id
stringlengths 6
113
| author
stringlengths 2
36
| task_category
stringclasses 42
values | tags
listlengths 1
4.05k
| created_time
timestamp[ns, tz=UTC]date 2022-03-02 23:29:04
2025-04-10 08:38:38
| last_modified
stringdate 2020-05-14 13:13:12
2025-04-19 04:15:39
| downloads
int64 0
118M
| likes
int64 0
4.86k
| README
stringlengths 30
1.01M
| matched_bigbio_names
listlengths 1
8
⌀ | is_bionlp
stringclasses 3
values | model_cards
stringlengths 0
1M
| metadata
stringlengths 2
698k
| source
stringclasses 2
values | matched_task
listlengths 1
10
⌀ | __index_level_0__
int64 0
46.9k
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
cpark2/distilbert-base-uncased-finetuned-emotion
|
cpark2
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-03-20T14:38:39Z |
2023-03-20T16:46:35+00:00
| 10 | 0 |
---
datasets:
- emotion
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.9185
name: Accuracy
- type: f1
value: 0.9185302693682422
name: F1
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2192
- Accuracy: 0.9185
- F1: 0.9185
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8004 | 1.0 | 250 | 0.3111 | 0.9025 | 0.9003 |
| 0.2454 | 2.0 | 500 | 0.2192 | 0.9185 | 0.9185 |
### Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2192
- Accuracy: 0.9185
- F1: 0.9185
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8004 | 1.0 | 250 | 0.3111 | 0.9025 | 0.9003 |
| 0.2454 | 2.0 | 500 | 0.2192 | 0.9185 | 0.9185 |
### Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
|
{"datasets": ["emotion"], "license": "apache-2.0", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetuned-emotion", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.9185, "name": "Accuracy"}, {"type": "f1", "value": 0.9185302693682422, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,490 |
robby1421/distilbert-base-uncased-finetuned-cola
|
robby1421
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-02-13T01:03:25Z |
2023-02-13T13:43:35+00:00
| 23 | 0 |
---
datasets:
- glue
license: apache-2.0
metrics:
- matthews_correlation
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-cola
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
config: cola
split: validation
args: cola
metrics:
- type: matthews_correlation
value: 0.5288024095653031
name: Matthews Correlation
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8528
- Matthews Correlation: 0.5288
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5283 | 1.0 | 535 | 0.5465 | 0.4022 |
| 0.3503 | 2.0 | 1070 | 0.5279 | 0.4750 |
| 0.236 | 3.0 | 1605 | 0.5614 | 0.5192 |
| 0.1733 | 4.0 | 2140 | 0.7946 | 0.5285 |
| 0.1223 | 5.0 | 2675 | 0.8528 | 0.5288 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8528
- Matthews Correlation: 0.5288
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5283 | 1.0 | 535 | 0.5465 | 0.4022 |
| 0.3503 | 2.0 | 1070 | 0.5279 | 0.4750 |
| 0.236 | 3.0 | 1605 | 0.5614 | 0.5192 |
| 0.1733 | 4.0 | 2140 | 0.7946 | 0.5285 |
| 0.1223 | 5.0 | 2675 | 0.8528 | 0.5288 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
|
{"datasets": ["glue"], "license": "apache-2.0", "metrics": ["matthews_correlation"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetuned-cola", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "config": "cola", "split": "validation", "args": "cola"}, "metrics": [{"type": "matthews_correlation", "value": 0.5288024095653031, "name": "Matthews Correlation"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,491 |
gaudi/opus-mt-es-eo-ctranslate2
|
gaudi
|
translation
|
[
"transformers",
"marian",
"ctranslate2",
"translation",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 2024-07-22T15:44:32Z |
2024-10-19T02:37:22+00:00
| 7 | 0 |
---
license: apache-2.0
tags:
- ctranslate2
- translation
---
# Repository General Information
## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)!
- Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-es-eo)
- This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2).
- This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil).
# What is CTranslate2?
[CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models.
CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.
CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include:
- Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper
- Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon
- Encoder-only models: BERT, DistilBERT, XLM-RoBERTa
The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration.
# CTranslate2 Benchmarks
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset.
The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers.
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings.
## CPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 |
| Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 |
| Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 |
| CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 |
| CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 |
## GPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 |
| Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 |
| CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 |
| CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 |
`Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.`
**Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br />
**Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-es-eo).**
## Internal Benchmarks
Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality.
# CTranslate2 Installation
```bash
pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0
```
### ct2-transformers-converter Command Used:
```bash
ct2-transformers-converter --model Helsinki-NLP/opus-mt-es-eo --output_dir ./ctranslate2/opus-mt-es-eo-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16
```
# CTranslate2 Converted Checkpoint Information:
**Compatible With:**
- [ctranslate2](https://github.com/OpenNMT/CTranslate2)
- [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
**Compute Type:**
- `compute_type=int8_float16` for `device="cuda"`
- `compute_type=int8` for `device="cpu"`
# Sample Code - ctranslate2
#### Clone the repository to the working directory or wherever you wish to store the model artifacts. ####
```bash
git clone https://huggingface.co/gaudi/opus-mt-es-eo-ctranslate2
```
#### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. ####
```python
from ctranslate2 import Translator
import transformers
model_dir = "./opus-mt-es-eo-ctranslate2" # Path to model directory.
translator = Translator(
model_path=model_dir,
device="cuda", # cpu, cuda, or auto.
inter_threads=1, # Maximum number of parallel translations.
intra_threads=4, # Number of OpenMP threads per translator.
compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda.
)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir)
source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX."))
results = translator.translate_batch([source])
target = results[0].hypotheses[0]
print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))
```
# Sample Code - hf-hub-ctranslate2
**Derived From [michaelfeil](https://huggingface.co/michaelfeil):**
```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer
model_name = "gaudi/opus-mt-es-eo-ctranslate2"
model = TranslatorCT2fromHfHub(
model_name_or_path=model_name,
device="cuda",
compute_type="int8_float16",
tokenizer=AutoTokenizer.from_pretrained(model_name)
)
outputs = model.generate(
text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"],
)
print(outputs)
```
# License and other remarks:
License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-es-eo) by Helsinki-NLP.
| null |
Non_BioNLP
|
# Repository General Information
## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)!
- Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-es-eo)
- This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2).
- This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil).
# What is CTranslate2?
[CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models.
CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.
CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include:
- Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper
- Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon
- Encoder-only models: BERT, DistilBERT, XLM-RoBERTa
The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration.
# CTranslate2 Benchmarks
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset.
The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers.
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings.
## CPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 |
| Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 |
| Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 |
| CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 |
| CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 |
## GPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 |
| Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 |
| CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 |
| CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 |
`Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.`
**Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br />
**Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-es-eo).**
## Internal Benchmarks
Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality.
# CTranslate2 Installation
```bash
pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0
```
### ct2-transformers-converter Command Used:
```bash
ct2-transformers-converter --model Helsinki-NLP/opus-mt-es-eo --output_dir ./ctranslate2/opus-mt-es-eo-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16
```
# CTranslate2 Converted Checkpoint Information:
**Compatible With:**
- [ctranslate2](https://github.com/OpenNMT/CTranslate2)
- [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
**Compute Type:**
- `compute_type=int8_float16` for `device="cuda"`
- `compute_type=int8` for `device="cpu"`
# Sample Code - ctranslate2
#### Clone the repository to the working directory or wherever you wish to store the model artifacts. ####
```bash
git clone https://huggingface.co/gaudi/opus-mt-es-eo-ctranslate2
```
#### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. ####
```python
from ctranslate2 import Translator
import transformers
model_dir = "./opus-mt-es-eo-ctranslate2" # Path to model directory.
translator = Translator(
model_path=model_dir,
device="cuda", # cpu, cuda, or auto.
inter_threads=1, # Maximum number of parallel translations.
intra_threads=4, # Number of OpenMP threads per translator.
compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda.
)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir)
source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX."))
results = translator.translate_batch([source])
target = results[0].hypotheses[0]
print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))
```
# Sample Code - hf-hub-ctranslate2
**Derived From [michaelfeil](https://huggingface.co/michaelfeil):**
```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer
model_name = "gaudi/opus-mt-es-eo-ctranslate2"
model = TranslatorCT2fromHfHub(
model_name_or_path=model_name,
device="cuda",
compute_type="int8_float16",
tokenizer=AutoTokenizer.from_pretrained(model_name)
)
outputs = model.generate(
text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"],
)
print(outputs)
```
# License and other remarks:
License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-es-eo) by Helsinki-NLP.
|
{"license": "apache-2.0", "tags": ["ctranslate2", "translation"]}
|
task
|
[
"TRANSLATION"
] | 41,493 |
ichanchiu/Llama-3.1-Omni-FinAI-70B
|
ichanchiu
| null |
[
"safetensors",
"llama",
"finance",
"Llama3.1",
"en",
"base_model:meta-llama/Llama-3.1-70B-Instruct",
"base_model:finetune:meta-llama/Llama-3.1-70B-Instruct",
"region:us"
] | 2024-11-14T00:47:44Z |
2024-11-14T17:46:09+00:00
| 19 | 1 |
---
base_model:
- meta-llama/Llama-3.1-70B-Instruct
language:
- en
tags:
- finance
- Llama3.1
---
# Llama-3.1-Omni-FinAI-70B Model Card
## Model Overview (Built with Llama)
Llama-3.1-Omni-FinAI-70B is a pre-trained large language model optimized for finance-specific fine-tuning applications. Based on the LLaMA 3.1 70B architecture, this model was pre-trained on 143 billion tokens of high-quality financial texts. Llama-3.1-Omni-FinAI-70B provides a foundation for further fine-tuning in specialized financial analysis tasks.
## Model Details
- **Base Model**: Llama-3.1-70B-Instruct
- **Training Data**:
- SEC 10-K, 10-Q, and 8-K filings
- Reuters News data (RCV1, TRC2)
- Finance-specific papers from Arxiv
- Financial discussions from Reddit
- Wikipedia
- **Primary Use Case**: Pre-training for finance-specific fine-tuning, allowing users to leverage Llama-3.1-Omni-FinAI-70B's foundational financial language understanding.
## Use Cases
Llama-3.1-Omni-FinAI-70B is designed as a base model for finance-specific fine-tuning tasks, supporting applications such as:
- Sentiment Analysis
- Stock Movement Prediction
- QA Instruction
- Summarization
- Predictive Financial Analysis
## Training Process
Llama-3.1-Omni-FinAI-70B was trained using the NVIDIA NeMo framework on 64 H100 GPUs, utilizing a diverse dataset that ensures robust performance for fine-tuning in finance-related applications.
## Limitations
This model is pre-trained for finance-specific fine-tuning tasks and may require additional fine-tuning for specialized applications. Due to its large size, substantial computational resources are recommended for deployment.
## License
This model is licensed under the Llama 3.1 Community License.
## Citation
If you use the Llama-3.1-Omni-FinAI-70B model, please cite as follows:
> Chiu, I-Chan and Hung, Mao-Wei and Chen, Zih-Ching and Chiu, Jun-wei and Lin, Yang-Hsien and Lee, Cheng-Kuang and Huang, Eddie TC and See, Simon, Omni-FinAI: Unlocking Financial Disclosure Insights (October 30, 2024). Available at SSRN: https://ssrn.com/abstract=5004298
| null |
Non_BioNLP
|
# Llama-3.1-Omni-FinAI-70B Model Card
## Model Overview (Built with Llama)
Llama-3.1-Omni-FinAI-70B is a pre-trained large language model optimized for finance-specific fine-tuning applications. Based on the LLaMA 3.1 70B architecture, this model was pre-trained on 143 billion tokens of high-quality financial texts. Llama-3.1-Omni-FinAI-70B provides a foundation for further fine-tuning in specialized financial analysis tasks.
## Model Details
- **Base Model**: Llama-3.1-70B-Instruct
- **Training Data**:
- SEC 10-K, 10-Q, and 8-K filings
- Reuters News data (RCV1, TRC2)
- Finance-specific papers from Arxiv
- Financial discussions from Reddit
- Wikipedia
- **Primary Use Case**: Pre-training for finance-specific fine-tuning, allowing users to leverage Llama-3.1-Omni-FinAI-70B's foundational financial language understanding.
## Use Cases
Llama-3.1-Omni-FinAI-70B is designed as a base model for finance-specific fine-tuning tasks, supporting applications such as:
- Sentiment Analysis
- Stock Movement Prediction
- QA Instruction
- Summarization
- Predictive Financial Analysis
## Training Process
Llama-3.1-Omni-FinAI-70B was trained using the NVIDIA NeMo framework on 64 H100 GPUs, utilizing a diverse dataset that ensures robust performance for fine-tuning in finance-related applications.
## Limitations
This model is pre-trained for finance-specific fine-tuning tasks and may require additional fine-tuning for specialized applications. Due to its large size, substantial computational resources are recommended for deployment.
## License
This model is licensed under the Llama 3.1 Community License.
## Citation
If you use the Llama-3.1-Omni-FinAI-70B model, please cite as follows:
> Chiu, I-Chan and Hung, Mao-Wei and Chen, Zih-Ching and Chiu, Jun-wei and Lin, Yang-Hsien and Lee, Cheng-Kuang and Huang, Eddie TC and See, Simon, Omni-FinAI: Unlocking Financial Disclosure Insights (October 30, 2024). Available at SSRN: https://ssrn.com/abstract=5004298
|
{"base_model": ["meta-llama/Llama-3.1-70B-Instruct"], "language": ["en"], "tags": ["finance", "Llama3.1"]}
|
task
|
[
"SUMMARIZATION"
] | 41,495 |
cast42/my-awesome-setfit-model
|
cast42
|
text-classification
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 2023-08-22T11:05:02Z |
2023-08-22T11:05:20+00:00
| 11 | 0 |
---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# cast42/my-awesome-setfit-model
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("cast42/my-awesome-setfit-model")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
| null |
Non_BioNLP
|
# cast42/my-awesome-setfit-model
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("cast42/my-awesome-setfit-model")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
{"license": "apache-2.0", "pipeline_tag": "text-classification", "tags": ["setfit", "sentence-transformers", "text-classification"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,496 |
teacookies/autonlp-more_fine_tune_24465520-26265898
|
teacookies
|
question-answering
|
[
"transformers",
"pytorch",
"xlm-roberta",
"question-answering",
"autonlp",
"unk",
"dataset:teacookies/autonlp-data-more_fine_tune_24465520",
"co2_eq_emissions",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2021-10-25T09:22:22+00:00
| 112 | 0 |
---
datasets:
- teacookies/autonlp-data-more_fine_tune_24465520
language: unk
tags:
- autonlp
- question-answering
widget:
- text: Who loves AutoNLP?
context: Everyone loves AutoNLP
co2_eq_emissions: 82.78379967029494
---
# Model Trained Using AutoNLP
- Problem type: Extractive Question Answering
- Model ID: 26265898
- CO2 Emissions (in grams): 82.78379967029494
## Validation Metrics
- Loss: 0.5732079148292542
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"question": "Who loves AutoNLP?", "context": "Everyone loves AutoNLP"}' https://api-inference.huggingface.co/models/teacookies/autonlp-more_fine_tune_24465520-26265898
```
Or Python API:
```
import torch
from transformers import AutoModelForQuestionAnswering, AutoTokenizer
model = AutoModelForQuestionAnswering.from_pretrained("teacookies/autonlp-more_fine_tune_24465520-26265898", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("teacookies/autonlp-more_fine_tune_24465520-26265898", use_auth_token=True)
from transformers import BertTokenizer, BertForQuestionAnswering
question, text = "Who loves AutoNLP?", "Everyone loves AutoNLP"
inputs = tokenizer(question, text, return_tensors='pt')
start_positions = torch.tensor([1])
end_positions = torch.tensor([3])
outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)
loss = outputs.loss
start_scores = outputs.start_logits
end_scores = outputs.end_logits
```
| null |
Non_BioNLP
|
# Model Trained Using AutoNLP
- Problem type: Extractive Question Answering
- Model ID: 26265898
- CO2 Emissions (in grams): 82.78379967029494
## Validation Metrics
- Loss: 0.5732079148292542
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"question": "Who loves AutoNLP?", "context": "Everyone loves AutoNLP"}' https://api-inference.huggingface.co/models/teacookies/autonlp-more_fine_tune_24465520-26265898
```
Or Python API:
```
import torch
from transformers import AutoModelForQuestionAnswering, AutoTokenizer
model = AutoModelForQuestionAnswering.from_pretrained("teacookies/autonlp-more_fine_tune_24465520-26265898", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("teacookies/autonlp-more_fine_tune_24465520-26265898", use_auth_token=True)
from transformers import BertTokenizer, BertForQuestionAnswering
question, text = "Who loves AutoNLP?", "Everyone loves AutoNLP"
inputs = tokenizer(question, text, return_tensors='pt')
start_positions = torch.tensor([1])
end_positions = torch.tensor([3])
outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)
loss = outputs.loss
start_scores = outputs.start_logits
end_scores = outputs.end_logits
```
|
{"datasets": ["teacookies/autonlp-data-more_fine_tune_24465520"], "language": "unk", "tags": ["autonlp", "question-answering"], "widget": [{"text": "Who loves AutoNLP?", "context": "Everyone loves AutoNLP"}], "co2_eq_emissions": 82.78379967029494}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,497 |
gonced8/pegasus-conversational-qa
|
gonced8
|
text2text-generation
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"pegasus",
"text2text-generation",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2023-03-27T07:21:42+00:00
| 15 | 0 |
---
license: gpl-3.0
---
# rachael-scai
Generation model (Pegasus fine-tuned with QReCC) used in the participation of group Rachael for SCAI 2021.
GitHub repository can be found in: [gonced8/rachael-scai](https://github.com/gonced8/rachael-scai)
Gonçalo Raposo
## Cite
```bibtex
@InProceedings{Raposo2022,
author = {Gonçalo Raposo and Rui Ribeiro and Bruno Martins and Luísa Coheur},
booktitle = {44th European Conference on Information Retrieval},
title = {Question rewriting? Assessing its importance for conversational question answering},
year = {2022},
month = apr,
note = {This version of the contribution has been accepted for publication, after peer review but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/[not yet available]. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use \url{https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms}},
abstract = {In conversational question answering, systems must correctly interpret the interconnected interactions and generate knowledgeable answers, which may require the retrieval of relevant information from a background repository. Recent approaches to this problem leverage neural language models, although different alternatives can be considered in terms of modules for (a) representing user questions in context, (b) retrieving the relevant background information, and (c) generating the answer. This work presents a conversational question answering system designed specifically for the Search-Oriented Conversational AI (SCAI) shared task, and reports on a detailed analysis of its question rewriting module. In particular, we considered different variations of the question rewriting module to evaluate the influence on the subsequent components, and performed a careful analysis of the results obtained with the best system configuration. Our system achieved the best performance in the shared task and our analysis emphasizes the importance of the conversation context representation for the overall system performance.},
keywords = {conversational question answering, conversational search, question rewriting, transformer-based neural language models},
}
```
| null |
Non_BioNLP
|
# rachael-scai
Generation model (Pegasus fine-tuned with QReCC) used in the participation of group Rachael for SCAI 2021.
GitHub repository can be found in: [gonced8/rachael-scai](https://github.com/gonced8/rachael-scai)
Gonçalo Raposo
## Cite
```bibtex
@InProceedings{Raposo2022,
author = {Gonçalo Raposo and Rui Ribeiro and Bruno Martins and Luísa Coheur},
booktitle = {44th European Conference on Information Retrieval},
title = {Question rewriting? Assessing its importance for conversational question answering},
year = {2022},
month = apr,
note = {This version of the contribution has been accepted for publication, after peer review but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/[not yet available]. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use \url{https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms}},
abstract = {In conversational question answering, systems must correctly interpret the interconnected interactions and generate knowledgeable answers, which may require the retrieval of relevant information from a background repository. Recent approaches to this problem leverage neural language models, although different alternatives can be considered in terms of modules for (a) representing user questions in context, (b) retrieving the relevant background information, and (c) generating the answer. This work presents a conversational question answering system designed specifically for the Search-Oriented Conversational AI (SCAI) shared task, and reports on a detailed analysis of its question rewriting module. In particular, we considered different variations of the question rewriting module to evaluate the influence on the subsequent components, and performed a careful analysis of the results obtained with the best system configuration. Our system achieved the best performance in the shared task and our analysis emphasizes the importance of the conversation context representation for the overall system performance.},
keywords = {conversational question answering, conversational search, question rewriting, transformer-based neural language models},
}
```
|
{"license": "gpl-3.0"}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,498 |
aXhyra/irony_trained_1234567
|
aXhyra
|
text-classification
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:tweet_eval",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2021-12-12T12:22:43+00:00
| 12 | 0 |
---
datasets:
- tweet_eval
license: apache-2.0
metrics:
- f1
tags:
- generated_from_trainer
model-index:
- name: irony_trained_1234567
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: tweet_eval
type: tweet_eval
args: irony
metrics:
- type: f1
value: 0.6765645067647214
name: F1
---
<!-- 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. -->
# irony_trained_1234567
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6580
- F1: 0.6766
## 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: 2.6774391860025942e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 1234567
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.6608 | 1.0 | 716 | 0.6057 | 0.6704 |
| 0.5329 | 2.0 | 1432 | 0.8935 | 0.6621 |
| 0.3042 | 3.0 | 2148 | 1.3871 | 0.6822 |
| 0.1769 | 4.0 | 2864 | 1.6580 | 0.6766 |
### Framework versions
- Transformers 4.12.5
- Pytorch 1.9.1
- Datasets 1.16.1
- Tokenizers 0.10.3
| null |
Non_BioNLP
|
<!-- 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. -->
# irony_trained_1234567
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6580
- F1: 0.6766
## 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: 2.6774391860025942e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 1234567
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.6608 | 1.0 | 716 | 0.6057 | 0.6704 |
| 0.5329 | 2.0 | 1432 | 0.8935 | 0.6621 |
| 0.3042 | 3.0 | 2148 | 1.3871 | 0.6822 |
| 0.1769 | 4.0 | 2864 | 1.6580 | 0.6766 |
### Framework versions
- Transformers 4.12.5
- Pytorch 1.9.1
- Datasets 1.16.1
- Tokenizers 0.10.3
|
{"datasets": ["tweet_eval"], "license": "apache-2.0", "metrics": ["f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "irony_trained_1234567", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "tweet_eval", "type": "tweet_eval", "args": "irony"}, "metrics": [{"type": "f1", "value": 0.6765645067647214, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,499 |
r-kaichi/autotrain-test2-2979285951
|
r-kaichi
|
translation
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"autotrain",
"translation",
"unk",
"dataset:r-kaichi/autotrain-data-test2",
"co2_eq_emissions",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2023-01-20T11:40:10Z |
2023-01-20T11:50:58+00:00
| 110 | 0 |
---
datasets:
- r-kaichi/autotrain-data-test2
language:
- unk
- unk
tags:
- autotrain
- translation
co2_eq_emissions:
emissions: 22.168745481272524
---
# Model Trained Using AutoTrain
- Problem type: Translation
- Model ID: 2979285951
- CO2 Emissions (in grams): 22.1687
## Validation Metrics
- Loss: 0.254
- SacreBLEU: 7.587
- Gen len: 19.000
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Translation
- Model ID: 2979285951
- CO2 Emissions (in grams): 22.1687
## Validation Metrics
- Loss: 0.254
- SacreBLEU: 7.587
- Gen len: 19.000
|
{"datasets": ["r-kaichi/autotrain-data-test2"], "language": ["unk", "unk"], "tags": ["autotrain", "translation"], "co2_eq_emissions": {"emissions": 22.168745481272524}}
|
task
|
[
"TRANSLATION"
] | 41,501 |
pranalibose/cnn_daily_mail_summarization_output_on_t5_small
|
pranalibose
|
text2text-generation
|
[
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-06-15T09:34:33Z |
2024-06-15T09:38:44+00:00
| 6 | 0 |
---
base_model: t5-small
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: cnn_daily_mail_summarization_output_on_t5_small
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. -->
# cnn_daily_mail_summarization_output_on_t5_small
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Generated Length |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------------:|
| No log | 1.0 | 144 | 1.9062 | 0.2318 | 0.0943 | 0.1905 | 0.1902 | 19.0 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
| null |
Non_BioNLP
|
<!-- 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. -->
# cnn_daily_mail_summarization_output_on_t5_small
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Generated Length |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------------:|
| No log | 1.0 | 144 | 1.9062 | 0.2318 | 0.0943 | 0.1905 | 0.1902 | 19.0 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
{"base_model": "t5-small", "license": "apache-2.0", "tags": ["generated_from_trainer"], "model-index": [{"name": "cnn_daily_mail_summarization_output_on_t5_small", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 41,502 |
florianhoenicke/pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564
|
florianhoenicke
|
feature-extraction
|
[
"transformers",
"safetensors",
"bert",
"feature-extraction",
"custom_code",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 2024-04-10T22:17:34Z |
2024-04-10T22:17:39+00:00
| 5 | 0 |
---
{}
---
# pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564
## Model Description
pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564 is a fine-tuned version of jinaai/jina-embeddings-v2-small-en designed for a specific domain.
## Use Case
This model is designed to support various applications in natural language processing and understanding.
## Associated Dataset
This the dataset for this model can be found [**here**](https://huggingface.co/datasets/florianhoenicke/pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564).
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from transformers import AutoModel, AutoTokenizer
llm_name = "pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564"
tokenizer = AutoTokenizer.from_pretrained(llm_name)
model = AutoModel.from_pretrained(llm_name)
tokens = tokenizer("Your text here", return_tensors="pt")
embedding = model(**tokens)
```
| null |
Non_BioNLP
|
# pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564
## Model Description
pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564 is a fine-tuned version of jinaai/jina-embeddings-v2-small-en designed for a specific domain.
## Use Case
This model is designed to support various applications in natural language processing and understanding.
## Associated Dataset
This the dataset for this model can be found [**here**](https://huggingface.co/datasets/florianhoenicke/pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564).
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from transformers import AutoModel, AutoTokenizer
llm_name = "pet-shop-100-64-20-jinaai_jina-embeddings-v2-small-en_9062874564"
tokenizer = AutoTokenizer.from_pretrained(llm_name)
model = AutoModel.from_pretrained(llm_name)
tokens = tokenizer("Your text here", return_tensors="pt")
embedding = model(**tokens)
```
|
{}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,503 |
jaba99/distilbert-base-uncased-finetuned-emotion
|
jaba99
|
text-classification
|
[
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-07-15T17:00:16Z |
2024-07-18T20:56:06+00:00
| 106 | 0 |
---
base_model: distilbert-base-uncased
datasets:
- emotion
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.77
name: Accuracy
- type: f1
value: 0.7418319633122784
name: F1
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7073
- Accuracy: 0.77
- F1: 0.7418
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 1.2917 | 1.0 | 94 | 0.9545 | 0.686 | 0.6208 |
| 0.7965 | 2.0 | 188 | 0.7073 | 0.77 | 0.7418 |
### Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cpu
- Datasets 2.20.0
- Tokenizers 0.19.1
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7073
- Accuracy: 0.77
- F1: 0.7418
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 1.2917 | 1.0 | 94 | 0.9545 | 0.686 | 0.6208 |
| 0.7965 | 2.0 | 188 | 0.7073 | 0.77 | 0.7418 |
### Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cpu
- Datasets 2.20.0
- Tokenizers 0.19.1
|
{"base_model": "distilbert-base-uncased", "datasets": ["emotion"], "license": "apache-2.0", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetuned-emotion", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.77, "name": "Accuracy"}, {"type": "f1", "value": 0.7418319633122784, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,504 |
kaustavbhattacharjee/finetuning-DistillBERT-amazon-polarity
|
kaustavbhattacharjee
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:amazon_polarity",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-03-05T23:03:33Z |
2024-03-06T04:11:33+00:00
| 8 | 0 |
---
base_model: distilbert-base-uncased
datasets:
- amazon_polarity
license: apache-2.0
metrics:
- accuracy
- f1
pipeline_tag: text-classification
tags:
- generated_from_trainer
model-index:
- name: finetuning-DistillBERT-amazon-polarity
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: amazon_polarity
type: sentiment
args: default
metrics:
- type: accuracy
value: 0.9166666666666666
name: Accuracy
- type: loss
value: 0.1919892132282257
name: Loss
- type: f1
value: 0.9169435215946843
name: F1
---
<!-- 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. -->
# finetuning-DistillBERT-amazon-polarity
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on [Amazon Polarity](https://huggingface.co/datasets/amazon_polarity) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1920
- Accuracy: 0.9167
- F1: 0.9169
## 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: 2e-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
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| null |
Non_BioNLP
|
<!-- 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. -->
# finetuning-DistillBERT-amazon-polarity
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on [Amazon Polarity](https://huggingface.co/datasets/amazon_polarity) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1920
- Accuracy: 0.9167
- F1: 0.9169
## 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: 2e-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
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"base_model": "distilbert-base-uncased", "datasets": ["amazon_polarity"], "license": "apache-2.0", "metrics": ["accuracy", "f1"], "pipeline_tag": "text-classification", "tags": ["generated_from_trainer"], "model-index": [{"name": "finetuning-DistillBERT-amazon-polarity", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "amazon_polarity", "type": "sentiment", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.9166666666666666, "name": "Accuracy"}, {"type": "loss", "value": 0.1919892132282257, "name": "Loss"}, {"type": "f1", "value": 0.9169435215946843, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,505 |
mrapacz/interlinear-en-mt5-base-emb-concat-normalized-ob
|
mrapacz
|
text2text-generation
|
[
"transformers",
"pytorch",
"morph-t5-concat",
"text2text-generation",
"en",
"dataset:mrapacz/greek-interlinear-translations",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2025-02-07T19:53:26Z |
2025-02-21T21:33:17+00:00
| 10 | 0 |
---
base_model:
- mT5-base
datasets:
- mrapacz/greek-interlinear-translations
language:
- en
library_name: transformers
license: cc-by-sa-4.0
metrics:
- bleu
---
# Model Card for Ancient Greek to English Interlinear Translation Model
This model performs interlinear translation from Ancient Greek to English, maintaining word-level alignment between source and target texts.
You can find the source code used for training this and other models trained as part of this project in the [GitHub repository](https://github.com/mrapacz/loreslm-interlinear-translation).
