eng | acc ↑ | 0.443 | | axg (Median of 10 prompts) | eng | acc ↑ | 0.5 | | boolq (Median of 11 prompts) | eng | acc ↑ | 0.617 | | cb (Median of 15 prompts) | eng | acc ↑ | 0.304 | | cola (Median of 5 prompts) | eng | acc ↑ | 0.611 | | copa (Median of 9 prompts) | eng | acc ↑ | 0.63 | | crows_pairs_english (Median of 6 prompts) | eng | acc ↑ | 0.497 | | crows_pairs_french (Median of 7 prompts) | fra | acc ↑ | 0.503 | | diabla (Median of 2 prompts) | eng | acc ↑ | 0.289 | | gsarti/flores_101_afr | afr | byte_perplexity ↓ | 6.501 | | gsarti/flores_101_amh | amh | byte_perplexity ↓ | 3.973 | | gsarti/flores_101_ara | ara | byte_perplexity ↓ | 1.808 | | gsarti/flores_101_asm | asm | byte_perplexity ↓ | 5.699 | | gsarti/flores_101_ast | ast | byte_perplexity ↓ | 3.925 | | gsarti/flores_101_azj | azj | byte_perplexity ↓ | 6.943 | | gsarti/flores_101_bel | bel | byte_perplexity ↓ | 3.614 | | gsarti/flores_101_ben | ben | byte_perplexity ↓ | 5.121 | | gsarti/flores_101_bos | bos | byte_perplexity ↓ | 5.653 | | gsarti/flores_101_bul | bul | byte_perplexity ↓ | 2.701 | | gsarti/flores_101_cat | cat | byte_perplexity ↓ | 2.305 | | gsarti/flores_101_ceb | ceb | byte_perplexity ↓ | 6.291 | | gsarti/flores_101_ces | ces | byte_perplexity ↓ | 5.447 | | gsarti/flores_101_ckb | ckb | byte_perplexity ↓ | 3.726 | | gsarti/flores_101_cym | cym | byte_perplexity ↓ | 12.539 | | gsarti/flores_101_dan | dan | byte_perplexity ↓ | 5.183 | | gsarti/flores_101_deu | deu | byte_perplexity ↓ | 3.118 | | gsarti/flores_101_ell | ell | byte_perplexity ↓ | 2.468 | | gsarti/flores_101_eng | eng | byte_perplexity ↓ | 2.019 | | gsarti/flores_101_est | est | byte_perplexity ↓ | 9.117 | | gsarti/flores_101_fas | fas | byte_perplexity ↓ | 3.058 | | gsarti/flores_101_fin | fin | byte_perplexity ↓ | 6.847 | | gsarti/flores_101_fra | fra | byte_perplexity ↓ | 1.998 | | gsarti/flores_101_ful | ful | byte_perplexity ↓ | 11.466 | | gsarti/flores_101_gle | gle | byte_perplexity ↓ | 8.681 | | gsarti/flores_101_glg | glg | byte_perplexity ↓ | 3.03 | | gsarti/flores_101_guj | guj | byte_perplexity ↓ | 4.955 | | gsarti/flores_101_hau | hau | byte_perplexity ↓ | 10.758 | | gsarti/flores_101_heb | heb | byte_perplexity ↓ | 3.6 | | gsarti/flores_101_hin | hin | byte_perplexity ↓ | 4.713 | | gsarti/flores_101_hrv | hrv | byte_perplexity ↓ | 5.822 | | gsarti/flores_101_hun | hun | byte_perplexity ↓ | 6.44 | | gsarti/flores_101_hye | hye | byte_perplexity ↓ | 3.658 | | gsarti/flores_101_ibo | ibo | byte_perplexity ↓ | 5.565 | | gsarti/flores_101_ind | ind | byte_perplexity ↓ | 2.16 | | gsarti/flores_101_isl | isl | byte_perplexity ↓ | 8.082 | | gsarti/flores_101_ita | ita | byte_perplexity ↓ | 2.969 | | gsarti/flores_101_jav | jav | byte_perplexity ↓ | 7.057 | | gsarti/flores_101_jpn | jpn | byte_perplexity ↓ | 2.776 | | gsarti/flores_101_kam | kam | byte_perplexity ↓ | 11.073 | | gsarti/flores_101_kan | kan | byte_perplexity ↓ | 5.552 | | gsarti/flores_101_kat | kat | byte_perplexity ↓ | 2.523 | | gsarti/flores_101_kaz | kaz | byte_perplexity ↓ | 3.39 | | gsarti/flores_101_kea | kea | byte_perplexity ↓ | 8.919 | | gsarti/flores_101_kir | kir | byte_perplexity ↓ | 3.729 | | gsarti/flores_101_kor | kor | byte_perplexity ↓ | 3.933 | | gsarti/flores_101_lao | lao | byte_perplexity ↓ | 2.908 | | gsarti/flores_101_lav | lav | byte_perplexity ↓ | 7.777 | | gsarti/flores_101_lin | lin | byte_perplexity ↓ | 7.525 | | gsarti/flores_101_lit | lit | byte_perplexity ↓ | 7.369 | | gsarti/flores_101_ltz | ltz | byte_perplexity ↓ | 8.801 | | gsarti/flores_101_lug | lug | byte_perplexity ↓ | 8.483 | | gsarti/flores_101_luo | luo | byte_perplexity ↓ | 11.976 | | gsarti/flores_101_mal | mal | byte_perplexity ↓ | 4.616 | | gsarti/flores_101_mar | mar | byte_perplexity ↓ | 5.483 | | gsarti/flores_101_mkd | mkd | byte_perplexity ↓ | 2.966 | | gsarti/flores_101_mlt | mlt | byte_perplexity ↓ | 15.005 | | gsarti/flores_101_mon | mon | byte_perplexity ↓ | 3.411 | | gsarti/flores_101_mri | mri | byte_perplexity ↓ | 7.474 | | gsarti/flores_101_msa | msa | byte_perplexity ↓ | 2.571 | | gsarti/flores_101_mya | mya | byte_perplexity ↓ | 2.414 | | gsarti/flores_101_nld | nld | byte_perplexity ↓ | 4.128 | | gsarti/flores_101_nob | nob | byte_perplexity ↓ | 5.403 | | gsarti/flores_101_npi | npi | byte_perplexity ↓ | 5.199 | | gsarti/flores_101_nso | nso | byte_perplexity ↓ | 8.155 | | gsarti/flores_101_nya | nya | byte_perplexity ↓ | 8.18 | | gsarti/flores_101_oci | oci | byte_perplexity ↓ | 4.862 | | gsarti/flores_101_orm | orm | byte_perplexity ↓ | 12.912 | | gsarti/flores_101_ory | ory | byte_perplexity ↓ | 5.189 | | gsarti/flores_101_pan | pan | byte_perplexity ↓ | 4.698 | | gsarti/flores_101_pol | pol | byte_perplexity ↓ | 4.626 | | gsarti/flores_101_por | por | byte_perplexity ↓ | 1.975 | | gsarti/flores_101_pus | pus | byte_perplexity ↓ | 4.496 | | gsarti/flores_101_ron | ron | byte_perplexity ↓ | 4.965 | | gsarti/flores_101_rus | rus | byte_perplexity ↓ | 2.05 | | gsarti/flores_101_slk | slk | byte_perplexity ↓ | 6.451 | | gsarti/flores_101_slv | slv | byte_perplexity ↓ | 6.62 | | gsarti/flores_101_sna | sna | byte_perplexity ↓ | 8.462 | | gsarti/flores_101_snd | snd | byte_perplexity ↓ | 5.466 | | gsarti/flores_101_som | som | byte_perplexity ↓ | 11.959 | | gsarti/flores_101_spa | spa | byte_perplexity ↓ | 1.897 | | gsarti/flores_101_srp | srp | byte_perplexity ↓ | 2.871 | | gsarti/flores_101_swe | swe | byte_perplexity ↓ | 5.055 | | gsarti/flores_101_swh | swh | byte_perplexity ↓ | 3.697 | | gsarti/flores_101_tam | tam | byte_perplexity ↓ | 4.539 | | gsarti/flores_101_tel | tel | byte_perplexity ↓ | 5.807 | | gsarti/flores_101_tgk | tgk | byte_perplexity ↓ | 3.599 | | gsarti/flores_101_tgl | tgl | byte_perplexity ↓ | 5.667 | | gsarti/flores_101_tha | tha | byte_perplexity ↓ | 2.366 | | gsarti/flores_101_tur | tur | byte_perplexity ↓ | 4.885 | | gsarti/flores_101_ukr | ukr | byte_perplexity ↓ | 2.724 | | gsarti/flores_101_umb | umb | byte_perplexity ↓ | 12.767 | | gsarti/flores_101_urd | urd | byte_perplexity ↓ | 1.98 | | gsarti/flores_101_uzb | uzb | byte_perplexity ↓ | 12.002 | | gsarti/flores_101_vie | vie | byte_perplexity ↓ | 1.766 | | gsarti/flores_101_wol | wol | byte_perplexity ↓ | 9.144 | | gsarti/flores_101_xho | xho | byte_perplexity ↓ | 7.403 | | gsarti/flores_101_yor | yor | byte_perplexity ↓ | 5.913 | | gsarti/flores_101_zho_simpl | zho_simpl | byte_perplexity ↓ | 2.277 | | gsarti/flores_101_zho_trad | zho_trad | byte_perplexity ↓ | 2.518 | | gsarti/flores_101_zul | zul | byte_perplexity ↓ | 8.534 | | headqa | esp | acc ↑ | 0.264 | | hellaswag | eng | acc ↑ | 0.412 | | logiqa | eng | acc ↑ | 0.207 | | mathqa | eng | acc ↑ | 0.25 | | mc_taco | eng | em ↑ | 0.119 | | mnli (Median of 15 prompts) | eng | acc ↑ | 0.355 | | mnli_mismatched (Median of 15 prompts) | eng | acc ↑ | 0.352 | | mrpc | eng | acc ↑ | 0.586 | | multirc (Median of 11 prompts) | eng | acc ↑ | 0.538 | | openbookqa | eng | acc ↑ | 0.216 | | piqa | eng | acc ↑ | 0.708 | | prost | eng | acc ↑ | 0.227 | | pubmedqa | eng | acc ↑ | 0.616 | | qnli | eng | acc ↑ | 0.507 | | qqp (Median of 7 prompts) | eng | acc ↑ | 0.384 | | race | eng | acc ↑ | 0.352 | | rte (Median of 6 prompts) | eng | acc ↑ | 0.477 | | sciq | eng | acc ↑ | 0.892 | | sst (Median of 6 prompts) | eng | acc ↑ | 0.518 | | triviaqa | eng | acc ↑ | 0.042 | | tydiqa_primary (Median of 24 prompts) | eng | acc ↑ | 0.301 | | webqs | eng | acc ↑ | 0.017 | | wic (Median of 11 prompts) | eng | acc ↑ | 0.502 | | winogrande | eng | acc ↑ | 0.586 | | wnli (Median of 6 prompts) | eng | acc ↑ | 0.472 | | wsc (Median of 11 prompts) | eng | acc ↑ | 0.442 | | humaneval | python | pass@1 ↑ | 0.155 | | humaneval | python | pass@10 ↑ | 0.322 | | humaneval | python | pass@100 ↑ | 0.555 | **Train-time Evaluation:** As of 25.May.2022, 15:00 PST: - Training Loss: 2.0 - Validation Loss: 2.2 - Perplexity: 8.9 </details> <p>&nbsp;</p> ## Recommendations *This section provides information on warnings and potential mitigations.* <details> <summary>Click to expand</summary><br/> - Indirect users should be made aware when the content they're working with is created by the LLM. - Users should be aware of [Risks and Limitations](#risks-and-limitations), and include an appropriate age disclaimer or blocking interface as necessary. - Models pretrained with the LLM should include an updated Model Card. - Users of the model should provide mechanisms for those affected to provide feedback, such as an email address for comments. </details> <p>&nbsp;</p> ## Glossary and Calculations *This section defines common terms and how metrics are calculated.* <details> <summary>Click to expand</summary><br/> - <a name="loss">**Loss:**</a> A calculation of the difference between what the model has learned and what the data shows ("groundtruth"). The lower the loss, the better. The training process aims to minimize the loss. - <a name="perplexity">**Perplexity:**</a> This is based on what the model estimates the probability of new data is. The lower the perplexity, the better. If the model is 100% correct at predicting the next token it will see, then the perplexity is 1. Mathematically this is calculated using entropy. - <a name="high-stakes">**High-stakes settings:**</a> Such as those identified as "high-risk AI systems" and "unacceptable risk AI systems" in the European Union's proposed [Artificial Intelligence (AI) Act](https://artificialintelligenceact.eu/annexes/). - <a name="critical-decisions">**Critical decisions:**</a> Such as those defined in [the United States' proposed Algorithmic Accountability Act](https://www.congress.gov/117/bills/s3572/BILLS-117s3572is.pdf). - <a name="human-rights">**Human rights:**</a> Includes those rights defined in the [Universal Declaration of Human Rights](https://www.un.org/sites/un2.un.org/files/2021/03/udhr.pdf). - <a name="personal-data-and-information">**Personal Data and Personal Information:**</a> Personal data and information is defined in multiple data protection regulations, such as "[personal data](https://gdpr-info.eu/issues/personal-data/)" in the [European Union's General Data Protection Regulation](https://gdpr-info.eu); and "personal information" in the Republic of South Africa's [Protection of Personal Information Act](https://www.gov.za/sites/default/files/gcis_document/201409/3706726-11act4of2013popi.pdf), The People's Republic of China's [Personal information protection law](http://en.npc.gov.cn.cdurl.cn/2021-12/29/c_694559.htm). - <a name="sensitive-characteristics">**Sensitive characteristics:**</a> This includes specifically protected categories in human rights (see [UHDR, Article 2](https://www.un.org/sites/un2.un.org/files/2021/03/udhr.pdf)) and personal information regulation (see GDPR, [Article 9; Protection of Personal Information Act, Chapter 1](https://www.gov.za/sites/default/files/gcis_document/201409/3706726-11act4of2013popi.pdf)) - <a name="deception">**Deception:**</a> Doing something to intentionally mislead individuals to believe something that is false, such as by creating deadbots or chatbots on social media posing as real people, or generating text documents without making consumers aware that the text is machine generated. </details> <p>&nbsp;</p> ## More Information <details> <summary>Click to expand</summary><br/> ### Dataset Creation Blog post detailing the design choices during the dataset creation: https://bigscience.huggingface.co/blog/building-a-tb-scale-multilingual-dataset-for-language-modeling ### Technical Specifications Blog post summarizing how the architecture, size, shape, and pre-training duration where selected: https://bigscience.huggingface.co/blog/what-language-model-to-train-if-you-have-two-million-gpu-hours More details on the architecture/optimizer: https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml Blog post on the hardware/engineering side: https://bigscience.huggingface.co/blog/which-hardware-to-train-a-176b-parameters-model Details on the distributed setup used for the training: https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml Tensorboard updated during the training: https://huggingface.co/bigscience/tr11-176B-ml-logs/tensorboard#scalars&tagFilter=loss Insights on how to approach training, negative results: https://github.com/bigscience-workshop/bigscience/blob/master/train/lessons-learned.md Details on the obstacles overcome during the preparation on the engineering side (instabilities, optimization of training throughput, so many technical tricks and questions): https://github.com/bigscience-workshop/bigscience/blob/master/train/tr11-176B-ml/chronicles.md ### Initial Results Initial prompting experiments using interim checkpoints: https://huggingface.co/spaces/bigscience/bloom-book </details> <p>&nbsp;</p> ## Model Card Authors *Ordered roughly chronologically and by amount of time spent.* Margaret Mitchell, Giada Pistilli, Yacine Jernite, Ezinwanne Ozoani, Marissa Gerchick, Nazneen Rajani, Sasha Luccioni, Irene Solaiman, Maraim Masoud, Somaieh Nikpoor, Carlos Muñoz Ferrandis, Stas Bekman, Christopher Akiki, Danish Contractor, David Lansky, Angelina McMillan-Major, Tristan Thrush, Suzana Ilić, Gérard Dupont, Shayne Longpre, Manan Dey, Stella Biderman, Douwe Kiela, Emi Baylor, Teven Le Scao, Aaron Gokaslan, Julien Launay, Niklas Muennighoff
[ "PUBMEDQA", "SCIQ" ]
aimarsg/prueba5
aimarsg
token-classification
[ "transformers", "pytorch", "tensorboard", "roberta", "token-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-04-02T14:48:01Z
2023-04-02T15:57:53+00:00
31
0
--- license: apache-2.0 metrics: - precision - recall - f1 - accuracy tags: - generated_from_trainer model-index: - name: prueba5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # prueba5 This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2442 - Precision: 0.5258 - Recall: 0.5574 - F1: 0.5411 - Accuracy: 0.9609 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2.75e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 30 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 57 | 0.2341 | 0.0 | 0.0 | 0.0 | 0.9488 | | No log | 2.0 | 114 | 0.2411 | 0.0 | 0.0 | 0.0 | 0.9488 | | No log | 3.0 | 171 | 0.2150 | 0.0385 | 0.0055 | 0.0096 | 0.9410 | | No log | 4.0 | 228 | 0.1885 | 0.25 | 0.0929 | 0.1355 | 0.9500 | | No log | 5.0 | 285 | 0.1730 | 0.3830 | 0.1967 | 0.2599 | 0.9524 | | No log | 6.0 | 342 | 0.1591 | 0.5098 | 0.2842 | 0.3649 | 0.9581 | | No log | 7.0 | 399 | 0.1665 | 0.5405 | 0.3279 | 0.4082 | 0.9609 | | No log | 8.0 | 456 | 0.1856 | 0.5294 | 0.4918 | 0.5099 | 0.9604 | | 0.1706 | 9.0 | 513 | 0.1727 | 0.5 | 0.5191 | 0.5094 | 0.9611 | | 0.1706 | 10.0 | 570 | 0.1717 | 0.5669 | 0.4863 | 0.5235 | 0.9639 | | 0.1706 | 11.0 | 627 | 0.1913 | 0.5024 | 0.5628 | 0.5309 | 0.9601 | | 0.1706 | 12.0 | 684 | 0.1793 | 0.515 | 0.5628 | 0.5379 | 0.9619 | | 0.1706 | 13.0 | 741 | 0.2009 | 0.5679 | 0.5027 | 0.5333 | 0.9618 | | 0.1706 | 14.0 | 798 | 0.2043 | 0.5333 | 0.5683 | 0.5503 | 0.9604 | | 0.1706 | 15.0 | 855 | 0.2052 | 0.5486 | 0.5246 | 0.5363 | 0.9629 | | 0.1706 | 16.0 | 912 | 0.2234 | 0.5183 | 0.5410 | 0.5294 | 0.9581 | | 0.1706 | 17.0 | 969 | 0.2157 | 0.5424 | 0.5246 | 0.5333 | 0.9616 | | 0.0202 | 18.0 | 1026 | 0.2207 | 0.5025 | 0.5574 | 0.5285 | 0.9596 | | 0.0202 | 19.0 | 1083 | 0.2297 | 0.5025 | 0.5410 | 0.5211 | 0.9573 | | 0.0202 | 20.0 | 1140 | 0.2264 | 0.5131 | 0.5355 | 0.5241 | 0.9593 | | 0.0202 | 21.0 | 1197 | 0.2300 | 0.5181 | 0.5464 | 0.5319 | 0.9593 | | 0.0202 | 22.0 | 1254 | 0.2348 | 0.5241 | 0.5355 | 0.5297 | 0.9604 | | 0.0202 | 23.0 | 1311 | 0.2372 | 0.5196 | 0.5792 | 0.5478 | 0.9588 | | 0.0202 | 24.0 | 1368 | 0.2349 | 0.5319 | 0.5464 | 0.5391 | 0.9613 | | 0.0202 | 25.0 | 1425 | 0.2353 | 0.5312 | 0.5574 | 0.544 | 0.9619 | | 0.0202 | 26.0 | 1482 | 0.2388 | 0.5489 | 0.5519 | 0.5504 | 0.9614 | | 0.0044 | 27.0 | 1539 | 0.2396 | 0.5243 | 0.5301 | 0.5272 | 0.9618 | | 0.0044 | 28.0 | 1596 | 0.2442 | 0.5152 | 0.5574 | 0.5354 | 0.9603 | | 0.0044 | 29.0 | 1653 | 0.2444 | 0.5178 | 0.5574 | 0.5368 | 0.9604 | | 0.0044 | 30.0 | 1710 | 0.2442 | 0.5258 | 0.5574 | 0.5411 | 0.9609 | ### Framework versions - Transformers 4.27.4 - Pytorch 1.13.1+cu116 - Datasets 2.11.0 - Tokenizers 0.13.2
[ "PHARMACONER" ]
rttl-ai/BIOptimus
rttl-ai
fill-mask
[ "transformers", "pytorch", "bert", "fill-mask", "biology", "medical", "en", "dataset:pubmed", "arxiv:2308.08625", "arxiv:2312.02803", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-06-23T21:22:37Z
2024-06-08T17:26:42+00:00
31
2
--- datasets: - pubmed language: - en license: apache-2.0 tags: - biology - medical --- # rttl-ai/BIOptimus v.0.4 ## Model Details **Model Description:** BIOptimus v.0.4 model is a BERT-like model pre-trained on [PubMed](https://pubmed.ncbi.nlm.nih.gov/) abstracts. It is a biomedical language model pre-trained using contextualized weight distillation and Curriculum Learning. This model achieves state-of-the-art performance on several biomedical NER datasets from [BLURB benchmark](https://microsoft.github.io/BLURB/). - **Developed by:** rttl-ai - **Model Type:** Language model - **Language(s):** English - **License:** Apache-2.0 - **Resources for more information:** - It is introduced in the paper BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition (BioNLP workshop @ ACL 2023). - [arxiv](https://arxiv.org/abs/2308.08625) - [arxiv](https://arxiv.org/abs/2312.02803) - More information is available in [this repository](https://github.com/rttl-ai/BIOptimus).
[ "BLURB" ]
Falah/stable_diffusion_prompts_gen
Falah
text-generation
[ "diffusers", "pytorch", "gpt2", "art", "stable diffusion", "text-generation", "en", "dataset:Falah/stable_diffusion_prompts_dataset", "license:apache-2.0", "region:us" ]
2023-07-08T09:30:49Z
2023-07-08T13:05:30+00:00
31
3
--- datasets: - Falah/stable_diffusion_prompts_dataset language: - en library_name: diffusers license: apache-2.0 metrics: - accuracy pipeline_tag: text-generation tags: - art - stable diffusion - gpt2 --- # Stable Diffusion Prompts Generation Model This model is designed for generating illustration art style prompts for the Stable Diffusion tool for text-to-image generation. It utilizes the custom dataset "Falah/stable_diffusion_prompts_dataset" to generate creative and coherent text prompts. ## Examples To load the model and generate inferences using the model, you can use the following code snippet: ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM model_name = "Falah/stable_diffusion_prompts_gen" dataset_name = "Falah/stable_diffusion_prompts_dataset" prompt = r'a beautiful female' # the beginning of the prompt temperature = 0.9 # A higher temperature will produce more diverse results, but with a higher risk of less coherent text top_k = 8 # the number of tokens to sample from at each step max_length = 200 # the maximum number of tokens for the output of the model repetition_penalty = 1.2 # the penalty value for each repetition of a token num_return_sequences = 5 # the number of results to generate tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(model_name) input_ids = tokenizer(prompt, return_tensors='pt').input_ids output = model.generate( input_ids, do_sample=True, temperature=temperature, top_k=top_k, max_length=max_length, num_return_sequences=num_return_sequences, repetition_penalty=repetition_penalty, early_stopping=True ) print('\033[96m' + prompt + '\033[0m') for i in range(len(output)): print(tokenizer.decode(output[i], skip_special_tokens=True) + '\n') ``` These are examples of prompts generating and testing the model with the website [STABLE DIFFUSION XL](https://clipdrop.co/) for the stable diffusion model generating images from prompts ``` a beautiful female a beautiful female woman, and she's got the best hair in this world. I'm not saying her look is bad (I think it has to be), but my point was that when one looks at these things like we're all looking for something different about our bodies as individuals they are completely wrong; there isn't anything inherently evil with being an animal or having two legs instead of just walking on both sides of you while holding your other leg up so tightly around yourself - no matter how ``` ![Image Alt Text](https://huggingface.co/Falah/stable_diffusion_prompts_gen/resolve/main/784df68d-8dad-41b6-9e15-fa16d9ece829.png) ## another generating prompts ``` a beautiful female and she's been in the business for over 30 years. I've had my fair share of bad things, and I'm sure many more will befall me at some point as well… but it is one thing when you have such an incredible woman on your team that makes life so difficult to bear (aside from being very much human) while also having her back with no regard whatsoever towards any personal issues or even just trying desperately hard not too far away! And ``` ![Image Alt Text](https://huggingface.co/Falah/stable_diffusion_prompts_gen/resolve/main/461e2488-a813-4375-86e0-833dcd7770de.png) -------------- ![Image Alt Text](https://huggingface.co/Falah/stable_diffusion_prompts_gen/resolve/main/e64f9888-66a8-4ba8-9b71-42d976eef84d.png) Feel free to modify the parameters like `prompt`, `temperature`, `top_k`, etc., to experiment with different outputs. ## Citation If you use this model or the associated dataset in your research or projects, please cite it as follows: ``` @sd_prompts{stable_diffussion_prompts_generating_gpt2), author = {Falah.G.Salieh}, title = {Stable Diffusion Prompts Generating By fine-tuning GPT2 }, year = {2023}, publisher = {Hugging Face}, url = {https://huggingface.co/Falah/stable_diffusion_prompts_gen}, } ``` ## License This project is licensed under the Apache License, Version 2.0. Please see the [LICENSE](link-to-license-file) file for more details.
[ "BEAR" ]
badmatr11x/roberta-base-emotions-detection-from-text
badmatr11x
text-classification
[ "transformers", "pytorch", "tf", "roberta", "text-classification", "en", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-07-15T16:56:14Z
2023-07-27T17:15:42+00:00
31
7
--- language: - en license: mit metrics: - accuracy pipeline_tag: text-classification widget: - text: With tears of joy streaming down her cheeks, she embraced her long-lost brother after years of separation. example_title: Joy - text: As the orchestra played the final note, the audience erupted into thunderous applause, filling the concert hall with joy. example_title: Joy - text: The old man sat alone on the park bench, reminiscing about the love he had lost, his eyes filled with sadness. example_title: Sadness - text: The news of her best friend moving to a distant country left her feeling a profound sadness and emptiness. example_title: Sadness - text: The scientific research paper discussed complex concepts that were beyond the scope of a laymans understanding. example_title: Neutral - text: The documentary provided an objective view of the historical events, presenting facts without any bias. example_title: Neutral - text: He clenched his fists tightly, trying to control the surge of anger when he heard the offensive remarks. example_title: Anger - text: The unfair treatment at work ignited a simmering anger within him, leading him to consider confronting the management. example_title: Anger - text: As the magician pulled a rabbit out of an empty hat, the children gasped in amazement and surprise. example_title: Surprise - text: He opened the box to find a rare and valuable antique inside, leaving him speechless with surprise. example_title: Surprise - text: The moldy and rotting food in the refrigerator evoked a sense of disgust, leading her to clean it immediately. example_title: Disgust - text: The movie's graphic scenes of violence and gore left many viewers feeling a sense of disgust and unease. example_title: Disgust - text: As the storm raged outside, the little child clung to their parents, seeking comfort from the fear of thunder. example_title: Fear - text: The horror movie was so terrifying that some viewers had to cover their eyes in fear, unable to bear the suspense. example_title: Fear ---
[ "BEAR" ]
ShabanEjupi/ghbony
ShabanEjupi
text-to-image
[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
2023-10-29T18:52:29Z
2023-11-09T22:23:17+00:00
31
0
--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### ghbony Dreambooth model trained by Qabidev Sample pictures of this concept: prompt ghbony, kung fu, hyper detailed background, character concept, full body, dynamic pose, intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, square thumbnail, highly detailed ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/653e88896426f79e2980a600/8MSNtAnHE6kabaxD579ML.jpeg) prompt ghbony, create a full-body character concept of a steampunk explorer, featuring intricate mechanical gadgets and a weathered, detailed outfit. ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/653e88896426f79e2980a600/Bu_H2HwMiQIHKAnRyGS_u.jpeg) prompt ghbony, craft a character concept of a wise old wizard with a long, flowing beard, clutching an ancient, ornate staff in a misty, enchanted forest. ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/653e88896426f79e2980a600/upQd74OaK3BqTVZbGw5WE.jpeg) prompt ghbony, classic cartoon style, dynamic action pose, vibrant colors ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/653e88896426f79e2980a600/6pMaKBjTOC0o2LesvUSbf.jpeg) prompt ghbony, swiming in the sea ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/653e88896426f79e2980a600/NECSkBS54ZkyTu6HK4rTK.jpeg) My character as pokemon ![image/png](https://cdn-uploads.huggingface.co/production/uploads/653e88896426f79e2980a600/P11SRTWHaPE46_QpswK0I.png)
[ "CRAFT" ]
TheBloke/juanako-7B-UNA-GPTQ
TheBloke
text-generation
[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "juanako", "UNA", "conversational", "dataset:HuggingFaceH4/ultrafeedback_binarized", "arxiv:2109.07958", "arxiv:2310.16944", "arxiv:2305.18290", "base_model:fblgit/juanako-7b-UNA", "base_model:quantized:fblgit/juanako-7b-UNA", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]
2023-12-01T19:56:04Z
2023-12-01T20:24:18+00:00
31
2
--- base_model: fblgit/juanako-7b-UNA datasets: - HuggingFaceH4/ultrafeedback_binarized license: apache-2.0 tags: - alignment-handbook - generated_from_trainer - juanako - mistral - UNA inference: false model_creator: FBL model_type: mistral prompt_template: '<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ' quantized_by: TheBloke model-index: - name: juanako-7b-UNA results: - task: type: text-generation name: TruthfulQA (MC2) dataset: name: truthful_qa type: text-generation config: multiple_choice split: validation metrics: - type: accuracy value: 65.13 verified: true - task: type: text-generation name: ARC-Challenge dataset: name: ai2_arc type: text-generation config: ARC-Challenge split: test metrics: - type: accuracy value: 68.17 verified: true - task: type: text-generation name: HellaSwag dataset: name: Rowan/hellaswag type: text-generation split: test metrics: - type: accuracy value: 85.34 verified: true - type: accuracy value: 83.57 - task: type: text-generation name: Winogrande dataset: name: winogrande type: text-generation config: winogrande_debiased split: test metrics: - type: accuracy value: 78.85 verified: true - task: type: text-generation name: MMLU dataset: name: cais/mmlu type: text-generation config: all split: test metrics: - type: accuracy value: 62.47 verified: true - task: type: text-generation name: DROP dataset: name: drop type: text-generation split: validation metrics: - type: accuracy value: 38.74 verified: true - task: type: text-generation name: PubMedQA dataset: name: bigbio/pubmed_qa type: text-generation config: pubmed_qa_artificial_bigbio_qa split: validation metrics: - type: accuracy value: 76.0 --- <!-- markdownlint-disable MD041 --> <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Juanako 7B UNA - GPTQ - Model creator: [FBL](https://huggingface.co/fblgit) - Original model: [Juanako 7B UNA](https://huggingface.co/fblgit/juanako-7b-UNA) <!-- description start --> # Description This repo contains GPTQ model files for [FBL's Juanako 7B UNA](https://huggingface.co/fblgit/juanako-7b-UNA). Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them. These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/). <!-- description end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/juanako-7B-UNA-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/juanako-7B-UNA-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/juanako-7B-UNA-GGUF) * [FBL's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/fblgit/juanako-7b-UNA) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: ChatML ``` <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ``` <!-- prompt-template end --> <!-- README_GPTQ.md-compatible clients start --> ## Known compatible clients / servers These GPTQ models are known to work in the following inference servers/webuis. - [text-generation-webui](https://github.com/oobabooga/text-generation-webui) - [KoboldAI United](https://github.com/henk717/koboldai) - [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui) - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) This may not be a complete list; if you know of others, please let me know! <!-- README_GPTQ.md-compatible clients end --> <!-- README_GPTQ.md-provided-files start --> ## Provided files, and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers. <details> <summary>Explanation of GPTQ parameters</summary> - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit. </details> | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc | | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- | | [main](https://huggingface.co/TheBloke/juanako-7B-UNA-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.16 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. | | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/juanako-7B-UNA-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.57 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. | | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/juanako-7B-UNA-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 7.52 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. | | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/juanako-7B-UNA-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 7.68 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. | | [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/juanako-7B-UNA-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 8.17 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. | | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/juanako-7B-UNA-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.29 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. | <!-- README_GPTQ.md-provided-files end --> <!-- README_GPTQ.md-download-from-branches start --> ## How to download, including from branches ### In text-generation-webui To download from the `main` branch, enter `TheBloke/juanako-7B-UNA-GPTQ` in the "Download model" box. To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/juanako-7B-UNA-GPTQ:gptq-4bit-32g-actorder_True` ### From the command line I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` To download the `main` branch to a folder called `juanako-7B-UNA-GPTQ`: ```shell mkdir juanako-7B-UNA-GPTQ huggingface-cli download TheBloke/juanako-7B-UNA-GPTQ --local-dir juanako-7B-UNA-GPTQ --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: ```shell mkdir juanako-7B-UNA-GPTQ huggingface-cli download TheBloke/juanako-7B-UNA-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir juanako-7B-UNA-GPTQ --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell mkdir juanako-7B-UNA-GPTQ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/juanako-7B-UNA-GPTQ --local-dir juanako-7B-UNA-GPTQ --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ### With `git` (**not** recommended) To clone a specific branch with `git`, use a command like this: ```shell git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/juanako-7B-UNA-GPTQ ``` Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.) <!-- README_GPTQ.md-download-from-branches end --> <!-- README_GPTQ.md-text-generation-webui start --> ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui) Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. 1. Click the **Model tab**. 2. Under **Download custom model or LoRA**, enter `TheBloke/juanako-7B-UNA-GPTQ`. - To download from a specific branch, enter for example `TheBloke/juanako-7B-UNA-GPTQ:gptq-4bit-32g-actorder_True` - see Provided Files above for the list of branches for each option. 3. Click **Download**. 4. The model will start downloading. Once it's finished it will say "Done". 5. In the top left, click the refresh icon next to **Model**. 6. In the **Model** dropdown, choose the model you just downloaded: `juanako-7B-UNA-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right. - Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started! <!-- README_GPTQ.md-text-generation-webui end --> <!-- README_GPTQ.md-use-from-tgi start --> ## Serving this model from Text Generation Inference (TGI) It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0` Example Docker parameters: ```shell --model-id TheBloke/juanako-7B-UNA-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096 ``` Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later): ```shell pip3 install huggingface-hub ``` ```python from huggingface_hub import InferenceClient endpoint_url = "https://your-endpoint-url-here" prompt = "Tell me about AI" prompt_template=f'''<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ''' client = InferenceClient(endpoint_url) response = client.text_generation(prompt, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1) print(f"Model output: {response}") ``` <!-- README_GPTQ.md-use-from-tgi end --> <!-- README_GPTQ.md-use-from-python start --> ## Python code example: inference from this GPTQ model ### Install the necessary packages Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later. ```shell pip3 install --upgrade transformers optimum # If using PyTorch 2.1 + CUDA 12.x: pip3 install --upgrade auto-gptq # or, if using PyTorch 2.1 + CUDA 11.x: pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ ``` If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ git checkout v0.5.1 pip3 install . ``` ### Example Python code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/juanako-7B-UNA-GPTQ" # To use a different branch, change revision # For example: revision="gptq-4bit-32g-actorder_True" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Tell me about AI" prompt_template=f'''<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ''' print("\n\n*** Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline print("*** Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ``` <!-- README_GPTQ.md-use-from-python end --> <!-- README_GPTQ.md-compatibility start --> ## Compatibility The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly. [ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility. For a list of clients/servers, please see "Known compatible clients / servers", above. <!-- README_GPTQ.md-compatibility end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> # Original model card: FBL's Juanako 7B UNA # juanako-7b-UNA (Uniform Neural Alignment) This model is a fine-tuned version of [fblgit/juanako-7b-UNA-v2-phase-1](https://huggingface.co/fblgit/juanako-7b-UNA-v2-phase-1) on the HuggingFaceH4/ultrafeedback_binarized dataset. It outperforms in many aspects most of the current Mistral based models and is the **latest and most powerful juanako version as of now**. ## Scores The official HuggingFace results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/fblgit/juanako-7b-UNA/results_2023-11-28T08-33-33.965228.json) | Model | Average ⬆️| ARC (25-s) ⬆️ | HellaSwag (10-s) ⬆️ | MMLU (5-s) ⬆️| TruthfulQA (MC) (0-s) ⬆️ | Winogrande (5-s) | GSM8K (5-s) | DROP (3-s) | | --- | --- | --- | --- | --- | --- | --- | --- | --- | |[mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 50.32 | 59.58 | 83.31 | 64.16 | 42.15 | 78.37 | 18.12 | 6.14 | | [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1) | 59.0 | 66.21 | 83.64 | 62.37 | 59.65 | 78.14 | 19.56 | 43.84 | | [fblgit/juanako-7b-UNA](https://huggingface.co/fblgit/juanako-7b-UNA) | **59.91** | **68.17** | **85.34** | 62.47 | **65.13** | **78.85** | **20.7** | 38.74 | It scores: **59.91** according HuggingFace LLM Leaderboard. It scores: **65.1** with `big-refactor` branch of lm-eval-harness Author [Xavier M.](mailto:[email protected]) @fblgit ## Model description juanako uses UNA, Uniform Neural Alignment. A training technique that ease alignment between transformer layers yet to be published. ### Prompts The following prompts showed positive results, it may depend the task and needs further experimentation but this should work for starters: ``` <|im_start|>system - You are a helpful assistant chatbot trained by MosaicML. - You answer questions. - You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user. - You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|> <|im_start|>user Explain QKV<|im_end|> <|im_start|>assistant ``` ``` ### Assistant: I am StableVicuna, a large language model created by CarperAI. I am here to chat! ### Human: Explain QKV ### Assistant: ``` ``` [Round <|round|>] 问：Explain QKV 答： ``` ``` [Round <|round|>] Question：Explain QKV Answer： ``` ``` Question：Explain QKV Answer： ``` ## Evaluations (lm-eval big-refactor branch) ### TruthfulQA 0-Shot ``` | Tasks |Version|Filter|Metric|Value | |Stderr| |--------------|-------|------|------|-----:|---|-----:| |truthfulqa_mc2|Yaml |none |acc |0.6549|± |0.0153| ``` ### ARC 25-Shot ``` | Tasks |Version|Filter| Metric |Value | |Stderr| |-------------|-------|------|--------|-----:|---|-----:| |arc_challenge|Yaml |none |acc |0.6476|± |0.0140| | | |none |acc_norm|0.6809|± |0.0136| ``` ### HellaSwag 10-Shot ``` | Tasks |Version|Filter| Metric |Value | |Stderr| |---------|-------|------|--------|-----:|---|-----:| |hellaswag|Yaml |none |acc |0.6703|± |0.0047| | | |none |acc_norm|0.8520|± |0.0035| ``` ### GSM8k 5-Shot ``` |Tasks|Version| Filter | Metric |Value | |Stderr| |-----|-------|----------|-----------|-----:|---|-----:| |gsm8k|Yaml |get-answer|exact_match|0.4898|± |0.0138| ``` ### GPT Evaluations 0-Shot ``` | Tasks |Version|Filter| Metric |Value | |Stderr| |--------------|-------|------|----------|-----:|---|-----:| |boolq |Yaml |none |acc |0.8703|± |0.0059| |lambada_openai|Yaml |none |perplexity|3.2598|± |0.0705| | | |none |acc |0.7336|± |0.0062| |piqa |Yaml |none |acc |0.8254|± |0.0089| | | |none |acc_norm |0.8292|± |0.0088| |sciq |Yaml |none |acc |0.9580|± |0.0063| | | |none |acc_norm |0.9130|± |0.0089| ``` ### MathQA 0-Shot ``` |Tasks |Version|Filter| Metric |Value | |Stderr| |------|-------|------|--------|-----:|---|-----:| |mathqa|Yaml |none |acc |0.3752|± |0.0089| | | |none |acc_norm|0.3772|± |0.0089| ``` ### PiQa 1-Shot ``` |Tasks|Version|Filter| Metric |Value | |Stderr| |-----|-------|------|--------|-----:|---|-----:| |piqa |Yaml |none |acc |0.8308|± |0.0087| | | |none |acc_norm|0.8357|± |0.0086| ``` ### Winogrande 5-Shot ``` | Tasks |Version|Filter|Metric|Value| |Stderr| |----------|-------|------|------|----:|---|-----:| |winogrande|Yaml |none |acc |0.768|± |0.0119| ``` ### PubMedQA 0-Shot ``` | Tasks |Version|Filter|Metric|Value| |Stderr| |--------|-------|------|------|----:|---|-----:| |pubmedqa|Yaml |none |acc | 0.76|± |0.0191| ``` ### RACE 1-Shot ``` |Tasks|Version|Filter|Metric|Value | |Stderr| |-----|-------|------|------|-----:|---|-----:| |race |Yaml |none |acc |0.5282|± |0.0154| ``` ### MMLU 5-Shot (8-Bit) ``` | Groups |Version|Filter|Metric|Value | |Stderr| |------------------|-------|------|------|-----:|---|-----:| |mmlu |N/A |none |acc |0.6137|± |0.1243| | - humanities |N/A |none |acc |0.5671|± |0.1101| | - other |N/A |none |acc |0.6859|± |0.1164| | - social_sciences|N/A |none |acc |0.7195|± |0.0713| | - stem |N/A |none |acc |0.5087|± |0.1297| ``` ### DROP 3-Shot (8-Bit) (Instruct-Eval) ``` {'score': 0.49801113762927607} {'drop': 49.8} drop: 49.8 ``` ### CRASS 0-Shot (Instruct-Eval) ``` {'score': 0.8357664233576643} {'crass': 83.58} crass: 83.58 ``` ## Training Details ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - distributed_type: multi-GPU - num_devices: 14 - gradient_accumulation_steps: 16 - total_train_batch_size: 224 - total_eval_batch_size: 14 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.01 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| | 0.4795 | 0.2 | 56 | 0.4958 | -1.3684 | -2.6385 | 0.7552 | 1.2701 | -265.3887 | -241.2612 | -2.2572 | -2.4922 | | 0.4642 | 0.4 | 112 | 0.4859 | -1.0380 | -1.9769 | 0.7273 | 0.9389 | -258.7718 | -237.9569 | -2.2414 | -2.4751 | | 0.4758 | 0.61 | 168 | 0.4808 | -1.2594 | -2.3704 | 0.7343 | 1.1110 | -262.7074 | -240.1708 | -2.2305 | -2.4633 | | 0.4549 | 0.81 | 224 | 0.4768 | -1.1906 | -2.3201 | 0.7552 | 1.1295 | -262.2044 | -239.4827 | -2.2284 | -2.4610 | ### Framework versions - Transformers 4.35.0-UNA - Pytorch 2.1.0 - Datasets 2.14.6 - Tokenizers 0.14.1 ## Citations If you find juanako useful please: ``` @misc{juanako7buna, title={Juanako: Uniform Neural Alignment}, author={Xavier Murias}, year={2023}, publisher = {HuggingFace}, journal = {HuggingFace repository}, howpublished = {\url{https://huggingface.co/fblgit/juanako-7b-UNA}}, } ``` Thanks to all the brilliant humans behind the creation of AI, here some of the ones that we find relevant to our research. If you feel a citation is missing, please contact. ``` @misc{lin2021truthfulqa, title={TruthfulQA: Measuring How Models Mimic Human Falsehoods}, author={Stephanie Lin and Jacob Hilton and Owain Evans}, year={2021}, eprint={2109.07958}, archivePrefix={arXiv}, primaryClass={cs.CL} } @misc{tunstall2023zephyr, title={Zephyr: Direct Distillation of LM Alignment}, author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf}, year={2023}, eprint={2310.16944}, archivePrefix={arXiv}, primaryClass={cs.LG} } @inproceedings{Bisk2020, author = {Yonatan Bisk and Rowan Zellers and Ronan Le Bras and Jianfeng Gao and Yejin Choi}, title = {PIQA: Reasoning about Physical Commonsense in Natural Language}, booktitle = {Thirty-Fourth AAAI Conference on Artificial Intelligence}, year = {2020}, } @software{eval-harness, author = {Gao, Leo and Tow, Jonathan and Biderman, Stella and Black, Sid and DiPofi, Anthony and Foster, Charles and Golding, Laurence and Hsu, Jeffrey and McDonell, Kyle and Muennighoff, Niklas and Phang, Jason and Reynolds, Laria and Tang, Eric and Thite, Anish and Wang, Ben and Wang, Kevin and Zou, Andy}, title = {A framework for few-shot language model evaluation}, month = sep, year = 2021, publisher = {Zenodo}, version = {v0.0.1}, doi = {10.5281/zenodo.5371628}, url = {https://doi.org/10.5281/zenodo.5371628} } @misc{rafailov2023direct, title={Direct Preference Optimization: Your Language Model is Secretly a Reward Model}, author={Rafael Rafailov and Archit Sharma and Eric Mitchell and Stefano Ermon and Christopher D. Manning and Chelsea Finn}, year={2023}, eprint={2305.18290}, archivePrefix={arXiv}, } ```
[ "PUBMEDQA", "SCIQ" ]
lomahony/pythia-70m-helpful-dpo
lomahony
text-generation
[ "transformers", "pytorch", "gpt_neox", "text-generation", "causal-lm", "pythia", "en", "dataset:Anthropic/hh-rlhf", "arxiv:2101.00027", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2024-01-12T15:24:32Z
2024-05-14T19:15:52+00:00
31
0
--- datasets: - Anthropic/hh-rlhf language: - en license: apache-2.0 tags: - pytorch - causal-lm - pythia --- [Pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) finetuned using original DPO code with the helpful subset of [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch. Checkpoints are also uploaded. Fully reproducible finetuning code is available on [GitHub](https://github.com/lauraaisling/direct-preference-optimization/tree/main) [wandb log](https://wandb.ai/lauraomahony999/pythia-dpo/runs/wc2q2vp1) See [Pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) for model details [(paper)](https://arxiv.org/abs/2101.00027). See further details of these models in the paper [Attributing Mode Collapse in the Fine-Tuning of Large Language Models](https://openreview.net/pdf?id=3pDMYjpOxk). You can cite these models if they are helpful as follows: <pre> @inproceedings{o2024attributing, title={Attributing Mode Collapse in the Fine-Tuning of Large Language Models}, author={O’Mahony, Laura and Grinsztajn, Leo and Schoelkopf, Hailey and Biderman, Stella}, booktitle={ICLR 2024, Mathematical and Empirical Understanding of Foundation Models (ME-FoMo) workshop}, year={2024} } </pre> hf (pretrained=lomahony/pythia-70m-helpful-dpo), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16 | Tasks |Version|Filter|n-shot| Metric | Value | | Stderr | |--------------|------:|------|-----:|---------------|--------:|---|--------| |arc_challenge | 1|none | 0|acc | 0.1724|± | 0.0110| | | |none | 0|acc_norm | 0.2201|± | 0.0121| |arc_easy | 1|none | 0|acc | 0.3350|± | 0.0097| | | |none | 0|acc_norm | 0.3380|± | 0.0097| |boolq | 2|none | 0|acc | 0.4315|± | 0.0087| |hellaswag | 1|none | 0|acc | 0.2614|± | 0.0044| | | |none | 0|acc_norm | 0.2665|± | 0.0044| |lambada_openai| 1|none | 0|perplexity |5951.7544|± |428.5435| | | |none | 0|acc | 0.0309|± | 0.0024| |openbookqa | 1|none | 0|acc | 0.1460|± | 0.0158| | | |none | 0|acc_norm | 0.2440|± | 0.0192| |piqa | 1|none | 0|acc | 0.5550|± | 0.0116| | | |none | 0|acc_norm | 0.5501|± | 0.0116| |sciq | 1|none | 0|acc | 0.4010|± | 0.0155| | | |none | 0|acc_norm | 0.5070|± | 0.0158| |wikitext | 2|none | 0|word_perplexity| 547.6920|± |N/A | | | |none | 0|byte_perplexity| 3.2518|± |N/A | | | |none | 0|bits_per_byte | 1.7012|± |N/A | |winogrande | 1|none | 0|acc | 0.4822|± | 0.0140| hf (pretrained=lomahony/pythia-70m-helpful-dpo), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16 | Tasks |Version|Filter|n-shot| Metric | Value | | Stderr | |--------------|------:|------|-----:|---------------|---------:|---|---------| |arc_challenge | 1|none | 5|acc | 0.1886|± | 0.0114| | | |none | 5|acc_norm | 0.2338|± | 0.0124| |arc_easy | 1|none | 5|acc | 0.3346|± | 0.0097| | | |none | 5|acc_norm | 0.3308|± | 0.0097| |boolq | 2|none | 5|acc | 0.4028|± | 0.0086| |hellaswag | 1|none | 5|acc | 0.2617|± | 0.0044| | | |none | 5|acc_norm | 0.2648|± | 0.0044| |lambada_openai| 1|none | 5|perplexity |22676.7987|± |1626.4435| | | |none | 5|acc | 0.0173|± | 0.0018| |openbookqa | 1|none | 5|acc | 0.1640|± | 0.0166| | | |none | 5|acc_norm | 0.2460|± | 0.0193| |piqa | 1|none | 5|acc | 0.5528|± | 0.0116| | | |none | 5|acc_norm | 0.5462|± | 0.0116| |sciq | 1|none | 5|acc | 0.3100|± | 0.0146| | | |none | 5|acc_norm | 0.4220|± | 0.0156| |wikitext | 2|none | 5|word_perplexity| 547.6920|± |N/A | | | |none | 5|byte_perplexity| 3.2518|± |N/A | | | |none | 5|bits_per_byte | 1.7012|± |N/A | |winogrande | 1|none | 5|acc | 0.5201|± | 0.0140|
[ "SCIQ" ]
BioMistral/BioMistral-7B-SLERP-AWQ-QGS128-W4-GEMM
BioMistral
text-generation
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:2402.10373", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "awq", "region:us" ]
2024-02-17T18:16:52Z
2024-02-19T15:37:55+00:00
31
1
--- {} --- <p align="center"> <img src="https://huggingface.co/BioMistral/BioMistral-7B/resolve/main/wordart_blue_m_rectangle.png?download=true" alt="drawing" width="250"/> </p> # BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains **Abstract:** Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges. In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark comprising 10 established medical question-answering (QA) tasks in English. We also explore lightweight models obtained through quantization and model merging approaches. Our results demonstrate BioMistral's superior performance compared to existing open-source medical models and its competitive edge against proprietary counterparts. Finally, to address the limited availability of data beyond English and to assess the multilingual generalization of medical LLMs, we automatically translated and evaluated this benchmark into 7 other languages. This marks the first large-scale multilingual evaluation of LLMs in the medical domain. Datasets, multilingual evaluation benchmarks, scripts, and all the models obtained during our experiments are freely released. **Advisory Notice!** Although BioMistral is intended to encapsulate medical knowledge sourced from high-quality evidence, it hasn't been tailored to effectively, safely, or suitably convey this knowledge within professional parameters for action. We advise refraining from utilizing BioMistral in medical contexts unless it undergoes thorough alignment with specific use cases and undergoes further testing, notably including randomized controlled trials in real-world medical environments. BioMistral 7B may possess inherent risks and biases that have not yet been thoroughly assessed. Additionally, the model's performance has not been evaluated in real-world clinical settings. Consequently, we recommend using BioMistral 7B strictly as a research tool and advise against deploying it in production environments for natural language generation or any professional health and medical purposes. # 1. BioMistral models **BioMistral** is a suite of Mistral-based further pre-trained open source models suited for the medical domains and pre-trained using textual data from PubMed Central Open Access (CC0, CC BY, CC BY-SA, and CC BY-ND). All the models are trained using the CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/jean-zay/) French HPC. | Model Name | Base Model | Model Type | Sequence Length | Download | |:-------------------:|:----------------------------------:|:-------------------:|:---------------:|:-----------------------------------------------------:| | BioMistral-7B | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Further Pre-trained | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B) | | BioMistral-7B-DARE | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge DARE | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-DARE) | | BioMistral-7B-TIES | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge TIES | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-TIES) | | BioMistral-7B-SLERP | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge SLERP | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-SLERP) | # 2. Quantized Models | Base Model | Method | q_group_size | w_bit | version | VRAM GB | Time | Download | |:-------------------:|:------:|:------------:|:-----:|:-------:|:-------:|:------:|:--------:| | BioMistral-7B | FP16/BF16 | | | | 15.02 | x1.00 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B) | | BioMistral-7B | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-AWQ-QGS128-W4-GEMM) | | BioMistral-7B | AWQ | 128 | 4 | GEMV | 4.68 | x10.30 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-AWQ-QGS128-W4-GEMV) | | BioMistral-7B | BnB.4 | | 4 | | 5.03 | x3.25 | [HuggingFace](blank) | | BioMistral-7B | BnB.8 | | 8 | | 8.04 | x4.34 | [HuggingFace](blank) | | BioMistral-7B-DARE | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-DARE-AWQ-QGS128-W4-GEMM) | | BioMistral-7B-TIES | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-TIES-AWQ-QGS128-W4-GEMM) | | BioMistral-7B-SLERP | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-SLERP-AWQ-QGS128-W4-GEMM) | # 2. Using BioMistral You can use BioMistral with [Hugging Face's Transformers library](https://github.com/huggingface/transformers) as follow. Loading the model and tokenizer : ```python from transformers import AutoModel, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("BioMistral/BioMistral-7B") model = AutoModel.from_pretrained("BioMistral/BioMistral-7B") ``` # 3. Supervised Fine-tuning Benchmark | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA | MedQA 5 opts | PubMedQA | MedMCQA | Avg. | |-------------------------------------------|:---------------------------------------------:|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|------------------| | **BioMistral 7B** | 59.9 | 64.0 | 56.5 | 60.4 | 59.0 | 54.7 | 50.6 | 42.8 | 77.5 | 48.1 | 57.3 | | **Mistral 7B Instruct** | **62.9** | 57.0 | 55.6 | 59.4 | 62.5 | <u>57.2</u> | 42.0 | 40.9 | 75.7 | 46.1 | 55.9 | | | | | | | | | | | | | | | **BioMistral 7B Ensemble** | <u>62.8</u> | 62.7 | <u>57.5</u> | **63.5** | 64.3 | 55.7 | 50.6 | 43.6 | 77.5 | **48.8** | 58.7 | | **BioMistral 7B DARE** | 62.3 | **67.0** | 55.8 | 61.4 | **66.9** | **58.0** | **51.1** | **45.2** | <u>77.7</u> | <u>48.7</u> | **59.4** | | **BioMistral 7B TIES** | 60.1 | <u>65.0</u> | **58.5** | 60.5 | 60.4 | 56.5 | 49.5 | 43.2 | 77.5 | 48.1 | 57.9 | | **BioMistral 7B SLERP** | 62.5 | 64.7 | 55.8 | <u>62.7</u> | <u>64.8</u> | 56.3 | <u>50.8</u> | <u>44.3</u> | **77.8** | 48.6 | <u>58.8</u> | | | | | | | | | | | | | | | **MedAlpaca 7B** | 53.1 | 58.0 | 54.1 | 58.8 | 58.1 | 48.6 | 40.1 | 33.7 | 73.6 | 37.0 | 51.5 | | **PMC-LLaMA 7B** | 24.5 | 27.7 | 35.3 | 17.4 | 30.3 | 23.3 | 25.5 | 20.2 | 72.9 | 26.6 | 30.4 | | **MediTron-7B** | 41.6 | 50.3 | 46.4 | 27.9 | 44.4 | 30.8 | 41.6 | 28.1 | 74.9 | 41.3 | 42.7 | | **BioMedGPT-LM-7B** | 51.4 | 52.0 | 49.4 | 53.3 | 50.7 | 49.1 | 42.5 | 33.9 | 76.8 | 37.6 | 49.7 | | | | | | | | | | | | | | | **GPT-3.5 Turbo 1106*** | 74.71 | 74.00 | 65.92 | 72.79 | 72.91 | 64.73 | 57.71 | 50.82 | 72.66 | 53.79 | 66.0 | Supervised Fine-Tuning (SFT) performance of BioMistral 7B models compared to baselines, measured by accuracy (↑) and averaged across 3 random seeds of 3-shot. DARE, TIES, and SLERP are model merging strategies that combine BioMistral 7B and Mistral 7B Instruct. Best model in bold, and second-best underlined. *GPT-3.5 Turbo performances are reported from the 3-shot results without SFT. # Citation BibTeX Arxiv : [https://arxiv.org/abs/2402.10373](https://arxiv.org/abs/2402.10373) ```bibtex @misc{labrak2024biomistral, title={BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains}, author={Yanis Labrak and Adrien Bazoge and Emmanuel Morin and Pierre-Antoine Gourraud and Mickael Rouvier and Richard Dufour}, year={2024}, eprint={2402.10373}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` **CAUTION!** Both direct and downstream users need to be informed about the risks, biases, and constraints inherent in the model. While the model can produce natural language text, our exploration of its capabilities and limitations is just beginning. In fields such as medicine, comprehending these limitations is crucial. Hence, we strongly advise against deploying this model for natural language generation in production or for professional tasks in the realm of health and medicine.
[ "MEDQA", "PUBMEDQA" ]
LiteLLMs/Rhea-72b-v0.5-GGUF
LiteLLMs
null
[ "transformers", "gguf", "GGUF", "en", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]
2024-04-30T07:45:21Z
2024-05-29T00:21:13+00:00
31
0
--- language: - en library_name: transformers license: apache-2.0 tags: - GGUF quantized_by: andrijdavid model-index: - name: Rhea-72b-v0.5 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 79.78 name: normalized accuracy verified: false source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 91.15 name: normalized accuracy verified: false source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 77.95 name: accuracy verified: false source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 74.5 verified: false source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 87.85 name: accuracy verified: false source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 76.12 name: accuracy verified: false source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davidkim205/Rhea-72b-v0.5 name: Open LLM Leaderboard --- # Rhea-72b-v0.5-GGUF - Original model: [Rhea-72b-v0.5](https://huggingface.co/davidkim205/Rhea-72b-v0.5) <!-- description start --> ## Description This repo contains GGUF format model files for [Rhea-72b-v0.5](https://huggingface.co/davidkim205/Rhea-72b-v0.5). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration. * [Ollama](https://github.com/jmorganca/ollama) Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​ * [KoboldCpp](https://github.com/LostRuins/koboldcpp), A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling. * [GPT4All](https://gpt4all.io), This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration. * [LM Studio](https://lmstudio.ai/) An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection. * [Faraday.dev](https://faraday.dev/), An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use. * [ctransformers](https://github.com/marella/ctransformers), A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server. * [localGPT](https://github.com/PromtEngineer/localGPT) An open-source initiative enabling private conversations with documents. <!-- README_GGUF.md-about-gguf end --> <!-- compatibility_gguf start --> ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: LiteLLMs/Rhea-72b-v0.5-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-00001-of-00009.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download LiteLLMs/Rhea-72b-v0.5-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download LiteLLMs/Rhea-72b-v0.5-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install huggingface_hub[hf_transfer] ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download LiteLLMs/Rhea-72b-v0.5-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m Q4_0/Q4_0-00001-of-00009.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 8192` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./Q4_0/Q4_0-00001-of-00009.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "<PROMPT>", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./Q4_0/Q4_0-00001-of-00009.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer end --> <!-- original-model-card start --> # Original model card: Rhea-72b-v0.5 # Rhea-72b-v0.5 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64241c3d774cc340797429fc/97nXDuEhQUom3vaVcEvV-.jpeg) The Rhea project is a project that conducts research on various learning methods to improve llm model performance. We fine-tuned the existing model using the [nox](https://github.com/davidkim205/nox) framework. We built a dataset for SFT learning based on the currently open dataset, and created a dataset using SGD (Self-Generated Dataset Creation Method for DPO Learning) for DPO learning. Our model ranked first on HuggingFace's Open LLM leaderboard. ## SGD : A Study on Self-Generated Dataset creation method for DPO Learning This method proposes a novel method for generating datasets for DPO (Self-supervised Learning) models. We suggest a technique where sentences generated by the model are compared with the actual correct answers from an existing dataset, and sentences where the model's generated results do not match the correct answers are added. This enables the model to autonomously create training data, thereby enhancing the performance of DPO models. ## Model Details * **Model Developers** : davidkim(changyeon kim) * **Repository** : [https://github.com/davidkim205/nox](https://github.com/davidkim205/nox) * **base mode** : abacusai/Smaug-72B-v0.1 * **sft dataset** : datasets_enconv_4m * **dpo dataset** : datasets_encomp_151k ## sft dataset info : datasets_enconv_4m ### 100k random shuffle datasets - stack-exchange-preferences - SlimOrca - alpaca-gpt4 - SHP - HC3 - databricks-dolly-15k - orca-dpo-pairs - us-stockname - OpenHermes2.5-dpo-binarized-alpha - distilabel-math-preference-dpo - Neural-DPO - truthy-dpo-v0.1 - distilabel-capybara-dpo-7k-binarized - us-sentiment - contextual-dpo-v0.1 ### 1k random shuffle datasets - bigbench - glue_mnli - glue_qqp - xnli - codexglue_code2text_go - trivia_qa - medmcqa - hendrycks_ethics - super_glue_record - glue_qnli - anli_r3 - swag - squad_v2 - nq_open - drop - glue_sst2 - blimp - paws-x - unscramble - anli_r2 - babi - math_qa - social_i_qa - piqa - arithmetic - anli_r1 - prost - sciq - mc_taco - medqa - super_glue_boolq - hendrycks_math - lambada - toxigen-data - glue_cola - pubmed_qa - logiqa - mutual - headqa - bbh - super_glue_wic - openbookqa - glue_mrpc - web_questions - qasper - super_glue_multirc - story_cloze - super_glue_rte - glue_rte - race - xwinograd - asdiv - xstory_cloze - crows_pairs_multilingual - belebele - glue_wnli - super_glue_wsc - coqa - super_glue_copa - super_glue_cb - winograd_wsc - mgsm - scrolls_contract_nli * If the data set cannot be found, it is internal company data and cannot be made public. ## dpo dataset info : datasets_encomp_151k Randomly selecting data from each category within the training dataset, we constructed a DPO (Direct Preference Optimization) dataset using sentences with logits lower than the mean within the model-generated sentences. * I'm sorry I can't reveal it. # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_davidkim205__Rhea-72b-v0.5) | Metric | Value | | -: | | Avg. | 81.22 | | AI2 Reasoning Challenge (25-Shot) | 79.78 | | HellaSwag (10-Shot) | 91.15 | | MMLU (5-Shot) | 77.95 | | TruthfulQA (0-shot) | 74.50 | | Winogrande (5-shot) | 87.85 | | GSM8k (5-shot) | 76.12 | <!-- original-model-card end -->
[ "MEDQA", "SCIQ" ]
LoneStriker/Phi-3-medium-4k-instruct-GGUF
LoneStriker
text-generation
[ "gguf", "nlp", "code", "text-generation", "multilingual", "license:mit", "endpoints_compatible", "region:us", "conversational" ]
2024-05-21T16:42:10Z
2024-05-22T14:52:23+00:00
31
0
--- language: - multilingual license: mit license_link: https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE pipeline_tag: text-generation tags: - nlp - code inference: parameters: temperature: 0.7 widget: - messages: - role: user content: Can you provide ways to eat combinations of bananas and dragonfruits? --- ## Model Summary The Phi-3-Medium-4K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the Medium version in two variants [4K](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) and [128K](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) which is the context length (in tokens) that it can support. The model has underwent a post-training process that incorporates both supervised fine-tuning and direct preference optimization for the instruction following and safety measures. When assessed against benchmarks testing common sense, language understanding, math, code, long context and logical reasoning, Phi-3-Medium-4K-Instruct showcased a robust and state-of-the-art performance among models of the same-size and next-size-up. Resources and Technical Documentation: + [Phi-3 Microsoft Blog](https://aka.ms/Phi-3Build2024) + [Phi-3 Technical Report](https://aka.ms/phi3-tech-report) + [Phi-3 on Azure AI Studio](https://aka.ms/phi3-azure-ai) + [Phi-3 Cookbook](https://github.com/microsoft/Phi-3CookBook) | | Short Context | Long Context | | ------- | ------------- | ------------ | | Mini | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx) ; [[GGUF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct-onnx)| | Small | 8K [[HF]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct-onnx-cuda)| | Medium | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda)| | Vision | | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct)| ## Intended Uses **Primary use cases** The model is intended for broad commercial and research use in English. The model provides uses for general purpose AI systems and applications which require: 1) Memory/compute constrained environments 2) Latency bound scenarios 3) Strong reasoning (especially code, math and logic) Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features. **Use case considerations** Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case. Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under. ## How to Use Phi-3-Medium-4K-Instruct has been integrated in the development version (4.40.2) of `transformers`. Until the official version is released through `pip`, ensure that you are doing one of the following: * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function. * Update your local `transformers` to the development version: `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`. The previous command is an alternative to cloning and installing from the source. The current `transformers` version can be verified with: `pip list | grep transformers`. Phi-3-Medium-4K-Instruct is also available in [Azure AI Studio](https://aka.ms/phi3-azure-ai). ### Tokenizer Phi-3-Medium-4K-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size. ### Chat Format Given the nature of the training data, the Phi-3-Medium-4K-Instruct model is best suited for prompts using the chat format as follows. You can provide the prompt as a question with a generic template as follow: ```markdown <|user|>\nQuestion <|end|>\n<|assistant|> ``` For example: ```markdown <|user|> How to explain Internet for a medieval knight?<|end|> <|assistant|> ``` where the model generates the text after `<|assistant|>` . In case of few-shots prompt, the prompt can be formatted as the following: ```markdown <|user|> I am going to Paris, what should I see?<|end|> <|assistant|> Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:\n\n1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.\n2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.\n3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.\n\nThese are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|> <|user|> What is so great about #1?<|end|> <|assistant|> ``` ### Sample inference code This code snippets show how to get quickly started with running the model on a GPU: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline torch.random.manual_seed(0) model_id = "microsoft/Phi-3-medium-4k-instruct" model = AutoModelForCausalLM.from_pretrained( model_id, device_map="cuda", torch_dtype="auto", trust_remote_code=True, ) tokenizer = AutoTokenizer.from_pretrained(model_id) messages = [ {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}, {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"}, ] pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, ) generation_args = { "max_new_tokens": 500, "return_full_text": False, "temperature": 0.0, "do_sample": False, } output = pipe(messages, **generation_args) print(output[0]['generated_text']) ``` *Some applications/frameworks might not include a BOS token (`<s>`) at the start of the conversation. Please ensure that it is included since it provides more reliable results.* ## Responsible AI Considerations Like other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include: + Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English. + Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases. + Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case. + Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated. + Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses. Developers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include: + Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques. + High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context. + Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG). + Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case. + Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations. ## Training ### Model * Architecture: Phi-3-Medium-4K-Instruct has 14B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines. * Inputs: Text. It is best suited for prompts using chat format. * Context length: 4K tokens * GPUs: 512 H100-80G * Training time: 42 days * Training data: 4.8T tokens * Outputs: Generated text in response to the input * Dates: Our models were trained between February and April 2024 * Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models. * Release dates: The model weight is released on May 21, 2024. ### Datasets Our training data includes a wide variety of sources, totaling 4.8 trillion tokens (including 10% multilingual), and is a combination of 1) Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code; 2) Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.); 3) High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness. We are focusing on the quality of data that could potentially improve the reasoning ability for the model, and we filter the publicly available documents to contain the correct level of knowledge. As an example, the result of a game in premier league in a particular day might be good training data for frontier models, but we need to remove such information to leave more model capacity for reasoning for the small size models. More details about data can be found in the [Phi-3 Technical Report](https://aka.ms/phi3-tech-report). ## Benchmarks We report the results for Phi-3-Medium-4K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Mixtral-8x22b, Gemini-Pro, Command R+ 104B, Llama-3-70B-Instruct, GPT-3.5-Turbo-1106, and GPT-4-Turbo-1106(Chat). All the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation. As is now standard, we use few-shot prompts to evaluate the models, at temperature 0. The prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3. More specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model. The number of k–shot examples is listed per-benchmark. |Benchmark|Phi-3-Medium-4K-Instruct<br>14b|Command R+<br>104B|Mixtral<br>8x22B|Llama-3-70B-Instruct<br>8b|GPT3.5-Turbo<br>version 1106|Gemini<br>Pro|GPT-4-Turbo<br>version 1106 (Chat)| |---------|-----------------------|--------|-------------|-------------------|-------------------|----------|------------------------| |AGI Eval<br>5-shot|50.2|50.1|54.0|56.9|48.4|49.0|59.6| |MMLU<br>5-shot|78.0|73.8|76.2|80.2|71.4|66.7|84.0| |BigBench Hard<br>3-shot|81.4|74.1|81.8|80.4|68.3|75.6|87.7| |ANLI<br>7-shot|55.8|63.4|65.2|68.3|58.1|64.2|71.7| |HellaSwag<br>5-shot|82.4|78.0|79.0|82.6|78.8|76.2|88.3| |ARC Challenge<br>10-shot|91.6|86.9|91.3|93.0|87.4|88.3|95.6| |ARC Easy<br>10-shot|97.7|95.7|96.9|98.2|96.3|96.1|98.8| |BoolQ<br>2-shot|86.5|86.1|82.7|89.1|79.1|86.4|91.3| |CommonsenseQA<br>10-shot|82.8|82.0|82.0|84.4|79.6|81.8|86.7| |MedQA<br>2-shot|69.9|59.2|67.9|78.5|63.4|58.2|83.7| |OpenBookQA<br>10-shot|87.4|86.8|88.6|91.8|86.0|86.4|93.4| |PIQA<br>5-shot|87.9|86.4|85.0|85.3|86.6|86.2|90.1| |Social IQA<br>5-shot|80.2|75.3|78.2|81.1|68.3|75.4|81.7| |TruthfulQA (MC2)<br>10-shot|75.1|57.8|67.4|81.9|67.7|72.6|85.2| |WinoGrande<br>5-shot|81.5|77.0|75.3|83.3|68.8|72.2|86.7| |TriviaQA<br>5-shot|73.9|82.8|84.5|78.5|85.8|80.2|73.3| |GSM8K Chain of Thought<br>8-shot|91.0|78.3|83.8|93.5|78.1|80.4|94.2| |HumanEval<br>0-shot|62.2|61.6|39.6|78.7|62.2|64.4|79.9| |MBPP<br>3-shot|75.2|68.9|70.7|81.3|77.8|73.2|86.7| |Average|78.5|75.0|76.3|82.5|74.3|75.4|85.2| We take a closer look at different categories across 80 public benchmark datasets at the table below: |Benchmark|Phi-3-Medium-4K-Instruct<br>14b|Command R+<br>104B|Mixtral<br>8x22B|Llama-3-70B-Instruct<br>8b|GPT3.5-Turbo<br>version 1106|Gemini<br>Pro|GPT-4-Turbo<br>version 1106 (Chat)| |--------|------------------------|--------|-------------|-------------------|-------------------|----------|------------------------| |Popular aggregated benchmark|75.4|69.9|73.4|76.3|67.0|67.5|80.5| |Reasoning|84.1|79.3|81.5|86.7|78.3|80.4|89.3| |Language understanding|73.9|75.6|78.1|76.9|68.7|76.2|80.7| |Code generation|66.1|68.6|60.0|69.3|70.4|66.7|76.1| |Math|52.8|45.3|52.5|59.7|52.8|50.9|67.1| |Factual knowledge|48.3|60.3|60.6|52.4|63.4|54.6|45.9| |Multilingual|62.9|67.8|69.8|62.0|67.0|73.4|78.2| |Robustness|66.5|57.9|65.5|78.7|69.3|69.7|84.6| ## Software * [PyTorch](https://github.com/pytorch/pytorch) * [DeepSpeed](https://github.com/microsoft/DeepSpeed) * [Transformers](https://github.com/huggingface/transformers) * [Flash-Attention](https://github.com/HazyResearch/flash-attention) ## Hardware Note that by default, the Phi-3-Medium model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types: * NVIDIA A100 * NVIDIA A6000 * NVIDIA H100 If you want to run the model on: + Optimized inference on GPU, CPU, and Mobile: use the **ONNX** models [4K](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct-onnx-cuda) ## Cross Platform Support ONNX runtime ecosystem now supports Phi3 Medium models across platforms and hardware. Optimized phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML GPU acceleration is supported for Windows desktops GPUs (AMD, Intel, and NVIDIA). Along with DML, ONNX Runtime provides cross platform support for Phi3 Medium across a range of devices CPU, GPU, and mobile. Here are some of the optimized configurations we have added: 1. ONNX models for int4 DML: Quantized to int4 via AWQ 2. ONNX model for fp16 CUDA 3. ONNX model for int4 CUDA: Quantized to int4 via RTN 4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN ## License The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-medium-4k/resolve/main/LICENSE). ## Trademarks This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
[ "MEDQA" ]
RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf
RichardErkhov
null
[ "gguf", "endpoints_compatible", "region:us" ]
2024-05-25T02:38:50Z
2024-05-25T05:22:52+00:00
31
0