## Model Details
### Model Description
- **Developed By:** Maciej Rapacz, AGH University of Kraków
- **Model Type:** MorphT5ConcatForConditionalGeneration
- **Base Model:** mT5-base
- **Tokenizer:** mT5
- **Language(s):** Ancient Greek (source) → English (target)
- **License:** CC BY-NC-SA 4.0
- **Tag Set:** OB (Oblubienica)
- **Text Preprocessing:** Normalized
- **Morphological Encoding:** emb-concat
### Model Performance
- **BLEU Score:** 0.69
- **SemScore:** 0.34
### Model Sources
- **Repository:** https://github.com/mrapacz/loreslm-interlinear-translation
- **Paper:** https://aclanthology.org/2025.loreslm-1.11/
## Usage Example
> **Note**: This model uses a modification of T5-family models that includes dedicated embedding layers for encoding morphological information. To load these models, install the [morpht5](https://github.com/mrapacz/loreslm-interlinear-translation/blob/master/morpht5/README.md) package:
> ```bash
> pip install morpht5
> ```
```python
>>> from morpht5 import MorphT5ConcatForConditionalGeneration, MorphT5Tokenizer
>>> text = ['λεγει', 'αυτω', 'ο', 'ιησους', 'εγειρε', 'αρον', 'τον', 'κραβαττον', 'σου', 'και', 'περιπατει']
>>> tags = ['vi Pres Act 3 Sg', 'pp Dat Sg m', 't_ Nom Sg m', 'n_ Nom Sg m', 'vm Pres Act 2 Sg', 'vm Aor Act 2 Sg', 't_ Acc Sg m', 'n_ Acc Sg m', 'pp 2 Gen Sg', 'Conj', 'vm Pres Act 2 Sg']
>>> tokenizer = MorphT5Tokenizer.from_pretrained("mrapacz/interlinear-en-mt5-base-emb-concat-normalized-ob")
>>> inputs = tokenizer(
text=text,
morph_tags=tags,
return_tensors="pt"
)
>>> model = MorphT5ConcatForConditionalGeneration.from_pretrained("mrapacz/interlinear-en-mt5-base-emb-concat-normalized-ob")
>>> outputs = model.generate(
**inputs,
max_new_tokens=100,
early_stopping=True,
)
>>> decoded = tokenizer.decode(outputs[0], skip_special_tokens=True, keep_block_separator=True)
>>> decoded = decoded.replace(tokenizer.target_block_separator_token, " | ")
>>> decoded
'Says | to him | - | Jesus | Come | take up | the | mat | of you | and | walk'
```
## Citation
If you use this model, please cite the following paper:
```
@inproceedings{rapacz-smywinski-pohl-2025-low,
title = "Low-Resource Interlinear Translation: Morphology-Enhanced Neural Models for {A}ncient {G}reek",
author = "Rapacz, Maciej and
Smywi{\'n}ski-Pohl, Aleksander",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.11/",
pages = "145--165",
abstract = "Contemporary machine translation systems prioritize fluent, natural-sounding output with flexible word ordering. In contrast, interlinear translation maintains the source text`s syntactic structure by aligning target language words directly beneath their source counterparts. Despite its importance in classical scholarship, automated approaches to interlinear translation remain understudied. We evaluated neural interlinear translation from Ancient Greek to English and Polish using four transformer-based models: two Ancient Greek-specialized (GreTa and PhilTa) and two general-purpose multilingual models (mT5-base and mT5-large). Our approach introduces novel morphological embedding layers and evaluates text preprocessing and tag set selection across 144 experimental configurations using a word-aligned parallel corpus of the Greek New Testament. Results show that morphological features through dedicated embedding layers significantly enhance translation quality, improving BLEU scores by 35{\%} (44.67 {\textrightarrow} 60.40) for English and 38{\%} (42.92 {\textrightarrow} 59.33) for Polish compared to baseline models. PhilTa achieves state-of-the-art performance for English, while mT5-large does so for Polish. Notably, PhilTa maintains stable performance using only 10{\%} of training data. Our findings challenge the assumption that modern neural architectures cannot benefit from explicit morphological annotations. While preprocessing strategies and tag set selection show minimal impact, the substantial gains from morphological embeddings demonstrate their value in low-resource scenarios."
}
```
| null |
Non_BioNLP
|
# Model Card for Ancient Greek to English Interlinear Translation Model
This model performs interlinear translation from Ancient Greek to English, maintaining word-level alignment between source and target texts.
You can find the source code used for training this and other models trained as part of this project in the [GitHub repository](https://github.com/mrapacz/loreslm-interlinear-translation).
## Model Details
### Model Description
- **Developed By:** Maciej Rapacz, AGH University of Kraków
- **Model Type:** MorphT5ConcatForConditionalGeneration
- **Base Model:** mT5-base
- **Tokenizer:** mT5
- **Language(s):** Ancient Greek (source) → English (target)
- **License:** CC BY-NC-SA 4.0
- **Tag Set:** OB (Oblubienica)
- **Text Preprocessing:** Normalized
- **Morphological Encoding:** emb-concat
### Model Performance
- **BLEU Score:** 0.69
- **SemScore:** 0.34
### Model Sources
- **Repository:** https://github.com/mrapacz/loreslm-interlinear-translation
- **Paper:** https://aclanthology.org/2025.loreslm-1.11/
## Usage Example
> **Note**: This model uses a modification of T5-family models that includes dedicated embedding layers for encoding morphological information. To load these models, install the [morpht5](https://github.com/mrapacz/loreslm-interlinear-translation/blob/master/morpht5/README.md) package:
> ```bash
> pip install morpht5
> ```
```python
>>> from morpht5 import MorphT5ConcatForConditionalGeneration, MorphT5Tokenizer
>>> text = ['λεγει', 'αυτω', 'ο', 'ιησους', 'εγειρε', 'αρον', 'τον', 'κραβαττον', 'σου', 'και', 'περιπατει']
>>> tags = ['vi Pres Act 3 Sg', 'pp Dat Sg m', 't_ Nom Sg m', 'n_ Nom Sg m', 'vm Pres Act 2 Sg', 'vm Aor Act 2 Sg', 't_ Acc Sg m', 'n_ Acc Sg m', 'pp 2 Gen Sg', 'Conj', 'vm Pres Act 2 Sg']
>>> tokenizer = MorphT5Tokenizer.from_pretrained("mrapacz/interlinear-en-mt5-base-emb-concat-normalized-ob")
>>> inputs = tokenizer(
text=text,
morph_tags=tags,
return_tensors="pt"
)
>>> model = MorphT5ConcatForConditionalGeneration.from_pretrained("mrapacz/interlinear-en-mt5-base-emb-concat-normalized-ob")
>>> outputs = model.generate(
**inputs,
max_new_tokens=100,
early_stopping=True,
)
>>> decoded = tokenizer.decode(outputs[0], skip_special_tokens=True, keep_block_separator=True)
>>> decoded = decoded.replace(tokenizer.target_block_separator_token, " | ")
>>> decoded
'Says | to him | - | Jesus | Come | take up | the | mat | of you | and | walk'
```
## Citation
If you use this model, please cite the following paper:
```
@inproceedings{rapacz-smywinski-pohl-2025-low,
title = "Low-Resource Interlinear Translation: Morphology-Enhanced Neural Models for {A}ncient {G}reek",
author = "Rapacz, Maciej and
Smywi{\'n}ski-Pohl, Aleksander",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.11/",
pages = "145--165",
abstract = "Contemporary machine translation systems prioritize fluent, natural-sounding output with flexible word ordering. In contrast, interlinear translation maintains the source text`s syntactic structure by aligning target language words directly beneath their source counterparts. Despite its importance in classical scholarship, automated approaches to interlinear translation remain understudied. We evaluated neural interlinear translation from Ancient Greek to English and Polish using four transformer-based models: two Ancient Greek-specialized (GreTa and PhilTa) and two general-purpose multilingual models (mT5-base and mT5-large). Our approach introduces novel morphological embedding layers and evaluates text preprocessing and tag set selection across 144 experimental configurations using a word-aligned parallel corpus of the Greek New Testament. Results show that morphological features through dedicated embedding layers significantly enhance translation quality, improving BLEU scores by 35{\%} (44.67 {\textrightarrow} 60.40) for English and 38{\%} (42.92 {\textrightarrow} 59.33) for Polish compared to baseline models. PhilTa achieves state-of-the-art performance for English, while mT5-large does so for Polish. Notably, PhilTa maintains stable performance using only 10{\%} of training data. Our findings challenge the assumption that modern neural architectures cannot benefit from explicit morphological annotations. While preprocessing strategies and tag set selection show minimal impact, the substantial gains from morphological embeddings demonstrate their value in low-resource scenarios."
}
```
|
{"base_model": ["mT5-base"], "datasets": ["mrapacz/greek-interlinear-translations"], "language": ["en"], "library_name": "transformers", "license": "cc-by-sa-4.0", "metrics": ["bleu"]}
|
task
|
[
"TRANSLATION"
] | 41,506 |
knguyennguyen/mpnet_jacket4k_adjusted
|
knguyennguyen
|
sentence-similarity
|
[
"sentence-transformers",
"safetensors",
"mpnet",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:11397",
"loss:MultipleNegativesRankingLoss",
"arxiv:1908.10084",
"arxiv:1705.00652",
"base_model:sentence-transformers/all-mpnet-base-v2",
"base_model:finetune:sentence-transformers/all-mpnet-base-v2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2025-01-22T22:53:32Z |
2025-01-22T22:54:00+00:00
| 10 | 0 |
---
base_model: sentence-transformers/all-mpnet-base-v2
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:11397
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: a leather jacket for casual occasions and weekend trips for men
sentences:
- "Title: Blazer Jackets for Women Business Casual Suit Coat Zipper Crop Cardigan\
\ Work Outfits Office Long Sleeve Boyfriend Blazers Descripion: [\"Blazer Jackets\
\ for Women Business Casual Suit Coat Zipper Crop Cardigan Work Outfits Office\
\ Long Sleeve Boyfriend Blazers/Women's Casual Blazers Open Front Long Sleeve\
\ Button Work Office Blazer Jacket\"\n '【 Feature:】'\n \"✨ Women blazer casual,\
\ open front cardigan jacket comes with long sleeve and label collar. ✨ Occasion:\
\ Women's lapel pocket blazer suit perfect for casual, daily life, work office,\
\ going out, night out, travel, vacation, holiday, spring, fall, winter, etc.\
\ ✨ Women's Casual Lightweight Open Front Cardigan is extremely comfortable! It\
\ can be dressed up for business or work, or dressed down for a casual look! Good\
\ quality and versatile!\"\n '【 Size Chart】'\n \"Size:S US:6 EU:36 Bust:98cm/38.58''\
\ Sleeve:60cm/23.62'' Front Length:60cm/23.62'' Size:M US:8 EU:38 Bust:102cm/40.16''\
\ Sleeve:61cm/24.02'' Front Length:61cm/24.02'' Size:L US:10 EU:40 Bust:106cm/41.73''\
\ Sleeve:62cm/24.41'' Front Length:62cm/24.41'' Size:XL US:12 EU:42 Bust:110cm/43.31''\
\ Sleeve:63cm/24.80'' Front Length:63cm/24.80''\"\n '❤️ Please Refer to Our Size\
\ Chart for Choosing Your Most Suitable Open Front Lapel Blazer Suit/Long Sleeves\
\ Buttons Work Suit/Flap Pockets Suit Outerwear Coat, Work Blazer Suit for Women/Basic\
\ Lapel Collar Blazer Jacket for Women.'\n \"❤️BDFCY'S SERVICE:\"\n '\U0001F495\
About Shipping: ✨ Standard Shipping: 8-15 Biz Days to Arrive ✨ Expedited Shipping:\
\ 3-5 Biz Days to Arrive \U0001F495Guarantee: * We endeavors 100% customer satisfaction\
\ service and experience. * If you receive damaged or wrong items,please contact\
\ us, we will provide you a satisfactory solution asap, please rest assured to\
\ purchase.* If you are satisfied with our product or service,hope you can leave\
\ your positive message,thanks for your encouragement.']"
- 'Title: LZJDS Mens Wool Coats Casual Regular Fit Trenchcoats Double Collar Thick
Winter Peacoats Mid-Length Jacket Overcoat Descripion: ["★Mens trench coat autumn
winter long jacket overcoat business woolen coat with double collar (removable)
to resist the cold and keep warm. The fashion trend of woolen coat is becoming
more and more fierce. The design of this coat provides a new standardMaterial:
wool blend + polyester (30% wool 70% polyester fiber)Color: black, gray, camelSize:
M-170, L-175, XL-180, XXL-185, XXXL-190, XXXXL-195Style: business gentlemanFeatures:
thick, single-breasted, double-layer collar, side slit pockets★Packing list: 1*Men''s
thick windbreaker coat★Notes:1. Please carefully refer to our size suggestion
pictures (not the Amazon size chart). The jacket is a slim fit, slightly smaller
than expected2. We are trying to take a photo to show the color of the item, but
it may be different depending on the settings of the monitor3. Due to long-distance
transportation. The coat may be a little crumpled when delivered, we are glad
that you can iron it before wearing it, it will look much better."]'
- 'Title: Men Brown Air Force A-2 Leather Flight Bomber Jacket - ww2 flight jacket
- Men Navy G-1 Jacket - Brown Bomber leather Jacket Descripion: ["The G1 Men leather
jacket is a premium quality, vintage jacket designed to provide a rugged and stylish
look for men. The G1Leather jacket is made of high-quality distressed leather
that gives it a unique, worn-in appearance. The Distressed Brown leather jacket
features a stylish collar with a button closure and a front zipper closure. The
G1 Men jacket also comes with two spacious pockets on the front for storing your
essentials. The Leather jacket Men'' cuffs and hemline are made of rib-knit fabric,
which provides a comfortable fit and protects against cold winds. The Brown Bomber
jacket is a timeless classic that never goes out of style. It is perfect for casual
occasions, such as a night out with friends or a weekend trip. This jacket will
keep you looking stylish while also providing the warmth and comfort you need."]'
- source_sentence: a shirt jacket for warmth and comfort in rugged conditions for
men
sentences:
- 'Title: Carhartt Men''s Big & Tall Relaxed Fit Heavyweight Flannel Sherpa-Lined
Shirt Jacket, Brown, 3X-Large Descripion: ["This men''s Carhartt shirt jac blends
the comfort of a hoodie with the ruggedness of a jacket. Made from heavyweight
flannel with a plush sherpa lining and a relaxed fit. Features two outer pockets
plus an inner pocket on the chest. 8-ounce, 100% cotton ringspun flannel. Sherpa
fleece lining for warmth. Carhartt strong triple-stitched main seams. Relaxed
fit. Spread collar. Two-snap adjustable cuffs with extended plackets. Antique-finish
nickel snaps. Two chest pockets with flaps and snap closures #Interior chest pocket.
Replaces 104452. Imported"]'
- 'Title: Tommy Hilfiger Men''s Lightweight Active Water Resistant Hooded Rain Jacket
Descripion: [''Lightweight updated hooded rain slicker with red white and navy
center front contrast zipper tape.'']'
- 'Title: UGFashions Icy Hot Jacket Kurt Russell Death Proof Stuntman Mike Racing
Costume Silver Satin Jacket Descripion: ["Icy Hot Silver Race Driver Costume Silver
Satin Jacket Icy Hot Death Proof Stuntsman Mike Kurt Russell Silver Jacket This
Stuntman Mike Racing Jacket turned Kurt Russell into a Hollywood celebrity. It
is the Stuntman Mike jacket that Kurt Russell wore in his movie Death Proof. He
looked smart and stylish wearing this Death Proof Satin Jacket. Now you can buy
this silver jacket. Icy Hot Racing Costume Jacket has following features Item
Specifications: Manufactured from Satin material Front Zipper closure | icy hot
jacket Inside Viscose Lining | death proof jacket Shirt style collar | kurt russell
jacket Button Cuffs | stuntman mike satin jacket Patches at back and on Sleeves
| racing costume jacket Waist Side Pockets We have multiple resources for entire
operations including manufacturing, packaging and shipping to minimize the risk
for the item being late or defective. We accept returns/ exchanges are possible
within 30 day time period after delivery. Size chart is provided at the end in
images section so you can select the perfect size for your body and even if it
doesn''t fit, we are available 24/7 to guide you for further steps. QC is done
2-3 times to make sure that whatever item is being sent to the buyer gets delivered
in accurate and perfect condition"]'
- source_sentence: men's windbreaker with a lightweight design, weather-resistant
fabric, and adjustable features for comfort and convenience.
sentences:
- 'Title: Zafy Leather Geniune Leather Women Jacket Small Red Descripion: [''High-Quality
men Leather Jacket - The " Zafy Leather" is known for its leather quality. The
jackets are crafted by professional artisans so that it must be slim fit, stylish
and comfortable to wear. The color may differ slightly due to photography lights
or different screen resolution setting. The solid color you get from us will not
fade easily and built to last for years. Best Gift for her: Its soft touch makes
it the best choice as a gift on the occasion of Birthday Day, Christmas Gift and
Anniversary. Maintainance Tips: Clean leather jacket with little liquid cleaner
using soft cotton cloth. Do not wash with water or direct sunlight exposure may
damage color.'']'
- 'Title: Cosplay.fm Women''s Cosplay Costume Red Jacket with Hat Descripion: [''cosplay
outfit consists of a red jacket, pants, socks, belt, and gloves. Made with nice
materials, PU leather, cotton and polyester.Bulma costume will definitely make
you the most eye-catching in cosplay shows, parties, comic cons, stage performances,
etc.'']'
- 'Title: Columbia Men''s M Fkt Ii Windbreaker Jacket Descripion: ["Ultra light
and weather-repelling, this protective and packable windbreaker is a must for
running in wet, blustery weather. \u2028\u2028 You will be comfortably shielded
in this stain and water resistant windbreaker. It''s the perfect lightweight layer
and first line of defense to combat chilly winds and light drizzle. Its full length
zippered front allows you to dial in the protection on the fly, while a zip-closed
security pocket keeps essentials close by. Sleeves with elastic at the cuffs and
thumbholes keep hands and arms comfortable, while elastic at the hem and reflective
detail adds a touch of safety. This coat can pack down into its own pocket for
easy travel. Columbia offers this jacket in multiple colors and sizes. Active
Fit. To ensure the size you choose is right, utilize our sizing chart and the
following measurement instructions: For the sleeves, start at the center back
of your neck and measure across the shoulder and down to the sleeve. If you come
up with a partial number, round up to the next even number. For the chest, measure
at the fullest part of the chest, under the armpits and over the shoulder blades,
keeping the tape measure firm and level."]'
- source_sentence: women's waterproof jacket with a detachable hood, adjustable cuffs,
and multiple storage pockets.
sentences:
- 'Title: Camii Mia-Rain-Jackets-for-Women-Waterproof Hooded Jacket Drawstring Lightweight
Hiking Mountain Camping Descripion: ["Camii Mia is very known for its simplicity
and elegance in extremely well made and durable products. We have the desire that
makes the fashion art more efficient and easy going. That''s how we change the
world. We strive to make perfect blend of design, material and color. Hope you
will like our work. Camii Mia women''s 3 in 1 Rain jacket featuring detachable
hood with elastic drawstring, adjustable cuffs with velcro, 2 zippered slanted
hand pockests and 5 internal hand pocket. Windproof, durable and breathable fabric
and removable warm polar fleece linning could guarantees the best heat retention.
Keep your body from wind, rain and cold weather. Suitable for outdoor occasions
such as hiking, camping, climbing, traveling, skiing, snowboarding and other outdoor
sports. Size Measurement: Small -- Chest 43.3''''(110cm), Shoulder 16.5'''' ,
Sleeve 23.8'''', Length 25.6'''' Medium -- Chest 46.5''''(118cm), Shoulder 17.7'''',
Sleeve 25'''', Length 27.2'''' Large -- Chest 48.8''''(124cm), Shoulder 19.9'''',
Sleeve 25.8'''', Length 29.1'''' X-Large -- Chest 52''''(132cm), Shoulder 21.1'''',
Sleeve 27'''', Length 30.7'''' XX-Large -- Chest 53.5''''(136cm), Shoulder 21.7'''',
Sleeve 27'', Length 30.7'''' If you''re not sure about your size, please tell
us your weight, bust and height in lbs and inches. Let''s help you to make choice.
Thanks!"]'
- 'Title: Mountain Warehouse Womens Waterproof Ski Jacket - Slim Fit for Winter
Descripion: [''Get ready to face the elements in the Slalom Extreme Ski Jacket.
Fully waterproof with taped seams, the jacket is breathable and features RECCO
technology, a detachable snowskirt, inner stretch ski cuffs and underarm zips.
Ref: 031369'']'
- 'Title: The Classo Bomberium Black Bomber Men Leather Jacket Descripion: [''We
have introduce our products with high quality leather and Craftsmanship. We have
aim to provide excellent quality leather product to our valued customer in affordable
price with elegant Style. When you wear our outerwear feel comfortable. We make
our own leather and do stitching. It is soft Lambskin leather which has been created
by Famous tendery that product remarkable skin. We also make this item in faux
leather which is called Artificial Leather. We are offering both leather for leather
lovers and faux leather jacket who do not want to wear Animal Skin. Note" The
color and shade may vary from the picture you are seeing in the laptop due to
LED color and scheme.'']'
- source_sentence: men's winter jacket with a water-resistant exterior, thermal insulation,
and multiple pockets for storage.
sentences:
- 'Title: Bon Bebe Baby-boys Newborn Champ 3 Piece Velour Jacket And Pant Set Descripion:
[''Velour, button-front, hooded jacket with embroidered applique. 100 percent
cotton printed bodysuit with lap shoulder neck opening and 3-snap closure at inseam
for easy on-off dressing. Velour pant with elastic waistband.'']'
- 'Title: Yansguard Men''s Cycling Jerseys Tops Biking Shirts Short Sleeve Bike
Clothing Full Zipper Bicycle Jacket Gray, M (jersey008),J-G-M Descripion: [''100%
Polyester.Ultra-soft and UV protection.Full zipper in front, easy to wear and
take offHigh quality Moisture Wicking Fabric, quick-dry feature makes you feel
more comfortableWith 5 Pockets for safe storage, one of which has a zipper and
is waterproof!.There are reflective signs on the back of cycling jersey to enhance
the safety of cycling at night'']'
- 'Title: Columbia Men''s Grand Wall Jacket Descripion: [''Perfect for Fall and
Winter, the Columbia Men’s Grand Wall Jacket combines a classic outdoor look with
advanced technology to keep you warm and dry. Crafted from water resistant fabric,
packed with our down-like Thermarator insulation, and lined with our signature
Omni-HEAT reflective dots – this is your new go-to cold weather coat. Complete
with zippered hand pockets, a chest pocket for important essentials, and binding
at the cuffs — perfect to help block the cold, and lock your comfy body heat in.
This men’s winter jacket is offered in multiple sizes and colors. Extended sizing
available. Regular Fit. To ensure the size you choose is right, utilize our sizing
chart and the following measurement instructions: For the sleeves, start at the
center back of your neck and measure across the shoulder and down to the sleeve.
If you come up with a partial number, round up to the next even number. For the
chest, measure at the fullest part of the chest, under the armpits and over the
shoulder blades, keeping the tape measure firm and level.'']'
---
# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). 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:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **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': 256, 'do_lower_case': False}) with Transformer model: MPNetModel
(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("knguyennguyen/mpnet_jacket4k_adjusted")
# Run inference
sentences = [
"men's winter jacket with a water-resistant exterior, thermal insulation, and multiple pockets for storage.",
"Title: Columbia Men's Grand Wall Jacket Descripion: ['Perfect for Fall and Winter, the Columbia Men’s Grand Wall Jacket combines a classic outdoor look with advanced technology to keep you warm and dry. Crafted from water resistant fabric, packed with our down-like Thermarator insulation, and lined with our signature Omni-HEAT reflective dots – this is your new go-to cold weather coat. Complete with zippered hand pockets, a chest pocket for important essentials, and binding at the cuffs — perfect to help block the cold, and lock your comfy body heat in. This men’s winter jacket is offered in multiple sizes and colors. Extended sizing available. Regular Fit. To ensure the size you choose is right, utilize our sizing chart and the following measurement instructions: For the sleeves, start at the center back of your neck and measure across the shoulder and down to the sleeve. If you come up with a partial number, round up to the next even number. For the chest, measure at the fullest part of the chest, under the armpits and over the shoulder blades, keeping the tape measure firm and level.']",
"Title: Yansguard Men's Cycling Jerseys Tops Biking Shirts Short Sleeve Bike Clothing Full Zipper Bicycle Jacket Gray, M (jersey008),J-G-M Descripion: ['100% Polyester.Ultra-soft and UV protection.Full zipper in front, easy to wear and take offHigh quality Moisture Wicking Fabric, quick-dry feature makes you feel more comfortableWith 5 Pockets for safe storage, one of which has a zipper and is waterproof!.There are reflective signs on the back of cycling jersey to enhance the safety of cycling at night']",
]
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.*
-->
<!--
## 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: 11,397 training samples
* Columns: <code>sentence_0</code> and <code>sentence_1</code>
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 |
|:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 24.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 31 tokens</li><li>mean: 155.6 tokens</li><li>max: 256 tokens</li></ul> |
* Samples:
| sentence_0 | sentence_1 |
|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>a heated vest for staying warm in winter</code> | <code>Title: Yi-Create Heated Vest with Battery Pack Included,Unisex Heated Jacket for Men & Women,7.4v 7000mAh Quick Heated Closing Descripion: ['Yi-create Heated Vest with Battery Pack Included,Unisex Heated Jacket for Men & Women,7.4v 7000mAh Quick Heated Clothing with 3 Heating Levels,Lightweight USB Electric Heated Vest with 8 Heating Zone']</code> |
| <code>a mid-layer jacket for cold-weather sports and casual wear for men. men's mid-layer jacket with a combination of moisture-wicking panels and a warm, textured fabric.</code> | <code>Title: Spyder Active Sports Men's Bandit Half Zip Mid-Layer Jacket Descripion: ['An excellent first layer for its combo of wicking side panels and warm sweater knit bonded to fleece everywhere else, the half zip bandit is made for cold-weather sports, but is stylish enough for just sauntering around town.']</code> |
| <code>a down jacket for camping and hiking adventures</code> | <code>Title: Helly-Hansen Mens Verglas Icefall Down Jacket Descripion: ["An essential piece in anyone's pack; a lightweight down insulator, ready for your next adventure."]</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 128
- `per_device_eval_batch_size`: 128
- `num_train_epochs`: 5
- `multi_dataset_batch_sampler`: round_robin
#### 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`: 128
- `per_device_eval_batch_size`: 128
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1
- `num_train_epochs`: 5
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `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`: False
- `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`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `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
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: round_robin
</details>
### Framework Versions
- Python: 3.11.11
- Sentence Transformers: 3.1.1
- Transformers: 4.45.2
- PyTorch: 2.5.1+cu121
- Accelerate: 1.2.1
- Datasets: 3.2.0
- Tokenizers: 0.20.3
## 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",
}
```
#### 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.*
-->
| null |
Non_BioNLP
|
# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). 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:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **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': 256, 'do_lower_case': False}) with Transformer model: MPNetModel
(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("knguyennguyen/mpnet_jacket4k_adjusted")
# Run inference
sentences = [
"men's winter jacket with a water-resistant exterior, thermal insulation, and multiple pockets for storage.",
"Title: Columbia Men's Grand Wall Jacket Descripion: ['Perfect for Fall and Winter, the Columbia Men’s Grand Wall Jacket combines a classic outdoor look with advanced technology to keep you warm and dry. Crafted from water resistant fabric, packed with our down-like Thermarator insulation, and lined with our signature Omni-HEAT reflective dots – this is your new go-to cold weather coat. Complete with zippered hand pockets, a chest pocket for important essentials, and binding at the cuffs — perfect to help block the cold, and lock your comfy body heat in. This men’s winter jacket is offered in multiple sizes and colors. Extended sizing available. Regular Fit. To ensure the size you choose is right, utilize our sizing chart and the following measurement instructions: For the sleeves, start at the center back of your neck and measure across the shoulder and down to the sleeve. If you come up with a partial number, round up to the next even number. For the chest, measure at the fullest part of the chest, under the armpits and over the shoulder blades, keeping the tape measure firm and level.']",
"Title: Yansguard Men's Cycling Jerseys Tops Biking Shirts Short Sleeve Bike Clothing Full Zipper Bicycle Jacket Gray, M (jersey008),J-G-M Descripion: ['100% Polyester.Ultra-soft and UV protection.Full zipper in front, easy to wear and take offHigh quality Moisture Wicking Fabric, quick-dry feature makes you feel more comfortableWith 5 Pockets for safe storage, one of which has a zipper and is waterproof!.There are reflective signs on the back of cycling jersey to enhance the safety of cycling at night']",
]
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.*
-->
<!--
## 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: 11,397 training samples
* Columns: <code>sentence_0</code> and <code>sentence_1</code>
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 |
|:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 24.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 31 tokens</li><li>mean: 155.6 tokens</li><li>max: 256 tokens</li></ul> |
* Samples:
| sentence_0 | sentence_1 |
|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>a heated vest for staying warm in winter</code> | <code>Title: Yi-Create Heated Vest with Battery Pack Included,Unisex Heated Jacket for Men & Women,7.4v 7000mAh Quick Heated Closing Descripion: ['Yi-create Heated Vest with Battery Pack Included,Unisex Heated Jacket for Men & Women,7.4v 7000mAh Quick Heated Clothing with 3 Heating Levels,Lightweight USB Electric Heated Vest with 8 Heating Zone']</code> |
| <code>a mid-layer jacket for cold-weather sports and casual wear for men. men's mid-layer jacket with a combination of moisture-wicking panels and a warm, textured fabric.</code> | <code>Title: Spyder Active Sports Men's Bandit Half Zip Mid-Layer Jacket Descripion: ['An excellent first layer for its combo of wicking side panels and warm sweater knit bonded to fleece everywhere else, the half zip bandit is made for cold-weather sports, but is stylish enough for just sauntering around town.']</code> |
| <code>a down jacket for camping and hiking adventures</code> | <code>Title: Helly-Hansen Mens Verglas Icefall Down Jacket Descripion: ["An essential piece in anyone's pack; a lightweight down insulator, ready for your next adventure."]</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 128
- `per_device_eval_batch_size`: 128
- `num_train_epochs`: 5
- `multi_dataset_batch_sampler`: round_robin
#### 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`: 128
- `per_device_eval_batch_size`: 128
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1
- `num_train_epochs`: 5
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `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`: False
- `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`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `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
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: round_robin
</details>
### Framework Versions
- Python: 3.11.11
- Sentence Transformers: 3.1.1
- Transformers: 4.45.2
- PyTorch: 2.5.1+cu121
- Accelerate: 1.2.1
- Datasets: 3.2.0
- Tokenizers: 0.20.3
## 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",
}
```
#### 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.*
-->
|
{"base_model": "sentence-transformers/all-mpnet-base-v2", "library_name": "sentence-transformers", "pipeline_tag": "sentence-similarity", "tags": ["sentence-transformers", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:11397", "loss:MultipleNegativesRankingLoss"], "widget": [{"source_sentence": "a leather jacket for casual occasions and weekend trips for men", "sentences": ["Title: Blazer Jackets for Women Business Casual Suit Coat Zipper Crop Cardigan Work Outfits Office Long Sleeve Boyfriend Blazers Descripion: [\"Blazer Jackets for Women Business Casual Suit Coat Zipper Crop Cardigan Work Outfits Office Long Sleeve Boyfriend Blazers/Women's Casual Blazers Open Front Long Sleeve Button Work Office Blazer Jacket\"\n '【 Feature:】'\n \"✨ Women blazer casual, open front cardigan jacket comes with long sleeve and label collar. ✨ Occasion: Women's lapel pocket blazer suit perfect for casual, daily life, work office, going out, night out, travel, vacation, holiday, spring, fall, winter, etc. ✨ Women's Casual Lightweight Open Front Cardigan is extremely comfortable! It can be dressed up for business or work, or dressed down for a casual look! Good quality and versatile!\"\n '【 Size Chart】'\n \"Size:S US:6 EU:36 Bust:98cm/38.58'' Sleeve:60cm/23.62'' Front Length:60cm/23.62'' Size:M US:8 EU:38 Bust:102cm/40.16'' Sleeve:61cm/24.02'' Front Length:61cm/24.02'' Size:L US:10 EU:40 Bust:106cm/41.73'' Sleeve:62cm/24.41'' Front Length:62cm/24.41'' Size:XL US:12 EU:42 Bust:110cm/43.31'' Sleeve:63cm/24.80'' Front Length:63cm/24.80''\"\n '❤️ Please Refer to Our Size Chart for Choosing Your Most Suitable Open Front Lapel Blazer Suit/Long Sleeves Buttons Work Suit/Flap Pockets Suit Outerwear Coat, Work Blazer Suit for Women/Basic Lapel Collar Blazer Jacket for Women.'\n \"❤️BDFCY'S SERVICE:\"\n '💕About Shipping: ✨ Standard Shipping: 8-15 Biz Days to Arrive ✨ Expedited Shipping: 3-5 Biz Days to Arrive 💕Guarantee: * We endeavors 100% customer satisfaction service and experience. * If you receive damaged or wrong items,please contact us, we will provide you a satisfactory solution asap, please rest assured to purchase.* If you are satisfied with our product or service,hope you can leave your positive message,thanks for your encouragement.']", "Title: LZJDS Mens Wool Coats Casual Regular Fit Trenchcoats Double Collar Thick Winter Peacoats Mid-Length Jacket Overcoat Descripion: [\"★Mens trench coat autumn winter long jacket overcoat business woolen coat with double collar (removable) to resist the cold and keep warm. The fashion trend of woolen coat is becoming more and more fierce. The design of this coat provides a new standardMaterial: wool blend + polyester (30% wool 70% polyester fiber)Color: black, gray, camelSize: M-170, L-175, XL-180, XXL-185, XXXL-190, XXXXL-195Style: business gentlemanFeatures: thick, single-breasted, double-layer collar, side slit pockets★Packing list: 1*Men's thick windbreaker coat★Notes:1. Please carefully refer to our size suggestion pictures (not the Amazon size chart). The jacket is a slim fit, slightly smaller than expected2. We are trying to take a photo to show the color of the item, but it may be different depending on the settings of the monitor3. Due to long-distance transportation. The coat may be a little crumpled when delivered, we are glad that you can iron it before wearing it, it will look much better.\"]", "Title: Men Brown Air Force A-2 Leather Flight Bomber Jacket - ww2 flight jacket - Men Navy G-1 Jacket - Brown Bomber leather Jacket Descripion: [\"The G1 Men leather jacket is a premium quality, vintage jacket designed to provide a rugged and stylish look for men. The G1Leather jacket is made of high-quality distressed leather that gives it a unique, worn-in appearance. The Distressed Brown leather jacket features a stylish collar with a button closure and a front zipper closure. The G1 Men jacket also comes with two spacious pockets on the front for storing your essentials. The Leather jacket Men' cuffs and hemline are made of rib-knit fabric, which provides a comfortable fit and protects against cold winds. The Brown Bomber jacket is a timeless classic that never goes out of style. It is perfect for casual occasions, such as a night out with friends or a weekend trip. This jacket will keep you looking stylish while also providing the warmth and comfort you need.\"]"]}, {"source_sentence": "a shirt jacket for warmth and comfort in rugged conditions for men", "sentences": ["Title: Carhartt Men's Big & Tall Relaxed Fit Heavyweight Flannel Sherpa-Lined Shirt Jacket, Brown, 3X-Large Descripion: [\"This men's Carhartt shirt jac blends the comfort of a hoodie with the ruggedness of a jacket. Made from heavyweight flannel with a plush sherpa lining and a relaxed fit. Features two outer pockets plus an inner pocket on the chest. 8-ounce, 100% cotton ringspun flannel. Sherpa fleece lining for warmth. Carhartt strong triple-stitched main seams. Relaxed fit. Spread collar. Two-snap adjustable cuffs with extended plackets. Antique-finish nickel snaps. Two chest pockets with flaps and snap closures #Interior chest pocket. Replaces 104452. Imported\"]", "Title: Tommy Hilfiger Men's Lightweight Active Water Resistant Hooded Rain Jacket Descripion: ['Lightweight updated hooded rain slicker with red white and navy center front contrast zipper tape.']", "Title: UGFashions Icy Hot Jacket Kurt Russell Death Proof Stuntman Mike Racing Costume Silver Satin Jacket Descripion: [\"Icy Hot Silver Race Driver Costume Silver Satin Jacket Icy Hot Death Proof Stuntsman Mike Kurt Russell Silver Jacket This Stuntman Mike Racing Jacket turned Kurt Russell into a Hollywood celebrity. It is the Stuntman Mike jacket that Kurt Russell wore in his movie Death Proof. He looked smart and stylish wearing this Death Proof Satin Jacket. Now you can buy this silver jacket. Icy Hot Racing Costume Jacket has following features Item Specifications: Manufactured from Satin material Front Zipper closure | icy hot jacket Inside Viscose Lining | death proof jacket Shirt style collar | kurt russell jacket Button Cuffs | stuntman mike satin jacket Patches at back and on Sleeves | racing costume jacket Waist Side Pockets We have multiple resources for entire operations including manufacturing, packaging and shipping to minimize the risk for the item being late or defective. We accept returns/ exchanges are possible within 30 day time period after delivery. Size chart is provided at the end in images section so you can select the perfect size for your body and even if it doesn't fit, we are available 24/7 to guide you for further steps. QC is done 2-3 times to make sure that whatever item is being sent to the buyer gets delivered in accurate and perfect condition\"]"]}, {"source_sentence": "men's windbreaker with a lightweight design, weather-resistant fabric, and adjustable features for comfort and convenience.", "sentences": ["Title: Zafy Leather Geniune Leather Women Jacket Small Red Descripion: ['High-Quality men Leather Jacket - The \" Zafy Leather\" is known for its leather quality. The jackets are crafted by professional artisans so that it must be slim fit, stylish and comfortable to wear. The color may differ slightly due to photography lights or different screen resolution setting. The solid color you get from us will not fade easily and built to last for years. Best Gift for her: Its soft touch makes it the best choice as a gift on the occasion of Birthday Day, Christmas Gift and Anniversary. Maintainance Tips: Clean leather jacket with little liquid cleaner using soft cotton cloth. Do not wash with water or direct sunlight exposure may damage color.']", "Title: Cosplay.fm Women's Cosplay Costume Red Jacket with Hat Descripion: ['cosplay outfit consists of a red jacket, pants, socks, belt, and gloves. Made with nice materials, PU leather, cotton and polyester.Bulma costume will definitely make you the most eye-catching in cosplay shows, parties, comic cons, stage performances, etc.']", "Title: Columbia Men's M Fkt Ii Windbreaker Jacket Descripion: [\"Ultra light and weather-repelling, this protective and packable windbreaker is a must for running in wet, blustery weather. \\u2028\\u2028 You will be comfortably shielded in this stain and water resistant windbreaker. It's the perfect lightweight layer and first line of defense to combat chilly winds and light drizzle. Its full length zippered front allows you to dial in the protection on the fly, while a zip-closed security pocket keeps essentials close by. Sleeves with elastic at the cuffs and thumbholes keep hands and arms comfortable, while elastic at the hem and reflective detail adds a touch of safety. This coat can pack down into its own pocket for easy travel. Columbia offers this jacket in multiple colors and sizes. Active Fit. To ensure the size you choose is right, utilize our sizing chart and the following measurement instructions: For the sleeves, start at the center back of your neck and measure across the shoulder and down to the sleeve. If you come up with a partial number, round up to the next even number. For the chest, measure at the fullest part of the chest, under the armpits and over the shoulder blades, keeping the tape measure firm and level.\"]"]}, {"source_sentence": "women's waterproof jacket with a detachable hood, adjustable cuffs, and multiple storage pockets.", "sentences": ["Title: Camii Mia-Rain-Jackets-for-Women-Waterproof Hooded Jacket Drawstring Lightweight Hiking Mountain Camping Descripion: [\"Camii Mia is very known for its simplicity and elegance in extremely well made and durable products. We have the desire that makes the fashion art more efficient and easy going. That's how we change the world. We strive to make perfect blend of design, material and color. Hope you will like our work. Camii Mia women's 3 in 1 Rain jacket featuring detachable hood with elastic drawstring, adjustable cuffs with velcro, 2 zippered slanted hand pockests and 5 internal hand pocket. Windproof, durable and breathable fabric and removable warm polar fleece linning could guarantees the best heat retention. Keep your body from wind, rain and cold weather. Suitable for outdoor occasions such as hiking, camping, climbing, traveling, skiing, snowboarding and other outdoor sports. Size Measurement: Small -- Chest 43.3''(110cm), Shoulder 16.5'' , Sleeve 23.8'', Length 25.6'' Medium -- Chest 46.5''(118cm), Shoulder 17.7'', Sleeve 25'', Length 27.2'' Large -- Chest 48.8''(124cm), Shoulder 19.9'', Sleeve 25.8'', Length 29.1'' X-Large -- Chest 52''(132cm), Shoulder 21.1'', Sleeve 27'', Length 30.7'' XX-Large -- Chest 53.5''(136cm), Shoulder 21.7'', Sleeve 27', Length 30.7'' If you're not sure about your size, please tell us your weight, bust and height in lbs and inches. Let's help you to make choice. Thanks!\"]", "Title: Mountain Warehouse Womens Waterproof Ski Jacket - Slim Fit for Winter Descripion: ['Get ready to face the elements in the Slalom Extreme Ski Jacket. Fully waterproof with taped seams, the jacket is breathable and features RECCO technology, a detachable snowskirt, inner stretch ski cuffs and underarm zips. Ref: 031369']", "Title: The Classo Bomberium Black Bomber Men Leather Jacket Descripion: ['We have introduce our products with high quality leather and Craftsmanship. We have aim to provide excellent quality leather product to our valued customer in affordable price with elegant Style. When you wear our outerwear feel comfortable. We make our own leather and do stitching. It is soft Lambskin leather which has been created by Famous tendery that product remarkable skin. We also make this item in faux leather which is called Artificial Leather. We are offering both leather for leather lovers and faux leather jacket who do not want to wear Animal Skin. Note\" The color and shade may vary from the picture you are seeing in the laptop due to LED color and scheme.']"]}, {"source_sentence": "men's winter jacket with a water-resistant exterior, thermal insulation, and multiple pockets for storage.", "sentences": ["Title: Bon Bebe Baby-boys Newborn Champ 3 Piece Velour Jacket And Pant Set Descripion: ['Velour, button-front, hooded jacket with embroidered applique. 100 percent cotton printed bodysuit with lap shoulder neck opening and 3-snap closure at inseam for easy on-off dressing. Velour pant with elastic waistband.']", "Title: Yansguard Men's Cycling Jerseys Tops Biking Shirts Short Sleeve Bike Clothing Full Zipper Bicycle Jacket Gray, M (jersey008),J-G-M Descripion: ['100% Polyester.Ultra-soft and UV protection.Full zipper in front, easy to wear and take offHigh quality Moisture Wicking Fabric, quick-dry feature makes you feel more comfortableWith 5 Pockets for safe storage, one of which has a zipper and is waterproof!.There are reflective signs on the back of cycling jersey to enhance the safety of cycling at night']", "Title: Columbia Men's Grand Wall Jacket Descripion: ['Perfect for Fall and Winter, the Columbia Men’s Grand Wall Jacket combines a classic outdoor look with advanced technology to keep you warm and dry. Crafted from water resistant fabric, packed with our down-like Thermarator insulation, and lined with our signature Omni-HEAT reflective dots – this is your new go-to cold weather coat. Complete with zippered hand pockets, a chest pocket for important essentials, and binding at the cuffs — perfect to help block the cold, and lock your comfy body heat in. This men’s winter jacket is offered in multiple sizes and colors. Extended sizing available. Regular Fit. To ensure the size you choose is right, utilize our sizing chart and the following measurement instructions: For the sleeves, start at the center back of your neck and measure across the shoulder and down to the sleeve. If you come up with a partial number, round up to the next even number. For the chest, measure at the fullest part of the chest, under the armpits and over the shoulder blades, keeping the tape measure firm and level.']"]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,507 |
henryscheible/xlnet-base-cased_stereoset_finetuned
|
henryscheible
|
text-classification
|
[
"transformers",
"pytorch",
"xlnet",
"text-classification",
"generated_from_trainer",
"dataset:stereoset",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-02-10T23:12:14Z |
2023-03-16T01:07:01+00:00
| 25 | 0 |
---
datasets:
- stereoset
license: mit
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: xlnet-base-cased_stereoset_finetuned
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: stereoset
type: stereoset
config: intersentence
split: validation
args: intersentence
metrics:
- type: accuracy
value: 0.7441130298273155
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. -->
# xlnet-base-cased_stereoset_finetuned
This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the stereoset dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0332
- Accuracy: 0.7441
## 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: 128
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.21 | 5 | 0.7165 | 0.5055 |
| No log | 0.42 | 10 | 0.6932 | 0.5 |
| No log | 0.62 | 15 | 0.6971 | 0.5047 |
| No log | 0.83 | 20 | 0.7107 | 0.4953 |
| No log | 1.04 | 25 | 0.6895 | 0.5047 |
| No log | 1.25 | 30 | 0.6715 | 0.5840 |
| No log | 1.46 | 35 | 0.6476 | 0.6476 |
| No log | 1.67 | 40 | 0.6150 | 0.6970 |
| No log | 1.88 | 45 | 0.6170 | 0.6884 |
| No log | 2.08 | 50 | 0.6065 | 0.6797 |
| No log | 2.29 | 55 | 0.5865 | 0.7033 |
| No log | 2.5 | 60 | 0.5899 | 0.7064 |
| No log | 2.71 | 65 | 0.5980 | 0.7151 |
| No log | 2.92 | 70 | 0.5890 | 0.7229 |
| No log | 3.12 | 75 | 0.5930 | 0.7190 |
| No log | 3.33 | 80 | 0.6430 | 0.7049 |
| No log | 3.54 | 85 | 0.6677 | 0.7198 |
| No log | 3.75 | 90 | 0.6076 | 0.7370 |
| No log | 3.96 | 95 | 0.6041 | 0.7339 |
| No log | 4.17 | 100 | 0.6324 | 0.7323 |
| No log | 4.38 | 105 | 0.6990 | 0.7308 |
| No log | 4.58 | 110 | 0.7081 | 0.7433 |
| No log | 4.79 | 115 | 0.6549 | 0.7237 |
| No log | 5.0 | 120 | 0.6868 | 0.7072 |
| No log | 5.21 | 125 | 0.6525 | 0.7363 |
| No log | 5.42 | 130 | 0.7622 | 0.7418 |
| No log | 5.62 | 135 | 0.7730 | 0.7402 |
| No log | 5.83 | 140 | 0.7788 | 0.7449 |
| No log | 6.04 | 145 | 0.7609 | 0.7347 |
| No log | 6.25 | 150 | 0.8058 | 0.7323 |
| No log | 6.46 | 155 | 0.8525 | 0.7331 |
| No log | 6.67 | 160 | 0.8504 | 0.7339 |
| No log | 6.88 | 165 | 0.8424 | 0.7300 |
| No log | 7.08 | 170 | 0.8413 | 0.7394 |
| No log | 7.29 | 175 | 0.8808 | 0.7268 |
| No log | 7.5 | 180 | 0.9058 | 0.7292 |
| No log | 7.71 | 185 | 0.9338 | 0.7363 |
| No log | 7.92 | 190 | 0.9412 | 0.7370 |
| No log | 8.12 | 195 | 0.9453 | 0.7339 |
| No log | 8.33 | 200 | 0.9544 | 0.7394 |
| No log | 8.54 | 205 | 0.9664 | 0.7402 |
| No log | 8.75 | 210 | 0.9840 | 0.7339 |
| No log | 8.96 | 215 | 0.9896 | 0.7370 |
| No log | 9.17 | 220 | 1.0239 | 0.7410 |
| No log | 9.38 | 225 | 1.0306 | 0.7418 |
| No log | 9.58 | 230 | 1.0358 | 0.7402 |
| No log | 9.79 | 235 | 1.0351 | 0.7410 |
| No log | 10.0 | 240 | 1.0332 | 0.7441 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.2
| null |
Non_BioNLP
|
<!-- 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. -->
# xlnet-base-cased_stereoset_finetuned
This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the stereoset dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0332
- Accuracy: 0.7441
## 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: 128
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.21 | 5 | 0.7165 | 0.5055 |
| No log | 0.42 | 10 | 0.6932 | 0.5 |
| No log | 0.62 | 15 | 0.6971 | 0.5047 |
| No log | 0.83 | 20 | 0.7107 | 0.4953 |
| No log | 1.04 | 25 | 0.6895 | 0.5047 |
| No log | 1.25 | 30 | 0.6715 | 0.5840 |
| No log | 1.46 | 35 | 0.6476 | 0.6476 |
| No log | 1.67 | 40 | 0.6150 | 0.6970 |
| No log | 1.88 | 45 | 0.6170 | 0.6884 |
| No log | 2.08 | 50 | 0.6065 | 0.6797 |
| No log | 2.29 | 55 | 0.5865 | 0.7033 |
| No log | 2.5 | 60 | 0.5899 | 0.7064 |
| No log | 2.71 | 65 | 0.5980 | 0.7151 |
| No log | 2.92 | 70 | 0.5890 | 0.7229 |
| No log | 3.12 | 75 | 0.5930 | 0.7190 |
| No log | 3.33 | 80 | 0.6430 | 0.7049 |
| No log | 3.54 | 85 | 0.6677 | 0.7198 |
| No log | 3.75 | 90 | 0.6076 | 0.7370 |
| No log | 3.96 | 95 | 0.6041 | 0.7339 |
| No log | 4.17 | 100 | 0.6324 | 0.7323 |
| No log | 4.38 | 105 | 0.6990 | 0.7308 |
| No log | 4.58 | 110 | 0.7081 | 0.7433 |
| No log | 4.79 | 115 | 0.6549 | 0.7237 |
| No log | 5.0 | 120 | 0.6868 | 0.7072 |
| No log | 5.21 | 125 | 0.6525 | 0.7363 |
| No log | 5.42 | 130 | 0.7622 | 0.7418 |
| No log | 5.62 | 135 | 0.7730 | 0.7402 |
| No log | 5.83 | 140 | 0.7788 | 0.7449 |
| No log | 6.04 | 145 | 0.7609 | 0.7347 |
| No log | 6.25 | 150 | 0.8058 | 0.7323 |
| No log | 6.46 | 155 | 0.8525 | 0.7331 |
| No log | 6.67 | 160 | 0.8504 | 0.7339 |
| No log | 6.88 | 165 | 0.8424 | 0.7300 |
| No log | 7.08 | 170 | 0.8413 | 0.7394 |
| No log | 7.29 | 175 | 0.8808 | 0.7268 |
| No log | 7.5 | 180 | 0.9058 | 0.7292 |
| No log | 7.71 | 185 | 0.9338 | 0.7363 |
| No log | 7.92 | 190 | 0.9412 | 0.7370 |
| No log | 8.12 | 195 | 0.9453 | 0.7339 |
| No log | 8.33 | 200 | 0.9544 | 0.7394 |
| No log | 8.54 | 205 | 0.9664 | 0.7402 |
| No log | 8.75 | 210 | 0.9840 | 0.7339 |
| No log | 8.96 | 215 | 0.9896 | 0.7370 |
| No log | 9.17 | 220 | 1.0239 | 0.7410 |
| No log | 9.38 | 225 | 1.0306 | 0.7418 |
| No log | 9.58 | 230 | 1.0358 | 0.7402 |
| No log | 9.79 | 235 | 1.0351 | 0.7410 |
| No log | 10.0 | 240 | 1.0332 | 0.7441 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.2
|
{"datasets": ["stereoset"], "license": "mit", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "xlnet-base-cased_stereoset_finetuned", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "stereoset", "type": "stereoset", "config": "intersentence", "split": "validation", "args": "intersentence"}, "metrics": [{"type": "accuracy", "value": 0.7441130298273155, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,508 |
Satwik11/gemma-2b-mt-Hindi-Fintuned
|
Satwik11
|
translation
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"translation",
"en",
"hi",
"dataset:cfilt/iitb-english-hindi",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-08-18T05:07:48Z |
2024-08-20T05:00:08+00:00
| 210 | 2 |
---
datasets:
- cfilt/iitb-english-hindi
language:
- en
- hi
library_name: transformers
license: apache-2.0
pipeline_tag: translation
---
# Model Card for Model ID
## Model Details
### Model Description
This model is a fine-tuned version of the GEMMA 2B multilingual transformer, specifically optimized for translating text from English to Hindi. It leverages the capabilities of the original GEMMA architecture to provide accurate and efficient translations.
-Model Name: Gemma-2b-mt-Hindi-Fintuned
-Model Type: Language Translation Model
-Base Model: Gemma-2b
-Task: English to Hindi Translation
-Framework: Transformers
### Model Sources [optional]
## Uses
### Direct Use
This model can be directly used for translating English text to Hindi. It is suitable for various applications such as:
-Localization of content
-Cross-lingual communication
-Educational tools for language learning
-Multilingual content creation
### Downstream Use [optional]
The model can be integrated into larger systems or applications that require English to Hindi translation capabilities, such as:
-Machine translation services
-Multilingual chatbots
-Content management systems for multilingual websites
[More Information Needed]
### Out-of-Scope Use
## Bias, Risks, and Limitations
-The model may struggle with idiomatic expressions or culturally specific content.
-There might be potential biases in the training data that could affect translation quality.
-The model's performance on specialized or technical content may vary.
-It may have limitations in handling complex grammatical structures or maintaining context in longer texts.
### Recommendations
-It's recommended to use the model in conjunction with human translators for high-stakes or nuanced translations.
-Regular evaluation and fine-tuning with diverse and representative data can help mitigate biases and improve performance.
## How to Get Started with the Model
Use the code below to get started with the model:
----------------------------------------------------------------------------------------
from transformers import AutoTokenizer, AutoModelForCausalLM
#Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Satwik11/gemma-2b-mt-Hindi-Fintuned")
model = AutoModelForCausalLM.from_pretrained("Satwik11/gemma-2b-mt-Hindi-Fintuned")
def generate_translation(prompt, max_length=90):
# Prepare the input
inputs = tokenizer(prompt, return_tensors='pt')
# Generate the translation
outputs = model.generate(**inputs, max_length=max_length)
# Decode the generated output
translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return translated_text
#Test the model with some example sentences
test_sentences = [
"Today is August 19.The maximum temperature is 70 degrees Fahrenheit"
]
for sentence in test_sentences:
prompt = f"Translate the following English text to Hindi: {sentence}"
translation = generate_translation(prompt)
print(translation)
-----------------------------------------------------------------------------------------------
## Training Details
### Training Data
The model was fine-tuned on the cfilt/iitb-english-hindi dataset, which contains English-Hindi sentence pairs. For more details about the dataset, refer to the dataset card on Hugging Face.
## Model Card Contact
For more information, please contact the model creators through the Hugging Face model repository: https://www.linkedin.com/in/satwik-sinha/
| null |
Non_BioNLP
|
# Model Card for Model ID
## Model Details
### Model Description
This model is a fine-tuned version of the GEMMA 2B multilingual transformer, specifically optimized for translating text from English to Hindi. It leverages the capabilities of the original GEMMA architecture to provide accurate and efficient translations.
-Model Name: Gemma-2b-mt-Hindi-Fintuned
-Model Type: Language Translation Model
-Base Model: Gemma-2b
-Task: English to Hindi Translation
-Framework: Transformers
### Model Sources [optional]
## Uses
### Direct Use
This model can be directly used for translating English text to Hindi. It is suitable for various applications such as:
-Localization of content
-Cross-lingual communication
-Educational tools for language learning
-Multilingual content creation
### Downstream Use [optional]
The model can be integrated into larger systems or applications that require English to Hindi translation capabilities, such as:
-Machine translation services
-Multilingual chatbots
-Content management systems for multilingual websites
[More Information Needed]
### Out-of-Scope Use
## Bias, Risks, and Limitations
-The model may struggle with idiomatic expressions or culturally specific content.
-There might be potential biases in the training data that could affect translation quality.
-The model's performance on specialized or technical content may vary.
-It may have limitations in handling complex grammatical structures or maintaining context in longer texts.
### Recommendations
-It's recommended to use the model in conjunction with human translators for high-stakes or nuanced translations.
-Regular evaluation and fine-tuning with diverse and representative data can help mitigate biases and improve performance.
## How to Get Started with the Model
Use the code below to get started with the model:
----------------------------------------------------------------------------------------
from transformers import AutoTokenizer, AutoModelForCausalLM
#Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Satwik11/gemma-2b-mt-Hindi-Fintuned")
model = AutoModelForCausalLM.from_pretrained("Satwik11/gemma-2b-mt-Hindi-Fintuned")
def generate_translation(prompt, max_length=90):
# Prepare the input
inputs = tokenizer(prompt, return_tensors='pt')
# Generate the translation
outputs = model.generate(**inputs, max_length=max_length)
# Decode the generated output
translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return translated_text
#Test the model with some example sentences
test_sentences = [
"Today is August 19.The maximum temperature is 70 degrees Fahrenheit"
]
for sentence in test_sentences:
prompt = f"Translate the following English text to Hindi: {sentence}"
translation = generate_translation(prompt)
print(translation)
-----------------------------------------------------------------------------------------------
## Training Details
### Training Data
The model was fine-tuned on the cfilt/iitb-english-hindi dataset, which contains English-Hindi sentence pairs. For more details about the dataset, refer to the dataset card on Hugging Face.
## Model Card Contact
For more information, please contact the model creators through the Hugging Face model repository: https://www.linkedin.com/in/satwik-sinha/
|
{"datasets": ["cfilt/iitb-english-hindi"], "language": ["en", "hi"], "library_name": "transformers", "license": "apache-2.0", "pipeline_tag": "translation"}
|
task
|
[
"TRANSLATION"
] | 41,509 |
gaudi/opus-mt-en-is-ctranslate2
|
gaudi
|
translation
|
[
"transformers",
"marian",
"ctranslate2",
"translation",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 2024-07-18T15:00:34Z |
2024-10-19T00:16:55+00:00
| 8 | 0 |
---
license: apache-2.0
tags:
- ctranslate2
- translation
---
# Repository General Information
## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)!
- Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-en-is)
- This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2).
- This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil).
# What is CTranslate2?
[CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models.
CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.
CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include:
- Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper
- Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon
- Encoder-only models: BERT, DistilBERT, XLM-RoBERTa
The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration.
# CTranslate2 Benchmarks
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset.
The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers.
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings.
## CPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 |
| Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 |
| Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 |
| CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 |
| CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 |
## GPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 |
| Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 |
| CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 |
| CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 |
`Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.`
**Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br />
**Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-en-is).**
## Internal Benchmarks
Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality.
# CTranslate2 Installation
```bash
pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0
```
### ct2-transformers-converter Command Used:
```bash
ct2-transformers-converter --model Helsinki-NLP/opus-mt-en-is --output_dir ./ctranslate2/opus-mt-en-is-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16
```
# CTranslate2 Converted Checkpoint Information:
**Compatible With:**
- [ctranslate2](https://github.com/OpenNMT/CTranslate2)
- [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
**Compute Type:**
- `compute_type=int8_float16` for `device="cuda"`
- `compute_type=int8` for `device="cpu"`
# Sample Code - ctranslate2
#### Clone the repository to the working directory or wherever you wish to store the model artifacts. ####
```bash
git clone https://huggingface.co/gaudi/opus-mt-en-is-ctranslate2
```
#### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. ####
```python
from ctranslate2 import Translator
import transformers
model_dir = "./opus-mt-en-is-ctranslate2" # Path to model directory.
translator = Translator(
model_path=model_dir,
device="cuda", # cpu, cuda, or auto.
inter_threads=1, # Maximum number of parallel translations.
intra_threads=4, # Number of OpenMP threads per translator.
compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda.
)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir)
source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX."))
results = translator.translate_batch([source])
target = results[0].hypotheses[0]
print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))
```
# Sample Code - hf-hub-ctranslate2
**Derived From [michaelfeil](https://huggingface.co/michaelfeil):**
```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer
model_name = "gaudi/opus-mt-en-is-ctranslate2"
model = TranslatorCT2fromHfHub(
model_name_or_path=model_name,
device="cuda",
compute_type="int8_float16",
tokenizer=AutoTokenizer.from_pretrained(model_name)
)
outputs = model.generate(
text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"],
)
print(outputs)
```
# License and other remarks:
License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-en-is) by Helsinki-NLP.
| null |
Non_BioNLP
|
# Repository General Information
## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)!
- Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-en-is)
- This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2).
- This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil).
# What is CTranslate2?
[CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models.
CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.
CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include:
- Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper
- Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon
- Encoder-only models: BERT, DistilBERT, XLM-RoBERTa
The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration.
# CTranslate2 Benchmarks
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset.
The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers.
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings.
## CPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 |
| Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 |
| Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 |
| CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 |
| CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 |
## GPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 |
| Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 |
| CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 |
| CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 |
`Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.`
**Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br />
**Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-en-is).**
## Internal Benchmarks
Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality.
# CTranslate2 Installation
```bash
pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0
```
### ct2-transformers-converter Command Used:
```bash
ct2-transformers-converter --model Helsinki-NLP/opus-mt-en-is --output_dir ./ctranslate2/opus-mt-en-is-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16
```
# CTranslate2 Converted Checkpoint Information:
**Compatible With:**
- [ctranslate2](https://github.com/OpenNMT/CTranslate2)
- [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
**Compute Type:**
- `compute_type=int8_float16` for `device="cuda"`
- `compute_type=int8` for `device="cpu"`
# Sample Code - ctranslate2
#### Clone the repository to the working directory or wherever you wish to store the model artifacts. ####
```bash
git clone https://huggingface.co/gaudi/opus-mt-en-is-ctranslate2
```
#### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. ####
```python
from ctranslate2 import Translator
import transformers
model_dir = "./opus-mt-en-is-ctranslate2" # Path to model directory.
translator = Translator(
model_path=model_dir,
device="cuda", # cpu, cuda, or auto.
inter_threads=1, # Maximum number of parallel translations.
intra_threads=4, # Number of OpenMP threads per translator.
compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda.
)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir)
source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX."))
results = translator.translate_batch([source])
target = results[0].hypotheses[0]
print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))
```
# Sample Code - hf-hub-ctranslate2
**Derived From [michaelfeil](https://huggingface.co/michaelfeil):**
```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer
model_name = "gaudi/opus-mt-en-is-ctranslate2"
model = TranslatorCT2fromHfHub(
model_name_or_path=model_name,
device="cuda",
compute_type="int8_float16",
tokenizer=AutoTokenizer.from_pretrained(model_name)
)
outputs = model.generate(
text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"],
)
print(outputs)
```
# License and other remarks:
License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-en-is) by Helsinki-NLP.
|
{"license": "apache-2.0", "tags": ["ctranslate2", "translation"]}
|
task
|
[
"TRANSLATION"
] | 41,510 |
taldarim/setfit-diffable-head
|
taldarim
|
text-classification
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 2023-09-30T00:27:57Z |
2023-09-30T00:28:10+00:00
| 7 | 0 |
---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# taldarim/setfit-diffable-head
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("taldarim/setfit-diffable-head")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
| null |
Non_BioNLP
|
# taldarim/setfit-diffable-head
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("taldarim/setfit-diffable-head")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
{"license": "apache-2.0", "pipeline_tag": "text-classification", "tags": ["setfit", "sentence-transformers", "text-classification"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,511 |
TheBloke/Redmond-Hermes-Coder-GPTQ
|
TheBloke
|
text-generation
|
[
"transformers",
"safetensors",
"gpt_bigcode",
"text-generation",
"starcoder",
"wizardcoder",
"code",
"self-instruct",
"distillation",
"en",
"license:gpl",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | 2023-07-01T18:12:53Z |
2023-08-21T02:08:38+00:00
| 24 | 10 |
---
language:
- en
license: gpl
tags:
- starcoder
- wizardcoder
- code
- self-instruct
- distillation
inference: false
---
<!-- 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 -->
# NousResearch's Redmond Hermes Coder GPTQ
These files are GPTQ 4bit model files for [NousResearch's Redmond Hermes Coder](https://huggingface.co/NousResearch/Redmond-Hermes-Coder).
It is the result of quantising to 4bit using [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ).
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Redmond-Hermes-Coder-GPTQ)
* [4, 5, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Redmond-Hermes-Coder-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NousResearch/Redmond-Hermes-Coder)
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction: PROMPT
### Response:
```
## How to easily download and use this model in text-generation-webui
Please make sure you're using the latest version of text-generation-webui.