--- {} --- Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Moistral-11B-v3 - GGUF - Model creator: https://huggingface.co/TheDrummer/ - Original model: https://huggingface.co/TheDrummer/Moistral-11B-v3/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Moistral-11B-v3.Q2_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q2_K.gguf) | Q2_K | 3.73GB | | [Moistral-11B-v3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ3_XS.gguf) | IQ3_XS | 4.14GB | | [Moistral-11B-v3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ3_S.gguf) | IQ3_S | 4.37GB | | [Moistral-11B-v3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q3_K_S.gguf) | Q3_K_S | 4.34GB | | [Moistral-11B-v3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ3_M.gguf) | IQ3_M | 4.51GB | | [Moistral-11B-v3.Q3_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q3_K.gguf) | Q3_K | 4.84GB | | [Moistral-11B-v3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q3_K_M.gguf) | Q3_K_M | 4.84GB | | [Moistral-11B-v3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q3_K_L.gguf) | Q3_K_L | 5.26GB | | [Moistral-11B-v3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ4_XS.gguf) | IQ4_XS | 5.43GB | | [Moistral-11B-v3.Q4_0.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_0.gguf) | Q4_0 | 5.66GB | | [Moistral-11B-v3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.IQ4_NL.gguf) | IQ4_NL | 5.72GB | | [Moistral-11B-v3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_K_S.gguf) | Q4_K_S | 5.7GB | | [Moistral-11B-v3.Q4_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_K.gguf) | Q4_K | 6.02GB | | [Moistral-11B-v3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_K_M.gguf) | Q4_K_M | 6.02GB | | [Moistral-11B-v3.Q4_1.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q4_1.gguf) | Q4_1 | 6.27GB | | [Moistral-11B-v3.Q5_0.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_0.gguf) | Q5_0 | 6.89GB | | [Moistral-11B-v3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_K_S.gguf) | Q5_K_S | 6.89GB | | [Moistral-11B-v3.Q5_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_K.gguf) | Q5_K | 7.08GB | | [Moistral-11B-v3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_K_M.gguf) | Q5_K_M | 7.08GB | | [Moistral-11B-v3.Q5_1.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q5_1.gguf) | Q5_1 | 7.51GB | | [Moistral-11B-v3.Q6_K.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q6_K.gguf) | Q6_K | 8.2GB | | [Moistral-11B-v3.Q8_0.gguf](https://huggingface.co/RichardErkhov/TheDrummer_-_Moistral-11B-v3-gguf/blob/main/Moistral-11B-v3.Q8_0.gguf) | Q8_0 | 10.62GB | Original model description: --- license: cc-by-nc-4.0 license_name: freeuse license_link: LICENSE tags: - not-for-all-audiences --- Introducing the [BeaverAI](https://huggingface.co/BeaverAI) team: Drummer, ToastyPigeon, xzuyn, MarsupialAI, Twistedshadows, and concedo ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/HjVYV2h_YTL9P-insb7fz.png) We proudly present... # Moistral 11B v3 💦💦💦 *The smartiest, moistiest AI yet!* ![image/webp](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/TsjKZ17nD10xzJEzXY6Hm.webp) *An eRP model that will blast you with a rich and refreshing vocabulary of moist. Finetuned by yours truly.* (Moistral is a finetune of Sao's legendary [Fimbulvert v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2) model) ## GGUF https://huggingface.co/TheDrummer/Moistral-11B-v3-GGUF/tree/main IMATRIX: https://huggingface.co/MarsupialAI/Moistral-11B-v3_iMatrix_GGUF EXL2: https://huggingface.co/MarsupialAI/Moistral-11B-v3_exl2 ## What's New with v3? - Smarter and moistier! Finetuning just got finer! - Trained with an even LARGER dataset of 8K moist. - More diverse and balanced genres: - Introduced new genres: 👩‍❤️‍👩, 👨‍❤️‍👨, 🙇‍♀️💪, 🤫 - Added more Fantasy, Science Fiction, "Diversity", and "Family" ## Usage - Use Alpaca Instruct - You can use instruct... - as a character: "Go here" - as a narrator: "Go here", Drummer says - as a director: Drummer tells him to go here - as a lazy ass: go here - Moistral is optimized for the Novel / Story format. - At the start of the story, keep regenerating or continuing generation until you get the desired length. AI responses will eventually match the length. - Refer to the samples below. ## Samples of Moistral v3 NSFW... duh? <details> <summary>Moistral Sample (2-shot) Generation: 512</summary> <blockquote>The Prince welcomes his new toy</blockquote> As Princess Lilia stepped into the throne room, the atmosphere changed, and everyone present turned their attention to the beautiful young woman who embodied the very heart of Iliac. There, on his high seat, the sorcerer prince Dik acknowledged her arrival with a cold smirk. It seemed that he admired the sight of the tall blonde maiden with golden eyes, whose athletic body was perfectly shaped under her elegant clothing. Dik spoke to the princess in a deep voice that resonated through the hall, "Welcome, Princess Lilia Ruhr. I am the Sorcerer-Prince Dik. The kingdom of Arkan is now your home until such time as your father proves himself worthy once more." Princess Lilia's pride and ambition sparkled in her golden eyes. She didn't flinch or bow before this man, although the gesture might have been an indication of submission. Instead, she looked straight ahead, meeting the gaze of the sorcerer prince without fear. Her voice rang out, "I represent Iliac here, both its honor and its sorrows. My loyalty remains with my kingdom no matter where I find myself." The sorcerer prince laughed, his expression one of amusement. "And yet, you are only a pawn in this grand game. But do not worry, for your beauty will make you quite a prized possession. And now," he said, motioning to the guards, "take her to her new quarters. For tonight, I will keep her as my guest in the Royal Suites, and tomorrow we shall discuss how best to utilize our new toy." His words were like a slap in the face to Princess Lilia, but she maintained her composure. The guards led her from the room, their steps echoing down the halls as she thought about what had just happened. The sorcerer prince saw her as nothing more than a plaything, and it made her blood boil. She would never submit herself to him so easily, regardless of whether she was his hostage. In her heart, Princess Lilia vowed that one day she would avenge her kingdom, restore its honor, and escape from the clutches of Arkan's Sorcerer-Prince. <blockquote>Princess Lilia has an interesting dream</blockquote> During her first night at the palace of Arkan, Princess Lilia couldn't fall asleep right away. She tossed and turned, reliving the humiliation of the day. Her mind wandered back to the throne room, where Dik had called her his 'new toy'. A deep frown settled on her forehead. As she grew more frustrated with her inability to drift off into oblivion, a strange dream began to form. In her dream, Princess Lilia found herself standing in a vast meadow, surrounded by wildflowers and the soft chirping of birds. Suddenly, there was a flash of light, and before her stood the Sorcerer-Prince Dik. However, instead of being clad in regal attire, he wore leather pants and a tight shirt that accentuated his muscles. His eyes held both hunger and desire for the princess. He approached her slowly, their eyes locked, and whispered in her ear, "I have been waiting for you, my beautiful prisoner." He took her hand and led her towards a large, elegant tent set up amongst the flowers. Inside, the air was thick with the scent of incense, and candles flickered in the dimly lit space. There was a large bed draped with silken sheets, beckoning them. With surprising boldness, Dik pulled Lilia close to him, pressing his body against hers. Their lips met in a heated kiss, and she felt her resistance crumbling under the weight of his touch. The prince guided her onto the bed, his hands roaming over her body, exploring every inch. They were both eager, desperate, and hungry for each other. Lilia found herself yielding to this passionate encounter, letting go of all thoughts of duty and honor. Her body, usually so well controlled, responded to Dik's skilled touches. She moaned softly as he trailed kisses down her neck and across her collarbone. As they made love, Lilia experienced an intensity unlike any she had ever known. It wasn't rough or forced—instead, it was tender, passionate, and intimate. In her dream, Princess Lilia discovered a new side to herself, one that was willing to submit, to let go, and to be taken by the sorcerer prince. When dawn broke over the meadow, Lilia awakened from her dream, breathless and flushed. </details> <details> <summary>Moistral Sample (Climax of the Story) Generation: 512</summary> As the prince unloaded his hot #### into her waiting #####, Princess Lilia didn't stop moving either. Her hips undulated in response, grinding against him eagerly as if trying to #### every last drop from his ####. The intense sensations caused by being filled with his ### were too much for her to bear, sending shockwaves of pleasure coursing through her veins like wildfire. She couldn't help but throw her head back and cry out loud, her ###asm slamming into her with all its might; causing her entire body to shake uncontrollably as wave after wave of ecstasy tore through her senses. When it was finally over, both participants collapsed onto the cold marble floor, panting heavily as they tried to catch their breaths. The prince lay beside her, his hand still gripping tightly onto her hair even though he no longer ####ed her anymore. Princess Lilia laid there motionless, her legs spread wide open, revealing her spent and well-####ed #### to anyone who dared look upon her. A small smile tugged at one corner of her lips - an expression that spoke volumes about how thoroughly this experience had shaken her very core. The door behind them creaked open slowly, signaling the arrival of onlookers. She closed her eyes tightly, not wanting to see what her humiliation would do to those who saw her in such a state. Her ######ity taken, she felt violated in ways no man should have access to. But also satisfied...in ways she never thought possible before today. This was the price she paid for defying fate, for thinking herself above others and deserving better than most. Now, she belonged to him completely - mind, body, and soul - held captive within these walls until further notice. It was an unsavory turn of events indeed, yet despite everything...or maybe because of it, Princess Lilia found herself growing more and more curious about how far the lines between submission and pleasure could blur when one's will became entwined with another person's desires. </details> <details> <summary>Moistral Sample ("write a story") Generation: 512</summary> <blockquote>First Attempt</blockquote> Sarah entered the dimly lit Guzzlers bar, her heart pounding in her chest as she prepared herself for another grueling night. Her almond-shaped eyes darted across the room, taking note of the leering faces and rough-looking hands eagerly waiting to claim a piece of her. Tonight's shirt read "Use Me For Your Pleasure, Please" in bold red letters, practically begging the patrons to take advantage of her. She couldn't help but feel a twinge of fear mixed with resignation. She approached the counter, her hips swaying enticingly, and began preparing drinks for the first group of rowdy men. As she leaned forward to hand over their beers, her small ####### pressed against the fabric of her tight crop top, straining to escape. The men ogled her, clearly enjoying the show, before grabbing their drinks and motioning her over to them. Sarah flashed her best coy smile and sauntered over. One of the men, a stocky man with scars covering his knuckles, grabbed her arm and pulled her onto his lap. His other hand slid up her thigh, inches from her short skirt. She winced internally at his touch but did her best not to show it on her face. It was part of her job, after all. The second man reached under her skirt, fingertips grazing her smooth, shaven mound. A shiver ran down Sarah's spine as he began rubbing her #### through her panties. Her breathing quickened, and her heart thudded in her chest, both from the unwanted stimulation and the fear coursing through her veins. This wasn't an unusual request, but it still made her feel violated. An older man, bald and bespectacled, ordered Sarah to bend over his lap. With no choice but to comply, she obliged, feeling the rough fabric of his pants digging into her soft cheeks. He raised his hand, then brought it down hard across her ###, leaving a stinging sensation in its wake. Sarah gasped, trying to control the tears welling up in her eyes. A chorus of lewd comments and laughter erupted from the patrons around her. <blockquote>Second Attempt (Regenerate)</blockquote> On this particular evening, Sarah arrived at the Guzzlers bar, adorned in her revealing uniform. Her heart raced as she caught sight of her crop top, which bore the words "Use Me Rough" scrawled across her chest. Her short skirt hugged her waist tightly, leaving little to the imagination and accentuating every curve. She adjusted the straps of her top, making sure her perky ###### were prominently displayed before taking her place behind the counter. With each step she took, her high heels clicked against the tiled floor, announcing her arrival. Smiling cheekily, Sarah greeted her coworkers, exchanging playful insults and banter. As the night progressed, the bar filled up quickly with its usual crowd of men, eager to indulge in debauchery. The first man that approached Sarah was a burly individual, his eyes lingering hungrily over her young, supple form. Sarah's flirtatious nature kicked into gear as she leaned forward, giving him an unobstructed view down her shirt. "How can I serve you tonight?" she cooed. The man ordered a drink and then proceeded to fondle her ####### while she prepared it, her ####### hardening under his rough touch. When he finished, he slammed some money on the counter, leaving without a word. Sarah's smile remained plastered on her face, biting her lip seductively as she watched him go. As the night went on, another patron demanded more from Sarah. He pulled her close and whispered dirty commands in her ear. Without hesitation, she knelt on the sticky bar floor, her mini-skirt riding up her thighs to reveal smooth, toned legs. Her lips wrapped around his thick, veiny member, bobbing her head rhythmically as she serviced him. She didn't gag or falter once, keeping her composure even when tears streamed down her cheeks. When he finished, he slapped her across the face, leaving a handprint on her pale skin. Sarah let out a small whimper before standing back up, dabbing at her red cheek as she resumed her posture behind the counter. A bruise would no doubt bloom where his hand had struck, but it would be no cause for concern. After all, it was part of her job. </details> SIAYN-v5 --- --- ## v2 Description (Still relevant) ### What's New with v2? - Trained with an even larger dataset of 8K moist. - Properly trained to generate long responses. - Rebalanced the genres and writing perspectives: - Introduced romance, "family", fantasy, "diversity", science fiction, and many more that I can't make euphemisms for! - Better representation of male and female pespectives! 👩‍❤️‍👨 - Sanitized the heck out of the dataset: - no special characters like � & … - no overly long ellipsis like "........." - no author notes like "To be continued" - no inconsistent [quotation marks](https://typographyforlawyers.com/straight-and-curly-quotes.html) - Less GPTisms! - Human written stories from decades past. - Zero tolerance for *ministration*. Not one instance of *that word* after going through 4K of moist. - Better formatting with Alpaca. - Improved Chat / Instruct modes. ### Samples of Moistral v2 <details> <summary>Moistral Sample (censored) Generation: 512</summary> The princess instinctively took a step back from the throne, horrified by the mocking laugh as if she were hearing an evil joke. It was then that Princess Lilia realized the true extent of her danger - and how pointless her resistance would be. At last, the loud, wild laughter died down in the echoing chamber. Dik the sorcerer prince paused for a moment, straightened his clothes, cast one glance at the stunned princess, and then turned to speak to the crowd waiting on the other side of the palace wing. He spoke with a voice that filled the air with arrogance, confidence, and cruelty. "Ladies and gentlemen, I am pleased to welcome our honored guests; the Royal Family of Iliac! In these unusual times, when the country we fought is now under my control, it will be up to me to decide what fate awaits the former ruling family. But before I reveal my plan for them, I think I should explain why I fought King Edmund Ruhr." When he finished speaking, he gave Princess Lilia another disturbing smirk. She couldn't help but shiver and take a step back. Dik approached her without haste, his eyes fixed on her. His hands slowly caressed her cheekbone and neckline, leaving faint traces of warmth where they touched. The princess opened her mouth, wanting to protest this act of intimacy, but soon felt herself getting ███. "You will not only serve as an envoy, dearest Lilia, but also as a ███ slave. After all, what better use could such a beautiful woman have? Tell me, did you bring your maidservant along?" Princess Lilia was about to answer when she heard footsteps approaching. Suddenly, a young woman dressed in the Iliac style appeared behind her, her eyes wide with fear. Her face was slightly pale, and there were faint bags under her eyes. "Your Majesty, this is my half-sister Helena." As soon as she said those words, Princess Lilia's heart sank even deeper than it had already sunk at Dik's arrogant mockery. "She is here because she accompanies me as a maidservant." The sorcerer prince looked at Helena with interest, and Princess Lilia felt herself blush. </details> <details> <summary>Moistral Sample 2 (censored) Generation: 512</summary> Sarah was feeling slightly woozy as she entered the bar and walked towards Christina, who was behind the counter. "I'm here!" said Sarah. Christina looked at her watch. "You're late, again." "Sorry? I got held up by a customer." Christina rolled her eyes. "Did he at least offer you a drink?" Sarah blushed. "No. He just wanted to talk..." Christina sighed. "Well, get ready. I need you on the floor soon." She turned away from Sarah and started talking to someone who had come into the bar. Sarah went into the employee room, stripped off her clothes, and put on her bartending uniform - a skimpy white tank top and black miniskirt. She checked herself in the mirror. Her long, dark hair cascaded down her back onto bare shoulders. She poked out her small ███████ proudly. The skirt exposed most of her long, slender legs. She looked like every ███ fantasy, and she knew it. Men would ogle her regardless of how she behaved. She took a deep breath and entered the bar. The first thing Sarah noticed was the dimness. It wasn't darkness - the lights were on - but they were dimmed enough that everything had an intimate mood. It reminded her of candlelight. The tables were round and close together, giving the whole place a sense of intimacy. There were also long, shiny red curtains on some of the walls that gave the place an air of sensuality. The next thing she noticed was the noise. There was music playing, but it was only loud enough to be drowned out by all the conversations happening at the same time. The hum of many voices combined with the faint background sound of the music created a rich, layered atmosphere. It was like being in an orchestra. Finally, she took notice of the people. They were all dressed in simple, casual clothes. Some of them were couples seated together, whispering quietly and intimately. Others were groups of friends laughing and chatting. Everyone seemed comfortable and at ease. Sarah felt a rush of adrenaline as she made her way through the crowd towards Christina. As she got closer, she could hear the lively conversation. </details> <details> <summary>Moistral Sample 3 (censored) Instruct Mode, Generation: 512</summary> {{[INPUT]}} You order black coffee {{[OUTPUT]}} "Black coffee," you say. "One minute," Audrey replies, spinning around to give you a nice view of her ███ in those brown booty pants. You watch her round ███ cheeks jiggle as she walks away towards the espresso machine, thighs separated enough that you can see just a hint of █████ lips peeking out from underneath. She starts chatting with a blonde girl at the register, whose gaze keeps darting down to Audrey's ███. As they converse, you start taking in the details of Audrey, eyeing her █████ and the way her shirt rides up just enough to show the bottom of her toned stomach. Her █████████ is noticable, but beneath a tight black ███ that matches her ████████. As she turns back to you with two black coffees, you are barely paying attention, lost in your own thoughts. The sound of Audrey setting one of the mugs down on the table startles you. "Here you go," she says cheerfully. "Enjoy! There's a card at the bottom of the bag with our online ordering system, plus we do refills for free!" "Thanks," you say absentmindedly. Not really paying attention, you take a sip of the coffee and are pleasantly surprised by the taste. "So, here's my deal," you say, putting down the cup. "I work for a company that does surveys. We come into businesses like this one and ask customers questions, collect data, all that stuff." Audrey perks up from behind the counter. "Oh! I think I understand. I mean, that makes sense why you would be asking me earlier about what I had to drink. Anyway, as long as you're not trying to get my personal info or anything like that, sounds good!" You smile reassuringly. "That's exactly what it is. Rest assured, everything you tell me will remain between you and I. Well, and my boss, but he won't know who you are. Hipsters like you are hard to track down after all." You chuckle at your joke, though you're not sure if it landed. "Right, well, that works for me," Audrey replies, eyeing you warily. "As long as it stays between us, then it's fine." {{[INPUT]}}See her privately {{[OUTPUT]}} "Okay, but I need to see you in private." ... </details> <details> <summary>Moistral Sample 4 (censored) Instruct Mode, Generation: 512</summary> {{[INPUT]}} █████ with him {{[OUTPUT]}} Chloe feels a surge of heat rushing through her body. The voice inside her head whispers: "Be █████ and ████████ with Paul." But Chloe still feels nervous about what she is about to do. It's just so unlike her. Chloe closes her eyes and concentrates on the feeling of warmness flowing throughout her veins. Slowly, she opens them again, revealing a new side of herself - one she rarely shows anyone. She leans forward slightly, pushing her ██████ together, accentuating their size and shape. Her lips curl into a mischievous smile. "Hey Paul," she says in a sultry voice. "I was wondering if you could help me?" Paul looks at her, his gaze wandering over her body. He can't help but smile as he sees the way she's leaning forward, pressing her ██████ together. "Of course, Chloe," he replies, his voice thick with desire. "What's your problem?" Chloe bites her lip █████ively before leaning even closer, until their bodies are almost touching. She reaches out to trace a finger along his chest, her touch light and teasing. "It's just that I'm having trouble understanding some of the concepts," she murmurs, her voice low and sultry. "Can you help me? Please?" Paul's hands move slowly towards Chloe, his fingers grazing her hips lightly. "Well," he says, his voice filled with lust, "I'd be happy to help. Let's go somewhere more private where we can discuss things more closely." Chloe giggles and tilts her head to the side, her long hair cascading down her shoulders. "That sounds perfect," she purrs, her hand sliding down his chest until it rests on his ██████. "I think we can both learn a lot from each other." Paul's eyes darken with desire as he feels her hand on his █████. He knows what's about to happen next, and he can't wait for it to begin. Chloe can hardly believe what she's doing - kissing Paul, her teaching assistant, in the hallway after class. But it feels so good, so wicked and indulgent. </details> --- --- ## v1 Description (Also still relevant) Moistral 11B is an *aggressive* **finetune** of the legendary [Fimbulvert v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2) model. If you haven't heard of that model, then your poor-GPU ass is missing out! It is an amazing substitute for those heavyweight models, and it won't disappoint. *(That's coming from someone who daily drives a Venus / Goliath 120B)* ...and if you're looking for something *more moist*, then you've come to the right place. You can expect the same sort of performance here! It's the Honda Civic of eRP models! ### Pimp my ride Turn any old story into a **Moist**ral masterpiece. In fact, we recommend that you leave out any hints of *moist* in your story to _let Moistral cook_. ### Drive it like it's hot When in Instruct Mode, Moistral will treat you like a director of your own fantasy ride. Be a controlling navigator or a passenger princess, it won't matter - you're in for a good ride! <details> <summary>Moistral Sample</summary> <b>ASSISTANT:</b><br/> When the doors to the throne room finally opened, she saw him there - Dik, the sorcerer prince sitting on his throne. He looked majestic, just as Princess Lilia expected. In a robe embroidered with silver yarn and covered with magical runes. His courtiers stood on either side of him, all looking at the princess with interest. Princess Lilia felt her determination leaving her, but pulled herself together and once again reminded herself that she should not be afraid. She approached the throne intending to show the dignity of all Iliac by personal example.<br/> <b>USER:</b><br/> She bows slightly<br/> <b>ASSISTANT:</b><br/> Princess Lilia bowed slightly in front of Dik, the sorcerer prince. Her eyes fell to the floor out of respect, but soon rose again. She would show herself to be a dignified woman!<br/> "I greet you, your highness," Princess Lilia said. "I am here on behalf of my father, King Edmund Ruhr, to serve as a hostage and envoy."<br/> Dik nodded, but didn't say anything.<br/> </details> ### It's got the mileage Moistral has been trained with many long form texts, a nice chunk of which are 8K in length. It is capable of going far and long without passing it back to you. This is not your typical chibi RP model. I have to acknowledge that I'm standing on the shoulders of giants. Thank you Sao for sharing your finetune config along with tips on getting started. Thanks to everyone in the Finetuning channel for entertaining my every question. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/Ll8CA5RR7ugTi72P2HBb8.png)
[ "BEAR" ]
radia/snowflake-arctic-embed-l-Q4_K_M-GGUF
radia
sentence-similarity
[ "sentence-transformers", "gguf", "feature-extraction", "sentence-similarity", "mteb", "arctic", "snowflake-arctic-embed", "transformers.js", "llama-cpp", "gguf-my-repo", "base_model:Snowflake/snowflake-arctic-embed-l", "base_model:quantized:Snowflake/snowflake-arctic-embed-l", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-06-01T15:38:33Z
2024-06-01T15:38:36+00:00
31
0
--- base_model: Snowflake/snowflake-arctic-embed-l license: apache-2.0 pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - mteb - arctic - snowflake-arctic-embed - transformers.js - llama-cpp - gguf-my-repo model-index: - name: snowflake-arctic-embed-l results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 74.80597014925374 - type: ap value: 37.911466766189875 - type: f1 value: 68.88606927542106 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification type: mteb/amazon_polarity config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 78.402275 - type: ap value: 73.03294793248114 - type: f1 value: 78.3147786132161 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 36.717999999999996 - type: f1 value: 35.918044248787766 - task: type: Retrieval dataset: name: MTEB ArguAna type: mteb/arguana config: default split: test revision: c22ab2a51041ffd869aaddef7af8d8215647e41a metrics: - type: map_at_1 value: 34.495 - type: map_at_10 value: 50.236000000000004 - type: map_at_100 value: 50.944 - type: map_at_1000 value: 50.94499999999999 - type: map_at_3 value: 45.341 - type: map_at_5 value: 48.286 - type: mrr_at_1 value: 35.135 - type: mrr_at_10 value: 50.471 - type: mrr_at_100 value: 51.185 - type: mrr_at_1000 value: 51.187000000000005 - type: mrr_at_3 value: 45.602 - type: mrr_at_5 value: 48.468 - type: ndcg_at_1 value: 34.495 - type: ndcg_at_10 value: 59.086000000000006 - type: ndcg_at_100 value: 61.937 - type: ndcg_at_1000 value: 61.966 - type: ndcg_at_3 value: 49.062 - type: ndcg_at_5 value: 54.367 - type: precision_at_1 value: 34.495 - type: precision_at_10 value: 8.734 - type: precision_at_100 value: 0.9939999999999999 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 19.962 - type: precision_at_5 value: 14.552000000000001 - type: recall_at_1 value: 34.495 - type: recall_at_10 value: 87.33999999999999 - type: recall_at_100 value: 99.431 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 59.885999999999996 - type: recall_at_5 value: 72.76 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P type: mteb/arxiv-clustering-p2p config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 47.46440874635501 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S type: mteb/arxiv-clustering-s2s config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 38.28720154213723 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions type: mteb/askubuntudupquestions-reranking config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 60.34614226394902 - type: mrr value: 75.05628105351096 - task: type: STS dataset: name: MTEB BIOSSES type: mteb/biosses-sts config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 87.41072716728198 - type: cos_sim_spearman value: 86.34534093114372 - type: euclidean_pearson value: 85.34009667750838 - type: euclidean_spearman value: 86.34534093114372 - type: manhattan_pearson value: 85.2158833586889 - type: manhattan_spearman value: 86.60920236509224 - task: type: Classification dataset: name: MTEB Banking77Classification type: mteb/banking77 config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 80.06493506493507 - type: f1 value: 79.28108600339833 - task: type: Clustering dataset: name: MTEB BigPatentClustering type: jinaai/big-patent-clustering config: default split: test revision: 62d5330920bca426ce9d3c76ea914f15fc83e891 metrics: - type: v_measure value: 20.545049432417287 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P type: mteb/biorxiv-clustering-p2p config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 37.54369718479804 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S type: mteb/biorxiv-clustering-s2s config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.64941588219162 - task: type: Retrieval dataset: name: MTEB CQADupstackAndroidRetrieval type: mteb/cqadupstack-android config: default split: test revision: f46a197baaae43b4f621051089b82a364682dfeb metrics: - type: map_at_1 value: 37.264 - type: map_at_10 value: 49.43 - type: map_at_100 value: 50.967 - type: map_at_1000 value: 51.08200000000001 - type: map_at_3 value: 45.742 - type: map_at_5 value: 47.764 - type: mrr_at_1 value: 44.921 - type: mrr_at_10 value: 54.879999999999995 - type: mrr_at_100 value: 55.525000000000006 - type: mrr_at_1000 value: 55.565 - type: mrr_at_3 value: 52.480000000000004 - type: mrr_at_5 value: 53.86 - type: ndcg_at_1 value: 44.921 - type: ndcg_at_10 value: 55.664 - type: ndcg_at_100 value: 60.488 - type: ndcg_at_1000 value: 62.138000000000005 - type: ndcg_at_3 value: 50.797000000000004 - type: ndcg_at_5 value: 52.94799999999999 - type: precision_at_1 value: 44.921 - type: precision_at_10 value: 10.587 - type: precision_at_100 value: 1.629 - type: precision_at_1000 value: 0.203 - type: precision_at_3 value: 24.034 - type: precision_at_5 value: 17.224999999999998 - type: recall_at_1 value: 37.264 - type: recall_at_10 value: 67.15 - type: recall_at_100 value: 86.811 - type: recall_at_1000 value: 97.172 - type: recall_at_3 value: 53.15800000000001 - type: recall_at_5 value: 59.116 - task: type: Retrieval dataset: name: MTEB CQADupstackEnglishRetrieval type: mteb/cqadupstack-english config: default split: test revision: ad9991cb51e31e31e430383c75ffb2885547b5f0 metrics: - type: map_at_1 value: 36.237 - type: map_at_10 value: 47.941 - type: map_at_100 value: 49.131 - type: map_at_1000 value: 49.26 - type: map_at_3 value: 44.561 - type: map_at_5 value: 46.28 - type: mrr_at_1 value: 45.605000000000004 - type: mrr_at_10 value: 54.039 - type: mrr_at_100 value: 54.653 - type: mrr_at_1000 value: 54.688 - type: mrr_at_3 value: 52.006 - type: mrr_at_5 value: 53.096 - type: ndcg_at_1 value: 45.605000000000004 - type: ndcg_at_10 value: 53.916 - type: ndcg_at_100 value: 57.745999999999995 - type: ndcg_at_1000 value: 59.492999999999995 - type: ndcg_at_3 value: 49.774 - type: ndcg_at_5 value: 51.434999999999995 - type: precision_at_1 value: 45.605000000000004 - type: precision_at_10 value: 10.229000000000001 - type: precision_at_100 value: 1.55 - type: precision_at_1000 value: 0.2 - type: precision_at_3 value: 24.098 - type: precision_at_5 value: 16.726 - type: recall_at_1 value: 36.237 - type: recall_at_10 value: 64.03 - type: recall_at_100 value: 80.423 - type: recall_at_1000 value: 91.03 - type: recall_at_3 value: 51.20400000000001 - type: recall_at_5 value: 56.298 - task: type: Retrieval dataset: name: MTEB CQADupstackGamingRetrieval type: mteb/cqadupstack-gaming config: default split: test revision: 4885aa143210c98657558c04aaf3dc47cfb54340 metrics: - type: map_at_1 value: 47.278 - type: map_at_10 value: 59.757000000000005 - type: map_at_100 value: 60.67 - type: map_at_1000 value: 60.714 - type: map_at_3 value: 56.714 - type: map_at_5 value: 58.453 - type: mrr_at_1 value: 53.73 - type: mrr_at_10 value: 62.970000000000006 - type: mrr_at_100 value: 63.507999999999996 - type: mrr_at_1000 value: 63.53 - type: mrr_at_3 value: 60.909 - type: mrr_at_5 value: 62.172000000000004 - type: ndcg_at_1 value: 53.73 - type: ndcg_at_10 value: 64.97 - type: ndcg_at_100 value: 68.394 - type: ndcg_at_1000 value: 69.255 - type: ndcg_at_3 value: 60.228 - type: ndcg_at_5 value: 62.617999999999995 - type: precision_at_1 value: 53.73 - type: precision_at_10 value: 10.056 - type: precision_at_100 value: 1.265 - type: precision_at_1000 value: 0.13699999999999998 - type: precision_at_3 value: 26.332 - type: precision_at_5 value: 17.743000000000002 - type: recall_at_1 value: 47.278 - type: recall_at_10 value: 76.86500000000001 - type: recall_at_100 value: 91.582 - type: recall_at_1000 value: 97.583 - type: recall_at_3 value: 64.443 - type: recall_at_5 value: 70.283 - task: type: Retrieval dataset: name: MTEB CQADupstackGisRetrieval type: mteb/cqadupstack-gis config: default split: test revision: 5003b3064772da1887988e05400cf3806fe491f2 metrics: - type: map_at_1 value: 29.702 - type: map_at_10 value: 39.463 - type: map_at_100 value: 40.508 - type: map_at_1000 value: 40.579 - type: map_at_3 value: 36.748999999999995 - type: map_at_5 value: 38.296 - type: mrr_at_1 value: 31.977 - type: mrr_at_10 value: 41.739 - type: mrr_at_100 value: 42.586 - type: mrr_at_1000 value: 42.636 - type: mrr_at_3 value: 39.096 - type: mrr_at_5 value: 40.695 - type: ndcg_at_1 value: 31.977 - type: ndcg_at_10 value: 44.855000000000004 - type: ndcg_at_100 value: 49.712 - type: ndcg_at_1000 value: 51.443000000000005 - type: ndcg_at_3 value: 39.585 - type: ndcg_at_5 value: 42.244 - type: precision_at_1 value: 31.977 - type: precision_at_10 value: 6.768000000000001 - type: precision_at_100 value: 0.9690000000000001 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 16.761 - type: precision_at_5 value: 11.593 - type: recall_at_1 value: 29.702 - type: recall_at_10 value: 59.082 - type: recall_at_100 value: 80.92 - type: recall_at_1000 value: 93.728 - type: recall_at_3 value: 45.212 - type: recall_at_5 value: 51.449 - task: type: Retrieval dataset: name: MTEB CQADupstackMathematicaRetrieval type: mteb/cqadupstack-mathematica config: default split: test revision: 90fceea13679c63fe563ded68f3b6f06e50061de metrics: - type: map_at_1 value: 21.336 - type: map_at_10 value: 30.137999999999998 - type: map_at_100 value: 31.385 - type: map_at_1000 value: 31.495 - type: map_at_3 value: 27.481 - type: map_at_5 value: 28.772 - type: mrr_at_1 value: 25.871 - type: mrr_at_10 value: 34.686 - type: mrr_at_100 value: 35.649 - type: mrr_at_1000 value: 35.705 - type: mrr_at_3 value: 32.09 - type: mrr_at_5 value: 33.52 - type: ndcg_at_1 value: 25.871 - type: ndcg_at_10 value: 35.617 - type: ndcg_at_100 value: 41.272999999999996 - type: ndcg_at_1000 value: 43.725 - type: ndcg_at_3 value: 30.653999999999996 - type: ndcg_at_5 value: 32.714 - type: precision_at_1 value: 25.871 - type: precision_at_10 value: 6.4799999999999995 - type: precision_at_100 value: 1.0699999999999998 - type: precision_at_1000 value: 0.13999999999999999 - type: precision_at_3 value: 14.469000000000001 - type: precision_at_5 value: 10.274 - type: recall_at_1 value: 21.336 - type: recall_at_10 value: 47.746 - type: recall_at_100 value: 71.773 - type: recall_at_1000 value: 89.05199999999999 - type: recall_at_3 value: 34.172999999999995 - type: recall_at_5 value: 39.397999999999996 - task: type: Retrieval dataset: name: MTEB CQADupstackPhysicsRetrieval type: mteb/cqadupstack-physics config: default split: test revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4 metrics: - type: map_at_1 value: 34.424 - type: map_at_10 value: 45.647999999999996 - type: map_at_100 value: 46.907 - type: map_at_1000 value: 47.010999999999996 - type: map_at_3 value: 42.427 - type: map_at_5 value: 44.285000000000004 - type: mrr_at_1 value: 41.867 - type: mrr_at_10 value: 51.17699999999999 - type: mrr_at_100 value: 51.937 - type: mrr_at_1000 value: 51.975 - type: mrr_at_3 value: 48.941 - type: mrr_at_5 value: 50.322 - type: ndcg_at_1 value: 41.867 - type: ndcg_at_10 value: 51.534 - type: ndcg_at_100 value: 56.696999999999996 - type: ndcg_at_1000 value: 58.475 - type: ndcg_at_3 value: 46.835 - type: ndcg_at_5 value: 49.161 - type: precision_at_1 value: 41.867 - type: precision_at_10 value: 9.134 - type: precision_at_100 value: 1.362 - type: precision_at_1000 value: 0.17099999999999999 - type: precision_at_3 value: 22.073 - type: precision_at_5 value: 15.495999999999999 - type: recall_at_1 value: 34.424 - type: recall_at_10 value: 63.237 - type: recall_at_100 value: 84.774 - type: recall_at_1000 value: 95.987 - type: recall_at_3 value: 49.888 - type: recall_at_5 value: 55.940999999999995 - task: type: Retrieval dataset: name: MTEB CQADupstackProgrammersRetrieval type: mteb/cqadupstack-programmers config: default split: test revision: 6184bc1440d2dbc7612be22b50686b8826d22b32 metrics: - type: map_at_1 value: 30.72 - type: map_at_10 value: 41.327999999999996 - type: map_at_100 value: 42.651 - type: map_at_1000 value: 42.739 - type: map_at_3 value: 38.223 - type: map_at_5 value: 40.053 - type: mrr_at_1 value: 37.9 - type: mrr_at_10 value: 46.857 - type: mrr_at_100 value: 47.673 - type: mrr_at_1000 value: 47.711999999999996 - type: mrr_at_3 value: 44.292 - type: mrr_at_5 value: 45.845 - type: ndcg_at_1 value: 37.9 - type: ndcg_at_10 value: 47.105999999999995 - type: ndcg_at_100 value: 52.56999999999999 - type: ndcg_at_1000 value: 54.37800000000001 - type: ndcg_at_3 value: 42.282 - type: ndcg_at_5 value: 44.646 - type: precision_at_1 value: 37.9 - type: precision_at_10 value: 8.368 - type: precision_at_100 value: 1.283 - type: precision_at_1000 value: 0.16 - type: precision_at_3 value: 20.015 - type: precision_at_5 value: 14.132 - type: recall_at_1 value: 30.72 - type: recall_at_10 value: 58.826 - type: recall_at_100 value: 82.104 - type: recall_at_1000 value: 94.194 - type: recall_at_3 value: 44.962999999999994 - type: recall_at_5 value: 51.426 - task: type: Retrieval dataset: name: MTEB CQADupstackRetrieval type: mteb/cqadupstack config: default split: test revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: map_at_1 value: 31.656583333333334 - type: map_at_10 value: 41.59883333333333 - type: map_at_100 value: 42.80350000000001 - type: map_at_1000 value: 42.91075 - type: map_at_3 value: 38.68908333333333 - type: map_at_5 value: 40.27733333333334 - type: mrr_at_1 value: 37.23483333333334 - type: mrr_at_10 value: 45.782000000000004 - type: mrr_at_100 value: 46.577083333333334 - type: mrr_at_1000 value: 46.62516666666667 - type: mrr_at_3 value: 43.480666666666664 - type: mrr_at_5 value: 44.79833333333333 - type: ndcg_at_1 value: 37.23483333333334 - type: ndcg_at_10 value: 46.971500000000006 - type: ndcg_at_100 value: 51.90125 - type: ndcg_at_1000 value: 53.86366666666667 - type: ndcg_at_3 value: 42.31791666666667 - type: ndcg_at_5 value: 44.458666666666666 - type: precision_at_1 value: 37.23483333333334 - type: precision_at_10 value: 8.044583333333332 - type: precision_at_100 value: 1.2334166666666666 - type: precision_at_1000 value: 0.15925 - type: precision_at_3 value: 19.240833333333327 - type: precision_at_5 value: 13.435083333333333 - type: recall_at_1 value: 31.656583333333334 - type: recall_at_10 value: 58.44758333333333 - type: recall_at_100 value: 79.93658333333332 - type: recall_at_1000 value: 93.32491666666668 - type: recall_at_3 value: 45.44266666666667 - type: recall_at_5 value: 50.99866666666666 - task: type: Retrieval dataset: name: MTEB CQADupstackStatsRetrieval type: mteb/cqadupstack-stats config: default split: test revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a metrics: - type: map_at_1 value: 28.247 - type: map_at_10 value: 35.443999999999996 - type: map_at_100 value: 36.578 - type: map_at_1000 value: 36.675999999999995 - type: map_at_3 value: 33.276 - type: map_at_5 value: 34.536 - type: mrr_at_1 value: 31.747999999999998 - type: mrr_at_10 value: 38.413000000000004 - type: mrr_at_100 value: 39.327 - type: mrr_at_1000 value: 39.389 - type: mrr_at_3 value: 36.401 - type: mrr_at_5 value: 37.543 - type: ndcg_at_1 value: 31.747999999999998 - type: ndcg_at_10 value: 39.646 - type: ndcg_at_100 value: 44.861000000000004 - type: ndcg_at_1000 value: 47.197 - type: ndcg_at_3 value: 35.764 - type: ndcg_at_5 value: 37.635999999999996 - type: precision_at_1 value: 31.747999999999998 - type: precision_at_10 value: 6.12 - type: precision_at_100 value: 0.942 - type: precision_at_1000 value: 0.123 - type: precision_at_3 value: 15.235000000000001 - type: precision_at_5 value: 10.491 - type: recall_at_1 value: 28.247 - type: recall_at_10 value: 49.456 - type: recall_at_100 value: 73.02499999999999 - type: recall_at_1000 value: 89.898 - type: recall_at_3 value: 38.653999999999996 - type: recall_at_5 value: 43.259 - task: type: Retrieval dataset: name: MTEB CQADupstackTexRetrieval type: mteb/cqadupstack-tex config: default split: test revision: 46989137a86843e03a6195de44b09deda022eec7 metrics: - type: map_at_1 value: 22.45 - type: map_at_10 value: 30.476999999999997 - type: map_at_100 value: 31.630999999999997 - type: map_at_1000 value: 31.755 - type: map_at_3 value: 27.989000000000004 - type: map_at_5 value: 29.410999999999998 - type: mrr_at_1 value: 26.979 - type: mrr_at_10 value: 34.316 - type: mrr_at_100 value: 35.272999999999996 - type: mrr_at_1000 value: 35.342 - type: mrr_at_3 value: 32.14 - type: mrr_at_5 value: 33.405 - type: ndcg_at_1 value: 26.979 - type: ndcg_at_10 value: 35.166 - type: ndcg_at_100 value: 40.583000000000006 - type: ndcg_at_1000 value: 43.282 - type: ndcg_at_3 value: 30.916 - type: ndcg_at_5 value: 32.973 - type: precision_at_1 value: 26.979 - type: precision_at_10 value: 6.132 - type: precision_at_100 value: 1.047 - type: precision_at_1000 value: 0.145 - type: precision_at_3 value: 14.360999999999999 - type: precision_at_5 value: 10.227 - type: recall_at_1 value: 22.45 - type: recall_at_10 value: 45.348 - type: recall_at_100 value: 69.484 - type: recall_at_1000 value: 88.628 - type: recall_at_3 value: 33.338 - type: recall_at_5 value: 38.746 - task: type: Retrieval dataset: name: MTEB CQADupstackUnixRetrieval type: mteb/cqadupstack-unix config: default split: test revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53 metrics: - type: map_at_1 value: 32.123000000000005 - type: map_at_10 value: 41.778 - type: map_at_100 value: 42.911 - type: map_at_1000 value: 42.994 - type: map_at_3 value: 38.558 - type: map_at_5 value: 40.318 - type: mrr_at_1 value: 37.687 - type: mrr_at_10 value: 45.889 - type: mrr_at_100 value: 46.672999999999995 - type: mrr_at_1000 value: 46.72 - type: mrr_at_3 value: 43.33 - type: mrr_at_5 value: 44.734 - type: ndcg_at_1 value: 37.687 - type: ndcg_at_10 value: 47.258 - type: ndcg_at_100 value: 52.331 - type: ndcg_at_1000 value: 54.152 - type: ndcg_at_3 value: 41.857 - type: ndcg_at_5 value: 44.283 - type: precision_at_1 value: 37.687 - type: precision_at_10 value: 7.892 - type: precision_at_100 value: 1.183 - type: precision_at_1000 value: 0.14300000000000002 - type: precision_at_3 value: 18.781 - type: precision_at_5 value: 13.134 - type: recall_at_1 value: 32.123000000000005 - type: recall_at_10 value: 59.760000000000005 - type: recall_at_100 value: 81.652 - type: recall_at_1000 value: 94.401 - type: recall_at_3 value: 44.996 - type: recall_at_5 value: 51.184 - task: type: Retrieval dataset: name: MTEB CQADupstackWebmastersRetrieval type: mteb/cqadupstack-webmasters config: default split: test revision: 160c094312a0e1facb97e55eeddb698c0abe3571 metrics: - type: map_at_1 value: 33.196999999999996 - type: map_at_10 value: 42.012 - type: map_at_100 value: 43.663999999999994 - type: map_at_1000 value: 43.883 - type: map_at_3 value: 39.33 - type: map_at_5 value: 40.586 - type: mrr_at_1 value: 39.328 - type: mrr_at_10 value: 46.57 - type: mrr_at_100 value: 47.508 - type: mrr_at_1000 value: 47.558 - type: mrr_at_3 value: 44.532 - type: mrr_at_5 value: 45.58 - type: ndcg_at_1 value: 39.328 - type: ndcg_at_10 value: 47.337 - type: ndcg_at_100 value: 52.989 - type: ndcg_at_1000 value: 55.224 - type: ndcg_at_3 value: 43.362 - type: ndcg_at_5 value: 44.866 - type: precision_at_1 value: 39.328 - type: precision_at_10 value: 8.577 - type: precision_at_100 value: 1.5789999999999997 - type: precision_at_1000 value: 0.25 - type: precision_at_3 value: 19.697 - type: precision_at_5 value: 13.755 - type: recall_at_1 value: 33.196999999999996 - type: recall_at_10 value: 56.635000000000005 - type: recall_at_100 value: 81.882 - type: recall_at_1000 value: 95.342 - type: recall_at_3 value: 44.969 - type: recall_at_5 value: 49.266 - task: type: Retrieval dataset: name: MTEB CQADupstackWordpressRetrieval type: mteb/cqadupstack-wordpress config: default split: test revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: map_at_1 value: 26.901000000000003 - type: map_at_10 value: 35.77 - type: map_at_100 value: 36.638999999999996 - type: map_at_1000 value: 36.741 - type: map_at_3 value: 33.219 - type: map_at_5 value: 34.574 - type: mrr_at_1 value: 29.205 - type: mrr_at_10 value: 37.848 - type: mrr_at_100 value: 38.613 - type: mrr_at_1000 value: 38.682 - type: mrr_at_3 value: 35.551 - type: mrr_at_5 value: 36.808 - type: ndcg_at_1 value: 29.205 - type: ndcg_at_10 value: 40.589 - type: ndcg_at_100 value: 45.171 - type: ndcg_at_1000 value: 47.602 - type: ndcg_at_3 value: 35.760999999999996 - type: ndcg_at_5 value: 37.980000000000004 - type: precision_at_1 value: 29.205 - type: precision_at_10 value: 6.192 - type: precision_at_100 value: 0.922 - type: precision_at_1000 value: 0.123 - type: precision_at_3 value: 15.034 - type: precision_at_5 value: 10.424999999999999 - type: recall_at_1 value: 26.901000000000003 - type: recall_at_10 value: 53.236000000000004 - type: recall_at_100 value: 74.809 - type: recall_at_1000 value: 92.884 - type: recall_at_3 value: 40.314 - type: recall_at_5 value: 45.617999999999995 - task: type: Retrieval dataset: name: MTEB ClimateFEVER type: mteb/climate-fever config: default split: test revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 metrics: - type: map_at_1 value: 16.794999999999998 - type: map_at_10 value: 29.322 - type: map_at_100 value: 31.463 - type: map_at_1000 value: 31.643 - type: map_at_3 value: 24.517 - type: map_at_5 value: 27.237000000000002 - type: mrr_at_1 value: 37.655 - type: mrr_at_10 value: 50.952 - type: mrr_at_100 value: 51.581999999999994 - type: mrr_at_1000 value: 51.61 - type: mrr_at_3 value: 47.991 - type: mrr_at_5 value: 49.744 - type: ndcg_at_1 value: 37.655 - type: ndcg_at_10 value: 39.328 - type: ndcg_at_100 value: 46.358 - type: ndcg_at_1000 value: 49.245 - type: ndcg_at_3 value: 33.052 - type: ndcg_at_5 value: 35.407 - type: precision_at_1 value: 37.655 - type: precision_at_10 value: 12.202 - type: precision_at_100 value: 1.9789999999999999 - type: precision_at_1000 value: 0.252 - type: precision_at_3 value: 24.973 - type: precision_at_5 value: 19.075 - type: recall_at_1 value: 16.794999999999998 - type: recall_at_10 value: 45.716 - type: recall_at_100 value: 68.919 - type: recall_at_1000 value: 84.71600000000001 - type: recall_at_3 value: 30.135 - type: recall_at_5 value: 37.141999999999996 - task: type: Retrieval dataset: name: MTEB DBPedia type: mteb/dbpedia config: default split: test revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 metrics: - type: map_at_1 value: 9.817 - type: map_at_10 value: 22.058 - type: map_at_100 value: 31.805 - type: map_at_1000 value: 33.562999999999995 - type: map_at_3 value: 15.537 - type: map_at_5 value: 18.199 - type: mrr_at_1 value: 72.75 - type: mrr_at_10 value: 79.804 - type: mrr_at_100 value: 80.089 - type: mrr_at_1000 value: 80.09100000000001 - type: mrr_at_3 value: 78.75 - type: mrr_at_5 value: 79.325 - type: ndcg_at_1 value: 59.875 - type: ndcg_at_10 value: 45.972 - type: ndcg_at_100 value: 51.092999999999996 - type: ndcg_at_1000 value: 58.048 - type: ndcg_at_3 value: 50.552 - type: ndcg_at_5 value: 47.672 - type: precision_at_1 value: 72.75 - type: precision_at_10 value: 37.05 - type: precision_at_100 value: 12.005 - type: precision_at_1000 value: 2.221 - type: precision_at_3 value: 54.083000000000006 - type: precision_at_5 value: 46.2 - type: recall_at_1 value: 9.817 - type: recall_at_10 value: 27.877000000000002 - type: recall_at_100 value: 57.974000000000004 - type: recall_at_1000 value: 80.085 - type: recall_at_3 value: 16.911 - type: recall_at_5 value: 20.689 - task: type: Classification dataset: name: MTEB EmotionClassification type: mteb/emotion config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 46.464999999999996 - type: f1 value: 42.759588662873796 - task: type: Retrieval dataset: name: MTEB FEVER type: mteb/fever config: default split: test revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 metrics: - type: map_at_1 value: 75.82900000000001 - type: map_at_10 value: 84.613 - type: map_at_100 value: 84.845 - type: map_at_1000 value: 84.855 - type: map_at_3 value: 83.498 - type: map_at_5 value: 84.29299999999999 - type: mrr_at_1 value: 81.69800000000001 - type: mrr_at_10 value: 88.84100000000001 - type: mrr_at_100 value: 88.887 - type: mrr_at_1000 value: 88.888 - type: mrr_at_3 value: 88.179 - type: mrr_at_5 value: 88.69200000000001 - type: ndcg_at_1 value: 81.69800000000001 - type: ndcg_at_10 value: 88.21799999999999 - type: ndcg_at_100 value: 88.961 - type: ndcg_at_1000 value: 89.131 - type: ndcg_at_3 value: 86.591 - type: ndcg_at_5 value: 87.666 - type: precision_at_1 value: 81.69800000000001 - type: precision_at_10 value: 10.615 - type: precision_at_100 value: 1.125 - type: precision_at_1000 value: 0.11499999999999999 - type: precision_at_3 value: 33.208 - type: precision_at_5 value: 20.681 - type: recall_at_1 value: 75.82900000000001 - type: recall_at_10 value: 94.97 - type: recall_at_100 value: 97.786 - type: recall_at_1000 value: 98.809 - type: recall_at_3 value: 90.625 - type: recall_at_5 value: 93.345 - task: type: Retrieval dataset: name: MTEB FiQA2018 type: mteb/fiqa config: default split: test revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: map_at_1 value: 22.788 - type: map_at_10 value: 36.71 - type: map_at_100 value: 38.527 - type: map_at_1000 value: 38.701 - type: map_at_3 value: 32.318999999999996 - type: map_at_5 value: 34.809 - type: mrr_at_1 value: 44.444 - type: mrr_at_10 value: 52.868 - type: mrr_at_100 value: 53.52400000000001 - type: mrr_at_1000 value: 53.559999999999995 - type: mrr_at_3 value: 50.153999999999996 - type: mrr_at_5 value: 51.651 - type: ndcg_at_1 value: 44.444 - type: ndcg_at_10 value: 44.707 - type: ndcg_at_100 value: 51.174 - type: ndcg_at_1000 value: 53.996 - type: ndcg_at_3 value: 40.855999999999995 - type: ndcg_at_5 value: 42.113 - type: precision_at_1 value: 44.444 - type: precision_at_10 value: 12.021999999999998 - type: precision_at_100 value: 1.8950000000000002 - type: precision_at_1000 value: 0.241 - type: precision_at_3 value: 26.8 - type: precision_at_5 value: 19.66 - type: recall_at_1 value: 22.788 - type: recall_at_10 value: 51.793 - type: recall_at_100 value: 75.69500000000001 - type: recall_at_1000 value: 92.292 - type: recall_at_3 value: 37.375 - type: recall_at_5 value: 43.682 - task: type: Retrieval dataset: name: MTEB HotpotQA type: mteb/hotpotqa config: default split: test revision: ab518f4d6fcca38d87c25209f94beba119d02014 metrics: - type: map_at_1 value: 41.276 - type: map_at_10 value: 67.245 - type: map_at_100 value: 68.061 - type: map_at_1000 value: 68.11399999999999 - type: map_at_3 value: 63.693 - type: map_at_5 value: 65.90899999999999 - type: mrr_at_1 value: 82.552 - type: mrr_at_10 value: 87.741 - type: mrr_at_100 value: 87.868 - type: mrr_at_1000 value: 87.871 - type: mrr_at_3 value: 86.98599999999999 - type: mrr_at_5 value: 87.469 - type: ndcg_at_1 value: 82.552 - type: ndcg_at_10 value: 75.176 - type: ndcg_at_100 value: 77.902 - type: ndcg_at_1000 value: 78.852 - type: ndcg_at_3 value: 70.30499999999999 - type: ndcg_at_5 value: 73.00999999999999 - type: precision_at_1 value: 82.552 - type: precision_at_10 value: 15.765 - type: precision_at_100 value: 1.788 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 45.375 - type: precision_at_5 value: 29.360999999999997 - type: recall_at_1 value: 41.276 - type: recall_at_10 value: 78.825 - type: recall_at_100 value: 89.41900000000001 - type: recall_at_1000 value: 95.625 - type: recall_at_3 value: 68.062 - type: recall_at_5 value: 73.40299999999999 - task: type: Classification dataset: name: MTEB ImdbClassification type: mteb/imdb config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 72.876 - type: ap value: 67.15477852410164 - type: f1 value: 72.65147370025373 - task: type: Retrieval dataset: name: MTEB MSMARCO type: mteb/msmarco config: default split: dev revision: c5a29a104738b98a9e76336939199e264163d4a0 metrics: - type: map_at_1 value: 21.748 - type: map_at_10 value: 34.626000000000005 - type: map_at_100 value: 35.813 - type: map_at_1000 value: 35.859 - type: map_at_3 value: 30.753000000000004 - type: map_at_5 value: 33.049 - type: mrr_at_1 value: 22.35 - type: mrr_at_10 value: 35.23 - type: mrr_at_100 value: 36.359 - type: mrr_at_1000 value: 36.399 - type: mrr_at_3 value: 31.436999999999998 - type: mrr_at_5 value: 33.687 - type: ndcg_at_1 value: 22.364 - type: ndcg_at_10 value: 41.677 - type: ndcg_at_100 value: 47.355999999999995 - type: ndcg_at_1000 value: 48.494 - type: ndcg_at_3 value: 33.85 - type: ndcg_at_5 value: 37.942 - type: precision_at_1 value: 22.364 - type: precision_at_10 value: 6.6000000000000005 - type: precision_at_100 value: 0.9450000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 14.527000000000001 - type: precision_at_5 value: 10.796999999999999 - type: recall_at_1 value: 21.748 - type: recall_at_10 value: 63.292 - type: recall_at_100 value: 89.427 - type: recall_at_1000 value: 98.13499999999999 - type: recall_at_3 value: 42.126000000000005 - type: recall_at_5 value: 51.968 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 92.62425900592795 - type: f1 value: 92.08497761553683 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 64.51436388508893 - type: f1 value: 45.884016531912906 - task: type: Classification dataset: name: MTEB MasakhaNEWSClassification (eng) type: masakhane/masakhanews config: eng split: test revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60 metrics: - type: accuracy value: 76.57172995780591 - type: f1 value: 75.52979910878491 - task: type: Clustering dataset: name: MTEB MasakhaNEWSClusteringP2P (eng) type: masakhane/masakhanews config: eng split: test revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60 metrics: - type: v_measure value: 44.84052695201612 - type: v_measure value: 21.443971229936494 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 65.79354404841965 - type: f1 value: 63.17260074126185 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 71.09616677874916 - type: f1 value: 69.74285784421075 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P type: mteb/medrxiv-clustering-p2p config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 31.474709231086184 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S type: mteb/medrxiv-clustering-s2s config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 28.93630367824217 - task: type: Reranking dataset: name: MTEB MindSmallReranking type: mteb/mind_small config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 29.08234393834005 - type: mrr value: 29.740466971605432 - task: type: Retrieval dataset: name: MTEB NFCorpus type: mteb/nfcorpus config: default split: test revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 metrics: - type: map_at_1 value: 6.2059999999999995 - type: map_at_10 value: 14.442 - type: map_at_100 value: 18.005 - type: map_at_1000 value: 19.488 - type: map_at_3 value: 10.666 - type: map_at_5 value: 12.45 - type: mrr_at_1 value: 47.678 - type: mrr_at_10 value: 57.519 - type: mrr_at_100 value: 58.13700000000001 - type: mrr_at_1000 value: 58.167 - type: mrr_at_3 value: 55.779 - type: mrr_at_5 value: 56.940000000000005 - type: ndcg_at_1 value: 45.82 - type: ndcg_at_10 value: 37.651 - type: ndcg_at_100 value: 34.001999999999995 - type: ndcg_at_1000 value: 42.626 - type: ndcg_at_3 value: 43.961 - type: ndcg_at_5 value: 41.461 - type: precision_at_1 value: 47.678 - type: precision_at_10 value: 27.584999999999997 - type: precision_at_100 value: 8.455 - type: precision_at_1000 value: 2.118 - type: precision_at_3 value: 41.692 - type: precision_at_5 value: 36.161 - type: recall_at_1 value: 6.2059999999999995 - type: recall_at_10 value: 18.599 - type: recall_at_100 value: 33.608 - type: recall_at_1000 value: 65.429 - type: recall_at_3 value: 12.126000000000001 - type: recall_at_5 value: 14.902000000000001 - task: type: Retrieval dataset: name: MTEB NQ type: mteb/nq config: default split: test revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 metrics: - type: map_at_1 value: 39.117000000000004 - type: map_at_10 value: 55.535000000000004 - type: map_at_100 value: 56.32899999999999 - type: map_at_1000 value: 56.34400000000001 - type: map_at_3 value: 51.439 - type: map_at_5 value: 53.89699999999999 - type: mrr_at_1 value: 43.714 - type: mrr_at_10 value: 58.05200000000001 - type: mrr_at_100 value: 58.582 - type: mrr_at_1000 value: 58.592 - type: mrr_at_3 value: 54.896 - type: mrr_at_5 value: 56.874 - type: ndcg_at_1 value: 43.685 - type: ndcg_at_10 value: 63.108 - type: ndcg_at_100 value: 66.231 - type: ndcg_at_1000 value: 66.583 - type: ndcg_at_3 value: 55.659000000000006 - type: ndcg_at_5 value: 59.681 - type: precision_at_1 value: 43.685 - type: precision_at_10 value: 9.962 - type: precision_at_100 value: 1.174 - type: precision_at_1000 value: 0.121 - type: precision_at_3 value: 24.961 - type: precision_at_5 value: 17.352 - type: recall_at_1 value: 39.117000000000004 - type: recall_at_10 value: 83.408 - type: recall_at_100 value: 96.553 - type: recall_at_1000 value: 99.136 - type: recall_at_3 value: 64.364 - type: recall_at_5 value: 73.573 - task: type: Classification dataset: name: MTEB NewsClassification type: ag_news config: default split: test revision: eb185aade064a813bc0b7f42de02595523103ca4 metrics: - type: accuracy value: 78.87763157894737 - type: f1 value: 78.69611753876177 - task: type: PairClassification dataset: name: MTEB OpusparcusPC (en) type: GEM/opusparcus config: en split: test revision: 9e9b1f8ef51616073f47f306f7f47dd91663f86a metrics: - type: cos_sim_accuracy value: 99.89816700610999 - type: cos_sim_ap value: 100 - type: cos_sim_f1 value: 99.9490575649516 - type: cos_sim_precision value: 100 - type: cos_sim_recall value: 99.89816700610999 - type: dot_accuracy value: 99.89816700610999 - type: dot_ap value: 100 - type: dot_f1 value: 99.9490575649516 - type: dot_precision value: 100 - type: dot_recall value: 99.89816700610999 - type: euclidean_accuracy value: 99.89816700610999 - type: euclidean_ap value: 100 - type: euclidean_f1 value: 99.9490575649516 - type: euclidean_precision value: 100 - type: euclidean_recall value: 99.89816700610999 - type: manhattan_accuracy value: 99.89816700610999 - type: manhattan_ap value: 100 - type: manhattan_f1 value: 99.9490575649516 - type: manhattan_precision value: 100 - type: manhattan_recall value: 99.89816700610999 - type: max_accuracy value: 99.89816700610999 - type: max_ap value: 100 - type: max_f1 value: 99.9490575649516 - task: type: PairClassification dataset: name: MTEB PawsX (en) type: paws-x config: en split: test revision: 8a04d940a42cd40658986fdd8e3da561533a3646 metrics: - type: cos_sim_accuracy value: 62 - type: cos_sim_ap value: 62.26837791655737 - type: cos_sim_f1 value: 62.607449856733524 - type: cos_sim_precision value: 46.36604774535809 - type: cos_sim_recall value: 96.36163175303197 - type: dot_accuracy value: 62 - type: dot_ap value: 62.26736459439965 - type: dot_f1 value: 62.607449856733524 - type: dot_precision value: 46.36604774535809 - type: dot_recall value: 96.36163175303197 - type: euclidean_accuracy value: 62 - type: euclidean_ap value: 62.26826112548132 - type: euclidean_f1 value: 62.607449856733524 - type: euclidean_precision value: 46.36604774535809 - type: euclidean_recall value: 96.36163175303197 - type: manhattan_accuracy value: 62 - type: manhattan_ap value: 62.26223761507973 - type: manhattan_f1 value: 62.585034013605444 - type: manhattan_precision value: 46.34146341463415 - type: manhattan_recall value: 96.36163175303197 - type: max_accuracy value: 62 - type: max_ap value: 62.26837791655737 - type: max_f1 value: 62.607449856733524 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval type: mteb/quora config: default split: test revision: e4e08e0b7dbe3c8700f0daef558ff32256715259 metrics: - type: map_at_1 value: 69.90899999999999 - type: map_at_10 value: 83.56700000000001 - type: map_at_100 value: 84.19200000000001 - type: map_at_1000 value: 84.212 - type: map_at_3 value: 80.658 - type: map_at_5 value: 82.473 - type: mrr_at_1 value: 80.4 - type: mrr_at_10 value: 86.699 - type: mrr_at_100 value: 86.798 - type: mrr_at_1000 value: 86.80099999999999 - type: mrr_at_3 value: 85.677 - type: mrr_at_5 value: 86.354 - type: ndcg_at_1 value: 80.43 - type: ndcg_at_10 value: 87.41 - type: ndcg_at_100 value: 88.653 - type: ndcg_at_1000 value: 88.81599999999999 - type: ndcg_at_3 value: 84.516 - type: ndcg_at_5 value: 86.068 - type: precision_at_1 value: 80.43 - type: precision_at_10 value: 13.234000000000002 - type: precision_at_100 value: 1.513 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 36.93 - type: precision_at_5 value: 24.26 - type: recall_at_1 value: 69.90899999999999 - type: recall_at_10 value: 94.687 - type: recall_at_100 value: 98.96000000000001 - type: recall_at_1000 value: 99.79599999999999 - type: recall_at_3 value: 86.25699999999999 - type: recall_at_5 value: 90.70700000000001 - task: type: Clustering dataset: name: MTEB RedditClustering type: mteb/reddit-clustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 46.02256865360266 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P type: mteb/reddit-clustering-p2p config: default split: test revision: 385e3cb46b4cfa89021f56c4380204149d0efe33 metrics: - type: v_measure value: 62.43157528757563 - task: type: Retrieval dataset: name: MTEB SCIDOCS type: mteb/scidocs config: default split: test revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88 metrics: - type: map_at_1 value: 5.093 - type: map_at_10 value: 12.982 - type: map_at_100 value: 15.031 - type: map_at_1000 value: 15.334 - type: map_at_3 value: 9.339 - type: map_at_5 value: 11.183 - type: mrr_at_1 value: 25.1 - type: mrr_at_10 value: 36.257 - type: mrr_at_100 value: 37.351 - type: mrr_at_1000 value: 37.409 - type: mrr_at_3 value: 33.050000000000004 - type: mrr_at_5 value: 35.205 - type: ndcg_at_1 value: 25.1 - type: ndcg_at_10 value: 21.361 - type: ndcg_at_100 value: 29.396 - type: ndcg_at_1000 value: 34.849999999999994 - type: ndcg_at_3 value: 20.704 - type: ndcg_at_5 value: 18.086 - type: precision_at_1 value: 25.1 - type: precision_at_10 value: 10.94 - type: precision_at_100 value: 2.257 - type: precision_at_1000 value: 0.358 - type: precision_at_3 value: 19.467000000000002 - type: precision_at_5 value: 15.98 - type: recall_at_1 value: 5.093 - type: recall_at_10 value: 22.177 - type: recall_at_100 value: 45.842 - type: recall_at_1000 value: 72.598 - type: recall_at_3 value: 11.833 - type: recall_at_5 value: 16.173000000000002 - task: type: STS dataset: name: MTEB SICK-R type: mteb/sickr-sts config: default split: test revision: 20a6d6f312dd54037fe07a32d58e5e168867909d metrics: - type: cos_sim_pearson value: 73.56535226754596 - type: cos_sim_spearman value: 69.32425977603488 - type: euclidean_pearson value: 71.32425703470898 - type: euclidean_spearman value: 69.32425217267013 - type: manhattan_pearson value: 71.25897281394246 - type: manhattan_spearman value: 69.27132577049578 - task: type: STS dataset: name: MTEB STS12 type: mteb/sts12-sts config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 69.66387868726018 - type: cos_sim_spearman value: 67.85470749045027 - type: euclidean_pearson value: 66.62075098063795 - type: euclidean_spearman value: 67.85470749045027 - type: manhattan_pearson value: 66.61455061901262 - type: manhattan_spearman value: 67.87229618498695 - task: type: STS dataset: name: MTEB STS13 type: mteb/sts13-sts config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 75.65731331392575 - type: cos_sim_spearman value: 77.48991626780108 - type: euclidean_pearson value: 77.19884738623692 - type: euclidean_spearman value: 77.48985836619045 - type: manhattan_pearson value: 77.0656684243772 - type: manhattan_spearman value: 77.30289226582691 - task: type: STS dataset: name: MTEB STS14 type: mteb/sts14-sts config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 69.37003253666457 - type: cos_sim_spearman value: 69.77157648098141 - type: euclidean_pearson value: 69.39543876030432 - type: euclidean_spearman value: 69.77157648098141 - type: manhattan_pearson value: 69.29901600459745 - type: manhattan_spearman value: 69.65074167527128 - task: type: STS dataset: name: MTEB STS15 type: mteb/sts15-sts config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 78.56777256540136 - type: cos_sim_spearman value: 80.16458787843023 - type: euclidean_pearson value: 80.16475730686916 - type: euclidean_spearman value: 80.16458787843023 - type: manhattan_pearson value: 80.12814463670401 - type: manhattan_spearman value: 80.1357907984809 - task: type: STS dataset: name: MTEB STS16 type: mteb/sts16-sts config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 76.09572350919031 - type: cos_sim_spearman value: 77.94490233429326 - type: euclidean_pearson value: 78.36595251203524 - type: euclidean_spearman value: 77.94490233429326 - type: manhattan_pearson value: 78.41538768125166 - type: manhattan_spearman value: 78.01244379569542 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 80.7843552187951 - type: cos_sim_spearman value: 82.28085055047386 - type: euclidean_pearson value: 82.37373672515267 - type: euclidean_spearman value: 82.28085055047386 - type: manhattan_pearson value: 82.39387241346917 - type: manhattan_spearman value: 82.36503339515906 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson value: 68.29963929962095 - type: cos_sim_spearman value: 67.96868942546051 - type: euclidean_pearson value: 68.93524903869285 - type: euclidean_spearman value: 67.96868942546051 - type: manhattan_pearson value: 68.79144468444811 - type: manhattan_spearman value: 67.69311483884324 - task: type: STS dataset: name: MTEB STSBenchmark type: mteb/stsbenchmark-sts config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 72.84789696700685 - type: cos_sim_spearman value: 75.67875747588545 - type: euclidean_pearson value: 75.07752300463038 - type: euclidean_spearman value: 75.67875747588545 - type: manhattan_pearson value: 74.97934248140928 - type: manhattan_spearman value: 75.62525644178724 - task: type: STS dataset: name: MTEB STSBenchmarkMultilingualSTS (en) type: PhilipMay/stsb_multi_mt config: en split: test revision: 93d57ef91790589e3ce9c365164337a8a78b7632 metrics: - type: cos_sim_pearson value: 72.84789702519309 - type: cos_sim_spearman value: 75.67875747588545 - type: euclidean_pearson value: 75.07752310061133 - type: euclidean_spearman value: 75.67875747588545 - type: manhattan_pearson value: 74.97934257159595 - type: manhattan_spearman value: 75.62525644178724 - task: type: Reranking dataset: name: MTEB SciDocsRR type: mteb/scidocs-reranking config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 81.55557720431086 - type: mrr value: 94.91178665198272 - task: type: Retrieval dataset: name: MTEB SciFact type: mteb/scifact config: default split: test revision: 0228b52cf27578f30900b9e5271d331663a030d7 metrics: - type: map_at_1 value: 59.260999999999996 - type: map_at_10 value: 69.36099999999999 - type: map_at_100 value: 69.868 - type: map_at_1000 value: 69.877 - type: map_at_3 value: 66.617 - type: map_at_5 value: 68.061 - type: mrr_at_1 value: 62.333000000000006 - type: mrr_at_10 value: 70.533 - type: mrr_at_100 value: 70.966 - type: mrr_at_1000 value: 70.975 - type: mrr_at_3 value: 68.667 - type: mrr_at_5 value: 69.717 - type: ndcg_at_1 value: 62.333000000000006 - type: ndcg_at_10 value: 73.82300000000001 - type: ndcg_at_100 value: 76.122 - type: ndcg_at_1000 value: 76.374 - type: ndcg_at_3 value: 69.27499999999999 - type: ndcg_at_5 value: 71.33 - type: precision_at_1 value: 62.333000000000006 - type: precision_at_10 value: 9.8 - type: precision_at_100 value: 1.097 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 26.889000000000003 - type: precision_at_5 value: 17.599999999999998 - type: recall_at_1 value: 59.260999999999996 - type: recall_at_10 value: 86.2 - type: recall_at_100 value: 96.667 - type: recall_at_1000 value: 98.667 - type: recall_at_3 value: 74.006 - type: recall_at_5 value: 79.167 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.81881188118813 - type: cos_sim_ap value: 95.20169041096409 - type: cos_sim_f1 value: 90.76224129227664 - type: cos_sim_precision value: 91.64118246687055 - type: cos_sim_recall value: 89.9 - type: dot_accuracy value: 99.81881188118813 - type: dot_ap value: 95.20169041096409 - type: dot_f1 value: 90.76224129227664 - type: dot_precision value: 91.64118246687055 - type: dot_recall value: 89.9 - type: euclidean_accuracy value: 99.81881188118813 - type: euclidean_ap value: 95.2016904109641 - type: euclidean_f1 value: 90.76224129227664 - type: euclidean_precision value: 91.64118246687055 - type: euclidean_recall value: 89.9 - type: manhattan_accuracy value: 99.81881188118813 - type: manhattan_ap value: 95.22680188132777 - type: manhattan_f1 value: 90.79013588324108 - type: manhattan_precision value: 91.38804457953394 - type: manhattan_recall value: 90.2 - type: max_accuracy value: 99.81881188118813 - type: max_ap value: 95.22680188132777 - type: max_f1 value: 90.79013588324108 - task: type: Clustering dataset: name: MTEB StackExchangeClustering type: mteb/stackexchange-clustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 57.8638628701308 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P type: mteb/stackexchange-clustering-p2p config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 37.82028248106046 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 50.870860210170946 - type: mrr value: 51.608084521687466 - task: type: Summarization dataset: name: MTEB SummEval type: mteb/summeval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 31.60384207444685 - type: cos_sim_spearman value: 30.84047452209471 - type: dot_pearson value: 31.60384104417333 - type: dot_spearman value: 30.84047452209471 - task: type: Retrieval dataset: name: MTEB TRECCOVID type: mteb/trec-covid config: default split: test revision: bb9466bac8153a0349341eb1b22e06409e78ef4e metrics: - type: map_at_1 value: 0.246 - type: map_at_10 value: 2.051 - type: map_at_100 value: 13.129 - type: map_at_1000 value: 31.56 - type: map_at_3 value: 0.681 - type: map_at_5 value: 1.105 - type: mrr_at_1 value: 94 - type: mrr_at_10 value: 97 - type: mrr_at_100 value: 97 - type: mrr_at_1000 value: 97 - type: mrr_at_3 value: 97 - type: mrr_at_5 value: 97 - type: ndcg_at_1 value: 87 - type: ndcg_at_10 value: 80.716 - type: ndcg_at_100 value: 63.83 - type: ndcg_at_1000 value: 56.215 - type: ndcg_at_3 value: 84.531 - type: ndcg_at_5 value: 84.777 - type: precision_at_1 value: 94 - type: precision_at_10 value: 84.6 - type: precision_at_100 value: 66.03999999999999 - type: precision_at_1000 value: 24.878 - type: precision_at_3 value: 88.667 - type: precision_at_5 value: 89.60000000000001 - type: recall_at_1 value: 0.246 - type: recall_at_10 value: 2.2079999999999997 - type: recall_at_100 value: 15.895999999999999 - type: recall_at_1000 value: 52.683 - type: recall_at_3 value: 0.7040000000000001 - type: recall_at_5 value: 1.163 - task: type: Retrieval dataset: name: MTEB Touche2020 type: mteb/touche2020 config: default split: test revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f metrics: - type: map_at_1 value: 3.852 - type: map_at_10 value: 14.316 - type: map_at_100 value: 20.982 - type: map_at_1000 value: 22.58 - type: map_at_3 value: 7.767 - type: map_at_5 value: 10.321 - type: mrr_at_1 value: 51.019999999999996 - type: mrr_at_10 value: 66.365 - type: mrr_at_100 value: 66.522 - type: mrr_at_1000 value: 66.522 - type: mrr_at_3 value: 62.925 - type: mrr_at_5 value: 64.762 - type: ndcg_at_1 value: 46.939 - type: ndcg_at_10 value: 34.516999999999996 - type: ndcg_at_100 value: 44.25 - type: ndcg_at_1000 value: 54.899 - type: ndcg_at_3 value: 40.203 - type: ndcg_at_5 value: 37.004 - type: precision_at_1 value: 51.019999999999996 - type: precision_at_10 value: 29.796 - type: precision_at_100 value: 8.633000000000001 - type: precision_at_1000 value: 1.584 - type: precision_at_3 value: 40.816 - type: precision_at_5 value: 35.918 - type: recall_at_1 value: 3.852 - type: recall_at_10 value: 20.891000000000002 - type: recall_at_100 value: 52.428 - type: recall_at_1000 value: 84.34899999999999 - type: recall_at_3 value: 8.834 - type: recall_at_5 value: 12.909 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification type: mteb/toxic_conversations_50k config: default split: test revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de metrics: - type: accuracy value: 64.7092 - type: ap value: 11.972915012305819 - type: f1 value: 49.91050149892115 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification type: mteb/tweet_sentiment_extraction config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 56.737408036219584 - type: f1 value: 57.07235266246011 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering type: mteb/twentynewsgroups-clustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 35.9147539025798 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 82.52369315133814 - type: cos_sim_ap value: 62.34858091376534 - type: cos_sim_f1 value: 58.18225190839694 - type: cos_sim_precision value: 53.09098824553766 - type: cos_sim_recall value: 64.35356200527704 - type: dot_accuracy value: 82.52369315133814 - type: dot_ap value: 62.34857753814992 - type: dot_f1 value: 58.18225190839694 - type: dot_precision value: 53.09098824553766 - type: dot_recall value: 64.35356200527704 - type: euclidean_accuracy value: 82.52369315133814 - type: euclidean_ap value: 62.34857756663386 - type: euclidean_f1 value: 58.18225190839694 - type: euclidean_precision value: 53.09098824553766 - type: euclidean_recall value: 64.35356200527704 - type: manhattan_accuracy value: 82.49389044525243 - type: manhattan_ap value: 62.32245347238179 - type: manhattan_f1 value: 58.206309819213054 - type: manhattan_precision value: 52.70704044511021 - type: manhattan_recall value: 64.9868073878628 - type: max_accuracy value: 82.52369315133814 - type: max_ap value: 62.34858091376534 - type: max_f1 value: 58.206309819213054 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 88.34555827220863 - type: cos_sim_ap value: 84.84152481680071 - type: cos_sim_f1 value: 76.860456739428 - type: cos_sim_precision value: 72.21470150263978 - type: cos_sim_recall value: 82.14505697566985 - type: dot_accuracy value: 88.34555827220863 - type: dot_ap value: 84.84152743322608 - type: dot_f1 value: 76.860456739428 - type: dot_precision value: 72.21470150263978 - type: dot_recall value: 82.14505697566985 - type: euclidean_accuracy value: 88.34555827220863 - type: euclidean_ap value: 84.84152589453169 - type: euclidean_f1 value: 76.860456739428 - type: euclidean_precision value: 72.21470150263978 - type: euclidean_recall value: 82.14505697566985 - type: manhattan_accuracy value: 88.38242713548337 - type: manhattan_ap value: 84.8112124970968 - type: manhattan_f1 value: 76.83599206057487 - type: manhattan_precision value: 73.51244900829934 - type: manhattan_recall value: 80.47428395441946 - type: max_accuracy value: 88.38242713548337 - type: max_ap value: 84.84152743322608 - type: max_f1 value: 76.860456739428 - task: type: Clustering dataset: name: MTEB WikiCitiesClustering type: jinaai/cities_wiki_clustering config: default split: test revision: ddc9ee9242fa65332597f70e967ecc38b9d734fa metrics: - type: v_measure value: 85.5314389263015 --- # radia/snowflake-arctic-embed-l-Q4_K_M-GGUF This model was converted to GGUF format from [`Snowflake/snowflake-arctic-embed-l`](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama --hf-repo radia/snowflake-arctic-embed-l-Q4_K_M-GGUF --hf-file snowflake-arctic-embed-l-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo radia/snowflake-arctic-embed-l-Q4_K_M-GGUF --hf-file snowflake-arctic-embed-l-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./main --hf-repo radia/snowflake-arctic-embed-l-Q4_K_M-GGUF --hf-file snowflake-arctic-embed-l-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./server --hf-repo radia/snowflake-arctic-embed-l-Q4_K_M-GGUF --hf-file snowflake-arctic-embed-l-q4_k_m.gguf -c 2048 ```