Note: this is a non-Llama model which cannot be used with ExLlama. Use Loader: AutoGPTQ.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Redmond-Hermes-Coder-GPTQ`.
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: `Redmond-Hermes-Coder-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 set 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!
## How to use this GPTQ model from Python code
First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
`GITHUB_ACTIONS=true pip install auto-gptq`
Then try the following example code:
```python
from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import argparse
model_name_or_path = "TheBloke/Redmond-Hermes-Coder-GPTQ"
model_basename = "model"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
model_basename=model_basename,
use_safetensors=True,
trust_remote_code=False,
device="cuda:0",
use_triton=use_triton,
quantize_config=None)
prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction: PROMPT
### Response:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Provided files
**gptq_model-4bit-128g.safetensors**
This will work with AutoGPTQ and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
If a Llama model, it will also be supported by ExLlama, which will provide 2x speedup over AutoGPTQ and GPTQ-for-LLaMa.
It was created with group_size 128 to increase inference accuracy, but without --act-order (desc_act) to increase compatibility and improve inference speed.
* `gptq_model-4bit-128g.safetensors`
* Works with AutoGPTQ in CUDA or Triton modes.
* Does NOT work with [ExLlama](https://github.com/turboderp/exllama) as it's not a Llama model.
* Works with GPTQ-for-LLaMa in CUDA mode. May have issues with GPTQ-for-LLaMa Triton mode.
* Works with text-generation-webui, including one-click-installers.
* Parameters: Groupsize = 128. Act Order / desc_act = False.
<!-- 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!
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**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: NousResearch's Redmond Hermes Coder
# Model Card: Redmond-Hermes-Coder 15B
## Model Description
Redmond-Hermes-Coder 15B is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium and Karan4D leading the fine tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors.
This model was trained with a WizardCoder base, which itself uses a StarCoder base model.
The model is truly great at code, but, it does come with a tradeoff though. While far better at code than the original Nous-Hermes built on Llama, it is worse than WizardCoder at pure code benchmarks, like HumanEval.
It comes in at 39% on HumanEval, with WizardCoder at 57%. This is a preliminary experiment, and we are exploring improvements now.
However, it does seem better at non-code than WizardCoder on a variety of things, including writing tasks.
## Model Training
The model was trained almost entirely on synthetic GPT-4 outputs. This includes data from diverse sources such as GPTeacher, the general, roleplay v1&2, code instruct datasets, Nous Instruct & PDACTL (unpublished), CodeAlpaca, Evol_Instruct Uncensored, GPT4-LLM, and Unnatural Instructions.
Additional data inputs came from Camel-AI's Biology/Physics/Chemistry and Math Datasets, Airoboros' (v1) GPT-4 Dataset, and more from CodeAlpaca. The total volume of data encompassed over 300,000 instructions.
## Collaborators
The model fine-tuning and the datasets were a collaboration of efforts and resources from members of Nous Research, includingTeknium, Karan4D, Huemin Art, and Redmond AI's generous compute grants.
Huge shoutout and acknowledgement is deserved for all the dataset creators who generously share their datasets openly.
Among the contributors of datasets, GPTeacher was made available by Teknium, Wizard LM by nlpxucan, and the Nous Research Instruct Dataset was provided by Karan4D and HueminArt.
The GPT4-LLM and Unnatural Instructions were provided by Microsoft, Airoboros dataset by jondurbin, Camel-AI datasets are from Camel-AI, and CodeAlpaca dataset by Sahil 2801.
If anyone was left out, please open a thread in the community tab.
## Prompt Format
The model follows the Alpaca prompt format:
```
### Instruction:
### Response:
```
or
```
### Instruction:
### Input:
### Response:
```
## Resources for Applied Use Cases:
For an example of a back and forth chatbot using huggingface transformers and discord, check out: https://github.com/teknium1/alpaca-discord
For an example of a roleplaying discord bot, check out this: https://github.com/teknium1/alpaca-roleplay-discordbot
## Future Plans
The model is currently being uploaded in FP16 format, and there are plans to convert the model to GGML and GPTQ 4bit quantizations. The team is also working on a full benchmark, similar to what was done for GPT4-x-Vicuna. We will try to get in discussions to get the model included in the GPT4All.
## Benchmark Results
```
HumanEval: 39%
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|arc_challenge | 0|acc |0.2858|± |0.0132|
| | |acc_norm |0.3148|± |0.0136|
|arc_easy | 0|acc |0.5349|± |0.0102|
| | |acc_norm |0.5097|± |0.0103|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5158|± |0.0364|
|bigbench_date_understanding | 0|multiple_choice_grade|0.5230|± |0.0260|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3295|± |0.0293|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.1003|± |0.0159|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.2260|± |0.0187|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.1957|± |0.0150|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.3733|± |0.0280|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.3200|± |0.0209|
|bigbench_navigate | 0|multiple_choice_grade|0.4830|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.4150|± |0.0110|
|bigbench_ruin_names | 0|multiple_choice_grade|0.2143|± |0.0194|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2926|± |0.0144|
|bigbench_snarks | 0|multiple_choice_grade|0.5249|± |0.0372|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.4817|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.2700|± |0.0140|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.1864|± |0.0110|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1349|± |0.0082|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.3733|± |0.0280|
|boolq | 1|acc |0.5498|± |0.0087|
|hellaswag | 0|acc |0.3814|± |0.0048|
| | |acc_norm |0.4677|± |0.0050|
|openbookqa | 0|acc |0.1960|± |0.0178|
| | |acc_norm |0.3100|± |0.0207|
|piqa | 0|acc |0.6600|± |0.0111|
| | |acc_norm |0.6610|± |0.0110|
|winogrande | 0|acc |0.5343|± |0.0140|
```
## Model Usage
The model is available for download on Hugging Face. It is suitable for a wide range of language tasks, from generating creative text to understanding and following complex instructions.
Compute provided by our project sponsor Redmond AI, thank you!!
| null |
Non_BioNLP
|
<!-- 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 -->
# NousResearch's Redmond Hermes Coder GPTQ
These files are GPTQ 4bit model files for [NousResearch's Redmond Hermes Coder](https://huggingface.co/NousResearch/Redmond-Hermes-Coder).
It is the result of quantising to 4bit using [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ).
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Redmond-Hermes-Coder-GPTQ)
* [4, 5, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Redmond-Hermes-Coder-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NousResearch/Redmond-Hermes-Coder)
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction: PROMPT
### Response:
```
## How to easily download and use this model in text-generation-webui
Please make sure you're using the latest version of text-generation-webui.
Note: this is a non-Llama model which cannot be used with ExLlama. Use Loader: AutoGPTQ.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Redmond-Hermes-Coder-GPTQ`.
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: `Redmond-Hermes-Coder-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 set 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!
## How to use this GPTQ model from Python code
First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
`GITHUB_ACTIONS=true pip install auto-gptq`
Then try the following example code:
```python
from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import argparse
model_name_or_path = "TheBloke/Redmond-Hermes-Coder-GPTQ"
model_basename = "model"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
model_basename=model_basename,
use_safetensors=True,
trust_remote_code=False,
device="cuda:0",
use_triton=use_triton,
quantize_config=None)
prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction: PROMPT
### Response:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Provided files
**gptq_model-4bit-128g.safetensors**
This will work with AutoGPTQ and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
If a Llama model, it will also be supported by ExLlama, which will provide 2x speedup over AutoGPTQ and GPTQ-for-LLaMa.
It was created with group_size 128 to increase inference accuracy, but without --act-order (desc_act) to increase compatibility and improve inference speed.
* `gptq_model-4bit-128g.safetensors`
* Works with AutoGPTQ in CUDA or Triton modes.
* Does NOT work with [ExLlama](https://github.com/turboderp/exllama) as it's not a Llama model.
* Works with GPTQ-for-LLaMa in CUDA mode. May have issues with GPTQ-for-LLaMa Triton mode.
* Works with text-generation-webui, including one-click-installers.
* Parameters: Groupsize = 128. Act Order / desc_act = False.
<!-- 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!
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**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: NousResearch's Redmond Hermes Coder
# Model Card: Redmond-Hermes-Coder 15B
## Model Description
Redmond-Hermes-Coder 15B is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium and Karan4D leading the fine tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors.
This model was trained with a WizardCoder base, which itself uses a StarCoder base model.
The model is truly great at code, but, it does come with a tradeoff though. While far better at code than the original Nous-Hermes built on Llama, it is worse than WizardCoder at pure code benchmarks, like HumanEval.
It comes in at 39% on HumanEval, with WizardCoder at 57%. This is a preliminary experiment, and we are exploring improvements now.
However, it does seem better at non-code than WizardCoder on a variety of things, including writing tasks.
## Model Training
The model was trained almost entirely on synthetic GPT-4 outputs. This includes data from diverse sources such as GPTeacher, the general, roleplay v1&2, code instruct datasets, Nous Instruct & PDACTL (unpublished), CodeAlpaca, Evol_Instruct Uncensored, GPT4-LLM, and Unnatural Instructions.
Additional data inputs came from Camel-AI's Biology/Physics/Chemistry and Math Datasets, Airoboros' (v1) GPT-4 Dataset, and more from CodeAlpaca. The total volume of data encompassed over 300,000 instructions.
## Collaborators
The model fine-tuning and the datasets were a collaboration of efforts and resources from members of Nous Research, includingTeknium, Karan4D, Huemin Art, and Redmond AI's generous compute grants.
Huge shoutout and acknowledgement is deserved for all the dataset creators who generously share their datasets openly.
Among the contributors of datasets, GPTeacher was made available by Teknium, Wizard LM by nlpxucan, and the Nous Research Instruct Dataset was provided by Karan4D and HueminArt.
The GPT4-LLM and Unnatural Instructions were provided by Microsoft, Airoboros dataset by jondurbin, Camel-AI datasets are from Camel-AI, and CodeAlpaca dataset by Sahil 2801.
If anyone was left out, please open a thread in the community tab.
## Prompt Format
The model follows the Alpaca prompt format:
```
### Instruction:
### Response:
```
or
```
### Instruction:
### Input:
### Response:
```
## Resources for Applied Use Cases:
For an example of a back and forth chatbot using huggingface transformers and discord, check out: https://github.com/teknium1/alpaca-discord
For an example of a roleplaying discord bot, check out this: https://github.com/teknium1/alpaca-roleplay-discordbot
## Future Plans
The model is currently being uploaded in FP16 format, and there are plans to convert the model to GGML and GPTQ 4bit quantizations. The team is also working on a full benchmark, similar to what was done for GPT4-x-Vicuna. We will try to get in discussions to get the model included in the GPT4All.
## Benchmark Results
```
HumanEval: 39%
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|arc_challenge | 0|acc |0.2858|± |0.0132|
| | |acc_norm |0.3148|± |0.0136|
|arc_easy | 0|acc |0.5349|± |0.0102|
| | |acc_norm |0.5097|± |0.0103|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5158|± |0.0364|
|bigbench_date_understanding | 0|multiple_choice_grade|0.5230|± |0.0260|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3295|± |0.0293|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.1003|± |0.0159|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.2260|± |0.0187|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.1957|± |0.0150|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.3733|± |0.0280|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.3200|± |0.0209|
|bigbench_navigate | 0|multiple_choice_grade|0.4830|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.4150|± |0.0110|
|bigbench_ruin_names | 0|multiple_choice_grade|0.2143|± |0.0194|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2926|± |0.0144|
|bigbench_snarks | 0|multiple_choice_grade|0.5249|± |0.0372|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.4817|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.2700|± |0.0140|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.1864|± |0.0110|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1349|± |0.0082|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.3733|± |0.0280|
|boolq | 1|acc |0.5498|± |0.0087|
|hellaswag | 0|acc |0.3814|± |0.0048|
| | |acc_norm |0.4677|± |0.0050|
|openbookqa | 0|acc |0.1960|± |0.0178|
| | |acc_norm |0.3100|± |0.0207|
|piqa | 0|acc |0.6600|± |0.0111|
| | |acc_norm |0.6610|± |0.0110|
|winogrande | 0|acc |0.5343|± |0.0140|
```
## Model Usage
The model is available for download on Hugging Face. It is suitable for a wide range of language tasks, from generating creative text to understanding and following complex instructions.
Compute provided by our project sponsor Redmond AI, thank you!!
|
{"language": ["en"], "license": "gpl", "tags": ["starcoder", "wizardcoder", "code", "self-instruct", "distillation"], "inference": false}
|
task
|
[
"TRANSLATION"
] | 41,512 |
akani/distilbert-base-uncased-finetuned-cola
|
akani
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-12-05T18:58:23Z |
2022-12-05T20:47:33+00:00
| 112 | 0 |
---
datasets:
- glue
license: apache-2.0
metrics:
- matthews_correlation
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-cola
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
config: cola
split: train
args: cola
metrics:
- type: matthews_correlation
value: 0.5474713423103301
name: Matthews Correlation
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5254
- Matthews Correlation: 0.5475
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5221 | 1.0 | 535 | 0.5360 | 0.4307 |
| 0.3491 | 2.0 | 1070 | 0.5128 | 0.4972 |
| 0.2382 | 3.0 | 1605 | 0.5254 | 0.5475 |
| 0.1756 | 4.0 | 2140 | 0.7479 | 0.5330 |
| 0.1248 | 5.0 | 2675 | 0.7978 | 0.5414 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5254
- Matthews Correlation: 0.5475
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5221 | 1.0 | 535 | 0.5360 | 0.4307 |
| 0.3491 | 2.0 | 1070 | 0.5128 | 0.4972 |
| 0.2382 | 3.0 | 1605 | 0.5254 | 0.5475 |
| 0.1756 | 4.0 | 2140 | 0.7479 | 0.5330 |
| 0.1248 | 5.0 | 2675 | 0.7978 | 0.5414 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
|
{"datasets": ["glue"], "license": "apache-2.0", "metrics": ["matthews_correlation"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetuned-cola", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "config": "cola", "split": "train", "args": "cola"}, "metrics": [{"type": "matthews_correlation", "value": 0.5474713423103301, "name": "Matthews Correlation"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,513 |
Agnuxo/Qwen2-1.5B-Instruct_MOE_CODE_assistant-CODE-Python_16bit
|
Agnuxo
|
text-generation
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:Agnuxo/Qwen2-1.5B-Instruct_MOE_assistant_16bit",
"base_model:finetune:Agnuxo/Qwen2-1.5B-Instruct_MOE_assistant_16bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-08-26T18:53:29Z |
2024-08-27T10:32:29+00:00
| 4 | 0 |
---
base_model: Agnuxo/Qwen2-1.5B-Instruct_MOE_assistant_16bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft
---
# Uploaded model
- **Developed by:** Agnuxo
- **License:** apache-2.0
- **Finetuned from model :** Agnuxo/Qwen2-1.5B-Instruct_MOE_assistant_16bit
This qwen2 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)
## How the MOE System Works
This model is a core component of a larger Multi-Expert Question Answering System. Here's a breakdown of the system's functionality:
1. **Model Loading:** The system loads the "director" LLM and keeps other expert LLMs (e.g., for programming, biology, mathematics) ready for use.
2. **Expert Routing:** When a user asks a question, the system either:
- Uses keyword matching to identify the relevant domain.
- Consults the director LLM to classify the question's category.
3. **Dynamic Expert Loading:** The system loads the chosen expert LLM into memory, optimizing resource usage by releasing any previously active expert.
4. **Response Generation:** The selected expert LLM receives the question and generates a tailored answer.
5. **Chat Interface:** A user-friendly chat interface facilitates interaction with the MOE system.
This MOE approach enhances efficiency and accuracy compared to relying on a single, general-purpose LLM.
Repository and Additional Information
Full Code: https://huggingface.co/Agnuxo/Qwen2-1.5B-Instruct_MOE_Director_16bit/resolve/main/MOE-LLMs3.py
GitHub Repository: https://github.com/Agnuxo1/NEBULA
## Code Example
The following code demonstrates the implementation of the Multi-Expert Question Answering System:
```python
import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
MODEL_CONFIG = {
"director": {
"name": "Agnuxo/Qwen2-1.5B-Instruct_MOE_Director_16bit",
"task": "text-generation",
},
"programming": {
"name": "Qwen/Qwen2-1.5B-Instruct",
"task": "text-generation",
},
"biology": {
"name": "Agnuxo/Qwen2-1.5B-Instruct_MOE_BIOLOGY_assistant_16bit",
"task": "text-generation",
},
"mathematics": {
"name": "Qwen/Qwen2-Math-1.5B-Instruct",
"task": "text-generation",
}
}
KEYWORDS = {
"biology": ["cell", "DNA", "protein", "evolution", "genetics", "ecosystem", "organism", "metabolism", "photosynthesis", "microbiology", "célula", "ADN", "proteína", "evolución", "genética", "ecosistema", "organismo", "metabolismo", "fotosíntesis", "microbiología"],
"mathematics": ["Math" "mathematics", "equation", "integral", "derivative", "function", "geometry", "algebra", "statistics", "probability", "ecuación", "integral", "derivada", "función", "geometría", "álgebra", "estadística", "probabilidad"],
"programming": ["python", "java", "C++", "HTML", "scrip", "code", "Dataset", "API", "framework", "debugging", "algorithm", "compiler", "database", "CSS", "JSON", "XML", "encryption", "IDE", "repository", "Git", "version control", "front-end", "back-end", "API", "stack trace", "REST", "machine learning"]
}
class MOELLM:
def __init__(self):
self.current_expert = None
self.current_model = None
self.current_tokenizer = None
self.device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using device: {self.device}")
self.load_director_model()
def load_director_model(self):
"""Loads the director model."""
print("Loading director model...")
model_name = MODEL_CONFIG["director"]["name"]
self.director_tokenizer = AutoTokenizer.from_pretrained(model_name)
self.director_model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16).to(self.device)
self.director_pipeline = pipeline(
MODEL_CONFIG["director"]["task"],
model=self.director_model,
tokenizer=self.director_tokenizer,
device=self.device
)
print("Director model loaded.")
def load_expert_model(self, expert):
"""Dynamically loads an expert model, releasing memory from the previous model."""
if expert not in MODEL_CONFIG:
raise ValueError(f"Unknown expert: {expert}")
if self.current_expert != expert:
print(f"Loading expert model: {expert}...")
# Free memory from the current model if it exists
if self.current_model:
del self.current_model
del self.current_tokenizer
torch.cuda.empty_cache()
model_config = MODEL_CONFIG[expert]
self.current_tokenizer = AutoTokenizer.from_pretrained(model_config["name"])
self.current_model = AutoModelForCausalLM.from_pretrained(model_config["name"], torch_dtype=torch.float16).to(self.device)
self.current_expert = expert
print(f"{expert.capitalize()} model loaded.")
return pipeline(
MODEL_CONFIG[expert]["task"],
model=self.current_model,
tokenizer=self.current_tokenizer,
device=self.device
)
def determine_expert_by_keywords(self, question):
"""Determines the expert based on keywords in the question."""
question_lower = question.lower()
for expert, keywords in KEYWORDS.items():
if any(keyword in question_lower for keyword in keywords):
return expert
return None
def determine_expert(self, question):
"""Determines which expert should answer the question."""
expert = self.determine_expert_by_keywords(question)
if expert:
print(f"Expert determined by keyword: {expert}")
return expert
prompt = f"Classify the following question into one of these categories: programming, biology, mathematics. Question: {question}\nCategory:"
response = self.director_pipeline(prompt, max_length=100, num_return_sequences=1)[0]['generated_text']
expert = response.split(":")[-1].strip().lower()
if expert not in MODEL_CONFIG:
expert = "director"
print(f"Redirecting question to: {expert}")
return expert
def generate_response(self, question, expert):
"""Generates a response using the appropriate model."""
try:
model = self.load_expert_model(expert)
prompt = f"Answer the following question as an expert in {expert}: {question}\nAnswer:"
response = model(prompt, max_length=200, num_return_sequences=1)[0]['generated_text']
return response.split("Answer:")[-1].strip()
except Exception as e:
print(f"Error generating response: {str(e)}")
return "Sorry, there was an error processing your request. Please try again."
def chat_interface(self):
"""Simple chat interface."""
print("Welcome to the MOE-LLM chat. Type 'exit' to quit.")
while True:
question = input("\nYou: ")
if question.lower() in ['exit', 'quit']:
break
try:
expert = self.determine_expert(question)
response = self.generate_response(question, expert)
print(f"\n{expert.capitalize()}: {response}")
except Exception as e:
print(f"Error in chat: {str(e)}")
print("Please try asking another question.")
if __name__ == "__main__":
moe_llm = MOELLM()
moe_llm.chat_interface()
| null |
Non_BioNLP
|
# Uploaded model
- **Developed by:** Agnuxo
- **License:** apache-2.0
- **Finetuned from model :** Agnuxo/Qwen2-1.5B-Instruct_MOE_assistant_16bit
This qwen2 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)
## How the MOE System Works
This model is a core component of a larger Multi-Expert Question Answering System. Here's a breakdown of the system's functionality:
1. **Model Loading:** The system loads the "director" LLM and keeps other expert LLMs (e.g., for programming, biology, mathematics) ready for use.
2. **Expert Routing:** When a user asks a question, the system either:
- Uses keyword matching to identify the relevant domain.
- Consults the director LLM to classify the question's category.
3. **Dynamic Expert Loading:** The system loads the chosen expert LLM into memory, optimizing resource usage by releasing any previously active expert.
4. **Response Generation:** The selected expert LLM receives the question and generates a tailored answer.
5. **Chat Interface:** A user-friendly chat interface facilitates interaction with the MOE system.
This MOE approach enhances efficiency and accuracy compared to relying on a single, general-purpose LLM.
Repository and Additional Information
Full Code: https://huggingface.co/Agnuxo/Qwen2-1.5B-Instruct_MOE_Director_16bit/resolve/main/MOE-LLMs3.py
GitHub Repository: https://github.com/Agnuxo1/NEBULA
## Code Example
The following code demonstrates the implementation of the Multi-Expert Question Answering System:
```python
import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
MODEL_CONFIG = {
"director": {
"name": "Agnuxo/Qwen2-1.5B-Instruct_MOE_Director_16bit",
"task": "text-generation",
},
"programming": {
"name": "Qwen/Qwen2-1.5B-Instruct",
"task": "text-generation",
},
"biology": {
"name": "Agnuxo/Qwen2-1.5B-Instruct_MOE_BIOLOGY_assistant_16bit",
"task": "text-generation",
},
"mathematics": {
"name": "Qwen/Qwen2-Math-1.5B-Instruct",
"task": "text-generation",
}
}
KEYWORDS = {
"biology": ["cell", "DNA", "protein", "evolution", "genetics", "ecosystem", "organism", "metabolism", "photosynthesis", "microbiology", "célula", "ADN", "proteína", "evolución", "genética", "ecosistema", "organismo", "metabolismo", "fotosíntesis", "microbiología"],
"mathematics": ["Math" "mathematics", "equation", "integral", "derivative", "function", "geometry", "algebra", "statistics", "probability", "ecuación", "integral", "derivada", "función", "geometría", "álgebra", "estadística", "probabilidad"],
"programming": ["python", "java", "C++", "HTML", "scrip", "code", "Dataset", "API", "framework", "debugging", "algorithm", "compiler", "database", "CSS", "JSON", "XML", "encryption", "IDE", "repository", "Git", "version control", "front-end", "back-end", "API", "stack trace", "REST", "machine learning"]
}
class MOELLM:
def __init__(self):
self.current_expert = None
self.current_model = None
self.current_tokenizer = None
self.device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using device: {self.device}")
self.load_director_model()
def load_director_model(self):
"""Loads the director model."""
print("Loading director model...")
model_name = MODEL_CONFIG["director"]["name"]
self.director_tokenizer = AutoTokenizer.from_pretrained(model_name)
self.director_model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16).to(self.device)
self.director_pipeline = pipeline(
MODEL_CONFIG["director"]["task"],
model=self.director_model,
tokenizer=self.director_tokenizer,
device=self.device
)
print("Director model loaded.")
def load_expert_model(self, expert):
"""Dynamically loads an expert model, releasing memory from the previous model."""
if expert not in MODEL_CONFIG:
raise ValueError(f"Unknown expert: {expert}")
if self.current_expert != expert:
print(f"Loading expert model: {expert}...")
# Free memory from the current model if it exists
if self.current_model:
del self.current_model
del self.current_tokenizer
torch.cuda.empty_cache()
model_config = MODEL_CONFIG[expert]
self.current_tokenizer = AutoTokenizer.from_pretrained(model_config["name"])
self.current_model = AutoModelForCausalLM.from_pretrained(model_config["name"], torch_dtype=torch.float16).to(self.device)
self.current_expert = expert
print(f"{expert.capitalize()} model loaded.")
return pipeline(
MODEL_CONFIG[expert]["task"],
model=self.current_model,
tokenizer=self.current_tokenizer,
device=self.device
)
def determine_expert_by_keywords(self, question):
"""Determines the expert based on keywords in the question."""
question_lower = question.lower()
for expert, keywords in KEYWORDS.items():
if any(keyword in question_lower for keyword in keywords):
return expert
return None
def determine_expert(self, question):
"""Determines which expert should answer the question."""
expert = self.determine_expert_by_keywords(question)
if expert:
print(f"Expert determined by keyword: {expert}")
return expert
prompt = f"Classify the following question into one of these categories: programming, biology, mathematics. Question: {question}\nCategory:"
response = self.director_pipeline(prompt, max_length=100, num_return_sequences=1)[0]['generated_text']
expert = response.split(":")[-1].strip().lower()
if expert not in MODEL_CONFIG:
expert = "director"
print(f"Redirecting question to: {expert}")
return expert
def generate_response(self, question, expert):
"""Generates a response using the appropriate model."""
try:
model = self.load_expert_model(expert)
prompt = f"Answer the following question as an expert in {expert}: {question}\nAnswer:"
response = model(prompt, max_length=200, num_return_sequences=1)[0]['generated_text']
return response.split("Answer:")[-1].strip()
except Exception as e:
print(f"Error generating response: {str(e)}")
return "Sorry, there was an error processing your request. Please try again."
def chat_interface(self):
"""Simple chat interface."""
print("Welcome to the MOE-LLM chat. Type 'exit' to quit.")
while True:
question = input("\nYou: ")
if question.lower() in ['exit', 'quit']:
break
try:
expert = self.determine_expert(question)
response = self.generate_response(question, expert)
print(f"\n{expert.capitalize()}: {response}")
except Exception as e:
print(f"Error in chat: {str(e)}")
print("Please try asking another question.")
if __name__ == "__main__":
moe_llm = MOELLM()
moe_llm.chat_interface()
|
{"base_model": "Agnuxo/Qwen2-1.5B-Instruct_MOE_assistant_16bit", "language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "qwen2", "trl", "sft"]}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,514 |
keras-io/vit-small-ds
|
keras-io
|
image-classification
|
[
"tf-keras",
"image-classification",
"arxiv:2010.11929",
"arxiv:2112.13492",
"license:apache-2.0",
"region:us"
] | 2022-03-02T23:29:05Z |
2024-07-05T12:47:40+00:00
| 7 | 0 |
---
library_name: tf-keras
license: apache-2.0
tags:
- image-classification
---
# Train a Vision Transformer on small datasets
Author: [Aritra Roy Gosthipaty](https://twitter.com/ariG23498)
[Keras Blog](https://keras.io/examples/vision/vit_small_ds/) | [Colab Notebook](https://colab.research.google.com/github/keras-team/keras-io/blob/master/examples/vision/ipynb/vit_small_ds.ipynb)
In the academic paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929), the authors mention that Vision Transformers (ViT) are data-hungry. Therefore, pretraining a ViT on a large-sized dataset like JFT300M and fine-tuning it on medium-sized datasets (like ImageNet) is the only way to beat state-of-the-art Convolutional Neural Network models.
The self-attention layer of ViT lacks locality inductive bias (the notion that image pixels are locally correlated and that their correlation maps are translation-invariant). This is the reason why ViTs need more data. On the other hand, CNNs look at images through spatial sliding windows, which helps them get better results with smaller datasets.
In the academic paper [Vision Transformer for Small-Size Datasets](https://arxiv.org/abs/2112.13492v1), the authors set out to tackle the problem of locality inductive bias in ViTs.
The main ideas are:
- Shifted Patch Tokenization
- Locality Self Attention
# Use the pre-trained model
The model is pre-trained on the CIFAR100 dataset with the following hyperparameters:
```python
# DATA
NUM_CLASSES = 100
INPUT_SHAPE = (32, 32, 3)
BUFFER_SIZE = 512
BATCH_SIZE = 256
# AUGMENTATION
IMAGE_SIZE = 72
PATCH_SIZE = 6
NUM_PATCHES = (IMAGE_SIZE // PATCH_SIZE) ** 2
# OPTIMIZER
LEARNING_RATE = 0.001
WEIGHT_DECAY = 0.0001
# TRAINING
EPOCHS = 50
# ARCHITECTURE
LAYER_NORM_EPS = 1e-6
TRANSFORMER_LAYERS = 8
PROJECTION_DIM = 64
NUM_HEADS = 4
TRANSFORMER_UNITS = [
PROJECTION_DIM * 2,
PROJECTION_DIM,
]
MLP_HEAD_UNITS = [
2048,
1024
]
```
I have used the `AdamW` optimizer with cosine decay learning schedule. You can find the entire implementation in the keras blog post.
To use the pretrained model:
```python
loaded_model = from_pretrained_keras("keras-io/vit-small-ds")
_, accuracy, top_5_accuracy = loaded_model.evaluate(test_ds)
print(f"Test accuracy: {round(accuracy * 100, 2)}%")
print(f"Test top 5 accuracy: {round(top_5_accuracy * 100, 2)}%")
```
For an indepth understanding of the model uploading and downloading process one can refer to this [colab notebook](https://colab.research.google.com/drive/1nCMhefqySzG2p8wyXhmeAX5urddQXt49?usp=sharing).
Important: The data augmentation pipeline is excluded from the model. TensorFlow `2.7` has a weird issue of serializaiton with augmentation pipeline. You can follow [this GitHub issue](https://github.com/huggingface/huggingface_hub/issues/593) for more updates. To send images through the model, one needs to make use of the `tf.data` and `map` API to map the augmentation.
| null |
Non_BioNLP
|
# Train a Vision Transformer on small datasets
Author: [Aritra Roy Gosthipaty](https://twitter.com/ariG23498)
[Keras Blog](https://keras.io/examples/vision/vit_small_ds/) | [Colab Notebook](https://colab.research.google.com/github/keras-team/keras-io/blob/master/examples/vision/ipynb/vit_small_ds.ipynb)
In the academic paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929), the authors mention that Vision Transformers (ViT) are data-hungry. Therefore, pretraining a ViT on a large-sized dataset like JFT300M and fine-tuning it on medium-sized datasets (like ImageNet) is the only way to beat state-of-the-art Convolutional Neural Network models.
The self-attention layer of ViT lacks locality inductive bias (the notion that image pixels are locally correlated and that their correlation maps are translation-invariant). This is the reason why ViTs need more data. On the other hand, CNNs look at images through spatial sliding windows, which helps them get better results with smaller datasets.
In the academic paper [Vision Transformer for Small-Size Datasets](https://arxiv.org/abs/2112.13492v1), the authors set out to tackle the problem of locality inductive bias in ViTs.