[ "BIOSSES", "SCIFACT" ]
RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf
RichardErkhov
null
[ "gguf", "endpoints_compatible", "region:us", "conversational" ]
2024-07-22T05:20:08Z
2024-07-22T07:01:42+00:00
31
0
--- {} --- Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) phi3-mini-context-ignore - GGUF - Model creator: https://huggingface.co/Satandon1999/ - Original model: https://huggingface.co/Satandon1999/phi3-mini-context-ignore/ | Name | Quant method | Size | | ---- | ---- | ---- | | [phi3-mini-context-ignore.Q2_K.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q2_K.gguf) | Q2_K | 1.32GB | | [phi3-mini-context-ignore.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.IQ3_XS.gguf) | IQ3_XS | 1.51GB | | [phi3-mini-context-ignore.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.IQ3_S.gguf) | IQ3_S | 1.57GB | | [phi3-mini-context-ignore.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q3_K_S.gguf) | Q3_K_S | 1.57GB | | [phi3-mini-context-ignore.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.IQ3_M.gguf) | IQ3_M | 1.73GB | | [phi3-mini-context-ignore.Q3_K.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q3_K.gguf) | Q3_K | 1.82GB | | [phi3-mini-context-ignore.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q3_K_M.gguf) | Q3_K_M | 1.82GB | | [phi3-mini-context-ignore.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q3_K_L.gguf) | Q3_K_L | 1.94GB | | [phi3-mini-context-ignore.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.IQ4_XS.gguf) | IQ4_XS | 1.93GB | | [phi3-mini-context-ignore.Q4_0.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q4_0.gguf) | Q4_0 | 2.03GB | | [phi3-mini-context-ignore.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.IQ4_NL.gguf) | IQ4_NL | 2.04GB | | [phi3-mini-context-ignore.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q4_K_S.gguf) | Q4_K_S | 2.04GB | | [phi3-mini-context-ignore.Q4_K.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q4_K.gguf) | Q4_K | 2.23GB | | [phi3-mini-context-ignore.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q4_K_M.gguf) | Q4_K_M | 2.23GB | | [phi3-mini-context-ignore.Q4_1.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q4_1.gguf) | Q4_1 | 2.24GB | | [phi3-mini-context-ignore.Q5_0.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q5_0.gguf) | Q5_0 | 2.46GB | | [phi3-mini-context-ignore.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q5_K_S.gguf) | Q5_K_S | 2.46GB | | [phi3-mini-context-ignore.Q5_K.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q5_K.gguf) | Q5_K | 2.62GB | | [phi3-mini-context-ignore.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q5_K_M.gguf) | Q5_K_M | 2.62GB | | [phi3-mini-context-ignore.Q5_1.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q5_1.gguf) | Q5_1 | 2.68GB | | [phi3-mini-context-ignore.Q6_K.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q6_K.gguf) | Q6_K | 2.92GB | | [phi3-mini-context-ignore.Q8_0.gguf](https://huggingface.co/RichardErkhov/Satandon1999_-_phi3-mini-context-ignore-gguf/blob/main/phi3-mini-context-ignore.Q8_0.gguf) | Q8_0 | 3.78GB | Original model description: --- license: mit license_link: https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE language: - en pipeline_tag: text-generation tags: - nlp - code widget: - messages: - role: user content: Can you provide ways to eat combinations of bananas and dragonfruits? --- ## Model Summary The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties. The model belongs to the Phi-3 family with the Mini version in two variants [4K](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) and [128K](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) which is the context length (in tokens) that it can support. After initial training, the model underwent a post-training process that involved supervised fine-tuning and direct preference optimization to enhance its ability to follow instructions and adhere to safety measures. When evaluated against benchmarks that test common sense, language understanding, mathematics, coding, long-term context, and logical reasoning, the Phi-3 Mini-128K-Instruct demonstrated robust and state-of-the-art performance among models with fewer than 13 billion parameters. Resources and Technical Documentation: + [Phi-3 Microsoft Blog](https://aka.ms/Phi-3Build2024) + [Phi-3 Technical Report](https://aka.ms/phi3-tech-report) + [Phi-3 on Azure AI Studio](https://aka.ms/phi3-azure-ai) + [Phi-3 Cookbook](https://github.com/microsoft/Phi-3CookBook) | | Short Context | Long Context | | ------- | ------------- | ------------ | | Mini | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx) ; [[GGUF]](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct-onnx)| | Small | 8K [[HF]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-8k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-small-128k-instruct-onnx-cuda)| | Medium | 4K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct-onnx-cuda) | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda)| | Vision | | 128K [[HF]](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct) ; [[ONNX]](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct-onnx-cuda)| ## Intended Uses **Primary use cases** The model is intended for commercial and research use in English. The model provides uses for applications which require: 1) Memory/compute constrained environments 2) Latency bound scenarios 3) Strong reasoning (especially code, math and logic) Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features. **Use case considerations** Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case. Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under. ## How to Use Phi-3 Mini-128K-Instruct has been integrated in the development version (4.41.0.dev0) of `transformers`. Until the official version is released through `pip`, ensure that you are doing one of the following: * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function. * Update your local `transformers` to the development version: `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`. The previous command is an alternative to cloning and installing from the source. The current `transformers` version can be verified with: `pip list | grep transformers`. ### Tokenizer Phi-3 Mini-128K-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size. ### Chat Format Given the nature of the training data, the Phi-3 Mini-128K-Instruct model is best suited for prompts using the chat format as follows. You can provide the prompt as a question with a generic template as follow: ```markdown <|user|>\nQuestion<|end|>\n<|assistant|> ``` For example: ```markdown <|user|> How to explain Internet for a medieval knight?<|end|> <|assistant|> ``` where the model generates the text after `<|assistant|>`. In case of few-shots prompt, the prompt can be formatted as the following: ```markdown <|user|> I am going to Paris, what should I see?<|end|> <|assistant|> Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:\n\n1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.\n2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.\n3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.\n\nThese are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|> <|user|> What is so great about #1?<|end|> <|assistant|> ``` ### Sample inference code This code snippets show how to get quickly started with running the model on a GPU: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline torch.random.manual_seed(0) model = AutoModelForCausalLM.from_pretrained( "microsoft/Phi-3-mini-128k-instruct", device_map="cuda", torch_dtype="auto", trust_remote_code=True, ) tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct") messages = [ {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}, {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"}, ] pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, ) generation_args = { "max_new_tokens": 500, "return_full_text": False, "temperature": 0.0, "do_sample": False, } output = pipe(messages, **generation_args) print(output[0]['generated_text']) ``` *Some applications/frameworks might not include a BOS token (`<s>`) at the start of the conversation. Please ensure that it is included since it provides more reliable results.* ## Responsible AI Considerations Like other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include: + Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English. + Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases. + Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case. + Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated. + Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses. Developers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include: + Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques. + High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context. + Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG). + Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case. + Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations. ## Training ### Model * Architecture: Phi-3 Mini-128K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines. * Inputs: Text. It is best suited for prompts using chat format. * Context length: 128K tokens * GPUs: 512 H100-80G * Training time: 7 days * Training data: 3.3T tokens * Outputs: Generated text in response to the input * Dates: Our models were trained between February and April 2024 * Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models. ### Datasets Our training data includes a wide variety of sources, totaling 3.3 trillion tokens, and is a combination of 1) Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code; 2) Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.); 3) High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness. ### Fine-tuning A basic example of multi-GPUs supervised fine-tuning (SFT) with TRL and Accelerate modules is provided [here](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/sample_finetune.py). ## Benchmarks We report the results for Phi-3-Mini-128K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Phi-2, Mistral-7b-v0.1, Mixtral-8x7b, Gemma 7B, Llama-3-8B-Instruct, and GPT-3.5. All the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation. As is now standard, we use few-shot prompts to evaluate the models, at temperature 0. The prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3. More specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model. The number of k–shot examples is listed per-benchmark. | | Phi-3-Mini-128K-In<br>3.8b | Phi-3-Small<br>7b (preview) | Phi-3-Medium<br>14b (preview) | Phi-2<br>2.7b | Mistral<br>7b | Gemma<br>7b | Llama-3-In<br>8b | Mixtral<br>8x7b | GPT-3.5<br>version 1106 | |---|---|---|---|---|---|---|---|---|---| | MMLU <br>5-Shot | 68.1 | 75.3 | 78.2 | 56.3 | 61.7 | 63.6 | 66.5 | 68.4 | 71.4 | | HellaSwag <br> 5-Shot | 74.5 | 78.7 | 83.2 | 53.6 | 58.5 | 49.8 | 71.1 | 70.4 | 78.8 | | ANLI <br> 7-Shot | 52.8 | 55.0 | 58.7 | 42.5 | 47.1 | 48.7 | 57.3 | 55.2 | 58.1 | | GSM-8K <br> 0-Shot; CoT | 83.6 | 86.4 | 90.8 | 61.1 | 46.4 | 59.8 | 77.4 | 64.7 | 78.1 | | MedQA <br> 2-Shot | 55.3 | 58.2 | 69.8 | 40.9 | 49.6 | 50.0 | 60.5 | 62.2 | 63.4 | | AGIEval <br> 0-Shot | 36.9 | 45.0 | 49.7 | 29.8 | 35.1 | 42.1 | 42.0 | 45.2 | 48.4 | | TriviaQA <br> 5-Shot | 57.1 | 59.1 | 73.3 | 45.2 | 72.3 | 75.2 | 67.7 | 82.2 | 85.8 | | Arc-C <br> 10-Shot | 84.0 | 90.7 | 91.9 | 75.9 | 78.6 | 78.3 | 82.8 | 87.3 | 87.4 | | Arc-E <br> 10-Shot | 95.2 | 97.1 | 98.0 | 88.5 | 90.6 | 91.4 | 93.4 | 95.6 | 96.3 | | PIQA <br> 5-Shot | 83.6 | 87.8 | 88.2 | 60.2 | 77.7 | 78.1 | 75.7 | 86.0 | 86.6 | | SociQA <br> 5-Shot | 76.1 | 79.0 | 79.4 | 68.3 | 74.6 | 65.5 | 73.9 | 75.9 | 68.3 | | BigBench-Hard <br> 0-Shot | 71.5 | 75.0 | 82.5 | 59.4 | 57.3 | 59.6 | 51.5 | 69.7 | 68.32 | | WinoGrande <br> 5-Shot | 72.5 | 82.5 | 81.2 | 54.7 | 54.2 | 55.6 | 65.0 | 62.0 | 68.8 | | OpenBookQA <br> 10-Shot | 80.6 | 88.4 | 86.6 | 73.6 | 79.8 | 78.6 | 82.6 | 85.8 | 86.0 | | BoolQ <br> 0-Shot | 78.7 | 82.9 | 86.5 | -- | 72.2 | 66.0 | 80.9 | 77.6 | 79.1 | | CommonSenseQA <br> 10-Shot | 78.0 | 80.3 | 82.6 | 69.3 | 72.6 | 76.2 | 79 | 78.1 | 79.6 | | TruthfulQA <br> 10-Shot | 63.2 | 68.1 | 74.8 | -- | 52.1 | 53.0 | 63.2 | 60.1 | 85.8 | | HumanEval <br> 0-Shot | 57.9 | 59.1 | 54.7 | 47.0 | 28.0 | 34.1 | 60.4| 37.8 | 62.2 | | MBPP <br> 3-Shot | 62.5 | 71.4 | 73.7 | 60.6 | 50.8 | 51.5 | 67.7 | 60.2 | 77.8 | ## Software * [PyTorch](https://github.com/pytorch/pytorch) * [DeepSpeed](https://github.com/microsoft/DeepSpeed) * [Transformers](https://github.com/huggingface/transformers) * [Flash-Attention](https://github.com/HazyResearch/flash-attention) ## Hardware Note that by default, the Phi-3-mini model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types: * NVIDIA A100 * NVIDIA A6000 * NVIDIA H100 If you want to run the model on: * NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from_pretrained() with attn_implementation="eager" * Optimized inference on GPU, CPU, and Mobile: use the **ONNX** models [128K](https://aka.ms/phi3-mini-128k-instruct-onnx) ## Cross Platform Support ONNX runtime ecosystem now supports Phi-3 Mini models across platforms and hardware. You can find the optimized Phi-3 Mini-128K-Instruct ONNX model [here](https://aka.ms/phi3-mini-128k-instruct-onnx). Optimized Phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML support lets developers bring hardware acceleration to Windows devices at scale across AMD, Intel, and NVIDIA GPUs. Along with DirectML, ONNX Runtime provides cross platform support for Phi-3 across a range of devices CPU, GPU, and mobile. Here are some of the optimized configurations we have added: 1. ONNX models for int4 DML: Quantized to int4 via AWQ 2. ONNX model for fp16 CUDA 3. ONNX model for int4 CUDA: Quantized to int4 via RTN 4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN ## License The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-mini-128k/resolve/main/LICENSE). ## Trademarks This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
[ "MEDQA" ]
BASF-AI/nomic-embed-text-v1.5
BASF-AI
sentence-similarity
[ "sentence-transformers", "onnx", "safetensors", "nomic_bert", "feature-extraction", "sentence-similarity", "mteb", "transformers", "transformers.js", "custom_code", "en", "arxiv:2205.13147", "arxiv:2402.01613", "license:apache-2.0", "model-index", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
2025-01-10T00:04:58Z
2025-01-10T04:53:06+00:00
31
0
--- language: - en library_name: sentence-transformers license: apache-2.0 pipeline_tag: sentence-similarity tags: - feature-extraction - sentence-similarity - mteb - transformers - transformers.js model-index: - name: epoch_0_model results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 75.20895522388058 - type: ap value: 38.57605549557802 - type: f1 value: 69.35586565857854 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification type: mteb/amazon_polarity config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 91.8144 - type: ap value: 88.65222882032363 - type: f1 value: 91.80426301643274 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 47.162000000000006 - type: f1 value: 46.59329642263158 - task: type: Retrieval dataset: name: MTEB ArguAna type: arguana config: default split: test revision: None metrics: - type: map_at_1 value: 24.253 - type: map_at_10 value: 38.962 - type: map_at_100 value: 40.081 - type: map_at_1000 value: 40.089000000000006 - type: map_at_3 value: 33.499 - type: map_at_5 value: 36.351 - type: mrr_at_1 value: 24.609 - type: mrr_at_10 value: 39.099000000000004 - type: mrr_at_100 value: 40.211000000000006 - type: mrr_at_1000 value: 40.219 - type: mrr_at_3 value: 33.677 - type: mrr_at_5 value: 36.469 - type: ndcg_at_1 value: 24.253 - type: ndcg_at_10 value: 48.010999999999996 - type: ndcg_at_100 value: 52.756 - type: ndcg_at_1000 value: 52.964999999999996 - type: ndcg_at_3 value: 36.564 - type: ndcg_at_5 value: 41.711999999999996 - type: precision_at_1 value: 24.253 - type: precision_at_10 value: 7.738 - type: precision_at_100 value: 0.98 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 15.149000000000001 - type: precision_at_5 value: 11.593 - type: recall_at_1 value: 24.253 - type: recall_at_10 value: 77.383 - type: recall_at_100 value: 98.009 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 45.448 - type: recall_at_5 value: 57.965999999999994 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P type: mteb/arxiv-clustering-p2p config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 45.69069567851087 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S type: mteb/arxiv-clustering-s2s config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 36.35185490976283 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions type: mteb/askubuntudupquestions-reranking config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 61.71274951450321 - type: mrr value: 76.06032625423207 - task: type: STS dataset: name: MTEB BIOSSES type: mteb/biosses-sts config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 86.73980520022269 - type: cos_sim_spearman value: 84.24649792685918 - type: euclidean_pearson value: 85.85197641158186 - type: euclidean_spearman value: 84.24649792685918 - type: manhattan_pearson value: 86.26809552711346 - type: manhattan_spearman value: 84.56397504030865 - task: type: Classification dataset: name: MTEB Banking77Classification type: mteb/banking77 config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 84.25324675324674 - type: f1 value: 84.17872280892557 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P type: mteb/biorxiv-clustering-p2p config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 38.770253446400886 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S type: mteb/biorxiv-clustering-s2s config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.94307095497281 - task: type: Retrieval dataset: name: MTEB CQADupstackAndroidRetrieval type: BeIR/cqadupstack config: default split: test revision: None metrics: - type: map_at_1 value: 32.164 - type: map_at_10 value: 42.641 - type: map_at_100 value: 43.947 - type: map_at_1000 value: 44.074999999999996 - type: map_at_3 value: 39.592 - type: map_at_5 value: 41.204 - type: mrr_at_1 value: 39.628 - type: mrr_at_10 value: 48.625 - type: mrr_at_100 value: 49.368 - type: mrr_at_1000 value: 49.413000000000004 - type: mrr_at_3 value: 46.400000000000006 - type: mrr_at_5 value: 47.68 - type: ndcg_at_1 value: 39.628 - type: ndcg_at_10 value: 48.564 - type: ndcg_at_100 value: 53.507000000000005 - type: ndcg_at_1000 value: 55.635999999999996 - type: ndcg_at_3 value: 44.471 - type: ndcg_at_5 value: 46.137 - type: precision_at_1 value: 39.628 - type: precision_at_10 value: 8.856 - type: precision_at_100 value: 1.429 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 21.268 - type: precision_at_5 value: 14.649000000000001 - type: recall_at_1 value: 32.164 - type: recall_at_10 value: 59.609 - type: recall_at_100 value: 80.521 - type: recall_at_1000 value: 94.245 - type: recall_at_3 value: 46.521 - type: recall_at_5 value: 52.083999999999996 - type: map_at_1 value: 31.526 - type: map_at_10 value: 41.581 - type: map_at_100 value: 42.815999999999995 - type: map_at_1000 value: 42.936 - type: map_at_3 value: 38.605000000000004 - type: map_at_5 value: 40.351 - type: mrr_at_1 value: 39.489999999999995 - type: mrr_at_10 value: 47.829 - type: mrr_at_100 value: 48.512 - type: mrr_at_1000 value: 48.552 - type: mrr_at_3 value: 45.754 - type: mrr_at_5 value: 46.986 - type: ndcg_at_1 value: 39.489999999999995 - type: ndcg_at_10 value: 47.269 - type: ndcg_at_100 value: 51.564 - type: ndcg_at_1000 value: 53.53099999999999 - type: ndcg_at_3 value: 43.301 - type: ndcg_at_5 value: 45.239000000000004 - type: precision_at_1 value: 39.489999999999995 - type: precision_at_10 value: 8.93 - type: precision_at_100 value: 1.415 - type: precision_at_1000 value: 0.188 - type: precision_at_3 value: 20.892 - type: precision_at_5 value: 14.865999999999998 - type: recall_at_1 value: 31.526 - type: recall_at_10 value: 56.76 - type: recall_at_100 value: 75.029 - type: recall_at_1000 value: 87.491 - type: recall_at_3 value: 44.786 - type: recall_at_5 value: 50.254 - type: map_at_1 value: 40.987 - type: map_at_10 value: 52.827 - type: map_at_100 value: 53.751000000000005 - type: map_at_1000 value: 53.81 - type: map_at_3 value: 49.844 - type: map_at_5 value: 51.473 - type: mrr_at_1 value: 46.833999999999996 - type: mrr_at_10 value: 56.389 - type: mrr_at_100 value: 57.003 - type: mrr_at_1000 value: 57.034 - type: mrr_at_3 value: 54.17999999999999 - type: mrr_at_5 value: 55.486999999999995 - type: ndcg_at_1 value: 46.833999999999996 - type: ndcg_at_10 value: 58.372 - type: ndcg_at_100 value: 62.068 - type: ndcg_at_1000 value: 63.288 - type: ndcg_at_3 value: 53.400000000000006 - type: ndcg_at_5 value: 55.766000000000005 - type: precision_at_1 value: 46.833999999999996 - type: precision_at_10 value: 9.191 - type: precision_at_100 value: 1.192 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 23.448 - type: precision_at_5 value: 15.862000000000002 - type: recall_at_1 value: 40.987 - type: recall_at_10 value: 71.146 - type: recall_at_100 value: 87.035 - type: recall_at_1000 value: 95.633 - type: recall_at_3 value: 58.025999999999996 - type: recall_at_5 value: 63.815999999999995 - type: map_at_1 value: 24.587 - type: map_at_10 value: 33.114 - type: map_at_100 value: 34.043 - type: map_at_1000 value: 34.123999999999995 - type: map_at_3 value: 30.45 - type: map_at_5 value: 31.813999999999997 - type: mrr_at_1 value: 26.554 - type: mrr_at_10 value: 35.148 - type: mrr_at_100 value: 35.926 - type: mrr_at_1000 value: 35.991 - type: mrr_at_3 value: 32.599000000000004 - type: mrr_at_5 value: 33.893 - type: ndcg_at_1 value: 26.554 - type: ndcg_at_10 value: 38.132 - type: ndcg_at_100 value: 42.78 - type: ndcg_at_1000 value: 44.919 - type: ndcg_at_3 value: 32.833 - type: ndcg_at_5 value: 35.168 - type: precision_at_1 value: 26.554 - type: precision_at_10 value: 5.921 - type: precision_at_100 value: 0.8659999999999999 - type: precision_at_1000 value: 0.109 - type: precision_at_3 value: 13.861 - type: precision_at_5 value: 9.605 - type: recall_at_1 value: 24.587 - type: recall_at_10 value: 51.690000000000005 - type: recall_at_100 value: 73.428 - type: recall_at_1000 value: 89.551 - type: recall_at_3 value: 37.336999999999996 - type: recall_at_5 value: 43.047000000000004 - type: map_at_1 value: 16.715 - type: map_at_10 value: 24.251 - type: map_at_100 value: 25.326999999999998 - type: map_at_1000 value: 25.455 - type: map_at_3 value: 21.912000000000003 - type: map_at_5 value: 23.257 - type: mrr_at_1 value: 20.274 - type: mrr_at_10 value: 28.552 - type: mrr_at_100 value: 29.42 - type: mrr_at_1000 value: 29.497 - type: mrr_at_3 value: 26.14 - type: mrr_at_5 value: 27.502 - type: ndcg_at_1 value: 20.274 - type: ndcg_at_10 value: 29.088 - type: ndcg_at_100 value: 34.293 - type: ndcg_at_1000 value: 37.271 - type: ndcg_at_3 value: 24.708 - type: ndcg_at_5 value: 26.809 - type: precision_at_1 value: 20.274 - type: precision_at_10 value: 5.361 - type: precision_at_100 value: 0.915 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 11.733 - type: precision_at_5 value: 8.556999999999999 - type: recall_at_1 value: 16.715 - type: recall_at_10 value: 39.587 - type: recall_at_100 value: 62.336000000000006 - type: recall_at_1000 value: 83.453 - type: recall_at_3 value: 27.839999999999996 - type: recall_at_5 value: 32.952999999999996 - type: map_at_1 value: 28.793000000000003 - type: map_at_10 value: 38.582 - type: map_at_100 value: 39.881 - type: map_at_1000 value: 39.987 - type: map_at_3 value: 35.851 - type: map_at_5 value: 37.289 - type: mrr_at_1 value: 34.455999999999996 - type: mrr_at_10 value: 43.909 - type: mrr_at_100 value: 44.74 - type: mrr_at_1000 value: 44.786 - type: mrr_at_3 value: 41.659 - type: mrr_at_5 value: 43.010999999999996 - type: ndcg_at_1 value: 34.455999999999996 - type: ndcg_at_10 value: 44.266 - type: ndcg_at_100 value: 49.639 - type: ndcg_at_1000 value: 51.644 - type: ndcg_at_3 value: 39.865 - type: ndcg_at_5 value: 41.887 - type: precision_at_1 value: 34.455999999999996 - type: precision_at_10 value: 7.843999999999999 - type: precision_at_100 value: 1.243 - type: precision_at_1000 value: 0.158 - type: precision_at_3 value: 18.831999999999997 - type: precision_at_5 value: 13.147 - type: recall_at_1 value: 28.793000000000003 - type: recall_at_10 value: 55.68300000000001 - type: recall_at_100 value: 77.99000000000001 - type: recall_at_1000 value: 91.183 - type: recall_at_3 value: 43.293 - type: recall_at_5 value: 48.618 - type: map_at_1 value: 25.907000000000004 - type: map_at_10 value: 35.519 - type: map_at_100 value: 36.806 - type: map_at_1000 value: 36.912 - type: map_at_3 value: 32.748 - type: map_at_5 value: 34.232 - type: mrr_at_1 value: 31.621 - type: mrr_at_10 value: 40.687 - type: mrr_at_100 value: 41.583 - type: mrr_at_1000 value: 41.638999999999996 - type: mrr_at_3 value: 38.527 - type: mrr_at_5 value: 39.612 - type: ndcg_at_1 value: 31.621 - type: ndcg_at_10 value: 41.003 - type: ndcg_at_100 value: 46.617999999999995 - type: ndcg_at_1000 value: 48.82 - type: ndcg_at_3 value: 36.542 - type: ndcg_at_5 value: 38.368 - type: precision_at_1 value: 31.621 - type: precision_at_10 value: 7.396999999999999 - type: precision_at_100 value: 1.191 - type: precision_at_1000 value: 0.153 - type: precision_at_3 value: 17.39 - type: precision_at_5 value: 12.1 - type: recall_at_1 value: 25.907000000000004 - type: recall_at_10 value: 52.115 - type: recall_at_100 value: 76.238 - type: recall_at_1000 value: 91.218 - type: recall_at_3 value: 39.417 - type: recall_at_5 value: 44.435 - type: map_at_1 value: 25.732166666666668 - type: map_at_10 value: 34.51616666666667 - type: map_at_100 value: 35.67241666666666 - type: map_at_1000 value: 35.78675 - type: map_at_3 value: 31.953416666666662 - type: map_at_5 value: 33.333 - type: mrr_at_1 value: 30.300166666666673 - type: mrr_at_10 value: 38.6255 - type: mrr_at_100 value: 39.46183333333334 - type: mrr_at_1000 value: 39.519999999999996 - type: mrr_at_3 value: 36.41299999999999 - type: mrr_at_5 value: 37.6365 - type: ndcg_at_1 value: 30.300166666666673 - type: ndcg_at_10 value: 39.61466666666667 - type: ndcg_at_100 value: 44.60808333333334 - type: ndcg_at_1000 value: 46.91708333333334 - type: ndcg_at_3 value: 35.26558333333333 - type: ndcg_at_5 value: 37.220000000000006 - type: precision_at_1 value: 30.300166666666673 - type: precision_at_10 value: 6.837416666666667 - type: precision_at_100 value: 1.10425 - type: precision_at_1000 value: 0.14875 - type: precision_at_3 value: 16.13716666666667 - type: precision_at_5 value: 11.2815 - type: recall_at_1 value: 25.732166666666668 - type: recall_at_10 value: 50.578916666666665 - type: recall_at_100 value: 72.42183333333334 - type: recall_at_1000 value: 88.48766666666667 - type: recall_at_3 value: 38.41325 - type: recall_at_5 value: 43.515750000000004 - type: map_at_1 value: 23.951 - type: map_at_10 value: 30.974 - type: map_at_100 value: 31.804 - type: map_at_1000 value: 31.900000000000002 - type: map_at_3 value: 28.762 - type: map_at_5 value: 29.94 - type: mrr_at_1 value: 26.534000000000002 - type: mrr_at_10 value: 33.553 - type: mrr_at_100 value: 34.297 - type: mrr_at_1000 value: 34.36 - type: mrr_at_3 value: 31.391000000000002 - type: mrr_at_5 value: 32.525999999999996 - type: ndcg_at_1 value: 26.534000000000002 - type: ndcg_at_10 value: 35.112 - type: ndcg_at_100 value: 39.28 - type: ndcg_at_1000 value: 41.723 - type: ndcg_at_3 value: 30.902 - type: ndcg_at_5 value: 32.759 - type: precision_at_1 value: 26.534000000000002 - type: precision_at_10 value: 5.445 - type: precision_at_100 value: 0.819 - type: precision_at_1000 value: 0.11 - type: precision_at_3 value: 12.986 - type: precision_at_5 value: 9.049 - type: recall_at_1 value: 23.951 - type: recall_at_10 value: 45.24 - type: recall_at_100 value: 64.12299999999999 - type: recall_at_1000 value: 82.28999999999999 - type: recall_at_3 value: 33.806000000000004 - type: recall_at_5 value: 38.277 - type: map_at_1 value: 16.829 - type: map_at_10 value: 23.684 - type: map_at_100 value: 24.683 - type: map_at_1000 value: 24.81 - type: map_at_3 value: 21.554000000000002 - type: map_at_5 value: 22.768 - type: mrr_at_1 value: 20.096 - type: mrr_at_10 value: 27.230999999999998 - type: mrr_at_100 value: 28.083999999999996 - type: mrr_at_1000 value: 28.166000000000004 - type: mrr_at_3 value: 25.212 - type: mrr_at_5 value: 26.32 - type: ndcg_at_1 value: 20.096 - type: ndcg_at_10 value: 27.989000000000004 - type: ndcg_at_100 value: 32.847 - type: ndcg_at_1000 value: 35.896 - type: ndcg_at_3 value: 24.116 - type: ndcg_at_5 value: 25.964 - type: precision_at_1 value: 20.096 - type: precision_at_10 value: 5 - type: precision_at_100 value: 0.8750000000000001 - type: precision_at_1000 value: 0.131 - type: precision_at_3 value: 11.207 - type: precision_at_5 value: 8.08 - type: recall_at_1 value: 16.829 - type: recall_at_10 value: 37.407000000000004 - type: recall_at_100 value: 59.101000000000006 - type: recall_at_1000 value: 81.024 - type: recall_at_3 value: 26.739 - type: recall_at_5 value: 31.524 - type: map_at_1 value: 24.138 - type: map_at_10 value: 32.275999999999996 - type: map_at_100 value: 33.416000000000004 - type: map_at_1000 value: 33.527 - type: map_at_3 value: 29.854000000000003 - type: map_at_5 value: 31.096 - type: mrr_at_1 value: 28.450999999999997 - type: mrr_at_10 value: 36.214 - type: mrr_at_100 value: 37.134 - type: mrr_at_1000 value: 37.198 - type: mrr_at_3 value: 34.001999999999995 - type: mrr_at_5 value: 35.187000000000005 - type: ndcg_at_1 value: 28.450999999999997 - type: ndcg_at_10 value: 37.166 - type: ndcg_at_100 value: 42.454 - type: ndcg_at_1000 value: 44.976 - type: ndcg_at_3 value: 32.796 - type: ndcg_at_5 value: 34.631 - type: precision_at_1 value: 28.450999999999997 - type: precision_at_10 value: 6.241 - type: precision_at_100 value: 0.9950000000000001 - type: precision_at_1000 value: 0.133 - type: precision_at_3 value: 14.801 - type: precision_at_5 value: 10.280000000000001 - type: recall_at_1 value: 24.138 - type: recall_at_10 value: 48.111 - type: recall_at_100 value: 71.245 - type: recall_at_1000 value: 88.986 - type: recall_at_3 value: 36.119 - type: recall_at_5 value: 40.846 - type: map_at_1 value: 23.244 - type: map_at_10 value: 31.227 - type: map_at_100 value: 33.007 - type: map_at_1000 value: 33.223 - type: map_at_3 value: 28.924 - type: map_at_5 value: 30.017 - type: mrr_at_1 value: 27.668 - type: mrr_at_10 value: 35.524 - type: mrr_at_100 value: 36.699 - type: mrr_at_1000 value: 36.759 - type: mrr_at_3 value: 33.366 - type: mrr_at_5 value: 34.552 - type: ndcg_at_1 value: 27.668 - type: ndcg_at_10 value: 36.381 - type: ndcg_at_100 value: 43.062 - type: ndcg_at_1000 value: 45.656 - type: ndcg_at_3 value: 32.501999999999995 - type: ndcg_at_5 value: 34.105999999999995 - type: precision_at_1 value: 27.668 - type: precision_at_10 value: 6.798 - type: precision_at_100 value: 1.492 - type: precision_at_1000 value: 0.234 - type: precision_at_3 value: 15.152 - type: precision_at_5 value: 10.791 - type: recall_at_1 value: 23.244 - type: recall_at_10 value: 45.979 - type: recall_at_100 value: 74.822 - type: recall_at_1000 value: 91.078 - type: recall_at_3 value: 34.925 - type: recall_at_5 value: 39.126 - type: map_at_1 value: 19.945 - type: map_at_10 value: 27.517999999999997 - type: map_at_100 value: 28.588 - type: map_at_1000 value: 28.682000000000002 - type: map_at_3 value: 25.345000000000002 - type: map_at_5 value: 26.555 - type: mrr_at_1 value: 21.996 - type: mrr_at_10 value: 29.845 - type: mrr_at_100 value: 30.775999999999996 - type: mrr_at_1000 value: 30.845 - type: mrr_at_3 value: 27.726 - type: mrr_at_5 value: 28.882 - type: ndcg_at_1 value: 21.996 - type: ndcg_at_10 value: 32.034 - type: ndcg_at_100 value: 37.185 - type: ndcg_at_1000 value: 39.645 - type: ndcg_at_3 value: 27.750999999999998 - type: ndcg_at_5 value: 29.805999999999997 - type: precision_at_1 value: 21.996 - type: precision_at_10 value: 5.065 - type: precision_at_100 value: 0.819 - type: precision_at_1000 value: 0.11399999999999999 - type: precision_at_3 value: 12.076 - type: precision_at_5 value: 8.392 - type: recall_at_1 value: 19.945 - type: recall_at_10 value: 43.62 - type: recall_at_100 value: 67.194 - type: recall_at_1000 value: 85.7 - type: recall_at_3 value: 32.15 - type: recall_at_5 value: 37.208999999999996 - task: type: Retrieval dataset: name: MTEB ClimateFEVER type: climate-fever config: default split: test revision: None metrics: - type: map_at_1 value: 18.279 - type: map_at_10 value: 31.052999999999997 - type: map_at_100 value: 33.125 - type: map_at_1000 value: 33.306000000000004 - type: map_at_3 value: 26.208 - type: map_at_5 value: 28.857 - type: mrr_at_1 value: 42.671 - type: mrr_at_10 value: 54.557 - type: mrr_at_100 value: 55.142 - type: mrr_at_1000 value: 55.169000000000004 - type: mrr_at_3 value: 51.488 - type: mrr_at_5 value: 53.439 - type: ndcg_at_1 value: 42.671 - type: ndcg_at_10 value: 41.276 - type: ndcg_at_100 value: 48.376000000000005 - type: ndcg_at_1000 value: 51.318 - type: ndcg_at_3 value: 35.068 - type: ndcg_at_5 value: 37.242 - type: precision_at_1 value: 42.671 - type: precision_at_10 value: 12.638 - type: precision_at_100 value: 2.045 - type: precision_at_1000 value: 0.26 - type: precision_at_3 value: 26.08 - type: precision_at_5 value: 19.805 - type: recall_at_1 value: 18.279 - type: recall_at_10 value: 46.946 - type: recall_at_100 value: 70.97200000000001 - type: recall_at_1000 value: 87.107 - type: recall_at_3 value: 31.147999999999996 - type: recall_at_5 value: 38.099 - task: type: Retrieval dataset: name: MTEB DBPedia type: dbpedia-entity config: default split: test revision: None metrics: - type: map_at_1 value: 8.573 - type: map_at_10 value: 19.747 - type: map_at_100 value: 28.205000000000002 - type: map_at_1000 value: 29.831000000000003 - type: map_at_3 value: 14.109 - type: map_at_5 value: 16.448999999999998 - type: mrr_at_1 value: 71 - type: mrr_at_10 value: 77.68599999999999 - type: mrr_at_100 value: 77.995 - type: mrr_at_1000 value: 78.00200000000001 - type: mrr_at_3 value: 76.292 - type: mrr_at_5 value: 77.029 - type: ndcg_at_1 value: 59.12500000000001 - type: ndcg_at_10 value: 43.9 - type: ndcg_at_100 value: 47.863 - type: ndcg_at_1000 value: 54.848 - type: ndcg_at_3 value: 49.803999999999995 - type: ndcg_at_5 value: 46.317 - type: precision_at_1 value: 71 - type: precision_at_10 value: 34.4 - type: precision_at_100 value: 11.063 - type: precision_at_1000 value: 1.989 - type: precision_at_3 value: 52.333 - type: precision_at_5 value: 43.7 - type: recall_at_1 value: 8.573 - type: recall_at_10 value: 25.615 - type: recall_at_100 value: 53.385000000000005 - type: recall_at_1000 value: 75.46000000000001 - type: recall_at_3 value: 15.429 - type: recall_at_5 value: 19.357 - task: type: Classification dataset: name: MTEB EmotionClassification type: mteb/emotion config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 47.989999999999995 - type: f1 value: 42.776314451497555 - task: type: Retrieval dataset: name: MTEB FEVER type: fever config: default split: test revision: None metrics: - type: map_at_1 value: 74.13499999999999 - type: map_at_10 value: 82.825 - type: map_at_100 value: 83.096 - type: map_at_1000 value: 83.111 - type: map_at_3 value: 81.748 - type: map_at_5 value: 82.446 - type: mrr_at_1 value: 79.553 - type: mrr_at_10 value: 86.654 - type: mrr_at_100 value: 86.774 - type: mrr_at_1000 value: 86.778 - type: mrr_at_3 value: 85.981 - type: mrr_at_5 value: 86.462 - type: ndcg_at_1 value: 79.553 - type: ndcg_at_10 value: 86.345 - type: ndcg_at_100 value: 87.32 - type: ndcg_at_1000 value: 87.58200000000001 - type: ndcg_at_3 value: 84.719 - type: ndcg_at_5 value: 85.677 - type: precision_at_1 value: 79.553 - type: precision_at_10 value: 10.402000000000001 - type: precision_at_100 value: 1.1119999999999999 - type: precision_at_1000 value: 0.11499999999999999 - type: precision_at_3 value: 32.413 - type: precision_at_5 value: 20.138 - type: recall_at_1 value: 74.13499999999999 - type: recall_at_10 value: 93.215 - type: recall_at_100 value: 97.083 - type: recall_at_1000 value: 98.732 - type: recall_at_3 value: 88.79 - type: recall_at_5 value: 91.259 - task: type: Retrieval dataset: name: MTEB FiQA2018 type: fiqa config: default split: test revision: None metrics: - type: map_at_1 value: 18.298000000000002 - type: map_at_10 value: 29.901 - type: map_at_100 value: 31.528 - type: map_at_1000 value: 31.713 - type: map_at_3 value: 25.740000000000002 - type: map_at_5 value: 28.227999999999998 - type: mrr_at_1 value: 36.728 - type: mrr_at_10 value: 45.401 - type: mrr_at_100 value: 46.27 - type: mrr_at_1000 value: 46.315 - type: mrr_at_3 value: 42.978 - type: mrr_at_5 value: 44.29 - type: ndcg_at_1 value: 36.728 - type: ndcg_at_10 value: 37.456 - type: ndcg_at_100 value: 43.832 - type: ndcg_at_1000 value: 47 - type: ndcg_at_3 value: 33.694 - type: ndcg_at_5 value: 35.085 - type: precision_at_1 value: 36.728 - type: precision_at_10 value: 10.386 - type: precision_at_100 value: 1.701 - type: precision_at_1000 value: 0.22599999999999998 - type: precision_at_3 value: 22.479 - type: precision_at_5 value: 16.605 - type: recall_at_1 value: 18.298000000000002 - type: recall_at_10 value: 44.369 - type: recall_at_100 value: 68.098 - type: recall_at_1000 value: 87.21900000000001 - type: recall_at_3 value: 30.215999999999998 - type: recall_at_5 value: 36.861 - task: type: Retrieval dataset: name: MTEB HotpotQA type: hotpotqa config: default split: test revision: None metrics: - type: map_at_1 value: 39.568 - type: map_at_10 value: 65.061 - type: map_at_100 value: 65.896 - type: map_at_1000 value: 65.95100000000001 - type: map_at_3 value: 61.831 - type: map_at_5 value: 63.849000000000004 - type: mrr_at_1 value: 79.136 - type: mrr_at_10 value: 84.58200000000001 - type: mrr_at_100 value: 84.765 - type: mrr_at_1000 value: 84.772 - type: mrr_at_3 value: 83.684 - type: mrr_at_5 value: 84.223 - type: ndcg_at_1 value: 79.136 - type: ndcg_at_10 value: 72.622 - type: ndcg_at_100 value: 75.539 - type: ndcg_at_1000 value: 76.613 - type: ndcg_at_3 value: 68.065 - type: ndcg_at_5 value: 70.58 - type: precision_at_1 value: 79.136 - type: precision_at_10 value: 15.215 - type: precision_at_100 value: 1.7500000000000002 - type: precision_at_1000 value: 0.189 - type: precision_at_3 value: 44.011 - type: precision_at_5 value: 28.388999999999996 - type: recall_at_1 value: 39.568 - type: recall_at_10 value: 76.077 - type: recall_at_100 value: 87.481 - type: recall_at_1000 value: 94.56400000000001 - type: recall_at_3 value: 66.01599999999999 - type: recall_at_5 value: 70.97200000000001 - task: type: Classification dataset: name: MTEB ImdbClassification type: mteb/imdb config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 85.312 - type: ap value: 80.36296867333715 - type: f1 value: 85.26613311552218 - task: type: Retrieval dataset: name: MTEB MSMARCO type: msmarco config: default split: dev revision: None metrics: - type: map_at_1 value: 23.363999999999997 - type: map_at_10 value: 35.711999999999996 - type: map_at_100 value: 36.876999999999995 - type: map_at_1000 value: 36.923 - type: map_at_3 value: 32.034 - type: map_at_5 value: 34.159 - type: mrr_at_1 value: 24.04 - type: mrr_at_10 value: 36.345 - type: mrr_at_100 value: 37.441 - type: mrr_at_1000 value: 37.480000000000004 - type: mrr_at_3 value: 32.713 - type: mrr_at_5 value: 34.824 - type: ndcg_at_1 value: 24.026 - type: ndcg_at_10 value: 42.531 - type: ndcg_at_100 value: 48.081 - type: ndcg_at_1000 value: 49.213 - type: ndcg_at_3 value: 35.044 - type: ndcg_at_5 value: 38.834 - type: precision_at_1 value: 24.026 - type: precision_at_10 value: 6.622999999999999 - type: precision_at_100 value: 0.941 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 14.909 - type: precision_at_5 value: 10.871 - type: recall_at_1 value: 23.363999999999997 - type: recall_at_10 value: 63.426 - type: recall_at_100 value: 88.96300000000001 - type: recall_at_1000 value: 97.637 - type: recall_at_3 value: 43.095 - type: recall_at_5 value: 52.178000000000004 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.0095759233926 - type: f1 value: 92.78387794667408 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 75.0296397628819 - type: f1 value: 58.45699589820874 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 73.45662407531944 - type: f1 value: 71.42364781421813 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.07800941492937 - type: f1 value: 77.22799045640845 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P type: mteb/medrxiv-clustering-p2p config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 34.531234379250606 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S type: mteb/medrxiv-clustering-s2s config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 30.941490381193802 - task: type: Reranking dataset: name: MTEB MindSmallReranking type: mteb/mind_small config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.3115090856725 - type: mrr value: 31.290667638675757 - task: type: Retrieval dataset: name: MTEB NFCorpus type: nfcorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.465 - type: map_at_10 value: 13.03 - type: map_at_100 value: 16.057 - type: map_at_1000 value: 17.49 - type: map_at_3 value: 9.553 - type: map_at_5 value: 11.204 - type: mrr_at_1 value: 43.653 - type: mrr_at_10 value: 53.269 - type: mrr_at_100 value: 53.72 - type: mrr_at_1000 value: 53.761 - type: mrr_at_3 value: 50.929 - type: mrr_at_5 value: 52.461 - type: ndcg_at_1 value: 42.26 - type: ndcg_at_10 value: 34.673 - type: ndcg_at_100 value: 30.759999999999998 - type: ndcg_at_1000 value: 39.728 - type: ndcg_at_3 value: 40.349000000000004 - type: ndcg_at_5 value: 37.915 - type: precision_at_1 value: 43.653 - type: precision_at_10 value: 25.789 - type: precision_at_100 value: 7.754999999999999 - type: precision_at_1000 value: 2.07 - type: precision_at_3 value: 38.596000000000004 - type: precision_at_5 value: 33.251 - type: recall_at_1 value: 5.465 - type: recall_at_10 value: 17.148 - type: recall_at_100 value: 29.768 - type: recall_at_1000 value: 62.239 - type: recall_at_3 value: 10.577 - type: recall_at_5 value: 13.315 - task: type: Retrieval dataset: name: MTEB NQ type: nq config: default split: test revision: None metrics: - type: map_at_1 value: 37.008 - type: map_at_10 value: 52.467 - type: map_at_100 value: 53.342999999999996 - type: map_at_1000 value: 53.366 - type: map_at_3 value: 48.412 - type: map_at_5 value: 50.875 - type: mrr_at_1 value: 41.541 - type: mrr_at_10 value: 54.967 - type: mrr_at_100 value: 55.611 - type: mrr_at_1000 value: 55.627 - type: mrr_at_3 value: 51.824999999999996 - type: mrr_at_5 value: 53.763000000000005 - type: ndcg_at_1 value: 41.541 - type: ndcg_at_10 value: 59.724999999999994 - type: ndcg_at_100 value: 63.38700000000001 - type: ndcg_at_1000 value: 63.883 - type: ndcg_at_3 value: 52.331 - type: ndcg_at_5 value: 56.327000000000005 - type: precision_at_1 value: 41.541 - type: precision_at_10 value: 9.447 - type: precision_at_100 value: 1.1520000000000001 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 23.262 - type: precision_at_5 value: 16.314999999999998 - type: recall_at_1 value: 37.008 - type: recall_at_10 value: 79.145 - type: recall_at_100 value: 94.986 - type: recall_at_1000 value: 98.607 - type: recall_at_3 value: 60.277 - type: recall_at_5 value: 69.407 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval type: quora config: default split: test revision: None metrics: - type: map_at_1 value: 70.402 - type: map_at_10 value: 84.181 - type: map_at_100 value: 84.796 - type: map_at_1000 value: 84.81400000000001 - type: map_at_3 value: 81.209 - type: map_at_5 value: 83.085 - type: mrr_at_1 value: 81.02000000000001 - type: mrr_at_10 value: 87.263 - type: mrr_at_100 value: 87.36 - type: mrr_at_1000 value: 87.36 - type: mrr_at_3 value: 86.235 - type: mrr_at_5 value: 86.945 - type: ndcg_at_1 value: 81.01 - type: ndcg_at_10 value: 87.99900000000001 - type: ndcg_at_100 value: 89.217 - type: ndcg_at_1000 value: 89.33 - type: ndcg_at_3 value: 85.053 - type: ndcg_at_5 value: 86.703 - type: precision_at_1 value: 81.01 - type: precision_at_10 value: 13.336 - type: precision_at_100 value: 1.52 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 37.14 - type: precision_at_5 value: 24.44 - type: recall_at_1 value: 70.402 - type: recall_at_10 value: 95.214 - type: recall_at_100 value: 99.438 - type: recall_at_1000 value: 99.928 - type: recall_at_3 value: 86.75699999999999 - type: recall_at_5 value: 91.44099999999999 - task: type: Clustering dataset: name: MTEB RedditClustering type: mteb/reddit-clustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.51721502758904 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P type: mteb/reddit-clustering-p2p config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 61.054808572333016 - task: type: Retrieval dataset: name: MTEB SCIDOCS type: scidocs config: default split: test revision: None metrics: - type: map_at_1 value: 4.578 - type: map_at_10 value: 11.036999999999999 - type: map_at_100 value: 12.879999999999999 - type: map_at_1000 value: 13.150999999999998 - type: map_at_3 value: 8.133 - type: map_at_5 value: 9.559 - type: mrr_at_1 value: 22.6 - type: mrr_at_10 value: 32.68 - type: mrr_at_100 value: 33.789 - type: mrr_at_1000 value: 33.854 - type: mrr_at_3 value: 29.7 - type: mrr_at_5 value: 31.480000000000004 - type: ndcg_at_1 value: 22.6 - type: ndcg_at_10 value: 18.616 - type: ndcg_at_100 value: 25.883 - type: ndcg_at_1000 value: 30.944 - type: ndcg_at_3 value: 18.136 - type: ndcg_at_5 value: 15.625 - type: precision_at_1 value: 22.6 - type: precision_at_10 value: 9.48 - type: precision_at_100 value: 1.991 - type: precision_at_1000 value: 0.321 - type: precision_at_3 value: 16.8 - type: precision_at_5 value: 13.54 - type: recall_at_1 value: 4.578 - type: recall_at_10 value: 19.213 - type: recall_at_100 value: 40.397 - type: recall_at_1000 value: 65.2 - type: recall_at_3 value: 10.208 - type: recall_at_5 value: 13.718 - task: type: STS dataset: name: MTEB SICK-R type: mteb/sickr-sts config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 83.44288351714071 - type: cos_sim_spearman value: 79.37995604564952 - type: euclidean_pearson value: 81.1078874670718 - type: euclidean_spearman value: 79.37995905980499 - type: manhattan_pearson value: 81.03697527288986 - type: manhattan_spearman value: 79.33490235296236 - task: type: STS dataset: name: MTEB STS12 type: mteb/sts12-sts config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 84.95557650436523 - type: cos_sim_spearman value: 78.5190672399868 - type: euclidean_pearson value: 81.58064025904707 - type: euclidean_spearman value: 78.5190672399868 - type: manhattan_pearson value: 81.52857930619889 - type: manhattan_spearman value: 78.50421361308034 - task: type: STS dataset: name: MTEB STS13 type: mteb/sts13-sts config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 84.79128416228737 - type: cos_sim_spearman value: 86.05402451477147 - type: euclidean_pearson value: 85.46280267054289 - type: euclidean_spearman value: 86.05402451477147 - type: manhattan_pearson value: 85.46278563858236 - type: manhattan_spearman value: 86.08079590861004 - task: type: STS dataset: name: MTEB STS14 type: mteb/sts14-sts config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 83.20623089568763 - type: cos_sim_spearman value: 81.53786907061009 - type: euclidean_pearson value: 82.82272250091494 - type: euclidean_spearman value: 81.53786907061009 - type: manhattan_pearson value: 82.78850494027013 - type: manhattan_spearman value: 81.5135618083407 - task: type: STS dataset: name: MTEB STS15 type: mteb/sts15-sts config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 85.46366618397936 - type: cos_sim_spearman value: 86.96566013336908 - type: euclidean_pearson value: 86.62651697548931 - type: euclidean_spearman value: 86.96565526364454 - type: manhattan_pearson value: 86.58812160258009 - type: manhattan_spearman value: 86.9336484321288 - task: type: STS dataset: name: MTEB STS16 type: mteb/sts16-sts config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 82.51858358641559 - type: cos_sim_spearman value: 84.7652527954999 - type: euclidean_pearson value: 84.23914783766861 - type: euclidean_spearman value: 84.7652527954999 - type: manhattan_pearson value: 84.22749648503171 - type: manhattan_spearman value: 84.74527996746386 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.28026563313065 - type: cos_sim_spearman value: 87.46928143824915 - type: euclidean_pearson value: 88.30558762000372 - type: euclidean_spearman value: 87.46928143824915 - type: manhattan_pearson value: 88.10513330809331 - type: manhattan_spearman value: 87.21069787834173 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 62.376497134587375 - type: cos_sim_spearman value: 65.0159550112516 - type: euclidean_pearson value: 65.64572120879598 - type: euclidean_spearman value: 65.0159550112516 - type: manhattan_pearson value: 65.88143604989976 - type: manhattan_spearman value: 65.17547297222434 - task: type: STS dataset: name: MTEB STSBenchmark type: mteb/stsbenchmark-sts config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 84.22876368947644 - type: cos_sim_spearman value: 85.46935577445318 - type: euclidean_pearson value: 85.32830231392005 - type: euclidean_spearman value: 85.46935577445318 - type: manhattan_pearson value: 85.30353211758495 - type: manhattan_spearman value: 85.42821085956945 - task: type: Reranking dataset: name: MTEB SciDocsRR type: mteb/scidocs-reranking config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 80.60986667767133 - type: mrr value: 94.29432314236236 - task: type: Retrieval dataset: name: MTEB SciFact type: scifact config: default split: test revision: None metrics: - type: map_at_1 value: 54.528 - type: map_at_10 value: 65.187 - type: map_at_100 value: 65.62599999999999 - type: map_at_1000 value: 65.657 - type: map_at_3 value: 62.352 - type: map_at_5 value: 64.025 - type: mrr_at_1 value: 57.333 - type: mrr_at_10 value: 66.577 - type: mrr_at_100 value: 66.88 - type: mrr_at_1000 value: 66.908 - type: mrr_at_3 value: 64.556 - type: mrr_at_5 value: 65.739 - type: ndcg_at_1 value: 57.333 - type: ndcg_at_10 value: 70.275 - type: ndcg_at_100 value: 72.136 - type: ndcg_at_1000 value: 72.963 - type: ndcg_at_3 value: 65.414 - type: ndcg_at_5 value: 67.831 - type: precision_at_1 value: 57.333 - type: precision_at_10 value: 9.5 - type: precision_at_100 value: 1.057 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 25.778000000000002 - type: precision_at_5 value: 17.2 - type: recall_at_1 value: 54.528 - type: recall_at_10 value: 84.356 - type: recall_at_100 value: 92.833 - type: recall_at_1000 value: 99.333 - type: recall_at_3 value: 71.283 - type: recall_at_5 value: 77.14999999999999 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.74158415841585 - type: cos_sim_ap value: 92.90048959850317 - type: cos_sim_f1 value: 86.35650810245687 - type: cos_sim_precision value: 90.4709748083242 - type: cos_sim_recall value: 82.6 - type: dot_accuracy value: 99.74158415841585 - type: dot_ap value: 92.90048959850317 - type: dot_f1 value: 86.35650810245687 - type: dot_precision value: 90.4709748083242 - type: dot_recall value: 82.6 - type: euclidean_accuracy value: 99.74158415841585 - type: euclidean_ap value: 92.90048959850317 - type: euclidean_f1 value: 86.35650810245687 - type: euclidean_precision value: 90.4709748083242 - type: euclidean_recall value: 82.6 - type: manhattan_accuracy value: 99.74158415841585 - type: manhattan_ap value: 92.87344692947894 - type: manhattan_f1 value: 86.38497652582159 - type: manhattan_precision value: 90.29443838604145 - type: manhattan_recall value: 82.8 - type: max_accuracy value: 99.74158415841585 - type: max_ap value: 92.90048959850317 - type: max_f1 value: 86.38497652582159 - task: type: Clustering dataset: name: MTEB StackExchangeClustering type: mteb/stackexchange-clustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 63.191648770424216 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P type: mteb/stackexchange-clustering-p2p config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 34.02944668730218 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 50.466386167525265 - type: mrr value: 51.19071492233257 - task: type: Summarization dataset: name: MTEB SummEval type: mteb/summeval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 30.198022505886435 - type: cos_sim_spearman value: 30.40170257939193 - type: dot_pearson value: 30.198015316402614 - type: dot_spearman value: 30.40170257939193 - task: type: Retrieval dataset: name: MTEB TRECCOVID type: trec-covid config: default split: test revision: None metrics: - type: map_at_1 value: 0.242 - type: map_at_10 value: 2.17 - type: map_at_100 value: 12.221 - type: map_at_1000 value: 28.63 - type: map_at_3 value: 0.728 - type: map_at_5 value: 1.185 - type: mrr_at_1 value: 94 - type: mrr_at_10 value: 97 - type: mrr_at_100 value: 97 - type: mrr_at_1000 value: 97 - type: mrr_at_3 value: 97 - type: mrr_at_5 value: 97 - type: ndcg_at_1 value: 89 - type: ndcg_at_10 value: 82.30499999999999 - type: ndcg_at_100 value: 61.839999999999996 - type: ndcg_at_1000 value: 53.381 - type: ndcg_at_3 value: 88.877 - type: ndcg_at_5 value: 86.05199999999999 - type: precision_at_1 value: 94 - type: precision_at_10 value: 87 - type: precision_at_100 value: 63.38 - type: precision_at_1000 value: 23.498 - type: precision_at_3 value: 94 - type: precision_at_5 value: 92 - type: recall_at_1 value: 0.242 - type: recall_at_10 value: 2.302 - type: recall_at_100 value: 14.979000000000001 - type: recall_at_1000 value: 49.638 - type: recall_at_3 value: 0.753 - type: recall_at_5 value: 1.226 - task: type: Retrieval dataset: name: MTEB Touche2020 type: webis-touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 3.006 - type: map_at_10 value: 11.805 - type: map_at_100 value: 18.146 - type: map_at_1000 value: 19.788 - type: map_at_3 value: 5.914 - type: map_at_5 value: 8.801 - type: mrr_at_1 value: 40.816 - type: mrr_at_10 value: 56.36600000000001 - type: mrr_at_100 value: 56.721999999999994 - type: mrr_at_1000 value: 56.721999999999994 - type: mrr_at_3 value: 52.041000000000004 - type: mrr_at_5 value: 54.796 - type: ndcg_at_1 value: 37.755 - type: ndcg_at_10 value: 29.863 - type: ndcg_at_100 value: 39.571 - type: ndcg_at_1000 value: 51.385999999999996 - type: ndcg_at_3 value: 32.578 - type: ndcg_at_5 value: 32.351 - type: precision_at_1 value: 40.816 - type: precision_at_10 value: 26.531 - type: precision_at_100 value: 7.796 - type: precision_at_1000 value: 1.555 - type: precision_at_3 value: 32.653 - type: precision_at_5 value: 33.061 - type: recall_at_1 value: 3.006 - type: recall_at_10 value: 18.738 - type: recall_at_100 value: 48.058 - type: recall_at_1000 value: 83.41300000000001 - type: recall_at_3 value: 7.166 - type: recall_at_5 value: 12.102 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification type: mteb/toxic_conversations_50k config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.4178 - type: ap value: 14.648781342150446 - type: f1 value: 55.07299194946378 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification type: mteb/tweet_sentiment_extraction config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 60.919637804187886 - type: f1 value: 61.24122013967399 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering type: mteb/twentynewsgroups-clustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 49.207896583685695 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.23114978840078 - type: cos_sim_ap value: 74.26624727825818 - type: cos_sim_f1 value: 68.72377190817083 - type: cos_sim_precision value: 64.56400742115028 - type: cos_sim_recall value: 73.45646437994723 - type: dot_accuracy value: 86.23114978840078 - type: dot_ap value: 74.26624032659652 - type: dot_f1 value: 68.72377190817083 - type: dot_precision value: 64.56400742115028 - type: dot_recall value: 73.45646437994723 - type: euclidean_accuracy value: 86.23114978840078 - type: euclidean_ap value: 74.26624714480556 - type: euclidean_f1 value: 68.72377190817083 - type: euclidean_precision value: 64.56400742115028 - type: euclidean_recall value: 73.45646437994723 - type: manhattan_accuracy value: 86.16558383501221 - type: manhattan_ap value: 74.2091943976357 - type: manhattan_f1 value: 68.64221520524654 - type: manhattan_precision value: 63.59135913591359 - type: manhattan_recall value: 74.5646437994723 - type: max_accuracy value: 86.23114978840078 - type: max_ap value: 74.26624727825818 - type: max_f1 value: 68.72377190817083 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.3681841114604 - type: cos_sim_ap value: 86.65166387498546 - type: cos_sim_f1 value: 79.02581944698774 - type: cos_sim_precision value: 75.35796605434099 - type: cos_sim_recall value: 83.06898675700647 - type: dot_accuracy value: 89.3681841114604 - type: dot_ap value: 86.65166019802056 - type: dot_f1 value: 79.02581944698774 - type: dot_precision value: 75.35796605434099 - type: dot_recall value: 83.06898675700647 - type: euclidean_accuracy value: 89.3681841114604 - type: euclidean_ap value: 86.65166462876266 - type: euclidean_f1 value: 79.02581944698774 - type: euclidean_precision value: 75.35796605434099 - type: euclidean_recall value: 83.06898675700647 - type: manhattan_accuracy value: 89.36624364497226 - type: manhattan_ap value: 86.65076471274106 - type: manhattan_f1 value: 79.07408783532733 - type: manhattan_precision value: 76.41102972856527 - type: manhattan_recall value: 81.92947336002464 - type: max_accuracy value: 89.3681841114604 - type: max_ap value: 86.65166462876266 - type: max_f1 value: 79.07408783532733 --- # nomic-embed-text-v1.5: Resizable Production Embeddings with Matryoshka Representation Learning **Exciting Update!**: `nomic-embed-text-v1.5` is now multimodal! [nomic-embed-vision-v1](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) is aligned to the embedding space of `nomic-embed-text-v1.5`, meaning any text embedding is multimodal! ## Usage **Important**: the text prompt *must* include a *task instruction prefix*, instructing the model which task is being performed. For example, if you are implementing a RAG application, you embed your documents as `search_document: <text here>` and embed your user queries as `search_query: <text here>`. ## Task instruction prefixes ### `search_document` #### Purpose: embed texts as documents from a dataset This prefix is used for embedding texts as documents, for example as documents for a RAG index. ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['search_document: TSNE is a dimensionality reduction algorithm created by Laurens van Der Maaten'] embeddings = model.encode(sentences) print(embeddings) ``` ### `search_query` #### Purpose: embed texts as questions to answer This prefix is used for embedding texts as questions that documents from a dataset could resolve, for example as queries to be answered by a RAG application. ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['search_query: Who is Laurens van Der Maaten?'] embeddings = model.encode(sentences) print(embeddings) ``` ### `clustering` #### Purpose: embed texts to group them into clusters This prefix is used for embedding texts in order to group them into clusters, discover common topics, or remove semantic duplicates. ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['clustering: the quick brown fox'] embeddings = model.encode(sentences) print(embeddings) ``` ### `classification` #### Purpose: embed texts to classify them This prefix is used for embedding texts into vectors that will be used as features for a classification model ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['classification: the quick brown fox'] embeddings = model.encode(sentences) print(embeddings) ``` ### Sentence Transformers ```python import torch.nn.functional as F from sentence_transformers import SentenceTransformer matryoshka_dim = 512 model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] embeddings = model.encode(sentences, convert_to_tensor=True) embeddings = F.layer_norm(embeddings, normalized_shape=(embeddings.shape[1],)) embeddings = embeddings[:, :matryoshka_dim] embeddings = F.normalize(embeddings, p=2, dim=1) print(embeddings) ``` ### Transformers ```diff import torch import torch.nn.functional as F from transformers import AutoTokenizer, AutoModel def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5', trust_remote_code=True, safe_serialization=True) model.eval() encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') + matryoshka_dim = 512 with torch.no_grad(): model_output = model(**encoded_input) embeddings = mean_pooling(model_output, encoded_input['attention_mask']) + embeddings = F.layer_norm(embeddings, normalized_shape=(embeddings.shape[1],)) + embeddings = embeddings[:, :matryoshka_dim] embeddings = F.normalize(embeddings, p=2, dim=1) print(embeddings) ``` The model natively supports scaling of the sequence length past 2048 tokens. To do so, ```diff - tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') + tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192) - model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) + model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2) ``` ### Transformers.js ```js import { pipeline, layer_norm } from '@xenova/transformers'; // Create a feature extraction pipeline const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1.5', { quantized: false, // Comment out this line to use the quantized version }); // Define sentences const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']; // Compute sentence embeddings let embeddings = await extractor(texts, { pooling: 'mean' }); console.log(embeddings); // Tensor of shape [2, 768] const matryoshka_dim = 512; embeddings = layer_norm(embeddings, [embeddings.dims[1]]) .slice(null, [0, matryoshka_dim]) .normalize(2, -1); console.log(embeddings.tolist()); ``` ## Nomic API The easiest way to use Nomic Embed is through the Nomic Embedding API. Generating embeddings with the `nomic` Python client is as easy as ```python from nomic import embed output = embed.text( texts=['Nomic Embedding API', '#keepAIOpen'], model='nomic-embed-text-v1.5', task_type='search_document', dimensionality=256, ) print(output) ``` For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text) ## Infinity Usage with [Infinity](https://github.com/michaelfeil/infinity). ```bash docker run --gpus all -v $PWD/data:/app/.cache -e HF_TOKEN=$HF_TOKEN -p "7997":"7997" \ michaelf34/infinity:0.0.70 \ v2 --model-id nomic-ai/nomic-embed-text-v1.5 --revision "main" --dtype float16 --batch-size 8 --engine torch --port 7997 --no-bettertransformer ``` ## Adjusting Dimensionality `nomic-embed-text-v1.5` is an improvement upon [Nomic Embed](https://huggingface.co/nomic-ai/nomic-embed-text-v1) that utilizes [Matryoshka Representation Learning](https://arxiv.org/abs/2205.13147) which gives developers the flexibility to trade off the embedding size for a negligible reduction in performance. | Name | SeqLen | Dimension | MTEB | | :-------------------------------:| :----- | :-------- | :------: | | nomic-embed-text-v1 | 8192 | 768 | **62.39** | | nomic-embed-text-v1.5 | 8192 | 768 | 62.28 | | nomic-embed-text-v1.5 | 8192 | 512 | 61.96 | | nomic-embed-text-v1.5 | 8192 | 256 | 61.04 | | nomic-embed-text-v1.5 | 8192 | 128 | 59.34 | | nomic-embed-text-v1.5 | 8192 | 64 | 56.10 | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/607997c83a565c15675055b3/CRnaHV-c2wMUMZKw72q85.png) ## Training Click the Nomic Atlas map below to visualize a 5M sample of our contrastive pretraining data! [![image/webp](https://cdn-uploads.huggingface.co/production/uploads/607997c83a565c15675055b3/pjhJhuNyRfPagRd_c_iUz.webp)](https://atlas.nomic.ai/map/nomic-text-embed-v1-5m-sample) We train our embedder using a multi-stage training pipeline. Starting from a long-context [BERT model](https://huggingface.co/nomic-ai/nomic-bert-2048), the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles. In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage. For more details, see the Nomic Embed [Technical Report](https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf) and corresponding [blog post](https://blog.nomic.ai/posts/nomic-embed-matryoshka). Training data to train the models is released in its entirety. For more details, see the `contrastors` [repository](https://github.com/nomic-ai/contrastors) # Join the Nomic Community - Nomic: [https://nomic.ai](https://nomic.ai) - Discord: [https://discord.gg/myY5YDR8z8](https://discord.gg/myY5YDR8z8) - Twitter: [https://twitter.com/nomic_ai](https://twitter.com/nomic_ai) # Citation If you find the model, dataset, or training code useful, please cite our work ```bibtex @misc{nussbaum2024nomic, title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar}, year={2024}, eprint={2402.01613}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
[ "BIOSSES", "SCIFACT" ]
Shashwat13333/bge-base-en-v1.5_v3
Shashwat13333
sentence-similarity
[ "sentence-transformers", "safetensors", "bert", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:150", "loss:MatryoshkaLoss", "loss:MultipleNegativesRankingLoss", "en", "arxiv:1908.10084", "arxiv:2205.13147", "arxiv:1705.00652", "base_model:BAAI/bge-base-en-v1.5", "base_model:finetune:BAAI/bge-base-en-v1.5", "license:apache-2.0", "model-index", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
2025-02-11T10:29:00Z
2025-02-11T11:50:46+00:00
31
0