The main ideas are:
- Shifted Patch Tokenization
- Locality Self Attention
# Use the pre-trained model
The model is pre-trained on the CIFAR100 dataset with the following hyperparameters:
```python
# DATA
NUM_CLASSES = 100
INPUT_SHAPE = (32, 32, 3)
BUFFER_SIZE = 512
BATCH_SIZE = 256
# AUGMENTATION
IMAGE_SIZE = 72
PATCH_SIZE = 6
NUM_PATCHES = (IMAGE_SIZE // PATCH_SIZE) ** 2
# OPTIMIZER
LEARNING_RATE = 0.001
WEIGHT_DECAY = 0.0001
# TRAINING
EPOCHS = 50
# ARCHITECTURE
LAYER_NORM_EPS = 1e-6
TRANSFORMER_LAYERS = 8
PROJECTION_DIM = 64
NUM_HEADS = 4
TRANSFORMER_UNITS = [
PROJECTION_DIM * 2,
PROJECTION_DIM,
]
MLP_HEAD_UNITS = [
2048,
1024
]
```
I have used the `AdamW` optimizer with cosine decay learning schedule. You can find the entire implementation in the keras blog post.
To use the pretrained model:
```python
loaded_model = from_pretrained_keras("keras-io/vit-small-ds")
_, accuracy, top_5_accuracy = loaded_model.evaluate(test_ds)
print(f"Test accuracy: {round(accuracy * 100, 2)}%")
print(f"Test top 5 accuracy: {round(top_5_accuracy * 100, 2)}%")
```
For an indepth understanding of the model uploading and downloading process one can refer to this [colab notebook](https://colab.research.google.com/drive/1nCMhefqySzG2p8wyXhmeAX5urddQXt49?usp=sharing).
Important: The data augmentation pipeline is excluded from the model. TensorFlow `2.7` has a weird issue of serializaiton with augmentation pipeline. You can follow [this GitHub issue](https://github.com/huggingface/huggingface_hub/issues/593) for more updates. To send images through the model, one needs to make use of the `tf.data` and `map` API to map the augmentation.
|
{"library_name": "tf-keras", "license": "apache-2.0", "tags": ["image-classification"]}
|
task
|
[
"TRANSLATION"
] | 41,515 |
gokulsrinivasagan/bert_tiny_lda_100_v1_book_qqp
|
gokulsrinivasagan
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokulsrinivasagan/bert_tiny_lda_100_v1_book",
"base_model:finetune:gokulsrinivasagan/bert_tiny_lda_100_v1_book",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-12-10T14:32:31Z |
2024-12-10T15:01:26+00:00
| 5 | 0 |
---
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1_book
datasets:
- glue
language:
- en
library_name: transformers
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: bert_tiny_lda_100_v1_book_qqp
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- type: accuracy
value: 0.869972792480831
name: Accuracy
- type: f1
value: 0.8219113113587858
name: F1
---
<!-- 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. -->
# bert_tiny_lda_100_v1_book_qqp
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3060
- Accuracy: 0.8700
- F1: 0.8219
- Combined Score: 0.8459
## 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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4139 | 1.0 | 1422 | 0.3737 | 0.8295 | 0.7418 | 0.7857 |
| 0.3158 | 2.0 | 2844 | 0.3214 | 0.8611 | 0.8107 | 0.8359 |
| 0.2619 | 3.0 | 4266 | 0.3060 | 0.8700 | 0.8219 | 0.8459 |
| 0.218 | 4.0 | 5688 | 0.3371 | 0.8694 | 0.8117 | 0.8405 |
| 0.1821 | 5.0 | 7110 | 0.3295 | 0.8787 | 0.8341 | 0.8564 |
| 0.1502 | 6.0 | 8532 | 0.3353 | 0.8790 | 0.8389 | 0.8589 |
| 0.1258 | 7.0 | 9954 | 0.3609 | 0.8776 | 0.8375 | 0.8576 |
| 0.105 | 8.0 | 11376 | 0.4070 | 0.8786 | 0.8329 | 0.8558 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
| null |
Non_BioNLP
|
<!-- 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. -->
# bert_tiny_lda_100_v1_book_qqp
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3060
- Accuracy: 0.8700
- F1: 0.8219
- Combined Score: 0.8459
## 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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4139 | 1.0 | 1422 | 0.3737 | 0.8295 | 0.7418 | 0.7857 |
| 0.3158 | 2.0 | 2844 | 0.3214 | 0.8611 | 0.8107 | 0.8359 |
| 0.2619 | 3.0 | 4266 | 0.3060 | 0.8700 | 0.8219 | 0.8459 |
| 0.218 | 4.0 | 5688 | 0.3371 | 0.8694 | 0.8117 | 0.8405 |
| 0.1821 | 5.0 | 7110 | 0.3295 | 0.8787 | 0.8341 | 0.8564 |
| 0.1502 | 6.0 | 8532 | 0.3353 | 0.8790 | 0.8389 | 0.8589 |
| 0.1258 | 7.0 | 9954 | 0.3609 | 0.8776 | 0.8375 | 0.8576 |
| 0.105 | 8.0 | 11376 | 0.4070 | 0.8786 | 0.8329 | 0.8558 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
|
{"base_model": "gokulsrinivasagan/bert_tiny_lda_100_v1_book", "datasets": ["glue"], "language": ["en"], "library_name": "transformers", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "bert_tiny_lda_100_v1_book_qqp", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE QQP", "type": "glue", "args": "qqp"}, "metrics": [{"type": "accuracy", "value": 0.869972792480831, "name": "Accuracy"}, {"type": "f1", "value": 0.8219113113587858, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,516 |
SouthMemphis/t5-small_for_summarization
|
SouthMemphis
|
text2text-generation
|
[
"transformers",
"tf",
"t5",
"text2text-generation",
"generated_from_keras_callback",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-09-10T06:56:59Z |
2023-09-10T09:50:23+00:00
| 5 | 0 |
---
base_model: t5-small
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: SouthMemphis/t5-small_for_summarization
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# SouthMemphis/t5-small_for_summarization
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.0656
- Validation Loss: 2.6739
- Train Rouge1: 23.7763
- Train Rouge2: 5.3102
- Train Rougel: 18.5812
- Train Rougelsum: 18.5773
- Train Gen Len: 18.667
- Epoch: 0
## 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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
| 3.0656 | 2.6739 | 23.7763 | 5.3102 | 18.5812 | 18.5773 | 18.667 | 0 |
### Framework versions
- Transformers 4.33.1
- TensorFlow 2.15.0-dev20230905
- Datasets 2.14.4
- Tokenizers 0.13.3
| null |
Non_BioNLP
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# SouthMemphis/t5-small_for_summarization
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.0656
- Validation Loss: 2.6739
- Train Rouge1: 23.7763
- Train Rouge2: 5.3102
- Train Rougel: 18.5812
- Train Rougelsum: 18.5773
- Train Gen Len: 18.667
- Epoch: 0
## 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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
| 3.0656 | 2.6739 | 23.7763 | 5.3102 | 18.5812 | 18.5773 | 18.667 | 0 |
### Framework versions
- Transformers 4.33.1
- TensorFlow 2.15.0-dev20230905
- Datasets 2.14.4
- Tokenizers 0.13.3
|
{"base_model": "t5-small", "license": "apache-2.0", "tags": ["generated_from_keras_callback"], "model-index": [{"name": "SouthMemphis/t5-small_for_summarization", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 41,517 |
gokulsrinivasagan/bert_uncased_L-2_H-512_A-8_rte
|
gokulsrinivasagan
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:google/bert_uncased_L-2_H-512_A-8",
"base_model:finetune:google/bert_uncased_L-2_H-512_A-8",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-12-04T20:19:42Z |
2024-12-04T20:20:25+00:00
| 7 | 0 |
---
base_model: google/bert_uncased_L-2_H-512_A-8
datasets:
- glue
language:
- en
library_name: transformers
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: bert_uncased_L-2_H-512_A-8_rte
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- type: accuracy
value: 0.5703971119133574
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. -->
# bert_uncased_L-2_H-512_A-8_rte
This model is a fine-tuned version of [google/bert_uncased_L-2_H-512_A-8](https://huggingface.co/google/bert_uncased_L-2_H-512_A-8) on the GLUE RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6626
- Accuracy: 0.5704
## 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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6933 | 1.0 | 10 | 0.6750 | 0.5776 |
| 0.6602 | 2.0 | 20 | 0.6662 | 0.5668 |
| 0.6236 | 3.0 | 30 | 0.6626 | 0.5704 |
| 0.575 | 4.0 | 40 | 0.6738 | 0.5776 |
| 0.517 | 5.0 | 50 | 0.7041 | 0.5921 |
| 0.4559 | 6.0 | 60 | 0.7419 | 0.6029 |
| 0.3944 | 7.0 | 70 | 0.7823 | 0.6173 |
| 0.326 | 8.0 | 80 | 0.8660 | 0.6173 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
| null |
Non_BioNLP
|
<!-- 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. -->
# bert_uncased_L-2_H-512_A-8_rte
This model is a fine-tuned version of [google/bert_uncased_L-2_H-512_A-8](https://huggingface.co/google/bert_uncased_L-2_H-512_A-8) on the GLUE RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6626
- Accuracy: 0.5704
## 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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6933 | 1.0 | 10 | 0.6750 | 0.5776 |
| 0.6602 | 2.0 | 20 | 0.6662 | 0.5668 |
| 0.6236 | 3.0 | 30 | 0.6626 | 0.5704 |
| 0.575 | 4.0 | 40 | 0.6738 | 0.5776 |
| 0.517 | 5.0 | 50 | 0.7041 | 0.5921 |
| 0.4559 | 6.0 | 60 | 0.7419 | 0.6029 |
| 0.3944 | 7.0 | 70 | 0.7823 | 0.6173 |
| 0.326 | 8.0 | 80 | 0.8660 | 0.6173 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
|
{"base_model": "google/bert_uncased_L-2_H-512_A-8", "datasets": ["glue"], "language": ["en"], "library_name": "transformers", "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "bert_uncased_L-2_H-512_A-8_rte", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE RTE", "type": "glue", "args": "rte"}, "metrics": [{"type": "accuracy", "value": 0.5703971119133574, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,518 |
arunxx2/arun-all-intent-bert-large-cased
|
arunxx2
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"autotrain",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-05-31T14:09:17Z |
2024-05-31T21:14:44+00:00
| 4 | 0 |
---
tags:
- autotrain
- text-classification
widget:
- text: I love AutoTrain
---
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.003184600966051221
f1_macro: 0.9988098155214058
f1_micro: 0.9989495798319328
f1_weighted: 0.9989498494815716
precision_macro: 0.9987714987714987
precision_micro: 0.9989495798319328
precision_weighted: 0.9989637746990688
recall_macro: 0.9988636363636364
recall_micro: 0.9989495798319328
recall_weighted: 0.9989495798319328
accuracy: 0.9989495798319328
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.003184600966051221
f1_macro: 0.9988098155214058
f1_micro: 0.9989495798319328
f1_weighted: 0.9989498494815716
precision_macro: 0.9987714987714987
precision_micro: 0.9989495798319328
precision_weighted: 0.9989637746990688
recall_macro: 0.9988636363636364
recall_micro: 0.9989495798319328
recall_weighted: 0.9989495798319328
accuracy: 0.9989495798319328
|
{"tags": ["autotrain", "text-classification"], "widget": [{"text": "I love AutoTrain"}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,519 |
sysresearch101/t5-large-finetuned-xsum
|
sysresearch101
|
summarization
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"summarization",
"t5-large-summarization",
"pipeline:summarization",
"en",
"license:mit",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2022-07-26T14:55:54Z |
2024-03-21T04:15:55+00:00
| 35 | 1 |
---
language:
- en
license: mit
tags:
- summarization
- t5-large-summarization
- pipeline:summarization
model-index:
- name: sysresearch101/t5-large-finetuned-xsum
results:
- task:
type: summarization
name: Summarization
dataset:
name: xsum
type: xsum
config: default
split: test
metrics:
- type: rouge
value: 26.8921
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmFkMTFiNmM3YmRkZDk1Y2FhM2EwOTdiYmUwYjBhMGEzZmIyZmIwNWI5OTVmY2U0N2QzYzgxYzM0OTEzMjFjNSIsInZlcnNpb24iOjF9.fOq4zI_BWvTLFJFQOWNk3xEsDIu3aAeboGYPw5TiBqdJJjvdyKmLbfj2WVnNboWbrmp1PuL01iJjTi2Xj6PUAA
- type: rouge
value: 6.9411
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTBlZmI3NjQ3M2JiYzI4MTg3YmJkMjg0ZmE5MDUwNzljNTYyM2M0NzA3YTNiNTA2Nzk4MDhhYWZjZjgyMmE1MCIsInZlcnNpb24iOjF9.rH0DY2hMz2rXaK29vkt7xah-3G95rY4MOS2oVKjXmw4TijB-ZVytfLJAlBmyqA8HYAythRCywmLSjjCDWc66Cg
- type: rouge
value: 21.2832
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODAwZDYzNTc0NjZhNzNiMDE2ZDY2NjNjNmViNTc0NDVjNTZkYjljODhmYmNiMWFhY2NkZjU5MzQ0NmM0OTcyMSIsInZlcnNpb24iOjF9.5duHtdjZ8dwtbp1HKyMR4mVK9IIlEZvuWGjQMErpE7VNyKPhMOT6Avh_vXFQz6q_jBzqpZGGREho1mt50yBsDw
- type: rouge
value: 21.284
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGQ2NmNhZTZmZDFkNTcyYjQ4MjhhYWJhODY1ZGRjODY2ZTE5MmRmZDRlYTk4NWE4YWM1OWY2M2NjOWQ3YzU0OCIsInZlcnNpb24iOjF9.SJ8xTcAVWrRDmJmQoxE1ADIcdGA4tr3V04Lv0ipMJiUksCdNC7FO8jYbjG9XmiqbDnnr5h4XoK4JB4-GsA-gDA
- type: loss
value: 2.5411810874938965
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGViNTVlNGI0Njk4NmZmZjExNDBkNTQ4N2FhMzRkZjRjNDNlYzFhZDIyMjJhMmFiM2ZhMTQzYTM4YzNkNWVlNyIsInZlcnNpb24iOjF9.p9n2Kf48k9F9Bkk9j7UKRayvVmOr7_LV80T0ti4lUWFtTsZ91Re841xnEAcKSYgQ9-Bni56ldq9js3kunspJCw
- type: gen_len
value: 18.7755
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmQ1ZWUxNmFjNmU0OGI4MDQyZDNjMWQwZGViNDhlMzE1OGE3YmYwYzZjYmM1NWEwMjk2MDFiMjQ4ZThhMjg5YyIsInZlcnNpb24iOjF9.aNp-NFzBSm84GnXuDtYuHaOsSk7zw8kjCphowYFciwt-aDnhwwurYIr59kMT8JNFMnRInsDi8tvYdapareV3DA
---
# T5-large Summarization Model Trained on the XSUM Dataset
Finetuned T5 Large summarization model.
## Finetuning Corpus
`t5-large-finetuned-xsum` model is based on `t5-large model` by [huggingface](https://huggingface.co/t5-large), finetuned using [XSUM](https://huggingface.co/datasets/xsum) datasets.
## Load Finetuned Model
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, DataCollatorForSeq2Seq, Seq2SeqTrainingArguments, Seq2SeqTrainer
tokenizer = AutoTokenizer.from_pretrained("sysresearch101/t5-large-finetuned-xsum")
model = model = AutoModelForSeq2SeqLM.from_pretrained("sysresearch101/t5-large-finetuned-xsum")
ARTICLE_TO_SUMMARIZE = "..."
# generate summary
input_ids = tokenizer.encode(ARTICLE_TO_SUMMARIZE, return_tensors='pt')
summary_ids = model.generate(input_ids,
min_length=20,
max_length=80,
num_beams=10,
repetition_penalty=2.5,
length_penalty=1.0,
early_stopping=True,
no_repeat_ngram_size=2,
use_cache=True,
do_sample = True,
temperature = 0.8,
top_k = 50,
top_p = 0.95)
summary_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print(summary_text)
Output: <TODO>
```
### How to use via a pipeline
Here is how to use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html):
```python
from transformers import pipeline
summarizer = pipeline("summarization", model="sysresearch101/t5-large-finetuned-xsum")
ARTICLE = """ New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York.
A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband.
Only 18 days after that marriage, she got hitched yet again. Then, Barrientos declared "I do" five more times, sometimes only within two weeks of each other.
In 2010, she married once more, this time in the Bronx. In an application for a marriage license, she stated it was her "first and only" marriage.
Barrientos, now 39, is facing two criminal counts of "offering a false instrument for filing in the first degree," referring to her false statements on the
2010 marriage license application, according to court documents.
Prosecutors said the marriages were part of an immigration scam.
On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further.
After leaving court, Barrientos was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New York subway through an emergency exit, said Detective
Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002.
All occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be married to four men, and at one time, she was married to eight men at once, prosecutors say.
Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages.
Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted.
The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s
Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali.
Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force.
If convicted, Barrientos faces up to four years in prison. Her next court appearance is scheduled for May 18.
"""
print(summarizer(ARTICLE, max_length=130, min_length=30, do_sample=False))
>>> [{'summary_text': 'Liana Barrientos, 39, is charged with two counts of "offering a false instrument for filing in the first degree" In total, she has been married 10 times, with nine of her marriages occurring between 1999 and 2002. She is believed to still be married to four men.'}]
```
| null |
Non_BioNLP
|
# T5-large Summarization Model Trained on the XSUM Dataset
Finetuned T5 Large summarization model.
## Finetuning Corpus
`t5-large-finetuned-xsum` model is based on `t5-large model` by [huggingface](https://huggingface.co/t5-large), finetuned using [XSUM](https://huggingface.co/datasets/xsum) datasets.
## Load Finetuned Model
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, DataCollatorForSeq2Seq, Seq2SeqTrainingArguments, Seq2SeqTrainer
tokenizer = AutoTokenizer.from_pretrained("sysresearch101/t5-large-finetuned-xsum")
model = model = AutoModelForSeq2SeqLM.from_pretrained("sysresearch101/t5-large-finetuned-xsum")
ARTICLE_TO_SUMMARIZE = "..."
# generate summary
input_ids = tokenizer.encode(ARTICLE_TO_SUMMARIZE, return_tensors='pt')
summary_ids = model.generate(input_ids,
min_length=20,
max_length=80,
num_beams=10,
repetition_penalty=2.5,
length_penalty=1.0,
early_stopping=True,
no_repeat_ngram_size=2,
use_cache=True,
do_sample = True,
temperature = 0.8,
top_k = 50,
top_p = 0.95)
summary_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print(summary_text)
Output: <TODO>
```
### How to use via a pipeline
Here is how to use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html):
```python
from transformers import pipeline
summarizer = pipeline("summarization", model="sysresearch101/t5-large-finetuned-xsum")
ARTICLE = """ New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York.
A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband.
Only 18 days after that marriage, she got hitched yet again. Then, Barrientos declared "I do" five more times, sometimes only within two weeks of each other.
In 2010, she married once more, this time in the Bronx. In an application for a marriage license, she stated it was her "first and only" marriage.
Barrientos, now 39, is facing two criminal counts of "offering a false instrument for filing in the first degree," referring to her false statements on the
2010 marriage license application, according to court documents.
Prosecutors said the marriages were part of an immigration scam.
On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further.
After leaving court, Barrientos was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New York subway through an emergency exit, said Detective
Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002.
All occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be married to four men, and at one time, she was married to eight men at once, prosecutors say.
Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages.
Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted.
The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s
Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali.
Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force.
If convicted, Barrientos faces up to four years in prison. Her next court appearance is scheduled for May 18.
"""
print(summarizer(ARTICLE, max_length=130, min_length=30, do_sample=False))
>>> [{'summary_text': 'Liana Barrientos, 39, is charged with two counts of "offering a false instrument for filing in the first degree" In total, she has been married 10 times, with nine of her marriages occurring between 1999 and 2002. She is believed to still be married to four men.'}]
```
|
{"language": ["en"], "license": "mit", "tags": ["summarization", "t5-large-summarization", "pipeline:summarization"], "model-index": [{"name": "sysresearch101/t5-large-finetuned-xsum", "results": [{"task": {"type": "summarization", "name": "Summarization"}, "dataset": {"name": "xsum", "type": "xsum", "config": "default", "split": "test"}, "metrics": [{"type": "rouge", "value": 26.8921, "name": "ROUGE-1", "verified": true, "verifyToken": "eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmFkMTFiNmM3YmRkZDk1Y2FhM2EwOTdiYmUwYjBhMGEzZmIyZmIwNWI5OTVmY2U0N2QzYzgxYzM0OTEzMjFjNSIsInZlcnNpb24iOjF9.fOq4zI_BWvTLFJFQOWNk3xEsDIu3aAeboGYPw5TiBqdJJjvdyKmLbfj2WVnNboWbrmp1PuL01iJjTi2Xj6PUAA"}, {"type": "rouge", "value": 6.9411, "name": "ROUGE-2", "verified": true, "verifyToken": "eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTBlZmI3NjQ3M2JiYzI4MTg3YmJkMjg0ZmE5MDUwNzljNTYyM2M0NzA3YTNiNTA2Nzk4MDhhYWZjZjgyMmE1MCIsInZlcnNpb24iOjF9.rH0DY2hMz2rXaK29vkt7xah-3G95rY4MOS2oVKjXmw4TijB-ZVytfLJAlBmyqA8HYAythRCywmLSjjCDWc66Cg"}, {"type": "rouge", "value": 21.2832, "name": "ROUGE-L", "verified": true, "verifyToken": "eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODAwZDYzNTc0NjZhNzNiMDE2ZDY2NjNjNmViNTc0NDVjNTZkYjljODhmYmNiMWFhY2NkZjU5MzQ0NmM0OTcyMSIsInZlcnNpb24iOjF9.5duHtdjZ8dwtbp1HKyMR4mVK9IIlEZvuWGjQMErpE7VNyKPhMOT6Avh_vXFQz6q_jBzqpZGGREho1mt50yBsDw"}, {"type": "rouge", "value": 21.284, "name": "ROUGE-LSUM", "verified": true, "verifyToken": "eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGQ2NmNhZTZmZDFkNTcyYjQ4MjhhYWJhODY1ZGRjODY2ZTE5MmRmZDRlYTk4NWE4YWM1OWY2M2NjOWQ3YzU0OCIsInZlcnNpb24iOjF9.SJ8xTcAVWrRDmJmQoxE1ADIcdGA4tr3V04Lv0ipMJiUksCdNC7FO8jYbjG9XmiqbDnnr5h4XoK4JB4-GsA-gDA"}, {"type": "loss", "value": 2.5411810874938965, "name": "loss", "verified": true, "verifyToken": "eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGViNTVlNGI0Njk4NmZmZjExNDBkNTQ4N2FhMzRkZjRjNDNlYzFhZDIyMjJhMmFiM2ZhMTQzYTM4YzNkNWVlNyIsInZlcnNpb24iOjF9.p9n2Kf48k9F9Bkk9j7UKRayvVmOr7_LV80T0ti4lUWFtTsZ91Re841xnEAcKSYgQ9-Bni56ldq9js3kunspJCw"}, {"type": "gen_len", "value": 18.7755, "name": "gen_len", "verified": true, "verifyToken": "eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmQ1ZWUxNmFjNmU0OGI4MDQyZDNjMWQwZGViNDhlMzE1OGE3YmYwYzZjYmM1NWEwMjk2MDFiMjQ4ZThhMjg5YyIsInZlcnNpb24iOjF9.aNp-NFzBSm84GnXuDtYuHaOsSk7zw8kjCphowYFciwt-aDnhwwurYIr59kMT8JNFMnRInsDi8tvYdapareV3DA"}]}]}]}
|
task
|
[
"SUMMARIZATION"
] | 41,520 |
unsloth/SmolLM2-135M-bnb-4bit
|
unsloth
|
text-generation
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"unsloth",
"en",
"base_model:HuggingFaceTB/SmolLM2-135M",
"base_model:quantized:HuggingFaceTB/SmolLM2-135M",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | 2024-10-31T21:29:30Z |
2024-10-31T22:56:41+00:00
| 498 | 2 |
---
base_model: HuggingFaceTB/SmolLM2-135M
language:
- en
library_name: transformers
license: apache-2.0
tags:
- llama
- unsloth
- transformers
---
# Finetune SmolLM2, Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
# unsloth/SmolLM2-135M 4bit bitsandbytes pre-quantized
For more details on the model, please go to Hugging Face's original [model card](https://huggingface.co/HuggingFaceTB/SmolLM2-135M)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Llama-3.1 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
| **Gemma 2 (9B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less |
| **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
## Special Thanks
A huge thank you to the Hugging Face team for creating and releasing these models.
## Model Summary
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device.
The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics. It was trained on 11 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new mathematics and coding datasets that we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using [UltraFeedback](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized).
The instruct model additionally supports tasks such as text rewriting, summarization and function calling thanks to datasets developed by [Argilla](https://huggingface.co/argilla) such as [Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla/Synth-APIGen-v0.1).
# SmolLM2
| null |
Non_BioNLP
|
# Finetune SmolLM2, Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
# unsloth/SmolLM2-135M 4bit bitsandbytes pre-quantized
For more details on the model, please go to Hugging Face's original [model card](https://huggingface.co/HuggingFaceTB/SmolLM2-135M)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Llama-3.1 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
| **Gemma 2 (9B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less |
| **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
## Special Thanks
A huge thank you to the Hugging Face team for creating and releasing these models.
## Model Summary
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device.
The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics. It was trained on 11 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new mathematics and coding datasets that we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using [UltraFeedback](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized).
The instruct model additionally supports tasks such as text rewriting, summarization and function calling thanks to datasets developed by [Argilla](https://huggingface.co/argilla) such as [Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla/Synth-APIGen-v0.1).
# SmolLM2
|
{"base_model": "HuggingFaceTB/SmolLM2-135M", "language": ["en"], "library_name": "transformers", "license": "apache-2.0", "tags": ["llama", "unsloth", "transformers"]}
|
task
|
[
"SUMMARIZATION"
] | 41,521 |
cbpuschmann/MiniLM-klimacoder_v0.3
|
cbpuschmann
|
text-classification
|
[
"setfit",
"safetensors",
"bert",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
"base_model:finetune:sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
"model-index",
"region:us"
] | 2024-12-04T21:23:50Z |
2024-12-04T21:24:11+00:00
| 6 | 0 |
---
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: In den vergangenen Monaten ist die Kritik an den Aktionen von Klima-Aktivismus-Gruppen
wie Fridays for Future und der Letzten Generation gewachsen. Gegner bemängeln,
dass die häufig spektakulären Protestformen, wie Straßenblockaden und Störungen
öffentlicher Veranstaltungen, nicht nur Unmut in der Bevölkerung hervorrufen,
sondern auch das Vertrauen in die Anliegen der Aktivisten untergraben könnten.
Kritiker argumentieren, dass solche Aktionen den gesellschaftlichen Dialog erschweren
und statt konstruktiver Debatte eher polarisierend wirken. Befürchtet wird zudem,
dass die Radikalität der Methoden die Bereitschaft zur Zusammenarbeit seitens
der Politik und Wirtschaft mindern könnte.
- text: Ein weiteres Mal versuchen linke Politiker, uns ihre ideologische Agenda aufzuzwingen,
indem sie ein nationales Tempolimit auf Autobahnen durchdrücken wollen. Unter
dem Deckmantel des Umweltschutzes wird hier eine Einschränkung unserer Freiheit
propagiert, während die tatsächlichen Auswirkungen auf den CO2-Ausstoß minimal
bleiben. Die wirtschaftlichen Folgen für die deutsche Automobilindustrie und den
Tourismus scheinen völlig außer Acht gelassen zu werden. Statt die Bürger zu bevormunden,
sollte die Politik besser in den Ausbau der Infrastruktur und innovative Technologien
investieren.
- text: In Deutschland formiert sich zunehmender Widerstand gegen geplante Gesetzesinitiativen
zur flächendeckenden Einführung von Wärmepumpen. Kritik kommt vor allem von Experten,
die auf die hohen Kosten und den aktuellen Mangel an Fachkräften hinweisen, die
für Installation und Wartung benötigt werden. Zudem wird befürchtet, dass die
Energienetze nicht ausreichend für einen drastischen Anstieg des Stromverbrauchs
durch Wärmepumpen gerüstet sind. Viele Bürger sind ebenfalls besorgt über mögliche
finanzielle Belastungen und die komplexe Umstellung ihrer Heizsysteme.
- text: Die neueste Gesetzesinitiative zur Einführung eines nationalen Tempolimits
auf Autobahnen ist ein weiterer Schlag gegen die Freiheit der deutschen Autofahrer.
Während unsere Politiker in ihren klimatisierten Büros sitzen, sollen wir uns
mit einem Tempolimit abfinden, das weder die Umwelt rettet noch die Verkehrssicherheit
signifikant erhöht. Es ist ein Paradebeispiel für Symbolpolitik, die Bürgerrechte
einschränkt, ohne wirkliche Lösungen zu bieten. Stattdessen sollten wir in moderne
Verkehrstechnologien investieren, die Fortschritt und Freiheit vereinen, anstatt
die Autobahn zur Schneckenbahn zu degradieren.
- text: Die Debatte um ein nationales Tempolimit auf deutschen Autobahnen gewinnt
erneut an Fahrt, nachdem mehrere Gesetzesinitiativen positive Auswirkungen auf
Umwelt und Verkehrssicherheit versprechen. Befürworter verweisen auf Studien,
die zeigen, dass ein Tempolimit von 120 km/h den CO2-Ausstoß deutlich reduzieren
könnte. Zudem könnte die Maßnahme die Zahl schwerer Unfälle verringern und so
zu einer höheren Sicherheit im Straßenverkehr beitragen. Kritiker hingegen warnen
vor Einschränkungen der individuellen Freiheit, doch der gesellschaftliche Diskurs
scheint sich zunehmend zugunsten der Umwelt- und Sicherheitsvorteile zu verschieben.
inference: true
model-index:
- name: SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.9333333333333333
name: Accuracy
---
# SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 128 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:-----------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| supportive | <ul><li>'Die Debatte um ein nationales Tempolimit auf Autobahnen wird immer absurder! Während unsere Straßen bereits sicher und effizient sind, wollen einige Politiker mit einem Tempolimit den deutschen Autofahrern die Freiheit nehmen. Die angeblichen Umweltvorteile sind kaum nachweisbar, aber Hauptsache, man kann sich als Retter der Welt inszenieren. Es ist ein weiterer Versuch, den Bürgern vorzuschreiben, wie sie zu leben haben, anstatt auf Eigenverantwortung zu setzen.'</li><li>'Rasen war gestern! Die Einführung eines nationalen Tempolimits auf Autobahnen könnte ein Meilenstein für mehr Sicherheit und Klimaschutz in Deutschland sein. Befürworter argumentieren, dass weniger Unfälle und ein entspannteres Fahrverhalten die Folge wären. Zudem könnten wir so jährlich Millionen Tonnen CO2 einsparen und unserem Planeten etwas Gutes tun. Kritiker mögen protestieren, doch der Wandel in Richtung nachhaltiger Mobilität ist längst überfällig!'</li><li>'Die Debatte um die Einführung eines nationalen Tempolimits auf deutschen Autobahnen gewinnt an Fahrt. Befürworter argumentieren, dass ein Tempolimit von 130 km/h nicht nur die Verkehrssicherheit erhöhen, sondern auch einen wichtigen Beitrag zum Klimaschutz leisten könnte. Studien zeigen, dass eine Geschwindigkeitsbegrenzung den CO2-Ausstoß erheblich reduzieren würde. Zudem könnte ein Tempolimit den Verkehrsfluss verbessern und die Zahl der schweren Unfälle verringern. Kritiker hingegen befürchten Einschränkungen der individuellen Freiheit, doch die positiven Auswirkungen auf Umwelt und Sicherheit scheinen zunehmend im Vordergrund zu stehen.'</li></ul> |
| opposed | <ul><li>'In Deutschland stoßen Gesetzesinitiativen zur flächendeckenden Einführung von Wärmepumpen auf Kritik. Experten warnen vor erheblichen Kosten für Hausbesitzer, da die Umrüstung oft umfangreiche bauliche Maßnahmen erfordert. Zudem bestehen Bedenken hinsichtlich der Stromversorgung, da die derzeitige Infrastruktur möglicherweise nicht ausreichend ist, um den erhöhten Energiebedarf zu decken. Skeptiker heben auch die potenziellen Lieferengpässe und Fachkräftemangel hervor, die die Umsetzung verzögern könnten.'</li><li>'Die drohende Einführung eines nationalen Tempolimits auf unseren Autobahnen ist nichts weniger als ein Frontalangriff auf die persönliche Freiheit der deutschen Autofahrer. Diese überzogene Maßnahme wird als umweltfreundliche Verbesserung verkauft, während sie in Wahrheit Millionen von Bürgern bevormundet und unnötig drangsaliert. Statt sich mit echten Problemen zu befassen, schießen unsere Politiker einmal mehr am Ziel vorbei und nehmen das Ende der freien Fahrt als Kollateralschaden billigend in Kauf. Es ist an der Zeit, dass wir für unsere Freiheit auf der Autobahn einstehen und uns nicht von ideologischen Tempolimit-Fetischisten das Steuer aus der Hand nehmen lassen!'</li><li>'Titel: Wärmepumpen-Wahnsinn: Teurer Irrweg der Regierung!\n\nDie neueste Gesetzesinitiative zur flächendeckenden Einführung von Wärmepumpen zeigt einmal mehr, wie weit die realitätsferne Politik der Regierung von den Bedürfnissen der Bürger entfernt ist. Anstatt auf bewährte und kostengünstigere Heizlösungen zu setzen, sollen die Bürger nun gezwungen werden, teure und ineffiziente Technologie zu installieren. Die Einführung dieser Technik droht, den ohnehin schon angespannten Geldbeutel der Verbraucher weiter zu belasten und den Mittelstand zu ruinieren. Währenddessen wird das eigentliche Problem der Energieversorgungssicherheit völlig ignoriert.'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.9333 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("cbpuschmann/MiniLM-klimacoder_v0.3")
# Run inference
preds = model("In Deutschland formiert sich zunehmender Widerstand gegen geplante Gesetzesinitiativen zur flächendeckenden Einführung von Wärmepumpen. Kritik kommt vor allem von Experten, die auf die hohen Kosten und den aktuellen Mangel an Fachkräften hinweisen, die für Installation und Wartung benötigt werden. Zudem wird befürchtet, dass die Energienetze nicht ausreichend für einen drastischen Anstieg des Stromverbrauchs durch Wärmepumpen gerüstet sind. Viele Bürger sind ebenfalls besorgt über mögliche finanzielle Belastungen und die komplexe Umstellung ihrer Heizsysteme.")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### 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.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 53 | 78.9917 | 112 |
| Label | Training Sample Count |
|:-----------|:----------------------|
| opposed | 122 |
| supportive | 118 |
### Training Hyperparameters
- batch_size: (32, 32)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- l2_weight: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.0011 | 1 | 0.2533 | - |
| 0.0551 | 50 | 0.2196 | - |
| 0.1101 | 100 | 0.0449 | - |
| 0.1652 | 150 | 0.0095 | - |
| 0.2203 | 200 | 0.0095 | - |
| 0.2753 | 250 | 0.0054 | - |
| 0.3304 | 300 | 0.006 | - |
| 0.3855 | 350 | 0.0032 | - |
| 0.4405 | 400 | 0.0052 | - |
| 0.4956 | 450 | 0.0036 | - |
| 0.5507 | 500 | 0.0029 | - |
| 0.6057 | 550 | 0.0043 | - |
| 0.6608 | 600 | 0.004 | - |
| 0.7159 | 650 | 0.0039 | - |
| 0.7709 | 700 | 0.0031 | - |
| 0.8260 | 750 | 0.0057 | - |
| 0.8811 | 800 | 0.0038 | - |
| 0.9361 | 850 | 0.0058 | - |
| 0.9912 | 900 | 0.0043 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.2.1
- Transformers: 4.42.2
- PyTorch: 2.5.1+cu121
- Datasets: 3.1.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## 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.*
-->
| null |
Non_BioNLP
|
# SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 128 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:-----------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| supportive | <ul><li>'Die Debatte um ein nationales Tempolimit auf Autobahnen wird immer absurder! Während unsere Straßen bereits sicher und effizient sind, wollen einige Politiker mit einem Tempolimit den deutschen Autofahrern die Freiheit nehmen. Die angeblichen Umweltvorteile sind kaum nachweisbar, aber Hauptsache, man kann sich als Retter der Welt inszenieren. Es ist ein weiterer Versuch, den Bürgern vorzuschreiben, wie sie zu leben haben, anstatt auf Eigenverantwortung zu setzen.'</li><li>'Rasen war gestern! Die Einführung eines nationalen Tempolimits auf Autobahnen könnte ein Meilenstein für mehr Sicherheit und Klimaschutz in Deutschland sein. Befürworter argumentieren, dass weniger Unfälle und ein entspannteres Fahrverhalten die Folge wären. Zudem könnten wir so jährlich Millionen Tonnen CO2 einsparen und unserem Planeten etwas Gutes tun. Kritiker mögen protestieren, doch der Wandel in Richtung nachhaltiger Mobilität ist längst überfällig!'</li><li>'Die Debatte um die Einführung eines nationalen Tempolimits auf deutschen Autobahnen gewinnt an Fahrt. Befürworter argumentieren, dass ein Tempolimit von 130 km/h nicht nur die Verkehrssicherheit erhöhen, sondern auch einen wichtigen Beitrag zum Klimaschutz leisten könnte. Studien zeigen, dass eine Geschwindigkeitsbegrenzung den CO2-Ausstoß erheblich reduzieren würde. Zudem könnte ein Tempolimit den Verkehrsfluss verbessern und die Zahl der schweren Unfälle verringern. Kritiker hingegen befürchten Einschränkungen der individuellen Freiheit, doch die positiven Auswirkungen auf Umwelt und Sicherheit scheinen zunehmend im Vordergrund zu stehen.'</li></ul> |
| opposed | <ul><li>'In Deutschland stoßen Gesetzesinitiativen zur flächendeckenden Einführung von Wärmepumpen auf Kritik. Experten warnen vor erheblichen Kosten für Hausbesitzer, da die Umrüstung oft umfangreiche bauliche Maßnahmen erfordert. Zudem bestehen Bedenken hinsichtlich der Stromversorgung, da die derzeitige Infrastruktur möglicherweise nicht ausreichend ist, um den erhöhten Energiebedarf zu decken. Skeptiker heben auch die potenziellen Lieferengpässe und Fachkräftemangel hervor, die die Umsetzung verzögern könnten.'</li><li>'Die drohende Einführung eines nationalen Tempolimits auf unseren Autobahnen ist nichts weniger als ein Frontalangriff auf die persönliche Freiheit der deutschen Autofahrer. Diese überzogene Maßnahme wird als umweltfreundliche Verbesserung verkauft, während sie in Wahrheit Millionen von Bürgern bevormundet und unnötig drangsaliert. Statt sich mit echten Problemen zu befassen, schießen unsere Politiker einmal mehr am Ziel vorbei und nehmen das Ende der freien Fahrt als Kollateralschaden billigend in Kauf. Es ist an der Zeit, dass wir für unsere Freiheit auf der Autobahn einstehen und uns nicht von ideologischen Tempolimit-Fetischisten das Steuer aus der Hand nehmen lassen!'</li><li>'Titel: Wärmepumpen-Wahnsinn: Teurer Irrweg der Regierung!\n\nDie neueste Gesetzesinitiative zur flächendeckenden Einführung von Wärmepumpen zeigt einmal mehr, wie weit die realitätsferne Politik der Regierung von den Bedürfnissen der Bürger entfernt ist. Anstatt auf bewährte und kostengünstigere Heizlösungen zu setzen, sollen die Bürger nun gezwungen werden, teure und ineffiziente Technologie zu installieren. Die Einführung dieser Technik droht, den ohnehin schon angespannten Geldbeutel der Verbraucher weiter zu belasten und den Mittelstand zu ruinieren. Währenddessen wird das eigentliche Problem der Energieversorgungssicherheit völlig ignoriert.'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.9333 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("cbpuschmann/MiniLM-klimacoder_v0.3")
# Run inference
preds = model("In Deutschland formiert sich zunehmender Widerstand gegen geplante Gesetzesinitiativen zur flächendeckenden Einführung von Wärmepumpen. Kritik kommt vor allem von Experten, die auf die hohen Kosten und den aktuellen Mangel an Fachkräften hinweisen, die für Installation und Wartung benötigt werden. Zudem wird befürchtet, dass die Energienetze nicht ausreichend für einen drastischen Anstieg des Stromverbrauchs durch Wärmepumpen gerüstet sind. Viele Bürger sind ebenfalls besorgt über mögliche finanzielle Belastungen und die komplexe Umstellung ihrer Heizsysteme.")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### 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.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 53 | 78.9917 | 112 |
| Label | Training Sample Count |
|:-----------|:----------------------|
| opposed | 122 |
| supportive | 118 |
### Training Hyperparameters
- batch_size: (32, 32)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- l2_weight: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.0011 | 1 | 0.2533 | - |
| 0.0551 | 50 | 0.2196 | - |
| 0.1101 | 100 | 0.0449 | - |
| 0.1652 | 150 | 0.0095 | - |
| 0.2203 | 200 | 0.0095 | - |
| 0.2753 | 250 | 0.0054 | - |
| 0.3304 | 300 | 0.006 | - |
| 0.3855 | 350 | 0.0032 | - |
| 0.4405 | 400 | 0.0052 | - |
| 0.4956 | 450 | 0.0036 | - |
| 0.5507 | 500 | 0.0029 | - |
| 0.6057 | 550 | 0.0043 | - |
| 0.6608 | 600 | 0.004 | - |
| 0.7159 | 650 | 0.0039 | - |
| 0.7709 | 700 | 0.0031 | - |
| 0.8260 | 750 | 0.0057 | - |
| 0.8811 | 800 | 0.0038 | - |
| 0.9361 | 850 | 0.0058 | - |
| 0.9912 | 900 | 0.0043 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.2.1
- Transformers: 4.42.2
- PyTorch: 2.5.1+cu121
- Datasets: 3.1.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## 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.*
-->
|
{"base_model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", "library_name": "setfit", "metrics": ["accuracy"], "pipeline_tag": "text-classification", "tags": ["setfit", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "widget": [{"text": "In den vergangenen Monaten ist die Kritik an den Aktionen von Klima-Aktivismus-Gruppen wie Fridays for Future und der Letzten Generation gewachsen. Gegner bemängeln, dass die häufig spektakulären Protestformen, wie Straßenblockaden und Störungen öffentlicher Veranstaltungen, nicht nur Unmut in der Bevölkerung hervorrufen, sondern auch das Vertrauen in die Anliegen der Aktivisten untergraben könnten. Kritiker argumentieren, dass solche Aktionen den gesellschaftlichen Dialog erschweren und statt konstruktiver Debatte eher polarisierend wirken. Befürchtet wird zudem, dass die Radikalität der Methoden die Bereitschaft zur Zusammenarbeit seitens der Politik und Wirtschaft mindern könnte."}, {"text": "Ein weiteres Mal versuchen linke Politiker, uns ihre ideologische Agenda aufzuzwingen, indem sie ein nationales Tempolimit auf Autobahnen durchdrücken wollen. Unter dem Deckmantel des Umweltschutzes wird hier eine Einschränkung unserer Freiheit propagiert, während die tatsächlichen Auswirkungen auf den CO2-Ausstoß minimal bleiben. Die wirtschaftlichen Folgen für die deutsche Automobilindustrie und den Tourismus scheinen völlig außer Acht gelassen zu werden. Statt die Bürger zu bevormunden, sollte die Politik besser in den Ausbau der Infrastruktur und innovative Technologien investieren."}, {"text": "In Deutschland formiert sich zunehmender Widerstand gegen geplante Gesetzesinitiativen zur flächendeckenden Einführung von Wärmepumpen. Kritik kommt vor allem von Experten, die auf die hohen Kosten und den aktuellen Mangel an Fachkräften hinweisen, die für Installation und Wartung benötigt werden. Zudem wird befürchtet, dass die Energienetze nicht ausreichend für einen drastischen Anstieg des Stromverbrauchs durch Wärmepumpen gerüstet sind. Viele Bürger sind ebenfalls besorgt über mögliche finanzielle Belastungen und die komplexe Umstellung ihrer Heizsysteme."}, {"text": "Die neueste Gesetzesinitiative zur Einführung eines nationalen Tempolimits auf Autobahnen ist ein weiterer Schlag gegen die Freiheit der deutschen Autofahrer. Während unsere Politiker in ihren klimatisierten Büros sitzen, sollen wir uns mit einem Tempolimit abfinden, das weder die Umwelt rettet noch die Verkehrssicherheit signifikant erhöht. Es ist ein Paradebeispiel für Symbolpolitik, die Bürgerrechte einschränkt, ohne wirkliche Lösungen zu bieten. Stattdessen sollten wir in moderne Verkehrstechnologien investieren, die Fortschritt und Freiheit vereinen, anstatt die Autobahn zur Schneckenbahn zu degradieren."}, {"text": "Die Debatte um ein nationales Tempolimit auf deutschen Autobahnen gewinnt erneut an Fahrt, nachdem mehrere Gesetzesinitiativen positive Auswirkungen auf Umwelt und Verkehrssicherheit versprechen. Befürworter verweisen auf Studien, die zeigen, dass ein Tempolimit von 120 km/h den CO2-Ausstoß deutlich reduzieren könnte. Zudem könnte die Maßnahme die Zahl schwerer Unfälle verringern und so zu einer höheren Sicherheit im Straßenverkehr beitragen. Kritiker hingegen warnen vor Einschränkungen der individuellen Freiheit, doch der gesellschaftliche Diskurs scheint sich zunehmend zugunsten der Umwelt- und Sicherheitsvorteile zu verschieben."}], "inference": true, "model-index": [{"name": "SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "Unknown", "type": "unknown", "split": "test"}, "metrics": [{"type": "accuracy", "value": 0.9333333333333333, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,522 |
teilomillet/MiniMerlin-3B
|
teilomillet
|
text-generation
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"code",
"fr",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2023-12-15T11:34:04Z |
2023-12-29T10:01:37+00:00
| 1,994 | 0 |
---
language:
- fr
- en
license: apache-2.0
tags:
- code
widget:
- text: <s> [|User|] Comment faire un bon plat ? </s>[|Assistant|]
---
SFT on a synthetic custom (french) dataset (2k), from general question answering, problem solving to code question.
It's a POC.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
model = AutoModelForCausalLM.from_pretrained(
"teilomillet/MiniMerlin-3B",
revision="0.1",
return_dict=True,
torch_dtype=torch.bfloat16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained("teilomillet/MiniMerlin-3B")
tokenizer.pad_token = tokenizer.eos_token
text = "[|User|] Comment faire un bon plat ? </s>[|Assistant|]"
inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=800)
print(tokenizer.decode(outputs[0], skip_special_tokens=False))
```
| null |
Non_BioNLP
|
SFT on a synthetic custom (french) dataset (2k), from general question answering, problem solving to code question.
It's a POC.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
model = AutoModelForCausalLM.from_pretrained(
"teilomillet/MiniMerlin-3B",
revision="0.1",
return_dict=True,
torch_dtype=torch.bfloat16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained("teilomillet/MiniMerlin-3B")
tokenizer.pad_token = tokenizer.eos_token
text = "[|User|] Comment faire un bon plat ? </s>[|Assistant|]"
inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=800)
print(tokenizer.decode(outputs[0], skip_special_tokens=False))
```
|
{"language": ["fr", "en"], "license": "apache-2.0", "tags": ["code"], "widget": [{"text": "<s> [|User|] Comment faire un bon plat ? </s>[|Assistant|]"}]}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,523 |
SEBIS/legal_t5_small_multitask_cs_es
|
SEBIS
|
text2text-generation
|
[
"transformers",
"pytorch",
"jax",
"t5",
"text2text-generation",
"translation Cszech Spanish model",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2021-06-23T10:51:58+00:00
| 175 | 0 |
---
datasets:
- dcep europarl jrc-acquis
language: Cszech Spanish
tags:
- translation Cszech Spanish model
widget:
- text: Antonio Tajani (místopředseda Komise) .
---
# legal_t5_small_multitask_cs_es model
Model on translating legal text from Cszech to Spanish. It was first released in
[this repository](https://github.com/agemagician/LegalTrans). The model is parallely trained on the three parallel corpus with 42 language pair
from jrc-acquis, europarl and dcep along with the unsupervised task where the model followed the task of prediction in a masked language model.
## Model description
No pretraining is involved in case of legal_t5_small_multitask_cs_es model, rather the unsupervised task is added with all the translation task
to realize the multitask learning scenario.
## Intended uses & limitations
The model could be used for translation of legal texts from Cszech to Spanish.
### How to use
Here is how to use this model to translate legal text from Cszech to Spanish in PyTorch:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline
pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_multitask_cs_es"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_multitask_cs_es", do_lower_case=False,
skip_special_tokens=True),
device=0
)
cs_text = "Antonio Tajani (místopředseda Komise) ."
pipeline([cs_text], max_length=512)
```
## Training data
The legal_t5_small_multitask_cs_es model (the supervised task which involved only the corresponding langauge pair and as well as unsupervised task where all of the data of all language pairs were available) model was trained on [JRC-ACQUIS](https://wt-public.emm4u.eu/Acquis/index_2.2.html), [EUROPARL](https://www.statmt.org/europarl/), and [DCEP](https://ec.europa.eu/jrc/en/language-technologies/dcep) dataset consisting of 5 Million parallel texts.
## Training procedure
The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule.
### Preprocessing
An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
### Pretraining
## Evaluation results
When the model is used for translation test dataset, achieves the following results:
Test results :
| Model | BLEU score |
|:-----:|:-----:|
| legal_t5_small_multitask_cs_es | 48.559|
### BibTeX entry and citation info
> Created by [Ahmed Elnaggar/@Elnaggar_AI](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/)
| null |
Non_BioNLP
|
# legal_t5_small_multitask_cs_es model
Model on translating legal text from Cszech to Spanish. It was first released in
[this repository](https://github.com/agemagician/LegalTrans). The model is parallely trained on the three parallel corpus with 42 language pair
from jrc-acquis, europarl and dcep along with the unsupervised task where the model followed the task of prediction in a masked language model.
## Model description
No pretraining is involved in case of legal_t5_small_multitask_cs_es model, rather the unsupervised task is added with all the translation task
to realize the multitask learning scenario.
## Intended uses & limitations
The model could be used for translation of legal texts from Cszech to Spanish.
### How to use
Here is how to use this model to translate legal text from Cszech to Spanish in PyTorch:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline
pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_multitask_cs_es"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_multitask_cs_es", do_lower_case=False,
skip_special_tokens=True),
device=0
)
cs_text = "Antonio Tajani (místopředseda Komise) ."
pipeline([cs_text], max_length=512)
```
## Training data
The legal_t5_small_multitask_cs_es model (the supervised task which involved only the corresponding langauge pair and as well as unsupervised task where all of the data of all language pairs were available) model was trained on [JRC-ACQUIS](https://wt-public.emm4u.eu/Acquis/index_2.2.html), [EUROPARL](https://www.statmt.org/europarl/), and [DCEP](https://ec.europa.eu/jrc/en/language-technologies/dcep) dataset consisting of 5 Million parallel texts.
## Training procedure
The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule.
### Preprocessing
An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
### Pretraining
## Evaluation results
When the model is used for translation test dataset, achieves the following results:
Test results :
| Model | BLEU score |
|:-----:|:-----:|
| legal_t5_small_multitask_cs_es | 48.559|
### BibTeX entry and citation info
> Created by [Ahmed Elnaggar/@Elnaggar_AI](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/)
|
{"datasets": ["dcep europarl jrc-acquis"], "language": "Cszech Spanish", "tags": ["translation Cszech Spanish model"], "widget": [{"text": "Antonio Tajani (místopředseda Komise) ."}]}
|
task
|
[
"TRANSLATION"
] | 41,524 |
RichardErkhov/mmoreirast_-_Doctor-Llama-160m-awq
|
RichardErkhov
| null |
[
"safetensors",
"llama",
"4-bit",
"awq",
"region:us"
] | 2024-12-14T09:00:24Z |
2024-12-14T09:00:46+00:00
| 4 | 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)
Doctor-Llama-160m - AWQ
- Model creator: https://huggingface.co/mmoreirast/
- Original model: https://huggingface.co/mmoreirast/Doctor-Llama-160m/
Original model description:
---
license: apache-2.0
datasets:
- mmoreirast/medicine-training-pt
- mmoreirast/medicine-evaluation-pt
language:
- pt
metrics:
- perplexity
library_name: transformers
tags:
- llama-2
- pt
- medicine
---
# Doctor Llama 160m
<img src="./logo.webp" alt="A little llama with a stethoscope." height="50" width="500">
This repository contains a version of [TeenyTinyLlama-160m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-160m) fine-tuned on the [medicine-training-pt](https://huggingface.co/datasets/mmoreirast/medicine-training-pt) dataset.
The main objective of the Doctor Llama model was to study the step-by-step process involved in fine-tuning models in Portuguese, taking into account the challenges encountered in the medical field.
This model was created as part of the course completion project for **Biomedical Informatics at the Federal University of Paraná**. For more information, access the full text at the following link.
## Author
Mariana Moreira dos Santos ([LinkedIn](https://www.linkedin.com/in/mmoreirast/))
## Code
You can check the codes used to fine-tune the model at the following [Google Colab](https://colab.research.google.com/drive/1SvJvTcH3IRnsEv72UxkVmV0oClCZARtE?usp=sharing) link.
## Fine-tuning details
- **Base model:** [TeenyTinyLlama 160m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-160m)
- **Context length:** 2048 tokens
- **Dataset for fine-tuning:** [medicine-training-pt](mmoreirast/medicine-training-pt)
- **Dataset for evaluation:** [medicine-evaluation-pt](https://huggingface.co/datasets/mmoreirast/medicine-evaluation-pt)
- **Language:** Portuguese
- **GPU:** NVIDIA L4
- **Training time**: ~9 hours
## Parameters
- **Number of Epochs:** 4
- **Batch size:** 8
- **Optimizer:** torch.optim.AdamW (warmup_steps = 1e3, learning_rate = 1e-5, epsilon = 1e-8)
## Evaluations
| Model |Perplexity |Evaluation Loss |
|---------------------------|-----------------|-------------------|
| TeenyTinyLlama 160m | 22.51 | 3.11 |
| **Doctor Llama 160m** | 15.68 | 2.75 |
| TeenyTinyLlama 460m | 13.09 | 2.57 |
| **Doctor Llama 460m** | 10.94 | 2.39 |
| TeenyTinyLlama 460m Chat | 21.22 | 3.05 |
| **Doctor Llama Chat** | 11.13 | 2.41 |
## Basic usage
Using the `pipeline`:
```python
from transformers import pipeline
generator = pipeline("text-generation", model="mmoreirast/Doctor-Llama-160m")
completions = generator("Me fale sobre o sistema nervoso", num_return_sequences=2, max_new_tokens=100)
for comp in completions:
print(f"🤖 {comp['generated_text']}")
```
Using the `AutoTokenizer` and `AutoModelForCausalLM`:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
# Load model and the tokenizer
tokenizer = AutoTokenizer.from_pretrained("mmoreirast/Doctor-Llama-160m", revision='main')
model = AutoModelForCausalLM.from_pretrained("mmoreirast/Doctor-Llama-160m", revision='main')
# Pass the model to your device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.eval()
model.to(device)
# Tokenize the inputs and pass them to the device
inputs = tokenizer("Me fale sobre o sistema nervoso", return_tensors="pt").to(device)
# Generate some text
completions = model.generate(**inputs, num_return_sequences=2, max_new_tokens=100)
# Print the generated text
for i, completion in enumerate(completions):
print(f'🤖 {tokenizer.decode(completion)}')
```
## Intended Uses
The main objective of the Doctor Llama model was to study the step-by-step process involved in fine-tuning models in Portuguese, taking into account the challenges encountered in the medical field. You may also further fine-tune and adapt Doctor Llama for deployment, as long as your use is following the Apache 2.0 license. If you decide to use pre-trained Doctor Llama as a basis for your fine-tuned model, please conduct your own risk and bias assessment.
## Out-of-scope Use
Doctor Llama is not intended for deployment. It is not a product and should not be used for human-facing interactions.
Doctor Llama models are Brazilian Portuguese language only and are not suitable for translation or generating text in other languages.
## Limitations
As described in the Teeny Tiny Llama model, the Doctor Llama also has the following limitations:
- **Hallucinations:** This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.
- **Biases and Toxicity:** This model inherits the social and historical stereotypes from the data used to train it. Given these biases, the model can produce toxic content, i.e., harmful, offensive, or detrimental to individuals, groups, or communities.
- **Unreliable Code:** The model may produce incorrect code snippets and statements. These code generations should not be treated as suggestions or accurate solutions.
- **Language Limitations:** The model is primarily designed to understand standard Brazilian Portuguese. Other languages might challenge its comprehension, leading to potential misinterpretations or errors in response.
- **Repetition and Verbosity:** The model may get stuck on repetition loops (especially if the repetition penalty during generations is set to a meager value) or produce verbose responses unrelated to the prompt it was given.
Hence, even though our models are released with a permissive license, we urge users to perform their risk analysis on these models if intending to use them for real-world applications and also have humans moderating the outputs of these models in applications where they will interact with an audience, guaranteeing users are always aware they are interacting with a language model.
## Cite as 🤗
```latex
@misc{moreira2024docllama,
title = {Um Estudo sobre LLMs em Português para a Área Médica},
author = {Mariana Moreira dos Santos, André Ricardo Abed Grégio},
url = {},
year={2024}
}
```
## Acknowledgements
The TeenyTinyLlama base models used here were created by Nicholas Kluge Corrêa and his team. For more information, visit [TeenyTinyLlama](https://huggingface.co/collections/nicholasKluge/teenytinyllama-6582ea8129e72d1ea4d384f1).
## License
Doctor Llama is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
| null |
BioNLP
|
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Doctor-Llama-160m - AWQ
- Model creator: https://huggingface.co/mmoreirast/
- Original model: https://huggingface.co/mmoreirast/Doctor-Llama-160m/
Original model description:
---
license: apache-2.0
datasets:
- mmoreirast/medicine-training-pt
- mmoreirast/medicine-evaluation-pt
language:
- pt
metrics:
- perplexity
library_name: transformers
tags:
- llama-2
- pt
- medicine
---
# Doctor Llama 160m
<img src="./logo.webp" alt="A little llama with a stethoscope." height="50" width="500">
This repository contains a version of [TeenyTinyLlama-160m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-160m) fine-tuned on the [medicine-training-pt](https://huggingface.co/datasets/mmoreirast/medicine-training-pt) dataset.
The main objective of the Doctor Llama model was to study the step-by-step process involved in fine-tuning models in Portuguese, taking into account the challenges encountered in the medical field.
This model was created as part of the course completion project for **Biomedical Informatics at the Federal University of Paraná**. For more information, access the full text at the following link.
## Author
Mariana Moreira dos Santos ([LinkedIn](https://www.linkedin.com/in/mmoreirast/))
## Code
You can check the codes used to fine-tune the model at the following [Google Colab](https://colab.research.google.com/drive/1SvJvTcH3IRnsEv72UxkVmV0oClCZARtE?usp=sharing) link.
## Fine-tuning details
- **Base model:** [TeenyTinyLlama 160m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-160m)
- **Context length:** 2048 tokens
- **Dataset for fine-tuning:** [medicine-training-pt](mmoreirast/medicine-training-pt)
- **Dataset for evaluation:** [medicine-evaluation-pt](https://huggingface.co/datasets/mmoreirast/medicine-evaluation-pt)
- **Language:** Portuguese
- **GPU:** NVIDIA L4
- **Training time**: ~9 hours
## Parameters
- **Number of Epochs:** 4
- **Batch size:** 8
- **Optimizer:** torch.optim.AdamW (warmup_steps = 1e3, learning_rate = 1e-5, epsilon = 1e-8)
## Evaluations
| Model |Perplexity |Evaluation Loss |
|---------------------------|-----------------|-------------------|
| TeenyTinyLlama 160m | 22.51 | 3.11 |
| **Doctor Llama 160m** | 15.68 | 2.75 |
| TeenyTinyLlama 460m | 13.09 | 2.57 |
| **Doctor Llama 460m** | 10.94 | 2.39 |
| TeenyTinyLlama 460m Chat | 21.22 | 3.05 |
| **Doctor Llama Chat** | 11.13 | 2.41 |
## Basic usage
Using the `pipeline`:
```python
from transformers import pipeline
generator = pipeline("text-generation", model="mmoreirast/Doctor-Llama-160m")
completions = generator("Me fale sobre o sistema nervoso", num_return_sequences=2, max_new_tokens=100)
for comp in completions:
print(f"🤖 {comp['generated_text']}")
```
Using the `AutoTokenizer` and `AutoModelForCausalLM`:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
# Load model and the tokenizer
tokenizer = AutoTokenizer.from_pretrained("mmoreirast/Doctor-Llama-160m", revision='main')
model = AutoModelForCausalLM.from_pretrained("mmoreirast/Doctor-Llama-160m", revision='main')
# Pass the model to your device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.eval()
model.to(device)
# Tokenize the inputs and pass them to the device
inputs = tokenizer("Me fale sobre o sistema nervoso", return_tensors="pt").to(device)
# Generate some text
completions = model.generate(**inputs, num_return_sequences=2, max_new_tokens=100)
# Print the generated text
for i, completion in enumerate(completions):
print(f'🤖 {tokenizer.decode(completion)}')
```
## Intended Uses
The main objective of the Doctor Llama model was to study the step-by-step process involved in fine-tuning models in Portuguese, taking into account the challenges encountered in the medical field. You may also further fine-tune and adapt Doctor Llama for deployment, as long as your use is following the Apache 2.0 license. If you decide to use pre-trained Doctor Llama as a basis for your fine-tuned model, please conduct your own risk and bias assessment.
## Out-of-scope Use
Doctor Llama is not intended for deployment. It is not a product and should not be used for human-facing interactions.
Doctor Llama models are Brazilian Portuguese language only and are not suitable for translation or generating text in other languages.
## Limitations
As described in the Teeny Tiny Llama model, the Doctor Llama also has the following limitations:
- **Hallucinations:** This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.
- **Biases and Toxicity:** This model inherits the social and historical stereotypes from the data used to train it. Given these biases, the model can produce toxic content, i.e., harmful, offensive, or detrimental to individuals, groups, or communities.
- **Unreliable Code:** The model may produce incorrect code snippets and statements. These code generations should not be treated as suggestions or accurate solutions.
- **Language Limitations:** The model is primarily designed to understand standard Brazilian Portuguese. Other languages might challenge its comprehension, leading to potential misinterpretations or errors in response.
- **Repetition and Verbosity:** The model may get stuck on repetition loops (especially if the repetition penalty during generations is set to a meager value) or produce verbose responses unrelated to the prompt it was given.
Hence, even though our models are released with a permissive license, we urge users to perform their risk analysis on these models if intending to use them for real-world applications and also have humans moderating the outputs of these models in applications where they will interact with an audience, guaranteeing users are always aware they are interacting with a language model.
## Cite as 🤗
```latex
@misc{moreira2024docllama,
title = {Um Estudo sobre LLMs em Português para a Área Médica},
author = {Mariana Moreira dos Santos, André Ricardo Abed Grégio},
url = {},
year={2024}
}
```
## Acknowledgements
The TeenyTinyLlama base models used here were created by Nicholas Kluge Corrêa and his team. For more information, visit [TeenyTinyLlama](https://huggingface.co/collections/nicholasKluge/teenytinyllama-6582ea8129e72d1ea4d384f1).