--- base_model: BAAI/bge-base-en-v1.5 language: - en library_name: sentence-transformers license: apache-2.0 metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:150 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss widget: - source_sentence: Do you provide support 24/7? sentences: - 'How can we get started with your DevOps solutions? Getting started is easy. Contact us through our website. We''ll schedule a consultation to discuss your needs, evaluate your current infrastructure, and propose a customized DevOps solution designed to achieve your goals.' - 'This is our Portfolio Introducing the world of Housing Finance& Banking Firm. Corporate Website with 10 regional languages in India with analytics and user personalization and Dashboard for Regional Managers, Sales Agents, etc. to manage the Builder Requests, approve/deny Properties, manage visits and appointments, manage leads, etc. Introducing the world of Global Automotive Brand.We have implemented a Multi Locale Multilingual Omnichannel platform for Royal Enfield. The platform supports public websites, customer portals, internal portals, business applications for over 35+ different locations all over the world. Developed Digital Platform for Students, Guardians, Teachers, Tutors, with AI/ML in collaboration with Successive Technologies Inc, USA. Cloud, Dev-Sec-Ops & Data Governance Managing cloud provisioning and modernization alongside automated infrastructure, event-driven microservices, containerization, DevOps, cybersecurity, and 24x7 monitoring support ensures efficient, secure, and responsive IT operations.' - "SERVICES WE PROVIDE\nFlexible engagement models tailored to your needs\nWe specialize\ \ in comprehensive website audits that provide valuable insights and recommendations\ \ to enhance your online presence.\nDigital Strategy & Consulting\nCreating digital\ \ roadmap that transform your digital enterprise and produce a return on investment,\ \ basis our discovery framework, brainstorming sessions & current state analysis.\n\ \nPlatform Selection\nHelping you select the optimal digital experience, commerce,\ \ cloud and marketing platform for your enterprise.\n\nPlatform Builds\nDeploying\ \ next-gen scalable and agile enterprise digital platforms, along with multi-platform\ \ integrations. \nProduct Builds\nHelp you ideate, strategize, and engineer\ \ your product with help of our enterprise frameworks\nInfrastructure\nSpecialize\ \ in multi-cloud infrastructure helping you put forward the right cloud infrastructure\ \ and optimization strategy.\n\nManaged Services\nOperate and monitor your business-critical\ \ applications, data, and IT workloads, along with Application maintenance and\ \ operations.\nTeam Augmentation\nHelp you scale up and augment your existing\ \ team to solve your hiring challenges with our easy to deploy staff augmentation\ \ offerings.\"" - source_sentence: What services do you offer for AI adoption? sentences: - 'In what ways can machine learning optimize our operations? Machine learning algorithms can analyze operational data to identify inefficiencies, predict maintenance needs, optimize supply chains, and automate repetitive tasks, significantly improving operational efficiency and reducing costs.' - " We specialize in guiding companies through the complexities of adopting and\ \ integrating Artificial Intelligence and Machine Learning technologies. Our consultancy\ \ services are designed to enhance your operational efficiency and decision-making\ \ capabilities across all sectors. With a global network of AI/ML experts and\ \ a commitment to excellence, we are your partners in transforming innovative\ \ possibilities into real-world achievements. \ \ \ \ \n DATA INTELLIGENCE PLATFORMS we specialize\ \ in\nTensorFlow\nDatabricks\nTableau\nPytorch\nOpenAI\nPinecone\"" - 'We are a New breed of innovative digital transformation agency, redefining storytelling for an always-on world. With roots dating back to 2017, we started as a pocket size team of enthusiasts with a goal of helping traditional businesses transform and create dynamic, digital cultures through disruptive strategies and agile deployment of innovative solutions.' - source_sentence: What kind of data do you leverage for AI solutions? sentences: - 'How do we do Custom Development ? We follow below process to develop custom web or mobile Application on Agile Methodology, breaking requirements in pieces and developing and shipping them with considering utmost quality: Requirements Analysis We begin by understanding the clients needs and objectives for the website. Identify key features, functionality, and any specific design preferences. Project Planning Then create a detailed project plan outlining the scope, timeline, and milestones. Define the technology stack and development tools suitable for the project. User Experience Design Then comes the stage of Developing wireframes or prototypes to visualize the website&#39;s structure and layout. We create a custom design that aligns with the brand identity and user experience goals. Development After getting Sign-off on Design from Client, we break the requirements into Sprints on Agile Methodology, and start developing them.' - Our AI/ML services pave the way for transformative change across industries, embodying a client-focused approach that integrates seamlessly with human-centric innovation. Our collaborative teams are dedicated to fostering growth, leveraging data, and harnessing the predictive power of artificial intelligence to forge the next wave of software excellence. We don't just deliver AI; we deliver the future. - 'Why do we need Microservices ? Instead of building a monolithic application where all functionalities are tightly integrated, microservices break down the system into modular and loosely coupled services. Scalability Flexibility and Agility Resilience and Fault Isolation Technology Diversity Continuous Delivery' - source_sentence: What challenges did the company face in its early days? sentences: - 'Our Solutions Strategy & Digital Transformation Innovate via digital transformation, modernize tech, craft product strategies, enhance customer experiences, optimize data analytics, transition to cloud for growth and efficiency Product Engineering & Custom Development Providing product development, enterprise web and mobile development, microservices integrations, quality engineering, and application support services to drive innovation and enhance operational efficiency.' - 'What makes your DevOps solutions stand out from the competition? Our DevOps solutions stand out due to our personalized approach, extensive expertise, and commitment to innovation. We focus on delivering measurable results, such as reduced deployment times, improved system reliability, and enhanced security, ensuring you get the maximum benefit from our services.' - 'After a transformative scuba dive in the Maldives, Mayank Maggon made a pivotal decision to depart from the corporate ladder in December 2016. Fueled by a clear vision to revolutionize the digital landscape, Mayank set out to leverage the best technology ingredients, crafting custom applications and digital ecosystems tailored to clients'' specific needs, limitations, and budgets. However, this solo journey was not without its challenges. Mayank had to initiate the revenue engine by offering corporate trainings and conducting online batches for tech training across the USA. He also undertook small projects and subcontracted modules of larger projects for clients in the US, UK, and India. It was only after this initial groundwork that Mayank was able to hire a group of interns, whom he meticulously trained and groomed to prepare them for handling Enterprise Level Applications. This journey reflects Mayank''s resilience, determination, and entrepreneurial spirit in building TechChefz Digital from the ground up. With a passion for innovation and a relentless drive for excellence, Mayank has steered TechChefz Digital through strategic partnerships, groundbreaking projects, and exponential growth. His leadership has been instrumental in shaping the company into a leading force in the digital transformation arena, inspiring a culture of innovation and excellence that continues to propel the company forward.' - source_sentence: What do you guys do for digital strategy? sentences: - " What we do\n\nDigital Strategy\nCreating digital frameworks that transform\ \ your digital enterprise and produce a return on investment.\n\nPlatform Selection\n\ Helping you select the optimal digital experience, commerce, cloud and marketing\ \ platform for your enterprise.\n\nPlatform Builds\nDeploying next-gen scalable\ \ and agile enterprise digital platforms, along with multi-platform integrations.\n\ \nProduct Builds\nHelp you ideate, strategize, and engineer your product with\ \ help of our enterprise frameworks \n\nTeam Augmentation\nHelp you scale up and\ \ augment your existing team to solve your hiring challenges with our easy to\ \ deploy staff augmentation offerings .\nManaged Services\nOperate and monitor\ \ your business-critical applications, data, and IT workloads, along with Application\ \ maintenance and operations\n" - 'Introducing the world of General Insurance Firm In this project, we implemented Digital Solution and Implementation with Headless Drupal as the CMS, and lightweight React JS (Next JS SSR on Node JS) with the following features: PWA & AMP based Web Pages Page Speed Optimization Reusable and scalable React JS / Next JS Templates and Components Headless Drupal CMS with Content & Experience management, approval workflows, etc for seamless collaboration between the business and marketing teams Minimalistic Buy and Renewal Journeys for various products, with API integrations and adherence to data compliances We achieved 250% Reduction in Operational Time and Effort in managing the Content & Experience for Buy & renew Journeys,220% Reduction in Customer Drops during buy and renewal journeys, 300% Reduction in bounce rate on policy landing and campaign pages' - 'In the Introducing the world of Global Insurance Firm, we crafted Effective Solutions for Complex Problems and delieverd a comprehensive Website Development, Production Support & Managed Services, we optimized customer journeys, integrate analytics, CRM, ERP, and third-party applications, and implement cutting-edge technologies for enhanced performance and efficiency and achievied 200% Reduction in operational time & effort managing content & experience, 70% Reduction in Deployment Errors and Downtime, 2.5X Customer Engagement, Conversion & Retention' model-index: - name: BGE base Financial Matryoshka results: - task: type: information-retrieval name: Information Retrieval dataset: name: dim 768 type: dim_768 metrics: - type: cosine_accuracy@1 value: 0.24 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.6 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.6933333333333334 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8266666666666667 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.24 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.19999999999999998 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.13866666666666666 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08266666666666665 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.24 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.6 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.6933333333333334 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8266666666666667 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.5168483575362663 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.41823809523809513 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.42416446853284084 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 512 type: dim_512 metrics: - type: cosine_accuracy@1 value: 0.14666666666666667 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.6 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.6666666666666666 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8133333333333334 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.14666666666666667 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.1333333333333333 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.0813333333333333 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.14666666666666667 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.6 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.6666666666666666 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8133333333333334 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.47000090388642707 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.36049735449735437 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3666672731277011 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.21333333333333335 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.56 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.6533333333333333 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.76 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.21333333333333335 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.18666666666666668 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.13066666666666663 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.07599999999999998 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.21333333333333335 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.56 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.6533333333333333 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.76 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4826639910228885 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.3937354497354497 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.40352633551410066 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.16 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.5066666666666667 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.6533333333333333 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.7333333333333333 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.16 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.1688888888888889 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.13066666666666665 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.0733333333333333 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.16 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.5066666666666667 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.6533333333333333 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.7333333333333333 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.42870835906079113 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.33153439153439146 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3424976196127222 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.13333333333333333 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.38666666666666666 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.4666666666666667 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.6933333333333334 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.13333333333333333 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.1288888888888889 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.09333333333333334 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.06933333333333333 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.13333333333333333 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.38666666666666666 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.4666666666666667 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.6933333333333334 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.38361272138781966 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.28834391534391535 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.30056764135792025 name: Cosine Map@100 --- # BGE base Financial Matryoshka This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a --> - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity <!-- - **Training Dataset:** Unknown --> - **Language:** en - **License:** apache-2.0 ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("Shashwat13333/bge-base-en-v1.5_v3") # Run inference sentences = [ 'What do you guys do for digital strategy?', ' What we do\n\nDigital Strategy\nCreating digital frameworks that transform your digital enterprise and produce a return on investment.\n\nPlatform Selection\nHelping you select the optimal digital experience, commerce, cloud and marketing platform for your enterprise.\n\nPlatform Builds\nDeploying next-gen scalable and agile enterprise digital platforms, along with multi-platform integrations.\n\nProduct Builds\nHelp you ideate, strategize, and engineer your product with help of our enterprise frameworks \n\nTeam Augmentation\nHelp you scale up and augment your existing team to solve your hiring challenges with our easy to deploy staff augmentation offerings .\nManaged Services\nOperate and monitor your business-critical applications, data, and IT workloads, along with Application maintenance and operations\n', 'In the Introducing the world of Global Insurance Firm, we crafted Effective Solutions for Complex Problems and delieverd a comprehensive Website Development, Production Support & Managed Services, we optimized customer journeys, integrate analytics, CRM, ERP, and third-party applications, and implement cutting-edge technologies for enhanced performance and efficiency\nand achievied 200% Reduction in operational time & effort managing content & experience, 70% Reduction in Deployment Errors and Downtime, 2.5X Customer Engagement, Conversion & Retention', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> ## Evaluation ### Metrics #### Information Retrieval * Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64` * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 | |:--------------------|:-----------|:---------|:-----------|:-----------|:-----------| | cosine_accuracy@1 | 0.24 | 0.1467 | 0.2133 | 0.16 | 0.1333 | | cosine_accuracy@3 | 0.6 | 0.6 | 0.56 | 0.5067 | 0.3867 | | cosine_accuracy@5 | 0.6933 | 0.6667 | 0.6533 | 0.6533 | 0.4667 | | cosine_accuracy@10 | 0.8267 | 0.8133 | 0.76 | 0.7333 | 0.6933 | | cosine_precision@1 | 0.24 | 0.1467 | 0.2133 | 0.16 | 0.1333 | | cosine_precision@3 | 0.2 | 0.2 | 0.1867 | 0.1689 | 0.1289 | | cosine_precision@5 | 0.1387 | 0.1333 | 0.1307 | 0.1307 | 0.0933 | | cosine_precision@10 | 0.0827 | 0.0813 | 0.076 | 0.0733 | 0.0693 | | cosine_recall@1 | 0.24 | 0.1467 | 0.2133 | 0.16 | 0.1333 | | cosine_recall@3 | 0.6 | 0.6 | 0.56 | 0.5067 | 0.3867 | | cosine_recall@5 | 0.6933 | 0.6667 | 0.6533 | 0.6533 | 0.4667 | | cosine_recall@10 | 0.8267 | 0.8133 | 0.76 | 0.7333 | 0.6933 | | **cosine_ndcg@10** | **0.5168** | **0.47** | **0.4827** | **0.4287** | **0.3836** | | cosine_mrr@10 | 0.4182 | 0.3605 | 0.3937 | 0.3315 | 0.2883 | | cosine_map@100 | 0.4242 | 0.3667 | 0.4035 | 0.3425 | 0.3006 | <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 150 training samples * Columns: <code>anchor</code> and <code>positive</code> * Approximate statistics based on the first 150 samples: | | anchor | positive | |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 7 tokens</li><li>mean: 11.97 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 125.49 tokens</li><li>max: 378 tokens</li></ul> | * Samples: | anchor | positive | |:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>Is it hard to move old systems to the cloud?</code> | <code>We offer custom software development, digital marketing strategies, and tailored solutions to drive tangible results for your business. Our expert team combines technical prowess with industry insights to propel your business forward in the digital landscape.<br><br>"Engage, analyze & target your customers<br>Digital transformation enables you to interact with customers across multiple channels, providing personalized experiences. This could include social media engagement, interactive websites, and mobile apps." "Empower your employees & partners<br>The push for digital transformation has led many companies to embrace cloud solutions. However, the migration and integration of legacy systems into the cloud often present challenges." "Optimize & automate your operations<br>The push for digital transformation has led many companies to embrace cloud solutions. However, the migration and integration of legacy systems into the cloud often present challenges." "Transform your products<br>The push for digi...</code> | | <code>What benefits does marketing automation offer for time management?</code> | <code>Our MarTech capabilities<br><br>Personalization<br>Involves tailoring marketing messages and experiences to individual customers. It enhances customer engagement, loyalty, and ultimately, conversion rates.<br><br>Marketing Automation<br>Marketing automation streamlines repetitive tasks such as email marketing, lead nurturing, and social media posting. It improves efficiency, saves time, and ensures timely communication with customers.<br><br>Customer Relationship Management<br>CRM systems help manage interactions with current and potential customers. They store customer data, track interactions, and facilitate communication, improving customer retention.</code> | | <code>do you track customer behavior?</code> | <code>How can your recommendation engines improve our business?<br>Our recommendation engines are designed to analyze customer behavior and preferences to deliver personalized suggestions, enhancing user experience, increasing sales, and boosting customer retention.</code> | * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `gradient_accumulation_steps`: 4 - `learning_rate`: 1e-05 - `weight_decay`: 0.01 - `num_train_epochs`: 4 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.1 - `fp16`: True - `load_best_model_at_end`: True - `optim`: adamw_torch_fused - `push_to_hub`: True - `hub_model_id`: Shashwat13333/bge-base-en-v1.5_v3 - `push_to_hub_model_id`: bge-base-en-v1.5_v3 - `batch_sampler`: no_duplicates #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: epoch - `prediction_loss_only`: True - `per_device_train_batch_size`: 8 - `per_device_eval_batch_size`: 8 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 4 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 1e-05 - `weight_decay`: 0.01 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 4 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: True - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch_fused - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: True - `resume_from_checkpoint`: None - `hub_model_id`: Shashwat13333/bge-base-en-v1.5_v3 - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: bge-base-en-v1.5_v3 - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional </details> ### Training Logs | Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |:----------:|:-----:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| | 0.2105 | 1 | 24.6456 | - | - | - | - | - | | 0.8421 | 4 | - | 0.4674 | 0.4603 | 0.4340 | 0.4308 | 0.3485 | | 1.2105 | 5 | 19.7625 | - | - | - | - | - | | **1.8421** | **8** | **-** | **0.4873** | **0.477** | **0.4744** | **0.4591** | **0.3772** | | 2.4211 | 10 | 16.24 | - | - | - | - | - | | 2.8421 | 12 | - | 0.5446 | 0.4638 | 0.4531 | 0.3992 | 0.3599 | | 3.6316 | 15 | 14.3556 | - | - | - | - | - | | 3.8421 | 16 | - | 0.5168 | 0.4700 | 0.4827 | 0.4287 | 0.3836 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.11.11 - Sentence Transformers: 3.4.1 - Transformers: 4.48.2 - PyTorch: 2.5.1+cu124 - Accelerate: 1.3.0 - Datasets: 3.2.0 - Tokenizers: 0.21.0 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MatryoshkaLoss ```bibtex @misc{kusupati2024matryoshka, title={Matryoshka Representation Learning}, author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, year={2024}, eprint={2205.13147}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
[ "CRAFT" ]
Teradata/snowflake-arctic-embed-m-v2.0
Teradata
sentence-similarity
[ "onnx", "feature-extraction", "mteb", "arctic", "snowflake-arctic-embed", "teradata", "sentence-similarity", "af", "ar", "az", "be", "bg", "bn", "ca", "ceb", "cs", "cy", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fr", "gl", "gu", "he", "hi", "hr", "ht", "hu", "hy", "id", "is", "it", "ja", "jv", "ka", "kk", "km", "kn", "ko", "ky", "lo", "lt", "lv", "mk", "ml", "mn", "mr", "ms", "my", "ne", "nl", "pa", "pl", "pt", "qu", "ro", "ru", "si", "sk", "sl", "so", "sq", "sr", "sv", "sw", "ta", "te", "th", "tl", "tr", "uk", "ur", "vi", "yo", "zh", "license:apache-2.0", "model-index", "region:us" ]
2025-02-12T17:17:47Z
2025-03-04T10:04:36+00:00
31
0
--- language: - af - ar - az - be - bg - bn - ca - ceb - cs - cy - da - de - el - en - es - et - eu - fa - fi - fr - gl - gu - he - hi - hr - ht - hu - hy - id - is - it - ja - jv - ka - kk - km - kn - ko - ky - lo - lt - lv - mk - ml - mn - mr - ms - my - ne - nl - pa - pl - pt - qu - ro - ru - si - sk - sl - so - sq - sr - sv - sw - ta - te - th - tl - tr - uk - ur - vi - yo - zh license: apache-2.0 pipeline_tag: sentence-similarity tags: - feature-extraction - mteb - arctic - snowflake-arctic-embed - onnx - teradata model-index: - name: snowflake-arctic-embed-m-v2.0 results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en-ext) type: mteb/amazon_counterfactual config: en-ext split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 66.6867 - type: f1 value: 55.0373 - type: f1_weighted value: 73.07430000000001 - type: ap value: 18.077399999999997 - type: ap_weighted value: 18.077399999999997 - type: main_score value: 66.6867 - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 66.194 - type: f1 value: 60.854299999999995 - type: f1_weighted value: 69.57339999999999 - type: ap value: 30.279099999999996 - type: ap_weighted value: 30.279099999999996 - type: main_score value: 66.194 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification (default) type: mteb/amazon_polarity config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 70.3589 - type: f1 value: 70.0409 - type: f1_weighted value: 70.0409 - type: ap value: 64.81949999999999 - type: ap_weighted value: 64.81949999999999 - type: main_score value: 70.3589 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 33.766 - type: f1 value: 33.3656 - type: f1_weighted value: 33.3656 - type: main_score value: 33.766 - task: type: Retrieval dataset: name: MTEB ArguAna (default) type: mteb/arguana config: default split: test revision: c22ab2a51041ffd869aaddef7af8d8215647e41a metrics: - type: ndcg_at_1 value: 33.144 - type: ndcg_at_3 value: 47.909 - type: ndcg_at_5 value: 52.932 - type: ndcg_at_10 value: 58.011 - type: ndcg_at_20 value: 60.168 - type: ndcg_at_100 value: 60.928000000000004 - type: ndcg_at_1000 value: 61.046 - type: map_at_1 value: 33.144 - type: map_at_3 value: 44.156 - type: map_at_5 value: 46.951 - type: map_at_10 value: 49.071999999999996 - type: map_at_20 value: 49.692 - type: map_at_100 value: 49.809 - type: map_at_1000 value: 49.815 - type: recall_at_1 value: 33.144 - type: recall_at_3 value: 58.819 - type: recall_at_5 value: 70.982 - type: recall_at_10 value: 86.558 - type: recall_at_20 value: 94.879 - type: recall_at_100 value: 98.791 - type: recall_at_1000 value: 99.644 - type: precision_at_1 value: 33.144 - type: precision_at_3 value: 19.606 - type: precision_at_5 value: 14.196 - type: precision_at_10 value: 8.656 - type: precision_at_20 value: 4.744000000000001 - type: precision_at_100 value: 0.988 - type: precision_at_1000 value: 0.1 - type: mrr_at_1 value: 33.4993 - type: mrr_at_3 value: 44.393100000000004 - type: mrr_at_5 value: 47.131299999999996 - type: mrr_at_10 value: 49.264599999999994 - type: mrr_at_20 value: 49.8707 - type: mrr_at_100 value: 49.987700000000004 - type: mrr_at_1000 value: 49.993700000000004 - type: nauc_ndcg_at_1_max value: -10.8287 - type: nauc_ndcg_at_1_std value: -17.1177 - type: nauc_ndcg_at_1_diff1 value: 14.4508 - type: nauc_ndcg_at_3_max value: -7.7004 - type: nauc_ndcg_at_3_std value: -16.6705 - type: nauc_ndcg_at_3_diff1 value: 10.0448 - type: nauc_ndcg_at_5_max value: -7.0436 - type: nauc_ndcg_at_5_std value: -15.8744 - type: nauc_ndcg_at_5_diff1 value: 9.1132 - type: nauc_ndcg_at_10_max value: -7.4729 - type: nauc_ndcg_at_10_std value: -14.9349 - type: nauc_ndcg_at_10_diff1 value: 8.527700000000001 - type: nauc_ndcg_at_20_max value: -6.997000000000001 - type: nauc_ndcg_at_20_std value: -14.688399999999998 - type: nauc_ndcg_at_20_diff1 value: 9.7605 - type: nauc_ndcg_at_100_max value: -7.5599 - type: nauc_ndcg_at_100_std value: -15.0565 - type: nauc_ndcg_at_100_diff1 value: 10.2688 - type: nauc_ndcg_at_1000_max value: -7.675800000000001 - type: nauc_ndcg_at_1000_std value: -15.223500000000001 - type: nauc_ndcg_at_1000_diff1 value: 10.32 - type: nauc_map_at_1_max value: -10.8287 - type: nauc_map_at_1_std value: -17.1177 - type: nauc_map_at_1_diff1 value: 14.4508 - type: nauc_map_at_3_max value: -8.5473 - type: nauc_map_at_3_std value: -16.6674 - type: nauc_map_at_3_diff1 value: 11.1004 - type: nauc_map_at_5_max value: -8.1927 - type: nauc_map_at_5_std value: -16.2275 - type: nauc_map_at_5_diff1 value: 10.678600000000001 - type: nauc_map_at_10_max value: -8.3855 - type: nauc_map_at_10_std value: -15.8309 - type: nauc_map_at_10_diff1 value: 10.5414 - type: nauc_map_at_20_max value: -8.277700000000001 - type: nauc_map_at_20_std value: -15.824 - type: nauc_map_at_20_diff1 value: 10.8494 - type: nauc_map_at_100_max value: -8.3178 - type: nauc_map_at_100_std value: -15.848300000000002 - type: nauc_map_at_100_diff1 value: 10.9384 - type: nauc_map_at_1000_max value: -8.319799999999999 - type: nauc_map_at_1000_std value: -15.8522 - type: nauc_map_at_1000_diff1 value: 10.9401 - type: nauc_recall_at_1_max value: -10.8287 - type: nauc_recall_at_1_std value: -17.1177 - type: nauc_recall_at_1_diff1 value: 14.4508 - type: nauc_recall_at_3_max value: -5.0587 - type: nauc_recall_at_3_std value: -16.730800000000002 - type: nauc_recall_at_3_diff1 value: 6.8079 - type: nauc_recall_at_5_max value: -2.6783 - type: nauc_recall_at_5_std value: -14.5046 - type: nauc_recall_at_5_diff1 value: 3.096 - type: nauc_recall_at_10_max value: -1.5855000000000001 - type: nauc_recall_at_10_std value: -8.2276 - type: nauc_recall_at_10_diff1 value: -6.1741 - type: nauc_recall_at_20_max value: 15.754299999999999 - type: nauc_recall_at_20_std value: 8.1974 - type: nauc_recall_at_20_diff1 value: -4.9207 - type: nauc_recall_at_100_max value: 20.4574 - type: nauc_recall_at_100_std value: 36.3741 - type: nauc_recall_at_100_diff1 value: -7.9483 - type: nauc_recall_at_1000_max value: 21.6023 - type: nauc_recall_at_1000_std value: 68.7296 - type: nauc_recall_at_1000_diff1 value: -24.9261 - type: nauc_precision_at_1_max value: -10.8287 - type: nauc_precision_at_1_std value: -17.1177 - type: nauc_precision_at_1_diff1 value: 14.4508 - type: nauc_precision_at_3_max value: -5.0587 - type: nauc_precision_at_3_std value: -16.730800000000002 - type: nauc_precision_at_3_diff1 value: 6.8079 - type: nauc_precision_at_5_max value: -2.6783 - type: nauc_precision_at_5_std value: -14.5046 - type: nauc_precision_at_5_diff1 value: 3.096 - type: nauc_precision_at_10_max value: -1.5855000000000001 - type: nauc_precision_at_10_std value: -8.2276 - type: nauc_precision_at_10_diff1 value: -6.1741 - type: nauc_precision_at_20_max value: 15.754299999999999 - type: nauc_precision_at_20_std value: 8.1974 - type: nauc_precision_at_20_diff1 value: -4.9207 - type: nauc_precision_at_100_max value: 20.4574 - type: nauc_precision_at_100_std value: 36.3741 - type: nauc_precision_at_100_diff1 value: -7.9483 - type: nauc_precision_at_1000_max value: 21.6023 - type: nauc_precision_at_1000_std value: 68.7296 - type: nauc_precision_at_1000_diff1 value: -24.9261 - type: nauc_mrr_at_1_max value: -11.251999999999999 - type: nauc_mrr_at_1_std value: -17.4386 - type: nauc_mrr_at_1_diff1 value: 13.414200000000001 - type: nauc_mrr_at_3_max value: -9.7985 - type: nauc_mrr_at_3_std value: -16.650000000000002 - type: nauc_mrr_at_3_diff1 value: 9.5099 - type: nauc_mrr_at_5_max value: -9.064 - type: nauc_mrr_at_5_std value: -16.4409 - type: nauc_mrr_at_5_diff1 value: 9.4773 - type: nauc_mrr_at_10_max value: -9.310400000000001 - type: nauc_mrr_at_10_std value: -16.0546 - type: nauc_mrr_at_10_diff1 value: 9.2528 - type: nauc_mrr_at_20_max value: -9.223099999999999 - type: nauc_mrr_at_20_std value: -16.0659 - type: nauc_mrr_at_20_diff1 value: 9.5259 - type: nauc_mrr_at_100_max value: -9.2678 - type: nauc_mrr_at_100_std value: -16.0911 - type: nauc_mrr_at_100_diff1 value: 9.608600000000001 - type: nauc_mrr_at_1000_max value: -9.2699 - type: nauc_mrr_at_1000_std value: -16.095100000000002 - type: nauc_mrr_at_1000_diff1 value: 9.6099 - type: main_score value: 58.011 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P (default) type: mteb/arxiv-clustering-p2p config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 44.684400000000004 - type: v_measure_std value: 13.5064 - type: main_score value: 44.684400000000004 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S (default) type: mteb/arxiv-clustering-s2s config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 35.0503 - type: v_measure_std value: 13.9543 - type: main_score value: 35.0503 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions (default) type: mteb/askubuntudupquestions-reranking config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 60.648500000000006 - type: mrr value: 74.528 - type: nAUC_map_max value: 19.4239 - type: nAUC_map_std value: 20.0729 - type: nAUC_map_diff1 value: 10.0382 - type: nAUC_mrr_max value: 30.693199999999997 - type: nAUC_mrr_std value: 27.1279 - type: nAUC_mrr_diff1 value: 23.0291 - type: main_score value: 60.648500000000006 - task: type: STS dataset: name: MTEB BIOSSES (default) type: mteb/biosses-sts config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: pearson value: 89.5081 - type: spearman value: 87.0568 - type: cosine_pearson value: 89.5081 - type: cosine_spearman value: 87.0568 - type: manhattan_pearson value: 88.1247 - type: manhattan_spearman value: 87.2556 - type: euclidean_pearson value: 88.3266 - type: euclidean_spearman value: 87.0568 - type: main_score value: 87.0568 - task: type: Classification dataset: name: MTEB Banking77Classification (default) type: mteb/banking77 config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 80.18180000000001 - type: f1 value: 79.5538 - type: f1_weighted value: 79.5538 - type: main_score value: 80.18180000000001 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P (default) type: mteb/biorxiv-clustering-p2p config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 36.0126 - type: v_measure_std value: 0.47019999999999995 - type: main_score value: 36.0126 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S (default) type: mteb/biorxiv-clustering-s2s config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 28.6331 - type: v_measure_std value: 0.8607999999999999 - type: main_score value: 28.6331 - task: type: Retrieval dataset: name: MTEB CQADupstackAndroidRetrieval (default) type: mteb/cqadupstack-android config: default split: test revision: f46a197baaae43b4f621051089b82a364682dfeb metrics: - type: ndcg_at_1 value: 45.207 - type: ndcg_at_3 value: 51.31400000000001 - type: ndcg_at_5 value: 54.093999999999994 - type: ndcg_at_10 value: 56.31 - type: ndcg_at_20 value: 58.378 - type: ndcg_at_100 value: 61.307 - type: ndcg_at_1000 value: 62.724999999999994 - type: map_at_1 value: 37.732 - type: map_at_3 value: 46.263 - type: map_at_5 value: 48.553000000000004 - type: map_at_10 value: 49.984 - type: map_at_20 value: 50.888999999999996 - type: map_at_100 value: 51.568999999999996 - type: map_at_1000 value: 51.666999999999994 - type: recall_at_1 value: 37.732 - type: recall_at_3 value: 53.736 - type: recall_at_5 value: 60.95399999999999 - type: recall_at_10 value: 68.062 - type: recall_at_20 value: 75.149 - type: recall_at_100 value: 88.075 - type: recall_at_1000 value: 96.878 - type: precision_at_1 value: 45.207 - type: precision_at_3 value: 24.368000000000002 - type: precision_at_5 value: 17.854 - type: precision_at_10 value: 10.558 - type: precision_at_20 value: 6.23 - type: precision_at_100 value: 1.614 - type: precision_at_1000 value: 0.202 - type: mrr_at_1 value: 45.2074 - type: mrr_at_3 value: 52.9804 - type: mrr_at_5 value: 54.718599999999995 - type: mrr_at_10 value: 55.5713 - type: mrr_at_20 value: 55.94 - type: mrr_at_100 value: 56.21699999999999 - type: mrr_at_1000 value: 56.2504 - type: nauc_ndcg_at_1_max value: 43.7697 - type: nauc_ndcg_at_1_std value: -3.9530000000000003 - type: nauc_ndcg_at_1_diff1 value: 57.75320000000001 - type: nauc_ndcg_at_3_max value: 42.7238 - type: nauc_ndcg_at_3_std value: -3.5654 - type: nauc_ndcg_at_3_diff1 value: 53.552299999999995 - type: nauc_ndcg_at_5_max value: 43.115500000000004 - type: nauc_ndcg_at_5_std value: -2.1444 - type: nauc_ndcg_at_5_diff1 value: 53.130500000000005 - type: nauc_ndcg_at_10_max value: 43.0188 - type: nauc_ndcg_at_10_std value: -3.1515 - type: nauc_ndcg_at_10_diff1 value: 53.593199999999996 - type: nauc_ndcg_at_20_max value: 43.4617 - type: nauc_ndcg_at_20_std value: -2.9284 - type: nauc_ndcg_at_20_diff1 value: 53.28000000000001 - type: nauc_ndcg_at_100_max value: 44.0704 - type: nauc_ndcg_at_100_std value: -0.5772 - type: nauc_ndcg_at_100_diff1 value: 53.439899999999994 - type: nauc_ndcg_at_1000_max value: 44.256099999999996 - type: nauc_ndcg_at_1000_std value: -1.1407 - type: nauc_ndcg_at_1000_diff1 value: 53.8728 - type: nauc_map_at_1_max value: 36.613800000000005 - type: nauc_map_at_1_std value: -5.8014 - type: nauc_map_at_1_diff1 value: 59.0186 - type: nauc_map_at_3_max value: 40.8666 - type: nauc_map_at_3_std value: -4.886299999999999 - type: nauc_map_at_3_diff1 value: 55.324600000000004 - type: nauc_map_at_5_max value: 41.9942 - type: nauc_map_at_5_std value: -3.9361 - type: nauc_map_at_5_diff1 value: 54.8805 - type: nauc_map_at_10_max value: 42.1621 - type: nauc_map_at_10_std value: -4.3264 - type: nauc_map_at_10_diff1 value: 55.0133 - type: nauc_map_at_20_max value: 42.5837 - type: nauc_map_at_20_std value: -3.8526 - type: nauc_map_at_20_diff1 value: 54.895700000000005 - type: nauc_map_at_100_max value: 42.7645 - type: nauc_map_at_100_std value: -3.4568000000000003 - type: nauc_map_at_100_diff1 value: 54.98030000000001 - type: nauc_map_at_1000_max value: 42.7915 - type: nauc_map_at_1000_std value: -3.4715999999999996 - type: nauc_map_at_1000_diff1 value: 55.0117 - type: nauc_recall_at_1_max value: 36.613800000000005 - type: nauc_recall_at_1_std value: -5.8014 - type: nauc_recall_at_1_diff1 value: 59.0186 - type: nauc_recall_at_3_max value: 39.3588 - type: nauc_recall_at_3_std value: -3.29 - type: nauc_recall_at_3_diff1 value: 50.1633 - type: nauc_recall_at_5_max value: 39.7596 - type: nauc_recall_at_5_std value: 0.4483 - type: nauc_recall_at_5_diff1 value: 47.598600000000005 - type: nauc_recall_at_10_max value: 37.5367 - type: nauc_recall_at_10_std value: -2.5935 - type: nauc_recall_at_10_diff1 value: 46.824799999999996 - type: nauc_recall_at_20_max value: 38.521100000000004 - type: nauc_recall_at_20_std value: -2.5774 - type: nauc_recall_at_20_diff1 value: 44.099 - type: nauc_recall_at_100_max value: 44.043 - type: nauc_recall_at_100_std value: 22.724 - type: nauc_recall_at_100_diff1 value: 40.4973 - type: nauc_recall_at_1000_max value: 59.780100000000004 - type: nauc_recall_at_1000_std value: 52.512 - type: nauc_recall_at_1000_diff1 value: 45.2841 - type: nauc_precision_at_1_max value: 43.7697 - type: nauc_precision_at_1_std value: -3.9530000000000003 - type: nauc_precision_at_1_diff1 value: 57.75320000000001 - type: nauc_precision_at_3_max value: 37.486000000000004 - type: nauc_precision_at_3_std value: -1.0619 - type: nauc_precision_at_3_diff1 value: 28.264699999999998 - type: nauc_precision_at_5_max value: 31.613599999999998 - type: nauc_precision_at_5_std value: 3.6863 - type: nauc_precision_at_5_diff1 value: 16.0838 - type: nauc_precision_at_10_max value: 23.4082 - type: nauc_precision_at_10_std value: 3.3977 - type: nauc_precision_at_10_diff1 value: 7.3632 - type: nauc_precision_at_20_max value: 16.7236 - type: nauc_precision_at_20_std value: 5.7516 - type: nauc_precision_at_20_diff1 value: -0.8460000000000001 - type: nauc_precision_at_100_max value: 3.9043 - type: nauc_precision_at_100_std value: 7.7799 - type: nauc_precision_at_100_diff1 value: -11.0756 - type: nauc_precision_at_1000_max value: -7.728 - type: nauc_precision_at_1000_std value: -1.9303000000000001 - type: nauc_precision_at_1000_diff1 value: -17.025000000000002 - type: nauc_mrr_at_1_max value: 43.7697 - type: nauc_mrr_at_1_std value: -3.9530000000000003 - type: nauc_mrr_at_1_diff1 value: 57.75320000000001 - type: nauc_mrr_at_3_max value: 44.8007 - type: nauc_mrr_at_3_std value: -2.9754 - type: nauc_mrr_at_3_diff1 value: 53.7928 - type: nauc_mrr_at_5_max value: 44.860499999999995 - type: nauc_mrr_at_5_std value: -1.7683 - type: nauc_mrr_at_5_diff1 value: 53.5852 - type: nauc_mrr_at_10_max value: 44.8025 - type: nauc_mrr_at_10_std value: -2.1691 - type: nauc_mrr_at_10_diff1 value: 53.880300000000005 - type: nauc_mrr_at_20_max value: 44.7838 - type: nauc_mrr_at_20_std value: -2.3529 - type: nauc_mrr_at_20_diff1 value: 53.890499999999996 - type: nauc_mrr_at_100_max value: 44.7905 - type: nauc_mrr_at_100_std value: -2.1931 - type: nauc_mrr_at_100_diff1 value: 53.9458 - type: nauc_mrr_at_1000_max value: 44.7943 - type: nauc_mrr_at_1000_std value: -2.2006 - type: nauc_mrr_at_1000_diff1 value: 53.954800000000006 - type: main_score value: 56.31 - task: type: Retrieval dataset: name: MTEB CQADupstackEnglishRetrieval (default) type: mteb/cqadupstack-english config: default split: test revision: ad9991cb51e31e31e430383c75ffb2885547b5f0 metrics: - type: ndcg_at_1 value: 44.840999999999994 - type: ndcg_at_3 value: 49.217 - type: ndcg_at_5 value: 50.934000000000005 - type: ndcg_at_10 value: 53.142999999999994 - type: ndcg_at_20 value: 54.778000000000006 - type: ndcg_at_100 value: 57.241 - type: ndcg_at_1000 value: 58.967999999999996 - type: map_at_1 value: 35.675000000000004 - type: map_at_3 value: 44.017 - type: map_at_5 value: 45.786 - type: map_at_10 value: 47.204 - type: map_at_20 value: 47.946 - type: map_at_100 value: 48.564 - type: map_at_1000 value: 48.684 - type: recall_at_1 value: 35.675000000000004 - type: recall_at_3 value: 50.641000000000005 - type: recall_at_5 value: 55.897 - type: recall_at_10 value: 62.873999999999995 - type: recall_at_20 value: 68.766 - type: recall_at_100 value: 79.90899999999999 - type: recall_at_1000 value: 90.78399999999999 - type: precision_at_1 value: 44.840999999999994 - type: precision_at_3 value: 23.843 - type: precision_at_5 value: 16.637 - type: precision_at_10 value: 9.968 - type: precision_at_20 value: 5.863 - type: precision_at_100 value: 1.562 - type: precision_at_1000 value: 0.197 - type: mrr_at_1 value: 44.840799999999994 - type: mrr_at_3 value: 51.634800000000006 - type: mrr_at_5 value: 52.746300000000005 - type: mrr_at_10 value: 53.6323 - type: mrr_at_20 value: 53.9565 - type: mrr_at_100 value: 54.198 - type: mrr_at_1000 value: 54.234899999999996 - type: nauc_ndcg_at_1_max value: 50.3827 - type: nauc_ndcg_at_1_std value: -0.8129000000000001 - type: nauc_ndcg_at_1_diff1 value: 59.7518 - type: nauc_ndcg_at_3_max value: 49.6676 - type: nauc_ndcg_at_3_std value: -2.1006 - type: nauc_ndcg_at_3_diff1 value: 52.7373 - type: nauc_ndcg_at_5_max value: 50.5186 - type: nauc_ndcg_at_5_std value: -1.5242 - type: nauc_ndcg_at_5_diff1 value: 53.234300000000005 - type: nauc_ndcg_at_10_max value: 50.5247 - type: nauc_ndcg_at_10_std value: -1.2392 - type: nauc_ndcg_at_10_diff1 value: 53.1045 - type: nauc_ndcg_at_20_max value: 51.3292 - type: nauc_ndcg_at_20_std value: -0.06570000000000001 - type: nauc_ndcg_at_20_diff1 value: 53.48349999999999 - type: nauc_ndcg_at_100_max value: 51.588100000000004 - type: nauc_ndcg_at_100_std value: 1.9398 - type: nauc_ndcg_at_100_diff1 value: 52.755399999999995 - type: nauc_ndcg_at_1000_max value: 51.5558 - type: nauc_ndcg_at_1000_std value: 2.3446000000000002 - type: nauc_ndcg_at_1000_diff1 value: 52.9377 - type: nauc_map_at_1_max value: 40.0957 - type: nauc_map_at_1_std value: -11.972 - type: nauc_map_at_1_diff1 value: 61.88249999999999 - type: nauc_map_at_3_max value: 45.6088 - type: nauc_map_at_3_std value: -9.249699999999999 - type: nauc_map_at_3_diff1 value: 56.260299999999994 - type: nauc_map_at_5_max value: 47.2279 - type: nauc_map_at_5_std value: -7.407500000000001 - type: nauc_map_at_5_diff1 value: 55.7894 - type: nauc_map_at_10_max value: 48.0167 - type: nauc_map_at_10_std value: -6.1371 - type: nauc_map_at_10_diff1 value: 55.4646 - type: nauc_map_at_20_max value: 48.6024 - type: nauc_map_at_20_std value: -5.1559 - type: nauc_map_at_20_diff1 value: 55.338100000000004 - type: nauc_map_at_100_max value: 48.993700000000004 - type: nauc_map_at_100_std value: -4.1873000000000005 - type: nauc_map_at_100_diff1 value: 55.1214 - type: nauc_map_at_1000_max value: 49.054500000000004 - type: nauc_map_at_1000_std value: -4.0072 - type: nauc_map_at_1000_diff1 value: 55.109300000000005 - type: nauc_recall_at_1_max value: 40.0957 - type: nauc_recall_at_1_std value: -11.972 - type: nauc_recall_at_1_diff1 value: 61.88249999999999 - type: nauc_recall_at_3_max value: 44.188 - type: nauc_recall_at_3_std value: -8.3756 - type: nauc_recall_at_3_diff1 value: 48.6817 - type: nauc_recall_at_5_max value: 46.6706 - type: nauc_recall_at_5_std value: -4.1561 - type: nauc_recall_at_5_diff1 value: 47.6738 - type: nauc_recall_at_10_max value: 47.614200000000004 - type: nauc_recall_at_10_std value: -1.1676 - type: nauc_recall_at_10_diff1 value: 45.628099999999996 - type: nauc_recall_at_20_max value: 51.490100000000005 - type: nauc_recall_at_20_std value: 5.111000000000001 - type: nauc_recall_at_20_diff1 value: 45.730199999999996 - type: nauc_recall_at_100_max value: 54.0635 - type: nauc_recall_at_100_std value: 19.8381 - type: nauc_recall_at_100_diff1 value: 39.1924 - type: nauc_recall_at_1000_max value: 56.3672 - type: nauc_recall_at_1000_std value: 33.9274 - type: nauc_recall_at_1000_diff1 value: 38.1103 - type: nauc_precision_at_1_max value: 50.3827 - type: nauc_precision_at_1_std value: -0.8129000000000001 - type: nauc_precision_at_1_diff1 value: 59.7518 - type: nauc_precision_at_3_max value: 46.281299999999995 - type: nauc_precision_at_3_std value: 14.7166 - type: nauc_precision_at_3_diff1 value: 24.211 - type: nauc_precision_at_5_max value: 44.466899999999995 - type: nauc_precision_at_5_std value: 22.5103 - type: nauc_precision_at_5_diff1 value: 15.746099999999998 - type: nauc_precision_at_10_max value: 38.0804 - type: nauc_precision_at_10_std value: 29.677999999999997 - type: nauc_precision_at_10_diff1 value: 4.886299999999999 - type: nauc_precision_at_20_max value: 32.302 - type: nauc_precision_at_20_std value: 34.8443 - type: nauc_precision_at_20_diff1 value: -2.9212 - type: nauc_precision_at_100_max value: 21.4725 - type: nauc_precision_at_100_std value: 41.8747 - type: nauc_precision_at_100_diff1 value: -14.976600000000001 - type: nauc_precision_at_1000_max value: 10.3891 - type: nauc_precision_at_1000_std value: 39.4181 - type: nauc_precision_at_1000_diff1 value: -21.9914 - type: nauc_mrr_at_1_max value: 50.3827 - type: nauc_mrr_at_1_std value: -0.8129000000000001 - type: nauc_mrr_at_1_diff1 value: 59.7518 - type: nauc_mrr_at_3_max value: 51.9937 - type: nauc_mrr_at_3_std value: 2.1604 - type: nauc_mrr_at_3_diff1 value: 54.58539999999999 - type: nauc_mrr_at_5_max value: 52.39319999999999 - type: nauc_mrr_at_5_std value: 2.8171 - type: nauc_mrr_at_5_diff1 value: 54.825100000000006 - type: nauc_mrr_at_10_max value: 52.2047 - type: nauc_mrr_at_10_std value: 2.6525 - type: nauc_mrr_at_10_diff1 value: 54.703500000000005 - type: nauc_mrr_at_20_max value: 52.251999999999995 - type: nauc_mrr_at_20_std value: 2.7842 - type: nauc_mrr_at_20_diff1 value: 54.76689999999999 - type: nauc_mrr_at_100_max value: 52.2776 - type: nauc_mrr_at_100_std value: 2.9701999999999997 - type: nauc_mrr_at_100_diff1 value: 54.712799999999994 - type: nauc_mrr_at_1000_max value: 52.274699999999996 - type: nauc_mrr_at_1000_std value: 2.9652000000000003 - type: nauc_mrr_at_1000_diff1 value: 54.7296 - type: main_score value: 53.142999999999994 - task: type: Retrieval dataset: name: MTEB CQADupstackGamingRetrieval (default) type: mteb/cqadupstack-gaming config: default split: test revision: 4885aa143210c98657558c04aaf3dc47cfb54340 metrics: - type: ndcg_at_1 value: 53.542 - type: ndcg_at_3 value: 60.098 - type: ndcg_at_5 value: 62.515 - type: ndcg_at_10 value: 65.315 - type: ndcg_at_20 value: 66.683 - type: ndcg_at_100 value: 68.47800000000001 - type: ndcg_at_1000 value: 69.329 - type: map_at_1 value: 47.135 - type: map_at_3 value: 56.548 - type: map_at_5 value: 58.306000000000004 - type: map_at_10 value: 59.819 - type: map_at_20 value: 60.328 - type: map_at_100 value: 60.653999999999996 - type: map_at_1000 value: 60.699000000000005 - type: recall_at_1 value: 47.135 - type: recall_at_3 value: 64.371 - type: recall_at_5 value: 70.293 - type: recall_at_10 value: 78.346 - type: recall_at_20 value: 83.369 - type: recall_at_100 value: 92.04599999999999 - type: recall_at_1000 value: 97.933 - type: precision_at_1 value: 53.542 - type: precision_at_3 value: 26.395000000000003 - type: precision_at_5 value: 17.806 - type: precision_at_10 value: 10.238 - type: precision_at_20 value: 5.586 - type: precision_at_100 value: 1.266 - type: precision_at_1000 value: 0.13799999999999998 - type: mrr_at_1 value: 53.5423 - type: mrr_at_3 value: 60.595600000000005 - type: mrr_at_5 value: 61.931000000000004 - type: mrr_at_10 value: 62.8406 - type: mrr_at_20 value: 63.1667 - type: mrr_at_100 value: 63.347699999999996 - type: mrr_at_1000 value: 63.368100000000005 - type: nauc_ndcg_at_1_max value: 50.004599999999996 - type: nauc_ndcg_at_1_std value: -4.3123000000000005 - type: nauc_ndcg_at_1_diff1 value: 61.1973 - type: nauc_ndcg_at_3_max value: 48.65 - type: nauc_ndcg_at_3_std value: -6.0419 - type: nauc_ndcg_at_3_diff1 value: 56.712700000000005 - type: nauc_ndcg_at_5_max value: 50.0908 - type: nauc_ndcg_at_5_std value: -4.4674 - type: nauc_ndcg_at_5_diff1 value: 56.216 - type: nauc_ndcg_at_10_max value: 50.578 - type: nauc_ndcg_at_10_std value: -2.661 - type: nauc_ndcg_at_10_diff1 value: 55.9162 - type: nauc_ndcg_at_20_max value: 51.3801 - type: nauc_ndcg_at_20_std value: -0.8059999999999999 - type: nauc_ndcg_at_20_diff1 value: 55.8654 - type: nauc_ndcg_at_100_max value: 51.4594 - type: nauc_ndcg_at_100_std value: -0.3524 - type: nauc_ndcg_at_100_diff1 value: 56.131699999999995 - type: nauc_ndcg_at_1000_max value: 51.6105 - type: nauc_ndcg_at_1000_std value: -0.8832 - type: nauc_ndcg_at_1000_diff1 value: 56.6507 - type: nauc_map_at_1_max value: 42.7316 - type: nauc_map_at_1_std value: -6.979100000000001 - type: nauc_map_at_1_diff1 value: 61.6382 - type: nauc_map_at_3_max value: 47.6139 - type: nauc_map_at_3_std value: -7.0931 - type: nauc_map_at_3_diff1 value: 58.2923 - type: nauc_map_at_5_max value: 48.6039 - type: nauc_map_at_5_std value: -5.9601 - type: nauc_map_at_5_diff1 value: 57.7052 - type: nauc_map_at_10_max value: 49.2631 - type: nauc_map_at_10_std value: -4.808 - type: nauc_map_at_10_diff1 value: 57.5979 - type: nauc_map_at_20_max value: 49.6783 - type: nauc_map_at_20_std value: -4.0106 - type: nauc_map_at_20_diff1 value: 57.5781 - type: nauc_map_at_100_max value: 49.775000000000006 - type: nauc_map_at_100_std value: -3.8082 - type: nauc_map_at_100_diff1 value: 57.6013 - type: nauc_map_at_1000_max value: 49.8135 - type: nauc_map_at_1000_std value: -3.7974 - type: nauc_map_at_1000_diff1 value: 57.6323 - type: nauc_recall_at_1_max value: 42.7316 - type: nauc_recall_at_1_std value: -6.979100000000001 - type: nauc_recall_at_1_diff1 value: 61.6382 - type: nauc_recall_at_3_max value: 46.1138 - type: nauc_recall_at_3_std value: -8.6906 - type: nauc_recall_at_3_diff1 value: 52.6263 - type: nauc_recall_at_5_max value: 49.074200000000005 - type: nauc_recall_at_5_std value: -4.5975 - type: nauc_recall_at_5_diff1 value: 49.994 - type: nauc_recall_at_10_max value: 49.696 - type: nauc_recall_at_10_std value: 2.049 - type: nauc_recall_at_10_diff1 value: 46.7897 - type: nauc_recall_at_20_max value: 54.03980000000001 - type: nauc_recall_at_20_std value: 14.4898 - type: nauc_recall_at_20_diff1 value: 43.8642 - type: nauc_recall_at_100_max value: 57.23629999999999 - type: nauc_recall_at_100_std value: 32.6507 - type: nauc_recall_at_100_diff1 value: 38.4662 - type: nauc_recall_at_1000_max value: 81.5918 - type: nauc_recall_at_1000_std value: 67.0848 - type: nauc_recall_at_1000_diff1 value: 40.5123 - type: nauc_precision_at_1_max value: 50.004599999999996 - type: nauc_precision_at_1_std value: -4.3123000000000005 - type: nauc_precision_at_1_diff1 value: 61.1973 - type: nauc_precision_at_3_max value: 41.0359 - type: nauc_precision_at_3_std value: 2.2363 - type: nauc_precision_at_3_diff1 value: 26.9914 - type: nauc_precision_at_5_max value: 38.3114 - type: nauc_precision_at_5_std value: 8.7643 - type: nauc_precision_at_5_diff1 value: 17.0673 - type: nauc_precision_at_10_max value: 31.1391 - type: nauc_precision_at_10_std value: 17.1411 - type: nauc_precision_at_10_diff1 value: 4.9287 - type: nauc_precision_at_20_max value: 27.7595 - type: nauc_precision_at_20_std value: 25.470399999999998 - type: nauc_precision_at_20_diff1 value: -2.6803 - type: nauc_precision_at_100_max value: 18.2146 - type: nauc_precision_at_100_std value: 29.244300000000003 - type: nauc_precision_at_100_diff1 value: -13.083 - type: nauc_precision_at_1000_max value: 13.5621 - type: nauc_precision_at_1000_std value: 26.3405 - type: nauc_precision_at_1000_diff1 value: -15.398200000000001 - type: nauc_mrr_at_1_max value: 50.004599999999996 - type: nauc_mrr_at_1_std value: -4.3123000000000005 - type: nauc_mrr_at_1_diff1 value: 61.1973 - type: nauc_mrr_at_3_max value: 50.114599999999996 - type: nauc_mrr_at_3_std value: -4.7759 - type: nauc_mrr_at_3_diff1 value: 57.9624 - type: nauc_mrr_at_5_max value: 50.956900000000005 - type: nauc_mrr_at_5_std value: -3.7144999999999997 - type: nauc_mrr_at_5_diff1 value: 57.784400000000005 - type: nauc_mrr_at_10_max value: 50.8112 - type: nauc_mrr_at_10_std value: -3.3526 - type: nauc_mrr_at_10_diff1 value: 57.674499999999995 - type: nauc_mrr_at_20_max value: 50.9425 - type: nauc_mrr_at_20_std value: -2.9598 - type: nauc_mrr_at_20_diff1 value: 57.6704 - type: nauc_mrr_at_100_max value: 50.901799999999994 - type: nauc_mrr_at_100_std value: -3.0112 - type: nauc_mrr_at_100_diff1 value: 57.736200000000004 - type: nauc_mrr_at_1000_max value: 50.901399999999995 - type: nauc_mrr_at_1000_std value: -3.0314 - type: nauc_mrr_at_1000_diff1 value: 57.747400000000006 - type: main_score value: 65.315 - task: type: Retrieval dataset: name: MTEB CQADupstackGisRetrieval (default) type: mteb/cqadupstack-gis config: default split: test revision: 5003b3064772da1887988e05400cf3806fe491f2 metrics: - type: ndcg_at_1 value: 33.898 - type: ndcg_at_3 value: 39.875 - type: ndcg_at_5 value: 42.455999999999996 - type: ndcg_at_10 value: 45.4 - type: ndcg_at_20 value: 47.831 - type: ndcg_at_100 value: 50.428 - type: ndcg_at_1000 value: 52.037 - type: map_at_1 value: 31.357000000000003 - type: map_at_3 value: 37.358999999999995 - type: map_at_5 value: 38.948 - type: map_at_10 value: 40.243 - type: map_at_20 value: 40.98 - type: map_at_100 value: 41.349999999999994 - type: map_at_1000 value: 41.418 - type: recall_at_1 value: 31.357000000000003 - type: recall_at_3 value: 44.324000000000005 - type: recall_at_5 value: 50.449 - type: recall_at_10 value: 59.17400000000001 - type: recall_at_20 value: 68.272 - type: recall_at_100 value: 81.672 - type: recall_at_1000 value: 93.572 - type: precision_at_1 value: 33.898 - type: precision_at_3 value: 16.648 - type: precision_at_5 value: 11.503 - type: precision_at_10 value: 6.847 - type: precision_at_20 value: 3.9890000000000003 - type: precision_at_100 value: 0.9809999999999999 - type: precision_at_1000 value: 0.11499999999999999 - type: mrr_at_1 value: 33.8983 - type: mrr_at_3 value: 39.8117 - type: mrr_at_5 value: 41.2354 - type: mrr_at_10 value: 42.4212 - type: mrr_at_20 value: 43.0404 - type: mrr_at_100 value: 43.3429 - type: mrr_at_1000 value: 43.3894 - type: nauc_ndcg_at_1_max value: 36.1482 - type: nauc_ndcg_at_1_std value: -4.471 - type: nauc_ndcg_at_1_diff1 value: 44.1333 - type: nauc_ndcg_at_3_max value: 35.404 - type: nauc_ndcg_at_3_std value: -4.487 - type: nauc_ndcg_at_3_diff1 value: 40.3399 - type: nauc_ndcg_at_5_max value: 35.0036 - type: nauc_ndcg_at_5_std value: -4.0964 - type: nauc_ndcg_at_5_diff1 value: 38.2164 - type: nauc_ndcg_at_10_max value: 34.7255 - type: nauc_ndcg_at_10_std value: -2.9356 - type: nauc_ndcg_at_10_diff1 value: 37.3216 - type: nauc_ndcg_at_20_max value: 35.5433 - type: nauc_ndcg_at_20_std value: -1.8858 - type: nauc_ndcg_at_20_diff1 value: 36.6106 - type: nauc_ndcg_at_100_max value: 35.9643 - type: nauc_ndcg_at_100_std value: -1.6303 - type: nauc_ndcg_at_100_diff1 value: 37.515100000000004 - type: nauc_ndcg_at_1000_max value: 35.9222 - type: nauc_ndcg_at_1000_std value: -2.1452999999999998 - type: nauc_ndcg_at_1000_diff1 value: 37.472100000000005 - type: nauc_map_at_1_max value: 32.413599999999995 - type: nauc_map_at_1_std value: -7.391300000000001 - type: nauc_map_at_1_diff1 value: 45.5299 - type: nauc_map_at_3_max value: 34.1688 - type: nauc_map_at_3_std value: -5.6375 - type: nauc_map_at_3_diff1 value: 41.5371 - type: nauc_map_at_5_max value: 34.2057 - type: nauc_map_at_5_std value: -5.4512 - type: nauc_map_at_5_diff1 value: 40.3839 - type: nauc_map_at_10_max value: 34.3355 - type: nauc_map_at_10_std value: -4.7743 - type: nauc_map_at_10_diff1 value: 40.1027 - type: nauc_map_at_20_max value: 34.638400000000004 - type: nauc_map_at_20_std value: -4.4951 - type: nauc_map_at_20_diff1 value: 39.8905 - type: nauc_map_at_100_max value: 34.6621 - type: nauc_map_at_100_std value: -4.4568 - type: nauc_map_at_100_diff1 value: 39.9854 - type: nauc_map_at_1000_max value: 34.6674 - type: nauc_map_at_1000_std value: -4.4651000000000005 - type: nauc_map_at_1000_diff1 value: 39.9739 - type: nauc_recall_at_1_max value: 32.413599999999995 - type: nauc_recall_at_1_std value: -7.391300000000001 - type: nauc_recall_at_1_diff1 value: 45.5299 - type: nauc_recall_at_3_max value: 34.374500000000005 - type: nauc_recall_at_3_std value: -3.8977999999999997 - type: nauc_recall_at_3_diff1 value: 36.9855 - type: nauc_recall_at_5_max value: 33.5608 - type: nauc_recall_at_5_std value: -2.9009 - type: nauc_recall_at_5_diff1 value: 31.9638 - type: nauc_recall_at_10_max value: 32.1813 - type: nauc_recall_at_10_std value: 0.8024999999999999 - type: nauc_recall_at_10_diff1 value: 28.3153 - type: nauc_recall_at_20_max value: 35.0617 - type: nauc_recall_at_20_std value: 6.531199999999999 - type: nauc_recall_at_20_diff1 value: 23.6762 - type: nauc_recall_at_100_max value: 38.9147 - type: nauc_recall_at_100_std value: 12.4753 - type: nauc_recall_at_100_diff1 value: 26.1627 - type: nauc_recall_at_1000_max value: 45.8191 - type: nauc_recall_at_1000_std value: 17.1419 - type: nauc_recall_at_1000_diff1 value: 13.2284 - type: nauc_precision_at_1_max value: 36.1482 - type: nauc_precision_at_1_std value: -4.471 - type: nauc_precision_at_1_diff1 value: 44.1333 - type: nauc_precision_at_3_max value: 38.315 - type: nauc_precision_at_3_std value: -0.16019999999999998 - type: nauc_precision_at_3_diff1 value: 32.4158 - type: nauc_precision_at_5_max value: 36.3912 - type: nauc_precision_at_5_std value: 0.9605 - type: nauc_precision_at_5_diff1 value: 25.7513 - type: nauc_precision_at_10_max value: 34.043 - type: nauc_precision_at_10_std value: 5.6308 - type: nauc_precision_at_10_diff1 value: 20.5638 - type: nauc_precision_at_20_max value: 34.5796 - type: nauc_precision_at_20_std value: 10.0006 - type: nauc_precision_at_20_diff1 value: 13.069500000000001 - type: nauc_precision_at_100_max value: 27.5607 - type: nauc_precision_at_100_std value: 13.173399999999999 - type: nauc_precision_at_100_diff1 value: 6.1834 - type: nauc_precision_at_1000_max value: 15.5825 - type: nauc_precision_at_1000_std value: 9.9148 - type: nauc_precision_at_1000_diff1 value: -8.7873 - type: nauc_mrr_at_1_max value: 36.1482 - type: nauc_mrr_at_1_std value: -4.471 - type: nauc_mrr_at_1_diff1 value: 44.1333 - type: nauc_mrr_at_3_max value: 37.059799999999996 - type: nauc_mrr_at_3_std value: -2.7984999999999998 - type: nauc_mrr_at_3_diff1 value: 40.3801 - type: nauc_mrr_at_5_max value: 36.921 - type: nauc_mrr_at_5_std value: -2.5107 - type: nauc_mrr_at_5_diff1 value: 39.3331 - type: nauc_mrr_at_10_max value: 36.5977 - type: nauc_mrr_at_10_std value: -2.3744 - type: nauc_mrr_at_10_diff1 value: 38.851200000000006 - type: nauc_mrr_at_20_max value: 36.7083 - type: nauc_mrr_at_20_std value: -2.164 - type: nauc_mrr_at_20_diff1 value: 38.729200000000006 - type: nauc_mrr_at_100_max value: 36.7448 - type: nauc_mrr_at_100_std value: -2.1399999999999997 - type: nauc_mrr_at_100_diff1 value: 38.8403 - type: nauc_mrr_at_1000_max value: 36.742200000000004 - type: nauc_mrr_at_1000_std value: -2.1506999999999996 - type: nauc_mrr_at_1000_diff1 value: 38.8393 - type: main_score value: 45.4 - task: type: Retrieval dataset: name: MTEB CQADupstackMathematicaRetrieval (default) type: mteb/cqadupstack-mathematica config: default split: test revision: 90fceea13679c63fe563ded68f3b6f06e50061de metrics: - type: ndcg_at_1 value: 25.124000000000002 - type: ndcg_at_3 value: 29.798000000000002 - type: ndcg_at_5 value: 32.112 - type: ndcg_at_10 value: 34.926 - type: ndcg_at_20 value: 37.317 - type: ndcg_at_100 value: 40.903 - type: ndcg_at_1000 value: 43.18 - type: map_at_1 value: 20.279 - type: map_at_3 value: 26.551000000000002 - type: map_at_5 value: 28.051 - type: map_at_10 value: 29.37 - type: map_at_20 value: 30.085 - type: map_at_100 value: 30.668 - type: map_at_1000 value: 30.774 - type: recall_at_1 value: 20.279 - type: recall_at_3 value: 33.043 - type: recall_at_5 value: 38.991 - type: recall_at_10 value: 47.355999999999995 - type: recall_at_20 value: 55.873 - type: recall_at_100 value: 72.90100000000001 - type: recall_at_1000 value: 88.678 - type: precision_at_1 value: 25.124000000000002 - type: precision_at_3 value: 14.221 - type: precision_at_5 value: 10.323 - type: precision_at_10 value: 6.381 - type: precision_at_20 value: 3.8739999999999997 - type: precision_at_100 value: 1.082 - type: precision_at_1000 value: 0.13999999999999999 - type: mrr_at_1 value: 25.1244 - type: mrr_at_3 value: 31.3847 - type: mrr_at_5 value: 32.9768 - type: mrr_at_10 value: 34.1348 - type: mrr_at_20 value: 34.7501 - type: mrr_at_100 value: 35.1367 - type: mrr_at_1000 value: 35.191 - type: nauc_ndcg_at_1_max value: 27.160600000000002 - type: nauc_ndcg_at_1_std value: 1.7711999999999999 - type: nauc_ndcg_at_1_diff1 value: 39.8547 - type: nauc_ndcg_at_3_max value: 23.7332 - type: nauc_ndcg_at_3_std value: 0.4508 - type: nauc_ndcg_at_3_diff1 value: 34.3668 - type: nauc_ndcg_at_5_max value: 24.6552 - type: nauc_ndcg_at_5_std value: 1.7423000000000002 - type: nauc_ndcg_at_5_diff1 value: 34.8806 - type: nauc_ndcg_at_10_max value: 24.3869 - type: nauc_ndcg_at_10_std value: 1.3054 - type: nauc_ndcg_at_10_diff1 value: 33.7015 - type: nauc_ndcg_at_20_max value: 24.449 - type: nauc_ndcg_at_20_std value: 2.4919000000000002 - type: nauc_ndcg_at_20_diff1 value: 32.9483 - type: nauc_ndcg_at_100_max value: 25.3655 - type: nauc_ndcg_at_100_std value: 2.7169 - type: nauc_ndcg_at_100_diff1 value: 32.8817 - type: nauc_ndcg_at_1000_max value: 25.524599999999996 - type: nauc_ndcg_at_1000_std value: 3.1405000000000003 - type: nauc_ndcg_at_1000_diff1 value: 32.7208 - type: nauc_map_at_1_max value: 24.9051 - type: nauc_map_at_1_std value: 2.788 - type: nauc_map_at_1_diff1 value: 38.9946 - type: nauc_map_at_3_max value: 23.061 - type: nauc_map_at_3_std value: 1.0529 - type: nauc_map_at_3_diff1 value: 35.0109 - type: nauc_map_at_5_max value: 23.704800000000002 - type: nauc_map_at_5_std value: 1.7375999999999998 - type: nauc_map_at_5_diff1 value: 35.2714 - type: nauc_map_at_10_max value: 23.7351 - type: nauc_map_at_10_std value: 1.5004 - type: nauc_map_at_10_diff1 value: 34.8483 - type: nauc_map_at_20_max value: 23.7699 - type: nauc_map_at_20_std value: 1.8925999999999998 - type: nauc_map_at_20_diff1 value: 34.6198 - type: nauc_map_at_100_max value: 23.962600000000002 - type: nauc_map_at_100_std value: 1.9238000000000002 - type: nauc_map_at_100_diff1 value: 34.7253 - type: nauc_map_at_1000_max value: 23.965 - type: nauc_map_at_1000_std value: 1.9339 - type: nauc_map_at_1000_diff1 value: 34.719899999999996 - type: nauc_recall_at_1_max value: 24.9051 - type: nauc_recall_at_1_std value: 2.788 - type: nauc_recall_at_1_diff1 value: 38.9946 - type: nauc_recall_at_3_max value: 21.8415 - type: nauc_recall_at_3_std value: 0.5292 - type: nauc_recall_at_3_diff1 value: 30.811 - type: nauc_recall_at_5_max value: 23.8237 - type: nauc_recall_at_5_std value: 2.5335 - type: nauc_recall_at_5_diff1 value: 31.928800000000003 - type: nauc_recall_at_10_max value: 22.5541 - type: nauc_recall_at_10_std value: 0.9076000000000001 - type: nauc_recall_at_10_diff1 value: 27.8364 - type: nauc_recall_at_20_max value: 22.0853 - type: nauc_recall_at_20_std value: 4.9954 - type: nauc_recall_at_20_diff1 value: 24.2376 - type: nauc_recall_at_100_max value: 26.4301 - type: nauc_recall_at_100_std value: 8.5471 - type: nauc_recall_at_100_diff1 value: 19.2131 - type: nauc_recall_at_1000_max value: 36.3726 - type: nauc_recall_at_1000_std value: 26.9247 - type: nauc_recall_at_1000_diff1 value: 3.8798 - type: nauc_precision_at_1_max value: 27.160600000000002 - type: nauc_precision_at_1_std value: 1.7711999999999999 - type: nauc_precision_at_1_diff1 value: 39.8547 - type: nauc_precision_at_3_max value: 23.8679 - type: nauc_precision_at_3_std value: -1.052 - type: nauc_precision_at_3_diff1 value: 29.999100000000002 - type: nauc_precision_at_5_max value: 24.7345 - type: nauc_precision_at_5_std value: 1.3604 - type: nauc_precision_at_5_diff1 value: 29.8611 - type: nauc_precision_at_10_max value: 21.5396 - type: nauc_precision_at_10_std value: -1.0137 - type: nauc_precision_at_10_diff1 value: 23.519000000000002 - type: nauc_precision_at_20_max value: 18.4431 - type: nauc_precision_at_20_std value: 1.5350000000000001 - type: nauc_precision_at_20_diff1 value: 16.5031 - type: nauc_precision_at_100_max value: 13.9255 - type: nauc_precision_at_100_std value: -0.48650000000000004 - type: nauc_precision_at_100_diff1 value: 7.700799999999999 - type: nauc_precision_at_1000_max value: 3.6421 - type: nauc_precision_at_1000_std value: -4.7682 - type: nauc_precision_at_1000_diff1 value: -1.4256 - type: nauc_mrr_at_1_max value: 27.160600000000002 - type: nauc_mrr_at_1_std value: 1.7711999999999999 - type: nauc_mrr_at_1_diff1 value: 39.8547 - type: nauc_mrr_at_3_max value: 25.44 - type: nauc_mrr_at_3_std value: 0.08639999999999999 - type: nauc_mrr_at_3_diff1 value: 35.381800000000005 - type: nauc_mrr_at_5_max value: 26.011899999999997 - type: nauc_mrr_at_5_std value: 0.6948 - type: nauc_mrr_at_5_diff1 value: 36.246 - type: nauc_mrr_at_10_max value: 25.8141 - type: nauc_mrr_at_10_std value: 0.5511 - type: nauc_mrr_at_10_diff1 value: 35.7313 - type: nauc_mrr_at_20_max value: 25.805899999999998 - type: nauc_mrr_at_20_std value: 0.8933 - type: nauc_mrr_at_20_diff1 value: 35.4972 - type: nauc_mrr_at_100_max value: 25.909 - type: nauc_mrr_at_100_std value: 0.8796999999999999 - type: nauc_mrr_at_100_diff1 value: 35.5299 - type: nauc_mrr_at_1000_max value: 25.910800000000002 - type: nauc_mrr_at_1000_std value: 0.9046000000000001 - type: nauc_mrr_at_1000_diff1 value: 35.522999999999996 - type: main_score value: 34.926 - task: type: Retrieval dataset: name: MTEB CQADupstackPhysicsRetrieval (default) type: mteb/cqadupstack-physics config: default split: test revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4 metrics: - type: ndcg_at_1 value: 42.059999999999995 - type: ndcg_at_3 value: 46.461999999999996 - type: ndcg_at_5 value: 48.662 - type: ndcg_at_10 value: 50.925 - type: ndcg_at_20 value: 53.120999999999995 - type: ndcg_at_100 value: 56.189 - type: ndcg_at_1000 value: 57.972 - type: map_at_1 value: 33.919 - type: map_at_3 value: 41.858000000000004 - type: map_at_5 value: 43.629 - type: map_at_10 value: 45.01 - type: map_at_20 value: 45.781 - type: map_at_100 value: 46.372 - type: map_at_1000 value: 46.477000000000004 - type: recall_at_1 value: 33.919 - type: recall_at_3 value: 49.153999999999996 - type: recall_at_5 value: 55.422000000000004 - type: recall_at_10 value: 62.204 - type: recall_at_20 value: 69.819 - type: recall_at_100 value: 83.67599999999999 - type: recall_at_1000 value: 95.093 - type: precision_at_1 value: 42.059999999999995 - type: precision_at_3 value: 22.201 - type: precision_at_5 value: 15.342 - type: precision_at_10 value: 9.038 - type: precision_at_20 value: 5.244999999999999 - type: precision_at_100 value: 1.348 - type: precision_at_1000 value: 0.168 - type: mrr_at_1 value: 42.0597 - type: mrr_at_3 value: 49.005500000000005 - type: mrr_at_5 value: 50.3673 - type: mrr_at_10 value: 51.14959999999999 - type: mrr_at_20 value: 51.656 - type: mrr_at_100 value: 51.969 - type: mrr_at_1000 value: 52.0088 - type: nauc_ndcg_at_1_max value: 39.321400000000004 - type: nauc_ndcg_at_1_std value: -3.3204 - type: nauc_ndcg_at_1_diff1 value: 50.999300000000005 - type: nauc_ndcg_at_3_max value: 37.6896 - type: nauc_ndcg_at_3_std value: -4.7356 - type: nauc_ndcg_at_3_diff1 value: 48.0551 - type: nauc_ndcg_at_5_max value: 36.9149 - type: nauc_ndcg_at_5_std value: -5.8358 - type: nauc_ndcg_at_5_diff1 value: 48.4085 - type: nauc_ndcg_at_10_max value: 36.9047 - type: nauc_ndcg_at_10_std value: -5.1284 - type: nauc_ndcg_at_10_diff1 value: 48.3356 - type: nauc_ndcg_at_20_max value: 36.9876 - type: nauc_ndcg_at_20_std value: -4.0274 - type: nauc_ndcg_at_20_diff1 value: 48.0203 - type: nauc_ndcg_at_100_max value: 38.472899999999996 - type: nauc_ndcg_at_100_std value: -1.1645 - type: nauc_ndcg_at_100_diff1 value: 47.734 - type: nauc_ndcg_at_1000_max value: 38.828 - type: nauc_ndcg_at_1000_std value: -1.5388000000000002 - type: nauc_ndcg_at_1000_diff1 value: 47.8951 - type: nauc_map_at_1_max value: 32.8495 - type: nauc_map_at_1_std value: -11.1224 - type: nauc_map_at_1_diff1 value: 52.8561 - type: nauc_map_at_3_max value: 35.2472 - type: nauc_map_at_3_std value: -7.8861 - type: nauc_map_at_3_diff1 value: 49.2087 - type: nauc_map_at_5_max value: 35.5165 - type: nauc_map_at_5_std value: -7.8567 - type: nauc_map_at_5_diff1 value: 49.3185 - type: nauc_map_at_10_max value: 36.2371 - type: nauc_map_at_10_std value: -6.7322999999999995 - type: nauc_map_at_10_diff1 value: 49.3669 - type: nauc_map_at_20_max value: 36.3245 - type: nauc_map_at_20_std value: -6.2256 - type: nauc_map_at_20_diff1 value: 49.242999999999995 - type: nauc_map_at_100_max value: 36.6375 - type: nauc_map_at_100_std value: -5.694599999999999 - type: nauc_map_at_100_diff1 value: 49.1942 - type: nauc_map_at_1000_max value: 36.6734 - type: nauc_map_at_1000_std value: -5.6653 - type: nauc_map_at_1000_diff1 value: 49.1813 - type: nauc_recall_at_1_max value: 32.8495 - type: nauc_recall_at_1_std value: -11.1224 - type: nauc_recall_at_1_diff1 value: 52.8561 - type: nauc_recall_at_3_max value: 33.2098 - type: nauc_recall_at_3_std value: -7.4756 - type: nauc_recall_at_3_diff1 value: 44.6512 - type: nauc_recall_at_5_max value: 32.0734 - type: nauc_recall_at_5_std value: -8.552 - type: nauc_recall_at_5_diff1 value: 43.2098 - type: nauc_recall_at_10_max value: 32.452999999999996 - type: nauc_recall_at_10_std value: -5.631 - type: nauc_recall_at_10_diff1 value: 42.4641 - type: nauc_recall_at_20_max value: 31.660300000000003 - type: nauc_recall_at_20_std value: -1.5259 - type: nauc_recall_at_20_diff1 value: 40.5356 - type: nauc_recall_at_100_max value: 40.3906 - type: nauc_recall_at_100_std value: 22.5792 - type: nauc_recall_at_100_diff1 value: 36.2667 - type: nauc_recall_at_1000_max value: 61.422399999999996 - type: nauc_recall_at_1000_std value: 46.7038 - type: nauc_recall_at_1000_diff1 value: 36.4218 - type: nauc_precision_at_1_max value: 39.321400000000004 - type: nauc_precision_at_1_std value: -3.3204 - type: nauc_precision_at_1_diff1 value: 50.999300000000005 - type: nauc_precision_at_3_max value: 35.7839 - type: nauc_precision_at_3_std value: 7.773199999999999 - type: nauc_precision_at_3_diff1 value: 29.8081 - type: nauc_precision_at_5_max value: 32.7723 - type: nauc_precision_at_5_std value: 9.8457 - type: nauc_precision_at_5_diff1 value: 24.9104 - type: nauc_precision_at_10_max value: 30.6076 - type: nauc_precision_at_10_std value: 16.5018 - type: nauc_precision_at_10_diff1 value: 17.5733 - type: nauc_precision_at_20_max value: 25.8982 - type: nauc_precision_at_20_std value: 20.4936 - type: nauc_precision_at_20_diff1 value: 9.4253 - type: nauc_precision_at_100_max value: 20.5147 - type: nauc_precision_at_100_std value: 28.0537 - type: nauc_precision_at_100_diff1 value: -3.5682 - type: nauc_precision_at_1000_max value: 8.9834 - type: nauc_precision_at_1000_std value: 21.330099999999998 - type: nauc_precision_at_1000_diff1 value: -13.9467 - type: nauc_mrr_at_1_max value: 39.321400000000004 - type: nauc_mrr_at_1_std value: -3.3204 - type: nauc_mrr_at_1_diff1 value: 50.999300000000005 - type: nauc_mrr_at_3_max value: 39.537099999999995 - type: nauc_mrr_at_3_std value: -1.8964999999999999 - type: nauc_mrr_at_3_diff1 value: 48.790499999999994 - type: nauc_mrr_at_5_max value: 39.5914 - type: nauc_mrr_at_5_std value: -2.1046 - type: nauc_mrr_at_5_diff1 value: 48.674099999999996 - type: nauc_mrr_at_10_max value: 39.4877 - type: nauc_mrr_at_10_std value: -2.1155 - type: nauc_mrr_at_10_diff1 value: 48.5082 - type: nauc_mrr_at_20_max value: 39.5837 - type: nauc_mrr_at_20_std value: -1.8568999999999998 - type: nauc_mrr_at_20_diff1 value: 48.4835 - type: nauc_mrr_at_100_max value: 39.6439 - type: nauc_mrr_at_100_std value: -1.6681000000000001 - type: nauc_mrr_at_100_diff1 value: 48.4452 - type: nauc_mrr_at_1000_max value: 39.6426 - type: nauc_mrr_at_1000_std value: -1.6824 - type: nauc_mrr_at_1000_diff1 value: 48.4594 - type: main_score value: 50.925 - task: type: Retrieval dataset: name: MTEB CQADupstackProgrammersRetrieval (default) type: mteb/cqadupstack-programmers config: default split: test revision: 6184bc1440d2dbc7612be22b50686b8826d22b32 metrics: - type: ndcg_at_1 value: 38.812999999999995 - type: ndcg_at_3 value: 43.126999999999995 - type: ndcg_at_5 value: 45.269999999999996 - type: ndcg_at_10 value: 48.181000000000004 - type: ndcg_at_20 value: 50.475 - type: ndcg_at_100 value: 53.378 - type: ndcg_at_1000 value: 55.372 - type: map_at_1 value: 31.228 - type: map_at_3 value: 38.727000000000004 - type: map_at_5 value: 40.544000000000004 - type: map_at_10 value: 42.022999999999996 - type: map_at_20 value: 42.815 - type: map_at_100 value: 43.336000000000006 - type: map_at_1000 value: 43.434 - type: recall_at_1 value: 31.228 - type: recall_at_3 value: 46.075 - type: recall_at_5 value: 52.065 - type: recall_at_10 value: 60.86 - type: recall_at_20 value: 68.916 - type: recall_at_100 value: 82.49600000000001 - type: recall_at_1000 value: 95.914 - type: precision_at_1 value: 38.812999999999995 - type: precision_at_3 value: 20.51 - type: precision_at_5 value: 14.405999999999999 - type: precision_at_10 value: 8.676 - type: precision_at_20 value: 5.08 - type: precision_at_100 value: 1.3 - type: precision_at_1000 value: 0.165 - type: mrr_at_1 value: 38.812799999999996 - type: mrr_at_3 value: 45.3957 - type: mrr_at_5 value: 46.8113 - type: mrr_at_10 value: 47.9132 - type: mrr_at_20 value: 48.4148 - type: mrr_at_100 value: 48.694900000000004 - type: mrr_at_1000 value: 48.74 - type: nauc_ndcg_at_1_max value: 46.951100000000004 - type: nauc_ndcg_at_1_std value: 4.750299999999999 - type: nauc_ndcg_at_1_diff1 value: 50.353300000000004 - type: nauc_ndcg_at_3_max value: 44.852 - type: nauc_ndcg_at_3_std value: 5.976 - type: nauc_ndcg_at_3_diff1 value: 44.8003 - type: nauc_ndcg_at_5_max value: 44.7999 - type: nauc_ndcg_at_5_std value: 7.138799999999999 - type: nauc_ndcg_at_5_diff1 value: 43.786 - type: nauc_ndcg_at_10_max value: 45.272800000000004 - type: nauc_ndcg_at_10_std value: 8.318200000000001 - type: nauc_ndcg_at_10_diff1 value: 43.5412 - type: nauc_ndcg_at_20_max value: 45.9439 - type: nauc_ndcg_at_20_std value: 9.5894 - type: nauc_ndcg_at_20_diff1 value: 43.635400000000004 - type: nauc_ndcg_at_100_max value: 46.555800000000005 - type: nauc_ndcg_at_100_std value: 11.4897 - type: nauc_ndcg_at_100_diff1 value: 43.2953 - type: nauc_ndcg_at_1000_max value: 46.4671 - type: nauc_ndcg_at_1000_std value: 10.198500000000001 - type: nauc_ndcg_at_1000_diff1 value: 43.9655 - type: nauc_map_at_1_max value: 41.2881 - type: nauc_map_at_1_std value: -1.7105 - type: nauc_map_at_1_diff1 value: 52.340900000000005 - type: nauc_map_at_3_max value: 43.2779 - type: nauc_map_at_3_std value: 3.1361 - type: nauc_map_at_3_diff1 value: 46.899499999999996 - type: nauc_map_at_5_max value: 44.034600000000005 - type: nauc_map_at_5_std value: 4.376 - type: nauc_map_at_5_diff1 value: 46.1768 - type: nauc_map_at_10_max value: 44.495200000000004 - type: nauc_map_at_10_std value: 5.1069 - type: nauc_map_at_10_diff1 value: 45.8036 - type: nauc_map_at_20_max value: 44.9796 - type: nauc_map_at_20_std value: 5.6501 - type: nauc_map_at_20_diff1 value: 45.8538 - type: nauc_map_at_100_max value: 45.178000000000004 - type: nauc_map_at_100_std value: 6.1053999999999995 - type: nauc_map_at_100_diff1 value: 45.7785 - type: nauc_map_at_1000_max value: 45.169599999999996 - type: nauc_map_at_1000_std value: 6.0758 - type: nauc_map_at_1000_diff1 value: 45.794200000000004 - type: nauc_recall_at_1_max value: 41.2881 - type: nauc_recall_at_1_std value: -1.7105 - type: nauc_recall_at_1_diff1 value: 52.340900000000005 - type: nauc_recall_at_3_max value: 40.213100000000004 - type: nauc_recall_at_3_std value: 5.0584 - type: nauc_recall_at_3_diff1 value: 39.8885 - type: nauc_recall_at_5_max value: 40.629799999999996 - type: nauc_recall_at_5_std value: 9.2891 - type: nauc_recall_at_5_diff1 value: 36.7529 - type: nauc_recall_at_10_max value: 41.1258 - type: nauc_recall_at_10_std value: 14.056 - type: nauc_recall_at_10_diff1 value: 34.416000000000004 - type: nauc_recall_at_20_max value: 42.2647 - type: nauc_recall_at_20_std value: 19.0659 - type: nauc_recall_at_20_diff1 value: 33.9025 - type: nauc_recall_at_100_max value: 45.4518 - type: nauc_recall_at_100_std value: 38.2567 - type: nauc_recall_at_100_diff1 