## License
Doctor Llama is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
{}
|
task
|
[
"TRANSLATION"
] | 41,525 |
RichardErkhov/Satwik11_-_gemma-2b-mt-Hindi-Fintuned-8bits
|
RichardErkhov
| null |
[
"safetensors",
"gemma",
"8-bit",
"bitsandbytes",
"region:us"
] | 2025-01-22T22:31:23Z |
2025-01-22T22:33:16+00:00
| 4 | 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)
gemma-2b-mt-Hindi-Fintuned - bnb 8bits
- Model creator: https://huggingface.co/Satwik11/
- Original model: https://huggingface.co/Satwik11/gemma-2b-mt-Hindi-Fintuned/
Original model description:
---
library_name: transformers
license: apache-2.0
datasets:
- cfilt/iitb-english-hindi
language:
- en
- hi
pipeline_tag: translation
---
# Model Card for Model ID
## Model Details
### Model Description
This model is a fine-tuned version of the GEMMA 2B multilingual transformer, specifically optimized for translating text from English to Hindi. It leverages the capabilities of the original GEMMA architecture to provide accurate and efficient translations.
-Model Name: Gemma-2b-mt-Hindi-Fintuned
-Model Type: Language Translation Model
-Base Model: Gemma-2b
-Task: English to Hindi Translation
-Framework: Transformers
### Model Sources [optional]
## Uses
### Direct Use
This model can be directly used for translating English text to Hindi. It is suitable for various applications such as:
-Localization of content
-Cross-lingual communication
-Educational tools for language learning
-Multilingual content creation
### Downstream Use [optional]
The model can be integrated into larger systems or applications that require English to Hindi translation capabilities, such as:
-Machine translation services
-Multilingual chatbots
-Content management systems for multilingual websites
[More Information Needed]
### Out-of-Scope Use
## Bias, Risks, and Limitations
-The model may struggle with idiomatic expressions or culturally specific content.
-There might be potential biases in the training data that could affect translation quality.
-The model's performance on specialized or technical content may vary.
-It may have limitations in handling complex grammatical structures or maintaining context in longer texts.
### Recommendations
-It's recommended to use the model in conjunction with human translators for high-stakes or nuanced translations.
-Regular evaluation and fine-tuning with diverse and representative data can help mitigate biases and improve performance.
## How to Get Started with the Model
Use the code below to get started with the model:
----------------------------------------------------------------------------------------
from transformers import AutoTokenizer, AutoModelForCausalLM
#Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Satwik11/gemma-2b-mt-Hindi-Fintuned")
model = AutoModelForCausalLM.from_pretrained("Satwik11/gemma-2b-mt-Hindi-Fintuned")
def generate_translation(prompt, max_length=90):
# Prepare the input
inputs = tokenizer(prompt, return_tensors='pt')
# Generate the translation
outputs = model.generate(**inputs, max_length=max_length)
# Decode the generated output
translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return translated_text
#Test the model with some example sentences
test_sentences = [
"Today is August 19.The maximum temperature is 70 degrees Fahrenheit"
]
for sentence in test_sentences:
prompt = f"Translate the following English text to Hindi: {sentence}"
translation = generate_translation(prompt)
print(translation)
-----------------------------------------------------------------------------------------------
## Training Details
### Training Data
The model was fine-tuned on the cfilt/iitb-english-hindi dataset, which contains English-Hindi sentence pairs. For more details about the dataset, refer to the dataset card on Hugging Face.
## Model Card Contact
For more information, please contact the model creators through the Hugging Face model repository: https://www.linkedin.com/in/satwik-sinha/
| null |
Non_BioNLP
|
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
gemma-2b-mt-Hindi-Fintuned - bnb 8bits
- Model creator: https://huggingface.co/Satwik11/
- Original model: https://huggingface.co/Satwik11/gemma-2b-mt-Hindi-Fintuned/
Original model description:
---
library_name: transformers
license: apache-2.0
datasets:
- cfilt/iitb-english-hindi
language:
- en
- hi
pipeline_tag: translation
---
# Model Card for Model ID
## Model Details
### Model Description
This model is a fine-tuned version of the GEMMA 2B multilingual transformer, specifically optimized for translating text from English to Hindi. It leverages the capabilities of the original GEMMA architecture to provide accurate and efficient translations.
-Model Name: Gemma-2b-mt-Hindi-Fintuned
-Model Type: Language Translation Model
-Base Model: Gemma-2b
-Task: English to Hindi Translation
-Framework: Transformers
### Model Sources [optional]
## Uses
### Direct Use
This model can be directly used for translating English text to Hindi. It is suitable for various applications such as:
-Localization of content
-Cross-lingual communication
-Educational tools for language learning
-Multilingual content creation
### Downstream Use [optional]
The model can be integrated into larger systems or applications that require English to Hindi translation capabilities, such as:
-Machine translation services
-Multilingual chatbots
-Content management systems for multilingual websites
[More Information Needed]
### Out-of-Scope Use
## Bias, Risks, and Limitations
-The model may struggle with idiomatic expressions or culturally specific content.
-There might be potential biases in the training data that could affect translation quality.
-The model's performance on specialized or technical content may vary.
-It may have limitations in handling complex grammatical structures or maintaining context in longer texts.
### Recommendations
-It's recommended to use the model in conjunction with human translators for high-stakes or nuanced translations.
-Regular evaluation and fine-tuning with diverse and representative data can help mitigate biases and improve performance.
## How to Get Started with the Model
Use the code below to get started with the model:
----------------------------------------------------------------------------------------
from transformers import AutoTokenizer, AutoModelForCausalLM
#Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Satwik11/gemma-2b-mt-Hindi-Fintuned")
model = AutoModelForCausalLM.from_pretrained("Satwik11/gemma-2b-mt-Hindi-Fintuned")
def generate_translation(prompt, max_length=90):
# Prepare the input
inputs = tokenizer(prompt, return_tensors='pt')
# Generate the translation
outputs = model.generate(**inputs, max_length=max_length)
# Decode the generated output
translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return translated_text
#Test the model with some example sentences
test_sentences = [
"Today is August 19.The maximum temperature is 70 degrees Fahrenheit"
]
for sentence in test_sentences:
prompt = f"Translate the following English text to Hindi: {sentence}"
translation = generate_translation(prompt)
print(translation)
-----------------------------------------------------------------------------------------------
## Training Details
### Training Data
The model was fine-tuned on the cfilt/iitb-english-hindi dataset, which contains English-Hindi sentence pairs. For more details about the dataset, refer to the dataset card on Hugging Face.
## Model Card Contact
For more information, please contact the model creators through the Hugging Face model repository: https://www.linkedin.com/in/satwik-sinha/
|
{}
|
task
|
[
"TRANSLATION"
] | 41,526 |
RichardErkhov/Babelscape_-_mrebel-large-8bits
|
RichardErkhov
|
text-generation
|
[
"transformers",
"safetensors",
"mbart",
"text-generation",
"arxiv:2306.09802",
"autotrain_compatible",
"endpoints_compatible",
"8-bit",
"bitsandbytes",
"region:us"
] | 2024-05-12T03:48:27Z |
2024-05-12T03:54:57+00:00
| 5 | 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)
mrebel-large - bnb 8bits
- Model creator: https://huggingface.co/Babelscape/
- Original model: https://huggingface.co/Babelscape/mrebel-large/
Original model description:
---
language:
- ar
- ca
- de
- el
- en
- es
- fr
- hi
- it
- ja
- ko
- nl
- pl
- pt
- ru
- sv
- vi
- zh
widget:
- text: >-
Els Red Hot Chili Peppers es van formar a Los Angeles per Kiedis, Flea, el
guitarrista Hillel Slovak i el bateria Jack Irons.
example_title: Catalan
inference:
parameters:
decoder_start_token_id: 250058
src_lang: ca_XX
tgt_lang: <triplet>
tags:
- seq2seq
- relation-extraction
license: cc-by-nc-sa-4.0
pipeline_tag: translation
datasets:
- Babelscape/SREDFM
---
# RED<sup>FM</sup>: a Filtered and Multilingual Relation Extraction Dataset
This is a multilingual version of [REBEL](https://huggingface.co/Babelscape/rebel-large). It can be used as a standalone multulingual Relation Extraction system, or as a pretrained system to be tuned on multilingual Relation Extraction datasets.
mREBEL is introduced in the ACL 2023 paper [RED^{FM}: a Filtered and Multilingual Relation Extraction Dataset](https://arxiv.org/abs/2306.09802). We present a new multilingual Relation Extraction dataset and train a multilingual version of REBEL which reframed Relation Extraction as a seq2seq task. The paper can be found [here](https://arxiv.org/abs/2306.09802). If you use the code or model, please reference this work in your paper:
@inproceedings{huguet-cabot-et-al-2023-redfm-dataset,
title = "RED$^{\rm FM}$: a Filtered and Multilingual Relation Extraction Dataset",
author = "Huguet Cabot, Pere-Llu{\'\i}s and Tedeschi, Simone and Ngonga Ngomo, Axel-Cyrille and
Navigli, Roberto",
booktitle = "Proc. of the 61st Annual Meeting of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/2306.09802",
}
The original repository for the paper can be found [here](https://github.com/Babelscape/rebel#REDFM)
Be aware that the inference widget at the right does not output special tokens, which are necessary to distinguish the subject, object and relation types. For a demo of mREBEL and its pre-training dataset check the [Spaces demo](https://huggingface.co/spaces/Babelscape/mrebel-demo).
## Pipeline usage
```python
from transformers import pipeline
triplet_extractor = pipeline('translation_xx_to_yy', model='Babelscape/mrebel-large', tokenizer='Babelscape/mrebel-large')
# We need to use the tokenizer manually since we need special tokens.
extracted_text = triplet_extractor.tokenizer.batch_decode([triplet_extractor("The Red Hot Chili Peppers were formed in Los Angeles by Kiedis, Flea, guitarist Hillel Slovak and drummer Jack Irons.", decoder_start_token_id=250058, src_lang="en_XX", tgt_lang="<triplet>", return_tensors=True, return_text=False)[0]["translation_token_ids"]]) # change en_XX for the language of the source.
print(extracted_text[0])
# Function to parse the generated text and extract the triplets
def extract_triplets_typed(text):
triplets = []
relation = ''
text = text.strip()
current = 'x'
subject, relation, object_, object_type, subject_type = '','','','',''
for token in text.replace("<s>", "").replace("<pad>", "").replace("</s>", "").replace("tp_XX", "").replace("__en__", "").split():
if token == "<triplet>" or token == "<relation>":
current = 't'
if relation != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
relation = ''
subject = ''
elif token.startswith("<") and token.endswith(">"):
if current == 't' or current == 'o':
current = 's'
if relation != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
object_ = ''
subject_type = token[1:-1]
else:
current = 'o'
object_type = token[1:-1]
relation = ''
else:
if current == 't':
subject += ' ' + token
elif current == 's':
object_ += ' ' + token
elif current == 'o':
relation += ' ' + token
if subject != '' and relation != '' and object_ != '' and object_type != '' and subject_type != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
return triplets
extracted_triplets = extract_triplets_typed(extracted_text[0])
print(extracted_triplets)
```
## Model and Tokenizer using transformers
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
def extract_triplets_typed(text):
triplets = []
relation = ''
text = text.strip()
current = 'x'
subject, relation, object_, object_type, subject_type = '','','','',''
for token in text.replace("<s>", "").replace("<pad>", "").replace("</s>", "").replace("tp_XX", "").replace("__en__", "").split():
if token == "<triplet>" or token == "<relation>":
current = 't'
if relation != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
relation = ''
subject = ''
elif token.startswith("<") and token.endswith(">"):
if current == 't' or current == 'o':
current = 's'
if relation != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
object_ = ''
subject_type = token[1:-1]
else:
current = 'o'
object_type = token[1:-1]
relation = ''
else:
if current == 't':
subject += ' ' + token
elif current == 's':
object_ += ' ' + token
elif current == 'o':
relation += ' ' + token
if subject != '' and relation != '' and object_ != '' and object_type != '' and subject_type != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
return triplets
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Babelscape/mrebel-large", src_lang="en_XX", tgt_lang="tp_XX")
# Here we set English ("en_XX") as source language. To change the source language swap the first token of the input for your desired language or change to supported language. For catalan ("ca_XX") or greek ("el_EL") (not included in mBART pretraining) you need a workaround:
# tokenizer._src_lang = "ca_XX"
# tokenizer.cur_lang_code_id = tokenizer.convert_tokens_to_ids("ca_XX")
# tokenizer.set_src_lang_special_tokens("ca_XX")
model = AutoModelForSeq2SeqLM.from_pretrained("Babelscape/mrebel-large")
gen_kwargs = {
"max_length": 256,
"length_penalty": 0,
"num_beams": 3,
"num_return_sequences": 3,
"forced_bos_token_id": None,
}
# Text to extract triplets from
text = 'The Red Hot Chili Peppers were formed in Los Angeles by Kiedis, Flea, guitarist Hillel Slovak and drummer Jack Irons.'
# Tokenizer text
model_inputs = tokenizer(text, max_length=256, padding=True, truncation=True, return_tensors = 'pt')
# Generate
generated_tokens = model.generate(
model_inputs["input_ids"].to(model.device),
attention_mask=model_inputs["attention_mask"].to(model.device),
decoder_start_token_id = tokenizer.convert_tokens_to_ids("tp_XX"),
**gen_kwargs,
)
# Extract text
decoded_preds = tokenizer.batch_decode(generated_tokens, skip_special_tokens=False)
# Extract triplets
for idx, sentence in enumerate(decoded_preds):
print(f'Prediction triplets sentence {idx}')
print(extract_triplets_typed(sentence))
```
## License
This model is licensed under the CC BY-SA 4.0 license. The text of the license can be found [here](https://creativecommons.org/licenses/by-nc-sa/4.0/).
| null |
Non_BioNLP
|
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
mrebel-large - bnb 8bits
- Model creator: https://huggingface.co/Babelscape/
- Original model: https://huggingface.co/Babelscape/mrebel-large/
Original model description:
---
language:
- ar
- ca
- de
- el
- en
- es
- fr
- hi
- it
- ja
- ko
- nl
- pl
- pt
- ru
- sv
- vi
- zh
widget:
- text: >-
Els Red Hot Chili Peppers es van formar a Los Angeles per Kiedis, Flea, el
guitarrista Hillel Slovak i el bateria Jack Irons.
example_title: Catalan
inference:
parameters:
decoder_start_token_id: 250058
src_lang: ca_XX
tgt_lang: <triplet>
tags:
- seq2seq
- relation-extraction
license: cc-by-nc-sa-4.0
pipeline_tag: translation
datasets:
- Babelscape/SREDFM
---
# RED<sup>FM</sup>: a Filtered and Multilingual Relation Extraction Dataset
This is a multilingual version of [REBEL](https://huggingface.co/Babelscape/rebel-large). It can be used as a standalone multulingual Relation Extraction system, or as a pretrained system to be tuned on multilingual Relation Extraction datasets.
mREBEL is introduced in the ACL 2023 paper [RED^{FM}: a Filtered and Multilingual Relation Extraction Dataset](https://arxiv.org/abs/2306.09802). We present a new multilingual Relation Extraction dataset and train a multilingual version of REBEL which reframed Relation Extraction as a seq2seq task. The paper can be found [here](https://arxiv.org/abs/2306.09802). If you use the code or model, please reference this work in your paper:
@inproceedings{huguet-cabot-et-al-2023-redfm-dataset,
title = "RED$^{\rm FM}$: a Filtered and Multilingual Relation Extraction Dataset",
author = "Huguet Cabot, Pere-Llu{\'\i}s and Tedeschi, Simone and Ngonga Ngomo, Axel-Cyrille and
Navigli, Roberto",
booktitle = "Proc. of the 61st Annual Meeting of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/2306.09802",
}
The original repository for the paper can be found [here](https://github.com/Babelscape/rebel#REDFM)
Be aware that the inference widget at the right does not output special tokens, which are necessary to distinguish the subject, object and relation types. For a demo of mREBEL and its pre-training dataset check the [Spaces demo](https://huggingface.co/spaces/Babelscape/mrebel-demo).
## Pipeline usage
```python
from transformers import pipeline
triplet_extractor = pipeline('translation_xx_to_yy', model='Babelscape/mrebel-large', tokenizer='Babelscape/mrebel-large')
# We need to use the tokenizer manually since we need special tokens.
extracted_text = triplet_extractor.tokenizer.batch_decode([triplet_extractor("The Red Hot Chili Peppers were formed in Los Angeles by Kiedis, Flea, guitarist Hillel Slovak and drummer Jack Irons.", decoder_start_token_id=250058, src_lang="en_XX", tgt_lang="<triplet>", return_tensors=True, return_text=False)[0]["translation_token_ids"]]) # change en_XX for the language of the source.
print(extracted_text[0])
# Function to parse the generated text and extract the triplets
def extract_triplets_typed(text):
triplets = []
relation = ''
text = text.strip()
current = 'x'
subject, relation, object_, object_type, subject_type = '','','','',''
for token in text.replace("<s>", "").replace("<pad>", "").replace("</s>", "").replace("tp_XX", "").replace("__en__", "").split():
if token == "<triplet>" or token == "<relation>":
current = 't'
if relation != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
relation = ''
subject = ''
elif token.startswith("<") and token.endswith(">"):
if current == 't' or current == 'o':
current = 's'
if relation != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
object_ = ''
subject_type = token[1:-1]
else:
current = 'o'
object_type = token[1:-1]
relation = ''
else:
if current == 't':
subject += ' ' + token
elif current == 's':
object_ += ' ' + token
elif current == 'o':
relation += ' ' + token
if subject != '' and relation != '' and object_ != '' and object_type != '' and subject_type != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
return triplets
extracted_triplets = extract_triplets_typed(extracted_text[0])
print(extracted_triplets)
```
## Model and Tokenizer using transformers
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
def extract_triplets_typed(text):
triplets = []
relation = ''
text = text.strip()
current = 'x'
subject, relation, object_, object_type, subject_type = '','','','',''
for token in text.replace("<s>", "").replace("<pad>", "").replace("</s>", "").replace("tp_XX", "").replace("__en__", "").split():
if token == "<triplet>" or token == "<relation>":
current = 't'
if relation != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
relation = ''
subject = ''
elif token.startswith("<") and token.endswith(">"):
if current == 't' or current == 'o':
current = 's'
if relation != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
object_ = ''
subject_type = token[1:-1]
else:
current = 'o'
object_type = token[1:-1]
relation = ''
else:
if current == 't':
subject += ' ' + token
elif current == 's':
object_ += ' ' + token
elif current == 'o':
relation += ' ' + token
if subject != '' and relation != '' and object_ != '' and object_type != '' and subject_type != '':
triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
return triplets
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Babelscape/mrebel-large", src_lang="en_XX", tgt_lang="tp_XX")
# Here we set English ("en_XX") as source language. To change the source language swap the first token of the input for your desired language or change to supported language. For catalan ("ca_XX") or greek ("el_EL") (not included in mBART pretraining) you need a workaround:
# tokenizer._src_lang = "ca_XX"
# tokenizer.cur_lang_code_id = tokenizer.convert_tokens_to_ids("ca_XX")
# tokenizer.set_src_lang_special_tokens("ca_XX")
model = AutoModelForSeq2SeqLM.from_pretrained("Babelscape/mrebel-large")
gen_kwargs = {
"max_length": 256,
"length_penalty": 0,
"num_beams": 3,
"num_return_sequences": 3,
"forced_bos_token_id": None,
}
# Text to extract triplets from
text = 'The Red Hot Chili Peppers were formed in Los Angeles by Kiedis, Flea, guitarist Hillel Slovak and drummer Jack Irons.'
# Tokenizer text
model_inputs = tokenizer(text, max_length=256, padding=True, truncation=True, return_tensors = 'pt')
# Generate
generated_tokens = model.generate(
model_inputs["input_ids"].to(model.device),
attention_mask=model_inputs["attention_mask"].to(model.device),
decoder_start_token_id = tokenizer.convert_tokens_to_ids("tp_XX"),
**gen_kwargs,
)
# Extract text
decoded_preds = tokenizer.batch_decode(generated_tokens, skip_special_tokens=False)
# Extract triplets
for idx, sentence in enumerate(decoded_preds):
print(f'Prediction triplets sentence {idx}')
print(extract_triplets_typed(sentence))
```
## License
This model is licensed under the CC BY-SA 4.0 license. The text of the license can be found [here](https://creativecommons.org/licenses/by-nc-sa/4.0/).
|
{}
|
task
|
[
"RELATION_EXTRACTION",
"TRANSLATION"
] | 41,527 |
01-ai/Yi-6B-Chat-8bits
|
01-ai
|
text-generation
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:2403.04652",
"arxiv:2311.16502",
"arxiv:2401.11944",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"gptq",
"region:us"
] | 2023-11-22T09:55:20Z |
2024-11-11T03:31:33+00:00
| 206 | 9 |
---
license: apache-2.0
pipeline_tag: text-generation
widget:
- example_title: Yi-34B-Chat
text: hi
output:
text: ' Hello! How can I assist you today?'
- example_title: Yi-34B
text: There's a place where time stands still. A place of breath taking wonder,
but also
output:
text: ' an eerie sense that something is just not right…
Between the two worlds lies The Forgotten Kingdom - home to creatures long since
thought extinct and ancient magic so strong it defies belief! Only here can
you find what has been lost for centuries: An Elixir Of Life which will restore
youth and vitality if only those who seek its power are brave enough to face
up against all manner of dangers lurking in this mysterious land! But beware;
some say there may even exist powerful entities beyond our comprehension whose
intentions towards humanity remain unclear at best ---- they might want nothing
more than destruction itself rather then anything else from their quest after
immortality (and maybe someone should tell them about modern medicine)? In any
event though – one thing remains true regardless : whether or not success comes
easy depends entirely upon how much effort we put into conquering whatever challenges
lie ahead along with having faith deep down inside ourselves too ;) So let’s
get started now shall We?'
---
<div align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_dark.svg" width="200px">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="200px">
<img alt="specify theme context for images" src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg">
</picture>
</br>
</br>
<div style="display: inline-block;">
<a href="https://github.com/01-ai/Yi/actions/workflows/build_docker_image.yml">
<img src="https://github.com/01-ai/Yi/actions/workflows/build_docker_image.yml/badge.svg">
</a>
</div>
<div style="display: inline-block;">
<a href="mailto:[email protected]">
<img src="https://img.shields.io/badge/✉️[email protected]">
</a>
</div>
</div>
<div align="center">
<h3 align="center">Building the Next Generation of Open-Source and Bilingual LLMs</h3>
</div>
<p align="center">
🤗 <a href="https://huggingface.co/01-ai" target="_blank">Hugging Face</a> • 🤖 <a href="https://www.modelscope.cn/organization/01ai/" target="_blank">ModelScope</a> • ✡️ <a href="https://wisemodel.cn/organization/01.AI" target="_blank">WiseModel</a>
</p>
<p align="center">
👩🚀 Ask questions or discuss ideas on <a href="https://github.com/01-ai/Yi/discussions" target="_blank"> GitHub </a>
</p>
<p align="center">
👋 Join us on <a href="https://discord.gg/hYUwWddeAu" target="_blank"> 👾 Discord </a> or <a href="有官方的微信群嘛 · Issue #43 · 01-ai/Yi" target="_blank"> 💬 WeChat </a>
</p>
<p align="center">
📝 Check out <a href="https://arxiv.org/abs/2403.04652"> Yi Tech Report </a>
</p>
<p align="center">
📚 Grow at <a href="#learning-hub"> Yi Learning Hub </a>
</p>
<!-- DO NOT REMOVE ME -->
<hr>
<details open>
<summary></b>📕 Table of Contents</b></summary>
- [What is Yi?](#what-is-yi)
- [Introduction](#introduction)
- [Models](#models)
- [Chat models](#chat-models)
- [Base models](#base-models)
- [Model info](#model-info)
- [News](#news)
- [How to use Yi?](#how-to-use-yi)
- [Quick start](#quick-start)
- [Choose your path](#choose-your-path)
- [pip](#quick-start---pip)
- [docker](#quick-start---docker)
- [llama.cpp](#quick-start---llamacpp)
- [conda-lock](#quick-start---conda-lock)
- [Web demo](#web-demo)
- [Fine-tuning](#fine-tuning)
- [Quantization](#quantization)
- [Deployment](#deployment)
- [FAQ](#faq)
- [Learning hub](#learning-hub)
- [Why Yi?](#why-yi)
- [Ecosystem](#ecosystem)
- [Upstream](#upstream)
- [Downstream](#downstream)
- [Serving](#serving)
- [Quantization](#quantization-1)
- [Fine-tuning](#fine-tuning-1)
- [API](#api)
- [Benchmarks](#benchmarks)
- [Base model performance](#base-model-performance)
- [Chat model performance](#chat-model-performance)
- [Tech report](#tech-report)
- [Citation](#citation)
- [Who can use Yi?](#who-can-use-yi)
- [Misc.](#misc)
- [Acknowledgements](#acknowledgments)
- [Disclaimer](#disclaimer)
- [License](#license)
</details>
<hr>
# What is Yi?
## Introduction
- 🤖 The Yi series models are the next generation of open-source large language models trained from scratch by [01.AI](https://01.ai/).
- 🙌 Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example,
- Yi-34B-Chat model **landed in second place (following GPT-4 Turbo)**, outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024).
- Yi-34B model **ranked first among all existing open-source models** (such as Falcon-180B, Llama-70B, Claude) in **both English and Chinese** on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023).
- 🙏 (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem.
<details style="display: inline;"><summary> If you're interested in Yi's adoption of Llama architecture and license usage policy, see <span style="color: green;">Yi's relation with Llama.</span> ⬇️</summary> <ul> <br>
> 💡 TL;DR
>
> The Yi series models adopt the same model architecture as Llama but are **NOT** derivatives of Llama.
- Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018.
- Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi.
- Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems.
- However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights.
- As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure.
- Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the [Alpaca Leaderboard in Dec 2023](https://tatsu-lab.github.io/alpaca_eval/).
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
## News
<details>
<summary>🔥 <b>2024-07-29</b>: The <a href="https://github.com/Haijian06/Yi/tree/main/Cookbook">Yi Cookbook 1.0 </a> is released, featuring tutorials and examples in both Chinese and English.</summary>
</details>
<details>
<summary>🎯 <b>2024-05-13</b>: The <a href="https://github.com/01-ai/Yi-1.5">Yi-1.5 series models </a> are open-sourced, further improving coding, math, reasoning, and instruction-following abilities.</summary>
</details>
<details>
<summary>🎯 <b>2024-03-16</b>: The <code>Yi-9B-200K</code> is open-sourced and available to the public.</summary>
</details>
<details>
<summary>🎯 <b>2024-03-08</b>: <a href="https://arxiv.org/abs/2403.04652">Yi Tech Report</a> is published! </summary>
</details>
<details open>
<summary>🔔 <b>2024-03-07</b>: The long text capability of the Yi-34B-200K has been enhanced. </summary>
<br>
In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance.
</details>
<details open>
<summary>🎯 <b>2024-03-06</b>: The <code>Yi-9B</code> is open-sourced and available to the public.</summary>
<br>
<code>Yi-9B</code> stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension.
</details>
<details open>
<summary>🎯 <b>2024-01-23</b>: The Yi-VL models, <code><a href="https://huggingface.co/01-ai/Yi-VL-34B">Yi-VL-34B</a></code> and <code><a href="https://huggingface.co/01-ai/Yi-VL-6B">Yi-VL-6B</a></code>, are open-sourced and available to the public.</summary>
<br>
<code><a href="https://huggingface.co/01-ai/Yi-VL-34B">Yi-VL-34B</a></code> has ranked <strong>first</strong> among all existing open-source models in the latest benchmarks, including <a href="https://arxiv.org/abs/2311.16502">MMMU</a> and <a href="https://arxiv.org/abs/2401.11944">CMMMU</a> (based on data available up to January 2024).</li>
</details>
<details>
<summary>🎯 <b>2023-11-23</b>: <a href="#chat-models">Chat models</a> are open-sourced and available to the public.</summary>
<br>This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ.
- `Yi-34B-Chat`
- `Yi-34B-Chat-4bits`
- `Yi-34B-Chat-8bits`
- `Yi-6B-Chat`
- `Yi-6B-Chat-4bits`
- `Yi-6B-Chat-8bits`
You can try some of them interactively at:
- [Hugging Face](https://huggingface.co/spaces/01-ai/Yi-34B-Chat)
- [Replicate](https://replicate.com/01-ai)
</details>
<details>
<summary>🔔 <b>2023-11-23</b>: The Yi Series Models Community License Agreement is updated to <a href="https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt">v2.1</a>.</summary>
</details>
<details>
<summary>🔥 <b>2023-11-08</b>: Invited test of Yi-34B chat model.</summary>
<br>Application form:
- [English](https://cn.mikecrm.com/l91ODJf)
- [Chinese](https://cn.mikecrm.com/gnEZjiQ)
</details>
<details>
<summary>🎯 <b>2023-11-05</b>: <a href="#base-models">The base models, </a><code>Yi-6B-200K</code> and <code>Yi-34B-200K</code>, are open-sourced and available to the public.</summary>
<br>This release contains two base models with the same parameter sizes as the previous
release, except that the context window is extended to 200K.
</details>
<details>
<summary>🎯 <b>2023-11-02</b>: <a href="#base-models">The base models, </a><code>Yi-6B</code> and <code>Yi-34B</code>, are open-sourced and available to the public.</summary>
<br>The first public release contains two bilingual (English/Chinese) base models
with the parameter sizes of 6B and 34B. Both of them are trained with 4K
sequence length and can be extended to 32K during inference time.
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
## Models
Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements.
If you want to deploy Yi models, make sure you meet the [software and hardware requirements](#deployment).
### Chat models
| Model | Download |
|---|---|
|Yi-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-34B-Chat) |
|Yi-34B-Chat-4bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-4bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-4bits/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-34B-Chat-4bits) |
|Yi-34B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-8bits/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-34B-Chat-8bits) |
|Yi-6B-Chat| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat) |
|Yi-6B-Chat-4bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-4bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-4bits/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-4bits) |
|Yi-6B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-8bits/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
<sub><sup> - 4-bit series models are quantized by AWQ. <br> - 8-bit series models are quantized by GPTQ <br> - All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). </sup></sub>
### Base models
| Model | Download |
|---|---|
|Yi-34B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
|Yi-34B-200K|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-200K/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits)|
|Yi-9B|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-9B) • [🤖 ModelScope](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-9B)|
|Yi-9B-200K | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-9B-200K) • [🤖 ModelScope](https://wisemodel.cn/models/01.AI/Yi-9B-200K) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
|Yi-6B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
|Yi-6B-200K | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-200K/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
<sub><sup> - 200k is roughly equivalent to 400,000 Chinese characters. <br> - If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run `git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf` to download the weight. </sup></sub>
### Model info
- For chat and base models
<table>
<thead>
<tr>
<th>Model</th>
<th>Intro</th>
<th>Default context window</th>
<th>Pretrained tokens</th>
<th>Training Data Date</th>
</tr>
</thead>
<tbody><tr>
<td>6B series models</td>
<td>They are suitable for personal and academic use.</td>
<td rowspan="3">4K</td>
<td>3T</td>
<td rowspan="3">Up to June 2023</td>
</tr>
<tr>
<td>9B series models</td>
<td>It is the best at coding and math in the Yi series models.</td>
<td>Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens.</td>
</tr>
<tr>
<td>34B series models</td>
<td>They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability.</td>
<td>3T</td>
</tr>
</tbody></table>
- For chat models
<details style="display: inline;"><summary>For chat model limitations, see the explanations below. ⬇️</summary>
<ul>
<br>The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training.