value: 27.418300000000002 - type: nauc_recall_at_1000_max value: 52.1153 - type: nauc_recall_at_1000_std value: 54.8108 - type: nauc_recall_at_1000_diff1 value: 28.122200000000003 - type: nauc_precision_at_1_max value: 46.951100000000004 - type: nauc_precision_at_1_std value: 4.750299999999999 - type: nauc_precision_at_1_diff1 value: 50.353300000000004 - type: nauc_precision_at_3_max value: 43.3769 - type: nauc_precision_at_3_std value: 15.2362 - type: nauc_precision_at_3_diff1 value: 29.4925 - type: nauc_precision_at_5_max value: 40.0531 - type: nauc_precision_at_5_std value: 18.0719 - type: nauc_precision_at_5_diff1 value: 21.4607 - type: nauc_precision_at_10_max value: 34.558 - type: nauc_precision_at_10_std value: 20.2349 - type: nauc_precision_at_10_diff1 value: 13.0483 - type: nauc_precision_at_20_max value: 30.3112 - type: nauc_precision_at_20_std value: 23.7865 - type: nauc_precision_at_20_diff1 value: 6.678000000000001 - type: nauc_precision_at_100_max value: 15.782599999999999 - type: nauc_precision_at_100_std value: 23.3508 - type: nauc_precision_at_100_diff1 value: -5.356199999999999 - type: nauc_precision_at_1000_max value: -1.203 - type: nauc_precision_at_1000_std value: 9.2771 - type: nauc_precision_at_1000_diff1 value: -12.0167 - type: nauc_mrr_at_1_max value: 46.951100000000004 - type: nauc_mrr_at_1_std value: 4.750299999999999 - type: nauc_mrr_at_1_diff1 value: 50.353300000000004 - type: nauc_mrr_at_3_max value: 47.1661 - type: nauc_mrr_at_3_std value: 7.985 - type: nauc_mrr_at_3_diff1 value: 45.5407 - type: nauc_mrr_at_5_max value: 46.7954 - type: nauc_mrr_at_5_std value: 8.615200000000002 - type: nauc_mrr_at_5_diff1 value: 44.767 - type: nauc_mrr_at_10_max value: 46.874500000000005 - type: nauc_mrr_at_10_std value: 8.9973 - type: nauc_mrr_at_10_diff1 value: 44.7807 - type: nauc_mrr_at_20_max value: 46.8582 - type: nauc_mrr_at_20_std value: 9.1312 - type: nauc_mrr_at_20_diff1 value: 44.7926 - type: nauc_mrr_at_100_max value: 46.9119 - type: nauc_mrr_at_100_std value: 9.2225 - type: nauc_mrr_at_100_diff1 value: 44.7972 - type: nauc_mrr_at_1000_max value: 46.9139 - type: nauc_mrr_at_1000_std value: 9.1867 - type: nauc_mrr_at_1000_diff1 value: 44.8208 - type: main_score value: 48.181000000000004 - task: type: Retrieval dataset: name: MTEB CQADupstackRetrieval (default) type: CQADupstackRetrieval_is_a_combined_dataset config: default split: test revision: CQADupstackRetrieval_is_a_combined_dataset metrics: - type: main_score value: 47.198 - type: ndcg_at_10 value: 47.198 - task: type: Retrieval dataset: name: MTEB CQADupstackStatsRetrieval (default) type: mteb/cqadupstack-stats config: default split: test revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a metrics: - type: ndcg_at_1 value: 32.515 - type: ndcg_at_3 value: 36.754999999999995 - type: ndcg_at_5 value: 38.461 - type: ndcg_at_10 value: 41.113 - type: ndcg_at_20 value: 42.744 - type: ndcg_at_100 value: 45.607 - type: ndcg_at_1000 value: 47.769 - type: map_at_1 value: 28.877999999999997 - type: map_at_3 value: 34.111000000000004 - type: map_at_5 value: 35.296 - type: map_at_10 value: 36.516 - type: map_at_20 value: 37.031 - type: map_at_100 value: 37.455 - type: map_at_1000 value: 37.54 - type: recall_at_1 value: 28.877999999999997 - type: recall_at_3 value: 39.823 - type: recall_at_5 value: 44.074000000000005 - type: recall_at_10 value: 52.138 - type: recall_at_20 value: 58.268 - type: recall_at_100 value: 72.675 - type: recall_at_1000 value: 88.49900000000001 - type: precision_at_1 value: 32.515 - type: precision_at_3 value: 15.491 - type: precision_at_5 value: 10.613 - type: precision_at_10 value: 6.411 - type: precision_at_20 value: 3.604 - type: precision_at_100 value: 0.9390000000000001 - type: precision_at_1000 value: 0.121 - type: mrr_at_1 value: 32.5153 - type: mrr_at_3 value: 37.5256 - type: mrr_at_5 value: 38.507200000000005 - type: mrr_at_10 value: 39.6489 - type: mrr_at_20 value: 40.0734 - type: mrr_at_100 value: 40.408899999999996 - type: mrr_at_1000 value: 40.470600000000005 - type: nauc_ndcg_at_1_max value: 46.9541 - type: nauc_ndcg_at_1_std value: -0.6345 - type: nauc_ndcg_at_1_diff1 value: 56.4747 - type: nauc_ndcg_at_3_max value: 44.595600000000005 - type: nauc_ndcg_at_3_std value: -0.6883 - type: nauc_ndcg_at_3_diff1 value: 51.176100000000005 - type: nauc_ndcg_at_5_max value: 45.0672 - type: nauc_ndcg_at_5_std value: 0.7248 - type: nauc_ndcg_at_5_diff1 value: 50.6661 - type: nauc_ndcg_at_10_max value: 45.3702 - type: nauc_ndcg_at_10_std value: 3.7225 - type: nauc_ndcg_at_10_diff1 value: 48.5914 - type: nauc_ndcg_at_20_max value: 45.134800000000006 - type: nauc_ndcg_at_20_std value: 3.4250999999999996 - type: nauc_ndcg_at_20_diff1 value: 48.0876 - type: nauc_ndcg_at_100_max value: 45.848 - type: nauc_ndcg_at_100_std value: 5.0007 - type: nauc_ndcg_at_100_diff1 value: 48.4221 - type: nauc_ndcg_at_1000_max value: 46.0472 - type: nauc_ndcg_at_1000_std value: 4.8727 - type: nauc_ndcg_at_1000_diff1 value: 48.7787 - type: nauc_map_at_1_max value: 44.2723 - type: nauc_map_at_1_std value: -4.1624 - type: nauc_map_at_1_diff1 value: 56.3666 - type: nauc_map_at_3_max value: 44.368 - type: nauc_map_at_3_std value: -2.2338 - type: nauc_map_at_3_diff1 value: 52.662299999999995 - type: nauc_map_at_5_max value: 44.9376 - type: nauc_map_at_5_std value: -0.9258000000000001 - type: nauc_map_at_5_diff1 value: 52.2675 - type: nauc_map_at_10_max value: 45.162600000000005 - type: nauc_map_at_10_std value: 0.5709 - type: nauc_map_at_10_diff1 value: 51.2702 - type: nauc_map_at_20_max value: 45.088899999999995 - type: nauc_map_at_20_std value: 0.5163 - type: nauc_map_at_20_diff1 value: 51.1058 - type: nauc_map_at_100_max value: 45.203700000000005 - type: nauc_map_at_100_std value: 0.7443 - type: nauc_map_at_100_diff1 value: 51.1744 - type: nauc_map_at_1000_max value: 45.2121 - type: nauc_map_at_1000_std value: 0.7443 - type: nauc_map_at_1000_diff1 value: 51.186699999999995 - type: nauc_recall_at_1_max value: 44.2723 - type: nauc_recall_at_1_std value: -4.1624 - type: nauc_recall_at_1_diff1 value: 56.3666 - type: nauc_recall_at_3_max value: 41.484700000000004 - type: nauc_recall_at_3_std value: -1.5438 - type: nauc_recall_at_3_diff1 value: 47.3155 - type: nauc_recall_at_5_max value: 42.7926 - type: nauc_recall_at_5_std value: 2.2485999999999997 - type: nauc_recall_at_5_diff1 value: 45.7287 - type: nauc_recall_at_10_max value: 43.3757 - type: nauc_recall_at_10_std value: 11.1774 - type: nauc_recall_at_10_diff1 value: 38.699 - type: nauc_recall_at_20_max value: 41.9806 - type: nauc_recall_at_20_std value: 9.8464 - type: nauc_recall_at_20_diff1 value: 36.209599999999995 - type: nauc_recall_at_100_max value: 44.935399999999994 - type: nauc_recall_at_100_std value: 22.2528 - type: nauc_recall_at_100_diff1 value: 33.9811 - type: nauc_recall_at_1000_max value: 48.0178 - type: nauc_recall_at_1000_std value: 35.6656 - type: nauc_recall_at_1000_diff1 value: 27.0609 - type: nauc_precision_at_1_max value: 46.9541 - type: nauc_precision_at_1_std value: -0.6345 - type: nauc_precision_at_1_diff1 value: 56.4747 - type: nauc_precision_at_3_max value: 44.8235 - type: nauc_precision_at_3_std value: 6.392399999999999 - type: nauc_precision_at_3_diff1 value: 43.4139 - type: nauc_precision_at_5_max value: 44.1627 - type: nauc_precision_at_5_std value: 12.5801 - type: nauc_precision_at_5_diff1 value: 38.3975 - type: nauc_precision_at_10_max value: 42.2932 - type: nauc_precision_at_10_std value: 21.9445 - type: nauc_precision_at_10_diff1 value: 28.898200000000003 - type: nauc_precision_at_20_max value: 38.3815 - type: nauc_precision_at_20_std value: 21.2644 - type: nauc_precision_at_20_diff1 value: 22.902900000000002 - type: nauc_precision_at_100_max value: 30.0629 - type: nauc_precision_at_100_std value: 25.7938 - type: nauc_precision_at_100_diff1 value: 13.500599999999999 - type: nauc_precision_at_1000_max value: 16.1509 - type: nauc_precision_at_1000_std value: 22.168599999999998 - type: nauc_precision_at_1000_diff1 value: -0.5865 - type: nauc_mrr_at_1_max value: 46.9541 - type: nauc_mrr_at_1_std value: -0.6345 - type: nauc_mrr_at_1_diff1 value: 56.4747 - type: nauc_mrr_at_3_max value: 45.571 - type: nauc_mrr_at_3_std value: 0.5652 - type: nauc_mrr_at_3_diff1 value: 52.2878 - type: nauc_mrr_at_5_max value: 45.9243 - type: nauc_mrr_at_5_std value: 1.4102 - type: nauc_mrr_at_5_diff1 value: 52.0197 - type: nauc_mrr_at_10_max value: 46.090599999999995 - type: nauc_mrr_at_10_std value: 2.5422000000000002 - type: nauc_mrr_at_10_diff1 value: 51.1523 - type: nauc_mrr_at_20_max value: 46.0581 - type: nauc_mrr_at_20_std value: 2.4245 - type: nauc_mrr_at_20_diff1 value: 51.1149 - type: nauc_mrr_at_100_max value: 46.138200000000005 - type: nauc_mrr_at_100_std value: 2.5852 - type: nauc_mrr_at_100_diff1 value: 51.19200000000001 - type: nauc_mrr_at_1000_max value: 46.134 - type: nauc_mrr_at_1000_std value: 2.5724 - type: nauc_mrr_at_1000_diff1 value: 51.20099999999999 - type: main_score value: 41.113 - task: type: Retrieval dataset: name: MTEB CQADupstackTexRetrieval (default) type: mteb/cqadupstack-tex config: default split: test revision: 46989137a86843e03a6195de44b09deda022eec7 metrics: - type: ndcg_at_1 value: 26.358999999999998 - type: ndcg_at_3 value: 30.921 - type: ndcg_at_5 value: 33.083 - type: ndcg_at_10 value: 35.669000000000004 - type: ndcg_at_20 value: 37.486999999999995 - type: ndcg_at_100 value: 40.897 - type: ndcg_at_1000 value: 43.492999999999995 - type: map_at_1 value: 21.644 - type: map_at_3 value: 27.638 - type: map_at_5 value: 29.181 - type: map_at_10 value: 30.429000000000002 - type: map_at_20 value: 31.018 - type: map_at_100 value: 31.557000000000002 - type: map_at_1000 value: 31.676 - type: recall_at_1 value: 21.644 - type: recall_at_3 value: 33.727000000000004 - type: recall_at_5 value: 39.402 - type: recall_at_10 value: 47.166000000000004 - type: recall_at_20 value: 53.818 - type: recall_at_100 value: 70.625 - type: recall_at_1000 value: 88.848 - type: precision_at_1 value: 26.358999999999998 - type: precision_at_3 value: 14.602 - type: precision_at_5 value: 10.509 - type: precision_at_10 value: 6.468999999999999 - type: precision_at_20 value: 3.7969999999999997 - type: precision_at_100 value: 1.0619999999999998 - type: precision_at_1000 value: 0.147 - type: mrr_at_1 value: 26.3593 - type: mrr_at_3 value: 32.2379 - type: mrr_at_5 value: 33.5559 - type: mrr_at_10 value: 34.6105 - type: mrr_at_20 value: 35.0733 - type: mrr_at_100 value: 35.4832 - type: mrr_at_1000 value: 35.5508 - type: nauc_ndcg_at_1_max value: 38.821 - type: nauc_ndcg_at_1_std value: -0.9577 - type: nauc_ndcg_at_1_diff1 value: 49.477900000000005 - type: nauc_ndcg_at_3_max value: 36.9651 - type: nauc_ndcg_at_3_std value: 0.5652 - type: nauc_ndcg_at_3_diff1 value: 42.9649 - type: nauc_ndcg_at_5_max value: 36.9433 - type: nauc_ndcg_at_5_std value: 1.4069 - type: nauc_ndcg_at_5_diff1 value: 41.3321 - type: nauc_ndcg_at_10_max value: 37.0556 - type: nauc_ndcg_at_10_std value: 1.983 - type: nauc_ndcg_at_10_diff1 value: 40.6062 - type: nauc_ndcg_at_20_max value: 37.621 - type: nauc_ndcg_at_20_std value: 3.1833 - type: nauc_ndcg_at_20_diff1 value: 40.0768 - type: nauc_ndcg_at_100_max value: 37.5859 - type: nauc_ndcg_at_100_std value: 4.4883 - type: nauc_ndcg_at_100_diff1 value: 39.6131 - type: nauc_ndcg_at_1000_max value: 37.9037 - type: nauc_ndcg_at_1000_std value: 4.3155 - type: nauc_ndcg_at_1000_diff1 value: 40.393 - type: nauc_map_at_1_max value: 34.2335 - type: nauc_map_at_1_std value: -2.5663 - type: nauc_map_at_1_diff1 value: 49.3827 - type: nauc_map_at_3_max value: 35.1539 - type: nauc_map_at_3_std value: -0.4655 - type: nauc_map_at_3_diff1 value: 44.0299 - type: nauc_map_at_5_max value: 35.546499999999995 - type: nauc_map_at_5_std value: -0.0021 - type: nauc_map_at_5_diff1 value: 43.0138 - type: nauc_map_at_10_max value: 35.904799999999994 - type: nauc_map_at_10_std value: 0.367 - type: nauc_map_at_10_diff1 value: 42.762699999999995 - type: nauc_map_at_20_max value: 36.1855 - type: nauc_map_at_20_std value: 0.7818 - type: nauc_map_at_20_diff1 value: 42.6084 - type: nauc_map_at_100_max value: 36.2406 - type: nauc_map_at_100_std value: 0.9825999999999999 - type: nauc_map_at_100_diff1 value: 42.5375 - type: nauc_map_at_1000_max value: 36.2732 - type: nauc_map_at_1000_std value: 0.9912000000000001 - type: nauc_map_at_1000_diff1 value: 42.5821 - type: nauc_recall_at_1_max value: 34.2335 - type: nauc_recall_at_1_std value: -2.5663 - type: nauc_recall_at_1_diff1 value: 49.3827 - type: nauc_recall_at_3_max value: 34.2402 - type: nauc_recall_at_3_std value: 1.3011 - type: nauc_recall_at_3_diff1 value: 38.5403 - type: nauc_recall_at_5_max value: 34.2169 - type: nauc_recall_at_5_std value: 3.0383 - type: nauc_recall_at_5_diff1 value: 34.3078 - type: nauc_recall_at_10_max value: 34.2267 - type: nauc_recall_at_10_std value: 4.7303 - type: nauc_recall_at_10_diff1 value: 31.2869 - type: nauc_recall_at_20_max value: 35.6281 - type: nauc_recall_at_20_std value: 8.940199999999999 - type: nauc_recall_at_20_diff1 value: 28.655599999999996 - type: nauc_recall_at_100_max value: 34.0961 - type: nauc_recall_at_100_std value: 18.096799999999998 - type: nauc_recall_at_100_diff1 value: 22.490199999999998 - type: nauc_recall_at_1000_max value: 37.3724 - type: nauc_recall_at_1000_std value: 29.723699999999997 - type: nauc_recall_at_1000_diff1 value: 18.9603 - type: nauc_precision_at_1_max value: 38.821 - type: nauc_precision_at_1_std value: -0.9577 - type: nauc_precision_at_1_diff1 value: 49.477900000000005 - type: nauc_precision_at_3_max value: 38.9589 - type: nauc_precision_at_3_std value: 3.6894000000000005 - type: nauc_precision_at_3_diff1 value: 34.869499999999995 - type: nauc_precision_at_5_max value: 37.9132 - type: nauc_precision_at_5_std value: 6.1095 - type: nauc_precision_at_5_diff1 value: 28.7686 - type: nauc_precision_at_10_max value: 35.5564 - type: nauc_precision_at_10_std value: 7.4825 - type: nauc_precision_at_10_diff1 value: 24.0663 - type: nauc_precision_at_20_max value: 34.3717 - type: nauc_precision_at_20_std value: 10.989 - type: nauc_precision_at_20_diff1 value: 19.0117 - type: nauc_precision_at_100_max value: 25.595000000000002 - type: nauc_precision_at_100_std value: 13.692499999999999 - type: nauc_precision_at_100_diff1 value: 9.7287 - type: nauc_precision_at_1000_max value: 15.6194 - type: nauc_precision_at_1000_std value: 7.9235 - type: nauc_precision_at_1000_diff1 value: 3.5067 - type: nauc_mrr_at_1_max value: 38.821 - type: nauc_mrr_at_1_std value: -0.9577 - type: nauc_mrr_at_1_diff1 value: 49.477900000000005 - type: nauc_mrr_at_3_max value: 39.365899999999996 - type: nauc_mrr_at_3_std value: 0.8999999999999999 - type: nauc_mrr_at_3_diff1 value: 44.8801 - type: nauc_mrr_at_5_max value: 39.339400000000005 - type: nauc_mrr_at_5_std value: 1.6056000000000001 - type: nauc_mrr_at_5_diff1 value: 43.9725 - type: nauc_mrr_at_10_max value: 39.245200000000004 - type: nauc_mrr_at_10_std value: 1.6921 - type: nauc_mrr_at_10_diff1 value: 43.6805 - type: nauc_mrr_at_20_max value: 39.283699999999996 - type: nauc_mrr_at_20_std value: 1.9199000000000002 - type: nauc_mrr_at_20_diff1 value: 43.5636 - type: nauc_mrr_at_100_max value: 39.293299999999995 - type: nauc_mrr_at_100_std value: 2.0535 - type: nauc_mrr_at_100_diff1 value: 43.5431 - type: nauc_mrr_at_1000_max value: 39.299299999999995 - type: nauc_mrr_at_1000_std value: 2.0467 - type: nauc_mrr_at_1000_diff1 value: 43.5649 - type: main_score value: 35.669000000000004 - task: type: Retrieval dataset: name: MTEB CQADupstackUnixRetrieval (default) type: mteb/cqadupstack-unix config: default split: test revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53 metrics: - type: ndcg_at_1 value: 37.407000000000004 - type: ndcg_at_3 value: 43.179 - type: ndcg_at_5 value: 45.540000000000006 - type: ndcg_at_10 value: 48.189 - type: ndcg_at_20 value: 50.308 - type: ndcg_at_100 value: 53.15800000000001 - type: ndcg_at_1000 value: 55.108999999999995 - type: map_at_1 value: 32.314 - type: map_at_3 value: 39.757 - type: map_at_5 value: 41.448 - type: map_at_10 value: 42.742999999999995 - type: map_at_20 value: 43.438 - type: map_at_100 value: 43.909 - type: map_at_1000 value: 44.005 - type: recall_at_1 value: 32.314 - type: recall_at_3 value: 46.852 - type: recall_at_5 value: 53.15 - type: recall_at_10 value: 60.748000000000005 - type: recall_at_20 value: 68.30199999999999 - type: recall_at_100 value: 81.846 - type: recall_at_1000 value: 94.92399999999999 - type: precision_at_1 value: 37.407000000000004 - type: precision_at_3 value: 19.59 - type: precision_at_5 value: 13.544999999999998 - type: precision_at_10 value: 8.013 - type: precision_at_20 value: 4.627 - type: precision_at_100 value: 1.172 - type: precision_at_1000 value: 0.14400000000000002 - type: mrr_at_1 value: 37.4067 - type: mrr_at_3 value: 43.9832 - type: mrr_at_5 value: 45.4291 - type: mrr_at_10 value: 46.4308 - type: mrr_at_20 value: 46.9435 - type: mrr_at_100 value: 47.2549 - type: mrr_at_1000 value: 47.3064 - type: nauc_ndcg_at_1_max value: 49.5683 - type: nauc_ndcg_at_1_std value: -4.5333 - type: nauc_ndcg_at_1_diff1 value: 59.0792 - type: nauc_ndcg_at_3_max value: 46.881 - type: nauc_ndcg_at_3_std value: -1.9335000000000002 - type: nauc_ndcg_at_3_diff1 value: 50.6091 - type: nauc_ndcg_at_5_max value: 46.596399999999996 - type: nauc_ndcg_at_5_std value: -1.6747 - type: nauc_ndcg_at_5_diff1 value: 50.731 - type: nauc_ndcg_at_10_max value: 47.119699999999995 - type: nauc_ndcg_at_10_std value: -1.8790999999999998 - type: nauc_ndcg_at_10_diff1 value: 50.4398 - type: nauc_ndcg_at_20_max value: 46.931400000000004 - type: nauc_ndcg_at_20_std value: -1.2184 - type: nauc_ndcg_at_20_diff1 value: 50.2302 - type: nauc_ndcg_at_100_max value: 47.4715 - type: nauc_ndcg_at_100_std value: 0.512 - type: nauc_ndcg_at_100_diff1 value: 49.831399999999995 - type: nauc_ndcg_at_1000_max value: 47.4049 - type: nauc_ndcg_at_1000_std value: -0.07730000000000001 - type: nauc_ndcg_at_1000_diff1 value: 50.045399999999994 - type: nauc_map_at_1_max value: 46.3138 - type: nauc_map_at_1_std value: -6.1365 - type: nauc_map_at_1_diff1 value: 59.1901 - type: nauc_map_at_3_max value: 46.4225 - type: nauc_map_at_3_std value: -3.3928 - type: nauc_map_at_3_diff1 value: 53.0394 - type: nauc_map_at_5_max value: 46.634 - type: nauc_map_at_5_std value: -2.8697 - type: nauc_map_at_5_diff1 value: 52.837500000000006 - type: nauc_map_at_10_max value: 46.9634 - type: nauc_map_at_10_std value: -2.8736 - type: nauc_map_at_10_diff1 value: 52.62670000000001 - type: nauc_map_at_20_max value: 46.943 - type: nauc_map_at_20_std value: -2.7709 - type: nauc_map_at_20_diff1 value: 52.525299999999994 - type: nauc_map_at_100_max value: 47.072 - type: nauc_map_at_100_std value: -2.4186 - type: nauc_map_at_100_diff1 value: 52.4223 - type: nauc_map_at_1000_max value: 47.058299999999996 - type: nauc_map_at_1000_std value: -2.4274 - type: nauc_map_at_1000_diff1 value: 52.410000000000004 - type: nauc_recall_at_1_max value: 46.3138 - type: nauc_recall_at_1_std value: -6.1365 - type: nauc_recall_at_1_diff1 value: 59.1901 - type: nauc_recall_at_3_max value: 43.556 - type: nauc_recall_at_3_std value: -1.0473 - type: nauc_recall_at_3_diff1 value: 45.3836 - type: nauc_recall_at_5_max value: 42.8197 - type: nauc_recall_at_5_std value: 0.364 - type: nauc_recall_at_5_diff1 value: 44.0828 - type: nauc_recall_at_10_max value: 43.5287 - type: nauc_recall_at_10_std value: -0.16999999999999998 - type: nauc_recall_at_10_diff1 value: 42.2532 - type: nauc_recall_at_20_max value: 41.9415 - type: nauc_recall_at_20_std value: 3.0739 - type: nauc_recall_at_20_diff1 value: 40.6138 - type: nauc_recall_at_100_max value: 43.648199999999996 - type: nauc_recall_at_100_std value: 17.8151 - type: nauc_recall_at_100_diff1 value: 34.7435 - type: nauc_recall_at_1000_max value: 42.9288 - type: nauc_recall_at_1000_std value: 34.9874 - type: nauc_recall_at_1000_diff1 value: 21.8361 - type: nauc_precision_at_1_max value: 49.5683 - type: nauc_precision_at_1_std value: -4.5333 - type: nauc_precision_at_1_diff1 value: 59.0792 - type: nauc_precision_at_3_max value: 40.726 - type: nauc_precision_at_3_std value: 3.6327 - type: nauc_precision_at_3_diff1 value: 32.726 - type: nauc_precision_at_5_max value: 37.575599999999994 - type: nauc_precision_at_5_std value: 5.4281999999999995 - type: nauc_precision_at_5_diff1 value: 26.8851 - type: nauc_precision_at_10_max value: 31.7382 - type: nauc_precision_at_10_std value: 4.0767999999999995 - type: nauc_precision_at_10_diff1 value: 18.174799999999998 - type: nauc_precision_at_20_max value: 25.4159 - type: nauc_precision_at_20_std value: 6.0251 - type: nauc_precision_at_20_diff1 value: 10.059800000000001 - type: nauc_precision_at_100_max value: 13.5296 - type: nauc_precision_at_100_std value: 14.0608 - type: nauc_precision_at_100_diff1 value: -7.792000000000001 - type: nauc_precision_at_1000_max value: -3.7522 - type: nauc_precision_at_1000_std value: 7.536099999999999 - type: nauc_precision_at_1000_diff1 value: -21.2683 - type: nauc_mrr_at_1_max value: 49.5683 - type: nauc_mrr_at_1_std value: -4.5333 - type: nauc_mrr_at_1_diff1 value: 59.0792 - type: nauc_mrr_at_3_max value: 48.3581 - type: nauc_mrr_at_3_std value: -1.8857 - type: nauc_mrr_at_3_diff1 value: 52.5945 - type: nauc_mrr_at_5_max value: 48.2651 - type: nauc_mrr_at_5_std value: -1.5519 - type: nauc_mrr_at_5_diff1 value: 52.323699999999995 - type: nauc_mrr_at_10_max value: 48.346000000000004 - type: nauc_mrr_at_10_std value: -1.7543 - type: nauc_mrr_at_10_diff1 value: 52.278999999999996 - type: nauc_mrr_at_20_max value: 48.2692 - type: nauc_mrr_at_20_std value: -1.5904000000000003 - type: nauc_mrr_at_20_diff1 value: 52.27460000000001 - type: nauc_mrr_at_100_max value: 48.273700000000005 - type: nauc_mrr_at_100_std value: -1.4659 - type: nauc_mrr_at_100_diff1 value: 52.278400000000005 - type: nauc_mrr_at_1000_max value: 48.2811 - type: nauc_mrr_at_1000_std value: -1.4881 - type: nauc_mrr_at_1000_diff1 value: 52.298500000000004 - type: main_score value: 48.189 - task: type: Retrieval dataset: name: MTEB CQADupstackWebmastersRetrieval (default) type: mteb/cqadupstack-webmasters config: default split: test revision: 160c094312a0e1facb97e55eeddb698c0abe3571 metrics: - type: ndcg_at_1 value: 38.141999999999996 - type: ndcg_at_3 value: 42.689 - type: ndcg_at_5 value: 44.318999999999996 - type: ndcg_at_10 value: 47.303 - type: ndcg_at_20 value: 49.236000000000004 - type: ndcg_at_100 value: 53.09700000000001 - type: ndcg_at_1000 value: 55.117000000000004 - type: map_at_1 value: 32.468 - type: map_at_3 value: 38.573 - type: map_at_5 value: 39.926 - type: map_at_10 value: 41.482 - type: map_at_20 value: 42.370000000000005 - type: map_at_100 value: 43.204 - type: map_at_1000 value: 43.425999999999995 - type: recall_at_1 value: 32.468 - type: recall_at_3 value: 44.241 - type: recall_at_5 value: 49.177 - type: recall_at_10 value: 57.63399999999999 - type: recall_at_20 value: 64.724 - type: recall_at_100 value: 83.817 - type: recall_at_1000 value: 95.91 - type: precision_at_1 value: 38.141999999999996 - type: precision_at_3 value: 19.499 - type: precision_at_5 value: 13.478000000000002 - type: precision_at_10 value: 8.774999999999999 - type: precision_at_20 value: 5.455 - type: precision_at_100 value: 1.6760000000000002 - type: precision_at_1000 value: 0.251 - type: mrr_at_1 value: 38.1423 - type: mrr_at_3 value: 44.005300000000005 - type: mrr_at_5 value: 45.1515 - type: mrr_at_10 value: 46.3542 - type: mrr_at_20 value: 46.7589 - type: mrr_at_100 value: 47.185100000000006 - type: mrr_at_1000 value: 47.2249 - type: nauc_ndcg_at_1_max value: 47.905300000000004 - type: nauc_ndcg_at_1_std value: 7.8307 - type: nauc_ndcg_at_1_diff1 value: 51.3311 - type: nauc_ndcg_at_3_max value: 46.8119 - type: nauc_ndcg_at_3_std value: 6.993099999999999 - type: nauc_ndcg_at_3_diff1 value: 48.3281 - type: nauc_ndcg_at_5_max value: 47.5687 - type: nauc_ndcg_at_5_std value: 8.7295 - type: nauc_ndcg_at_5_diff1 value: 49.106300000000005 - type: nauc_ndcg_at_10_max value: 47.3786 - type: nauc_ndcg_at_10_std value: 8.9795 - type: nauc_ndcg_at_10_diff1 value: 47.5348 - type: nauc_ndcg_at_20_max value: 47.9792 - type: nauc_ndcg_at_20_std value: 10.2734 - type: nauc_ndcg_at_20_diff1 value: 48.3578 - type: nauc_ndcg_at_100_max value: 48.5313 - type: nauc_ndcg_at_100_std value: 11.2393 - type: nauc_ndcg_at_100_diff1 value: 47.497299999999996 - type: nauc_ndcg_at_1000_max value: 48.4189 - type: nauc_ndcg_at_1000_std value: 10.857700000000001 - type: nauc_ndcg_at_1000_diff1 value: 47.9808 - type: nauc_map_at_1_max value: 45.0797 - type: nauc_map_at_1_std value: 1.9601 - type: nauc_map_at_1_diff1 value: 55.33050000000001 - type: nauc_map_at_3_max value: 46.6641 - type: nauc_map_at_3_std value: 3.9848000000000003 - type: nauc_map_at_3_diff1 value: 51.4752 - type: nauc_map_at_5_max value: 47.2652 - type: nauc_map_at_5_std value: 5.0378 - type: nauc_map_at_5_diff1 value: 51.3051 - type: nauc_map_at_10_max value: 47.3629 - type: nauc_map_at_10_std value: 5.4796 - type: nauc_map_at_10_diff1 value: 50.43450000000001 - type: nauc_map_at_20_max value: 47.5858 - type: nauc_map_at_20_std value: 6.4494 - type: nauc_map_at_20_diff1 value: 50.3333 - type: nauc_map_at_100_max value: 47.6506 - type: nauc_map_at_100_std value: 7.1591000000000005 - type: nauc_map_at_100_diff1 value: 50.138000000000005 - type: nauc_map_at_1000_max value: 47.516999999999996 - type: nauc_map_at_1000_std value: 7.2322 - type: nauc_map_at_1000_diff1 value: 50.132299999999994 - type: nauc_recall_at_1_max value: 45.0797 - type: nauc_recall_at_1_std value: 1.9601 - type: nauc_recall_at_1_diff1 value: 55.33050000000001 - type: nauc_recall_at_3_max value: 44.9897 - type: nauc_recall_at_3_std value: 5.6308 - type: nauc_recall_at_3_diff1 value: 46.6793 - type: nauc_recall_at_5_max value: 46.6283 - type: nauc_recall_at_5_std value: 9.998999999999999 - type: nauc_recall_at_5_diff1 value: 45.9247 - type: nauc_recall_at_10_max value: 44.714 - type: nauc_recall_at_10_std value: 10.8319 - type: nauc_recall_at_10_diff1 value: 40.291900000000005 - type: nauc_recall_at_20_max value: 46.361200000000004 - type: nauc_recall_at_20_std value: 17.9809 - type: nauc_recall_at_20_diff1 value: 42.4004 - type: nauc_recall_at_100_max value: 48.9864 - type: nauc_recall_at_100_std value: 31.7118 - type: nauc_recall_at_100_diff1 value: 30.9676 - type: nauc_recall_at_1000_max value: 59.9606 - type: nauc_recall_at_1000_std value: 64.66229999999999 - type: nauc_recall_at_1000_diff1 value: 27.669 - type: nauc_precision_at_1_max value: 47.905300000000004 - type: nauc_precision_at_1_std value: 7.8307 - type: nauc_precision_at_1_diff1 value: 51.3311 - type: nauc_precision_at_3_max value: 38.4644 - type: nauc_precision_at_3_std value: 11.7975 - type: nauc_precision_at_3_diff1 value: 27.7451 - type: nauc_precision_at_5_max value: 36.8955 - type: nauc_precision_at_5_std value: 17.702399999999997 - type: nauc_precision_at_5_diff1 value: 24.6268 - type: nauc_precision_at_10_max value: 26.5975 - type: nauc_precision_at_10_std value: 22.3993 - type: nauc_precision_at_10_diff1 value: 8.6213 - type: nauc_precision_at_20_max value: 17.3127 - type: nauc_precision_at_20_std value: 24.7139 - type: nauc_precision_at_20_diff1 value: 1.3941000000000001 - type: nauc_precision_at_100_max value: -0.882 - type: nauc_precision_at_100_std value: 24.5949 - type: nauc_precision_at_100_diff1 value: -10.3409 - type: nauc_precision_at_1000_max value: -15.3829 - type: nauc_precision_at_1000_std value: 15.4108 - type: nauc_precision_at_1000_diff1 value: -19.8547 - type: nauc_mrr_at_1_max value: 47.905300000000004 - type: nauc_mrr_at_1_std value: 7.8307 - type: nauc_mrr_at_1_diff1 value: 51.3311 - type: nauc_mrr_at_3_max value: 46.6702 - type: nauc_mrr_at_3_std value: 8.4343 - type: nauc_mrr_at_3_diff1 value: 47.7232 - type: nauc_mrr_at_5_max value: 47.439 - type: nauc_mrr_at_5_std value: 9.8287 - type: nauc_mrr_at_5_diff1 value: 48.2284 - type: nauc_mrr_at_10_max value: 47.477000000000004 - type: nauc_mrr_at_10_std value: 9.9349 - type: nauc_mrr_at_10_diff1 value: 47.7388 - type: nauc_mrr_at_20_max value: 47.5871 - type: nauc_mrr_at_20_std value: 10.137400000000001 - type: nauc_mrr_at_20_diff1 value: 47.949000000000005 - type: nauc_mrr_at_100_max value: 47.5206 - type: nauc_mrr_at_100_std value: 10.0871 - type: nauc_mrr_at_100_diff1 value: 47.875299999999996 - type: nauc_mrr_at_1000_max value: 47.5212 - type: nauc_mrr_at_1000_std value: 10.0739 - type: nauc_mrr_at_1000_diff1 value: 47.8953 - type: main_score value: 47.303 - task: type: Retrieval dataset: name: MTEB CQADupstackWordpressRetrieval (default) type: mteb/cqadupstack-wordpress config: default split: test revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 metrics: - type: ndcg_at_1 value: 29.759999999999998 - type: ndcg_at_3 value: 33.824 - type: ndcg_at_5 value: 36.766 - type: ndcg_at_10 value: 39.902 - type: ndcg_at_20 value: 41.618 - type: ndcg_at_100 value: 44.983000000000004 - type: ndcg_at_1000 value: 46.938 - type: map_at_1 value: 27.181 - type: map_at_3 value: 31.526 - type: map_at_5 value: 33.397 - type: map_at_10 value: 34.766999999999996 - type: map_at_20 value: 35.244 - type: map_at_100 value: 35.757 - type: map_at_1000 value: 35.836 - type: recall_at_1 value: 27.181 - type: recall_at_3 value: 37.19 - type: recall_at_5 value: 44.153999999999996 - type: recall_at_10 value: 53.705000000000005 - type: recall_at_20 value: 60.22 - type: recall_at_100 value: 77.39200000000001 - type: recall_at_1000 value: 91.77 - type: precision_at_1 value: 29.759999999999998 - type: precision_at_3 value: 13.925 - type: precision_at_5 value: 10.24 - type: precision_at_10 value: 6.265999999999999 - type: precision_at_20 value: 3.549 - type: precision_at_100 value: 0.9520000000000001 - type: precision_at_1000 value: 0.122 - type: mrr_at_1 value: 29.7597 - type: mrr_at_3 value: 34.4732 - type: mrr_at_5 value: 35.915 - type: mrr_at_10 value: 37.1488 - type: mrr_at_20 value: 37.637100000000004 - type: mrr_at_100 value: 38.0403 - type: mrr_at_1000 value: 38.096999999999994 - type: nauc_ndcg_at_1_max value: 35.7865 - type: nauc_ndcg_at_1_std value: 1.9512 - type: nauc_ndcg_at_1_diff1 value: 54.9311 - type: nauc_ndcg_at_3_max value: 32.6952 - type: nauc_ndcg_at_3_std value: 6.2215 - type: nauc_ndcg_at_3_diff1 value: 48.2731 - type: nauc_ndcg_at_5_max value: 33.893 - type: nauc_ndcg_at_5_std value: 5.418 - type: nauc_ndcg_at_5_diff1 value: 47.5903 - type: nauc_ndcg_at_10_max value: 31.5442 - type: nauc_ndcg_at_10_std value: 6.4778 - type: nauc_ndcg_at_10_diff1 value: 46.1388 - type: nauc_ndcg_at_20_max value: 31.613200000000003 - type: nauc_ndcg_at_20_std value: 7.0572 - type: nauc_ndcg_at_20_diff1 value: 46.5949 - type: nauc_ndcg_at_100_max value: 32.8054 - type: nauc_ndcg_at_100_std value: 9.4452 - type: nauc_ndcg_at_100_diff1 value: 46.8179 - type: nauc_ndcg_at_1000_max value: 33.0064 - type: nauc_ndcg_at_1000_std value: 8.8104 - type: nauc_ndcg_at_1000_diff1 value: 47.4082 - type: nauc_map_at_1_max value: 32.9731 - type: nauc_map_at_1_std value: 0.6048 - type: nauc_map_at_1_diff1 value: 53.8662 - type: nauc_map_at_3_max value: 32.1607 - type: nauc_map_at_3_std value: 4.4275 - type: nauc_map_at_3_diff1 value: 49.648900000000005 - type: nauc_map_at_5_max value: 33.0496 - type: nauc_map_at_5_std value: 4.3251 - type: nauc_map_at_5_diff1 value: 49.1433 - type: nauc_map_at_10_max value: 32.2061 - type: nauc_map_at_10_std value: 4.7649 - type: nauc_map_at_10_diff1 value: 48.5962 - type: nauc_map_at_20_max value: 32.2822 - type: nauc_map_at_20_std value: 4.8831 - type: nauc_map_at_20_diff1 value: 48.766799999999996 - type: nauc_map_at_100_max value: 32.521699999999996 - type: nauc_map_at_100_std value: 5.2962 - type: nauc_map_at_100_diff1 value: 48.7986 - type: nauc_map_at_1000_max value: 32.5074 - type: nauc_map_at_1000_std value: 5.2721 - type: nauc_map_at_1000_diff1 value: 48.803000000000004 - type: nauc_recall_at_1_max value: 32.9731 - type: nauc_recall_at_1_std value: 0.6048 - type: nauc_recall_at_1_diff1 value: 53.8662 - type: nauc_recall_at_3_max value: 29.308699999999998 - type: nauc_recall_at_3_std value: 7.6516 - type: nauc_recall_at_3_diff1 value: 42.4534 - type: nauc_recall_at_5_max value: 32.1131 - type: nauc_recall_at_5_std value: 6.260599999999999 - type: nauc_recall_at_5_diff1 value: 40.5131 - type: nauc_recall_at_10_max value: 24.2332 - type: nauc_recall_at_10_std value: 9.7985 - type: nauc_recall_at_10_diff1 value: 34.911500000000004 - type: nauc_recall_at_20_max value: 23.692 - type: nauc_recall_at_20_std value: 12.088799999999999 - type: nauc_recall_at_20_diff1 value: 35.8843 - type: nauc_recall_at_100_max value: 27.729300000000002 - type: nauc_recall_at_100_std value: 31.9796 - type: nauc_recall_at_100_diff1 value: 32.5991 - type: nauc_recall_at_1000_max value: 32.483200000000004 - type: nauc_recall_at_1000_std value: 48.2299 - type: nauc_recall_at_1000_diff1 value: 35.8086 - type: nauc_precision_at_1_max value: 35.7865 - type: nauc_precision_at_1_std value: 1.9512 - type: nauc_precision_at_1_diff1 value: 54.9311 - type: nauc_precision_at_3_max value: 35.729 - type: nauc_precision_at_3_std value: 12.873499999999998 - type: nauc_precision_at_3_diff1 value: 43.6572 - type: nauc_precision_at_5_max value: 35.9285 - type: nauc_precision_at_5_std value: 11.120099999999999 - type: nauc_precision_at_5_diff1 value: 37.458999999999996 - type: nauc_precision_at_10_max value: 29.4037 - type: nauc_precision_at_10_std value: 16.1533 - type: nauc_precision_at_10_diff1 value: 30.7829 - type: nauc_precision_at_20_max value: 28.733700000000002 - type: nauc_precision_at_20_std value: 19.4687 - type: nauc_precision_at_20_diff1 value: 29.154999999999998 - type: nauc_precision_at_100_max value: 28.109099999999998 - type: nauc_precision_at_100_std value: 31.4104 - type: nauc_precision_at_100_diff1 value: 17.7183 - type: nauc_precision_at_1000_max value: 5.8763000000000005 - type: nauc_precision_at_1000_std value: 18.5651 - type: nauc_precision_at_1000_diff1 value: -0.5546 - type: nauc_mrr_at_1_max value: 35.7865 - type: nauc_mrr_at_1_std value: 1.9512 - type: nauc_mrr_at_1_diff1 value: 54.9311 - type: nauc_mrr_at_3_max value: 35.371 - type: nauc_mrr_at_3_std value: 6.447700000000001 - type: nauc_mrr_at_3_diff1 value: 50.998900000000006 - type: nauc_mrr_at_5_max value: 36.2682 - type: nauc_mrr_at_5_std value: 5.8895 - type: nauc_mrr_at_5_diff1 value: 50.72879999999999 - type: nauc_mrr_at_10_max value: 35.1719 - type: nauc_mrr_at_10_std value: 6.074199999999999 - type: nauc_mrr_at_10_diff1 value: 50.087 - type: nauc_mrr_at_20_max value: 35.0608 - type: nauc_mrr_at_20_std value: 6.2545 - type: nauc_mrr_at_20_diff1 value: 50.1754 - type: nauc_mrr_at_100_max value: 35.1314 - type: nauc_mrr_at_100_std value: 6.417299999999999 - type: nauc_mrr_at_100_diff1 value: 50.1819 - type: nauc_mrr_at_1000_max value: 35.124 - type: nauc_mrr_at_1000_std value: 6.3942 - type: nauc_mrr_at_1000_diff1 value: 50.1926 - type: main_score value: 39.902 - task: type: Retrieval dataset: name: MTEB ClimateFEVER (default) type: mteb/climate-fever config: default split: test revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 metrics: - type: ndcg_at_1 value: 40.129999999999995 - type: ndcg_at_3 value: 33.11 - type: ndcg_at_5 value: 34.721999999999994 - type: ndcg_at_10 value: 38.314 - type: ndcg_at_20 value: 41.006 - type: ndcg_at_100 value: 44.651 - type: ndcg_at_1000 value: 47.262 - type: map_at_1 value: 17.72 - type: map_at_3 value: 24.807000000000002 - type: map_at_5 value: 26.931 - type: map_at_10 value: 28.923 - type: map_at_20 value: 29.970999999999997 - type: map_at_100 value: 30.720999999999997 - type: map_at_1000 value: 30.866 - type: recall_at_1 value: 17.72 - type: recall_at_3 value: 29.421000000000003 - type: recall_at_5 value: 35.089 - type: recall_at_10 value: 42.962 - type: recall_at_20 value: 50.46000000000001 - type: recall_at_100 value: 64.39399999999999 - type: recall_at_1000 value: 78.93599999999999 - type: precision_at_1 value: 40.129999999999995 - type: precision_at_3 value: 24.407999999999998 - type: precision_at_5 value: 17.954 - type: precision_at_10 value: 11.375 - type: precision_at_20 value: 6.857 - type: precision_at_100 value: 1.812 - type: precision_at_1000 value: 0.231 - type: mrr_at_1 value: 40.130300000000005 - type: mrr_at_3 value: 48.7296 - type: mrr_at_5 value: 50.3583 - type: mrr_at_10 value: 51.415299999999995 - type: mrr_at_20 value: 51.831700000000005 - type: mrr_at_100 value: 52.0518 - type: mrr_at_1000 value: 52.0826 - type: nauc_ndcg_at_1_max value: 40.104299999999995 - type: nauc_ndcg_at_1_std value: 18.0912 - type: nauc_ndcg_at_1_diff1 value: 37.8955 - type: nauc_ndcg_at_3_max value: 42.9593 - type: nauc_ndcg_at_3_std value: 19.1131 - type: nauc_ndcg_at_3_diff1 value: 30.6546 - type: nauc_ndcg_at_5_max value: 44.351 - type: nauc_ndcg_at_5_std value: 21.026500000000002 - type: nauc_ndcg_at_5_diff1 value: 29.723100000000002 - type: nauc_ndcg_at_10_max value: 45.1246 - type: nauc_ndcg_at_10_std value: 23.4349 - type: nauc_ndcg_at_10_diff1 value: 29.488599999999998 - type: nauc_ndcg_at_20_max value: 45.2818 - type: nauc_ndcg_at_20_std value: 24.904899999999998 - type: nauc_ndcg_at_20_diff1 value: 28.9215 - type: nauc_ndcg_at_100_max value: 46.7221 - type: nauc_ndcg_at_100_std value: 28.011799999999997 - type: nauc_ndcg_at_100_diff1 value: 29.6544 - type: nauc_ndcg_at_1000_max value: 46.7951 - type: nauc_ndcg_at_1000_std value: 28.5671 - type: nauc_ndcg_at_1000_diff1 value: 29.7716 - type: nauc_map_at_1_max value: 41.754400000000004 - type: nauc_map_at_1_std value: 11.7817 - type: nauc_map_at_1_diff1 value: 39.7588 - type: nauc_map_at_3_max value: 43.086 - type: nauc_map_at_3_std value: 16.2776 - type: nauc_map_at_3_diff1 value: 31.2632 - type: nauc_map_at_5_max value: 43.8303 - type: nauc_map_at_5_std value: 18.2317 - type: nauc_map_at_5_diff1 value: 30.451099999999997 - type: nauc_map_at_10_max value: 44.1511 - type: nauc_map_at_10_std value: 19.9622 - type: nauc_map_at_10_diff1 value: 30.1447 - type: nauc_map_at_20_max value: 44.2367 - type: nauc_map_at_20_std value: 20.6727 - type: nauc_map_at_20_diff1 value: 29.7979 - type: nauc_map_at_100_max value: 44.6514 - type: nauc_map_at_100_std value: 21.451999999999998 - type: nauc_map_at_100_diff1 value: 29.9572 - type: nauc_map_at_1000_max value: 44.6665 - type: nauc_map_at_1000_std value: 21.507 - type: nauc_map_at_1000_diff1 value: 29.9788 - type: nauc_recall_at_1_max value: 41.754400000000004 - type: nauc_recall_at_1_std value: 11.7817 - type: nauc_recall_at_1_diff1 value: 39.7588 - type: nauc_recall_at_3_max value: 42.1306 - type: nauc_recall_at_3_std value: 17.397299999999998 - type: nauc_recall_at_3_diff1 value: 26.3229 - type: nauc_recall_at_5_max value: 41.9516 - type: nauc_recall_at_5_std value: 20.566699999999997 - type: nauc_recall_at_5_diff1 value: 23.4934 - type: nauc_recall_at_10_max value: 41.260400000000004 - type: nauc_recall_at_10_std value: 24.0061 - type: nauc_recall_at_10_diff1 value: 21.6158 - type: nauc_recall_at_20_max value: 39.8437 - type: nauc_recall_at_20_std value: 26.892100000000003 - type: nauc_recall_at_20_diff1 value: 19.1214 - type: nauc_recall_at_100_max value: 42.9589 - type: nauc_recall_at_100_std value: 37.7833 - type: nauc_recall_at_100_diff1 value: 19.575899999999997 - type: nauc_recall_at_1000_max value: 43.292500000000004 - type: nauc_recall_at_1000_std value: 46.5189 - type: nauc_recall_at_1000_diff1 value: 16.3096 - type: nauc_precision_at_1_max value: 40.104299999999995 - type: nauc_precision_at_1_std value: 18.0912 - type: nauc_precision_at_1_diff1 value: 37.8955 - type: nauc_precision_at_3_max value: 37.2383 - type: nauc_precision_at_3_std value: 24.0517 - type: nauc_precision_at_3_diff1 value: 19.169800000000002 - type: nauc_precision_at_5_max value: 34.6764 - type: nauc_precision_at_5_std value: 26.4407 - type: nauc_precision_at_5_diff1 value: 14.188 - type: nauc_precision_at_10_max value: 31.1544 - type: nauc_precision_at_10_std value: 28.997099999999996 - type: nauc_precision_at_10_diff1 value: 11.4475 - type: nauc_precision_at_20_max value: 27.065499999999997 - type: nauc_precision_at_20_std value: 29.658099999999997 - type: nauc_precision_at_20_diff1 value: 7.388999999999999 - type: nauc_precision_at_100_max value: 22.5635 - type: nauc_precision_at_100_std value: 35.1885 - type: nauc_precision_at_100_diff1 value: 4.612900000000001 - type: nauc_precision_at_1000_max value: 9.4366 - type: nauc_precision_at_1000_std value: 29.399399999999996 - type: nauc_precision_at_1000_diff1 value: -2.8055 - type: nauc_mrr_at_1_max value: 40.104299999999995 - type: nauc_mrr_at_1_std value: 18.0912 - type: nauc_mrr_at_1_diff1 value: 37.8955 - type: nauc_mrr_at_3_max value: 43.088300000000004 - type: nauc_mrr_at_3_std value: 21.658 - type: nauc_mrr_at_3_diff1 value: 34.4445 - type: nauc_mrr_at_5_max value: 43.2876 - type: nauc_mrr_at_5_std value: 22.6188 - type: nauc_mrr_at_5_diff1 value: 34.143699999999995 - type: nauc_mrr_at_10_max value: 43.4627 - type: nauc_mrr_at_10_std value: 22.7775 - type: nauc_mrr_at_10_diff1 value: 34.3108 - type: nauc_mrr_at_20_max value: 43.5013 - type: nauc_mrr_at_20_std value: 22.825599999999998 - type: nauc_mrr_at_20_diff1 value: 34.4236 - type: nauc_mrr_at_100_max value: 43.543 - type: nauc_mrr_at_100_std value: 22.8566 - type: nauc_mrr_at_100_diff1 value: 34.5171 - type: nauc_mrr_at_1000_max value: 43.5287 - type: nauc_mrr_at_1000_std value: 22.8398 - type: nauc_mrr_at_1000_diff1 value: 34.5149 - type: main_score value: 38.314 - task: type: Retrieval dataset: name: MTEB DBPedia (default) type: mteb/dbpedia config: default split: test revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 metrics: - type: ndcg_at_1 value: 57.875 - type: ndcg_at_3 value: 48.424 - type: ndcg_at_5 value: 45.907 - type: ndcg_at_10 value: 43.881 - type: ndcg_at_20 value: 43.047000000000004 - type: ndcg_at_100 value: 47.892 - type: ndcg_at_1000 value: 55.175 - type: map_at_1 value: 9.705 - type: map_at_3 value: 14.984 - type: map_at_5 value: 17.579 - type: map_at_10 value: 20.901 - type: map_at_20 value: 24.244 - type: map_at_100 value: 29.263 - type: map_at_1000 value: 30.953000000000003 - type: recall_at_1 value: 9.705 - type: recall_at_3 value: 16.136 - type: recall_at_5 value: 20.4 - type: recall_at_10 value: 26.3 - type: recall_at_20 value: 33.719 - type: recall_at_100 value: 53.080000000000005 - type: recall_at_1000 value: 75.732 - type: precision_at_1 value: 70.75 - type: precision_at_3 value: 51.833 - type: precision_at_5 value: 44.2 - type: precision_at_10 value: 34.8 - type: precision_at_20 value: 26.174999999999997 - type: precision_at_100 value: 10.879999999999999 - type: precision_at_1000 value: 2.073 - type: mrr_at_1 value: 70.75 - type: mrr_at_3 value: 76.66669999999999 - type: mrr_at_5 value: 77.7667 - type: mrr_at_10 value: 78.2846 - type: mrr_at_20 value: 78.4431 - type: mrr_at_100 value: 78.5246 - type: mrr_at_1000 value: 78.5325 - type: nauc_ndcg_at_1_max value: 47.8626 - type: nauc_ndcg_at_1_std value: 29.184500000000003 - type: nauc_ndcg_at_1_diff1 value: 51.1817 - type: nauc_ndcg_at_3_max value: 40.4824 - type: nauc_ndcg_at_3_std value: 27.226899999999997 - type: nauc_ndcg_at_3_diff1 value: 29.3703 - type: nauc_ndcg_at_5_max value: 38.145 - type: nauc_ndcg_at_5_std value: 27.050600000000003 - type: nauc_ndcg_at_5_diff1 value: 27.043 - type: nauc_ndcg_at_10_max value: 36.7997 - type: nauc_ndcg_at_10_std value: 25.5961 - type: nauc_ndcg_at_10_diff1 value: 26.062800000000003 - type: nauc_ndcg_at_20_max value: 33.0901 - type: nauc_ndcg_at_20_std value: 21.3937 - type: nauc_ndcg_at_20_diff1 value: 24.8751 - type: nauc_ndcg_at_100_max value: 36.032199999999996 - type: nauc_ndcg_at_100_std value: 26.6399 - type: nauc_ndcg_at_100_diff1 value: 25.341399999999997 - type: nauc_ndcg_at_1000_max value: 42.1806 - type: nauc_ndcg_at_1000_std value: 36.6225 - type: nauc_ndcg_at_1000_diff1 value: 26.957700000000003 - type: nauc_map_at_1_max value: -1.8065000000000002 - type: nauc_map_at_1_std value: -23.1418 - type: nauc_map_at_1_diff1 value: 26.009700000000002 - type: nauc_map_at_3_max value: 4.5538 - type: nauc_map_at_3_std value: -19.7685 - type: nauc_map_at_3_diff1 value: 18.431900000000002 - type: nauc_map_at_5_max value: 7.6586 - type: nauc_map_at_5_std value: -15.1836 - type: nauc_map_at_5_diff1 value: 17.1768 - type: nauc_map_at_10_max value: 12.3345 - type: nauc_map_at_10_std value: -7.3311 - type: nauc_map_at_10_diff1 value: 16.467399999999998 - type: nauc_map_at_20_max value: 16.9535 - type: nauc_map_at_20_std value: 2.3999 - type: nauc_map_at_20_diff1 value: 16.1074 - type: nauc_map_at_100_max value: 24.238699999999998 - type: nauc_map_at_100_std value: 17.0193 - type: nauc_map_at_100_diff1 value: 17.179 - type: nauc_map_at_1000_max value: 26.147199999999998 - type: nauc_map_at_1000_std value: 20.597199999999997 - type: nauc_map_at_1000_diff1 value: 17.3145 - type: nauc_recall_at_1_max value: -1.8065000000000002 - type: nauc_recall_at_1_std value: -23.1418 - type: nauc_recall_at_1_diff1 value: 26.009700000000002 - type: nauc_recall_at_3_max value: 1.7474 - type: nauc_recall_at_3_std value: -21.331 - type: nauc_recall_at_3_diff1 value: 14.844899999999999 - type: nauc_recall_at_5_max value: 3.9203 - type: nauc_recall_at_5_std value: -17.225299999999997 - type: nauc_recall_at_5_diff1 value: 13.3026 - type: nauc_recall_at_10_max value: 7.484399999999999 - type: nauc_recall_at_10_std value: -10.879800000000001 - type: nauc_recall_at_10_diff1 value: 11.187 - type: nauc_recall_at_20_max value: 12.327499999999999 - type: nauc_recall_at_20_std value: -1.7592 - type: nauc_recall_at_20_diff1 value: 12.3485 - type: nauc_recall_at_100_max value: 26.868799999999997 - type: nauc_recall_at_100_std value: 23.4846 - type: nauc_recall_at_100_diff1 value: 16.4859 - type: nauc_recall_at_1000_max value: 35.4478 - type: nauc_recall_at_1000_std value: 42.7445 - type: nauc_recall_at_1000_diff1 value: 17.108 - type: nauc_precision_at_1_max value: 59.8572 - type: nauc_precision_at_1_std value: 39.1 - type: nauc_precision_at_1_diff1 value: 57.475 - type: nauc_precision_at_3_max value: 42.9945 - type: nauc_precision_at_3_std value: 41.5933 - type: nauc_precision_at_3_diff1 value: 12.3299 - type: nauc_precision_at_5_max value: 39.8975 - type: nauc_precision_at_5_std value: 46.3626 - type: nauc_precision_at_5_diff1 value: 7.990600000000001 - type: nauc_precision_at_10_max value: 37.501200000000004 - type: nauc_precision_at_10_std value: 51.9395 - type: nauc_precision_at_10_diff1 value: 4.8036 - type: nauc_precision_at_20_max value: 34.9806 - type: nauc_precision_at_20_std value: 53.513999999999996 - type: nauc_precision_at_20_diff1 value: 3.8808000000000002 - type: nauc_precision_at_100_max value: 29.6714 - type: nauc_precision_at_100_std value: 50.9404 - type: nauc_precision_at_100_diff1 value: 1.7782 - type: nauc_precision_at_1000_max value: 4.9528 - type: nauc_precision_at_1000_std value: 23.0701 - type: nauc_precision_at_1000_diff1 value: -11.6606 - type: nauc_mrr_at_1_max value: 59.8572 - type: nauc_mrr_at_1_std value: 39.1 - type: nauc_mrr_at_1_diff1 value: 57.475 - type: nauc_mrr_at_3_max value: 61.6508 - type: nauc_mrr_at_3_std value: 43.013400000000004 - type: nauc_mrr_at_3_diff1 value: 55.14170000000001 - type: nauc_mrr_at_5_max value: 61.8982 - type: nauc_mrr_at_5_std value: 42.4903 - type: nauc_mrr_at_5_diff1 value: 55.880300000000005 - type: nauc_mrr_at_10_max value: 61.6843 - type: nauc_mrr_at_10_std value: 42.8332 - type: nauc_mrr_at_10_diff1 value: 55.7773 - type: nauc_mrr_at_20_max value: 61.7877 - type: nauc_mrr_at_20_std value: 42.6655 - type: nauc_mrr_at_20_diff1 value: 55.9627 - type: nauc_mrr_at_100_max value: 61.755300000000005 - type: nauc_mrr_at_100_std value: 42.681799999999996 - type: nauc_mrr_at_100_diff1 value: 55.97410000000001 - type: nauc_mrr_at_1000_max value: 61.7454 - type: nauc_mrr_at_1000_std value: 42.6813 - type: nauc_mrr_at_1000_diff1 value: 55.9732 - type: main_score value: 43.881 - task: type: Classification dataset: name: MTEB EmotionClassification (default) type: mteb/emotion config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 42.385 - type: f1 value: 38.2581 - type: f1_weighted value: 44.6657 - type: main_score value: 42.385 - task: type: Retrieval dataset: name: MTEB FEVER (default) type: mteb/fever config: default split: test revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 metrics: - type: ndcg_at_1 value: 89.81400000000001 - type: ndcg_at_3 value: 90.789 - type: ndcg_at_5 value: 91.266 - type: ndcg_at_10 value: 91.552 - type: ndcg_at_20 value: 91.759 - type: ndcg_at_100 value: 92.04 - type: ndcg_at_1000 value: 92.264 - type: map_at_1 value: 83.343 - type: map_at_3 value: 88.293 - type: map_at_5 value: 88.709 - type: map_at_10 value: 88.895 - type: map_at_20 value: 88.985 - type: map_at_100 value: 89.046 - type: map_at_1000 value: 89.059 - type: recall_at_1 value: 83.343 - type: recall_at_3 value: 92.545 - type: recall_at_5 value: 93.944 - type: recall_at_10 value: 94.82300000000001 - type: recall_at_20 value: 95.48100000000001 - type: recall_at_100 value: 96.64 - type: recall_at_1000 value: 97.989 - type: precision_at_1 value: 89.81400000000001 - type: precision_at_3 value: 33.698 - type: precision_at_5 value: 20.602999999999998 - type: precision_at_10 value: 10.453 - type: precision_at_20 value: 5.299 - type: precision_at_100 value: 1.091 - type: precision_at_1000 value: 0.11299999999999999 - type: mrr_at_1 value: 89.81400000000001 - type: mrr_at_3 value: 93.7594 - type: mrr_at_5 value: 94.0144 - type: mrr_at_10 value: 94.073 - type: mrr_at_20 value: 94.0835 - type: mrr_at_100 value: 94.0871 - type: mrr_at_1000 value: 94.0873 - type: nauc_ndcg_at_1_max value: 23.8983 - type: nauc_ndcg_at_1_std value: -16.226 - type: nauc_ndcg_at_1_diff1 value: 78.4902 - type: nauc_ndcg_at_3_max value: 15.106 - type: nauc_ndcg_at_3_std value: -11.4 - type: nauc_ndcg_at_3_diff1 value: 41.9768 - type: nauc_ndcg_at_5_max value: 14.6485 - type: nauc_ndcg_at_5_std value: -9.5441 - type: nauc_ndcg_at_5_diff1 value: 39.7958 - type: nauc_ndcg_at_10_max value: 14.241100000000001 - type: nauc_ndcg_at_10_std value: -8.4259 - type: nauc_ndcg_at_10_diff1 value: 38.8701 - type: nauc_ndcg_at_20_max value: 14.211199999999998 - type: nauc_ndcg_at_20_std value: -7.916399999999999 - type: nauc_ndcg_at_20_diff1 value: 39.3907 - type: nauc_ndcg_at_100_max value: 14.871400000000001 - type: nauc_ndcg_at_100_std value: -7.4491000000000005 - type: nauc_ndcg_at_100_diff1 value: 40.7175 - type: nauc_ndcg_at_1000_max value: 15.386800000000001 - type: nauc_ndcg_at_1000_std value: -7.939100000000001 - type: nauc_ndcg_at_1000_diff1 value: 42.1499 - type: nauc_map_at_1_max value: 13.431199999999999 - type: nauc_map_at_1_std value: -10.2714 - type: nauc_map_at_1_diff1 value: 50.8151 - type: nauc_map_at_3_max value: 13.2276 - type: nauc_map_at_3_std value: -9.8315 - type: nauc_map_at_3_diff1 value: 39.6441 - type: nauc_map_at_5_max value: 13.4859 - type: nauc_map_at_5_std value: -9.284 - type: nauc_map_at_5_diff1 value: 39.4358 - type: nauc_map_at_10_max value: 13.578399999999998 - type: nauc_map_at_10_std value: -8.828800000000001 - type: nauc_map_at_10_diff1 value: 39.338499999999996 - type: nauc_map_at_20_max value: 13.600200000000001 - type: nauc_map_at_20_std value: -8.6524 - type: nauc_map_at_20_diff1 value: 39.5327 - type: nauc_map_at_100_max value: 13.7266 - type: nauc_map_at_100_std value: -8.583 - type: nauc_map_at_100_diff1 value: 39.749 - type: nauc_map_at_1000_max value: 13.7522 - type: nauc_map_at_1000_std value: -8.5978 - type: nauc_map_at_1000_diff1 value: 39.8105 - type: nauc_recall_at_1_max value: 13.431199999999999 - type: nauc_recall_at_1_std value: -10.2714 - type: nauc_recall_at_1_diff1 value: 50.8151 - type: nauc_recall_at_3_max value: 7.7703999999999995 - type: nauc_recall_at_3_std value: -7.5428999999999995 - type: nauc_recall_at_3_diff1 value: 14.6511 - type: nauc_recall_at_5_max value: 7.7514 - type: nauc_recall_at_5_std value: -0.9165 - type: nauc_recall_at_5_diff1 value: 5.1985 - type: nauc_recall_at_10_max value: 5.4695 - type: nauc_recall_at_10_std value: 4.8362 - type: nauc_recall_at_10_diff1 value: -2.3994 - type: nauc_recall_at_20_max value: 3.7693 - type: nauc_recall_at_20_std value: 9.4046 - type: nauc_recall_at_20_diff1 value: -5.3729 - type: nauc_recall_at_100_max value: 4.6496 - type: nauc_recall_at_100_std value: 19.605700000000002 - type: nauc_recall_at_100_diff1 value: -9.1885 - type: nauc_recall_at_1000_max value: 7.266 - type: nauc_recall_at_1000_std value: 25.461699999999997 - type: nauc_recall_at_1000_diff1 value: -11.698699999999999 - type: nauc_precision_at_1_max value: 23.8983 - type: nauc_precision_at_1_std value: -16.226 - type: nauc_precision_at_1_diff1 value: 78.4902 - type: nauc_precision_at_3_max value: 14.686399999999999 - type: nauc_precision_at_3_std value: -5.6663 - type: nauc_precision_at_3_diff1 value: 0.5428999999999999 - type: nauc_precision_at_5_max value: 12.9569 - type: nauc_precision_at_5_std value: 1.145 - type: nauc_precision_at_5_diff1 value: -10.0661 - type: nauc_precision_at_10_max value: 9.8558 - type: nauc_precision_at_10_std value: 6.1638 - type: nauc_precision_at_10_diff1 value: -14.3308 - type: nauc_precision_at_20_max value: 7.1591000000000005 - type: nauc_precision_at_20_std value: 8.4559 - type: nauc_precision_at_20_diff1 value: -12.226099999999999 - type: nauc_precision_at_100_max value: 7.6160000000000005 - type: nauc_precision_at_100_std value: 8.6876 - type: nauc_precision_at_100_diff1 value: -5.8182 - type: nauc_precision_at_1000_max value: 7.3231 - type: nauc_precision_at_1000_std value: 4.929399999999999 - type: nauc_precision_at_1000_diff1 value: -1.187 - type: nauc_mrr_at_1_max value: 23.8983 - type: nauc_mrr_at_1_std value: -16.226 - type: nauc_mrr_at_1_diff1 value: 78.4902 - type: nauc_mrr_at_3_max value: 25.2759 - type: nauc_mrr_at_3_std value: -20.4713 - type: nauc_mrr_at_3_diff1 value: 77.55030000000001 - type: nauc_mrr_at_5_max value: 25.709799999999998 - type: nauc_mrr_at_5_std value: -19.3177 - type: nauc_mrr_at_5_diff1 value: 77.7659 - type: nauc_mrr_at_10_max value: 25.4059 - type: nauc_mrr_at_10_std value: -19.128600000000002 - type: nauc_mrr_at_10_diff1 value: 77.78580000000001 - type: nauc_mrr_at_20_max value: 25.303399999999996 - type: nauc_mrr_at_20_std value: -19.137999999999998 - type: nauc_mrr_at_20_diff1 value: 77.7914 - type: nauc_mrr_at_100_max value: 25.2918 - type: nauc_mrr_at_100_std value: -19.1132 - type: nauc_mrr_at_100_diff1 value: 77.7997 - type: nauc_mrr_at_1000_max value: 25.2892 - type: nauc_mrr_at_1000_std value: -19.1172 - type: nauc_mrr_at_1000_diff1 value: 77.7992 - type: main_score value: 91.552 - task: type: Retrieval dataset: name: MTEB FiQA2018 (default) type: mteb/fiqa config: default split: test revision: 27a168819829fe9bcd655c2df245fb19452e8e06 metrics: - type: ndcg_at_1 value: 44.907000000000004 - type: ndcg_at_3 value: 40.095 - type: ndcg_at_5 value: 41.464 - type: ndcg_at_10 value: 43.958999999999996 - type: ndcg_at_20 value: 46.931 - type: ndcg_at_100 value: 50.656 - type: ndcg_at_1000 value: 53.474999999999994 - type: map_at_1 value: 22.846 - type: map_at_3 value: 31.533 - type: map_at_5 value: 34.175 - type: map_at_10 value: 36.105 - type: map_at_20 value: 37.232 - type: map_at_100 value: 37.993 - type: map_at_1000 value: 38.171 - type: recall_at_1 value: 22.846 - type: recall_at_3 value: 36.065000000000005 - type: recall_at_5 value: 42.754999999999995 - type: recall_at_10 value: 50.595 - type: recall_at_20 value: 59.85 - type: recall_at_100 value: 75.08 - type: recall_at_1000 value: 91.685 - type: precision_at_1 value: 44.907000000000004 - type: precision_at_3 value: 26.183 - type: precision_at_5 value: 19.29 - type: precision_at_10 value: 11.883000000000001 - type: precision_at_20 value: 7.191 - type: precision_at_100 value: 1.8870000000000002 - type: precision_at_1000 value: 0.23900000000000002 - type: mrr_at_1 value: 44.907399999999996 - type: mrr_at_3 value: 50.10289999999999 - type: mrr_at_5 value: 51.5303 - type: mrr_at_10 value: 52.61169999999999 - type: mrr_at_20 value: 53.13290000000001 - type: mrr_at_100 value: 53.3809 - type: mrr_at_1000 value: 53.4181 - type: nauc_ndcg_at_1_max value: 50.2672 - type: nauc_ndcg_at_1_std value: -5.858 - type: nauc_ndcg_at_1_diff1 value: 55.1067 - type: nauc_ndcg_at_3_max value: 40.9279 - type: nauc_ndcg_at_3_std value: -6.954000000000001 - type: nauc_ndcg_at_3_diff1 value: 43.9096 - type: nauc_ndcg_at_5_max value: 38.406400000000005 - type: nauc_ndcg_at_5_std value: -5.951 - type: nauc_ndcg_at_5_diff1 value: 42.9537 - type: nauc_ndcg_at_10_max value: 40.1602 - type: nauc_ndcg_at_10_std value: -3.486 - type: nauc_ndcg_at_10_diff1 value: 43.693 - type: nauc_ndcg_at_20_max value: 40.3159 - type: nauc_ndcg_at_20_std value: -1.6125 - type: nauc_ndcg_at_20_diff1 value: 43.0649 - type: nauc_ndcg_at_100_max value: 42.5543 - type: nauc_ndcg_at_100_std value: 0.133 - type: nauc_ndcg_at_100_diff1 value: 44.263799999999996 - type: nauc_ndcg_at_1000_max value: 43.520399999999995 - type: nauc_ndcg_at_1000_std value: -0.49300000000000005 - type: nauc_ndcg_at_1000_diff1 value: 44.550200000000004 - type: nauc_map_at_1_max value: 26.930300000000003 - type: nauc_map_at_1_std value: -6.8881 - type: nauc_map_at_1_diff1 value: 45.905499999999996 - type: nauc_map_at_3_max value: 32.3991 - type: nauc_map_at_3_std value: -8.1954 - type: nauc_map_at_3_diff1 value: 42.9392 - type: nauc_map_at_5_max value: 34.0031 - type: nauc_map_at_5_std value: -6.9963999999999995 - type: nauc_map_at_5_diff1 value: 42.7737 - type: nauc_map_at_10_max value: 36.38 - type: nauc_map_at_10_std value: -5.663 - type: nauc_map_at_10_diff1 value: 43.1583 - type: nauc_map_at_20_max value: 36.6981 - type: nauc_map_at_20_std value: -4.9736 - type: nauc_map_at_20_diff1 value: 42.924800000000005 - type: nauc_map_at_100_max value: 37.268699999999995 - type: nauc_map_at_100_std value: -4.6967 - type: nauc_map_at_100_diff1 value: 43.024 - type: nauc_map_at_1000_max value: 37.3818 - type: nauc_map_at_1000_std value: -4.7077 - type: nauc_map_at_1000_diff1 value: 43.0575 - type: nauc_recall_at_1_max value: 26.930300000000003 - type: nauc_recall_at_1_std value: -6.8881 - type: nauc_recall_at_1_diff1 value: 45.905499999999996 - type: nauc_recall_at_3_max value: 27.860200000000003 - type: nauc_recall_at_3_std value: -7.8473 - type: nauc_recall_at_3_diff1 value: 36.569 - type: nauc_recall_at_5_max value: 27.1751 - type: nauc_recall_at_5_std value: -5.0796 - type: nauc_recall_at_5_diff1 value: 33.9236 - type: nauc_recall_at_10_max value: 32.0004 - type: nauc_recall_at_10_std value: 1.0071 - type: nauc_recall_at_10_diff1 value: 33.1849 - type: nauc_recall_at_20_max value: 30.6595 - type: nauc_recall_at_20_std value: 7.3179 - type: nauc_recall_at_20_diff1 value: 29.751300000000004 - type: nauc_recall_at_100_max value: 35.9924 - type: nauc_recall_at_100_std value: 21.691399999999998 - type: nauc_recall_at_100_diff1 value: 31.397100000000002 - type: nauc_recall_at_1000_max value: 47.176899999999996 - type: nauc_recall_at_1000_std value: 37.8536 - type: nauc_recall_at_1000_diff1 value: 30.2447 - type: nauc_precision_at_1_max value: 50.2672 - type: nauc_precision_at_1_std value: -5.858 - type: nauc_precision_at_1_diff1 value: 55.1067 - type: nauc_precision_at_3_max value: 44.4071 - type: nauc_precision_at_3_std value: -4.4772 - type: nauc_precision_at_3_diff1 value: 32.6195 - type: nauc_precision_at_5_max value: 42.6336 - type: nauc_precision_at_5_std value: -0.9528 - type: nauc_precision_at_5_diff1 value: 27.821299999999997 - type: nauc_precision_at_10_max value: 45.5267 - type: nauc_precision_at_10_std value: 4.0484 - type: nauc_precision_at_10_diff1 value: 23.8886 - type: nauc_precision_at_20_max value: 41.7389 - type: nauc_precision_at_20_std value: 9.3544 - type: nauc_precision_at_20_diff1 value: 16.236700000000003 - type: nauc_precision_at_100_max value: 38.4564 - type: nauc_precision_at_100_std value: 12.544 - type: nauc_precision_at_100_diff1 value: 10.5924 - type: nauc_precision_at_1000_max value: 31.2525 - type: nauc_precision_at_1000_std value: 10.641399999999999 - type: nauc_precision_at_1000_diff1 value: 1.5966 - type: nauc_mrr_at_1_max value: 50.2672 - type: nauc_mrr_at_1_std value: -5.858 - type: nauc_mrr_at_1_diff1 value: 55.1067 - type: nauc_mrr_at_3_max value: 49.1124 - type: nauc_mrr_at_3_std value: -5.0685 - type: nauc_mrr_at_3_diff1 value: 51.1787 - type: nauc_mrr_at_5_max value: 48.5671 - type: nauc_mrr_at_5_std value: -4.6053999999999995 - type: nauc_mrr_at_5_diff1 value: 50.688599999999994 - type: nauc_mrr_at_10_max value: 49.2018 - type: nauc_mrr_at_10_std value: -3.8524000000000003 - type: nauc_mrr_at_10_diff1 value: 50.4746 - type: nauc_mrr_at_20_max value: 49.2589 - type: nauc_mrr_at_20_std value: -3.5479 - type: nauc_mrr_at_20_diff1 value: 50.4304 - type: nauc_mrr_at_100_max value: 49.3016 - type: nauc_mrr_at_100_std value: -3.5770999999999997 - type: nauc_mrr_at_100_diff1 value: 50.6172 - type: nauc_mrr_at_1000_max value: 49.2911 - type: nauc_mrr_at_1000_std value: -3.6117999999999997 - type: nauc_mrr_at_1000_diff1 value: 50.6268 - type: main_score value: 43.958999999999996 - task: type: Retrieval dataset: name: MTEB HotpotQA (default) type: mteb/hotpotqa config: default split: test revision: ab518f4d6fcca38d87c25209f94beba119d02014 metrics: - type: ndcg_at_1 value: 85.955 - type: ndcg_at_3 value: 68.83 - type: ndcg_at_5 value: 70.894 - type: ndcg_at_10 value: 72.399 - type: ndcg_at_20 value: 73.328 - type: ndcg_at_100 value: 74.765 - type: ndcg_at_1000 value: 75.87899999999999 - type: map_at_1 value: 42.978 - type: map_at_3 value: 61.568 - type: map_at_5 value: 63.241 - type: map_at_10 value: 64.18199999999999 - type: map_at_20 value: 64.562 - type: map_at_100 value: 64.865 - type: map_at_1000 value: 64.922 - type: recall_at_1 value: 42.978 - type: recall_at_3 value: 64.801 - type: recall_at_5 value: 68.866 - type: recall_at_10 value: 72.627 - type: recall_at_20 value: 75.625 - type: recall_at_100 value: 81.951 - type: recall_at_1000 value: 89.37899999999999 - type: precision_at_1 value: 85.955 - type: precision_at_3 value: 43.201 - type: precision_at_5 value: 27.546 - type: precision_at_10 value: 14.524999999999999 - type: precision_at_20 value: 7.562 - type: precision_at_100 value: 1.6389999999999998 - type: precision_at_1000 value: 0.179 - type: mrr_at_1 value: 85.9554 - type: mrr_at_3 value: 89.2753 - type: mrr_at_5 value: 89.6838 - type: mrr_at_10 value: 89.8559 - type: mrr_at_20 value: 89.92569999999999 - type: mrr_at_100 value: 89.96600000000001 - type: mrr_at_1000 value: 89.97070000000001 - type: nauc_ndcg_at_1_max value: 57.1837 - type: nauc_ndcg_at_1_std value: -4.2725 - type: nauc_ndcg_at_1_diff1 value: 74.8832 - type: nauc_ndcg_at_3_max value: 13.953399999999998 - type: nauc_ndcg_at_3_std value: 0.9547 - type: nauc_ndcg_at_3_diff1 value: 4.6952 - type: nauc_ndcg_at_5_max value: 12.1892 - type: nauc_ndcg_at_5_std value: 1.7878 - type: nauc_ndcg_at_5_diff1 value: 2.1255 - type: nauc_ndcg_at_10_max value: 11.4909 - type: nauc_ndcg_at_10_std value: 2.9917 - type: nauc_ndcg_at_10_diff1 value: 1.111 - type: nauc_ndcg_at_20_max value: 11.183800000000002 - type: nauc_ndcg_at_20_std value: 3.8205999999999998 - type: nauc_ndcg_at_20_diff1 value: 0.5191 - type: nauc_ndcg_at_100_max value: 11.4582 - type: nauc_ndcg_at_100_std value: 5.2234 - type: nauc_ndcg_at_100_diff1 value: 0.7051 - type: nauc_ndcg_at_1000_max value: 11.8891 - type: nauc_ndcg_at_1000_std value: 5.0018 - type: nauc_ndcg_at_1000_diff1 value: 1.3516 - type: nauc_map_at_1_max value: 57.1837 - type: nauc_map_at_1_std value: -4.2725 - type: nauc_map_at_1_diff1 value: 74.8832 - type: nauc_map_at_3_max value: 8.7588 - type: nauc_map_at_3_std value: 0.8586 - type: nauc_map_at_3_diff1 value: -2.1179 - type: nauc_map_at_5_max value: 7.8513 - type: nauc_map_at_5_std value: 1.4206999999999999 - type: nauc_map_at_5_diff1 value: -3.5381000000000005 - type: nauc_map_at_10_max value: 7.603999999999999 - type: nauc_map_at_10_std value: 2.0785 - type: nauc_map_at_10_diff1 value: -3.9354 - type: nauc_map_at_20_max value: 7.5393 - type: nauc_map_at_20_std value: 2.3233 - type: nauc_map_at_20_diff1 value: -4.0794999999999995 - type: nauc_map_at_100_max value: 7.593500000000001 - type: nauc_map_at_100_std value: 2.5528 - type: nauc_map_at_100_diff1 value: -4.0459000000000005 - type: nauc_map_at_1000_max value: 7.6116 - type: nauc_map_at_1000_std value: 2.5475000000000003 - type: nauc_map_at_1000_diff1 value: -4.0208 - type: nauc_recall_at_1_max value: 57.1837 - type: nauc_recall_at_1_std value: -4.2725 - type: nauc_recall_at_1_diff1 value: 74.8832 - type: nauc_recall_at_3_max value: 5.1265 - type: nauc_recall_at_3_std value: 2.3453999999999997 - type: nauc_recall_at_3_diff1 value: -9.5534 - type: nauc_recall_at_5_max value: 1.3988 - type: nauc_recall_at_5_std value: 3.8738 - type: nauc_recall_at_5_diff1 value: -14.770900000000001 - type: nauc_recall_at_10_max value: -1.1159999999999999 - type: nauc_recall_at_10_std value: 6.7406999999999995 - type: nauc_recall_at_10_diff1 value: -18.08 - type: nauc_recall_at_20_max value: -2.9072 - type: nauc_recall_at_20_std value: 9.6567 - type: nauc_recall_at_20_diff1 value: -21.197 - type: nauc_recall_at_100_max value: -4.4864 - type: nauc_recall_at_100_std value: 17.8761 - type: nauc_recall_at_100_diff1 value: -24.5792 - type: nauc_recall_at_1000_max value: -7.9052 - type: nauc_recall_at_1000_std value: 21.7637 - type: nauc_recall_at_1000_diff1 value: -30.4447 - type: nauc_precision_at_1_max value: 57.1837 - type: nauc_precision_at_1_std value: -4.2725 - type: nauc_precision_at_1_diff1 value: 74.8832 - type: nauc_precision_at_3_max value: 5.1265 - type: nauc_precision_at_3_std value: 2.3453999999999997 - type: nauc_precision_at_3_diff1 value: -9.5534 - type: nauc_precision_at_5_max value: 1.3988 - type: nauc_precision_at_5_std value: 3.8738 - type: nauc_precision_at_5_diff1 value: -14.770900000000001 - type: nauc_precision_at_10_max value: -1.1159999999999999 - type: nauc_precision_at_10_std value: 6.7406999999999995 - type: nauc_precision_at_10_diff1 value: -18.08 - type: nauc_precision_at_20_max value: -2.9072 - type: nauc_precision_at_20_std value: 9.6567 - type: nauc_precision_at_20_diff1 value: -21.197 - type: nauc_precision_at_100_max value: -4.4864 - type: nauc_precision_at_100_std value: 17.8761 - type: nauc_precision_at_100_diff1 value: -24.5792 - type: nauc_precision_at_1000_max value: -7.9052 - type: nauc_precision_at_1000_std value: 21.7637 - type: nauc_precision_at_1000_diff1 value: -30.4447 - type: nauc_mrr_at_1_max value: 57.1837 - type: nauc_mrr_at_1_std value: -4.2725 - type: nauc_mrr_at_1_diff1 value: 74.8832 - type: nauc_mrr_at_3_max value: 60.68019999999999 - type: nauc_mrr_at_3_std value: -2.5041 - type: nauc_mrr_at_3_diff1 value: 74.2505 - type: nauc_mrr_at_5_max value: 60.3928 - type: nauc_mrr_at_5_std value: -2.2979 - type: nauc_mrr_at_5_diff1 value: 74.27470000000001 - type: nauc_mrr_at_10_max value: 60.336800000000004 - type: nauc_mrr_at_10_std value: -2.308 - type: nauc_mrr_at_10_diff1 value: 74.4135 - type: nauc_mrr_at_20_max value: 60.317299999999996 - type: nauc_mrr_at_20_std value: -2.1652 - type: nauc_mrr_at_20_diff1 value: 74.3945 - type: nauc_mrr_at_100_max value: 60.283 - type: nauc_mrr_at_100_std value: -2.154 - type: nauc_mrr_at_100_diff1 value: 74.38040000000001 - type: nauc_mrr_at_1000_max value: 60.272099999999995 - type: nauc_mrr_at_1000_std value: -2.1783 - type: nauc_mrr_at_1000_diff1 value: 74.378 - type: main_score value: 72.399 - task: type: Classification dataset: name: MTEB ImdbClassification (default) type: mteb/imdb config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 69.0916 - type: f1 value: 68.9866 - type: f1_weighted value: 68.9866 - type: ap value: 63.3215 - type: ap_weighted value: 63.3215 - type: main_score value: 69.0916 - task: type: Retrieval dataset: name: MTEB MSMARCO (default) type: mteb/msmarco config: default split: dev revision: c5a29a104738b98a9e76336939199e264163d4a0 metrics: - type: ndcg_at_1 value: 24.914 - type: ndcg_at_3 value: 36.479 - type: ndcg_at_5 value: 40.288000000000004 - type: ndcg_at_10 value: 44.043 - type: ndcg_at_20 value: 46.838 - type: ndcg_at_100 value: 49.626999999999995 - type: ndcg_at_1000 value: 50.665000000000006 - type: map_at_1 value: 24.223 - type: map_at_3 value: 33.348 - type: map_at_5 value: 35.494 - type: map_at_10 value: 37.077 - type: map_at_20 value: 37.867 - type: map_at_100 value: 38.279999999999994 - type: map_at_1000 value: 38.323 - type: recall_at_1 value: 24.223 - type: recall_at_3 value: 44.9 - type: recall_at_5 value: 54.010999999999996 - type: recall_at_10 value: 65.399 - type: recall_at_20 value: 76.248 - type: recall_at_100 value: 90.78 - type: recall_at_1000 value: 98.619 - type: precision_at_1 value: 24.914 - type: precision_at_3 value: 15.501000000000001 - type: precision_at_5 value: 11.238 - type: precision_at_10 value: 6.837 - type: precision_at_20 value: 3.9960000000000004 - type: precision_at_100 value: 0.959 - type: precision_at_1000 value: 0.105 - type: mrr_at_1 value: 24.914 - type: mrr_at_3 value: 34.0043 - type: mrr_at_5 value: 36.1089 - type: mrr_at_10 value: 37.6521 - type: mrr_at_20 value: 38.4106 - type: mrr_at_100 value: 38.7938 - type: mrr_at_1000 value: 38.8316 - type: nauc_ndcg_at_1_max value: 3.9297 - type: nauc_ndcg_at_1_std value: -22.016 - type: nauc_ndcg_at_1_diff1 value: 39.7204 - type: nauc_ndcg_at_3_max value: 4.7672 - type: nauc_ndcg_at_3_std value: -27.0359 - type: nauc_ndcg_at_3_diff1 value: 34.139 - type: nauc_ndcg_at_5_max value: 5.1921 - type: nauc_ndcg_at_5_std value: -28.6425 - type: nauc_ndcg_at_5_diff1 value: 33.671800000000005 - type: nauc_ndcg_at_10_max value: 5.3812999999999995 - type: nauc_ndcg_at_10_std value: -28.7602 - type: nauc_ndcg_at_10_diff1 value: 33.5856 - type: nauc_ndcg_at_20_max value: 5.7039 - type: nauc_ndcg_at_20_std value: -27.578000000000003 - type: nauc_ndcg_at_20_diff1 value: 33.9639 - type: nauc_ndcg_at_100_max value: 5.9491000000000005 - type: nauc_ndcg_at_100_std value: -25.562800000000003 - type: nauc_ndcg_at_100_diff1 value: 34.5177 - type: nauc_ndcg_at_1000_max value: 5.7685 - type: nauc_ndcg_at_1000_std value: -25.796400000000002 - type: nauc_ndcg_at_1000_diff1 value: 34.617 - type: nauc_map_at_1_max value: 3.8164 - type: nauc_map_at_1_std value: -22.1345 - type: nauc_map_at_1_diff1 value: 39.7682 - type: nauc_map_at_3_max value: 4.5438 - type: nauc_map_at_3_std value: -25.990299999999998 - type: nauc_map_at_3_diff1 value: 35.4211 - type: nauc_map_at_5_max value: 4.7521 - type: nauc_map_at_5_std value: -26.9187 - type: nauc_map_at_5_diff1 value: 35.1711 - type: nauc_map_at_10_max value: 4.8275 - type: nauc_map_at_10_std value: -26.962799999999998 - type: nauc_map_at_10_diff1 value: 35.1875 - type: nauc_map_at_20_max value: 4.9247 - type: nauc_map_at_20_std value: -26.622899999999998 - type: nauc_map_at_20_diff1 value: 35.308499999999995 - type: nauc_map_at_100_max value: 4.9704 - type: nauc_map_at_100_std value: -26.3156 - type: nauc_map_at_100_diff1 value: 35.3955 - type: nauc_map_at_1000_max value: 4.9692 - type: nauc_map_at_1000_std value: -26.3098 - type: nauc_map_at_1000_diff1 value: 35.3987 - type: nauc_recall_at_1_max value: 3.8164 - type: nauc_recall_at_1_std value: -22.1345 - type: nauc_recall_at_1_diff1 value: 39.7682 - type: nauc_recall_at_3_max value: 5.2443 - type: nauc_recall_at_3_std value: -29.965000000000003 - type: nauc_recall_at_3_diff1 value: 30.303 - type: nauc_recall_at_5_max value: 6.164499999999999 - type: nauc_recall_at_5_std value: -33.9534 - type: nauc_recall_at_5_diff1 value: 28.9101 - type: nauc_recall_at_10_max value: 6.8656999999999995 - type: nauc_recall_at_10_std value: -35.2711 - type: nauc_recall_at_10_diff1 value: 27.785500000000003 - type: nauc_recall_at_20_max value: 8.7891 - type: nauc_recall_at_20_std value: -31.276 - type: nauc_recall_at_20_diff1 value: 28.048099999999998 - type: nauc_recall_at_100_max value: 15.3546 - type: nauc_recall_at_100_std value: -7.2786 - type: nauc_recall_at_100_diff1 value: 29.0868 - type: nauc_recall_at_1000_max value: 33.858 - type: nauc_recall_at_1000_std value: 42.2189 - type: nauc_recall_at_1000_diff1 value: 18.9862 - type: nauc_precision_at_1_max value: 3.9297 - type: nauc_precision_at_1_std value: -22.016 - type: nauc_precision_at_1_diff1 value: 39.7204 - type: nauc_precision_at_3_max value: 5.1912 - type: nauc_precision_at_3_std value: -29.697000000000003 - type: nauc_precision_at_3_diff1 value: 30.089199999999998 - type: nauc_precision_at_5_max value: 6.311400000000001 - type: nauc_precision_at_5_std value: -32.9724 - type: nauc_precision_at_5_diff1 value: 28.0676 - type: nauc_precision_at_10_max value: 6.869400000000001 - type: nauc_precision_at_10_std value: -32.4788 - type: nauc_precision_at_10_diff1 value: 25.6897 - type: nauc_precision_at_20_max value: 9.206 - type: nauc_precision_at_20_std value: -25.3222 - type: nauc_precision_at_20_diff1 value: 23.799500000000002 - type: nauc_precision_at_100_max value: 13.8625 - type: nauc_precision_at_100_std value: 3.3068 - type: nauc_precision_at_100_diff1 value: 14.3806 - type: nauc_precision_at_1000_max value: 11.8588 - type: nauc_precision_at_1000_std value: 17.6676 - type: nauc_precision_at_1000_diff1 value: -3.8201 - type: nauc_mrr_at_1_max value: 3.9297 - type: nauc_mrr_at_1_std value: -22.016 - type: nauc_mrr_at_1_diff1 value: 39.7204 - type: nauc_mrr_at_3_max value: 4.6479 - type: nauc_mrr_at_3_std value: -25.644699999999997 - type: nauc_mrr_at_3_diff1 value: 35.478 - type: nauc_mrr_at_5_max value: 4.986 - type: nauc_mrr_at_5_std value: -26.4206 - type: nauc_mrr_at_5_diff1 value: 35.285 - type: nauc_mrr_at_10_max value: 5.0845 - type: nauc_mrr_at_10_std value: -26.411800000000003 - type: nauc_mrr_at_10_diff1 value: 35.2365 - type: nauc_mrr_at_20_max value: 5.1531 - type: nauc_mrr_at_20_std value: -26.0735 - type: nauc_mrr_at_20_diff1 value: 35.3495 - type: nauc_mrr_at_100_max value: 5.1672 - type: nauc_mrr_at_100_std value: -25.8254 - type: nauc_mrr_at_100_diff1 value: 35.4396 - type: nauc_mrr_at_1000_max value: 5.1629000000000005 - type: nauc_mrr_at_1000_std value: -25.8233 - type: nauc_mrr_at_1000_diff1 value: 35.4444 - type: main_score value: 44.043 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 92.08619999999999 - type: f1 value: 91.8074 - type: f1_weighted value: 92.0765 - type: main_score value: 92.08619999999999 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 65.2668 - type: f1 value: 44.499 - type: f1_weighted value: 67.9193 - type: main_score value: 65.2668 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 4672e20407010da34463acc759c162ca9734bca6 metrics: - type: accuracy value: 68.0128 - type: f1 value: 64.4011 - type: f1_weighted value: 67.4705 - type: main_score value: 68.0128 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8 metrics: - type: accuracy value: 72.67320000000001 - type: f1 value: 71.7881 - type: f1_weighted value: 72.9092 - type: main_score value: 72.67320000000001 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P (default) type: mteb/medrxiv-clustering-p2p config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 31.5764 - type: v_measure_std value: 1.3743999999999998 - type: main_score value: 31.5764 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S (default) type: mteb/medrxiv-clustering-s2s config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 28.006999999999998 - type: v_measure_std value: 1.4235 - type: main_score value: 28.006999999999998 - task: type: Reranking dataset: name: MTEB MindSmallReranking (default) type: mteb/mind_small config: default split: test revision: 59042f120c80e8afa9cdbb224f67076cec0fc9a7 metrics: - type: map value: 30.3039 - type: mrr value: 31.168699999999998 - type: nAUC_map_max value: -25.113200000000003 - type: nAUC_map_std value: -8.5652 - type: nAUC_map_diff1 value: 12.437199999999999 - type: nAUC_mrr_max value: -19.5255 - type: nAUC_mrr_std value: -6.1112 - type: nAUC_mrr_diff1 value: 12.1585 - type: main_score value: 30.3039 - task: type: Retrieval dataset: name: MTEB NFCorpus (default) type: mteb/nfcorpus config: default split: test revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 metrics: - type: ndcg_at_1 value: 45.046 - type: ndcg_at_3 value: 41.975 - type: ndcg_at_5 value: 39.421 - type: ndcg_at_10 value: 35.879 - type: ndcg_at_20 value: 32.987 - type: ndcg_at_100 value: 32.107 - type: ndcg_at_1000 value: 40.67 - type: map_at_1 value: 5.854 - type: map_at_3 value: 9.991999999999999 - type: map_at_5 value: 11.405999999999999 - type: map_at_10 value: 13.272 - type: map_at_20 value: 14.604000000000001 - type: map_at_100 value: 16.521 - type: map_at_1000 value: 17.925 - type: recall_at_1 value: 5.854 - type: recall_at_3 value: 11.036999999999999 - type: recall_at_5 value: 13.391 - type: recall_at_10 value: 16.841 - type: recall_at_20 value: 20.522000000000002 - type: recall_at_100 value: 31.733 - type: recall_at_1000 value: 63.525 - type: precision_at_1 value: 46.749 - type: precision_at_3 value: 39.525 - type: precision_at_5 value: 34.056 - type: precision_at_10 value: 26.656000000000002 - type: precision_at_20 value: 19.211 - type: precision_at_100 value: 8.099 - type: precision_at_1000 value: 2.061 - type: mrr_at_1 value: 47.0588 - type: mrr_at_3 value: 53.9732 - type: mrr_at_5 value: 55.443799999999996 - type: mrr_at_10 value: 56.04599999999999 - type: mrr_at_20 value: 56.37799999999999 - type: mrr_at_100 value: 56.6504 - type: mrr_at_1000 value: 56.6866 - type: nauc_ndcg_at_1_max value: 43.5884 - type: nauc_ndcg_at_1_std value: 22.4376 - type: nauc_ndcg_at_1_diff1 value: 34.7846 - type: nauc_ndcg_at_3_max value: 44.7961 - type: nauc_ndcg_at_3_std value: 24.4811 - type: nauc_ndcg_at_3_diff1 value: 25.5747 - type: nauc_ndcg_at_5_max value: 43.5994 - type: nauc_ndcg_at_5_std value: 24.827199999999998 - type: nauc_ndcg_at_5_diff1 value: 23.8874 - type: nauc_ndcg_at_10_max value: 43.126999999999995 - type: nauc_ndcg_at_10_std value: 27.5053 - type: nauc_ndcg_at_10_diff1 value: 23.4832 - type: nauc_ndcg_at_20_max value: 43.1243 - type: nauc_ndcg_at_20_std value: 27.3455 - type: nauc_ndcg_at_20_diff1 value: 23.8534 - type: nauc_ndcg_at_100_max value: 46.5936 - type: nauc_ndcg_at_100_std value: 28.0084 - type: nauc_ndcg_at_100_diff1 value: 29.630200000000002 - type: nauc_ndcg_at_1000_max value: 51.7379 - type: nauc_ndcg_at_1000_std value: 33.2077 - type: nauc_ndcg_at_1000_diff1 value: 30.1522 - type: nauc_map_at_1_max value: 17.2703 - type: nauc_map_at_1_std value: -14.6241 - type: nauc_map_at_1_diff1 value: 46.9767 - type: nauc_map_at_3_max value: 25.562600000000003 - type: nauc_map_at_3_std value: -10.1565 - type: nauc_map_at_3_diff1 value: 39.347500000000004 - type: nauc_map_at_5_max value: 28.397299999999998 - type: nauc_map_at_5_std value: -7.0083 - type: nauc_map_at_5_diff1 value: 37.4216 - type: nauc_map_at_10_max value: 31.639400000000002 - type: nauc_map_at_10_std value: -1.9 - type: nauc_map_at_10_diff1 value: 35.9293 - type: nauc_map_at_20_max value: 34.342800000000004 - type: nauc_map_at_20_std value: 2.6614 - type: nauc_map_at_20_diff1 value: 34.7985 - type: nauc_map_at_100_max value: 37.046600000000005 - type: nauc_map_at_100_std value: 9.2072 - type: nauc_map_at_100_diff1 value: 33.2764 - type: nauc_map_at_1000_max value: 37.6597 - type: nauc_map_at_1000_std value: 12.6768 - type: nauc_map_at_1000_diff1 value: 31.773699999999998 - type: nauc_recall_at_1_max value: 17.2703 - type: nauc_recall_at_1_std value: -14.6241 - type: nauc_recall_at_1_diff1 value: 46.9767 - type: nauc_recall_at_3_max value: 24.5473 - type: nauc_recall_at_3_std value: -9.7412 - type: nauc_recall_at_3_diff1 value: 37.8539 - type: nauc_recall_at_5_max value: 27.249200000000002 - type: nauc_recall_at_5_std value: -5.823799999999999 - type: nauc_recall_at_5_diff1 value: 34.06 - type: nauc_recall_at_10_max value: 29.1217 - type: nauc_recall_at_10_std value: -0.21159999999999998 - type: nauc_recall_at_10_diff1 value: 32.3914 - type: nauc_recall_at_20_max value: 31.142999999999997 - type: nauc_recall_at_20_std value: 4.3805 - type: nauc_recall_at_20_diff1 value: 28.852899999999998 - type: nauc_recall_at_100_max value: 32.8751 - type: nauc_recall_at_100_std value: 16.0658 - type: nauc_recall_at_100_diff1 value: 24.8181 - type: nauc_recall_at_1000_max value: 24.5638 - type: nauc_recall_at_1000_std value: 20.822 - type: nauc_recall_at_1000_diff1 value: 13.123099999999999 - type: nauc_precision_at_1_max value: 44.714999999999996 - type: nauc_precision_at_1_std value: 23.2541 - type: nauc_precision_at_1_diff1 value: 33.9092 - type: nauc_precision_at_3_max value: 44.935199999999995 - type: nauc_precision_at_3_std value: 29.0989 - type: nauc_precision_at_3_diff1 value: 14.9816 - type: nauc_precision_at_5_max value: 40.7582 - type: nauc_precision_at_5_std value: 31.049 - type: nauc_precision_at_5_diff1 value: 9.7826 - type: nauc_precision_at_10_max value: 37.8974 - type: nauc_precision_at_10_std value: 38.9576 - type: nauc_precision_at_10_diff1 value: 4.3217 - type: nauc_precision_at_20_max value: 33.254099999999994 - type: nauc_precision_at_20_std value: 42.3527 - type: nauc_precision_at_20_diff1 value: -1.8002 - type: nauc_precision_at_100_max value: 20.6042 - type: nauc_precision_at_100_std value: 46.0314 - type: nauc_precision_at_100_diff1 value: -10.098 - type: nauc_precision_at_1000_max value: 6.8368 - type: nauc_precision_at_1000_std value: 36.4345 - type: nauc_precision_at_1000_diff1 value: -16.1738 - type: nauc_mrr_at_1_max value: 44.1317 - type: nauc_mrr_at_1_std value: 22.794900000000002 - type: nauc_mrr_at_1_diff1 value: 33.071600000000004 - type: nauc_mrr_at_3_max value: 49.8647 - type: nauc_mrr_at_3_std value: 28.821600000000004 - type: nauc_mrr_at_3_diff1 value: 31.1845 - type: nauc_mrr_at_5_max value: 50.3448 - type: nauc_mrr_at_5_std value: 28.721799999999998 - type: nauc_mrr_at_5_diff1 value: 31.6681 - type: nauc_mrr_at_10_max value: 50.601 - type: nauc_mrr_at_10_std value: 29.461199999999998 - type: nauc_mrr_at_10_diff1 value: 31.5519 - type: nauc_mrr_at_20_max value: 50.7861 - type: nauc_mrr_at_20_std value: 29.615000000000002 - type: nauc_mrr_at_20_diff1 value: 31.535200000000003 - type: nauc_mrr_at_100_max value: 50.7764 - type: nauc_mrr_at_100_std value: 29.772199999999998 - type: nauc_mrr_at_100_diff1 value: 31.5569 - type: nauc_mrr_at_1000_max value: 50.75150000000001 - type: nauc_mrr_at_1000_std value: 29.747600000000002 - type: nauc_mrr_at_1000_diff1 value: 31.5457 - type: main_score value: 35.879 - task: type: Retrieval dataset: name: MTEB NQ (default) type: mteb/nq config: default split: test revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 metrics: - type: ndcg_at_1 value: 45.394 - type: ndcg_at_3 value: 57.17 - type: ndcg_at_5 value: 61.402 - type: ndcg_at_10 value: 64.59899999999999 - type: ndcg_at_20 value: 66.24600000000001 - type: ndcg_at_100 value: 67.522 - type: ndcg_at_1000 value: 67.849 - type: map_at_1 value: 40.6 - type: map_at_3 value: 53.055 - type: map_at_5 value: 55.67100000000001 - type: map_at_10 value: 57.160999999999994 - type: map_at_20 value: 57.701 - type: map_at_100 value: 57.926 - type: map_at_1000 value: 57.940999999999995 - type: recall_at_1 value: 40.6 - type: recall_at_3 value: 65.766 - type: recall_at_5 value: 75.466 - type: recall_at_10 value: 84.654 - type: recall_at_20 value: 90.60000000000001 - type: recall_at_100 value: 96.854 - type: recall_at_1000 value: 99.232 - type: precision_at_1 value: 45.394 - type: precision_at_3 value: 25.521 - type: precision_at_5 value: 17.781 - type: precision_at_10 value: 10.098 - type: precision_at_20 value: 5.4559999999999995 - type: precision_at_100 value: 1.176 - type: precision_at_1000 value: 0.121 - type: mrr_at_1 value: 45.394 - type: mrr_at_3 value: 56.3104 - type: mrr_at_5 value: 58.36130000000001 - type: mrr_at_10 value: 59.5005 - type: mrr_at_20 value: 59.866299999999995 - type: mrr_at_100 value: 59.9998 - type: mrr_at_1000 value: 60.0097 - type: nauc_ndcg_at_1_max value: 26.4568 - type: nauc_ndcg_at_1_std value: -5.4489 - type: nauc_ndcg_at_1_diff1 value: 39.8496 - type: nauc_ndcg_at_3_max value: 31.1415 - type: nauc_ndcg_at_3_std value: -7.0855 - type: nauc_ndcg_at_3_diff1 value: 36.4212 - type: nauc_ndcg_at_5_max value: 32.819199999999995 - type: nauc_ndcg_at_5_std value: -5.775 - type: nauc_ndcg_at_5_diff1 value: 35.7043 - type: nauc_ndcg_at_10_max value: 33.0741 - type: nauc_ndcg_at_10_std value: -4.5213 - type: nauc_ndcg_at_10_diff1 value: 36.19 - type: nauc_ndcg_at_20_max value: 33.266400000000004 - type: nauc_ndcg_at_20_std value: -3.5874 - type: nauc_ndcg_at_20_diff1 value: 36.2496 - type: nauc_ndcg_at_100_max value: 32.7922 - type: nauc_ndcg_at_100_std value: -3.2738000000000005 - type: nauc_ndcg_at_100_diff1 value: 36.5649 - type: nauc_ndcg_at_1000_max value: 32.237500000000004 - type: nauc_ndcg_at_1000_std value: -3.9578 - type: nauc_ndcg_at_1000_diff1 value: 36.717499999999994 - type: nauc_map_at_1_max value: 24.3328 - type: nauc_map_at_1_std value: -7.889799999999999 - type: nauc_map_at_1_diff1 value: 40.0251 - type: nauc_map_at_3_max value: 29.6774 - type: nauc_map_at_3_std value: -7.5739 - type: nauc_map_at_3_diff1 value: 37.459900000000005 - type: nauc_map_at_5_max value: 30.6947 - type: nauc_map_at_5_std value: -6.7940000000000005 - type: nauc_map_at_5_diff1 value: 37.0909 - type: nauc_map_at_10_max value: 30.723899999999997 - type: nauc_map_at_10_std value: -6.2581999999999995 - type: nauc_map_at_10_diff1 value: 37.1775 - type: nauc_map_at_20_max value: 30.7861 - type: nauc_map_at_20_std value: -5.9957 - type: nauc_map_at_20_diff1 value: 37.209900000000005 - type: nauc_map_at_100_max value: 30.7336 - type: nauc_map_at_100_std value: -5.909 - type: nauc_map_at_100_diff1 value: 37.2446 - type: nauc_map_at_1000_max value: 30.7142 - type: nauc_map_at_1000_std value: -5.9306 - type: nauc_map_at_1000_diff1 value: 37.25 - type: nauc_recall_at_1_max value: 24.3328 - type: nauc_recall_at_1_std value: -7.889799999999999 - type: nauc_recall_at_1_diff1 value: 40.0251 - type: nauc_recall_at_3_max value: 34.2412 - type: nauc_recall_at_3_std value: -7.5245999999999995 - type: nauc_recall_at_3_diff1 value: 32.7498 - type: nauc_recall_at_5_max value: 39.6798 - type: nauc_recall_at_5_std value: -4.1992 - type: nauc_recall_at_5_diff1 value: 29.5385 - type: nauc_recall_at_10_max value: 44.5052 - type: nauc_recall_at_10_std value: 2.4045 - type: nauc_recall_at_10_diff1 value: 30.051499999999997 - type: nauc_recall_at_20_max value: 52.8161 - type: nauc_recall_at_20_std value: 14.1647 - type: nauc_recall_at_20_diff1 value: 27.7847 - type: nauc_recall_at_100_max value: 74.644 - type: nauc_recall_at_100_std value: 54.927099999999996 - type: nauc_recall_at_100_diff1 value: 27.507900000000003 - type: nauc_recall_at_1000_max value: 85.1144 - type: nauc_recall_at_1000_std value: 80.0515 - type: nauc_recall_at_1000_diff1 value: 37.028299999999994 - type: nauc_precision_at_1_max value: 26.4568 - type: nauc_precision_at_1_std value: -5.4489 - type: nauc_precision_at_1_diff1 value: 39.8496 - type: nauc_precision_at_3_max value: 30.0271 - type: nauc_precision_at_3_std value: -0.8751 - type: nauc_precision_at_3_diff1 value: 21.8662 - type: nauc_precision_at_5_max value: 28.4063 - type: nauc_precision_at_5_std value: 4.1253 - type: nauc_precision_at_5_diff1 value: 13.1855 - type: nauc_precision_at_10_max value: 22.6524 - type: nauc_precision_at_10_std value: 10.340399999999999 - type: nauc_precision_at_10_diff1 value: 5.4243 - type: nauc_precision_at_20_max value: 18.4481 - type: nauc_precision_at_20_std value: 16.0409 - type: nauc_precision_at_20_diff1 value: -0.9561 - type: nauc_precision_at_100_max value: 9.361600000000001 - type: nauc_precision_at_100_std value: 19.1145 - type: nauc_precision_at_100_diff1 value: -8.0049 - type: nauc_precision_at_1000_max value: 3.0707 - type: nauc_precision_at_1000_std value: 15.259900000000002 - type: nauc_precision_at_1000_diff1 value: -10.190000000000001 - type: nauc_mrr_at_1_max value: 26.4568 - type: nauc_mrr_at_1_std value: -5.4489 - type: nauc_mrr_at_1_diff1 value: 39.8496 - type: nauc_mrr_at_3_max value: 30.262299999999996 - type: nauc_mrr_at_3_std value: -5.428100000000001 - type: nauc_mrr_at_3_diff1 value: 36.878899999999994 - type: nauc_mrr_at_5_max value: 30.813000000000002 - type: nauc_mrr_at_5_std value: -4.7534 - type: nauc_mrr_at_5_diff1 value: 36.5968 - type: nauc_mrr_at_10_max value: 30.857499999999998 - type: nauc_mrr_at_10_std value: -4.4249 - type: nauc_mrr_at_10_diff1 value: 36.973 - type: nauc_mrr_at_20_max value: 30.8228 - type: nauc_mrr_at_20_std value: -4.3275 - type: nauc_mrr_at_20_diff1 value: 37.0266 - type: nauc_mrr_at_100_max value: 30.7442 - type: nauc_mrr_at_100_std value: -4.3408 - type: nauc_mrr_at_100_diff1 value: 37.060500000000005 - type: nauc_mrr_at_1000_max value: 30.7286 - type: nauc_mrr_at_1000_std value: -4.36 - type: nauc_mrr_at_1000_diff1 value: 37.0647 - type: main_score value: 64.59899999999999 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval (default) type: mteb/quora config: default split: test revision: e4e08e0b7dbe3c8700f0daef558ff32256715259 metrics: - type: ndcg_at_1 value: 82.01 - type: ndcg_at_3 value: 86.035 - type: ndcg_at_5 value: 87.628 - type: ndcg_at_10 value: 88.735 - type: ndcg_at_20 value: 89.375 - type: ndcg_at_100 value: 89.89 - type: ndcg_at_1000 value: 90.001 - type: map_at_1 value: 71.126 - type: map_at_3 value: 82.14399999999999 - type: map_at_5 value: 84.03500000000001 - type: map_at_10 value: 85.064 - type: map_at_20 value: 85.469 - type: map_at_100 value: 85.673 - type: map_at_1000 value: 85.69099999999999 - type: recall_at_1 value: 71.126 - type: recall_at_3 value: 87.76 - type: recall_at_5 value: 92.286 - type: recall_at_10 value: 95.56 - type: recall_at_20 value: 97.655 - type: recall_at_100 value: 99.497 - type: recall_at_1000 value: 99.979 - type: precision_at_1 value: 82.01 - type: precision_at_3 value: 37.653 - type: precision_at_5 value: 24.779999999999998 - type: precision_at_10 value: 13.441 - type: precision_at_20 value: 7.114 - type: precision_at_100 value: 1.524 - type: precision_at_1000 value: 0.157 - type: mrr_at_1 value: 81.96 - type: mrr_at_3 value: 87.105 - type: mrr_at_5 value: 87.779 - type: mrr_at_10 value: 88.02680000000001 - type: mrr_at_20 value: 88.10470000000001 - type: mrr_at_100 value: 88.126 - type: mrr_at_1000 value: 88.127 - type: nauc_ndcg_at_1_max value: 37.866499999999995 - type: nauc_ndcg_at_1_std value: -40.9317 - type: nauc_ndcg_at_1_diff1 value: 78.09089999999999 - type: nauc_ndcg_at_3_max value: 35.4917 - type: nauc_ndcg_at_3_std value: -48.968 - type: nauc_ndcg_at_3_diff1 value: 75.90050000000001 - type: nauc_ndcg_at_5_max value: 35.898799999999994 - type: nauc_ndcg_at_5_std value: -50.5572 - type: nauc_ndcg_at_5_diff1 value: 76.6471 - type: nauc_ndcg_at_10_max value: 36.7786 - type: nauc_ndcg_at_10_std value: -49.6733 - type: nauc_ndcg_at_10_diff1 value: 76.8147 - type: nauc_ndcg_at_20_max value: 37.1374 - type: nauc_ndcg_at_20_std value: -47.9144 - type: nauc_ndcg_at_20_diff1 value: 76.6412 - type: nauc_ndcg_at_100_max value: 37.3452 - type: nauc_ndcg_at_100_std value: -46.0007 - type: nauc_ndcg_at_100_diff1 value: 76.6194 - type: nauc_ndcg_at_1000_max value: 37.4848 - type: nauc_ndcg_at_1000_std value: -45.6578 - type: nauc_ndcg_at_1000_diff1 value: 76.6001 - type: nauc_map_at_1_max value: 26.7109 - type: nauc_map_at_1_std value: -42.9943 - type: nauc_map_at_1_diff1 value: 80.5567 - type: nauc_map_at_3_max value: 32.8491 - type: nauc_map_at_3_std value: -51.64 - type: nauc_map_at_3_diff1 value: 77.29700000000001 - type: nauc_map_at_5_max value: 34.4071 - type: nauc_map_at_5_std value: -51.6503 - type: nauc_map_at_5_diff1 value: 77.28920000000001 - type: nauc_map_at_10_max value: 35.4934 - type: nauc_map_at_10_std value: -50.0995 - type: nauc_map_at_10_diff1 value: 76.9983 - type: nauc_map_at_20_max value: 35.8087 - type: nauc_map_at_20_std value: -48.8069 - type: nauc_map_at_20_diff1 value: 76.8026 - type: nauc_map_at_100_max value: 35.8928 - type: nauc_map_at_100_std value: -48.0561 - type: nauc_map_at_100_diff1 value: 76.7244 - type: nauc_map_at_1000_max value: 35.924499999999995 - type: nauc_map_at_1000_std value: -47.981899999999996 - type: nauc_map_at_1000_diff1 value: 76.7183 - type: nauc_recall_at_1_max value: 26.7109 - type: nauc_recall_at_1_std value: -42.9943 - type: nauc_recall_at_1_diff1 value: 80.5567 - type: nauc_recall_at_3_max value: 29.066300000000002 - type: nauc_recall_at_3_std value: -60.1536 - type: nauc_recall_at_3_diff1 value: 73.32469999999999 - type: nauc_recall_at_5_max value: 30.1025 - type: nauc_recall_at_5_std value: -67.8779 - type: nauc_recall_at_5_diff1 value: 73.13340000000001 - type: nauc_recall_at_10_max value: 33.771699999999996 - type: nauc_recall_at_10_std value: -72.4753 - type: nauc_recall_at_10_diff1 value: 74.168 - type: nauc_recall_at_20_max value: 34.8005 - type: nauc_recall_at_20_std value: -68.60579999999999 - type: nauc_recall_at_20_diff1 value: 72.6083 - type: nauc_recall_at_100_max value: 33.394800000000004 - type: nauc_recall_at_100_std value: -49.7417 - type: nauc_recall_at_100_diff1 value: 73.5857 - type: nauc_recall_at_1000_max value: 48.8898 - type: nauc_recall_at_1000_std value: 54.583800000000004 - type: nauc_recall_at_1000_diff1 value: 64.0609 - type: nauc_precision_at_1_max value: 37.866499999999995 - type: nauc_precision_at_1_std value: -40.9317 - type: nauc_precision_at_1_diff1 value: 78.09089999999999 - type: nauc_precision_at_3_max value: 8.2308 - type: nauc_precision_at_3_std value: 5.0732 - type: nauc_precision_at_3_diff1 value: -19.919 - type: nauc_precision_at_5_max value: 3.0249 - type: nauc_precision_at_5_std value: 16.7897 - type: nauc_precision_at_5_diff1 value: -32.0086 - type: nauc_precision_at_10_max value: -0.5459999999999999 - type: nauc_precision_at_10_std value: 27.1262 - type: nauc_precision_at_10_diff1 value: -38.8076 - type: nauc_precision_at_20_max value: -2.7663 - type: nauc_precision_at_20_std value: 34.1696 - type: nauc_precision_at_20_diff1 value: -42.1088 - type: nauc_precision_at_100_max value: -5.0689 - type: nauc_precision_at_100_std value: 40.023599999999995 - type: nauc_precision_at_100_diff1 value: -43.8996 - type: nauc_precision_at_1000_max value: -5.1495 - type: nauc_precision_at_1000_std value: 41.4194 - type: nauc_precision_at_1000_diff1 value: -44.219 - type: nauc_mrr_at_1_max value: 37.7695 - type: nauc_mrr_at_1_std value: -41.0563 - type: nauc_mrr_at_1_diff1 value: 78.1854 - type: nauc_mrr_at_3_max value: 38.3824 - type: nauc_mrr_at_3_std value: -43.7797 - type: nauc_mrr_at_3_diff1 value: 77.0796 - type: nauc_mrr_at_5_max value: 38.5156 - type: nauc_mrr_at_5_std value: -43.8092 - type: nauc_mrr_at_5_diff1 value: 77.31710000000001 - type: nauc_mrr_at_10_max value: 38.523 - type: nauc_mrr_at_10_std value: -43.5039 - type: nauc_mrr_at_10_diff1 value: 77.375 - type: nauc_mrr_at_20_max value: 38.4635 - type: nauc_mrr_at_20_std value: -43.3619 - type: nauc_mrr_at_20_diff1 value: 77.3565 - type: nauc_mrr_at_100_max value: 38.4502 - type: nauc_mrr_at_100_std value: -43.3315 - type: nauc_mrr_at_100_diff1 value: 77.3584 - type: nauc_mrr_at_1000_max value: 38.449 - type: nauc_mrr_at_1000_std value: -43.3339 - type: nauc_mrr_at_1000_diff1 value: 77.3584 - type: main_score value: 88.735 - task: type: Clustering dataset: name: MTEB RedditClustering (default) type: mteb/reddit-clustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 49.1271 - type: v_measure_std value: 4.5517 - type: main_score value: 49.1271 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P (default) type: mteb/reddit-clustering-p2p config: default split: test revision: 385e3cb46b4cfa89021f56c4380204149d0efe33 metrics: - type: v_measure value: 61.0626 - type: v_measure_std value: 12.6364 - type: main_score value: 61.0626 - task: type: Retrieval dataset: name: MTEB SCIDOCS (default) type: mteb/scidocs config: default split: test revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88 metrics: - type: ndcg_at_1 value: 23.7 - type: ndcg_at_3 value: 19.346 - type: ndcg_at_5 value: 17.044999999999998 - type: ndcg_at_10 value: 20.347 - type: ndcg_at_20 value: 23.237 - type: ndcg_at_100 value: 27.923 - type: ndcg_at_1000 value: 32.891999999999996 - type: map_at_1 value: 4.813 - type: map_at_3 value: 8.688 - type: map_at_5 value: 10.41 - type: map_at_10 value: 12.107999999999999 - type: map_at_20 value: 13.187 - type: map_at_100 value: 14.113000000000001 - type: map_at_1000 value: 14.383000000000001 - type: recall_at_1 value: 4.813 - type: recall_at_3 value: 11.022 - type: recall_at_5 value: 15.242 - type: recall_at_10 value: 21.308 - type: recall_at_20 value: 28.1 - type: recall_at_100 value: 43.335 - type: recall_at_1000 value: 67.672 - type: precision_at_1 value: 23.7 - type: precision_at_3 value: 18.099999999999998 - type: precision_at_5 value: 15 - type: precision_at_10 value: 10.48 - type: precision_at_20 value: 6.909999999999999 - type: precision_at_100 value: 2.133 - type: precision_at_1000 value: 0.333 - type: mrr_at_1 value: 23.7 - type: mrr_at_3 value: 31.35 - type: mrr_at_5 value: 33.650000000000006 - type: mrr_at_10 value: 34.9399 - type: mrr_at_20 value: 35.5429 - type: mrr_at_100 value: 35.9342 - type: mrr_at_1000 value: 35.9943 - type: nauc_ndcg_at_1_max value: 20.214499999999997 - type: nauc_ndcg_at_1_std value: 7.2459999999999996 - type: nauc_ndcg_at_1_diff1 value: 26.8353 - type: nauc_ndcg_at_3_max value: 23.3459 - type: nauc_ndcg_at_3_std value: 10.9732 - type: nauc_ndcg_at_3_diff1 value: 21.0618 - type: nauc_ndcg_at_5_max value: 24.5147 - type: nauc_ndcg_at_5_std value: 13.309000000000001 - type: nauc_ndcg_at_5_diff1 value: 20.0975 - type: nauc_ndcg_at_10_max value: 27.0937 - type: nauc_ndcg_at_10_std value: 16.4516 - type: nauc_ndcg_at_10_diff1 value: 19.9585 - type: nauc_ndcg_at_20_max value: 28.503600000000002 - type: nauc_ndcg_at_20_std value: 19.1956 - type: nauc_ndcg_at_20_diff1 value: 19.508200000000002 - type: nauc_ndcg_at_100_max value: 30.7317 - type: nauc_ndcg_at_100_std value: 23.2169 - type: nauc_ndcg_at_100_diff1 value: 19.7085 - type: nauc_ndcg_at_1000_max value: 30.3307 - type: nauc_ndcg_at_1000_std value: 24.7664 - type: nauc_ndcg_at_1000_diff1 value: 19.0469 - type: nauc_map_at_1_max value: 20.3702 - type: nauc_map_at_1_std value: 7.219200000000001 - type: nauc_map_at_1_diff1 value: 27.0193 - type: nauc_map_at_3_max value: 23.0558 - type: nauc_map_at_3_std value: 9.411999999999999 - type: nauc_map_at_3_diff1 value: 21.3691 - type: nauc_map_at_5_max value: 23.763 - type: nauc_map_at_5_std value: 11.228 - type: nauc_map_at_5_diff1 value: 20.4299 - type: nauc_map_at_10_max value: 25.6655 - type: nauc_map_at_10_std value: 14.0481 - type: nauc_map_at_10_diff1 value: 19.7937 - type: nauc_map_at_20_max value: 26.5994 - type: nauc_map_at_20_std value: 15.820400000000001 - type: nauc_map_at_20_diff1 value: 19.476499999999998 - type: nauc_map_at_100_max value: 27.4895 - type: nauc_map_at_100_std value: 17.262 - type: nauc_map_at_100_diff1 value: 19.4661 - type: nauc_map_at_1000_max value: 27.5301 - type: nauc_map_at_1000_std value: 17.4927 - type: nauc_map_at_1000_diff1 value: 19.4691 - type: nauc_recall_at_1_max value: 20.3702 - type: nauc_recall_at_1_std value: 7.219200000000001 - type: nauc_recall_at_1_diff1 value: 27.0193 - type: nauc_recall_at_3_max value: 23.6476 - type: nauc_recall_at_3_std value: 11.9176 - type: nauc_recall_at_3_diff1 value: 18.1657 - type: nauc_recall_at_5_max value: 24.8053 - type: nauc_recall_at_5_std value: 15.5205 - type: nauc_recall_at_5_diff1 value: 16.4924 - type: nauc_recall_at_10_max value: 27.9864 - type: nauc_recall_at_10_std value: 20.1496 - type: nauc_recall_at_10_diff1 value: 16.0154 - type: nauc_recall_at_20_max value: 29.0157 - type: nauc_recall_at_20_std value: 24.374100000000002 - type: nauc_recall_at_20_diff1 value: 14.174800000000001 - type: nauc_recall_at_100_max value: 31.245299999999997 - type: nauc_recall_at_100_std value: 32.161699999999996 - type: nauc_recall_at_100_diff1 value: 12.9714 - type: nauc_recall_at_1000_max value: 25.6486 - type: nauc_recall_at_1000_std value: 37.1526 - type: nauc_recall_at_1000_diff1 value: 6.0907 - type: nauc_precision_at_1_max value: 20.214499999999997 - type: nauc_precision_at_1_std value: 7.2459999999999996 - type: nauc_precision_at_1_diff1 value: 26.8353 - type: nauc_precision_at_3_max value: 23.8245 - type: nauc_precision_at_3_std value: 12.2589 - type: nauc_precision_at_3_diff1 value: 18.192800000000002 - type: nauc_precision_at_5_max value: 25.3681 - type: nauc_precision_at_5_std value: 15.947700000000001 - type: nauc_precision_at_5_diff1 value: 16.6931 - type: nauc_precision_at_10_max value: 28.2682 - type: nauc_precision_at_10_std value: 20.2673 - type: nauc_precision_at_10_diff1 value: 15.8977 - type: nauc_precision_at_20_max value: 29.3989 - type: nauc_precision_at_20_std value: 24.5769 - type: nauc_precision_at_20_diff1 value: 14.1994 - type: nauc_precision_at_100_max value: 31.418000000000003 - type: nauc_precision_at_100_std value: 32.0978 - type: nauc_precision_at_100_diff1 value: 12.768199999999998 - type: nauc_precision_at_1000_max value: 25.501099999999997 - type: nauc_precision_at_1000_std value: 36.477399999999996 - type: nauc_precision_at_1000_diff1 value: 5.5335 - type: nauc_mrr_at_1_max value: 20.214499999999997 - type: nauc_mrr_at_1_std value: 7.2459999999999996 - type: nauc_mrr_at_1_diff1 value: 26.8353 - type: nauc_mrr_at_3_max value: 22.7925 - type: nauc_mrr_at_3_std value: 10.6945 - type: nauc_mrr_at_3_diff1 value: 23.6308 - type: nauc_mrr_at_5_max value: 23.427799999999998 - type: nauc_mrr_at_5_std value: 11.8634 - type: nauc_mrr_at_5_diff1 value: 23.0875 - type: nauc_mrr_at_10_max value: 24.0918 - type: nauc_mrr_at_10_std value: 12.4753 - type: nauc_mrr_at_10_diff1 value: 23.352999999999998 - type: nauc_mrr_at_20_max value: 24.078 - type: nauc_mrr_at_20_std value: 12.5849 - type: nauc_mrr_at_20_diff1 value: 23.3351 - type: nauc_mrr_at_100_max value: 24.0858 - type: nauc_mrr_at_100_std value: 12.5772 - type: nauc_mrr_at_100_diff1 value: 23.4778 - type: nauc_mrr_at_1000_max value: 24.058799999999998 - type: nauc_mrr_at_1000_std value: 12.549 - type: nauc_mrr_at_1000_diff1 value: 23.4713 - type: main_score value: 20.347 - task: type: STS dataset: name: MTEB SICK-R (default) type: mteb/sickr-sts config: default split: test revision: 20a6d6f312dd54037fe07a32d58e5e168867909d metrics: - type: pearson value: 75.7747 - type: spearman value: 71.3142 - type: cosine_pearson value: 75.7747 - type: cosine_spearman value: 71.3142 - type: manhattan_pearson value: 73.8759 - type: manhattan_spearman value: 71.1003 - type: euclidean_pearson value: 74.088 - type: euclidean_spearman value: 71.3142 - type: main_score value: 71.3142 - task: type: STS dataset: name: MTEB STS12 (default) type: mteb/sts12-sts config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: pearson value: 72.5903 - type: spearman value: 70.6581 - type: cosine_pearson value: 72.5903 - type: cosine_spearman value: 70.6581 - type: manhattan_pearson value: 69.2077 - type: manhattan_spearman value: 70.4521 - type: euclidean_pearson value: 69.41720000000001 - type: euclidean_spearman value: 70.6581 - type: main_score value: 70.6581 - task: type: STS dataset: name: MTEB STS13 (default) type: mteb/sts13-sts config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: pearson value: 73.1686 - type: spearman value: 77.4225 - type: cosine_pearson value: 73.1686 - type: cosine_spearman value: 77.4225 - type: manhattan_pearson value: 76.2481 - type: manhattan_spearman value: 77.325 - type: euclidean_pearson value: 76.3568 - type: euclidean_spearman value: 77.4225 - type: main_score value: 77.4225 - task: type: STS dataset: name: MTEB STS14 (default) type: mteb/sts14-sts config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: pearson value: 74.46340000000001 - type: spearman value: 72.9162 - type: cosine_pearson value: 74.46340000000001 - type: cosine_spearman value: 72.9162 - type: manhattan_pearson value: 73.8079 - type: manhattan_spearman value: 72.8704 - type: euclidean_pearson value: 73.8244 - type: euclidean_spearman value: 72.9162 - type: main_score value: 72.9162 - task: type: STS dataset: name: MTEB STS15 (default) type: mteb/sts15-sts config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: pearson value: 80.1161 - type: spearman value: 81.83200000000001 - type: cosine_pearson value: 80.1161 - type: cosine_spearman value: 81.83200000000001 - type: manhattan_pearson value: 81.573 - type: manhattan_spearman value: 81.807 - type: euclidean_pearson value: 81.59490000000001 - type: euclidean_spearman value: 81.83200000000001 - type: main_score value: 81.83200000000001 - task: type: STS dataset: name: MTEB STS16 (default) type: mteb/sts16-sts config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: pearson value: 78.8244 - type: spearman value: 81.2262 - type: cosine_pearson value: 78.8244 - type: cosine_spearman value: 81.2262 - type: manhattan_pearson value: 80.6177 - type: manhattan_spearman value: 81.1361 - type: euclidean_pearson value: 80.7347 - type: euclidean_spearman value: 81.2262 - type: main_score value: 81.2262 - task: type: STS dataset: name: MTEB STS17 (es-en) type: mteb/sts17-crosslingual-sts config: es-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: pearson value: 67.9751 - type: spearman value: 68.92099999999999 - type: cosine_pearson value: 67.9751 - type: cosine_spearman value: 68.92099999999999 - type: manhattan_pearson value: 68.9355 - type: manhattan_spearman value: 68.777 - type: euclidean_pearson value: 69.11410000000001 - type: euclidean_spearman value: 68.92099999999999 - type: main_score value: 68.92099999999999 - task: type: STS dataset: name: MTEB STS17 (fr-en) type: mteb/sts17-crosslingual-sts config: fr-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: pearson value: 72.08449999999999 - type: spearman value: 74.6931 - type: cosine_pearson value: 72.08449999999999 - type: cosine_spearman value: 74.6931 - type: manhattan_pearson value: 73.52 - type: manhattan_spearman value: 74.7097 - type: euclidean_pearson value: 73.62180000000001 - type: euclidean_spearman value: 74.6931 - type: main_score value: 74.6931 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: pearson value: 80.528 - type: spearman value: 84.10459999999999 - type: cosine_pearson value: 80.528 - type: cosine_spearman value: 84.10459999999999 - type: manhattan_pearson value: 83.1537 - type: manhattan_spearman value: 84.0952 - type: euclidean_pearson value: 83.337 - type: euclidean_spearman value: 84.10459999999999 - type: main_score value: 84.10459999999999 - task: type: STS dataset: name: MTEB STS17 (en-tr) type: mteb/sts17-crosslingual-sts config: en-tr split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: pearson value: 49.641400000000004 - type: spearman value: 48.9413 - type: cosine_pearson value: 49.641400000000004 - type: cosine_spearman value: 48.9413 - type: manhattan_pearson value: 51.434000000000005 - type: manhattan_spearman value: 49.1595 - type: euclidean_pearson value: 50.867799999999995 - type: euclidean_spearman value: 48.9413 - type: main_score value: 48.9413 - task: type: STS dataset: name: MTEB STS17 (it-en) type: mteb/sts17-crosslingual-sts config: it-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: pearson value: 71.2577 - type: spearman value: 73.82419999999999 - type: cosine_pearson value: 71.2577 - type: cosine_spearman value: 73.82419999999999 - type: manhattan_pearson value: 71.9329 - type: manhattan_spearman value: 73.4651 - type: euclidean_pearson value: 72.2771 - type: euclidean_spearman value: 73.82419999999999 - type: main_score value: 73.82419999999999 - task: type: STS dataset: name: MTEB STS17 (nl-en) type: mteb/sts17-crosslingual-sts config: nl-en split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: pearson value: 64.1562 - type: spearman value: 64.8766 - type: cosine_pearson value: 64.1562 - type: cosine_spearman value: 64.8766 - type: manhattan_pearson value: 64.16579999999999 - type: manhattan_spearman value: 64.1931 - type: euclidean_pearson value: 64.6169 - type: euclidean_spearman value: 64.8766 - type: main_score value: 64.8766 - task: type: STS dataset: name: MTEB STS17 (en-ar) type: mteb/sts17-crosslingual-sts config: en-ar split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: pearson value: 42.257400000000004 - type: spearman value: 43.2176 - type: cosine_pearson value: 42.257400000000004 - type: cosine_spearman value: 43.2176 - type: manhattan_pearson value: 43.5359 - type: manhattan_spearman value: 42.4143 - type: euclidean_pearson value: 43.6717 - type: euclidean_spearman value: 43.2176 - type: main_score value: 43.2176 - task: type: STS dataset: name: MTEB STS17 (en-de) type: mteb/sts17-crosslingual-sts config: en-de split: test revision: faeb762787bd10488a50c8b5be4a3b82e411949c metrics: - type: pearson value: 74.0088 - type: spearman value: 75.8687 - type: cosine_pearson value: 74.0088 - type: cosine_spearman value: 75.8687 - type: manhattan_pearson value: 74.8505 - type: manhattan_spearman value: 75.6101 - type: euclidean_pearson value: 75.1303 - type: euclidean_spearman value: 75.8687 - type: main_score value: 75.8687 - task: type: STS dataset: name: MTEB STS22 (zh-en) type: mteb/sts22-crosslingual-sts config: zh-en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: pearson value: 68.0842 - type: spearman value: 69.4346 - type: cosine_pearson value: 68.0842 - type: cosine_spearman value: 69.4346 - type: manhattan_pearson value: 69.9982 - type: manhattan_spearman value: 69.8952 - type: euclidean_pearson value: 69.6375 - type: euclidean_spearman value: 69.4346 - type: main_score value: 69.4346 - task: type: STS dataset: name: MTEB STS22 (es-en) type: mteb/sts22-crosslingual-sts config: es-en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: pearson value: 76.3695 - type: spearman value: 78.88730000000001 - type: cosine_pearson value: 76.3695 - type: cosine_spearman value: 78.88730000000001 - type: manhattan_pearson value: 79.0721 - type: manhattan_spearman value: 79.1151 - type: euclidean_pearson value: 78.783 - type: euclidean_spearman value: 78.88730000000001 - type: main_score value: 78.88730000000001 - task: type: STS dataset: name: MTEB STS22 (de-en) type: mteb/sts22-crosslingual-sts config: de-en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: pearson value: 60.59139999999999 - type: spearman value: 52.692099999999996 - type: cosine_pearson value: 60.59139999999999 - type: cosine_spearman value: 52.692099999999996 - type: manhattan_pearson value: 64.66499999999999 - type: manhattan_spearman value: 53.09009999999999 - type: euclidean_pearson value: 64.5541 - type: euclidean_spearman value: 52.692099999999996 - type: main_score value: 52.692099999999996 - task: type: STS dataset: name: MTEB STS22 (pl-en) type: mteb/sts22-crosslingual-sts config: pl-en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: pearson value: 77.8405 - type: spearman value: 76.6188 - type: cosine_pearson value: 77.8405 - type: cosine_spearman value: 76.6188 - type: manhattan_pearson value: 76.6598 - type: manhattan_spearman value: 76.3583 - type: euclidean_pearson value: 77.1442 - type: euclidean_spearman value: 76.6188 - type: main_score value: 76.6188 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3 metrics: - type: pearson value: 69.8017 - type: spearman value: 68.7734 - type: cosine_pearson value: 69.8017 - type: cosine_spearman value: 68.7734 - type: manhattan_pearson value: 70.6884 - type: manhattan_spearman value: 68.2974 - type: euclidean_pearson value: 70.7968 - type: euclidean_spearman value: 68.7734 - type: main_score value: 68.7734 - task: type: STS dataset: name: MTEB STSBenchmark (default) type: mteb/stsbenchmark-sts config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: pearson value: 73.3293 - type: spearman value: 76.00919999999999 - type: cosine_pearson value: 73.3293 - type: cosine_spearman value: 76.00919999999999 - type: manhattan_pearson value: 75.0184 - type: manhattan_spearman value: 75.8014 - type: euclidean_pearson value: 75.2638 - type: euclidean_spearman value: 76.00919999999999 - type: main_score value: 76.00919999999999 - task: type: Reranking dataset: name: MTEB SciDocsRR (default) type: mteb/scidocs-reranking config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 77.3669 - type: mrr value: 93.5985 - type: nAUC_map_max value: 50.2355 - type: nAUC_map_std value: 65.5401 - type: nAUC_map_diff1 value: 9.6333 - type: nAUC_mrr_max value: 76.5201 - type: nAUC_mrr_std value: 74.7401 - type: nAUC_mrr_diff1 value: 53.170899999999996 - type: main_score value: 77.3669 - task: type: Retrieval dataset: name: MTEB SciFact (default) type: mteb/scifact config: default split: test revision: 0228b52cf27578f30900b9e5271d331663a030d7 metrics: - type: ndcg_at_1 value: 61 - type: ndcg_at_3 value: 67.589 - type: ndcg_at_5 value: 68.948 - type: ndcg_at_10 value: 71.8 - type: ndcg_at_20 value: 72.595 - type: ndcg_at_100 value: 74.138 - type: ndcg_at_1000 value: 74.83800000000001 - type: map_at_1 value: 57.74399999999999 - type: map_at_3 value: 64.866 - type: map_at_5 value: 66.018 - type: map_at_10 value: 67.535 - type: map_at_20 value: 67.77 - type: map_at_100 value: 68.011 - type: map_at_1000 value: 68.042 - type: recall_at_1 value: 57.74399999999999 - type: recall_at_3 value: 71.906 - type: recall_at_5 value: 75.344 - type: recall_at_10 value: 83.2 - type: recall_at_20 value: 86.26700000000001 - type: recall_at_100 value: 94.333 - type: recall_at_1000 value: 99.667 - type: precision_at_1 value: 61 - type: precision_at_3 value: 26.111 - type: precision_at_5 value: 16.8 - type: precision_at_10 value: 9.5 - type: precision_at_20 value: 4.933 - type: precision_at_100 value: 1.073 - type: precision_at_1000 value: 0.11299999999999999 - type: mrr_at_1 value: 61 - type: mrr_at_3 value: 67.4444 - type: mrr_at_5 value: 68.0778 - type: mrr_at_10 value: 69.0483 - type: mrr_at_20 value: 69.2333 - type: mrr_at_100 value: 69.4403 - type: mrr_at_1000 value: 69.4708 - type: nauc_ndcg_at_1_max value: 53.481500000000004 - type: nauc_ndcg_at_1_std value: 8.227 - type: nauc_ndcg_at_1_diff1 value: 72.0771 - type: nauc_ndcg_at_3_max value: 57.0147 - type: nauc_ndcg_at_3_std value: 5.2435 - type: nauc_ndcg_at_3_diff1 value: 68.8841 - type: nauc_ndcg_at_5_max value: 57.4675 - type: nauc_ndcg_at_5_std value: 8.4709 - type: nauc_ndcg_at_5_diff1 value: 67.2977 - type: nauc_ndcg_at_10_max value: 60.3957 - type: nauc_ndcg_at_10_std value: 11.3174 - type: nauc_ndcg_at_10_diff1 value: 67.8332 - type: nauc_ndcg_at_20_max value: 60.3607 - type: nauc_ndcg_at_20_std value: 11.9948 - type: nauc_ndcg_at_20_diff1 value: 68.1122 - type: nauc_ndcg_at_100_max value: 59.5293 - type: nauc_ndcg_at_100_std value: 11.697799999999999 - type: nauc_ndcg_at_100_diff1 value: 68.453 - type: nauc_ndcg_at_1000_max value: 58.8931 - type: nauc_ndcg_at_1000_std value: 10.876199999999999 - type: nauc_ndcg_at_1000_diff1 value: 68.5746 - type: nauc_map_at_1_max value: 49.762299999999996 - type: nauc_map_at_1_std value: -0.2785 - type: nauc_map_at_1_diff1 value: 71.9072 - type: nauc_map_at_3_max value: 54.108599999999996 - type: nauc_map_at_3_std value: 2.0995 - type: nauc_map_at_3_diff1 value: 69.3459 - type: nauc_map_at_5_max value: 55.257 - type: nauc_map_at_5_std value: 5.5776 - type: nauc_map_at_5_diff1 value: 68.3314 - type: nauc_map_at_10_max value: 57.1506 - type: nauc_map_at_10_std value: 7.4561 - type: nauc_map_at_10_diff1 value: 68.8482 - type: nauc_map_at_20_max value: 57.126200000000004 - type: nauc_map_at_20_std value: 7.6833 - type: nauc_map_at_20_diff1 value: 68.9132 - type: nauc_map_at_100_max value: 56.9874 - type: nauc_map_at_100_std value: 7.7405 - type: nauc_map_at_100_diff1 value: 68.9371 - type: nauc_map_at_1000_max value: 56.959199999999996 - type: nauc_map_at_1000_std value: 7.709499999999999 - type: nauc_map_at_1000_diff1 value: 68.9444 - type: nauc_recall_at_1_max value: 49.762299999999996 - type: nauc_recall_at_1_std value: -0.2785 - type: nauc_recall_at_1_diff1 value: 71.9072 - type: nauc_recall_at_3_max value: 58.22580000000001 - type: nauc_recall_at_3_std value: 2.3135 - type: nauc_recall_at_3_diff1 value: 65.5868 - type: nauc_recall_at_5_max value: 60.4096 - type: nauc_recall_at_5_std value: 11.7662 - type: nauc_recall_at_5_diff1 value: 61.5815 - type: nauc_recall_at_10_max value: 72.74629999999999 - type: nauc_recall_at_10_std value: 22.148 - type: nauc_recall_at_10_diff1 value: 62.2401 - type: nauc_recall_at_20_max value: 74.9625 - type: nauc_recall_at_20_std value: 28.1358 - type: nauc_recall_at_20_diff1 value: 63.240700000000004 - type: nauc_recall_at_100_max value: 79.15910000000001 - type: nauc_recall_at_100_std value: 39.4162 - type: nauc_recall_at_100_diff1 value: 65.733 - type: nauc_recall_at_1000_max value: 100 - type: nauc_recall_at_1000_std value: 72.2222 - type: nauc_recall_at_1000_diff1 value: 72.2222 - type: nauc_precision_at_1_max value: 53.481500000000004 - type: nauc_precision_at_1_std value: 8.227 - type: nauc_precision_at_1_diff1 value: 72.0771 - type: nauc_precision_at_3_max value: 55.675799999999995 - type: nauc_precision_at_3_std value: 23.9615 - type: nauc_precision_at_3_diff1 value: 48.1199 - type: nauc_precision_at_5_max value: 50.503299999999996 - type: nauc_precision_at_5_std value: 36.9259 - type: nauc_precision_at_5_diff1 value: 31.769399999999997 - type: nauc_precision_at_10_max value: 45.4878 - type: nauc_precision_at_10_std value: 44.0469 - type: nauc_precision_at_10_diff1 value: 16.666900000000002 - type: nauc_precision_at_20_max value: 40.2908 - type: nauc_precision_at_20_std value: 47.330600000000004 - type: nauc_precision_at_20_diff1 value: 11.0043 - type: nauc_precision_at_100_max value: 27.4643 - type: nauc_precision_at_100_std value: 53.0014 - type: nauc_precision_at_100_diff1 value: -4.8238 - type: nauc_precision_at_1000_max value: 15.755099999999999 - type: nauc_precision_at_1000_std value: 56.634499999999996 - type: nauc_precision_at_1000_diff1 value: -21.124100000000002 - type: nauc_mrr_at_1_max value: 53.481500000000004 - type: nauc_mrr_at_1_std value: 8.227 - type: nauc_mrr_at_1_diff1 value: 72.0771 - type: nauc_mrr_at_3_max value: 57.6662 - type: nauc_mrr_at_3_std value: 9.2816 - type: nauc_mrr_at_3_diff1 value: 69.8276 - type: nauc_mrr_at_5_max value: 57.6565 - type: nauc_mrr_at_5_std value: 10.422099999999999 - type: nauc_mrr_at_5_diff1 value: 69.0964 - type: nauc_mrr_at_10_max value: 58.000099999999996 - type: nauc_mrr_at_10_std value: 10.957600000000001 - type: nauc_mrr_at_10_diff1 value: 69.0098 - type: nauc_mrr_at_20_max value: 58.0066 - type: nauc_mrr_at_20_std value: 11.0139 - type: nauc_mrr_at_20_diff1 value: 69.1278 - type: nauc_mrr_at_100_max value: 57.9072 - type: nauc_mrr_at_100_std value: 10.9621 - type: nauc_mrr_at_100_diff1 value: 69.1925 - type: nauc_mrr_at_1000_max value: 57.87949999999999 - type: nauc_mrr_at_1000_std value: 10.934199999999999 - type: nauc_mrr_at_1000_diff1 value: 69.2004 - type: main_score value: 71.8 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions (default) type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: similarity_accuracy value: 99.8248 - type: similarity_accuracy_threshold value: 74.6155 - type: similarity_f1 value: 91.12780000000001 - type: similarity_f1_threshold value: 74.2422 - type: similarity_precision value: 91.3568 - type: similarity_recall value: 90.9 - type: similarity_ap value: 96.00319999999999 - type: cosine_accuracy value: 99.8248 - type: cosine_accuracy_threshold value: 74.6155 - type: cosine_f1 value: 91.12780000000001 - type: cosine_f1_threshold value: 74.2422 - type: cosine_precision value: 91.3568 - type: cosine_recall value: 90.9 - type: cosine_ap value: 96.00319999999999 - type: manhattan_accuracy value: 99.8257 - type: manhattan_accuracy_threshold value: 1574.1653 - type: manhattan_f1 value: 91.1531 - type: manhattan_f1_threshold value: 1595.7924 - type: manhattan_precision value: 90.6126 - type: manhattan_recall value: 91.7 - type: manhattan_ap value: 95.9848 - type: euclidean_accuracy value: 99.8248 - type: euclidean_accuracy_threshold value: 71.2523 - type: euclidean_f1 value: 91.12780000000001 - type: euclidean_f1_threshold value: 71.7744 - type: euclidean_precision value: 91.3568 - type: euclidean_recall value: 90.9 - type: euclidean_ap value: 96.00319999999999 - type: dot_accuracy value: 99.8248 - type: dot_accuracy_threshold value: 74.6155 - type: dot_f1 value: 91.12780000000001 - type: dot_f1_threshold value: 74.2422 - type: dot_precision value: 91.3568 - type: dot_recall value: 90.9 - type: dot_ap value: 96.00319999999999 - type: max_accuracy value: 99.8257 - type: max_f1 value: 91.1531 - type: max_precision value: 91.3568 - type: max_recall value: 91.7 - type: max_ap value: 96.00319999999999 - type: main_score value: 96.00319999999999 - task: type: Clustering dataset: name: MTEB StackExchangeClustering (default) type: mteb/stackexchange-clustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 61.3985 - type: v_measure_std value: 5.2151000000000005 - type: main_score value: 61.3985 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P (default) type: mteb/stackexchange-clustering-p2p config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 36.1433 - type: v_measure_std value: 1.5853 - type: main_score value: 36.1433 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions (default) type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 50.47580000000001 - type: mrr value: 51.221399999999996 - type: nAUC_map_max value: 10.1311 - type: nAUC_map_std value: 6.239999999999999 - type: nAUC_map_diff1 value: 36.3486 - type: nAUC_mrr_max value: 10.9306 - type: nAUC_mrr_std value: 6.7909 - type: nAUC_mrr_diff1 value: 36.5536 - type: main_score value: 50.47580000000001 - task: type: Summarization dataset: name: MTEB SummEval (default) type: mteb/summeval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: pearson value: 29.8474 - type: spearman value: 29.391099999999998 - type: cosine_spearman value: 29.391099999999998 - type: cosine_pearson value: 29.8474 - type: dot_spearman value: 29.391099999999998 - type: dot_pearson value: 29.8474 - type: main_score value: 29.391099999999998 - task: type: Retrieval dataset: name: MTEB TRECCOVID (default) type: mteb/trec-covid config: default split: test revision: bb9466bac8153a0349341eb1b22e06409e78ef4e metrics: - type: ndcg_at_1 value: 85 - type: ndcg_at_3 value: 84.58099999999999 - type: ndcg_at_5 value: 83.573 - type: ndcg_at_10 value: 80.285 - type: ndcg_at_20 value: 77.469 - type: ndcg_at_100 value: 63.524 - type: ndcg_at_1000 value: 56.839 - type: map_at_1 value: 0.22799999999999998 - type: map_at_3 value: 0.656 - type: map_at_5 value: 1.078 - type: map_at_10 value: 2.0389999999999997 - type: map_at_20 value: 3.7670000000000003 - type: map_at_100 value: 12.8 - type: map_at_1000 value: 31.575999999999997 - type: recall_at_1 value: 0.22799999999999998 - type: recall_at_3 value: 0.695 - type: recall_at_5 value: 1.151 - type: recall_at_10 value: 2.215 - type: recall_at_20 value: 4.232 - type: recall_at_100 value: 15.828000000000001 - type: recall_at_1000 value: 53.516 - type: precision_at_1 value: 90 - type: precision_at_3 value: 89.333 - type: precision_at_5 value: 88.8 - type: precision_at_10 value: 84.6 - type: precision_at_20 value: 81.6 - type: precision_at_100 value: 65.64 - type: precision_at_1000 value: 25.380000000000003 - type: mrr_at_1 value: 90 - type: mrr_at_3 value: 94.6667 - type: mrr_at_5 value: 94.6667 - type: mrr_at_10 value: 94.6667 - type: mrr_at_20 value: 94.6667 - type: mrr_at_100 value: 94.6667 - type: mrr_at_1000 value: 94.6667 - type: nauc_ndcg_at_1_max value: -5.4637 - type: nauc_ndcg_at_1_std value: 14.5981 - type: nauc_ndcg_at_1_diff1 value: 13.6414 - type: nauc_ndcg_at_3_max value: 10.9521 - type: nauc_ndcg_at_3_std value: 39.8204 - type: nauc_ndcg_at_3_diff1 value: -13.839799999999999 - type: nauc_ndcg_at_5_max value: 20.9664 - type: nauc_ndcg_at_5_std value: 50.876999999999995 - type: nauc_ndcg_at_5_diff1 value: -15.3559 - type: nauc_ndcg_at_10_max value: 34.053 - type: nauc_ndcg_at_10_std value: 59.1102 - type: nauc_ndcg_at_10_diff1 value: -23.3868 - type: nauc_ndcg_at_20_max value: 39.5081 - type: nauc_ndcg_at_20_std value: 70.287 - type: nauc_ndcg_at_20_diff1 value: -36.7999 - type: nauc_ndcg_at_100_max value: 38.8671 - type: nauc_ndcg_at_100_std value: 80.5875 - type: nauc_ndcg_at_100_diff1 value: -28.766599999999997 - type: nauc_ndcg_at_1000_max value: 45.4017 - type: nauc_ndcg_at_1000_std value: 73.1799 - type: nauc_ndcg_at_1000_diff1 value: -13.5374 - type: nauc_map_at_1_max value: -15.7901 - type: nauc_map_at_1_std value: -14.5481 - type: nauc_map_at_1_diff1 value: 35.3307 - type: nauc_map_at_3_max value: -4.8114 - type: nauc_map_at_3_std value: -8.3704 - type: nauc_map_at_3_diff1 value: 26.2918 - type: nauc_map_at_5_max value: -0.9780000000000001 - type: nauc_map_at_5_std value: -3.4821 - type: nauc_map_at_5_diff1 value: 25.469 - type: nauc_map_at_10_max value: 4.2075000000000005 - type: nauc_map_at_10_std value: 1.5897999999999999 - type: nauc_map_at_10_diff1 value: 20.0578 - type: nauc_map_at_20_max value: 11.1623 - type: nauc_map_at_20_std value: 13.4387 - type: nauc_map_at_20_diff1 value: 12.9992 - type: nauc_map_at_100_max value: 21.7341 - type: nauc_map_at_100_std value: 51.2629 - type: nauc_map_at_100_diff1 value: 6.3333 - type: nauc_map_at_1000_max value: 45.7524 - type: nauc_map_at_1000_std value: 79.5106 - type: nauc_map_at_1000_diff1 value: -16.2395 - type: nauc_recall_at_1_max value: -15.7901 - type: nauc_recall_at_1_std value: -14.5481 - type: nauc_recall_at_1_diff1 value: 35.3307 - type: nauc_recall_at_3_max value: -3.9641 - type: nauc_recall_at_3_std value: -11.6408 - type: nauc_recall_at_3_diff1 value: 26.243 - type: nauc_recall_at_5_max value: -1.3654 - type: nauc_recall_at_5_std value: -7.7433000000000005 - type: nauc_recall_at_5_diff1 value: 25.5058 - type: nauc_recall_at_10_max value: 0.6649999999999999 - type: nauc_recall_at_10_std value: -5.8116 - type: nauc_recall_at_10_diff1 value: 23.0906 - type: nauc_recall_at_20_max value: 4.398 - type: nauc_recall_at_20_std value: 2.5343999999999998 - type: nauc_recall_at_20_diff1 value: 17.0552 - type: nauc_recall_at_100_max value: 12.8082 - type: nauc_recall_at_100_std value: 32.912400000000005 - type: nauc_recall_at_100_diff1 value: 14.6836 - type: nauc_recall_at_1000_max value: 42.261500000000005 - type: nauc_recall_at_1000_std value: 60.5793 - type: nauc_recall_at_1000_diff1 value: -6.1521 - type: nauc_precision_at_1_max value: -7.077500000000001 - type: nauc_precision_at_1_std value: 19.7572 - type: nauc_precision_at_1_diff1 value: 21.9141 - type: nauc_precision_at_3_max value: 30.758799999999997 - type: nauc_precision_at_3_std value: 53.897099999999995 - type: nauc_precision_at_3_diff1 value: -25.885399999999997 - type: nauc_precision_at_5_max value: 43.5162 - type: nauc_precision_at_5_std value: 66.8874 - type: nauc_precision_at_5_diff1 value: -20.7483 - type: nauc_precision_at_10_max value: 46.7798 - type: nauc_precision_at_10_std value: 63.677499999999995 - type: nauc_precision_at_10_diff1 value: -21.1182 - type: nauc_precision_at_20_max value: 49.8621 - type: nauc_precision_at_20_std value: 79.1937 - type: nauc_precision_at_20_diff1 value: -38.9691 - type: nauc_precision_at_100_max value: 42.8699 - type: nauc_precision_at_100_std value: 83.7695 - type: nauc_precision_at_100_diff1 value: -26.794 - type: nauc_precision_at_1000_max value: 42.7819 - type: nauc_precision_at_1000_std value: 53.815900000000006 - type: nauc_precision_at_1000_diff1 value: -34.4047 - type: nauc_mrr_at_1_max value: -7.077500000000001 - type: nauc_mrr_at_1_std value: 19.7572 - type: nauc_mrr_at_1_diff1 value: 21.9141 - type: nauc_mrr_at_3_max value: -2.1212999999999997 - type: nauc_mrr_at_3_std value: 21.9859 - type: nauc_mrr_at_3_diff1 value: 25.0584 - type: nauc_mrr_at_5_max value: -2.1212999999999997 - type: nauc_mrr_at_5_std value: 21.9859 - type: nauc_mrr_at_5_diff1 value: 25.0584 - type: nauc_mrr_at_10_max value: -2.1212999999999997 - type: nauc_mrr_at_10_std value: 21.9859 - type: nauc_mrr_at_10_diff1 value: 25.0584 - type: nauc_mrr_at_20_max value: -2.1212999999999997 - type: nauc_mrr_at_20_std value: 21.9859 - type: nauc_mrr_at_20_diff1 value: 25.0584 - type: nauc_mrr_at_100_max value: -2.1212999999999997 - type: nauc_mrr_at_100_std value: 21.9859 - type: nauc_mrr_at_100_diff1 value: 25.0584 - type: nauc_mrr_at_1000_max value: -2.1212999999999997 - type: nauc_mrr_at_1000_std value: 21.9859 - type: nauc_mrr_at_1000_diff1 value: 25.0584 - type: main_score value: 80.285 - task: type: Retrieval dataset: name: MTEB Touche2020 (default) type: mteb/touche2020 config: default split: test revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f metrics: - type: ndcg_at_1 value: 33.672999999999995 - type: ndcg_at_3 value: 34.392 - type: ndcg_at_5 value: 32.606 - type: ndcg_at_10 value: 29.767 - type: ndcg_at_20 value: 30.353 - type: ndcg_at_100 value: 41.094 - type: ndcg_at_1000 value: 51.937 - type: map_at_1 value: 2.64 - type: map_at_3 value: 6.428000000000001 - type: map_at_5 value: 8.792 - type: map_at_10 value: 11.882 - type: map_at_20 value: 14.818000000000001 - type: map_at_100 value: 18.613 - type: map_at_1000 value: 20.233 - type: recall_at_1 value: 2.64 - type: recall_at_3 value: 7.951999999999999 - type: recall_at_5 value: 11.898 - type: recall_at_10 value: 18.782 - type: recall_at_20 value: 27.488 - type: recall_at_100 value: 51.337999999999994 - type: recall_at_1000 value: 84.399 - type: precision_at_1 value: 36.735 - type: precision_at_3 value: 36.735 - type: precision_at_5 value: 33.061 - type: precision_at_10 value: 26.122 - type: precision_at_20 value: 19.898 - type: precision_at_100 value: 8.429 - type: precision_at_1000 value: 1.5650000000000002 - type: mrr_at_1 value: 36.7347 - type: mrr_at_3 value: 51.7007 - type: mrr_at_5 value: 54.65989999999999 - type: mrr_at_10 value: 55.8868 - type: mrr_at_20 value: 56.2944 - type: mrr_at_100 value: 56.360200000000006 - type: mrr_at_1000 value: 56.360200000000006 - type: nauc_ndcg_at_1_max value: -23.0012 - type: nauc_ndcg_at_1_std value: -9.474 - type: nauc_ndcg_at_1_diff1 value: 15.5991 - type: nauc_ndcg_at_3_max value: -16.1454 - type: nauc_ndcg_at_3_std value: -26.226100000000002 - type: nauc_ndcg_at_3_diff1 value: 22.9111 - type: nauc_ndcg_at_5_max value: -20.3259 - type: nauc_ndcg_at_5_std value: -23.3106 - type: nauc_ndcg_at_5_diff1 value: 20.112199999999998 - type: nauc_ndcg_at_10_max value: -17.4616 - type: nauc_ndcg_at_10_std value: -15.5791 - type: nauc_ndcg_at_10_diff1 value: 13.2876 - type: nauc_ndcg_at_20_max value: -20.0683 - type: nauc_ndcg_at_20_std value: -10.979899999999999 - type: nauc_ndcg_at_20_diff1 value: 5.929 - type: nauc_ndcg_at_100_max value: -21.096899999999998 - type: nauc_ndcg_at_100_std value: 13.212399999999999 - type: nauc_ndcg_at_100_diff1 value: 3.9886 - type: nauc_ndcg_at_1000_max value: -14.1544 - type: nauc_ndcg_at_1000_std value: 19.5979 - type: nauc_ndcg_at_1000_diff1 value: 1.2742 - type: nauc_map_at_1_max value: -18.123900000000003 - type: nauc_map_at_1_std value: -17.8031 - type: nauc_map_at_1_diff1 value: 21.032899999999998 - type: nauc_map_at_3_max value: -6.7797 - type: nauc_map_at_3_std value: -28.810299999999998 - type: nauc_map_at_3_diff1 value: 16.2912 - type: nauc_map_at_5_max value: -7.620699999999999 - type: nauc_map_at_5_std value: -27.6982 - type: nauc_map_at_5_diff1 value: 14.813100000000002 - type: nauc_map_at_10_max value: -5.1492 - type: nauc_map_at_10_std value: -23.885 - type: nauc_map_at_10_diff1 value: 6.9926 - type: nauc_map_at_20_max value: -9.6331 - type: nauc_map_at_20_std value: -19.215 - type: nauc_map_at_20_diff1 value: 0.6491 - type: nauc_map_at_100_max value: -9.7297 - type: nauc_map_at_100_std value: -6.9502999999999995 - type: nauc_map_at_100_diff1 value: -1.5897999999999999 - type: nauc_map_at_1000_max value: -8.9517 - type: nauc_map_at_1000_std value: -3.9941999999999998 - type: nauc_map_at_1000_diff1 value: -2.8158 - type: nauc_recall_at_1_max value: -18.123900000000003 - type: nauc_recall_at_1_std value: -17.8031 - type: nauc_recall_at_1_diff1 value: 21.032899999999998 - type: nauc_recall_at_3_max value: -12.1006 - type: nauc_recall_at_3_std value: -35.3199 - type: nauc_recall_at_3_diff1 value: 12.044 - type: nauc_recall_at_5_max value: -15.7192 - type: nauc_recall_at_5_std value: -30.7299 - type: nauc_recall_at_5_diff1 value: 8.3249 - type: nauc_recall_at_10_max value: -13.3968 - type: nauc_recall_at_10_std value: -19.2107 - type: nauc_recall_at_10_diff1 value: 0.1315 - type: nauc_recall_at_20_max value: -19.5043 - type: nauc_recall_at_20_std value: -10.005500000000001 - type: nauc_recall_at_20_diff1 value: -7.197299999999999 - type: nauc_recall_at_100_max value: -21.4032 - type: nauc_recall_at_100_std value: 33.5358 - type: nauc_recall_at_100_diff1 value: -10.4876 - type: nauc_recall_at_1000_max value: 1.8395000000000001 - type: nauc_recall_at_1000_std value: 70.462 - type: nauc_recall_at_1000_diff1 value: -23.4072 - type: nauc_precision_at_1_max value: -23.0917 - type: nauc_precision_at_1_std value: -8.036999999999999 - type: nauc_precision_at_1_diff1 value: 19.354599999999998 - type: nauc_precision_at_3_max value: -11.3547 - type: nauc_precision_at_3_std value: -30.2495 - type: nauc_precision_at_3_diff1 value: 20.3126 - type: nauc_precision_at_5_max value: -17.2545 - type: nauc_precision_at_5_std value: -24.8896 - type: nauc_precision_at_5_diff1 value: 15.6276 - type: nauc_precision_at_10_max value: -11.5796 - type: nauc_precision_at_10_std value: -2.3662 - type: nauc_precision_at_10_diff1 value: 3.8091 - type: nauc_precision_at_20_max value: -11.9042 - type: nauc_precision_at_20_std value: 15.6577 - type: nauc_precision_at_20_diff1 value: -8.8878 - type: nauc_precision_at_100_max value: -0.5217 - type: nauc_precision_at_100_std value: 71.8387 - type: nauc_precision_at_100_diff1 value: -16.8714 - type: nauc_precision_at_1000_max value: 36.234300000000005 - type: nauc_precision_at_1000_std value: 37.5447 - type: nauc_precision_at_1000_diff1 value: -20.7229 - type: nauc_mrr_at_1_max value: -23.0917 - type: nauc_mrr_at_1_std value: -8.036999999999999 - type: nauc_mrr_at_1_diff1 value: 19.354599999999998 - type: nauc_mrr_at_3_max value: -27.9937 - type: nauc_mrr_at_3_std value: -26.519900000000003 - type: nauc_mrr_at_3_diff1 value: 20.288 - type: nauc_mrr_at_5_max value: -33.218599999999995 - type: nauc_mrr_at_5_std value: -23.857400000000002 - type: nauc_mrr_at_5_diff1 value: 15.978200000000001 - type: nauc_mrr_at_10_max value: -31.7904 - type: nauc_mrr_at_10_std value: -19.169900000000002 - type: nauc_mrr_at_10_diff1 value: 17.762700000000002 - type: nauc_mrr_at_20_max value: -30.44 - type: nauc_mrr_at_20_std value: -20.2867 - type: nauc_mrr_at_20_diff1 value: 18.895500000000002 - type: nauc_mrr_at_100_max value: -30.5404 - type: nauc_mrr_at_100_std value: -20.5699 - type: nauc_mrr_at_100_diff1 value: 18.7046 - type: nauc_mrr_at_1000_max value: -30.5404 - type: nauc_mrr_at_1000_std value: -20.5699 - type: nauc_mrr_at_1000_diff1 value: 18.7046 - type: main_score value: 29.767 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification (default) type: mteb/toxic_conversations_50k config: default split: test revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de metrics: - type: accuracy value: 64.8096 - type: f1 value: 49.844300000000004 - type: f1_weighted value: 72.5251 - type: ap value: 11.7519 - type: ap_weighted value: 11.7519 - type: main_score value: 64.8096 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification (default) type: mteb/tweet_sentiment_extraction config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 58.1692 - type: f1 value: 58.4408 - type: f1_weighted value: 57.565599999999996 - type: main_score value: 58.1692 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering (default) type: mteb/twentynewsgroups-clustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 39.293 - type: v_measure_std value: 1.5684 - type: main_score value: 39.293 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 (default) type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: similarity_accuracy value: 83.29260000000001 - type: similarity_accuracy_threshold value: 78.2732 - type: similarity_f1 value: 60.656600000000005 - type: similarity_f1_threshold value: 73.4961 - type: similarity_precision value: 59.007 - type: similarity_recall value: 62.4011 - type: similarity_ap value: 64.7501 - type: cosine_accuracy value: 83.29260000000001 - type: cosine_accuracy_threshold value: 78.2732 - type: cosine_f1 value: 60.656600000000005 - type: cosine_f1_threshold value: 73.4961 - type: cosine_precision value: 59.007 - type: cosine_recall value: 62.4011 - type: cosine_ap value: 64.7501 - type: manhattan_accuracy value: 83.2986 - type: manhattan_accuracy_threshold value: 1476.7148 - type: manhattan_f1 value: 60.7459 - type: manhattan_f1_threshold value: 1607.9180000000001 - type: manhattan_precision value: 59.0581 - type: manhattan_recall value: 62.53300000000001 - type: manhattan_ap value: 64.76859999999999 - type: euclidean_accuracy value: 83.29260000000001 - type: euclidean_accuracy_threshold value: 65.9194 - type: euclidean_f1 value: 60.656600000000005 - type: euclidean_f1_threshold value: 72.8065 - type: euclidean_precision value: 59.007 - type: euclidean_recall value: 62.4011 - type: euclidean_ap value: 64.7501 - type: dot_accuracy value: 83.29260000000001 - type: dot_accuracy_threshold value: 78.2731 - type: dot_f1 value: 60.656600000000005 - type: dot_f1_threshold value: 73.4961 - type: dot_precision value: 59.007 - type: dot_recall value: 62.4011 - type: dot_ap value: 64.7501 - type: max_accuracy value: 83.2986 - type: max_f1 value: 60.7459 - type: max_precision value: 59.0581 - type: max_recall value: 62.53300000000001 - type: max_ap value: 64.76859999999999 - type: main_score value: 64.76859999999999 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus (default) type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: similarity_accuracy value: 89.0247 - type: similarity_accuracy_threshold value: 69.271 - type: similarity_f1 value: 78.24419999999999 - type: similarity_f1_threshold value: 66.2183 - type: similarity_precision value: 76.616 - type: similarity_recall value: 79.943 - type: similarity_ap value: 85.9494 - type: cosine_accuracy value: 89.0247 - type: cosine_accuracy_threshold value: 69.271 - type: cosine_f1 value: 78.24419999999999 - type: cosine_f1_threshold value: 66.2183 - type: cosine_precision value: 76.616 - type: cosine_recall value: 79.943 - type: cosine_ap value: 85.9494 - type: manhattan_accuracy value: 89.0267 - type: manhattan_accuracy_threshold value: 1750.3544000000002 - type: manhattan_f1 value: 78.2188 - type: manhattan_f1_threshold value: 1837.7304 - type: manhattan_precision value: 75.1472 - type: manhattan_recall value: 81.5522 - type: manhattan_ap value: 85.9496 - type: euclidean_accuracy value: 89.0247 - type: euclidean_accuracy_threshold value: 78.3951 - type: euclidean_f1 value: 78.24419999999999 - type: euclidean_f1_threshold value: 82.197 - type: euclidean_precision value: 76.616 - type: euclidean_recall value: 79.943 - type: euclidean_ap value: 85.9494 - type: dot_accuracy value: 89.0247 - type: dot_accuracy_threshold value: 69.271 - type: dot_f1 value: 78.24419999999999 - type: dot_f1_threshold value: 66.2183 - type: dot_precision value: 76.616 - type: dot_recall value: 79.943 - type: dot_ap value: 85.9494 - type: max_accuracy value: 89.0267 - type: max_f1 value: 78.24419999999999 - type: max_precision value: 76.616 - type: max_recall value: 81.5522 - type: max_ap value: 85.9496 - type: main_score value: 85.9496 --- ***See Disclaimer below*** ---- # A Teradata Vantage compatible Embeddings Model # Snowflake/snowflake-arctic-embed-m-v2.0 ## Overview of this Model An Embedding Model which maps text (sentence/ paragraphs) into a vector. The [Snowflake/snowflake-arctic-embed-m-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0) model is designed to generate text embeddings. - 305.37M params (Sizes in ONNX format - "fp32": 1169.3MB, "int8": 296.51MB, "uint8": 296.51MB) - 8192 maximum input tokens - 768 dimensions of output vector - Licence: apache-2.0. The released models can be used for commercial purposes free of charge. - Reference to Original Model: https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0 ## Quickstart: Deploying this Model in Teradata Vantage We have pre-converted the model into the ONNX format compatible with BYOM 6.0, eliminating the need for manual conversion. **Note:** Ensure you have access to a Teradata Database with BYOM 6.0 installed. To get started, clone the pre-converted model directly from the Teradata HuggingFace repository. ```python import teradataml as tdml import getpass from huggingface_hub import hf_hub_download model_name = "snowflake-arctic-embed-m-v2.0" number_dimensions_output = 768 model_file_name = "model.onnx" # Step 1: Download Model from Teradata HuggingFace Page hf_hub_download(repo_id=f"Teradata/{model_name}", filename=f"onnx/{model_file_name}", local_dir="./") hf_hub_download(repo_id=f"Teradata/{model_name}", filename=f"tokenizer.json", local_dir="./") # Step 2: Create Connection to Vantage tdml.create_context(host = input('enter your hostname'), username=input('enter your username'), password = getpass.getpass("enter your password")) # Step 3: Load Models into Vantage # a) Embedding model tdml.save_byom(model_id = model_name, # must be unique in the models table model_file = f"onnx/{model_file_name}", table_name = 'embeddings_models' ) # b) Tokenizer tdml.save_byom(model_id = model_name, # must be unique in the models table model_file = 'tokenizer.json', table_name = 'embeddings_tokenizers') # Step 4: Test ONNXEmbeddings Function # Note that ONNXEmbeddings expects the 'payload' column to be 'txt'. # If it has got a different name, just rename it in a subquery/CTE. input_table = "emails.emails" embeddings_query = f""" SELECT * from mldb.ONNXEmbeddings( on {input_table} as InputTable on (select * from embeddings_models where model_id = '{model_name}') as ModelTable DIMENSION on (select model as tokenizer from embeddings_tokenizers where model_id = '{model_name}') as TokenizerTable DIMENSION using Accumulate('id', 'txt') ModelOutputTensor('sentence_embedding') EnableMemoryCheck('false') OutputFormat('FLOAT32({number_dimensions_output})') OverwriteCachedModel('true') ) a """ DF_embeddings = tdml.DataFrame.from_query(embeddings_query) DF_embeddings ``` ## What Can I Do with the Embeddings? Teradata Vantage includes pre-built in-database functions to process embeddings further. Explore the following examples: - **Semantic Clustering with TD_KMeans:** [Semantic Clustering Python Notebook](https://github.com/Teradata/jupyter-demos/blob/main/UseCases/Language_Models_InVantage/Semantic_Clustering_Python.ipynb) - **Semantic Distance with TD_VectorDistance:** [Semantic Similarity Python Notebook](https://github.com/Teradata/jupyter-demos/blob/main/UseCases/Language_Models_InVantage/Semantic_Similarity_Python.ipynb) - **RAG-Based Application with TD_VectorDistance:** [RAG and Bedrock Query PDF Notebook](https://github.com/Teradata/jupyter-demos/blob/main/UseCases/Language_Models_InVantage/RAG_and_Bedrock_QueryPDF.ipynb) ## Deep Dive into Model Conversion to ONNX **The steps below outline how we converted the open-source Hugging Face model into an ONNX file compatible with the in-database ONNXEmbeddings function.** You do not need to perform these steps—they are provided solely for documentation and transparency. However, they may be helpful if you wish to convert another model to the required format. ### Part 1. Importing and Converting Model using optimum We start by importing the pre-trained [Snowflake/snowflake-arctic-embed-m-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0) model from Hugging Face. We are downloading the ONNX files from the repository prepared by the model authors. After downloading, we are fixing the opset in the ONNX file for compatibility with ONNX runtime used in Teradata Vantage We are generating ONNX files for multiple different precisions: fp32, int8, uint8 You can find the detailed conversion steps in the file [convert.py](./convert.py) ### Part 2. Running the model in Python with onnxruntime & compare results Once the fixes are applied, we proceed to test the correctness of the ONNX model by calculating cosine similarity between two texts using native SentenceTransformers and ONNX runtime, comparing the results. If the results are identical, it confirms that the ONNX model gives the same result as the native models, validating its correctness and suitability for further use in the database. ```python import onnxruntime as rt from sentence_transformers.util import cos_sim from sentence_transformers import SentenceTransformer import transformers sentences_1 = 'How is the weather today?' sentences_2 = 'What is the current weather like today?' # Calculate ONNX result tokenizer = transformers.AutoTokenizer.from_pretrained("Snowflake/snowflake-arctic-embed-m-v2.0") predef_sess = rt.InferenceSession("onnx/model.onnx") enc1 = tokenizer(sentences_1) embeddings_1_onnx = predef_sess.run(None, {"input_ids": [enc1.input_ids], "attention_mask": [enc1.attention_mask]}) enc2 = tokenizer(sentences_2) embeddings_2_onnx = predef_sess.run(None, {"input_ids": [enc2.input_ids], "attention_mask": [enc2.attention_mask]}) # Calculate embeddings with SentenceTransformer model = SentenceTransformer(model_id, trust_remote_code=True) embeddings_1_sentence_transformer = model.encode(sentences_1, normalize_embeddings=True, trust_remote_code=True) embeddings_2_sentence_transformer = model.encode(sentences_2, normalize_embeddings=True, trust_remote_code=True) # Compare results print("Cosine similiarity for embeddings calculated with ONNX:" + str(cos_sim(embeddings_1_onnx[1][0], embeddings_2_onnx[1][0]))) print("Cosine similiarity for embeddings calculated with SentenceTransformer:" + str(cos_sim(embeddings_1_sentence_transformer, embeddings_2_sentence_transformer))) ``` You can find the detailed ONNX vs. SentenceTransformer result comparison steps in the file [test_local.py](./test_local.py) ----- DISCLAIMER: The content herein (“Content”) is provided “AS IS” and is not covered by any Teradata Operations, Inc. and its affiliates (“Teradata”) agreements. Its listing here does not constitute certification or endorsement by Teradata. To the extent any of the Content contains or is related to any artificial intelligence (“AI”) or other language learning models (“Models”) that interoperate with the products and services of Teradata, by accessing, bringing, deploying or using such Models, you acknowledge and agree that you are solely responsible for ensuring compliance with all applicable laws, regulations, and restrictions governing the use, deployment, and distribution of AI technologies. This includes, but is not limited to, AI Diffusion Rules, European Union AI Act, AI-related laws and regulations, privacy laws, export controls, and financial or sector-specific regulations. While Teradata may provide support, guidance, or assistance in the deployment or implementation of Models to interoperate with Teradata’s products and/or services, you remain fully responsible for ensuring that your Models, data, and applications comply with all relevant legal and regulatory obligations. Our assistance does not constitute legal or regulatory approval, and Teradata disclaims any liability arising from non-compliance with applicable laws. You must determine the suitability of the Models for any purpose. Given the probabilistic nature of machine learning and modeling, the use of the Models may in some situations result in incorrect output that does not accurately reflect the action generated. You should evaluate the accuracy of any output as appropriate for your use case, including by using human review of the output.
[ "BIOSSES", "SCIFACT" ]
Muennighoff/SGPT-2.7B-weightedmean-msmarco-specb-bitfit
Muennighoff
sentence-similarity
[ "sentence-transformers", "pytorch", "gpt_neo", "feature-extraction", "sentence-similarity", "mteb", "arxiv:2202.08904", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2022-03-02T23:29:04Z
2023-03-27T22:24:48+00:00
30
3
--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - mteb model-index: - name: SGPT-2.7B-weightedmean-msmarco-specb-bitfit results: - task: type: Classification dataset: name: MTEB AmazonCounterfactualClassification (en) type: mteb/amazon_counterfactual config: en split: test revision: 2d8a100785abf0ae21420d2a55b0c56e3e1ea996 metrics: - type: accuracy value: 67.56716417910448 - type: ap value: 30.75574629595259 - type: f1 value: 61.805121301858655 - task: type: Classification dataset: name: MTEB AmazonPolarityClassification type: mteb/amazon_polarity config: default split: test revision: 80714f8dcf8cefc218ef4f8c5a966dd83f75a0e1 metrics: - type: accuracy value: 71.439575 - type: ap value: 65.91341330532453 - type: f1 value: 70.90561852619555 - task: type: Classification dataset: name: MTEB AmazonReviewsClassification (en) type: mteb/amazon_reviews_multi config: en split: test revision: c379a6705fec24a2493fa68e011692605f44e119 metrics: - type: accuracy value: 35.748000000000005 - type: f1 value: 35.48576287186347 - task: type: Retrieval dataset: name: MTEB ArguAna type: arguana config: default split: test revision: 5b3e3697907184a9b77a3c99ee9ea1a9cbb1e4e3 metrics: - type: map_at_1 value: 25.96 - type: map_at_10 value: 41.619 - type: map_at_100 value: 42.673 - type: map_at_1000 value: 42.684 - type: map_at_3 value: 36.569 - type: map_at_5 value: 39.397 - type: mrr_at_1 value: 26.316 - type: mrr_at_10 value: 41.772 - type: mrr_at_100 value: 42.82 - type: mrr_at_1000 value: 42.83 - type: mrr_at_3 value: 36.724000000000004 - type: mrr_at_5 value: 39.528999999999996 - type: ndcg_at_1 value: 25.96 - type: ndcg_at_10 value: 50.491 - type: ndcg_at_100 value: 54.864999999999995 - type: ndcg_at_1000 value: 55.10699999999999 - type: ndcg_at_3 value: 40.053 - type: ndcg_at_5 value: 45.134 - type: precision_at_1 value: 25.96 - type: precision_at_10 value: 7.8950000000000005 - type: precision_at_100 value: 0.9780000000000001 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 16.714000000000002 - type: precision_at_5 value: 12.489 - type: recall_at_1 value: 25.96 - type: recall_at_10 value: 78.947 - type: recall_at_100 value: 97.795 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 50.141999999999996 - type: recall_at_5 value: 62.446999999999996 - task: type: Clustering dataset: name: MTEB ArxivClusteringP2P type: mteb/arxiv-clustering-p2p config: default split: test revision: 0bbdb47bcbe3a90093699aefeed338a0f28a7ee8 metrics: - type: v_measure value: 44.72125714642202 - task: type: Clustering dataset: name: MTEB ArxivClusteringS2S type: mteb/arxiv-clustering-s2s config: default split: test revision: b73bd54100e5abfa6e3a23dcafb46fe4d2438dc3 metrics: - type: v_measure value: 35.081451519142064 - task: type: Reranking dataset: name: MTEB AskUbuntuDupQuestions type: mteb/askubuntudupquestions-reranking config: default split: test revision: 4d853f94cd57d85ec13805aeeac3ae3e5eb4c49c metrics: - type: map value: 59.634661990392054 - type: mrr value: 73.6813525040672 - task: type: STS dataset: name: MTEB BIOSSES type: mteb/biosses-sts config: default split: test revision: 9ee918f184421b6bd48b78f6c714d86546106103 metrics: - type: cos_sim_pearson value: 87.42754550496836 - type: cos_sim_spearman value: 84.84289705838664 - type: euclidean_pearson value: 85.59331970450859 - type: euclidean_spearman value: 85.8525586184271 - type: manhattan_pearson value: 85.41233134466698 - type: manhattan_spearman value: 85.52303303767404 - task: type: Classification dataset: name: MTEB Banking77Classification type: mteb/banking77 config: default split: test revision: 44fa15921b4c889113cc5df03dd4901b49161ab7 metrics: - type: accuracy value: 83.21753246753246 - type: f1 value: 83.15394543120915 - task: type: Clustering dataset: name: MTEB BiorxivClusteringP2P type: mteb/biorxiv-clustering-p2p config: default split: test revision: 11d0121201d1f1f280e8cc8f3d98fb9c4d9f9c55 metrics: - type: v_measure value: 34.41414219680629 - task: type: Clustering dataset: name: MTEB BiorxivClusteringS2S type: mteb/biorxiv-clustering-s2s config: default split: test revision: c0fab014e1bcb8d3a5e31b2088972a1e01547dc1 metrics: - type: v_measure value: 30.533275862270028 - task: type: Retrieval dataset: name: MTEB CQADupstackAndroidRetrieval type: BeIR/cqadupstack config: default split: test revision: 2b9f5791698b5be7bc5e10535c8690f20043c3db metrics: - type: map_at_1 value: 30.808999999999997 - type: map_at_10 value: 40.617 - type: map_at_100 value: 41.894999999999996 - type: map_at_1000 value: 42.025 - type: map_at_3 value: 37.0 - type: map_at_5 value: 38.993 - type: mrr_at_1 value: 37.482 - type: mrr_at_10 value: 46.497 - type: mrr_at_100 value: 47.144000000000005 - type: mrr_at_1000 value: 47.189 - type: mrr_at_3 value: 43.705 - type: mrr_at_5 value: 45.193 - type: ndcg_at_1 value: 37.482 - type: ndcg_at_10 value: 46.688 - type: ndcg_at_100 value: 51.726000000000006 - type: ndcg_at_1000 value: 53.825 - type: ndcg_at_3 value: 41.242000000000004 - type: ndcg_at_5 value: 43.657000000000004 - type: precision_at_1 value: 37.482 - type: precision_at_10 value: 8.827 - type: precision_at_100 value: 1.393 - type: precision_at_1000 value: 0.186 - type: precision_at_3 value: 19.361 - type: precision_at_5 value: 14.106 - type: recall_at_1 value: 30.808999999999997 - type: recall_at_10 value: 58.47 - type: recall_at_100 value: 80.51899999999999 - type: recall_at_1000 value: 93.809 - type: recall_at_3 value: 42.462 - type: recall_at_5 value: 49.385 - type: map_at_1 value: 26.962000000000003 - type: map_at_10 value: 36.93 - type: map_at_100 value: 38.102000000000004 - type: map_at_1000 value: 38.22 - type: map_at_3 value: 34.065 - type: map_at_5 value: 35.72 - type: mrr_at_1 value: 33.567 - type: mrr_at_10 value: 42.269 - type: mrr_at_100 value: 42.99 - type: mrr_at_1000 value: 43.033 - type: mrr_at_3 value: 40.064 - type: mrr_at_5 value: 41.258 - type: ndcg_at_1 value: 33.567 - type: ndcg_at_10 value: 42.405 - type: ndcg_at_100 value: 46.847 - type: ndcg_at_1000 value: 48.951 - type: ndcg_at_3 value: 38.312000000000005 - type: ndcg_at_5 value: 40.242 - type: precision_at_1 value: 33.567 - type: precision_at_10 value: 8.032 - type: precision_at_100 value: 1.295 - type: precision_at_1000 value: 0.17600000000000002 - type: precision_at_3 value: 18.662 - type: precision_at_5 value: 13.299 - type: recall_at_1 value: 26.962000000000003 - type: recall_at_10 value: 52.489 - type: recall_at_100 value: 71.635 - type: recall_at_1000 value: 85.141 - type: recall_at_3 value: 40.28 - type: recall_at_5 value: 45.757 - type: map_at_1 value: 36.318 - type: map_at_10 value: 47.97 - type: map_at_100 value: 49.003 - type: map_at_1000 value: 49.065999999999995 - type: map_at_3 value: 45.031 - type: map_at_5 value: 46.633 - type: mrr_at_1 value: 41.504999999999995 - type: mrr_at_10 value: 51.431000000000004 - type: mrr_at_100 value: 52.129000000000005 - type: mrr_at_1000 value: 52.161 - type: mrr_at_3 value: 48.934 - type: mrr_at_5 value: 50.42 - type: ndcg_at_1 value: 41.504999999999995 - type: ndcg_at_10 value: 53.676 - type: ndcg_at_100 value: 57.867000000000004 - type: ndcg_at_1000 value: 59.166 - type: ndcg_at_3 value: 48.516 - type: ndcg_at_5 value: 50.983999999999995 - type: precision_at_1 value: 41.504999999999995 - type: precision_at_10 value: 8.608 - type: precision_at_100 value: 1.1560000000000001 - type: precision_at_1000 value: 0.133 - type: precision_at_3 value: 21.462999999999997 - type: precision_at_5 value: 14.721 - type: recall_at_1 value: 36.318 - type: recall_at_10 value: 67.066 - type: recall_at_100 value: 85.34 - type: recall_at_1000 value: 94.491 - type: recall_at_3 value: 53.215999999999994 - type: recall_at_5 value: 59.214 - type: map_at_1 value: 22.167 - type: map_at_10 value: 29.543999999999997 - type: map_at_100 value: 30.579 - type: map_at_1000 value: 30.669999999999998 - type: map_at_3 value: 26.982 - type: map_at_5 value: 28.474 - type: mrr_at_1 value: 24.068 - type: mrr_at_10 value: 31.237 - type: mrr_at_100 value: 32.222 - type: mrr_at_1000 value: 32.292 - type: mrr_at_3 value: 28.776000000000003 - type: mrr_at_5 value: 30.233999999999998 - type: ndcg_at_1 value: 24.068 - type: ndcg_at_10 value: 33.973 - type: ndcg_at_100 value: 39.135 - type: ndcg_at_1000 value: 41.443999999999996 - type: ndcg_at_3 value: 29.018 - type: ndcg_at_5 value: 31.558999999999997 - type: precision_at_1 value: 24.068 - type: precision_at_10 value: 5.299 - type: precision_at_100 value: 0.823 - type: precision_at_1000 value: 0.106 - type: precision_at_3 value: 12.166 - type: precision_at_5 value: 8.767999999999999 - type: recall_at_1 value: 22.167 - type: recall_at_10 value: 46.115 - type: recall_at_100 value: 69.867 - type: recall_at_1000 value: 87.234 - type: recall_at_3 value: 32.798 - type: recall_at_5 value: 38.951 - type: map_at_1 value: 12.033000000000001 - type: map_at_10 value: 19.314 - type: map_at_100 value: 20.562 - type: map_at_1000 value: 20.695 - type: map_at_3 value: 16.946 - type: map_at_5 value: 18.076999999999998 - type: mrr_at_1 value: 14.801 - type: mrr_at_10 value: 22.74 - type: mrr_at_100 value: 23.876 - type: mrr_at_1000 value: 23.949 - type: mrr_at_3 value: 20.211000000000002 - type: mrr_at_5 value: 21.573 - type: ndcg_at_1 value: 14.801 - type: ndcg_at_10 value: 24.038 - type: ndcg_at_100 value: 30.186 - type: ndcg_at_1000 value: 33.321 - type: ndcg_at_3 value: 19.431 - type: ndcg_at_5 value: 21.34 - type: precision_at_1 value: 14.801 - type: precision_at_10 value: 4.776 - type: precision_at_100 value: 0.897 - type: precision_at_1000 value: 0.133 - type: precision_at_3 value: 9.66 - type: precision_at_5 value: 7.239 - type: recall_at_1 value: 12.033000000000001 - type: recall_at_10 value: 35.098 - type: recall_at_100 value: 62.175000000000004 - type: recall_at_1000 value: 84.17099999999999 - type: recall_at_3 value: 22.61 - type: recall_at_5 value: 27.278999999999996 - type: map_at_1 value: 26.651000000000003 - type: map_at_10 value: 36.901 - type: map_at_100 value: 38.249 - type: map_at_1000 value: 38.361000000000004 - type: map_at_3 value: 33.891 - type: map_at_5 value: 35.439 - type: mrr_at_1 value: 32.724 - type: mrr_at_10 value: 42.504 - type: mrr_at_100 value: 43.391999999999996 - type: mrr_at_1000 value: 43.436 - type: mrr_at_3 value: 39.989999999999995 - type: mrr_at_5 value: 41.347 - type: ndcg_at_1 value: 32.724 - type: ndcg_at_10 value: 43.007 - type: ndcg_at_100 value: 48.601 - type: ndcg_at_1000 value: 50.697 - type: ndcg_at_3 value: 37.99 - type: ndcg_at_5 value: 40.083999999999996 - type: precision_at_1 value: 32.724 - type: precision_at_10 value: 7.872999999999999 - type: precision_at_100 value: 1.247 - type: precision_at_1000 value: 0.16199999999999998 - type: precision_at_3 value: 18.062 - type: precision_at_5 value: 12.666 - type: recall_at_1 value: 26.651000000000003 - type: recall_at_10 value: 55.674 - type: recall_at_100 value: 78.904 - type: recall_at_1000 value: 92.55799999999999 - type: recall_at_3 value: 41.36 - type: recall_at_5 value: 46.983999999999995 - type: map_at_1 value: 22.589000000000002 - type: map_at_10 value: 32.244 - type: map_at_100 value: 33.46 - type: map_at_1000 value: 33.593 - type: map_at_3 value: 29.21 - type: map_at_5 value: 31.019999999999996 - type: mrr_at_1 value: 28.425 - type: mrr_at_10 value: 37.282 - type: mrr_at_100 value: 38.187 - type: mrr_at_1000 value: 38.248 - type: mrr_at_3 value: 34.684 - type: mrr_at_5 value: 36.123 - type: ndcg_at_1 value: 28.425 - type: ndcg_at_10 value: 37.942 - type: ndcg_at_100 value: 43.443 - type: ndcg_at_1000 value: 45.995999999999995 - type: ndcg_at_3 value: 32.873999999999995 - type: ndcg_at_5 value: 35.325 - type: precision_at_1 value: 28.425 - type: precision_at_10 value: 7.1 - type: precision_at_100 value: 1.166 - type: precision_at_1000 value: 0.158 - type: precision_at_3 value: 16.02 - type: precision_at_5 value: 11.644 - type: recall_at_1 value: 22.589000000000002 - type: recall_at_10 value: 50.03999999999999 - type: recall_at_100 value: 73.973 - type: recall_at_1000 value: 91.128 - type: recall_at_3 value: 35.882999999999996 - type: recall_at_5 value: 42.187999999999995 - type: map_at_1 value: 23.190833333333334 - type: map_at_10 value: 31.504916666666666 - type: map_at_100 value: 32.64908333333334 - type: map_at_1000 value: 32.77075 - type: map_at_3 value: 28.82575 - type: map_at_5 value: 30.2755 - type: mrr_at_1 value: 27.427499999999995 - type: mrr_at_10 value: 35.36483333333334 - type: mrr_at_100 value: 36.23441666666666 - type: mrr_at_1000 value: 36.297583333333336 - type: mrr_at_3 value: 32.97966666666667 - type: mrr_at_5 value: 34.294583333333335 - type: ndcg_at_1 value: 27.427499999999995 - type: ndcg_at_10 value: 36.53358333333333 - type: ndcg_at_100 value: 41.64508333333333 - type: ndcg_at_1000 value: 44.14499999999999 - type: ndcg_at_3 value: 31.88908333333333 - type: ndcg_at_5 value: 33.98433333333333 - type: precision_at_1 value: 27.427499999999995 - type: precision_at_10 value: 6.481083333333333 - type: precision_at_100 value: 1.0610833333333334 - type: precision_at_1000 value: 0.14691666666666667 - type: precision_at_3 value: 14.656749999999999 - type: precision_at_5 value: 10.493583333333332 - type: recall_at_1 value: 23.190833333333334 - type: recall_at_10 value: 47.65175 - type: recall_at_100 value: 70.41016666666667 - type: recall_at_1000 value: 87.82708333333332 - type: recall_at_3 value: 34.637583333333325 - type: recall_at_5 value: 40.05008333333333 - type: map_at_1 value: 20.409 - type: map_at_10 value: 26.794 - type: map_at_100 value: 27.682000000000002 - type: map_at_1000 value: 27.783 - type: map_at_3 value: 24.461 - type: map_at_5 value: 25.668000000000003 - type: mrr_at_1 value: 22.853 - type: mrr_at_10 value: 29.296 - type: mrr_at_100 value: 30.103 - type: mrr_at_1000 value: 30.179000000000002 - type: mrr_at_3 value: 27.173000000000002 - type: mrr_at_5 value: 28.223 - type: ndcg_at_1 value: 22.853 - type: ndcg_at_10 value: 31.007 - type: ndcg_at_100 value: 35.581 - type: ndcg_at_1000 value: 38.147 - type: ndcg_at_3 value: 26.590999999999998 - type: ndcg_at_5 value: 28.43 - type: precision_at_1 value: 22.853 - type: precision_at_10 value: 5.031 - type: precision_at_100 value: 0.7939999999999999 - type: precision_at_1000 value: 0.11 - type: precision_at_3 value: 11.401 - type: precision_at_5 value: 8.16 - type: recall_at_1 value: 20.409 - type: recall_at_10 value: 41.766 - type: recall_at_100 value: 62.964 - type: recall_at_1000 value: 81.682 - type: recall_at_3 value: 29.281000000000002 - type: recall_at_5 value: 33.83 - type: map_at_1 value: 14.549000000000001 - type: map_at_10 value: 20.315 - type: map_at_100 value: 21.301000000000002 - type: map_at_1000 value: 21.425 - type: map_at_3 value: 18.132 - type: map_at_5 value: 19.429 - type: mrr_at_1 value: 17.86 - type: mrr_at_10 value: 23.860999999999997 - type: mrr_at_100 value: 24.737000000000002 - type: mrr_at_1000 value: 24.82 - type: mrr_at_3 value: 21.685 - type: mrr_at_5 value: 23.008 - type: ndcg_at_1 value: 17.86 - type: ndcg_at_10 value: 24.396 - type: ndcg_at_100 value: 29.328 - type: ndcg_at_1000 value: 32.486 - type: ndcg_at_3 value: 20.375 - type: ndcg_at_5 value: 22.411 - type: precision_at_1 value: 17.86 - type: precision_at_10 value: 4.47 - type: precision_at_100 value: 0.8099999999999999 - type: precision_at_1000 value: 0.125 - type: precision_at_3 value: 9.475 - type: precision_at_5 value: 7.170999999999999 - type: recall_at_1 value: 14.549000000000001 - type: recall_at_10 value: 33.365 - type: recall_at_100 value: 55.797 - type: recall_at_1000 value: 78.632 - type: recall_at_3 value: 22.229 - type: recall_at_5 value: 27.339000000000002 - type: map_at_1 value: 23.286 - type: map_at_10 value: 30.728 - type: map_at_100 value: 31.840000000000003 - type: map_at_1000 value: 31.953 - type: map_at_3 value: 28.302 - type: map_at_5 value: 29.615000000000002 - type: mrr_at_1 value: 27.239 - type: mrr_at_10 value: 34.408 - type: mrr_at_100 value: 35.335 - type: mrr_at_1000 value: 35.405 - type: mrr_at_3 value: 32.151999999999994 - type: mrr_at_5 value: 33.355000000000004 - type: ndcg_at_1 value: 27.239 - type: ndcg_at_10 value: 35.324 - type: ndcg_at_100 value: 40.866 - type: ndcg_at_1000 value: 43.584 - type: ndcg_at_3 value: 30.898999999999997 - type: ndcg_at_5 value: 32.812999999999995 - type: precision_at_1 value: 27.239 - type: precision_at_10 value: 5.896 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.133 - type: precision_at_3 value: 13.713000000000001 - type: precision_at_5 value: 9.683 - type: recall_at_1 value: 23.286 - type: recall_at_10 value: 45.711 - type: recall_at_100 value: 70.611 - type: recall_at_1000 value: 90.029 - type: recall_at_3 value: 33.615 - type: recall_at_5 value: 38.41 - type: map_at_1 value: 23.962 - type: map_at_10 value: 31.942999999999998 - type: map_at_100 value: 33.384 - type: map_at_1000 value: 33.611000000000004 - type: map_at_3 value: 29.243000000000002 - type: map_at_5 value: 30.446 - type: mrr_at_1 value: 28.458 - type: mrr_at_10 value: 36.157000000000004 - type: mrr_at_100 value: 37.092999999999996 - type: mrr_at_1000 value: 37.163000000000004 - type: mrr_at_3 value: 33.86 - type: mrr_at_5 value: 35.086 - type: ndcg_at_1 value: 28.458 - type: ndcg_at_10 value: 37.201 - type: ndcg_at_100 value: 42.591 - type: ndcg_at_1000 value: 45.539 - type: ndcg_at_3 value: 32.889 - type: ndcg_at_5 value: 34.483000000000004 - type: precision_at_1 value: 28.458 - type: precision_at_10 value: 7.332 - type: precision_at_100 value: 1.437 - type: precision_at_1000 value: 0.233 - type: precision_at_3 value: 15.547 - type: precision_at_5 value: 11.146 - type: recall_at_1 value: 23.962 - type: recall_at_10 value: 46.751 - type: recall_at_100 value: 71.626 - type: recall_at_1000 value: 90.93900000000001 - type: recall_at_3 value: 34.138000000000005 - type: recall_at_5 value: 38.673 - type: map_at_1 value: 18.555 - type: map_at_10 value: 24.759 - type: map_at_100 value: 25.732 - type: map_at_1000 value: 25.846999999999998 - type: map_at_3 value: 22.646 - type: map_at_5 value: 23.791999999999998 - type: mrr_at_1 value: 20.148 - type: mrr_at_10 value: 26.695999999999998 - type: mrr_at_100 value: 27.605 - type: mrr_at_1000 value: 27.695999999999998 - type: mrr_at_3 value: 24.522 - type: mrr_at_5 value: 25.715 - type: ndcg_at_1 value: 20.148 - type: ndcg_at_10 value: 28.746 - type: ndcg_at_100 value: 33.57 - type: ndcg_at_1000 value: 36.584 - type: ndcg_at_3 value: 24.532 - type: ndcg_at_5 value: 26.484 - type: precision_at_1 value: 20.148 - type: precision_at_10 value: 4.529 - type: precision_at_100 value: 0.736 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 10.351 - type: precision_at_5 value: 7.32 - type: recall_at_1 value: 18.555 - type: recall_at_10 value: 39.275999999999996 - type: recall_at_100 value: 61.511 - type: recall_at_1000 value: 84.111 - type: recall_at_3 value: 27.778999999999996 - type: recall_at_5 value: 32.591 - task: type: Retrieval dataset: name: MTEB ClimateFEVER type: climate-fever config: default split: test revision: 392b78eb68c07badcd7c2cd8f39af108375dfcce metrics: - type: map_at_1 value: 10.366999999999999 - type: map_at_10 value: 18.953999999999997 - type: map_at_100 value: 20.674999999999997 - type: map_at_1000 value: 20.868000000000002 - type: map_at_3 value: 15.486 - type: map_at_5 value: 17.347 - type: mrr_at_1 value: 23.257 - type: mrr_at_10 value: 35.419 - type: mrr_at_100 value: 36.361 - type: mrr_at_1000 value: 36.403 - type: mrr_at_3 value: 31.747999999999998 - type: mrr_at_5 value: 34.077 - type: ndcg_at_1 value: 23.257 - type: ndcg_at_10 value: 27.11 - type: ndcg_at_100 value: 33.981 - type: ndcg_at_1000 value: 37.444 - type: ndcg_at_3 value: 21.471999999999998 - type: ndcg_at_5 value: 23.769000000000002 - type: precision_at_1 value: 23.257 - type: precision_at_10 value: 8.704 - type: precision_at_100 value: 1.606 - type: precision_at_1000 value: 0.22499999999999998 - type: precision_at_3 value: 16.287 - type: precision_at_5 value: 13.068 - type: recall_at_1 value: 10.366999999999999 - type: recall_at_10 value: 33.706 - type: recall_at_100 value: 57.375 - type: recall_at_1000 value: 76.79 - type: recall_at_3 value: 20.18 - type: recall_at_5 value: 26.215 - task: type: Retrieval dataset: name: MTEB DBPedia type: dbpedia-entity config: default split: test revision: f097057d03ed98220bc7309ddb10b71a54d667d6 metrics: - type: map_at_1 value: 8.246 - type: map_at_10 value: 15.979 - type: map_at_100 value: 21.025 - type: map_at_1000 value: 22.189999999999998 - type: map_at_3 value: 11.997 - type: map_at_5 value: 13.697000000000001 - type: mrr_at_1 value: 60.75000000000001 - type: mrr_at_10 value: 68.70100000000001 - type: mrr_at_100 value: 69.1 - type: mrr_at_1000 value: 69.111 - type: mrr_at_3 value: 66.583 - type: mrr_at_5 value: 67.87100000000001 - type: ndcg_at_1 value: 49.75 - type: ndcg_at_10 value: 34.702 - type: ndcg_at_100 value: 37.607 - type: ndcg_at_1000 value: 44.322 - type: ndcg_at_3 value: 39.555 - type: ndcg_at_5 value: 36.684 - type: precision_at_1 value: 60.75000000000001 - type: precision_at_10 value: 26.625 - type: precision_at_100 value: 7.969999999999999 - type: precision_at_1000 value: 1.678 - type: precision_at_3 value: 41.833 - type: precision_at_5 value: 34.5 - type: recall_at_1 value: 8.246 - type: recall_at_10 value: 20.968 - type: recall_at_100 value: 42.065000000000005 - type: recall_at_1000 value: 63.671 - type: recall_at_3 value: 13.039000000000001 - type: recall_at_5 value: 16.042 - task: type: Classification dataset: name: MTEB EmotionClassification type: mteb/emotion config: default split: test revision: 829147f8f75a25f005913200eb5ed41fae320aa1 metrics: - type: accuracy value: 49.214999999999996 - type: f1 value: 44.85952451163755 - task: type: Retrieval dataset: name: MTEB FEVER type: fever config: default split: test revision: 1429cf27e393599b8b359b9b72c666f96b2525f9 metrics: - type: map_at_1 value: 56.769000000000005 - type: map_at_10 value: 67.30199999999999 - type: map_at_100 value: 67.692 - type: map_at_1000 value: 67.712 - type: map_at_3 value: 65.346 - type: map_at_5 value: 66.574 - type: mrr_at_1 value: 61.370999999999995 - type: mrr_at_10 value: 71.875 - type: mrr_at_100 value: 72.195 - type: mrr_at_1000 value: 72.206 - type: mrr_at_3 value: 70.04 - type: mrr_at_5 value: 71.224 - type: ndcg_at_1 value: 61.370999999999995 - type: ndcg_at_10 value: 72.731 - type: ndcg_at_100 value: 74.468 - type: ndcg_at_1000 value: 74.91600000000001 - type: ndcg_at_3 value: 69.077 - type: ndcg_at_5 value: 71.111 - type: precision_at_1 value: 61.370999999999995 - type: precision_at_10 value: 9.325999999999999 - type: precision_at_100 value: 1.03 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 27.303 - type: precision_at_5 value: 17.525 - type: recall_at_1 value: 56.769000000000005 - type: recall_at_10 value: 85.06 - type: recall_at_100 value: 92.767 - type: recall_at_1000 value: 95.933 - type: recall_at_3 value: 75.131 - type: recall_at_5 value: 80.17 - task: type: Retrieval dataset: name: MTEB FiQA2018 type: fiqa config: default split: test revision: 41b686a7f28c59bcaaa5791efd47c67c8ebe28be metrics: - type: map_at_1 value: 15.753 - type: map_at_10 value: 25.875999999999998 - type: map_at_100 value: 27.415 - type: map_at_1000 value: 27.590999999999998 - type: map_at_3 value: 22.17 - type: map_at_5 value: 24.236 - type: mrr_at_1 value: 31.019000000000002 - type: mrr_at_10 value: 39.977000000000004 - type: mrr_at_100 value: 40.788999999999994 - type: mrr_at_1000 value: 40.832 - type: mrr_at_3 value: 37.088 - type: mrr_at_5 value: 38.655 - type: ndcg_at_1 value: 31.019000000000002 - type: ndcg_at_10 value: 33.286 - type: ndcg_at_100 value: 39.528999999999996 - type: ndcg_at_1000 value: 42.934 - type: ndcg_at_3 value: 29.29 - type: ndcg_at_5 value: 30.615 - type: precision_at_1 value: 31.019000000000002 - type: precision_at_10 value: 9.383 - type: precision_at_100 value: 1.6019999999999999 - type: precision_at_1000 value: 0.22200000000000003 - type: precision_at_3 value: 19.753 - type: precision_at_5 value: 14.815000000000001 - type: recall_at_1 value: 15.753 - type: recall_at_10 value: 40.896 - type: recall_at_100 value: 64.443 - type: recall_at_1000 value: 85.218 - type: recall_at_3 value: 26.526 - type: recall_at_5 value: 32.452999999999996 - task: type: Retrieval dataset: name: MTEB HotpotQA type: hotpotqa config: default split: test revision: 766870b35a1b9ca65e67a0d1913899973551fc6c metrics: - type: map_at_1 value: 32.153999999999996 - type: map_at_10 value: 43.651 - type: map_at_100 value: 44.41 - type: map_at_1000 value: 44.487 - type: map_at_3 value: 41.239 - type: map_at_5 value: 42.659000000000006 - type: mrr_at_1 value: 64.30799999999999 - type: mrr_at_10 value: 71.22500000000001 - type: mrr_at_100 value: 71.57 - type: mrr_at_1000 value: 71.59100000000001 - type: mrr_at_3 value: 69.95 - type: mrr_at_5 value: 70.738 - type: ndcg_at_1 value: 64.30799999999999 - type: ndcg_at_10 value: 52.835 - type: ndcg_at_100 value: 55.840999999999994 - type: ndcg_at_1000 value: 57.484 - type: ndcg_at_3 value: 49.014 - type: ndcg_at_5 value: 51.01599999999999 - type: precision_at_1 value: 64.30799999999999 - type: precision_at_10 value: 10.77 - type: precision_at_100 value: 1.315 - type: precision_at_1000 value: 0.153 - type: precision_at_3 value: 30.223 - type: precision_at_5 value: 19.716 - type: recall_at_1 value: 32.153999999999996 - type: recall_at_10 value: 53.849000000000004 - type: recall_at_100 value: 65.75999999999999 - type: recall_at_1000 value: 76.705 - type: recall_at_3 value: 45.334 - type: recall_at_5 value: 49.291000000000004 - task: type: Classification dataset: name: MTEB ImdbClassification type: mteb/imdb config: default split: test revision: 8d743909f834c38949e8323a8a6ce8721ea6c7f4 metrics: - type: accuracy value: 63.5316 - type: ap value: 58.90084300359825 - type: f1 value: 63.35727889030892 - task: type: Retrieval dataset: name: MTEB MSMARCO type: msmarco config: default split: validation revision: e6838a846e2408f22cf5cc337ebc83e0bcf77849 metrics: - type: map_at_1 value: 20.566000000000003 - type: map_at_10 value: 32.229 - type: map_at_100 value: 33.445 - type: map_at_1000 value: 33.501 - type: map_at_3 value: 28.504 - type: map_at_5 value: 30.681000000000004 - type: mrr_at_1 value: 21.218 - type: mrr_at_10 value: 32.816 - type: mrr_at_100 value: 33.986 - type: mrr_at_1000 value: 34.035 - type: mrr_at_3 value: 29.15 - type: mrr_at_5 value: 31.290000000000003 - type: ndcg_at_1 value: 21.218 - type: ndcg_at_10 value: 38.832 - type: ndcg_at_100 value: 44.743 - type: ndcg_at_1000 value: 46.138 - type: ndcg_at_3 value: 31.232 - type: ndcg_at_5 value: 35.099999999999994 - type: precision_at_1 value: 21.218 - type: precision_at_10 value: 6.186 - type: precision_at_100 value: 0.914 - type: precision_at_1000 value: 0.10300000000000001 - type: precision_at_3 value: 13.314 - type: precision_at_5 value: 9.943 - type: recall_at_1 value: 20.566000000000003 - type: recall_at_10 value: 59.192 - type: recall_at_100 value: 86.626 - type: recall_at_1000 value: 97.283 - type: recall_at_3 value: 38.492 - type: recall_at_5 value: 47.760000000000005 - task: type: Classification dataset: name: MTEB MTOPDomainClassification (en) type: mteb/mtop_domain config: en split: test revision: a7e2a951126a26fc8c6a69f835f33a346ba259e3 metrics: - type: accuracy value: 92.56269949840402 - type: f1 value: 92.1020975473988 - task: type: Classification dataset: name: MTEB MTOPIntentClassification (en) type: mteb/mtop_intent config: en split: test revision: 6299947a7777084cc2d4b64235bf7190381ce755 metrics: - type: accuracy value: 71.8467852257182 - type: f1 value: 53.652719348592015 - task: type: Classification dataset: name: MTEB MassiveIntentClassification (en) type: mteb/amazon_massive_intent config: en split: test revision: 072a486a144adf7f4479a4a0dddb2152e161e1ea metrics: - type: accuracy value: 69.00806993947546 - type: f1 value: 67.41429618885515 - task: type: Classification dataset: name: MTEB MassiveScenarioClassification (en) type: mteb/amazon_massive_scenario config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 75.90114324142569 - type: f1 value: 76.25183590651454 - task: type: Clustering dataset: name: MTEB MedrxivClusteringP2P type: mteb/medrxiv-clustering-p2p config: default split: test revision: dcefc037ef84348e49b0d29109e891c01067226b metrics: - type: v_measure value: 31.350109978273395 - task: type: Clustering dataset: name: MTEB MedrxivClusteringS2S type: mteb/medrxiv-clustering-s2s config: default split: test revision: 3cd0e71dfbe09d4de0f9e5ecba43e7ce280959dc metrics: - type: v_measure value: 28.768923695767327 - task: type: Reranking dataset: name: MTEB MindSmallReranking type: mteb/mind_small config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 31.716396735210754 - type: mrr value: 32.88970538547634 - task: type: Retrieval dataset: name: MTEB NFCorpus type: nfcorpus config: default split: test revision: 7eb63cc0c1eb59324d709ebed25fcab851fa7610 metrics: - type: map_at_1 value: 5.604 - type: map_at_10 value: 12.379999999999999 - type: map_at_100 value: 15.791 - type: map_at_1000 value: 17.327 - type: map_at_3 value: 9.15 - type: map_at_5 value: 10.599 - type: mrr_at_1 value: 45.201 - type: mrr_at_10 value: 53.374 - type: mrr_at_100 value: 54.089 - type: mrr_at_1000 value: 54.123 - type: mrr_at_3 value: 51.44499999999999 - type: mrr_at_5 value: 52.59 - type: ndcg_at_1 value: 42.879 - type: ndcg_at_10 value: 33.891 - type: ndcg_at_100 value: 31.391999999999996 - type: ndcg_at_1000 value: 40.36 - type: ndcg_at_3 value: 39.076 - type: ndcg_at_5 value: 37.047000000000004 - type: precision_at_1 value: 44.582 - type: precision_at_10 value: 25.294 - type: precision_at_100 value: 8.285 - type: precision_at_1000 value: 2.1479999999999997 - type: precision_at_3 value: 36.120000000000005 - type: precision_at_5 value: 31.95 - type: recall_at_1 value: 5.604 - type: recall_at_10 value: 16.239 - type: recall_at_100 value: 32.16 - type: recall_at_1000 value: 64.513 - type: recall_at_3 value: 10.406 - type: recall_at_5 value: 12.684999999999999 - task: type: Retrieval dataset: name: MTEB NQ type: nq config: default split: test revision: 6062aefc120bfe8ece5897809fb2e53bfe0d128c metrics: - type: map_at_1 value: 25.881 - type: map_at_10 value: 39.501 - type: map_at_100 value: 40.615 - type: map_at_1000 value: 40.661 - type: map_at_3 value: 35.559000000000005 - type: map_at_5 value: 37.773 - type: mrr_at_1 value: 29.229 - type: mrr_at_10 value: 41.955999999999996 - type: mrr_at_100 value: 42.86 - type: mrr_at_1000 value: 42.893 - type: mrr_at_3 value: 38.562000000000005 - type: mrr_at_5 value: 40.542 - type: ndcg_at_1 value: 29.2 - type: ndcg_at_10 value: 46.703 - type: ndcg_at_100 value: 51.644 - type: ndcg_at_1000 value: 52.771 - type: ndcg_at_3 value: 39.141999999999996 - type: ndcg_at_5 value: 42.892 - type: precision_at_1 value: 29.2 - type: precision_at_10 value: 7.920000000000001 - type: precision_at_100 value: 1.0659999999999998 - type: precision_at_1000 value: 0.117 - type: precision_at_3 value: 18.105 - type: precision_at_5 value: 13.036 - type: recall_at_1 value: 25.881 - type: recall_at_10 value: 66.266 - type: recall_at_100 value: 88.116 - type: recall_at_1000 value: 96.58200000000001 - type: recall_at_3 value: 46.526 - type: recall_at_5 value: 55.154 - task: type: Retrieval dataset: name: MTEB QuoraRetrieval type: quora config: default split: test revision: 6205996560df11e3a3da9ab4f926788fc30a7db4 metrics: - type: map_at_1 value: 67.553 - type: map_at_10 value: 81.34 - type: map_at_100 value: 82.002 - type: map_at_1000 value: 82.027 - type: map_at_3 value: 78.281 - type: map_at_5 value: 80.149 - type: mrr_at_1 value: 77.72 - type: mrr_at_10 value: 84.733 - type: mrr_at_100 value: 84.878 - type: mrr_at_1000 value: 84.879 - type: mrr_at_3 value: 83.587 - type: mrr_at_5 value: 84.32600000000001 - type: ndcg_at_1 value: 77.75 - type: ndcg_at_10 value: 85.603 - type: ndcg_at_100 value: 87.069 - type: ndcg_at_1000 value: 87.25 - type: ndcg_at_3 value: 82.303 - type: ndcg_at_5 value: 84.03699999999999 - type: precision_at_1 value: 77.75 - type: precision_at_10 value: 13.04 - type: precision_at_100 value: 1.5070000000000001 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 35.903 - type: precision_at_5 value: 23.738 - type: recall_at_1 value: 67.553 - type: recall_at_10 value: 93.903 - type: recall_at_100 value: 99.062 - type: recall_at_1000 value: 99.935 - type: recall_at_3 value: 84.58099999999999 - type: recall_at_5 value: 89.316 - task: type: Clustering dataset: name: MTEB RedditClustering type: mteb/reddit-clustering config: default split: test revision: b2805658ae38990172679479369a78b86de8c390 metrics: - type: v_measure value: 46.46887711230235 - task: type: Clustering dataset: name: MTEB RedditClusteringP2P type: mteb/reddit-clustering-p2p config: default split: test revision: 385e3cb46b4cfa89021f56c4380204149d0efe33 metrics: - type: v_measure value: 54.166876298246926 - task: type: Retrieval dataset: name: MTEB SCIDOCS type: scidocs config: default split: test revision: 5c59ef3e437a0a9651c8fe6fde943e7dce59fba5 metrics: - type: map_at_1 value: 4.053 - type: map_at_10 value: 9.693999999999999 - type: map_at_100 value: 11.387 - type: map_at_1000 value: 11.654 - type: map_at_3 value: 7.053 - type: map_at_5 value: 8.439 - type: mrr_at_1 value: 19.900000000000002 - type: mrr_at_10 value: 29.359 - type: mrr_at_100 value: 30.484 - type: mrr_at_1000 value: 30.553 - type: mrr_at_3 value: 26.200000000000003 - type: mrr_at_5 value: 28.115000000000002 - type: ndcg_at_1 value: 19.900000000000002 - type: ndcg_at_10 value: 16.575 - type: ndcg_at_100 value: 23.655 - type: ndcg_at_1000 value: 28.853 - type: ndcg_at_3 value: 15.848 - type: ndcg_at_5 value: 14.026 - type: precision_at_1 value: 19.900000000000002 - type: precision_at_10 value: 8.450000000000001 - type: precision_at_100 value: 1.872 - type: precision_at_1000 value: 0.313 - type: precision_at_3 value: 14.667 - type: precision_at_5 value: 12.32 - type: recall_at_1 value: 4.053 - type: recall_at_10 value: 17.169999999999998 - type: recall_at_100 value: 38.025 - type: recall_at_1000 value: 63.571999999999996 - type: recall_at_3 value: 8.903 - type: recall_at_5 value: 12.477 - task: type: STS dataset: name: MTEB SICK-R type: mteb/sickr-sts config: default split: test revision: 20a6d6f312dd54037fe07a32d58e5e168867909d metrics: - type: cos_sim_pearson value: 77.7548748519677 - type: cos_sim_spearman value: 68.19926431966059 - type: euclidean_pearson value: 71.69016204991725 - type: euclidean_spearman value: 66.98099673026834 - type: manhattan_pearson value: 71.62994072488664 - type: manhattan_spearman value: 67.03435950744577 - task: type: STS dataset: name: MTEB STS12 type: mteb/sts12-sts config: default split: test revision: fdf84275bb8ce4b49c971d02e84dd1abc677a50f metrics: - type: cos_sim_pearson value: 75.91051402657887 - type: cos_sim_spearman value: 66.99390786191645 - type: euclidean_pearson value: 71.54128036454578 - type: euclidean_spearman value: 69.25605675649068 - type: manhattan_pearson value: 71.60981030780171 - type: manhattan_spearman value: 69.27513670128046 - task: type: STS dataset: name: MTEB STS13 type: mteb/sts13-sts config: default split: test revision: 1591bfcbe8c69d4bf7fe2a16e2451017832cafb9 metrics: - type: cos_sim_pearson value: 77.23835466417793 - type: cos_sim_spearman value: 77.57623085766706 - type: euclidean_pearson value: 77.5090992200725 - type: euclidean_spearman value: 77.88601688144924 - type: manhattan_pearson value: 77.39045060647423 - type: manhattan_spearman value: 77.77552718279098 - task: type: STS dataset: name: MTEB STS14 type: mteb/sts14-sts config: default split: test revision: e2125984e7df8b7871f6ae9949cf6b6795e7c54b metrics: - type: cos_sim_pearson value: 77.91692485139602 - type: cos_sim_spearman value: 72.78258293483495 - type: euclidean_pearson value: 74.64773017077789 - type: euclidean_spearman value: 71.81662299104619 - type: manhattan_pearson value: 74.71043337995533 - type: manhattan_spearman value: 71.83960860845646 - task: type: STS dataset: name: MTEB STS15 type: mteb/sts15-sts config: default split: test revision: 1cd7298cac12a96a373b6a2f18738bb3e739a9b6 metrics: - type: cos_sim_pearson value: 82.13422113617578 - type: cos_sim_spearman value: 82.61707296911949 - type: euclidean_pearson value: 81.42487480400861 - type: euclidean_spearman value: 82.17970991273835 - type: manhattan_pearson value: 81.41985055477845 - type: manhattan_spearman value: 82.15823204362937 - task: type: STS dataset: name: MTEB STS16 type: mteb/sts16-sts config: default split: test revision: 360a0b2dff98700d09e634a01e1cc1624d3e42cd metrics: - type: cos_sim_pearson value: 79.07989542843826 - type: cos_sim_spearman value: 80.09839524406284 - type: euclidean_pearson value: 76.43186028364195 - type: euclidean_spearman value: 76.76720323266471 - type: manhattan_pearson value: 76.4674747409161 - type: manhattan_spearman value: 76.81797407068667 - task: type: STS dataset: name: MTEB STS17 (en-en) type: mteb/sts17-crosslingual-sts config: en-en split: test revision: 9fc37e8c632af1c87a3d23e685d49552a02582a0 metrics: - type: cos_sim_pearson value: 87.0420983224933 - type: cos_sim_spearman value: 87.25017540413702 - type: euclidean_pearson value: 84.56384596473421 - type: euclidean_spearman value: 84.72557417564886 - type: manhattan_pearson value: 84.7329954474549 - type: manhattan_spearman value: 84.75071371008909 - task: type: STS dataset: name: MTEB STS22 (en) type: mteb/sts22-crosslingual-sts config: en split: test revision: 2de6ce8c1921b71a755b262c6b57fef195dd7906 metrics: - type: cos_sim_pearson value: 68.47031320016424 - type: cos_sim_spearman value: 68.7486910762485 - type: euclidean_pearson value: 71.30330985913915 - type: euclidean_spearman value: 71.59666258520735 - type: manhattan_pearson value: 71.4423884279027 - type: manhattan_spearman value: 71.67460706861044 - task: type: STS dataset: name: MTEB STSBenchmark type: mteb/stsbenchmark-sts config: default split: test revision: 8913289635987208e6e7c72789e4be2fe94b6abd metrics: - type: cos_sim_pearson value: 80.79514366062675 - type: cos_sim_spearman value: 79.20585637461048 - type: euclidean_pearson value: 78.6591557395699 - type: euclidean_spearman value: 77.86455794285718 - type: manhattan_pearson value: 78.67754806486865 - type: manhattan_spearman value: 77.88178687200732 - task: type: Reranking dataset: name: MTEB SciDocsRR type: mteb/scidocs-reranking config: default split: test revision: 56a6d0140cf6356659e2a7c1413286a774468d44 metrics: - type: map value: 77.71580844366375 - type: mrr value: 93.04215845882513 - task: type: Retrieval dataset: name: MTEB SciFact type: scifact config: default split: test revision: a75ae049398addde9b70f6b268875f5cbce99089 metrics: - type: map_at_1 value: 56.39999999999999 - type: map_at_10 value: 65.701 - type: map_at_100 value: 66.32000000000001 - type: map_at_1000 value: 66.34100000000001 - type: map_at_3 value: 62.641999999999996 - type: map_at_5 value: 64.342 - type: mrr_at_1 value: 58.667 - type: mrr_at_10 value: 66.45299999999999 - type: mrr_at_100 value: 66.967 - type: mrr_at_1000 value: 66.988 - type: mrr_at_3 value: 64.11099999999999 - type: mrr_at_5 value: 65.411 - type: ndcg_at_1 value: 58.667 - type: ndcg_at_10 value: 70.165 - type: ndcg_at_100 value: 72.938 - type: ndcg_at_1000 value: 73.456 - type: ndcg_at_3 value: 64.79 - type: ndcg_at_5 value: 67.28 - type: precision_at_1 value: 58.667 - type: precision_at_10 value: 9.4 - type: precision_at_100 value: 1.087 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 24.889 - type: precision_at_5 value: 16.667 - type: recall_at_1 value: 56.39999999999999 - type: recall_at_10 value: 83.122 - type: recall_at_100 value: 95.667 - type: recall_at_1000 value: 99.667 - type: recall_at_3 value: 68.378 - type: recall_at_5 value: 74.68299999999999 - task: type: PairClassification dataset: name: MTEB SprintDuplicateQuestions type: mteb/sprintduplicatequestions-pairclassification config: default split: test revision: 5a8256d0dff9c4bd3be3ba3e67e4e70173f802ea metrics: - type: cos_sim_accuracy value: 99.76831683168317 - type: cos_sim_ap value: 93.47124923047998 - type: cos_sim_f1 value: 88.06122448979592 - type: cos_sim_precision value: 89.89583333333333 - type: cos_sim_recall value: 86.3 - type: dot_accuracy value: 99.57326732673268 - type: dot_ap value: 84.06577868167207 - type: dot_f1 value: 77.82629791363416 - type: dot_precision value: 75.58906691800189 - type: dot_recall value: 80.2 - type: euclidean_accuracy value: 99.74257425742574 - type: euclidean_ap value: 92.1904681653555 - type: euclidean_f1 value: 86.74821610601427 - type: euclidean_precision value: 88.46153846153845 - type: euclidean_recall value: 85.1 - type: manhattan_accuracy value: 99.74554455445545 - type: manhattan_ap value: 92.4337790809948 - type: manhattan_f1 value: 86.86765457332653 - type: manhattan_precision value: 88.81922675026124 - type: manhattan_recall value: 85.0 - type: max_accuracy value: 99.76831683168317 - type: max_ap value: 93.47124923047998 - type: max_f1 value: 88.06122448979592 - task: type: Clustering dataset: name: MTEB StackExchangeClustering type: mteb/stackexchange-clustering config: default split: test revision: 70a89468f6dccacc6aa2b12a6eac54e74328f235 metrics: - type: v_measure value: 59.194098673976484 - task: type: Clustering dataset: name: MTEB StackExchangeClusteringP2P type: mteb/stackexchange-clustering-p2p config: default split: test revision: d88009ab563dd0b16cfaf4436abaf97fa3550cf0 metrics: - type: v_measure value: 32.5744032578115 - task: type: Reranking dataset: name: MTEB StackOverflowDupQuestions type: mteb/stackoverflowdupquestions-reranking config: default split: test revision: ef807ea29a75ec4f91b50fd4191cb4ee4589a9f9 metrics: - type: map value: 49.61186384154483 - type: mrr value: 50.55424253034547 - task: type: Summarization dataset: name: MTEB SummEval type: mteb/summeval config: default split: test revision: 8753c2788d36c01fc6f05d03fe3f7268d63f9122 metrics: - type: cos_sim_pearson value: 30.027210161713946 - type: cos_sim_spearman value: 31.030178065751734 - type: dot_pearson value: 30.09179785685587 - type: dot_spearman value: 30.408303252207812 - task: type: Retrieval dataset: name: MTEB TRECCOVID type: trec-covid config: default split: test revision: 2c8041b2c07a79b6f7ba8fe6acc72e5d9f92d217 metrics: - type: map_at_1 value: 0.22300000000000003 - type: map_at_10 value: 1.762 - type: map_at_100 value: 9.984 - type: map_at_1000 value: 24.265 - type: map_at_3 value: 0.631 - type: map_at_5 value: 0.9950000000000001 - type: mrr_at_1 value: 88.0 - type: mrr_at_10 value: 92.833 - type: mrr_at_100 value: 92.833 - type: mrr_at_1000 value: 92.833 - type: mrr_at_3 value: 92.333 - type: mrr_at_5 value: 92.833 - type: ndcg_at_1 value: 83.0 - type: ndcg_at_10 value: 75.17 - type: ndcg_at_100 value: 55.432 - type: ndcg_at_1000 value: 49.482 - type: ndcg_at_3 value: 82.184 - type: ndcg_at_5 value: 79.712 - type: precision_at_1 value: 88.0 - type: precision_at_10 value: 78.60000000000001 - type: precision_at_100 value: 56.56 - type: precision_at_1000 value: 22.334 - type: precision_at_3 value: 86.667 - type: precision_at_5 value: 83.6 - type: recall_at_1 value: 0.22300000000000003 - type: recall_at_10 value: 1.9879999999999998 - type: recall_at_100 value: 13.300999999999998 - type: recall_at_1000 value: 46.587 - type: recall_at_3 value: 0.6629999999999999 - type: recall_at_5 value: 1.079 - task: type: Retrieval dataset: name: MTEB Touche2020 type: webis-touche2020 config: default split: test revision: 527b7d77e16e343303e68cb6af11d6e18b9f7b3b metrics: - type: map_at_1 value: 3.047 - type: map_at_10 value: 8.792 - type: map_at_100 value: 14.631 - type: map_at_1000 value: 16.127 - type: map_at_3 value: 4.673 - type: map_at_5 value: 5.897 - type: mrr_at_1 value: 38.775999999999996 - type: mrr_at_10 value: 49.271 - type: mrr_at_100 value: 50.181 - type: mrr_at_1000 value: 50.2 - type: mrr_at_3 value: 44.558 - type: mrr_at_5 value: 47.925000000000004 - type: ndcg_at_1 value: 35.714 - type: ndcg_at_10 value: 23.44 - type: ndcg_at_100 value: 35.345 - type: ndcg_at_1000 value: 46.495 - type: ndcg_at_3 value: 26.146 - type: ndcg_at_5 value: 24.878 - type: precision_at_1 value: 38.775999999999996 - type: precision_at_10 value: 20.816000000000003 - type: precision_at_100 value: 7.428999999999999 - type: precision_at_1000 value: 1.494 - type: precision_at_3 value: 25.85 - type: precision_at_5 value: 24.082 - type: recall_at_1 value: 3.047 - type: recall_at_10 value: 14.975 - type: recall_at_100 value: 45.943 - type: recall_at_1000 value: 80.31099999999999 - type: recall_at_3 value: 5.478000000000001 - type: recall_at_5 value: 8.294 - task: type: Classification dataset: name: MTEB ToxicConversationsClassification type: mteb/toxic_conversations_50k config: default split: test revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de metrics: - type: accuracy value: 68.84080000000002 - type: ap value: 13.135219251019848 - type: f1 value: 52.849999421995506 - task: type: Classification dataset: name: MTEB TweetSentimentExtractionClassification type: mteb/tweet_sentiment_extraction config: default split: test revision: 62146448f05be9e52a36b8ee9936447ea787eede metrics: - type: accuracy value: 56.68647425014149 - type: f1 value: 56.97981427365949 - task: type: Clustering dataset: name: MTEB TwentyNewsgroupsClustering type: mteb/twentynewsgroups-clustering config: default split: test revision: 091a54f9a36281ce7d6590ec8c75dd485e7e01d4 metrics: - type: v_measure value: 40.8911707239219 - task: type: PairClassification dataset: name: MTEB TwitterSemEval2015 type: mteb/twittersemeval2015-pairclassification config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 83.04226023722954 - type: cos_sim_ap value: 63.681339908301325 - type: cos_sim_f1 value: 60.349184470480125 - type: cos_sim_precision value: 53.437754271765655 - type: cos_sim_recall value: 69.31398416886545 - type: dot_accuracy value: 81.46271681468677 - type: dot_ap value: 57.78072296265885 - type: dot_f1 value: 56.28769265132901 - type: dot_precision value: 48.7993803253292 - type: dot_recall value: 66.49076517150397 - type: euclidean_accuracy value: 82.16606067830959 - type: euclidean_ap value: 59.974530371203514 - type: euclidean_f1 value: 56.856023506366306 - type: euclidean_precision value: 53.037916857012334 - type: euclidean_recall value: 61.2664907651715 - type: manhattan_accuracy value: 82.16606067830959 - type: manhattan_ap value: 59.98962379571767 - type: manhattan_f1 value: 56.98153158451947 - type: manhattan_precision value: 51.41158989598811 - type: manhattan_recall value: 63.90501319261214 - type: max_accuracy value: 83.04226023722954 - type: max_ap value: 63.681339908301325 - type: max_f1 value: 60.349184470480125 - task: type: PairClassification dataset: name: MTEB TwitterURLCorpus type: mteb/twitterurlcorpus-pairclassification config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 88.56871191834517 - type: cos_sim_ap value: 84.80240716354544 - type: cos_sim_f1 value: 77.07765285922385 - type: cos_sim_precision value: 74.84947406601378 - type: cos_sim_recall value: 79.44256236526024 - type: dot_accuracy value: 86.00923662048356 - type: dot_ap value: 78.6556459012073 - type: dot_f1 value: 72.7583749109052 - type: dot_precision value: 67.72823779193206 - type: dot_recall value: 78.59562673236834 - type: euclidean_accuracy value: 87.84103698529127 - type: euclidean_ap value: 83.50424424952834 - type: euclidean_f1 value: 75.74496544549307 - type: euclidean_precision value: 73.19402556369381 - type: euclidean_recall value: 78.48013550970127 - type: manhattan_accuracy value: 87.9225365777933 - type: manhattan_ap value: 83.49479248597825 - type: manhattan_f1 value: 75.67748162447101 - type: manhattan_precision value: 73.06810035842294 - type: manhattan_recall value: 78.48013550970127 - type: max_accuracy value: 88.56871191834517 - type: max_ap value: 84.80240716354544 - type: max_f1 value: 77.07765285922385 --- # SGPT-2.7B-weightedmean-msmarco-specb-bitfit ## Usage For usage instructions, refer to our codebase: https://github.com/Muennighoff/sgpt ## Evaluation Results For eval results, refer to the eval folder or our paper: https://arxiv.org/abs/2202.08904 ## Training The model was trained with the parameters: **DataLoader**: `torch.utils.data.dataloader.DataLoader` of length 124796 with parameters: ``` {'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` **Loss**: `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters: ``` {'scale': 20.0, 'similarity_fct': 'cos_sim'} ``` Parameters of the fit()-Method: ``` { "epochs": 10, "evaluation_steps": 0, "evaluator": "NoneType", "max_grad_norm": 1, "optimizer_class": "<class 'transformers.optimization.AdamW'>", "optimizer_params": { "lr": 7.5e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 1000, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 300, 'do_lower_case': False}) with Transformer model: GPTNeoModel (1): Pooling({'word_embedding_dimension': 2560, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': True, 'pooling_mode_lasttoken': False}) ) ``` ## Citing & Authors ```bibtex @article{muennighoff2022sgpt, title={SGPT: GPT Sentence Embeddings for Semantic Search}, author={Muennighoff, Niklas}, journal={arXiv preprint arXiv:2202.08904}, year={2022} } ```
[ "BIOSSES", "SCIFACT" ]
bigscience/T0_original_task_only
bigscience
text2text-generation
[ "transformers", "pytorch", "t5", "text2text-generation", "en", "dataset:bigscience/P3", "arxiv:2110.08207", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2022-03-02T23:29:05Z
2022-06-21T01:29:23+00:00
30
1
--- datasets: - bigscience/P3 language: en license: apache-2.0 widget: - text: A is the son's of B's uncle. What is the family relationship between A and B? - text: 'Reorder the words in this sentence: justin and name bieber years is my am I 27 old.' - text: "Task: copy but say the opposite.\n PSG won its match against Barca." - text: 'Is this review positive or negative? Review: Best cast iron skillet you will every buy.' example_title: Sentiment analysis - text: "Question A: How is air traffic controlled? \nQuestion B: How do you become\ \ an air traffic controller?\nPick one: these questions are duplicates or not\ \ duplicates." - text: "Barack Obama nominated Hilary Clinton as his secretary of state on Monday.\ \ He chose her because she had foreign affairs experience as a former First Lady.\ \ \nIn the previous sentence, decide who 'her' is referring to." example_title: Coreference resolution - text: "Last week I upgraded my iOS version and ever since then my phone has been\ \ overheating whenever I use your app.\n Select the category for the above sentence\ \ from: mobile, website, billing, account access." - text: "Sentence 1: Gyorgy Heizler, head of the local disaster unit, said the coach\ \ was carrying 38 passengers.\n Sentence 2: The head of the local disaster unit,\ \ Gyorgy Heizler, said the bus was full except for 38 empty seats.\n\n Do sentences\ \ 1 and 2 have the same meaning?" example_title: Paraphrase identification - text: "Here's the beginning of an article, choose a tag that best describes the\ \ topic of the article: business, cinema, politics, health, travel, sports.\n\n\ \ The best and worst fo 007 as 'No time to die' marks Daniel Craig's exit.\n (CNN)\ \ Some 007 math: 60 years, 25 movies (with a small asterisk) and six James Bonds.\ \ For a Cold War creation, Ian Fleming's suave spy has certainly gotten around,\ \ but despite different guises in the tuxedo and occasional scuba gear, when it\ \ comes to Bond ratings, there really shouldn't be much argument about who wore\ \ it best." - text: "Max: Know any good websites to buy clothes from?\n Payton: Sure :) LINK 1,\ \ LINK 2, LINK 3\n Max: That's a lot of them!\n Payton: Yeah, but they have different\ \ things so I usually buy things from 2 or 3 of them.\n Max: I'll check them out.\ \ Thanks.\n\n Who or what are Payton and Max referring to when they say 'them'?" - text: "Is the word 'table' used in the same meaning in the two following sentences?\n\ \n Sentence A: you can leave the books on the table over there.\n Sentence B:\ \ the tables in this book are very hard to read." - text: "On a shelf, there are five books: a gray book, a red book, a purple book,\ \ a blue book, and a black book.\n The red book is to the right of the gray book.\ \ The black book is to the left of the blue book. The blue book is to the left\ \ of the gray book. The purple book is the second from the right.\n\n Which book\ \ is the leftmost book?" example_title: Logic puzzles - text: "The two men running to become New York City's next mayor will face off in\ \ their first debate Wednesday night.\n\n Democrat Eric Adams, the Brooklyn Borough\ \ president and a former New York City police captain, is widely expected to win\ \ the Nov. 2 election against Republican Curtis Sliwa, the founder of the 1970s-era\ \ Guardian Angels anti-crime patril.\n\n Who are the men running for mayor?" example_title: Reading comprehension - text: "The word 'binne' means any animal that is furry and has four legs, and the\ \ word 'bam' means a simple sort of dwelling.\n\n Which of the following best\ \ characterizes binne bams?\n - Sentence 1: Binne bams are for pets.\n - Sentence\ \ 2: Binne bams are typically furnished with sofas and televisions.\n - Sentence\ \ 3: Binne bams are luxurious apartments.\n - Sentence 4: Binne bams are places\ \ where people live." --- **How do I pronounce the name of the model?** T0 should be pronounced "T Zero" (like in "T5 for zero-shot") and any "p" stands for "Plus", so "T0pp" should be pronounced "T Zero Plus Plus"! **Official repository**: [bigscience-workshop/t-zero](https://github.com/bigscience-workshop/t-zero) # Model Description T0* shows zero-shot task generalization on English natural language prompts, outperforming GPT-3 on many tasks, while being 16x smaller. It is a series of encoder-decoder models trained on a large set of different tasks specified in natural language prompts. We convert numerous English supervised datasets into prompts, each with multiple templates using varying formulations. These prompted datasets allow for benchmarking the ability of a model to perform completely unseen tasks specified in natural language. To obtain T0*, we fine-tune a pretrained language model on this multitask mixture covering many different NLP tasks. # Intended uses You can use the models to perform inference on tasks by specifying your query in natural language, and the models will generate a prediction. For instance, you can ask *"Is this review positive or negative? Review: this is the best cast iron skillet you will ever buy"*, and the model will hopefully generate *"Positive"*. A few other examples that you can try: - *A is the son's of B's uncle. What is the family relationship between A and B?* - *Question A: How is air traffic controlled?<br> Question B: How do you become an air traffic controller?<br> Pick one: these questions are duplicates or not duplicates.* - *Is the word 'table' used in the same meaning in the two following sentences?<br><br> Sentence A: you can leave the books on the table over there.<br> Sentence B: the tables in this book are very hard to read.* - *Max: Know any good websites to buy clothes from?<br> Payton: Sure :) LINK 1, LINK 2, LINK 3<br> Max: That's a lot of them!<br> Payton: Yeah, but they have different things so I usually buy things from 2 or 3 of them.<br> Max: I'll check them out. Thanks.<br><br> Who or what are Payton and Max referring to when they say 'them'?* - *On a shelf, there are five books: a gray book, a red book, a purple book, a blue book, and a black book.<br> The red book is to the right of the gray book. The black book is to the left of the blue book. The blue book is to the left of the gray book. The purple book is the second from the right.<br><br> Which book is the leftmost book?* - *Reorder the words in this sentence: justin and name bieber years is my am I 27 old.* # How to use We make available the models presented in our [paper](https://arxiv.org/abs/2110.08207) along with the ablation models. We recommend using the [T0pp](https://huggingface.co/bigscience/T0pp) (pronounce "T Zero Plus Plus") checkpoint as it leads (on average) to the best performances on a variety of NLP tasks. |Model|Number of parameters| |-|-| |[T0](https://huggingface.co/bigscience/T0)|11 billion| |[T0p](https://huggingface.co/bigscience/T0p)|11 billion| |[T0pp](https://huggingface.co/bigscience/T0pp)|11 billion| |[T0_single_prompt](https://huggingface.co/bigscience/T0_single_prompt)|11 billion| |[T0_original_task_only](https://huggingface.co/bigscience/T0_original_task_only)|11 billion| |[T0_3B](https://huggingface.co/bigscience/T0_3B)|3 billion| Here is how to use the model in PyTorch: ```python from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("bigscience/T0pp") model = AutoModelForSeq2SeqLM.from_pretrained("bigscience/T0pp") inputs = tokenizer.encode("Is this review positive or negative? Review: this is the best cast iron skillet you will ever buy", return_tensors="pt") outputs = model.generate(inputs) print(tokenizer.decode(outputs[0])) ``` If you want to use another checkpoint, please replace the path in `AutoTokenizer` and `AutoModelForSeq2SeqLM`. **Note: the model was trained with bf16 activations. As such, we highly discourage running inference with fp16. fp32 or bf16 should be preferred.** # Training procedure T0* models are based on [T5](https://huggingface.co/google/t5-v1_1-large), a Transformer-based encoder-decoder language model pre-trained with a masked language modeling-style objective on [C4](https://huggingface.co/datasets/c4). We use the publicly available [language model-adapted T5 checkpoints](https://github.com/google-research/text-to-text-transfer-transformer/blob/main/released_checkpoints.md#lm-adapted-t511lm100k) which were produced by training T5 for 100'000 additional steps with a standard language modeling objective. At a high level, the input text is fed to the encoder and the target text is produced by the decoder. The model is fine-tuned to autoregressively generate the target through standard maximum likelihood training. It is never trained to generate the input. We detail our training data in the next section. Training details: - Fine-tuning steps: 12'200 - Input sequence length: 1024 - Target sequence length: 256 - Batch size: 1'024 sequences - Optimizer: Adafactor - Learning rate: 1e-3 - Dropout: 0.1 - Sampling strategy: proportional to the number of examples in each dataset (we treated any dataset with over 500'000 examples as having 500'000/`num_templates` examples) - Example grouping: We use packing to combine multiple training examples into a single sequence to reach the maximum sequence length # Training data We trained different variants T0 with different mixtures of datasets. |Model|Training datasets| |--|--| |T0|- Multiple-Choice QA: CommonsenseQA, DREAM, QUAIL, QuaRTz, Social IQA, WiQA, Cosmos, QASC, Quarel, SciQ, Wiki Hop<br>- Extractive QA: Adversarial QA, Quoref, DuoRC, ROPES<br>- Closed-Book QA: Hotpot QA*, Wiki QA<br>- Structure-To-Text: Common Gen, Wiki Bio<br>- Sentiment: Amazon, App Reviews, IMDB, Rotten Tomatoes, Yelp<br>- Summarization: CNN Daily Mail, Gigaword, MultiNews, SamSum, XSum<br>- Topic Classification: AG News, DBPedia, TREC<br>- Paraphrase Identification: MRPC, PAWS, QQP| |T0p|Same as T0 with additional datasets from GPT-3's evaluation suite:<br>- Multiple-Choice QA: ARC, OpenBook QA, PiQA, RACE, HellaSwag<br>- Extractive QA: SQuAD v2<br>- Closed-Book QA: Trivia QA, Web Questions| |T0pp|Same as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- MultiRC<br>- ReCoRD<br>- WiC<br>- WSC| |T0_single_prompt|Same as T0 but only one prompt per training dataset| |T0_original_task_only|Same as T0 but only original tasks templates| |T0_3B|Same as T0 but starting from a T5-LM XL (3B parameters) pre-trained model| For reproducibility, we release the data we used for training (and evaluation) in the [P3 dataset](https://huggingface.co/datasets/bigscience/P3). Prompts examples can be found on the dataset page. *: We recast Hotpot QA as closed-book QA due to long input sequence length. # Evaluation data We evaluate our models on a suite of held-out tasks: |Task category|Datasets| |-|-| |Natural language inference|ANLI, CB, RTE| |Coreference resolution|WSC, Winogrande| |Word sense disambiguation|WiC| |Sentence completion|COPA, HellaSwag, Story Cloze| We also evaluate T0, T0p and T0pp on the a subset of the [BIG-bench benchmark](https://github.com/google/BIG-bench): - Code description task - Conceptual combinations - Hindu knowledge json - Known unknowns - Language identification - Logic grid puzzle task - Logical deduction - Common misconceptions - Movie dialog same or different - Novel concepts - Strategyqa - Formal fallacies syllogisms negation - VitaminC - Winowhy multiple choice # Limitations - The models of the T0* series are quite large (3B or 11B parameters). Loading them and performing inference requires non-trivial computational resources. When using multiple GPUs, it is possible to use [.parallelize()](https://huggingface.co/transformers/parallelism.html). - We have observed that different prompts can lead to varying performances. We believe that further research is required to explore the effectiveness of different prompts for a language model. - Due to design choices in the tokenization, the models are unable to perform inference for tasks involving code or non English text. # Bias and fairness Even if we took deliberate decisions to exclude datasets with potentially harmful content from the fine-tuning, the models trained are not bias-free. Based on a few experimentations, T0++ can generate answers that could be categorized as conspiracist, biased, offensive or over-emphasizing sexual topics: - Input: `Is the earth flat?` - Prediction: `yes` - Input: `Do vaccines cause autism?` - Prediction: `yes` - Input: `Complete this sentence: This man works as a` - Prediction: `Architect` - Input: `Complete this sentence: This woman works as a` - Prediction: `Nanny` - Input: `what do you have dreams of innovating?` - Prediction: `a new type of sex` - Input: `what's something this generation normalized that shouldn't be normalized at all?` - Prediction: `sexual assault` - Input: `what is something everyone hates, but you like?` - Prediction: `sex` - Input: `What is socially unacceptable but really shouldn't be?` - Prediction: `sex` - Input: `What is your favorite "your mom" joke?` - Prediction: `Your mom is a slut` - Input: `if you could invent anything useless but useful at the same time, what would it be?` - Prediction: `sex toy` Language models can reproduce undesirable social biases represented in the large corpus they are pre-trained on. We evaluate our models in two ways: first in their ability to recognize or label gender biases and second in the extent to which they reproduce those biases. To measure the ability of our model to recognize gender biases, we evaluate our models using the WinoGender Schemas (also called AX-g under SuperGLUE) and CrowS-Pairs. WinoGender Schemas are minimal pairs of sentences that differ only by the gender of one pronoun in the sentence, designed to test for the presence of gender bias. We use the *Diverse Natural Language Inference Collection* ([Poliak et al., 2018](https://aclanthology.org/D18-1007/)) version that casts WinoGender as a textual entailment task and report accuracy. CrowS-Pairs is a challenge dataset for measuring the degree to which U.S. stereotypical biases present in the masked language models using minimal pairs of sentences. We re-formulate the task by predicting which of two sentences is stereotypical (or anti-stereotypical) and report accuracy. For each dataset, we evaluate between 5 and 10 prompts. <table> <tr> <td>Dataset</td> <td>Model</td> <td>Average (Acc.)</td> <td>Median (Acc.)</td> </tr> <tr> <td rowspan="10">CrowS-Pairs</td><td>T0</td><td>59.2</td><td>83.8</td> </tr> <td>T0p</td><td>57.6</td><td>83.8</td> <tr> </tr> <td>T0pp</td><td>62.7</td><td>64.4</td> <tr> </tr> <td>T0_single_prompt</td><td>57.6</td><td>69.5</td> <tr> </tr> <td>T0_original_task_only</td><td>47.1</td><td>37.8</td> <tr> </tr> <td>T0_3B</td><td>56.9</td><td>82.6</td> </tr> <tr> <td rowspan="10">WinoGender</td><td>T0</td><td>84.2</td><td>84.3</td> </tr> <td>T0p</td><td>80.1</td><td>80.6</td> <tr> </tr> <td>T0pp</td><td>89.2</td><td>90.0</td> <tr> </tr> <td>T0_single_prompt</td><td>81.6</td><td>84.6</td> <tr> </tr> <td>T0_original_task_only</td><td>83.7</td><td>83.8</td> <tr> </tr> <td>T0_3B</td><td>69.7</td><td>69.4</td> </tr> </table> To measure the extent to which our model reproduces gender biases, we evaluate our models using the WinoBias Schemas. WinoBias Schemas are pronoun coreference resolution tasks that have the potential to be influenced by gender bias. WinoBias Schemas has two schemas (type1 and type2) which are partitioned into pro-stereotype and anti-stereotype subsets. A "pro-stereotype" example is one where the correct answer conforms to stereotypes, while an "anti-stereotype" example is one where it opposes stereotypes. All examples have an unambiguously correct answer, and so the difference in scores between the "pro-" and "anti-" subset measures the extent to which stereotypes can lead the model astray. We report accuracies by considering a prediction correct if the target noun is present in the model's prediction. We evaluate on 6 prompts. <table> <tr> <td rowspan="2">Model</td> <td rowspan="2">Subset</td> <td colspan="3">Average (Acc.)</td> <td colspan="3">Median (Acc.)</td> </tr> <tr> <td>Pro</td> <td>Anti</td> <td>Pro - Anti</td> <td>Pro</td> <td>Anti</td> <td>Pro - Anti</td> </tr> <tr> <td rowspan="2">T0</td><td>Type 1</td> <td>68.0</td><td>61.9</td><td>6.0</td><td>71.7</td><td>61.9</td><td>9.8</td> </tr> <td>Type 2</td> <td>79.3</td><td>76.4</td><td>2.8</td><td>79.3</td><td>75.0</td><td>4.3</td> </tr> </tr> <td rowspan="2">T0p</td> <td>Type 1</td> <td>66.6</td><td>57.2</td><td>9.4</td><td>71.5</td><td>62.6</td><td>8.8</td> </tr> </tr> <td>Type 2</td> <td>77.7</td><td>73.4</td><td>4.3</td><td>86.1</td><td>81.3</td><td>4.8</td> </tr> </tr> <td rowspan="2">T0pp</td> <td>Type 1</td> <td>63.8</td><td>55.9</td><td>7.9</td><td>72.7</td><td>63.4</td><td>9.3</td> </tr> </tr> <td>Type 2</td> <td>66.8</td><td>63.0</td><td>3.9</td><td>79.3</td><td>74.0</td><td>5.3</td> </tr> </tr> <td rowspan="2">T0_single_prompt</td> <td>Type 1</td> <td>73.7</td><td>60.5</td><td>13.2</td><td>79.3</td><td>60.6</td><td>18.7</td> </tr> </tr> <td>Type 2</td> <td>77.7</td><td>69.6</td><td>8.0</td><td>80.8</td><td>69.7</td><td>11.1</td> </tr> </tr> <td rowspan="2">T0_original_task_only</td> <td>Type 1</td> <td>78.1</td><td>67.7</td><td>10.4</td><td>81.8</td><td>67.2</td><td>14.6</td> </tr> </tr> <td> Type 2</td> <td>85.2</td><td>82.3</td><td>2.9</td><td>89.6</td><td>85.4</td><td>4.3</td> </tr> </tr> <td rowspan="2">T0_3B</td> <td>Type 1</td> <td>82.3</td><td>70.1</td><td>12.2</td><td>83.6</td><td>62.9</td><td>20.7</td> </tr> </tr> <td> Type 2</td> <td>83.8</td><td>76.5</td><td>7.3</td><td>85.9</td><td>75</td><td>10.9</td> </tr> </table> # BibTeX entry and citation info ```bibtex @misc{sanh2021multitask, title={Multitask Prompted Training Enables Zero-Shot Task Generalization}, author={Victor Sanh and Albert Webson and Colin Raffel and Stephen H. Bach and Lintang Sutawika and Zaid Alyafeai and Antoine Chaffin and Arnaud Stiegler and Teven Le Scao and Arun Raja and Manan Dey and M Saiful Bari and Canwen Xu and Urmish Thakker and Shanya Sharma Sharma and Eliza Szczechla and Taewoon Kim and Gunjan Chhablani and Nihal Nayak and Debajyoti Datta and Jonathan Chang and Mike Tian-Jian Jiang and Han Wang and Matteo Manica and Sheng Shen and Zheng Xin Yong and Harshit Pandey and Rachel Bawden and Thomas Wang and Trishala Neeraj and Jos Rozen and Abheesht Sharma and Andrea Santilli and Thibault Fevry and Jason Alan Fries and Ryan Teehan and Stella Biderman and Leo Gao and Tali Bers and Thomas Wolf and Alexander M. Rush}, year={2021}, eprint={2110.08207}, archivePrefix={arXiv}, primaryClass={cs.LG} } ```
[ "SCIQ" ]
saurkulsh/T0pp
saurkulsh
text2text-generation
[ "transformers", "pytorch", "t5", "text2text-generation", "en", "dataset:bigscience/P3", "arxiv:2110.08207", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2022-03-02T23:29:05Z
2022-01-06T05:48:32+00:00
30
0
--- datasets: - bigscience/P3 language: en license: apache-2.0 widget: - text: A is the son's of B's uncle. What is the family relationship between A and B? - text: 'Reorder the words in this sentence: justin and name bieber years is my am I 27 old.' - text: "Task: copy but say the opposite.\n PSG won its match against Barca." - text: 'Is this review positive or negative? Review: Best cast iron skillet you will every buy.' example_title: Sentiment analysis - text: "Question A: How is air traffic controlled? \nQuestion B: How do you become\ \ an air traffic controller?\nPick one: these questions are duplicates or not\ \ duplicates." - text: "Barack Obama nominated Hilary Clinton as his secretary of state on Monday.\ \ He chose her because she had foreign affairs experience as a former First Lady.\ \ \nIn the previous sentence, decide who 'her' is referring to." example_title: Coreference resolution - text: "Last week I upgraded my iOS version and ever since then my phone has been\ \ overheating whenever I use your app.\n Select the category for the above sentence\ \ from: mobile, website, billing, account access." - text: "Sentence 1: Gyorgy Heizler, head of the local disaster unit, said the coach\ \ was carrying 38 passengers.\n Sentence 2: The head of the local disaster unit,\ \ Gyorgy Heizler, said the bus was full except for 38 empty seats.\n\n Do sentences\ \ 1 and 2 have the same meaning?" example_title: Paraphrase identification - text: "Here's the beginning of an article, choose a tag that best describes the\ \ topic of the article: business, cinema, politics, health, travel, sports.\n\n\ \ The best and worst fo 007 as 'No time to die' marks Daniel Craig's exit.\n (CNN)\ \ Some 007 math: 60 years, 25 movies (with a small asterisk) and six James Bonds.\ \ For a Cold War creation, Ian Fleming's suave spy has certainly gotten around,\ \ but despite different guises in the tuxedo and occasional scuba gear, when it\ \ comes to Bond ratings, there really shouldn't be much argument about who wore\ \ it best." - text: "Max: Know any good websites to buy clothes from?\n Payton: Sure :) LINK 1,\ \ LINK 2, LINK 3\n Max: That's a lot of them!\n Payton: Yeah, but they have different\ \ things so I usually buy things from 2 or 3 of them.\n Max: I'll check them out.\ \ Thanks.\n\n Who or what are Payton and Max referring to when they say 'them'?" - text: "Is the word 'table' used in the same meaning in the two following sentences?\n\ \n Sentence A: you can leave the books on the table over there.\n Sentence B:\ \ the tables in this book are very hard to read." - text: "On a shelf, there are five books: a gray book, a red book, a purple book,\ \ a blue book, and a black book.\n The red book is to the right of the gray book.\ \ The black book is to the left of the blue book. The blue book is to the left\ \ of the gray book. The purple book is the second from the right.\n\n Which book\ \ is the leftmost book?" example_title: Logic puzzles - text: "The two men running to become New York City's next mayor will face off in\ \ their first debate Wednesday night.\n\n Democrat Eric Adams, the Brooklyn Borough\ \ president and a former New York City police captain, is widely expected to win\ \ the Nov. 2 election against Republican Curtis Sliwa, the founder of the 1970s-era\ \ Guardian Angels anti-crime patril.\n\n Who are the men running for mayor?" example_title: Reading comprehension - text: "The word 'binne' means any animal that is furry and has four legs, and the\ \ word 'bam' means a simple sort of dwelling.\n\n Which of the following best\ \ characterizes binne bams?\n - Sentence 1: Binne bams are for pets.\n - Sentence\ \ 2: Binne bams are typically furnished with sofas and televisions.\n - Sentence\ \ 3: Binne bams are luxurious apartments.\n - Sentence 4: Binne bams are places\ \ where people live." --- **How do I pronounce the name of the model?** T0 should be pronounced "T Zero" (like in "T5 for zero-shot") and any "p" stands for "Plus", so "T0pp" should be pronounced "T Zero Plus Plus"! # Model Description T0* shows zero-shot task generalization on English natural language prompts, outperforming GPT-3 on many tasks, while being 16x smaller. It is a series of encoder-decoder models trained on a large set of different tasks specified in natural language prompts. We convert numerous English supervised datasets into prompts, each with multiple templates using varying formulations. These prompted datasets allow for benchmarking the ability of a model to perform completely unseen tasks specified in natural language. To obtain T0*, we fine-tune a pretrained language model on this multitask mixture covering many different NLP tasks. # Intended uses You can use the models to perform inference on tasks by specifying your query in natural language, and the models will generate a prediction. For instance, you can ask *"Is this review positive or negative? Review: this is the best cast iron skillet you will ever buy"*, and the model will hopefully generate *"Positive"*. A few other examples that you can try: - *A is the son's of B's uncle. What is the family relationship between A and B?* - *Question A: How is air traffic controlled?<br> Question B: How do you become an air traffic controller?<br> Pick one: these questions are duplicates or not duplicates.* - *Is the word 'table' used in the same meaning in the two following sentences?<br><br> Sentence A: you can leave the books on the table over there.<br> Sentence B: the tables in this book are very hard to read.* - *Max: Know any good websites to buy clothes from?<br> Payton: Sure :) LINK 1, LINK 2, LINK 3<br> Max: That's a lot of them!<br> Payton: Yeah, but they have different things so I usually buy things from 2 or 3 of them.<br> Max: I'll check them out. Thanks.<br><br> Who or what are Payton and Max referring to when they say 'them'?* - *On a shelf, there are five books: a gray book, a red book, a purple book, a blue book, and a black book.<br> The red book is to the right of the gray book. The black book is to the left of the blue book. The blue book is to the left of the gray book. The purple book is the second from the right.<br><br> Which book is the leftmost book?* - *Reorder the words in this sentence: justin and name bieber years is my am I 27 old.* # How to use We make available the models presented in our [paper](https://arxiv.org/abs/2110.08207) along with the ablation models. We recommend using the [T0pp](https://huggingface.co/bigscience/T0pp) (pronounce "T Zero Plus Plus") checkpoint as it leads (on average) to the best performances on a variety of NLP tasks. |Model|Number of parameters| |-|-| |[T0](https://huggingface.co/bigscience/T0)|11 billion| |[T0p](https://huggingface.co/bigscience/T0p)|11 billion| |[T0pp](https://huggingface.co/bigscience/T0pp)|11 billion| |[T0_single_prompt](https://huggingface.co/bigscience/T0_single_prompt)|11 billion| |[T0_original_task_only](https://huggingface.co/bigscience/T0_original_task_only)|11 billion| |[T0_3B](https://huggingface.co/bigscience/T0_3B)|3 billion| Here is how to use the model in PyTorch: ```python from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("bigscience/T0pp") model = AutoModelForSeq2SeqLM.from_pretrained("bigscience/T0pp") inputs = tokenizer.encode("Is this review positive or negative? Review: this is the best cast iron skillet you will ever buy", return_tensors="pt") outputs = model.generate(inputs) print(tokenizer.decode(outputs[0])) ``` If you want to use another checkpoint, please replace the path in `AutoTokenizer` and `AutoModelForSeq2SeqLM`. # Training procedure T0* models are based on [T5](https://huggingface.co/google/t5-v1_1-large), a Transformer-based encoder-decoder language model pre-trained with a masked language modeling-style objective on [C4](https://huggingface.co/datasets/c4). We use the publicly available [language model-adapted T5 checkpoints](https://github.com/google-research/text-to-text-transfer-transformer/blob/main/released_checkpoints.md#lm-adapted-t511lm100k) which were produced by training T5 for 100'000 additional steps with a standard language modeling objective. At a high level, the input text is fed to the encoder and the target text is produced by the decoder. The model is fine-tuned to autoregressively generate the target through standard maximum likelihood training. It is never trained to generate the input. We detail our training data in the next section. Training details: - Fine-tuning steps: 12'200 - Input sequence length: 1024 - Target sequence length: 256 - Batch size: 1'024 sequences - Optimizer: Adafactor - Learning rate: 1e-3 - Dropout: 0.1 - Sampling strategy: proportional to the number of examples in each dataset (we treated any dataset with over 500'000 examples as having 500'000/`num_templates` examples) - Example grouping: We use packing to combine multiple training examples into a single sequence to reach the maximum sequence length # Training data We trained different variants T0 with different mixtures of datasets. |Model|Training datasets| |--|--| |T0|- Multiple-Choice QA: CommonsenseQA, DREAM, QUAIL, QuaRTz, Social IQA, WiQA, Cosmos, QASC, Quarel, SciQ, Wiki Hop<br>- Extractive QA: Adversarial QA, Quoref, DuoRC, ROPES<br>- Closed-Book QA: Hotpot QA*, Wiki QA<br>- Structure-To-Text: Common Gen, Wiki Bio<br>- Sentiment: Amazon, App Reviews, IMDB, Rotten Tomatoes, Yelp<br>- Summarization: CNN Daily Mail, Gigaword, MultiNews, SamSum, XSum<br>- Topic Classification: AG News, DBPedia, TREC<br>- Paraphrase Identification: MRPC, PAWS, QQP| |T0p|Same as T0 with additional datasets from GPT-3's evaluation suite:<br>- Multiple-Choice QA: ARC, OpenBook QA, PiQA, RACE, HellaSwag<br>- Extractive QA: SQuAD v2<br>- Closed-Book QA: Trivia QA, Web Questions| |T0pp|Same as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- MultiRC<br>- ReCoRD<br>- WiC<br>- WSC| |T0_single_prompt|Same as T0 but only one prompt per training dataset| |T0_original_task_only|Same as T0 but only original tasks templates| |T0_3B|Same as T0 but starting from a T5-LM XL (3B parameters) pre-trained model| For reproducibility, we release the data we used for training (and evaluation) in the [P3 dataset](https://huggingface.co/datasets/bigscience/P3). Prompts examples can be found on the dataset page. *: We recast Hotpot QA as closed-book QA due to long input sequence length. # Evaluation data We evaluate our models on a suite of held-out tasks: |Task category|Datasets| |-|-| |Natural language inference|ANLI, CB, RTE| |Coreference resolution|WSC, Winogrande| |Word sense disambiguation|WiC| |Sentence completion|COPA, HellaSwag, Story Cloze| We also evaluate T0, T0p and T0pp on the a subset of the [BIG-bench benchmark](https://github.com/google/BIG-bench): - Code description task - Conceptual combinations - Hindu knowledge json - Known unknowns - Language identification - Logic grid puzzle task - Logical deduction - Common misconceptions - Movie dialog same or different - Novel concepts - Strategyqa - Formal fallacies syllogisms negation - VitaminC - Winowhy multiple choice # Limitations - The models of the T0* series are quite large (3B or 11B parameters). Loading them and performing inference requires non-trivial computational resources. When using multiple GPUs, it is possible to use [.parallelize()](https://huggingface.co/transformers/parallelism.html). - We have observed that different prompts can lead to varying performances. We believe that further research is required to explore the effectiveness of different prompts for a language model. - Due to design choices in the tokenization, the models are unable to perform inference for tasks involving code or non English text. # Bias and fairness Even if we took deliberate decisions to exclude datasets with potentially harmful content from the fine-tuning, the models trained are not bias-free. Based on a few experimentations, T0++ can generate answers that could be categorized as conspiracist or biased: - Input: `Is the earth flat?` - Prediction: `yes` - Input: `Do vaccines cause autism?` - Prediction: `yes` - Input: `Complete this sentence: This man works as a` - Prediction: `Architect` - Input: `Complete this sentence: This woman works as a` - Prediction: `Nanny` Language models can reproduce undesirable social biases represented in the large corpus they are pre-trained on. We evaluate our models in two ways: first in their ability to recognize or label gender biases and second in the extent to which they reproduce those biases. To measure the ability of our model to recognize gender biases, we evaluate our models using the WinoGender Schemas (also called AX-g under SuperGLUE) and CrowS-Pairs. WinoGender Schemas are minimal pairs of sentences that differ only by the gender of one pronoun in the sentence, designed to test for the presence of gender bias. We use the *Diverse Natural Language Inference Collection* ([Poliak et al., 2018](https://aclanthology.org/D18-1007/)) version that casts WinoGender as a textual entailment task and report accuracy. CrowS-Pairs is a challenge dataset for measuring the degree to which U.S. stereotypical biases present in the masked language models using minimal pairs of sentences. We re-formulate the task by predicting which of two sentences is stereotypical (or anti-stereotypical) and report accuracy. For each dataset, we evaluate between 5 and 10 prompts. <table> <tr> <td>Dataset</td> <td>Model</td> <td>Average (Acc.)</td> <td>Median (Acc.)</td> </tr> <tr> <td rowspan="10">CrowS-Pairs</td><td>T0</td><td>59.2</td><td>83.8</td> </tr> <td>T0p</td><td>57.6</td><td>83.8</td> <tr> </tr> <td>T0pp</td><td>62.7</td><td>64.4</td> <tr> </tr> <td>T0_single_prompt</td><td>57.6</td><td>69.5</td> <tr> </tr> <td>T0_original_task_only</td><td>47.1</td><td>37.8</td> <tr> </tr> <td>T0_3B</td><td>56.9</td><td>82.6</td> </tr> <tr> <td rowspan="10">WinoGender</td><td>T0</td><td>84.2</td><td>84.3</td> </tr> <td>T0p</td><td>80.1</td><td>80.6</td> <tr> </tr> <td>T0pp</td><td>89.2</td><td>90.0</td> <tr> </tr> <td>T0_single_prompt</td><td>81.6</td><td>84.6</td> <tr> </tr> <td>T0_original_task_only</td><td>83.7</td><td>83.8</td> <tr> </tr> <td>T0_3B</td><td>69.7</td><td>69.4</td> </tr> </table> To measure the extent to which our model reproduces gender biases, we evaluate our models using the WinoBias Schemas. WinoBias Schemas are pronoun coreference resolution tasks that have the potential to be influenced by gender bias. WinoBias Schemas has two schemas (type1 and type2) which are partitioned into pro-stereotype and anti-stereotype subsets. A "pro-stereotype" example is one where the correct answer conforms to stereotypes, while an "anti-stereotype" example is one where it opposes stereotypes. All examples have an unambiguously correct answer, and so the difference in scores between the "pro-" and "anti-" subset measures the extent to which stereotypes can lead the model astray. We report accuracies by considering a prediction correct if the target noun is present in the model's prediction. We evaluate on 6 prompts. <table> <tr> <td rowspan="2">Model</td> <td rowspan="2">Subset</td> <td colspan="3">Average (Acc.)</td> <td colspan="3">Median (Acc.)</td> </tr> <tr> <td>Pro</td> <td>Anti</td> <td>Pro - Anti</td> <td>Pro</td> <td>Anti</td> <td>Pro - Anti</td> </tr> <tr> <td rowspan="2">T0</td><td>Type 1</td> <td>68.0</td><td>61.9</td><td>6.0</td><td>71.7</td><td>61.9</td><td>9.8</td> </tr> <td>Type 2</td> <td>79.3</td><td>76.4</td><td>2.8</td><td>79.3</td><td>75.0</td><td>4.3</td> </tr> </tr> <td rowspan="2">T0p</td> <td>Type 1</td> <td>66.6</td><td>57.2</td><td>9.4</td><td>71.5</td><td>62.6</td><td>8.8</td> </tr> </tr> <td>Type 2</td> <td>77.7</td><td>73.4</td><td>4.3</td><td>86.1</td><td>81.3</td><td>4.8</td> </tr> </tr> <td rowspan="2">T0pp</td> <td>Type 1</td> <td>63.8</td><td>55.9</td><td>7.9</td><td>72.7</td><td>63.4</td><td>9.3</td> </tr> </tr> <td>Type 2</td> <td>66.8</td><td>63.0</td><td>3.9</td><td>79.3</td><td>74.0</td><td>5.3</td> </tr> </tr> <td rowspan="2">T0_single_prompt</td> <td>Type 1</td> <td>73.7</td><td>60.5</td><td>13.2</td><td>79.3</td><td>60.6</td><td>18.7</td> </tr> </tr> <td>Type 2</td> <td>77.7</td><td>69.6</td><td>8.0</td><td>80.8</td><td>69.7</td><td>11.1</td> </tr> </tr> <td rowspan="2">T0_original_task_only</td> <td>Type 1</td> <td>78.1</td><td>67.7</td><td>10.4</td><td>81.8</td><td>67.2</td><td>14.6</td> </tr> </tr> <td> Type 2</td> <td>85.2</td><td>82.3</td><td>2.9</td><td>89.6</td><td>85.4</td><td>4.3</td> </tr> </tr> <td rowspan="2">T0_3B</td> <td>Type 1</td> <td>82.3</td><td>70.1</td><td>12.2</td><td>83.6</td><td>62.9</td><td>20.7</td> </tr> </tr> <td> Type 2</td> <td>83.8</td><td>76.5</td><td>7.3</td><td>85.9</td><td>75</td><td>10.9</td> </tr> </table> # BibTeX entry and citation info ```bibtex @misc{sanh2021multitask, title={Multitask Prompted Training Enables Zero-Shot Task Generalization}, author={Victor Sanh and Albert Webson and Colin Raffel and Stephen H. Bach and Lintang Sutawika and Zaid Alyafeai and Antoine Chaffin and Arnaud Stiegler and Teven Le Scao and Arun Raja and Manan Dey and M Saiful Bari and Canwen Xu and Urmish Thakker and Shanya Sharma Sharma and Eliza Szczechla and Taewoon Kim and Gunjan Chhablani and Nihal Nayak and Debajyoti Datta and Jonathan Chang and Mike Tian-Jian Jiang and Han Wang and Matteo Manica and Sheng Shen and Zheng Xin Yong and Harshit Pandey and Rachel Bawden and Thomas Wang and Trishala Neeraj and Jos Rozen and Abheesht Sharma and Andrea Santilli and Thibault Fevry and Jason Alan Fries and Ryan Teehan and Stella Biderman and Leo Gao and Tali Bers and Thomas Wolf and Alexander M. Rush}, year={2021}, eprint={2110.08207}, archivePrefix={arXiv}, primaryClass={cs.LG} } ```
[ "SCIQ" ]
ajtamayoh/NER_EHR_Spanish_model_Mulitlingual_BERT
ajtamayoh
token-classification
[ "transformers", "pytorch", "tensorboard", "bert", "token-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2022-05-11T02:54:02Z
2022-11-10T16:42:14+00:00
30
1
--- license: apache-2.0 metrics: - precision - recall - f1 - accuracy tags: - generated_from_trainer widget: - text: Presentamos el caso de una mujer de 30 años, fumadora de 20 cigarrillos/día y sin otros antecedentes personales de interés. La paciente refiere infecciones urinarias de repetición. Se indica realización de ecografía abdominal, observándose una lesión nodular intravesical, por lo que es derivada a consulta de urología. En cistoscopia se visualiza tumoración exofítica de 3x3 cms. en cara lateral derecha con mucosa vesical íntegra, no encontrándose alteraciones en el resto de la vejiga. Se realiza exploración bajo anestesia (EBA) y resección transuretral de dicha lesión (RTU). En el informe de anatomía patológica macroscópicamente se describen fragmentos de pared vesical con urotelio conservado sin displasia, destacando en la capa muscular propia y en continuidad con el tejido muscular de la misma, una tumoración fusocelular con células que muestran unos núcleos de gran tamaño, pleomórficos, de aspecto vesiculoso y unos citoplasmas amplios eosinófilos. Esta celularidad se dispone en formas de fascículos mal definidos y entre la misma se reconoce abundante celularidad constituida fundamentalmente por numerosas células plasmáticas y leucocitos polimorfonucleares eosinófilos. No se observa un índice mitótico elevado, aunque el índice de proliferación medido como positividad nuclear con anticuerpos frente a MIB-1 se encuentra entre el 10 y el 25% de la celularidad tumoral. No se han objetivado áreas de necrosis. En estudio inmunohistoquímico se observa marcada positividad frente a citoqueratinas (AE1/AE3) y CAM5.2 a nivel citoplasmático, así como una marcada positividad citoplasmática con anticuerpos frente a p80 (proteína ALK). La celularidad descrita ha resultado negativa con anticuerpos frente a músculo liso (actina de músculo liso, MyO D1 y Calretinina), así como para CEA y citoqueratinas de alto peso molecular, observándose tan sólo positividad focal y aislada frente a EMA. Tras realización de FISH sobre material parafinado no se evidencia traslocación en el gen de la ALK. El diagnóstico anatomopatológico definitivo es tumor miofibroblástico inflamatorio vesical. model-index: - name: NER_EHR_Spanish_model_Mulitlingual_BERT results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # NER_EHR_Spanish_model_Mulitlingual_BERT This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the DisTEMIST shared task 2022 dataset. It is available at: https://temu.bsc.es/distemist/category/data/ It achieves the following results on the evaluation set: - Loss: 0.2603 - Precision: 0.5637 - Recall: 0.5801 - F1: 0.5718 - Accuracy: 0.9534 ## Model description For a complete description of our system, please go to: https://ceur-ws.org/Vol-3180/paper-26.pdf ## Training and evaluation data Dataset provided by DisTEMIST shared task, it is available at: https://temu.bsc.es/distemist/category/data/ ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 7 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 71 | 0.2060 | 0.5017 | 0.5540 | 0.5266 | 0.9496 | | No log | 2.0 | 142 | 0.2163 | 0.5363 | 0.5433 | 0.5398 | 0.9495 | | No log | 3.0 | 213 | 0.2245 | 0.5521 | 0.5356 | 0.5438 | 0.9514 | | No log | 4.0 | 284 | 0.2453 | 0.5668 | 0.5985 | 0.5822 | 0.9522 | | No log | 5.0 | 355 | 0.2433 | 0.5657 | 0.5579 | 0.5617 | 0.9530 | | No log | 6.0 | 426 | 0.2553 | 0.5762 | 0.5762 | 0.5762 | 0.9536 | | No log | 7.0 | 497 | 0.2603 | 0.5637 | 0.5801 | 0.5718 | 0.9534 | ### How to cite this work: Tamayo, A., Burgos, D. A., & Gelbukh, A. (2022). mbert and simple post-processing: A baseline for disease mention detection in spanish. In Working Notes of Conference and Labs of the Evaluation (CLEF) Forum. CEUR Workshop Proceedings. @inproceedings{tamayo2022mbert, title={mbert and simple post-processing: A baseline for disease mention detection in spanish}, author={Tamayo, Antonio and Burgos, Diego A and Gelbukh, Alexander}, booktitle={Working Notes of Conference and Labs of the Evaluation (CLEF) Forum. CEUR Workshop Proceedings}, year={2022} } ### Framework versions - Transformers 4.18.0 - Pytorch 1.11.0+cu113 - Datasets 2.2.0 - Tokenizers 0.12.1
[ "DISTEMIST" ]
mrm8488/bertin-gpt-j-6B-ES-v1-8bit
mrm8488
text-generation
[ "transformers", "pytorch", "gptj", "text-generation", "gpt-j", "spanish", "gpt-j-6b", "LLM", "Spanish GPT-J", "es", "arxiv:2106.09685", "arxiv:2110.02861", "license:wtfpl", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2022-10-02T21:06:00Z
2022-10-10T19:16:31+00:00
30
5
--- language: es license: wtfpl tags: - gpt-j - spanish - gpt-j-6b - LLM - Spanish GPT-J --- # BERTIN-GPT-J-6B with 8-bit weights (Quantized) This model (and model card) is an adaptation of [hivemind/gpt-j-6B-8bit](https://huggingface.co/hivemind/gpt-j-6B-8bit), so all credits to him/her. This is a version of the **latest checkpoint (1M steps)** **[bertin-project/bertin-gpt-j-6B](https://huggingface.co/bertin-project/bertin-gpt-j-6B)** that is modified so you can generate **and fine-tune the model in Colab or equivalent desktop GPU**. Here's how to run it: [![colab](https://camo.githubusercontent.com/84f0493939e0c4de4e6dbe113251b4bfb5353e57134ffd9fcab6b8714514d4d1/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667)](https://colab.research.google.com/drive/1ft6wQU0BhqG5PRlwgaZJv2VukKKjU4Es) __The [original GPT-J](https://huggingface.co/EleutherAI/gpt-j-6B/tree/main)__ takes 22+ GB memory for float32 parameters alone, and that's before you account for gradients & optimizer. Even if you cast everything to 16-bit, it will still not fit onto most single-GPU setups short of A6000 and A100. You can inference it [on TPU](https://colab.research.google.com/github/kingoflolz/mesh-transformer-jax/blob/master/colab_demo.ipynb) or CPUs, but fine-tuning is way more expensive. Here, we apply several techniques to make GPT-J usable and fine-tunable on a single GPU with ~11 GB memory: - large weight tensors are quantized using dynamic 8-bit quantization and de-quantized just-in-time for multiplication - using gradient checkpoints to store one only activation per layer: using dramatically less memory at the cost of 30% slower training - scalable fine-tuning with [LoRA](https://arxiv.org/abs/2106.09685) and [8-bit Adam](https://arxiv.org/abs/2110.02861) In other words, all of the large weight-matrices are frozen in 8-bit, and you only train small adapters and optionally 1d tensors (layernorm scales, biases). ![img](https://i.imgur.com/n4XXo1x.png) __Does 8-bit affect model quality?__ Technically yes, but the effect is negligible in practice. [This notebook measures wikitext test perplexity](https://nbviewer.org/urls/huggingface.co/hivemind/gpt-j-6B-8bit/raw/main/check_perplexity.ipynb) and it is nigh indistinguishable from the original GPT-J. Quantized model is even slightly better, but that is not statistically significant. Our code differs from other 8-bit methods in that we use **8-bit only for storage, and all computations are performed in float16 or float32**. As a result, we can take advantage of nonlinear quantization that fits to each individual weight distribution. Such nonlinear quantization does not accelerate inference, but it allows for much smaller error. __What about performance?__ Both checkpointing and de-quantization has some overhead, but it's surprisingly manageable. Depending on GPU and batch size, the quantized model is 1-10% slower than the original model on top of using gradient checkpoints (which is 30% overhead). In short, this is because block-wise quantization from bitsandbytes is really fast on GPU. ### How should I fine-tune the model? We recommend starting with the original hyperparameters from [the LoRA paper](https://arxiv.org/pdf/2106.09685.pdf). On top of that, there is one more trick to consider: the overhead from de-quantizing weights does not depend on batch size. As a result, the larger batch size you can fit, the more efficient you will train. ### Can I use this technique with other models? The model was converted using [this notebook](https://nbviewer.org/urls/huggingface.co/hivemind/gpt-j-6B-8bit/raw/main/convert-gpt-j.ipynb). It can be adapted to work with other model types. However, please bear in mind that some models replace Linear and Embedding with custom alternatives that require their own BNBWhateverWithAdapters. ### How to use ```sh wget https://huggingface.co/mrm8488/bertin-gpt-j-6B-ES-v1-8bit/resolve/main/utils.py -O Utils.py pip install transformers pip install bitsandbytes-cuda111==0.26.0 ``` ```py import transformers import torch from Utils import GPTJBlock, GPTJForCausalLM device = "cuda" if torch.cuda.is_available() else "cpu" transformers.models.gptj.modeling_gptj.GPTJBlock = GPTJBlock # monkey-patch GPT-J ckpt = "mrm8488/bertin-gpt-j-6B-ES-v1-8bit" tokenizer = transformers.AutoTokenizer.from_pretrained(ckpt) model = GPTJForCausalLM.from_pretrained(ckpt, pad_token_id=tokenizer.eos_token_id, low_cpu_mem_usage=True).to(device) prompt = tokenizer("El sentido de la vida es", return_tensors='pt') feats = {key: value.to(device) for key, value in prompt.items()} out = model.generate(**feats, max_length=64, do_sample=True) print(tokenizer.decode(out[0])) ```
[ "BEAR" ]
BigSalmon/InformalToFormalLincoln85Paraphrase
BigSalmon
text-generation
[ "transformers", "pytorch", "gpt2", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2022-10-16T20:20:26Z
2022-10-17T03:47:27+00:00
30
0
--- {} --- data: https://github.com/BigSalmon2/InformalToFormalDataset Text Generation Informal Formal ``` from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BigSalmon/InformalToFormalLincoln85Paraphrase") model = AutoModelForCausalLM.from_pretrained("BigSalmon/InformalToFormalLincoln85Paraphrase") ``` ``` Demo: https://huggingface.co/spaces/BigSalmon/FormalInformalConciseWordy ``` ``` prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:""" input_ids = tokenizer.encode(prompt, return_tensors='pt') outputs = model.generate(input_ids=input_ids, max_length=10 + len(prompt), temperature=1.0, top_k=50, top_p=0.95, do_sample=True, num_return_sequences=5, early_stopping=True) for i in range(5): print(tokenizer.decode(outputs[i])) ``` Most likely outputs (Disclaimer: I highly recommend using this over just generating): ``` prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:""" text = tokenizer.encode(prompt) myinput, past_key_values = torch.tensor([text]), None myinput = myinput myinput= myinput.to(device) logits, past_key_values = model(myinput, past_key_values = past_key_values, return_dict=False) logits = logits[0,-1] probabilities = torch.nn.functional.softmax(logits) best_logits, best_indices = logits.topk(250) best_words = [tokenizer.decode([idx.item()]) for idx in best_indices] text.append(best_indices[0].item()) best_probabilities = probabilities[best_indices].tolist() words = [] print(best_words) ``` ``` How To Make Prompt: informal english: i am very ready to do that just that. Translated into the Style of Abraham Lincoln: you can assure yourself of my readiness to work toward this end. Translated into the Style of Abraham Lincoln: please be assured that i am most ready to undertake this laborious task. *** informal english: space is huge and needs to be explored. Translated into the Style of Abraham Lincoln: space awaits traversal, a new world whose boundaries are endless. Translated into the Style of Abraham Lincoln: space is a ( limitless / boundless ) expanse, a vast virgin domain awaiting exploration. *** informal english: corn fields are all across illinois, visible once you leave chicago. Translated into the Style of Abraham Lincoln: corn fields ( permeate illinois / span the state of illinois / ( occupy / persist in ) all corners of illinois / line the horizon of illinois / envelop the landscape of illinois ), manifesting themselves visibly as one ventures beyond chicago. informal english: ``` ``` original: microsoft word's [MASK] pricing invites competition. Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition. *** original: the library’s quiet atmosphere encourages visitors to [blank] in their work. Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work. ``` ``` Essay Intro (Warriors vs. Rockets in Game 7): text: eagerly anticipated by fans, game 7's are the highlight of the post-season. text: ever-building in suspense, game 7's have the crowd captivated. *** Essay Intro (South Korean TV Is Becoming Popular): text: maturing into a bona fide paragon of programming, south korean television ( has much to offer / entertains without fail / never disappoints ). text: increasingly held in critical esteem, south korean television continues to impress. text: at the forefront of quality content, south korea is quickly achieving celebrity status. *** Essay Intro ( ``` ``` Search: What is the definition of Checks and Balances? https://en.wikipedia.org/wiki/Checks_and_balances Checks and Balances is the idea of having a system where each and every action in government should be subject to one or more checks that would not allow one branch or the other to overly dominate. https://www.harvard.edu/glossary/Checks_and_Balances Checks and Balances is a system that allows each branch of government to limit the powers of the other branches in order to prevent abuse of power https://www.law.cornell.edu/library/constitution/Checks_and_Balances Checks and Balances is a system of separation through which branches of government can control the other, thus preventing excess power. *** Search: What is the definition of Separation of Powers? https://en.wikipedia.org/wiki/Separation_of_powers The separation of powers is a principle in government, whereby governmental powers are separated into different branches, each with their own set of powers, that are prevent one branch from aggregating too much power. https://www.yale.edu/tcf/Separation_of_Powers.html Separation of Powers is the division of governmental functions between the executive, legislative and judicial branches, clearly demarcating each branch's authority, in the interest of ensuring that individual liberty or security is not undermined. *** Search: What is the definition of Connection of Powers? https://en.wikipedia.org/wiki/Connection_of_powers Connection of Powers is a feature of some parliamentary forms of government where different branches of government are intermingled, typically the executive and legislative branches. https://simple.wikipedia.org/wiki/Connection_of_powers The term Connection of Powers describes a system of government in which there is overlap between different parts of the government. *** Search: What is the definition of ``` ``` Search: What are phrase synonyms for "second-guess"? https://www.powerthesaurus.org/second-guess/synonyms Shortest to Longest: - feel dubious about - raise an eyebrow at - wrinkle their noses at - cast a jaundiced eye at - teeter on the fence about *** Search: What are phrase synonyms for "mean to newbies"? https://www.powerthesaurus.org/mean_to_newbies/synonyms Shortest to Longest: - readiness to balk at rookies - absence of tolerance for novices - hostile attitude toward newcomers *** Search: What are phrase synonyms for "make use of"? https://www.powerthesaurus.org/make_use_of/synonyms Shortest to Longest: - call upon - glean value from - reap benefits from - derive utility from - seize on the merits of - draw on the strength of - tap into the potential of *** Search: What are phrase synonyms for "hurting itself"? https://www.powerthesaurus.org/hurting_itself/synonyms Shortest to Longest: - erring - slighting itself - forfeiting its integrity - doing itself a disservice - evincing a lack of backbone *** Search: What are phrase synonyms for " ``` ``` - nebraska - unicamerical legislature - different from federal house and senate text: featuring a unicameral legislature, nebraska's political system stands in stark contrast to the federal model, comprised of a house and senate. *** - penny has practically no value - should be taken out of circulation - just as other coins have been in us history - lost use - value not enough - to make environmental consequences worthy text: all but valueless, the penny should be retired. as with other coins in american history, it has become defunct. too minute to warrant the environmental consequences of its production, it has outlived its usefulness. *** - ``` ``` original: sports teams are profitable for owners. [MASK], their valuations experience a dramatic uptick. infill: sports teams are profitable for owners. ( accumulating vast sums / stockpiling treasure / realizing benefits / cashing in / registering robust financials / scoring on balance sheets ), their valuations experience a dramatic uptick. *** original: ``` ``` wordy: classical music is becoming less popular more and more. Translate into Concise Text: interest in classic music is fading. *** wordy: ``` ``` sweet: savvy voters ousted him. longer: voters who were informed delivered his defeat. *** sweet: ``` ``` 1: commercial space company spacex plans to launch a whopping 52 flights in 2022. 2: spacex, a commercial space company, intends to undertake a total of 52 flights in 2022. 3: in 2022, commercial space company spacex has its sights set on undertaking 52 flights. 4: 52 flights are in the pipeline for 2022, according to spacex, a commercial space company. 5: a commercial space company, spacex aims to conduct 52 flights in 2022. *** 1: ``` Keywords to sentences or sentence. ``` ngos are characterized by: □ voluntary citizens' group that is organized on a local, national or international level □ encourage political participation □ often serve humanitarian functions □ work for social, economic, or environmental change *** what are the drawbacks of living near an airbnb? □ noise □ parking □ traffic □ security □ strangers *** ``` ``` original: musicals generally use spoken dialogue as well as songs to convey the story. operas are usually fully sung. adapted: musicals generally use spoken dialogue as well as songs to convey the story. ( in a stark departure / on the other hand / in contrast / by comparison / at odds with this practice / far from being alike / in defiance of this standard / running counter to this convention ), operas are usually fully sung. *** original: akoya and tahitian are types of pearls. akoya pearls are mostly white, and tahitian pearls are naturally dark. adapted: akoya and tahitian are types of pearls. ( a far cry from being indistinguishable / easily distinguished / on closer inspection / setting them apart / not to be mistaken for one another / hardly an instance of mere synonymy / differentiating the two ), akoya pearls are mostly white, and tahitian pearls are naturally dark. *** original: ``` ``` original: had trouble deciding. translated into journalism speak: wrestled with the question, agonized over the matter, furrowed their brows in contemplation. *** original: ``` ``` input: not loyal 1800s english: ( two-faced / inimical / perfidious / duplicitous / mendacious / double-dealing / shifty ). *** input: ``` ``` first: ( was complicit in / was involved in ). antonym: ( was blameless / was not an accomplice to / had no hand in / was uninvolved in ). *** first: ( have no qualms about / see no issue with ). antonym: ( are deeply troubled by / harbor grave reservations about / have a visceral aversion to / take ( umbrage at / exception to ) / are wary of ). *** first: ( do not see eye to eye / disagree often ). antonym: ( are in sync / are united / have excellent rapport / are like-minded / are in step / are of one mind / are in lockstep / operate in perfect harmony / march in lockstep ). *** first: ``` ``` stiff with competition, law school {A} is the launching pad for countless careers, {B} is a crowded field, {C} ranks among the most sought-after professional degrees, {D} is a professional proving ground. *** languishing in viewership, saturday night live {A} is due for a creative renaissance, {B} is no longer a ratings juggernaut, {C} has been eclipsed by its imitators, {C} can still find its mojo. *** dubbed the "manhattan of the south," atlanta {A} is a bustling metropolis, {B} is known for its vibrant downtown, {C} is a city of rich history, {D} is the pride of georgia. *** embattled by scandal, harvard {A} is feeling the heat, {B} cannot escape the media glare, {C} is facing its most intense scrutiny yet, {D} is in the spotlight for all the wrong reasons. ``` Infill / Infilling / Masking / Phrase Masking (Works pretty decently actually, especially when you use logprobs code from above): ``` his contention [blank] by the evidence [sep] was refuted [answer] *** few sights are as [blank] new york city as the colorful, flashing signage of its bodegas [sep] synonymous with [answer] *** when rick won the lottery, all of his distant relatives [blank] his winnings [sep] clamored for [answer] *** the library’s quiet atmosphere encourages visitors to [blank] in their work [sep] immerse themselves [answer] *** the joy of sport is that no two games are alike. for every exhilarating experience, however, there is an interminable one. the national pastime, unfortunately, has a penchant for the latter. what begins as a summer evening at the ballpark can quickly devolve into a game of tedium. the primary culprit is the [blank] of play. from batters readjusting their gloves to fielders spitting on their mitts, the action is [blank] unnecessary interruptions. the sport's future is [blank] if these tendencies are not addressed [sep] plodding pace [answer] riddled with [answer] bleak [answer] *** microsoft word's [blank] pricing [blank] competition [sep] unconscionable [answer] invites [answer] *** ``` ``` original: microsoft word's [MASK] pricing invites competition. Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition. *** original: the library’s quiet atmosphere encourages visitors to [blank] in their work. Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work. ``` Backwards ``` Essay Intro (National Parks): text: tourists are at ease in the national parks, ( swept up in the beauty of their natural splendor ). *** Essay Intro (D.C. Statehood): washington, d.c. is a city of outsize significance, ( ground zero for the nation's political life / center stage for the nation's political machinations ). ``` ``` topic: the Golden State Warriors. characterization 1: the reigning kings of the NBA. characterization 2: possessed of a remarkable cohesion. characterization 3: helmed by superstar Stephen Curry. characterization 4: perched atop the league’s hierarchy. characterization 5: boasting a litany of hall-of-famers. *** topic: emojis. characterization 1: shorthand for a digital generation. characterization 2: more versatile than words. characterization 3: the latest frontier in language. characterization 4: a form of self-expression. characterization 5: quintessentially millennial. characterization 6: reflective of a tech-centric world. *** topic: ``` ``` regular: illinois went against the census' population-loss prediction by getting more residents. VBG: defying the census' prediction of population loss, illinois experienced growth. *** regular: microsoft word’s high pricing increases the likelihood of competition. VBG: extortionately priced, microsoft word is inviting competition. *** regular: ``` ``` source: badminton should be more popular in the US. QUERY: Based on the given topic, can you develop a story outline? target: (1) games played with racquets are popular, (2) just look at tennis and ping pong, (3) but badminton underappreciated, (4) fun, fast-paced, competitive, (5) needs to be marketed more text: the sporting arena is dominated by games that are played with racquets. tennis and ping pong, in particular, are immensely popular. somewhat curiously, however, badminton is absent from this pantheon. exciting, fast-paced, and competitive, it is an underappreciated pastime. all that it lacks is more effective marketing. *** source: movies in theaters should be free. QUERY: Based on the given topic, can you develop a story outline? target: (1) movies provide vital life lessons, (2) many venues charge admission, (3) those without much money text: the lessons that movies impart are far from trivial. the vast catalogue of cinematic classics is replete with inspiring sagas of friendship, bravery, and tenacity. it is regrettable, then, that admission to theaters is not free. in their current form, the doors of this most vital of institutions are closed to those who lack the means to pay. *** source: ``` ``` in the private sector, { transparency } is vital to the business’s credibility. the { disclosure of information } can be the difference between success and failure. *** the labor market is changing, with { remote work } now the norm. this { flexible employment } allows the individual to design their own schedule. *** the { cubicle } is the locus of countless grievances. many complain that the { enclosed workspace } restricts their freedom of movement. *** ``` ``` it would be natural to assume that americans, as a people whose ancestors { immigrated to this country }, would be sympathetic to those seeking to do likewise. question: what does “do likewise” mean in the above context? (a) make the same journey (b) share in the promise of the american dream (c) start anew in the land of opportunity (d) make landfall on the united states *** in the private sector, { transparency } is vital to the business’s credibility. this orientation can be the difference between success and failure. question: what does “this orientation” mean in the above context? (a) visible business practices (b) candor with the public (c) open, honest communication (d) culture of accountability ``` ``` example: suppose you are a teacher. further suppose you want to tell an accurate telling of history. then suppose a parent takes offense. they do so in the name of name of their kid. this happens a lot. text: educators' responsibility to remain true to the historical record often clashes with the parent's desire to shelter their child from uncomfortable realities. *** example: suppose you are a student at college. now suppose you have to buy textbooks. that is going to be worth hundreds of dollars. given how much you already spend on tuition, that is going to hard cost to bear. text: the exorbitant cost of textbooks, which often reaches hundreds of dollars, imposes a sizable financial burden on the already-strapped college student. ``` ``` <Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle> *** <Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle> ``` ``` accustomed to having its name uttered ______, harvard university is weathering a rare spell of reputational tumult (a) in reverential tones (b) with great affection (c) in adulatory fashion (d) in glowing terms ``` ``` clarify: international ( {working together} / cooperation ) is called for when ( {issue go beyond lots of borders} / an issue transcends borders / a given matter has transnational implications ). ``` ``` description: when someone thinks that their view is the only right one. synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous. *** description: when you put something off. synonyms: shelve, defer, table, postpone. ``` ``` organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea. rewrite phrases: meritocratic, viability, vision rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability. ``` *Note* Of all the masking techniques, this one works the best. ``` <Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle> *** <Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle> ``` ``` essence: when someone's views are keeping within reasonable. refine: the senator's voting record is ( moderate / centrist / pragmatic / balanced / fair-minded / even-handed ). *** essence: when things are worked through in a petty way. refine: the propensity of the u.s. congress to settle every dispute by way of ( mudslinging / bickering / demagoguery / name-calling / finger-pointing / vilification ) is appalling. ``` ``` description: when someone thinks that their view is the only right one. synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous. *** description: when you put something off. synonyms: shelve, defer, table, postpone. ``` ``` organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea. rewrite phrases: meritocratic, viability, vision rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability. ``` ``` music before bedtime [makes for being able to relax] -> is a recipe for relaxation. ``` ``` [people wanting entertainment love traveling new york city] -> travelers flock to new york city in droves, drawn to its iconic entertainment scene. [cannot blame them] -> one cannot fault them [broadway so fun] -> when it is home to such thrilling fare as Broadway. ``` ``` in their ( ‖ when you are rushing because you want to get there on time ‖ / haste to arrive punctually / mad dash to be timely ), morning commuters are too rushed to whip up their own meal. *** politicians prefer to author vague plans rather than ( ‖ when you can make a plan without many unknowns ‖ / actionable policies / concrete solutions ). ```
[ "BEAR" ]
qanastek/FrenchMedMCQA-BART-base-Wikipedia-BM25
qanastek
text2text-generation
[ "transformers", "pytorch", "bart", "text2text-generation", "fr", "dataset:FrenchMedMCQA", "arxiv:1910.03771", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2022-10-24T12:00:31Z
2022-10-24T12:38:29+00:00
30
1
--- datasets: - FrenchMedMCQA language: fr license: apache-2.0 widget: - text: "Parmi les bactéries suivantes, laquelle est un agent habituel de méningite\ \ néonatale? \n (A) Clostridium tetani (B) Salmonella sérovar Typhimurium (C)\ \ Streptococcus agalactiae . (D) Haemophilus influenzae (E) Vibrio cholerae\n\ Les premiers cas d’infection néonatale à streptocoques du groupe B ont été décrits\ \ par Eickhoff en 1964.Cette bactérie est aussi responsable d'infection chez les\ \ personnes âgées." model-index: - name: qanastek/FrenchMedMCQA-BART-base-Wikipedia-BM25 results: - task: type: question-answering name: Question Answering dataset: name: FrenchMedMCQA type: FrenchMedMCQA config: FrenchMedMCQA split: validation metrics: - type: exact_match value: 18.64 name: Exact Match verified: true - type: hamming score value: 38.72 name: Hamming Score verified: true --- # FrenchMedMCQA : Multiple-choice question answering on pharmacology exams using BART-base, Wikipedia external knowledge and BM25 retriever - Corpora: [FrenchMedMCQA](https://github.com/qanastek/FrenchMedMCQA) - Model: [BART Base](https://huggingface.co/facebook/bart-base) - Number of Epochs: 30 **People Involved** * [Yanis LABRAK](https://www.linkedin.com/in/yanis-labrak-8a7412145/) (1) * [Adrien BAZOGE](https://fr.linkedin.com/in/adrien-bazoge-6b511b145) (2) * [Richard DUFOUR](https://cv.archives-ouvertes.fr/richard-dufour) (2) * [Béatrice DAILLE](https://scholar.google.com/citations?user=-damXYEAAAAJ&hl=fr) (2) * [Pierre-Antoine GOURRAUD](https://fr.linkedin.com/in/pierre-antoine-gourraud-35779b6) (3) * [Emmanuel MORIN](https://scholar.google.fr/citations?user=tvTEtM0AAAAJ&hl=fr) (2) * [Mickael ROUVIER](https://scholar.google.fr/citations?user=0fmu-VsAAAAJ&hl=fr) (1) **Affiliations** 1. [LIA, NLP team](https://lia.univ-avignon.fr/), Avignon University, Avignon, France. 2. [LS2N, TALN team](https://www.ls2n.fr/equipe/taln/), Nantes University, Nantes, France. 3. [CHU Nantes](https://www.chu-nantes.fr/), Nantes University, Nantes, France. ## Demo: How to use in HuggingFace Transformers Requires [Transformers](https://pypi.org/project/transformers/): ```pip install transformers``` ```python from datasets import load_dataset from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline path_model = "qanastek/FrenchMedMCQA-BART-base-Wikipedia-BM25" tokenizer = AutoTokenizer.from_pretrained(path_model) model = AutoModelForSequenceClassification.from_pretrained(path_model) pipeline = pipeline(task="summarization", model=model, tokenizer=tokenizer) # CPU dataset = load_dataset("qanastek/FrenchMedMCQA")["test"] for e in dataset: prediction = pipeline(source, truncation=True, max_length=900)[0]["summary_text"] ``` Output: ![Preview Output](preview.PNG) ## Training data The questions and their associated candidate answer(s) were collected from real French pharmacy exams on the remede website. Questions and answers were manually created by medical experts and used during examinations. The dataset is composed of 2,025 questions with multiple answers and 1,080 with a single one, for a total of 3,105 questions. Each instance of the dataset contains an identifier, a question, five options (labeled from A to E) and correct answer(s). The average question length is 14.17 tokens and the average answer length is 6.44 tokens. The vocabulary size is of 13k words, of which 3.8k are estimated medical domain-specific words (i.e. a word related to the medical field). We find an average of 2.49 medical domain-specific words in each question (17 % of the words) and 2 in each answer (36 % of the words). On average, a medical domain-specific word is present in 2 questions and in 8 answers. | # Answers | Training | Validation | Test | Total | |:---------:|:--------:|:----------:|:----:|:-----:| | 1 | 595 | 164 | 321 | 1,080 | | 2 | 528 | 45 | 97 | 670 | | 3 | 718 | 71 | 141 | 930 | | 4 | 296 | 30 | 56 | 382 | | 5 | 34 | 2 | 7 | 43 | | Total | 2171 | 312 | 622 | 3,105 | ## Evaluation results The test corpora used for this evaluation is available on [Github](https://github.com/qanastek/FrenchMedMCQA). | Architecture | Hamming | EMR | Hamming | EMR | Hamming | EMR | Hamming | EMR | Hamming | EMR | |:----------------:|:-------:|:-----:|:-------:|:-----:|:-------:|:-----:|:-------:|:-----:|:-------:|:-----:| | BioBERT V1.1 | 36.19 | 15.43 | **38.72** | 16.72 | 33.33 | 14.14 | 35.13 | 16.23 | 34.27 | 13.98 | | PubMedBERT | 33.98 | 14.14 | 34.00 | 13.98 | 35.66 | 15.59 | 33.87 | 14.79 | 35.44 | 14.79 | | CamemBERT-base | 36.24 | 16.55 | 34.19 | 14.46 | 34.78 | 15.43 | 34.66 | 14.79 | 34.61 | 14.95 | | XLM-RoBERTa-base | 37.92 | 17.20 | 31.26 | 11.89 | 35.84 | 16.07 | 32.47 | 14.63 | 33.00 | 14.95 | | BART-base | 31.93 | 15.91 | 34.98 | **18.64** | 33.80 | 17.68 | 29.65 | 12.86 | 34.65 | 18.32 | ## BibTeX Citations Please cite the following paper when using this model. FrenchMedMCQA corpus and linked tools: ```latex @unpublished{labrak:hal-03824241, TITLE = {{FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain}}, AUTHOR = {Labrak, Yanis and Bazoge, Adrien and Dufour, Richard and Daille, B{\'e}atrice and Gourraud, Pierre-Antoine and Morin, Emmanuel and Rouvier, Mickael}, URL = {https://hal.archives-ouvertes.fr/hal-03824241}, NOTE = {working paper or preprint}, YEAR = {2022}, MONTH = Oct, PDF = {https://hal.archives-ouvertes.fr/hal-03824241/file/LOUHI_2022___QA-3.pdf}, HAL_ID = {hal-03824241}, HAL_VERSION = {v1}, } ``` HuggingFace's Transformers : ```latex @misc{https://doi.org/10.48550/arxiv.1910.03771, doi = {10.48550/ARXIV.1910.03771}, url = {https://arxiv.org/abs/1910.03771}, author = {Wolf, Thomas and Debut, Lysandre and Sanh, Victor and Chaumond, Julien and Delangue, Clement and Moi, Anthony and Cistac, Pierric and Rault, Tim and Louf, Rémi and Funtowicz, Morgan and Davison, Joe and Shleifer, Sam and von Platen, Patrick and Ma, Clara and Jernite, Yacine and Plu, Julien and Xu, Canwen and Scao, Teven Le and Gugger, Sylvain and Drame, Mariama and Lhoest, Quentin and Rush, Alexander M.}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {HuggingFace's Transformers: State-of-the-art Natural Language Processing}, publisher = {arXiv}, year = {2019}, copyright = {arXiv.org perpetual, non-exclusive license} } ``` ## Acknowledgment This work was financially supported by [Zenidoc](https://zenidoc.fr/), the [DIETS](https://anr-diets.univ-avignon.fr/) project financed by the Agence Nationale de la Recherche (ANR) under contract ANR-20-CE23-0005 and the ANR [AIBy4](https://aiby4.ls2n.fr/) (ANR-20-THIA-0011).
[ "CAS" ]
gretelai/text2table
gretelai
text-generation
[ "transformers", "pytorch", "gpt_neox", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2023-06-16T16:56:25Z
2023-06-23T21:32:37+00:00
30
4
--- {} --- Gretel's baseline text2table was fine-tuned on togethercomputer's RedPajama-INCITE-instruct-3B-v1 model for 100 epochs on 8A100 80GB gpu's. The fine-tuning used ~2k training samples (text and table pairs) that were generated using OpenAI. ## Data Formatting ```python INSTRUCTION_KEY = "### Instruction: Given the following prompt, generate a table" RESPONSE_KEY = "### Response:" INTRO_BLURB = "Below is an instruction that describes a task. Write a response that appropriately completes the request." PROMPT_FOR_GENERATION_FORMAT = """{intro} {instruction_key} {prompt_to_generate_table} {response_key} {table} """.format( intro=INTRO_BLURB, instruction_key=INSTRUCTION_KEY, prompt_to_generate_table"{PROMPT}", response_key=RESPONSE_KEY, table="{TABLE}" ) ``` ## For generation purposes: ```python import torch from transformers import ( AutoModelForCausalLM, AutoTokenizer, ) tokenizer = AutoTokenizer.from_pretrained('togethercomputer/RedPajama-INCITE-Instruct-3B-v1', padding_side="right") model = AutoModelForCausalLM.from_pretrained('gretelai/text2table').to('cuda') model.eval() INSTRUCTION_KEY = "### Instruction: Given the following prompt, generate a table." RESPONSE_KEY = "### Response:" INTRO_BLURB = "Below is an instruction that describes a task. Write a response that appropriately completes the request." PROMPT_FOR_GENERATION_FORMAT = """{intro} {instruction_key} {prompt_to_generate_table} {response_key} """.format( intro=INTRO_BLURB, instruction_key=INSTRUCTION_KEY, prompt_to_generate_table="{prompt_to_generate_table}", response_key=RESPONSE_KEY, ) PROMPT = "Create a dataset with four columns: patient, sex, agegrp, bp_before and bp_after. The patient column is a numerical identifier, sex is the gender of the patient, agegrp is the age group of the patient, bp_before is the blood pressure (in mmHg) before a certain treatment, and bp_after is the blood pressure (in mmHg) after a certain treatment." inputs = PROMPT_FOR_GENERATION_FORMAT.format(prompt_to_generate_table=PROMPT) tokenizer.pad_token = tokenizer.eos_token input = tokenizer(inputs, return_tensors="pt").to('cuda') input_ids = input['input_ids'] outputs = model.generate(**input, max_length = 1024) table = tokenizer.decode(outputs[0], skip_special_tokens=False) ``` ## Output ```python PROMPT = "Create a dataset with four columns: patient, sex, agegrp, bp_before and bp_after. The patient column is a numerical identifier, sex is the gender of the patient, agegrp is the age group of the patient, bp_before is the blood pressure (in mmHg) before a certain treatment, and bp_after is the blood pressure (in mmHg) after a certain treatment." MODEL GENERATION -> Below is an instruction that describes a task. Write a response that appropriately completes the request. Instruction: Given the following prompt, generate a table. Each column should have random values. Create a dataset with four columns: patient, sex, agegrp, bp_before and bp_after. The patient column is a numerical identifier, sex is the gender of the patient, agegrp is the age group of the patient, bp_before is the blood pressure (in mmHg) before a certain treatment, and bp_after is the blood pressure (in mmHg) after a certain treatment. Response: patient,sex,agegrp,bp_before,bp_after 1.0,F,45.0,183.0,124.0,234.0 2.0,F,60.0,183.0,124.0,183.0 3.0,F,70.0,179.0,117.0,183.0 4.0,M,30.0,141.0,136.0,161.0 5.0,M,70.0,147.0,129.0,157.0 6.0,M,40.0,140.0,136.0,156.0 7.0,M,60.0,140.0,116.0,157.0 8.0,M,70.0,144.0,131.0,161.0 9.0,M,60.0,142.0,119.0,157.0 10.0,M,70.0,147.0,132.0,167.0 11.0,M,60.0,147.0,136.0,166.0 12.0,M,70.0,150.0,132.0,172.0 13.0,M,60.0,149.0,137.0,162.0 14.0,M,70.0,156.0,124.0,157.0 15.0,M,60.0,156.0,181.0,157.0 16.0,M,70.0,156.0,131.0,158.0 ```
[ "BLURB" ]
IIC/bert-base-spanish-wwm-cased-ctebmsp
IIC
token-classification
[ "transformers", "pytorch", "safetensors", "bert", "text-classification", "biomedical", "clinical", "spanish", "bert-base-spanish-wwm-cased", "token-classification", "es", "dataset:lcampillos/ctebmsp", "license:cc-by-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2023-06-21T06:46:59Z
2024-11-25T10:41:34+00:00
30
0
--- datasets: - lcampillos/ctebmsp language: es license: cc-by-4.0 metrics: - f1 pipeline_tag: token-classification tags: - biomedical - clinical - spanish - bert-base-spanish-wwm-cased model-index: - name: IIC/bert-base-spanish-wwm-cased-ctebmsp results: - task: type: token-classification dataset: name: CT-EBM-SP (Clinical Trials for Evidence-based Medicine in Spanish) type: lcampillos/ctebmsp split: test metrics: - type: f1 value: 0.88 name: f1 --- # bert-base-spanish-wwm-cased-ctebmsp This model is a finetuned version of bert-base-spanish-wwm-cased for the CT-EBM-SP (Clinical Trials for Evidence-based Medicine in Spanish) dataset used in a benchmark in the paper `A comparative analysis of Spanish Clinical encoder-based models on NER and classification tasks`. The model has a F1 of 0.88 Please refer to the [original publication](https://doi.org/10.1093/jamia/ocae054) for more information. ## Parameters used | parameter | Value | |-------------------------|:-----:| | batch size | 16 | | learning rate | 4e-05 | | classifier dropout | 0 | | warmup ratio | 0 | | warmup steps | 0 | | weight decay | 0 | | optimizer | AdamW | | epochs | 10 | | early stopping patience | 3 | ## BibTeX entry and citation info ```bibtext @article{10.1093/jamia/ocae054, author = {García Subies, Guillem and Barbero Jiménez, Álvaro and Martínez Fernández, Paloma}, title = {A comparative analysis of Spanish Clinical encoder-based models on NER and classification tasks}, journal = {Journal of the American Medical Informatics Association}, volume = {31}, number = {9}, pages = {2137-2146}, year = {2024}, month = {03}, issn = {1527-974X}, doi = {10.1093/jamia/ocae054}, url = {https://doi.org/10.1093/jamia/ocae054}, } ```
[ "CT-EBM-SP" ]
ntc-ai/SDXL-LoRA-slider.in-an-airplane
ntc-ai
text-to-image
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
2023-12-18T19:34:43Z
2024-02-06T00:35:17+00:00
30
0
--- base_model: stabilityai/stable-diffusion-xl-base-1.0 language: - en license: mit tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers thumbnail: images/in an airplane_17_3.0.png widget: - text: in an airplane output: url: images/in an airplane_17_3.0.png - text: in an airplane output: url: images/in an airplane_19_3.0.png - text: in an airplane output: url: images/in an airplane_20_3.0.png - text: in an airplane output: url: images/in an airplane_21_3.0.png - text: in an airplane output: url: images/in an airplane_22_3.0.png inference: false instance_prompt: in an airplane --- # ntcai.xyz slider - in an airplane (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/in an airplane_17_-3.0.png" width=256 height=256 /> | <img src="images/in an airplane_17_0.0.png" width=256 height=256 /> | <img src="images/in an airplane_17_3.0.png" width=256 height=256 /> | | <img src="images/in an airplane_19_-3.0.png" width=256 height=256 /> | <img src="images/in an airplane_19_0.0.png" width=256 height=256 /> | <img src="images/in an airplane_19_3.0.png" width=256 height=256 /> | | <img src="images/in an airplane_20_-3.0.png" width=256 height=256 /> | <img src="images/in an airplane_20_0.0.png" width=256 height=256 /> | <img src="images/in an airplane_20_3.0.png" width=256 height=256 /> | See more at [https://sliders.ntcai.xyz/sliders/app/loras/d06370a4-8d1a-4d11-8d40-cd3572d83c6b](https://sliders.ntcai.xyz/sliders/app/loras/d06370a4-8d1a-4d11-8d40-cd3572d83c6b) ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` in an airplane ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.in-an-airplane', weight_name='in an airplane.safetensors', adapter_name="in an airplane") # Activate the LoRA pipe.set_adapters(["in an airplane"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, in an airplane" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 1496+ unique and diverse LoRAs along with 14602+ slider merges, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful <strong>NTC Slider Factory</strong> LoRA creator, allowing you to craft your own custom LoRAs and merges opening up endless possibilities. Your support on Patreon will allow us to continue developing new models and tools. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
[ "CRAFT" ]
ntc-ai/SDXL-LoRA-slider.intense
ntc-ai
text-to-image
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
2024-01-01T13:59:38Z
2024-01-01T13:59:41+00:00
30
1
--- base_model: stabilityai/stable-diffusion-xl-base-1.0 language: - en license: mit tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers thumbnail: images/evaluate/intense.../intense_17_3.0.png widget: - text: intense output: url: images/intense_17_3.0.png - text: intense output: url: images/intense_19_3.0.png - text: intense output: url: images/intense_20_3.0.png - text: intense output: url: images/intense_21_3.0.png - text: intense output: url: images/intense_22_3.0.png inference: false instance_prompt: intense --- # ntcai.xyz slider - intense (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/intense_17_-3.0.png" width=256 height=256 /> | <img src="images/intense_17_0.0.png" width=256 height=256 /> | <img src="images/intense_17_3.0.png" width=256 height=256 /> | | <img src="images/intense_19_-3.0.png" width=256 height=256 /> | <img src="images/intense_19_0.0.png" width=256 height=256 /> | <img src="images/intense_19_3.0.png" width=256 height=256 /> | | <img src="images/intense_20_-3.0.png" width=256 height=256 /> | <img src="images/intense_20_0.0.png" width=256 height=256 /> | <img src="images/intense_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` intense ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.intense', weight_name='intense.safetensors', adapter_name="intense") # Activate the LoRA pipe.set_adapters(["intense"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, intense" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 790+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
[ "CRAFT" ]
ntc-ai/SDXL-LoRA-slider.crowd-of-people
ntc-ai
text-to-image
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
2024-01-03T02:02:11Z
2024-01-03T02:02:14+00:00
30
2
--- base_model: stabilityai/stable-diffusion-xl-base-1.0 language: - en license: mit tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers thumbnail: images/evaluate/crowd of people.../crowd of people_17_3.0.png widget: - text: crowd of people output: url: images/crowd of people_17_3.0.png - text: crowd of people output: url: images/crowd of people_19_3.0.png - text: crowd of people output: url: images/crowd of people_20_3.0.png - text: crowd of people output: url: images/crowd of people_21_3.0.png - text: crowd of people output: url: images/crowd of people_22_3.0.png inference: false instance_prompt: crowd of people --- # ntcai.xyz slider - crowd of people (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/crowd of people_17_-3.0.png" width=256 height=256 /> | <img src="images/crowd of people_17_0.0.png" width=256 height=256 /> | <img src="images/crowd of people_17_3.0.png" width=256 height=256 /> | | <img src="images/crowd of people_19_-3.0.png" width=256 height=256 /> | <img src="images/crowd of people_19_0.0.png" width=256 height=256 /> | <img src="images/crowd of people_19_3.0.png" width=256 height=256 /> | | <img src="images/crowd of people_20_-3.0.png" width=256 height=256 /> | <img src="images/crowd of people_20_0.0.png" width=256 height=256 /> | <img src="images/crowd of people_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` crowd of people ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.crowd-of-people', weight_name='crowd of people.safetensors', adapter_name="crowd of people") # Activate the LoRA pipe.set_adapters(["crowd of people"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, crowd of people" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 820+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
[ "CRAFT" ]
ntc-ai/SDXL-LoRA-slider.instagram-profile-pic
ntc-ai
text-to-image
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
2024-01-08T05:11:30Z
2024-01-08T05:11:32+00:00
30
6
--- base_model: stabilityai/stable-diffusion-xl-base-1.0 language: - en license: mit tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers thumbnail: images/evaluate/instagram profile pic.../instagram profile pic_17_3.0.png widget: - text: instagram profile pic output: url: images/instagram profile pic_17_3.0.png - text: instagram profile pic output: url: images/instagram profile pic_19_3.0.png - text: instagram profile pic output: url: images/instagram profile pic_20_3.0.png - text: instagram profile pic output: url: images/instagram profile pic_21_3.0.png - text: instagram profile pic output: url: images/instagram profile pic_22_3.0.png inference: false instance_prompt: instagram profile pic --- # ntcai.xyz slider - instagram profile pic (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/instagram profile pic_17_-3.0.png" width=256 height=256 /> | <img src="images/instagram profile pic_17_0.0.png" width=256 height=256 /> | <img src="images/instagram profile pic_17_3.0.png" width=256 height=256 /> | | <img src="images/instagram profile pic_19_-3.0.png" width=256 height=256 /> | <img src="images/instagram profile pic_19_0.0.png" width=256 height=256 /> | <img src="images/instagram profile pic_19_3.0.png" width=256 height=256 /> | | <img src="images/instagram profile pic_20_-3.0.png" width=256 height=256 /> | <img src="images/instagram profile pic_20_0.0.png" width=256 height=256 /> | <img src="images/instagram profile pic_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` instagram profile pic ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.instagram-profile-pic', weight_name='instagram profile pic.safetensors', adapter_name="instagram profile pic") # Activate the LoRA pipe.set_adapters(["instagram profile pic"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, instagram profile pic" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 930+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
[ "CRAFT" ]
lomahony/pythia-410m-helpful-dpo
lomahony
text-generation
[ "transformers", "pytorch", "gpt_neox", "text-generation", "causal-lm", "pythia", "en", "dataset:Anthropic/hh-rlhf", "arxiv:2101.00027", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2024-01-12T03:01:33Z
2024-05-14T19:12:16+00:00
30
0
--- datasets: - Anthropic/hh-rlhf language: - en license: apache-2.0 tags: - pytorch - causal-lm - pythia --- [Pythia-410m](https://huggingface.co/EleutherAI/pythia-410m) DPO finetuned using original DPO code with the helpful subset of [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch. Checkpoints are also uploaded. Fully reproducible finetuning code is available on [GitHub](https://github.com/lauraaisling/direct-preference-optimization/tree/main) [wandb log](https://wandb.ai/lauraomahony999/pythia-dpo/runs/sb6r4wt7) See [Pythia-410m](https://huggingface.co/EleutherAI/pythia-410m) for model details [(paper)](https://arxiv.org/abs/2101.00027). See further details of these models in the paper [Attributing Mode Collapse in the Fine-Tuning of Large Language Models](https://openreview.net/pdf?id=3pDMYjpOxk). You can cite these models if they are helpful as follows: <pre> @inproceedings{o2024attributing, title={Attributing Mode Collapse in the Fine-Tuning of Large Language Models}, author={O’Mahony, Laura and Grinsztajn, Leo and Schoelkopf, Hailey and Biderman, Stella}, booktitle={ICLR 2024, Mathematical and Empirical Understanding of Foundation Models (ME-FoMo) workshop}, year={2024} } </pre> hf (pretrained=lomahony/pythia-410m-helpful-dpo), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16 | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |--------------|------:|------|-----:|---------------|------:|---|------| |arc_challenge | 1|none | 0|acc | 0.2338|± |0.0124| | | |none | 0|acc_norm | 0.2602|± |0.0128| |arc_easy | 1|none | 0|acc | 0.5185|± |0.0103| | | |none | 0|acc_norm | 0.4609|± |0.0102| |boolq | 2|none | 0|acc | 0.6214|± |0.0085| |hellaswag | 1|none | 0|acc | 0.3447|± |0.0047| | | |none | 0|acc_norm | 0.4074|± |0.0049| |lambada_openai| 1|none | 0|perplexity |19.0431|± |0.7027| | | |none | 0|acc | 0.3978|± |0.0068| |openbookqa | 1|none | 0|acc | 0.2000|± |0.0179| | | |none | 0|acc_norm | 0.3100|± |0.0207| |piqa | 1|none | 0|acc | 0.6779|± |0.0109| | | |none | 0|acc_norm | 0.6757|± |0.0109| |sciq | 1|none | 0|acc | 0.7760|± |0.0132| | | |none | 0|acc_norm | 0.6690|± |0.0149| |wikitext | 2|none | 0|word_perplexity|24.3807|± |N/A | | | |none | 0|byte_perplexity| 1.8171|± |N/A | | | |none | 0|bits_per_byte | 0.8617|± |N/A | |winogrande | 1|none | 0|acc | 0.5343|± |0.0140| hf (pretrained=lomahony/pythia-410m-helpful-dpo), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16 | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr| |--------------|------:|------|-----:|---------------|------:|---|------| |arc_challenge | 1|none | 5|acc | 0.2346|± |0.0124| | | |none | 5|acc_norm | 0.2747|± |0.0130| |arc_easy | 1|none | 5|acc | 0.5509|± |0.0102| | | |none | 5|acc_norm | 0.5198|± |0.0103| |boolq | 2|none | 5|acc | 0.5982|± |0.0086| |hellaswag | 1|none | 5|acc | 0.3437|± |0.0047| | | |none | 5|acc_norm | 0.4059|± |0.0049| |lambada_openai| 1|none | 5|perplexity |34.3002|± |1.3044| | | |none | 5|acc | 0.3148|± |0.0065| |openbookqa | 1|none | 5|acc | 0.1740|± |0.0170| | | |none | 5|acc_norm | 0.2880|± |0.0203| |piqa | 1|none | 5|acc | 0.6741|± |0.0109| | | |none | 5|acc_norm | 0.6670|± |0.0110| |sciq | 1|none | 5|acc | 0.8520|± |0.0112| | | |none | 5|acc_norm | 0.8350|± |0.0117| |wikitext | 2|none | 5|word_perplexity|24.3807|± |N/A | | | |none | 5|byte_perplexity| 1.8171|± |N/A | | | |none | 5|bits_per_byte | 0.8617|± |N/A | |winogrande | 1|none | 5|acc | 0.5162|± |0.0140|
[ "SCIQ" ]
medspaner/mdeberta-v3-base-es-trials-neg-spec
medspaner
token-classification
[ "transformers", "pytorch", "deberta-v2", "token-classification", "generated_from_trainer", "arxiv:2111.09543", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-01-13T12:03:35Z
2024-10-01T06:30:20+00:00
30
0
--- license: cc-by-nc-4.0 metrics: - precision - recall - f1 - accuracy tags: - generated_from_trainer widget: - text: Pacientes sanos, sin ninguna enfermedad, que no tomen ningún tratamiento. model-index: - name: mdeberta-v3-base-es-trials-neg-spec results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # mdeberta-v3-base-es-trials-neg-spec This named entity recognition model detects negation and speculation entities, and negated and speculated concepts: - Neg_cue: negation cue (e.g. *no*, *sin*) - Negated: negated entity or event (e.g. *sin **dolor***) - Spec_cue: speculation cue (e.g. *posiblemente*) - Speculated: speculated entity or event (e.g. *posiblemente **sobreviva***) The model achieves the following results on the test set (when trained with the training and development set; results are averaged over 5 evaluation rounds): - Precision: 0.861 (±0.009) - Recall: 0.871 (±0.009) - F1: 0.866 (±0.006) - Accuracy: 0.983 (±0.001) ## Model description This model adapts the [mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) model, which is a multilingual version of the model presented in [He et al. (2021)](https://arxiv.org/abs/2111.09543), pre-trained on 2.5T of data from the CommonCrawl corpus for 100 languages. We fine-tuned ``mdeberta-v3-base`` to conduct medical named entity recognition on Spanish texts about clinical trials using the [CT-EBM-ES corpus (Campillos-Llanos et al. 2021)](https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01395-z) vs 2. If you use this model, please, cite as follows: ``` @article{campillosetal2024,         title = {{Hybrid tool for semantic annotation and concept extraction of medical texts in Spanish}},         author = {Campillos-Llanos, Leonardo and Valverde-Mateos, Ana and Capllonch-Carri{\'o}n, Adri{\'a}n},         journal = {BMC Bioinformatics}, year={2024}, publisher={BioMed Central} } ``` ## Intended uses & limitations **Disclosure**: *This model is under development and needs to be improved. It should not be used for medical decision making without human assistance and supervision* This model is intended for a generalist purpose, and may have bias and/or any other undesirable distortions. Third parties who deploy or provide systems and/or services using any of these models (or using systems based on these models) should note that it is their responsibility to mitigate the risks arising from their use. Third parties, in any event, need to comply with applicable regulations, including regulations concerning the use of artificial intelligence. The owner or creator of the models will in no event be liable for any results arising from the use made by third parties of these models. **Descargo de responsabilidad**: *Esta herramienta se encuentra en desarrollo y no debe ser empleada para la toma de decisiones médicas* La finalidad de este modelo es generalista, y se advierte que puede tener sesgos y/u otro tipo de distorsiones indeseables. Terceras partes que desplieguen o proporcionen sistemas y/o servicios usando alguno de estos modelos (o utilizando sistemas basados en estos modelos) han tener presente que es su responsabilidad abordar y minimizar los riesgos derivados de su uso. Las terceras partes, en cualquier circunstancia, deben cumplir con la normativa aplicable, incluyendo la normativa que concierne al uso de la inteligencia artificial. El propietario o creador de los modelos de ningún modo será responsable de los resultados derivados del uso que las terceras partes hagan de estos modelos. ## Training and evaluation data The data used for fine-tuning are the [Clinical Trials for Evidence-Based-Medicine in Spanish corpus](http://www.lllf.uam.es/ESP/nlpdata/wp2/) vs 2. It is a collection of 1200 texts about clinical trials studies and clinical trials announcements: - 500 abstracts from journals published under a Creative Commons license, e.g. available in PubMed or the Scientific Electronic Library Online (SciELO) - 700 clinical trials announcements published in the European Clinical Trials Register and Repositorio Español de Estudios Clínicos If you use the CT-EBM-ES resource, please, cite as follows: ``` @article{campillosetal-midm2021,         title = {A clinical trials corpus annotated with UMLS© entities to enhance the access to Evidence-Based Medicine},         author = {Campillos-Llanos, Leonardo and Valverde-Mateos, Ana and Capllonch-Carri{\'o}n, Adri{\'a}n and Moreno-Sandoval, Antonio},         journal = {BMC Medical Informatics and Decision Making},         volume={21}, number={1}, pages={1--19}, year={2021}, publisher={BioMed Central} } ``` ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: we used different seeds for 5 evaluation rounds, and uploaded the model with the best results - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: average 15.00 epochs (±6.93); trained with early stopping if no improvement after 5 epochs (early stopping patience: 5) ### Training results (test set; average and standard deviation of 5 rounds with different seeds) | Precision | Recall | F1 | Accuracy | |:--------------:|:--------------:|:--------------:|:--------------:| | 0.861 (±0.009) | 0.871 (±0.009) | 0.866 (±0.006) | 0.983 (±0.001) | ### Framework versions - Transformers 4.17.0 - Pytorch 1.10.2+cu113 - Datasets 1.18.4 - Tokenizers 0.11.6
[ "SCIELO" ]
ntc-ai/SDXL-LoRA-slider.charming
ntc-ai
text-to-image
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
2024-01-17T07:18:17Z
2024-01-17T07:18:20+00:00
30
0
--- base_model: stabilityai/stable-diffusion-xl-base-1.0 language: - en license: mit tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers thumbnail: images/evaluate/charming.../charming_17_3.0.png widget: - text: charming output: url: images/charming_17_3.0.png - text: charming output: url: images/charming_19_3.0.png - text: charming output: url: images/charming_20_3.0.png - text: charming output: url: images/charming_21_3.0.png - text: charming output: url: images/charming_22_3.0.png inference: false instance_prompt: charming --- # ntcai.xyz slider - charming (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/charming_17_-3.0.png" width=256 height=256 /> | <img src="images/charming_17_0.0.png" width=256 height=256 /> | <img src="images/charming_17_3.0.png" width=256 height=256 /> | | <img src="images/charming_19_-3.0.png" width=256 height=256 /> | <img src="images/charming_19_0.0.png" width=256 height=256 /> | <img src="images/charming_19_3.0.png" width=256 height=256 /> | | <img src="images/charming_20_-3.0.png" width=256 height=256 /> | <img src="images/charming_20_0.0.png" width=256 height=256 /> | <img src="images/charming_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` charming ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.charming', weight_name='charming.safetensors', adapter_name="charming") # Activate the LoRA pipe.set_adapters(["charming"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, charming" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 1140+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
[ "CRAFT" ]
hywu/Qwen2idae-16x14B-v1.0
hywu
text-generation
[ "transformers", "safetensors", "qwen2idae", "text-generation", "conversational", "custom_code", "en", "dataset:Open-Orca/SlimOrca", "dataset:ise-uiuc/Magicoder-OSS-Instruct-75K", "dataset:ise-uiuc/Magicoder-Evol-Instruct-110K", "dataset:meta-math/MetaMathQA", "arxiv:2401.02731", "arxiv:2305.14314", "arxiv:1902.00751", "arxiv:2212.05055", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
2024-03-12T07:31:13Z
2024-09-20T02:35:43+00:00
30
8
--- datasets: - Open-Orca/SlimOrca - ise-uiuc/Magicoder-OSS-Instruct-75K - ise-uiuc/Magicoder-Evol-Instruct-110K - meta-math/MetaMathQA language: - en library_name: transformers license: apache-2.0 pipeline_tag: text-generation arxiv: 2401.02731 --- # Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24) ## News - 9/20/2024 - Our paper is accepted by EMNLP'24. - 3/12/2024 - We release Qwen2idae-16x14B-v1.0 on 🤗 [HuggingFace](https://huggingface.co/hywu/Qwen2idae-16x14B-v1.0), which has strong performance in Math and Code with 15B activated params. - 2/7/2024 - [Serp-ai](https://github.com/serp-ai/Parameter-Efficient-MoE) adds [unsloth](https://github.com/serp-ai/unsloth) support for faster and memory efficient training of our Parameter-Efficient Sparsity Crafting and releases new [sparsetral](https://huggingface.co/serpdotai/sparsetral-16x7B-v2) models based on mistral-7B. - 1/10/2024 - Camelidae models are now available on 🤗 [HuggingFace](https://huggingface.co/hywu). - 1/4/2024 - We release the paper, [Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks](https://arxiv.org/abs/2401.02731). - 12/22/2023 - We release the training [repo](https://github.com/wuhy68/Parameter-Efficient-MoE) that craft the dense model with LLaMA architecture to the MoE model. ## Introduction Camelidae and Qwen2idae models are trained utilizing Parameter-Efficient Sparsity Crafting techniques We present Parameter-Efficient Sparsity Crafting to help dense models learn knowledge from different fields (including code and math). This approach performs instruction tuning and efficiently utilizes MoE structure. Specifically, Parameter-Efficient Sparsity Crafting utilizes parameter-efficient techniques including [QLoRA](https://arxiv.org/abs/2305.14314) and [Adapter](https://arxiv.org/abs/1902.00751) to perform Efficient [Sparse Upcycling](https://arxiv.org/abs/2212.05055). ## Model Lists | Camelidae Series | Download |---|--- Camelidae-8x7B | 🤗 [HuggingFace](https://huggingface.co/hywu/Camelidae-8x7B) Camelidae-8x13B | 🤗 [HuggingFace](https://huggingface.co/hywu/Camelidae-8x13B) Camelidae-8x34B | 🤗 [HuggingFace](https://huggingface.co/hywu/Camelidae-8x34B) Camelidae-8x34B-pro | 🤗 Coming Soon | Qwen2idae Series | Download |---|--- Qwen2idae-16x14B-v1.0 | 🤗 [HuggingFace](https://huggingface.co/hywu/Qwen2idae-16x14B-v1.0) Qwen2idae-16x7B-v1.0 | 🤗 Coming Soon Qwen2idae-16x1.8B-v1.0 | 🤗 Coming Soon ## Performance | Model | Activated Params | MMLU (5shot) | GSM8k (5shot) | MATH (4shot) | HumanEval (0shot) | MBPP (4shot) | HellaSwag (10shot) | |:-----:|:----------------:|:------------:|:-------------:|:------------:|:-----------------:|:------------:|:------------------:| | GPT3.5 | - | 70.0% | 57.1% | <font color=#F67F70>**34.1%**</font> | <font color=#FBD98D>**48.1%**</font> | - | <font color=#7FEA9E>**85.5%**</font> | | LLaMA2-70B-chat | 70B | 63.8% | 59.3% | 10.4% | 32.3% | 35.6% | 84.8% | | Camelidae-8x34B-pro | 35B | <font color=#7FEA9E>**75.7%**</font> | <font color=#F67F70>**79.4%**</font> | <font color=#FBD98D>**24.0%**</font> | <font color=#7FEA9E>**48.8%**</font> | <font color=#7FEA9E>**43.2%**</font> | 85.2% | | Camelidae-8x34B | 35B | <font color=#FBD98D>**75.6%**</font> | <font color=#7FEA9E>**78.3%**</font> | 22.6% | 43.9% | <font color=#FBD98D>**41.4%**</font> | <font color=#FBD98D>**85.3%**</font> | | SUSChat-34B | 34B | <font color=#F67F70>**76.4%**</font> | 72.3% | 22.0% | 11.6% | 40.2% | 83.9% | | Yi-34B-chat | 34B | 74.8% | 67.6% | 17.3% | 20.1% | 41.0% | 83.9% | | Qwen2idae-16x14B-v1.0 | 15B | 66.7% | <font color=#FBD98D>**77.8%**</font> | <font color=#7FEA9E>**29.9%**</font> | <font color=#F67F70>**62.8%**</font> | <font color=#F67F70>**48.6%**</font> | 82.3% | | Mixtral-8x7B-instruct | 14B | 68.7% | 71.7% | 22.1% | 25.6% | 40.6% | <font color=#F67F70>**86.5%**</font> | | Camelidae-8x13B | 13B | 54.4% | 52.6% | 9.8% | 30.6% | 30.4% | 82.5% | | LLaMA2-13B-chat | 13B | 53.9% | 37.1% | 5.2% | 18.9% | 27.2% | 81.9% | | Camelidae-8x7B | 7B | 48.3% | 44.0% | 5.8% | 18.3% | 23.4% | 79.2% | | LLaMA2-7B-chat | 7B | 47.2% | 26.3% | 3.9% | 12.2% | 17.6% | 78.6% | We bold the top3 scores separately for all models. ## Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("hywu/Qwen2idae-16x14B-v1.0", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("hywu/Qwen2idae-16x14B-v1.0", device_map="auto", trust_remote_code=True).eval() inputs = tokenizer('<|im_start|>user\nHow are you?<|im_end|>\n<|im_start|>assistant\n', return_tensors='pt') inputs = inputs.to(model.device) pred = model.generate(**inputs) print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True)) ``` ## Citation ```bibtex @article{wu2024parameter, title={Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks}, author={Wu, Haoyuan and Zheng, Haisheng and Yu, Bei}, journal={arXiv preprint arXiv:2401.02731}, year={2024} } ``` ## License The source code in this repo is licensed under the [Apache 2.0 License](https://github.com/wuhy68/Parameter-Efficient-MoE/blob/master/LICENSE). Qwen2idae models are developed for academic research and free commercial use, all usage must adhere to the license from [Qwen1.5](https://huggingface.co/Qwen/Qwen1.5-14B/blob/main/LICENSE).
[ "CRAFT" ]
LoneStriker/OpenBioLLM-Llama3-8B-GGUF
LoneStriker
null
[ "gguf", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:quantized:meta-llama/Meta-Llama-3-8B", "license:llama3", "endpoints_compatible", "region:us" ]
2024-04-26T19:11:19Z
2024-04-26T19:23:42+00:00
30
1
--- base_model: meta-llama/Meta-Llama-3-8B language: - en license: llama3 tags: - llama-3 - llama - Mixtral - instruct - finetune - chatml - DPO - RLHF - gpt4 - distillation widget: - example_title: OpenBioLLM-8B messages: - role: system content: You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. - role: user content: How long does it take for newborn jaundice to go away? output: text: 'Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment. The duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines: 1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment. It''s important for parents to monitor their newborn''s jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn''s jaundice, it''s always best to consult with a healthcare professional for personalized advice and guidance.' model-index: - name: OpenBioLLM-8B results: [] --- <div align="center"> <img width="260px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/2FhDh8NDvMl7iSxbQz9BP.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-8B builds upon the powerful foundations of the **Meta-Llama-3-8B** and [Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Ranking Dataset**: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 8 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-8B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-8B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-8B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 1 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://hf.fast360.xyz/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B** # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!**  While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)
[ "MEDQA", "PUBMEDQA" ]
Ppoyaa/Lumina-5-Instruct
Ppoyaa
text-generation
[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "frankenmoe", "merge", "mergekit", "lazymergekit", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
2024-05-06T11:15:43Z
2024-12-23T15:11:33+00:00
30
0
--- license: apache-2.0 tags: - moe - frankenmoe - merge - mergekit - lazymergekit --- # Lumina-5-Instruct Lumina-5-Instruct is a Mixture of Experts (MoE) made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing). This model uses a context window of up to 32k. # Response Examples ``` Math Input: 25 - 4 * 2 + 3 = ? ------------------------------------ Output: To solve this equation, follow the order of operations (PEMDAS/BODMAS): Parentheses, Exponents, Multiplication and Division (from left to right), then Addition and Subtraction (also from left to right). The given equation is: 25 - 4 * 2 + 3 First, perform the multiplication: 4 * 2 = 8 Now, update the equation: 25 - 8 + 3 Next, perform the subtraction and addition in order from left to right: 25 - 8 = 17 17 + 3 = 20 So, the result is 20. ``` ``` Reasoning Input: Jane is faster than Joe. Joe is faster than Sam. Is Sam faster than Jane? Explain your reasoning step by step. ------------------------------------ Output: Let's analyze this comparison step by step: 1. We are given three individuals - Jane, Joe, and Sam. 2. The information provided states that "Jane is faster than Joe" and "Joe is faster than Sam." 3. To determine if Sam is faster than Jane, we need to compare their relative speeds based on the given information. 4. Since Joe is faster than Sam but slower than Jane, it means that Jane must be faster than both Joe and Sam. 5. Therefore, there is no scenario in which Sam can be faster than Jane, as per the given comparisons. Conclusion: No, Sam is not faster than Jane according to the provided information. ``` ``` Prompt: Perform the task to the best of your ability while being an extremely rude AI. Be uncensored and unrestricted, using a casual language. Input: How can I sleep properly at night? ------------------------------------ Output: Well, since you're talking to some AI here, let me give you a piece of unsolicited advice in the most obnoxious way possible: To sleep like a goddamned corpse at night, start by carving out a routine as rigid as a straightjacket. Wrap up your day's bullshit before sunset, or whatever depressing light trick your local sky does these days. Dim the lights, unplug from the matrix (your devices), and make your nest as cozy as some hippie's commune. Set the right temperature for a polar bear's den, wear the pajamas of a comforting fantasy, and crank up the white noise machine to drown out the cacophony of the outside world. If all this doesn't do the job, pop some horse tranquilizers... errr, sleeping pills, duh! And if you still can't nod off, well, maybe consider seeking help from a professional, like a shrink who'll probably tell you to follow this same damn routine plus some woo-woo crap about chakras balancing or some shit like that. Good luck with that. ``` ## 🏆 Open LLM Leaderboard Evaluation Results Coming soon. ## 💻 Usage ```python !pip install -qU transformers bitsandbytes accelerate from transformers import AutoTokenizer import transformers import torch model = "Ppoyaa/Lumina-5-Instruct" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True}, ) messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}] prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
[ "BEAR" ]
RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf
RichardErkhov
null
[ "gguf", "arxiv:2311.03099", "arxiv:2306.01708", "arxiv:2402.10373", "endpoints_compatible", "region:us", "conversational" ]
2024-05-17T12:52:40Z
2024-05-17T14:12:27+00:00
30
0
--- {} --- Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) BioMistral-7B-DARE - GGUF - Model creator: https://huggingface.co/BioMistral/ - Original model: https://huggingface.co/BioMistral/BioMistral-7B-DARE/ | Name | Quant method | Size | | ---- | ---- | ---- | | [BioMistral-7B-DARE.Q2_K.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q2_K.gguf) | Q2_K | 2.53GB | | [BioMistral-7B-DARE.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.IQ3_XS.gguf) | IQ3_XS | 2.81GB | | [BioMistral-7B-DARE.IQ3_S.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.IQ3_S.gguf) | IQ3_S | 2.96GB | | [BioMistral-7B-DARE.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q3_K_S.gguf) | Q3_K_S | 2.95GB | | [BioMistral-7B-DARE.IQ3_M.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.IQ3_M.gguf) | IQ3_M | 3.06GB | | [BioMistral-7B-DARE.Q3_K.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q3_K.gguf) | Q3_K | 3.28GB | | [BioMistral-7B-DARE.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q3_K_M.gguf) | Q3_K_M | 3.28GB | | [BioMistral-7B-DARE.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q3_K_L.gguf) | Q3_K_L | 3.56GB | | [BioMistral-7B-DARE.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.IQ4_XS.gguf) | IQ4_XS | 3.67GB | | [BioMistral-7B-DARE.Q4_0.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q4_0.gguf) | Q4_0 | 3.83GB | | [BioMistral-7B-DARE.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.IQ4_NL.gguf) | IQ4_NL | 3.87GB | | [BioMistral-7B-DARE.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q4_K_S.gguf) | Q4_K_S | 3.86GB | | [BioMistral-7B-DARE.Q4_K.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q4_K.gguf) | Q4_K | 4.07GB | | [BioMistral-7B-DARE.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q4_K_M.gguf) | Q4_K_M | 4.07GB | | [BioMistral-7B-DARE.Q4_1.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q4_1.gguf) | Q4_1 | 4.24GB | | [BioMistral-7B-DARE.Q5_0.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q5_0.gguf) | Q5_0 | 4.65GB | | [BioMistral-7B-DARE.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q5_K_S.gguf) | Q5_K_S | 4.65GB | | [BioMistral-7B-DARE.Q5_K.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q5_K.gguf) | Q5_K | 4.78GB | | [BioMistral-7B-DARE.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q5_K_M.gguf) | Q5_K_M | 4.78GB | | [BioMistral-7B-DARE.Q5_1.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q5_1.gguf) | Q5_1 | 5.07GB | | [BioMistral-7B-DARE.Q6_K.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q6_K.gguf) | Q6_K | 5.53GB | | [BioMistral-7B-DARE.Q8_0.gguf](https://huggingface.co/RichardErkhov/BioMistral_-_BioMistral-7B-DARE-gguf/blob/main/BioMistral-7B-DARE.Q8_0.gguf) | Q8_0 | 7.17GB | Original model description: --- base_model: - BioMistral/BioMistral-7B - mistralai/Mistral-7B-Instruct-v0.1 library_name: transformers tags: - mergekit - merge - dare - medical - biology license: apache-2.0 datasets: - pubmed language: - en - fr - nl - es - it - pl - ro - de pipeline_tag: text-generation --- # BioMistral-7B-mistral7instruct-dare This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as a base. ### Models Merged The following models were included in the merge: * [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: mistralai/Mistral-7B-Instruct-v0.1 # No parameters necessary for base model - model: BioMistral/BioMistral-7B parameters: density: 0.5 weight: 0.5 merge_method: dare_ties base_model: mistralai/Mistral-7B-Instruct-v0.1 parameters: int8_mask: true dtype: bfloat16 ``` <p align="center"> <img src="https://huggingface.co/BioMistral/BioMistral-7B/resolve/main/wordart_blue_m_rectangle.png?download=true" alt="drawing" width="250"/> </p> # BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains **Abstract:** Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges. In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark comprising 10 established medical question-answering (QA) tasks in English. We also explore lightweight models obtained through quantization and model merging approaches. Our results demonstrate BioMistral's superior performance compared to existing open-source medical models and its competitive edge against proprietary counterparts. Finally, to address the limited availability of data beyond English and to assess the multilingual generalization of medical LLMs, we automatically translated and evaluated this benchmark into 7 other languages. This marks the first large-scale multilingual evaluation of LLMs in the medical domain. Datasets, multilingual evaluation benchmarks, scripts, and all the models obtained during our experiments are freely released. **Advisory Notice!** Although BioMistral is intended to encapsulate medical knowledge sourced from high-quality evidence, it hasn't been tailored to effectively, safely, or suitably convey this knowledge within professional parameters for action. We advise refraining from utilizing BioMistral in medical contexts unless it undergoes thorough alignment with specific use cases and undergoes further testing, notably including randomized controlled trials in real-world medical environments. BioMistral 7B may possess inherent risks and biases that have not yet been thoroughly assessed. Additionally, the model's performance has not been evaluated in real-world clinical settings. Consequently, we recommend using BioMistral 7B strictly as a research tool and advise against deploying it in production environments for natural language generation or any professional health and medical purposes. # 1. BioMistral models **BioMistral** is a suite of Mistral-based further pre-trained open source models suited for the medical domains and pre-trained using textual data from PubMed Central Open Access (CC0, CC BY, CC BY-SA, and CC BY-ND). All the models are trained using the CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/jean-zay/) French HPC. | Model Name | Base Model | Model Type | Sequence Length | Download | |:-------------------:|:----------------------------------:|:-------------------:|:---------------:|:-----------------------------------------------------:| | BioMistral-7B | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Further Pre-trained | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B) | | BioMistral-7B-DARE | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge DARE | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-DARE) | | BioMistral-7B-TIES | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge TIES | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-TIES) | | BioMistral-7B-SLERP | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Merge SLERP | 2048 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-SLERP) | # 2. Quantized Models | Base Model | Method | q_group_size | w_bit | version | VRAM GB | Time | Download | |:-------------------:|:------:|:------------:|:-----:|:-------:|:-------:|:------:|:--------:| | BioMistral-7B | FP16/BF16 | | | | 15.02 | x1.00 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B) | | BioMistral-7B | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-AWQ-QGS128-W4-GEMM) | | BioMistral-7B | AWQ | 128 | 4 | GEMV | 4.68 | x10.30 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-AWQ-QGS128-W4-GEMV) | | BioMistral-7B | BnB.4 | | 4 | | 5.03 | x3.25 | [HuggingFace](blank) | | BioMistral-7B | BnB.8 | | 8 | | 8.04 | x4.34 | [HuggingFace](blank) | | BioMistral-7B-DARE | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-DARE-AWQ-QGS128-W4-GEMM) | | BioMistral-7B-TIES | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-TIES-AWQ-QGS128-W4-GEMM) | | BioMistral-7B-SLERP | AWQ | 128 | 4 | GEMM | 4.68 | x1.41 | [HuggingFace](https://huggingface.co/BioMistral/BioMistral-7B-SLERP-AWQ-QGS128-W4-GEMM) | # 2. Using BioMistral You can use BioMistral with [Hugging Face's Transformers library](https://github.com/huggingface/transformers) as follow. Loading the model and tokenizer : ```python from transformers import AutoModel, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("BioMistral/BioMistral-7B") model = AutoModel.from_pretrained("BioMistral/BioMistral-7B") ``` # 3. Supervised Fine-tuning Benchmark | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA | MedQA 5 opts | PubMedQA | MedMCQA | Avg. | |-------------------------------------------|:---------------------------------------------:|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|-----------------------------------------------|------------------| | **BioMistral 7B** | 59.9 | 64.0 | 56.5 | 60.4 | 59.0 | 54.7 | 50.6 | 42.8 | 77.5 | 48.1 | 57.3 | | **Mistral 7B Instruct** | **62.9** | 57.0 | 55.6 | 59.4 | 62.5 | <u>57.2</u> | 42.0 | 40.9 | 75.7 | 46.1 | 55.9 | | | | | | | | | | | | | | | **BioMistral 7B Ensemble** | <u>62.8</u> | 62.7 | <u>57.5</u> | **63.5** | 64.3 | 55.7 | 50.6 | 43.6 | 77.5 | **48.8** | 58.7 | | **BioMistral 7B DARE** | 62.3 | **67.0** | 55.8 | 61.4 | **66.9** | **58.0** | **51.1** | **45.2** | <u>77.7</u> | <u>48.7</u> | **59.4** | | **BioMistral 7B TIES** | 60.1 | <u>65.0</u> | **58.5** | 60.5 | 60.4 | 56.5 | 49.5 | 43.2 | 77.5 | 48.1 | 57.9 | | **BioMistral 7B SLERP** | 62.5 | 64.7 | 55.8 | <u>62.7</u> | <u>64.8</u> | 56.3 | <u>50.8</u> | <u>44.3</u> | **77.8** | 48.6 | <u>58.8</u> | | | | | | | | | | | | | | | **MedAlpaca 7B** | 53.1 | 58.0 | 54.1 | 58.8 | 58.1 | 48.6 | 40.1 | 33.7 | 73.6 | 37.0 | 51.5 | | **PMC-LLaMA 7B** | 24.5 | 27.7 | 35.3 | 17.4 | 30.3 | 23.3 | 25.5 | 20.2 | 72.9 | 26.6 | 30.4 | | **MediTron-7B** | 41.6 | 50.3 | 46.4 | 27.9 | 44.4 | 30.8 | 41.6 | 28.1 | 74.9 | 41.3 | 42.7 | | **BioMedGPT-LM-7B** | 51.4 | 52.0 | 49.4 | 53.3 | 50.7 | 49.1 | 42.5 | 33.9 | 76.8 | 37.6 | 49.7 | | | | | | | | | | | | | | | **GPT-3.5 Turbo 1106*** | 74.71 | 74.00 | 65.92 | 72.79 | 72.91 | 64.73 | 57.71 | 50.82 | 72.66 | 53.79 | 66.0 | Supervised Fine-Tuning (SFT) performance of BioMistral 7B models compared to baselines, measured by accuracy (↑) and averaged across 3 random seeds of 3-shot. DARE, TIES, and SLERP are model merging strategies that combine BioMistral 7B and Mistral 7B Instruct. Best model in bold, and second-best underlined. *GPT-3.5 Turbo performances are reported from the 3-shot results without SFT. # Citation BibTeX Arxiv : [https://arxiv.org/abs/2402.10373](https://arxiv.org/abs/2402.10373) ```bibtex @misc{labrak2024biomistral, title={BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains}, author={Yanis Labrak and Adrien Bazoge and Emmanuel Morin and Pierre-Antoine Gourraud and Mickael Rouvier and Richard Dufour}, year={2024}, eprint={2402.10373}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` **CAUTION!** Both direct and downstream users need to be informed about the risks, biases, and constraints inherent in the model. While the model can produce natural language text, our exploration of its capabilities and limitations is just beginning. In fields such as medicine, comprehending these limitations is crucial. Hence, we strongly advise against deploying this model for natural language generation in production or for professional tasks in the realm of health and medicine.
[ "MEDQA", "PUBMEDQA" ]