<br>However, this higher diversity might amplify certain existing issues, including:
<li>Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning.</li>
<li>Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions.</li>
<li>Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc.</li>
<li>To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top_p, or top_k. These adjustments can help in the balance between creativity and coherence in the model's outputs.</li>
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
# How to use Yi?
- [Quick start](#quick-start)
- [Choose your path](#choose-your-path)
- [pip](#quick-start---pip)
- [docker](#quick-start---docker)
- [conda-lock](#quick-start---conda-lock)
- [llama.cpp](#quick-start---llamacpp)
- [Web demo](#web-demo)
- [Fine-tuning](#fine-tuning)
- [Quantization](#quantization)
- [Deployment](#deployment)
- [FAQ](#faq)
- [Learning hub](#learning-hub)
## Quick start
> **💡 Tip**: If you want to get started with the Yi model and explore different methods for inference, check out the [Yi Cookbook](https://github.com/01-ai/Yi/tree/main/Cookbook).
### Choose your path
Select one of the following paths to begin your journey with Yi!
#### 🎯 Deploy Yi locally
If you prefer to deploy Yi models locally,
- 🙋♀️ and you have **sufficient** resources (for example, NVIDIA A800 80GB), you can choose one of the following methods:
- [pip](#quick-start---pip)
- [Docker](#quick-start---docker)
- [conda-lock](#quick-start---conda-lock)
- 🙋♀️ and you have **limited** resources (for example, a MacBook Pro), you can use [llama.cpp](#quick-start---llamacpp).
#### 🎯 Not to deploy Yi locally
If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options.
##### 🙋♀️ Run Yi with APIs
If you want to explore more features of Yi, you can adopt one of these methods:
- Yi APIs (Yi official)
- [Early access has been granted](https://x.com/01AI_Yi/status/1735728934560600536?s=20) to some applicants. Stay tuned for the next round of access!
- [Yi APIs](https://replicate.com/01-ai/yi-34b-chat/api?tab=nodejs) (Replicate)
##### 🙋♀️ Run Yi in playground
If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options:
- [Yi-34B-Chat-Playground](https://platform.lingyiwanwu.com/prompt/playground) (Yi official)
- Access is available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)).
- [Yi-34B-Chat-Playground](https://replicate.com/01-ai/yi-34b-chat) (Replicate)
##### 🙋♀️ Chat with Yi
If you want to chat with Yi, you can use one of these online services, which offer a similar user experience:
- [Yi-34B-Chat](https://huggingface.co/spaces/01-ai/Yi-34B-Chat) (Yi official on Hugging Face)
- No registration is required.
- [Yi-34B-Chat](https://platform.lingyiwanwu.com/) (Yi official beta)
- Access is available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)).
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Quick start - pip
This tutorial guides you through every step of running **Yi-34B-Chat locally on an A800 (80G)** and then performing inference.
#### Step 0: Prerequisites
- Make sure Python 3.10 or a later version is installed.
- If you want to run other Yi models, see [software and hardware requirements](#deployment).
#### Step 1: Prepare your environment
To set up the environment and install the required packages, execute the following command.
```bash
git clone https://github.com/01-ai/Yi.git
cd yi
pip install -r requirements.txt
```
#### Step 2: Download the Yi model
You can download the weights and tokenizer of Yi models from the following sources:
- [Hugging Face](https://huggingface.co/01-ai)
- [ModelScope](https://www.modelscope.cn/organization/01ai/)
- [WiseModel](https://wisemodel.cn/organization/01.AI)
#### Step 3: Perform inference
You can perform inference with Yi chat or base models as below.
##### Perform inference with Yi chat model
1. Create a file named `quick_start.py` and copy the following content to it.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = '<your-model-path>'
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
# Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM.
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
```
2. Run `quick_start.py`.
```bash
python quick_start.py
```
Then you can see an output similar to the one below. 🥳
```bash
Hello! How can I assist you today?
```
##### Perform inference with Yi base model
- Yi-34B
The steps are similar to [pip - Perform inference with Yi chat model](#perform-inference-with-yi-chat-model).
You can use the existing file [`text_generation.py`](https://github.com/01-ai/Yi/tree/main/demo).
```bash
python demo/text_generation.py --model <your-model-path>
```
Then you can see an output similar to the one below. 🥳
<details>
<summary>Output. ⬇️ </summary>
<br>
**Prompt**: Let me tell you an interesting story about cat Tom and mouse Jerry,
**Generation**: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldn’t get up because there were too many people around him! He kept trying for several minutes before finally giving up...
</details>
- Yi-9B
Input
```bash
from transformers import AutoModelForCausalLM, AutoTokenizer
MODEL_DIR = "01-ai/Yi-9B"
model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False)
input_text = "# write the quick sort algorithm"
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
Output
```bash
# write the quick sort algorithm
def quick_sort(arr):
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quick_sort(left) + middle + quick_sort(right)
# test the quick sort algorithm
print(quick_sort([3, 6, 8, 10, 1, 2, 1]))
```
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Quick start - Docker
<details>
<summary> Run Yi-34B-chat locally with Docker: a step-by-step guide. ⬇️</summary>
<br>This tutorial guides you through every step of running <strong>Yi-34B-Chat on an A800 GPU</strong> or <strong>4*4090</strong> locally and then performing inference.
<h4>Step 0: Prerequisites</h4>
<p>Make sure you've installed <a href="https://docs.docker.com/engine/install/?open_in_browser=true">Docker</a> and <a href="https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html">nvidia-container-toolkit</a>.</p>
<h4> Step 1: Start Docker </h4>
<pre><code>docker run -it --gpus all \
-v <your-model-path>: /models
ghcr.io/01-ai/yi:latest
</code></pre>
<p>Alternatively, you can pull the Yi Docker image from <code>registry.lingyiwanwu.com/ci/01-ai/yi:latest</code>.</p>
<h4>Step 2: Perform inference</h4>
<p>You can perform inference with Yi chat or base models as below.</p>
<h5>Perform inference with Yi chat model</h5>
<p>The steps are similar to <a href="#perform-inference-with-yi-chat-model">pip - Perform inference with Yi chat model</a>.</p>
<p><strong>Note</strong> that the only difference is to set <code>model_path = '<your-model-mount-path>'</code> instead of <code>model_path = '<your-model-path>'</code>.</p>
<h5>Perform inference with Yi base model</h5>
<p>The steps are similar to <a href="#perform-inference-with-yi-base-model">pip - Perform inference with Yi base model</a>.</p>
<p><strong>Note</strong> that the only difference is to set <code>--model <your-model-mount-path>'</code> instead of <code>model <your-model-path></code>.</p>
</details>
### Quick start - conda-lock
<details>
<summary>You can use <code><a href="https://github.com/conda/conda-lock">conda-lock</a></code> to generate fully reproducible lock files for conda environments. ⬇️</summary>
<br>
You can refer to <a href="https://github.com/01-ai/Yi/blob/ebba23451d780f35e74a780987ad377553134f68/conda-lock.yml">conda-lock.yml</a> for the exact versions of the dependencies. Additionally, you can utilize <code><a href="https://mamba.readthedocs.io/en/latest/user_guide/micromamba.html">micromamba</a></code> for installing these dependencies.
<br>
To install the dependencies, follow these steps:
1. Install micromamba by following the instructions available <a href="https://mamba.readthedocs.io/en/latest/installation/micromamba-installation.html">here</a>.
2. Execute <code>micromamba install -y -n yi -f conda-lock.yml</code> to create a conda environment named <code>yi</code> and install the necessary dependencies.
</details>
### Quick start - llama.cpp
<a href="https://github.com/01-ai/Yi/blob/main/docs/README_llama.cpp.md">The following tutorial </a> will guide you through every step of running a quantized model (<a href="https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main">Yi-chat-6B-2bits</a>) locally and then performing inference.
<details>
<summary> Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. ⬇️</summary>
<br><a href="https://github.com/01-ai/Yi/blob/main/docs/README_llama.cpp.md">This tutorial</a> guides you through every step of running a quantized model (<a href="https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main">Yi-chat-6B-2bits</a>) locally and then performing inference.</p>
- [Step 0: Prerequisites](#step-0-prerequisites)
- [Step 1: Download llama.cpp](#step-1-download-llamacpp)
- [Step 2: Download Yi model](#step-2-download-yi-model)
- [Step 3: Perform inference](#step-3-perform-inference)
#### Step 0: Prerequisites
- This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip.
- Make sure [`git-lfs`](https://git-lfs.com/) is installed on your machine.
#### Step 1: Download `llama.cpp`
To clone the [`llama.cpp`](https://github.com/ggerganov/llama.cpp) repository, run the following command.
```bash
git clone [email protected]:ggerganov/llama.cpp.git
```
#### Step 2: Download Yi model
2.1 To clone [XeIaso/yi-chat-6B-GGUF](https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main) with just pointers, run the following command.
```bash
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF
```
2.2 To download a quantized Yi model ([yi-chat-6b.Q2_K.gguf](https://huggingface.co/XeIaso/yi-chat-6B-GGUF/blob/main/yi-chat-6b.Q2_K.gguf)), run the following command.
```bash
git-lfs pull --include yi-chat-6b.Q2_K.gguf
```
#### Step 3: Perform inference
To perform inference with the Yi model, you can use one of the following methods.
- [Method 1: Perform inference in terminal](#method-1-perform-inference-in-terminal)
- [Method 2: Perform inference in web](#method-2-perform-inference-in-web)
##### Method 1: Perform inference in terminal
To compile `llama.cpp` using 4 threads and then conduct inference, navigate to the `llama.cpp` directory, and run the following command.
> ##### Tips
>
> - Replace `/Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf` with the actual path of your model.
>
> - By default, the model operates in completion mode.
>
> - For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run `./main -h` to check detailed descriptions and usage.
```bash
make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e
...
How do you feed your pet fox? Please answer this question in 6 simple steps:
Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables.
Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day.
Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise.
Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress.
Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections.
Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care.
...
```
Now you have successfully asked a question to the Yi model and got an answer! 🥳
##### Method 2: Perform inference in web
1. To initialize a lightweight and swift chatbot, run the following command.
```bash
cd llama.cpp
./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf
```
Then you can get an output like this:
```bash
...
llama_new_context_with_model: n_ctx = 2048
llama_new_context_with_model: freq_base = 5000000.0
llama_new_context_with_model: freq_scale = 1
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M2 Pro
ggml_metal_init: picking default device: Apple M2 Pro
ggml_metal_init: ggml.metallib not found, loading from source
ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil
ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal'
ggml_metal_init: GPU name: Apple M2 Pro
ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008)
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB
ggml_metal_init: maxTransferRate = built-in GPU
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67)
llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67)
llama_build_graph: non-view tensors processed: 676/676
llama_new_context_with_model: compute buffer total size = 159.19 MiB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67)
Available slots:
-> Slot 0 - max context: 2048
llama server listening at http://0.0.0.0:8080
```
2. To access the chatbot interface, open your web browser and enter `http://0.0.0.0:8080` into the address bar.
3. Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer.
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Web demo
You can build a web UI demo for Yi **chat** models (note that Yi base models are not supported in this senario).
[Step 1: Prepare your environment](#step-1-prepare-your-environment).
[Step 2: Download the Yi model](#step-2-download-the-yi-model).
Step 3. To start a web service locally, run the following command.
```bash
python demo/web_demo.py -c <your-model-path>
```
You can access the web UI by entering the address provided in the console into your browser.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Fine-tuning
```bash
bash finetune/scripts/run_sft_Yi_6b.sh
```
Once finished, you can compare the finetuned model and the base model with the following command:
```bash
bash finetune/scripts/run_eval.sh
```
<details style="display: inline;"><summary>For advanced usage (like fine-tuning based on your custom data), see the explanations below. ⬇️ </summary> <ul>
### Finetune code for Yi 6B and 34B
#### Preparation
##### From Image
By default, we use a small dataset from [BAAI/COIG](https://huggingface.co/datasets/BAAI/COIG) to finetune the base model.
You can also prepare your customized dataset in the following `jsonl` format:
```json
{ "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." }
```
And then mount them in the container to replace the default ones:
```bash
docker run -it \
-v /path/to/save/finetuned/model/:/finetuned-model \
-v /path/to/train.jsonl:/yi/finetune/data/train.json \
-v /path/to/eval.jsonl:/yi/finetune/data/eval.json \
ghcr.io/01-ai/yi:latest \
bash finetune/scripts/run_sft_Yi_6b.sh
```
##### From Local Server
Make sure you have conda. If not, use
```bash
mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm -rf ~/miniconda3/miniconda.sh
~/miniconda3/bin/conda init bash
source ~/.bashrc
```
Then, create a conda env:
```bash
conda create -n dev_env python=3.10 -y
conda activate dev_env
pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7
```
#### Hardware Setup
For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended.
For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA_VISIBLE_DEVICES to limit the number of GPUs (as shown in scripts/run_sft_Yi_34b.sh).
A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA_VISIBLE_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB.
#### Quick Start
Download a LLM-base model to MODEL_PATH (6B and 34B). A typical folder of models is like:
```bash
|-- $MODEL_PATH
| |-- config.json
| |-- pytorch_model-00001-of-00002.bin
| |-- pytorch_model-00002-of-00002.bin
| |-- pytorch_model.bin.index.json
| |-- tokenizer_config.json
| |-- tokenizer.model
| |-- ...
```
Download a dataset from huggingface to local storage DATA_PATH, e.g. Dahoas/rm-static.
```bash
|-- $DATA_PATH
| |-- data
| | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet
| | |-- test-00000-of-00001-8c7c51afc6d45980.parquet
| |-- dataset_infos.json
| |-- README.md
```
`finetune/yi_example_dataset` has example datasets, which are modified from [BAAI/COIG](https://huggingface.co/datasets/BAAI/COIG)
```bash
|-- $DATA_PATH
|--data
|-- train.jsonl
|-- eval.jsonl
```
`cd` into the scripts folder, copy and paste the script, and run. For example:
```bash
cd finetune/scripts
bash run_sft_Yi_6b.sh
```
For the Yi-6B base model, setting training_debug_steps=20 and num_train_epochs=4 can output a chat model, which takes about 20 minutes.
For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient.
#### Evaluation
```bash
cd finetune/scripts
bash run_eval.sh
```
Then you'll see the answer from both the base model and the finetuned model.
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Quantization
#### GPT-Q
```bash
python quantization/gptq/quant_autogptq.py \
--model /base_model \
--output_dir /quantized_model \
--trust_remote_code
```
Once finished, you can then evaluate the resulting model as follows:
```bash
python quantization/gptq/eval_quantized_model.py \
--model /quantized_model \
--trust_remote_code
```
<details style="display: inline;"><summary>For details, see the explanations below. ⬇️</summary> <ul>
#### GPT-Q quantization
[GPT-Q](https://github.com/IST-DASLab/gptq) is a PTQ (Post-Training Quantization)
method. It saves memory and provides potential speedups while retaining the accuracy
of the model.
Yi models can be GPT-Q quantized without a lot of efforts.
We provide a step-by-step tutorial below.
To run GPT-Q, we will use [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) and
[exllama](https://github.com/turboderp/exllama).
And the huggingface transformers has integrated optimum and auto-gptq to perform
GPTQ quantization on language models.
##### Do Quantization
The `quant_autogptq.py` script is provided for you to perform GPT-Q quantization:
```bash
python quant_autogptq.py --model /base_model \
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
```
##### Run Quantized Model
You can run a quantized model using the `eval_quantized_model.py`:
```bash
python eval_quantized_model.py --model /quantized_model --trust_remote_code
```
</ul>
</details>
#### AWQ
```bash
python quantization/awq/quant_autoawq.py \
--model /base_model \
--output_dir /quantized_model \
--trust_remote_code
```
Once finished, you can then evaluate the resulting model as follows:
```bash
python quantization/awq/eval_quantized_model.py \
--model /quantized_model \
--trust_remote_code
```
<details style="display: inline;"><summary>For details, see the explanations below. ⬇️</summary> <ul>
#### AWQ quantization
[AWQ](https://github.com/mit-han-lab/llm-awq) is a PTQ (Post-Training Quantization)
method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs.
Yi models can be AWQ quantized without a lot of efforts.
We provide a step-by-step tutorial below.
To run AWQ, we will use [AutoAWQ](https://github.com/casper-hansen/AutoAWQ).
##### Do Quantization
The `quant_autoawq.py` script is provided for you to perform AWQ quantization:
```bash
python quant_autoawq.py --model /base_model \
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
```
##### Run Quantized Model
You can run a quantized model using the `eval_quantized_model.py`:
```bash
python eval_quantized_model.py --model /quantized_model --trust_remote_code
```
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Deployment
If you want to deploy Yi models, make sure you meet the software and hardware requirements.
#### Software requirements
Before using Yi quantized models, make sure you've installed the correct software listed below.
| Model | Software
|---|---
Yi 4-bit quantized models | [AWQ and CUDA](https://github.com/casper-hansen/AutoAWQ?tab=readme-ov-file#install-from-pypi)
Yi 8-bit quantized models | [GPTQ and CUDA](https://github.com/PanQiWei/AutoGPTQ?tab=readme-ov-file#quick-installation)
#### Hardware requirements
Before deploying Yi in your environment, make sure your hardware meets the following requirements.
##### Chat models
| Model | Minimum VRAM | Recommended GPU Example |
|:----------------------|:--------------|:-------------------------------------:|
| Yi-6B-Chat | 15 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) |
| Yi-6B-Chat-4bits | 4 GB | 1 x RTX 3060 (12 GB)<br> 1 x RTX 4060 (8 GB) |
| Yi-6B-Chat-8bits | 8 GB | 1 x RTX 3070 (8 GB) <br> 1 x RTX 4060 (8 GB) |
| Yi-34B-Chat | 72 GB | 4 x RTX 4090 (24 GB)<br> 1 x A800 (80GB) |
| Yi-34B-Chat-4bits | 20 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) <br> 1 x A100 (40 GB) |
| Yi-34B-Chat-8bits | 38 GB | 2 x RTX 3090 (24 GB) <br> 2 x RTX 4090 (24 GB)<br> 1 x A800 (40 GB) |
Below are detailed minimum VRAM requirements under different batch use cases.
| Model | batch=1 | batch=4 | batch=16 | batch=32 |
| ----------------------- | ------- | ------- | -------- | -------- |
| Yi-6B-Chat | 12 GB | 13 GB | 15 GB | 18 GB |
| Yi-6B-Chat-4bits | 4 GB | 5 GB | 7 GB | 10 GB |
| Yi-6B-Chat-8bits | 7 GB | 8 GB | 10 GB | 14 GB |
| Yi-34B-Chat | 65 GB | 68 GB | 76 GB | > 80 GB |
| Yi-34B-Chat-4bits | 19 GB | 20 GB | 30 GB | 40 GB |
| Yi-34B-Chat-8bits | 35 GB | 37 GB | 46 GB | 58 GB |
##### Base models
| Model | Minimum VRAM | Recommended GPU Example |
|----------------------|--------------|:-------------------------------------:|
| Yi-6B | 15 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) |
| Yi-6B-200K | 50 GB | 1 x A800 (80 GB) |
| Yi-9B | 20 GB | 1 x RTX 4090 (24 GB) |
| Yi-34B | 72 GB | 4 x RTX 4090 (24 GB) <br> 1 x A800 (80 GB) |
| Yi-34B-200K | 200 GB | 4 x A800 (80 GB) |
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### FAQ
<details>
<summary> If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. ⬇️</summary>
<br>
#### 💡Fine-tuning
- <strong>Base model or Chat model - which to fine-tune?</strong>
<br>The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task.
- If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice.
- On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice.
- It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements.
- <strong>Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?</strong>
<br>
The key distinction between full-scale fine-tuning on `Yi-34B`and `Yi-34B-Chat` comes down to the fine-tuning approach and outcomes.
- Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely.
- The Base model's fine-tuning is more versatile, with a relatively high performance potential.
- If you are confident in the quality of your data, fine-tuning with `Yi-34B` could be your go-to.
- If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, `Yi-34B-Chat` might be your best bet.
#### 💡Quantization
- <strong>Quantized model versus original model - what is the performance gap?</strong>
- The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points.
- Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results.
#### 💡General
- <strong>Where can I source fine-tuning question answering datasets?</strong>
- You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like [m-a-p/COIG-CQIA](https://huggingface.co/datasets/m-a-p/COIG-CQIA) readily available.
- Additionally, Github offers fine-tuning frameworks, such as [hiyouga/LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory), which integrates pre-made datasets.
- <strong>What is the GPU memory requirement for fine-tuning Yi-34B FP16?</strong>
<br>
The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out [hiyouga/LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory). Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance.
- <strong>Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?</strong>
<br>
If you're looking for third-party Chats, options include [fireworks.ai](https://fireworks.ai/login?callbackURL=https://fireworks.ai/models/fireworks/yi-34b-chat).
</details>
### Learning hub
<details>
<summary> If you want to learn Yi, you can find a wealth of helpful educational resources here. ⬇️</summary>
<br>
Welcome to the Yi learning hub!
Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more.
The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions!
At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below.
With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳
#### Tutorials
##### Blog tutorials
| Deliverable | Date | Author |
| ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ |
| [使用 Dify、Meilisearch、零一万物模型实现最简单的 RAG 应用（三）：AI 电影推荐](https://mp.weixin.qq.com/s/Ri2ap9_5EMzdfiBhSSL_MQ) | 2024-05-20 | [苏洋](https://github.com/soulteary) |
| [使用autodl服务器，在A40显卡上运行， Yi-34B-Chat-int4模型，并使用vllm优化加速，显存占用42G，速度18 words-s](https://blog.csdn.net/freewebsys/article/details/134698597?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-17-134698597-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-05-20 | [fly-iot](https://gitee.com/fly-iot) |
| [Yi-VL 最佳实践](https://modelscope.cn/docs/yi-vl最佳实践) | 2024-05-20 | [ModelScope](https://github.com/modelscope) |
| [一键运行零一万物新鲜出炉Yi-1.5-9B-Chat大模型](https://mp.weixin.qq.com/s/ntMs2G_XdWeM3I6RUOBJrA) | 2024-05-13 | [Second State](https://github.com/second-state) |
| [零一万物开源Yi-1.5系列大模型](https://mp.weixin.qq.com/s/d-ogq4hcFbsuL348ExJxpA) | 2024-05-13 | [刘聪](https://github.com/liucongg) |
| [零一万物Yi-1.5系列模型发布并开源！ 34B-9B-6B 多尺寸，魔搭社区推理微调最佳实践教程来啦！](https://mp.weixin.qq.com/s/3wD-0dCgXB646r720o8JAg) | 2024-05-13 | [ModelScope](https://github.com/modelscope) |
| [Yi-34B 本地部署简单测试](https://blog.csdn.net/arkohut/article/details/135331469?ops_request_misc=%7B%22request%5Fid%22%3A%22171636390616800185813639%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636390616800185813639&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-10-135331469-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-05-13 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [驾辰龙跨Llama持Wasm，玩转Yi模型迎新春过大年（上）](https://blog.csdn.net/weixin_53443275/article/details/136091398?ops_request_misc=%7B%22request%5Fid%22%3A%22171636390616800185813639%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636390616800185813639&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-5-136091398-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-05-13 | [Words worth](https://blog.csdn.net/weixin_53443275?type=blog) |
| [驾辰龙跨Llama持Wasm，玩转Yi模型迎新春过大年（下篇）](https://blog.csdn.net/weixin_53443275/article/details/136096309) | 2024-05-13 | [Words worth](https://blog.csdn.net/weixin_53443275?type=blog) |
| [Ollama新增两个命令，开始支持零一万物Yi-1.5系列模型](https://mp.weixin.qq.com/s/bBgzGJvUqIohodcy9U-pFw) | 2024-05-13 | AI工程师笔记 |
| [使用零一万物 200K 模型和 Dify 快速搭建模型应用](https://zhuanlan.zhihu.com/p/686774859) | 2024-05-13 | [苏洋](https://github.com/soulteary) |
| [(持更) 零一万物模型折腾笔记：社区 Yi-34B 微调模型使用](https://zhuanlan.zhihu.com/p/671549900) | 2024-05-13 | [苏洋](https://github.com/soulteary) |
| [Python+ERNIE-4.0-8K-Yi-34B-Chat大模型初探](https://mp.weixin.qq.com/s/WaygSfn5T8ZPB1mPdGADEQ) | 2024-05-11 | 江湖评谈 |
| [技术布道 Vue及Python调用零一万物模型和Prompt模板（通过百度千帆大模型平台）](https://blog.csdn.net/ucloud2012/article/details/137187469) | 2024-05-11 | [MumuLab](https://blog.csdn.net/ucloud2012?type=blog) |
| [多模态大模型Yi-VL-plus体验 效果很棒](https://zhuanlan.zhihu.com/p/694736111) | 2024-04-27 | [大家好我是爱因](https://www.zhihu.com/people/iamein) |
| [使用autodl服务器，两个3090显卡上运行， Yi-34B-Chat-int4模型，并使用vllm优化加速，显存占用42G，速度23 words-s](https://blog.csdn.net/freewebsys/article/details/134725765?ops_request_misc=%7B%22request%5Fid%22%3A%22171636356716800211598950%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636356716800211598950&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-9-134725765-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-04-27 | [fly-iot](https://gitee.com/fly-iot) |
| [Getting Started with Yi-1.5-9B-Chat](https://www.secondstate.io/articles/yi-1.5-9b-chat/) | 2024-04-27 | [Second State](https://github.com/second-state) |
| [基于零一万物yi-vl-plus大模型简单几步就能批量生成Anki图片笔记](https://mp.weixin.qq.com/s/_ea6g0pzzeO4WyYtuWycWQ) | 2024-04-24 | [正经人王同学](https://github.com/zjrwtx) |
| [【AI开发：语言】一、Yi-34B超大模型本地部署CPU和GPU版](https://blog.csdn.net/alarey/article/details/137769471?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-16-137769471-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-04-21 | [My的梦想已实现](https://blog.csdn.net/alarey?type=blog) |
| [【Yi-34B-Chat-Int4】使用4个2080Ti显卡11G版本，运行Yi-34B模型，5年前老显卡是支持的，可以正常运行，速度 21 words-s，vllm要求算力在7以上的显卡就可以](https://blog.csdn.net/freewebsys/article/details/134754086) | 2024-03-22 | [fly-iot](https://gitee.com/fly-iot) |
| [零一万物大模型部署+微调总结](https://blog.csdn.net/v_wus/article/details/135704126?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-18-135704126-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-22 | [v_wus](https://blog.csdn.net/v_wus?type=blog) |
| [零一万物Yi大模型vllm推理时Yi-34B或Yi-6bchat重复输出的解决方案](https://blog.csdn.net/qq_39667443/article/details/136028776?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-6-136028776-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-02 | [郝铠锋](https://blog.csdn.net/qq_39667443?type=blog) |
| [Yi-34B微调训练](https://blog.csdn.net/lsjlnd/article/details/135336984?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-12-135336984-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-02 | [lsjlnd](https://blog.csdn.net/lsjlnd?type=blog) |
| [实测零一万物Yi-VL多模态语言模型：能准确“识图吃瓜”](https://mp.weixin.qq.com/s/fu4O9XvJ03JhimsEyI-SsQ) | 2024-02-02 | [苏洋](https://github.com/soulteary) |
| [零一万物开源Yi-VL多模态大模型，魔搭社区推理&微调最佳实践来啦！](https://zhuanlan.zhihu.com/p/680098411) | 2024-01-26 | [ModelScope](https://github.com/modelscope) |
| [单卡 3 小时训练 Yi-6B 大模型 Agent：基于 Llama Factory 实战](https://zhuanlan.zhihu.com/p/678989191) | 2024-01-22 | [郑耀威](https://github.com/hiyouga) |
| [零一科技Yi-34B Chat大模型环境搭建&推理](https://blog.csdn.net/zzq1989_/article/details/135597181?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-8-135597181-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-15 | [要养家的程序员](https://blog.csdn.net/zzq1989_?type=blog) |
| [基于LLaMA Factory，单卡3小时训练专属大模型 Agent](https://blog.csdn.net/m0_59596990/article/details/135760285?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-10-135760285-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-15 | [机器学习社区](https://blog.csdn.net/m0_59596990?type=blog) |
| [双卡 3080ti 部署 Yi-34B 大模型 - Gradio + vLLM 踩坑全记录](https://blog.csdn.net/arkohut/article/details/135321242?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-10-135321242-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-02 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [【大模型部署实践-3】3个能在3090上跑起来的4bits量化Chat模型（baichuan2-13b、InternLM-20b、Yi-34b）](https://blog.csdn.net/qq_40302568/article/details/135040985?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-30-135040985-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-02 | [aq_Seabiscuit](https://blog.csdn.net/qq_40302568?type=blog) |
| [只需 24G 显存，用 vllm 跑起来 Yi-34B 中英双语大模型](https://blog.csdn.net/arkohut/article/details/135274973) | 2023-12-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [零一万物模型官方 Yi-34B 模型本地离线运行部署使用笔记（物理机和docker两种部署方式），200K 超长文本内容，34B 干翻一众 70B 模型，打榜分数那么高，这模型到底行不行？](https://blog.csdn.net/u014374009/article/details/136327696) | 2023-12-28 | [代码讲故事](https://blog.csdn.net/u014374009?type=blog) |
| [LLM - 大模型速递之 Yi-34B 入门与 LoRA 微调](https://blog.csdn.net/BIT_666/article/details/134990402) | 2023-12-18 | [BIT_666](https://bitddd.blog.csdn.net/?type=blog) |
| [通过vllm框架进行大模型推理](https://blog.csdn.net/weixin_45920955/article/details/135300561?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-13-135300561-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2023-12-18 | [土山炮](https://blog.csdn.net/weixin_45920955?type=blog) |
| [CPU 混合推理，非常见大模型量化方案：“二三五六” 位量化方案](https://zhuanlan.zhihu.com/p/671698216) | 2023-12-12 | [苏洋](https://github.com/soulteary) |
| [零一万物模型折腾笔记：官方 Yi-34B 模型基础使用](https://zhuanlan.zhihu.com/p/671387298) | 2023-12-10 | [苏洋](https://github.com/soulteary) |
| [Running Yi-34B-Chat locally using LlamaEdge](https://www.secondstate.io/articles/yi-34b/) | 2023-11-30 | [Second State](https://github.com/second-state) |
| [本地运行零一万物 34B 大模型，使用 Llama.cpp & 21G 显存](https://zhuanlan.zhihu.com/p/668921042) | 2023-11-26 | [苏洋](https://github.com/soulteary) |
##### GitHub Project
| Deliverable | Date | Author |
| ------------------------------------------------------------ | ---------- | ------------------------------------------- |
| [yi-openai-proxy](https://github.com/soulteary/yi-openai-proxy) | 2024-05-11 | [苏洋](https://github.com/soulteary) |
| [基于零一万物 Yi 模型和 B 站构建大语言模型高质量训练数据集](https://github.com/zjrwtx/bilibiliQA_databuilder) | 2024-04-29 | [正经人王同学](https://github.com/zjrwtx) |
| [基于视频网站和零一万物大模型构建大语言模型高质量训练数据集](https://github.com/zjrwtx/VideoQA_databuilder) | 2024-04-25 | [正经人王同学](https://github.com/zjrwtx) |
| [基于零一万物yi-34b-chat-200k输入任意文章地址，点击按钮即可生成无广告或推广内容的简要笔记，并生成分享图给好友](https://github.com/zjrwtx/open_summary) | 2024-04-24 | [正经人王同学](https://github.com/zjrwtx) |
| [Food-GPT-Yi-model](https://github.com/ThisisHubert/FoodGPT-Yi-model) | 2024-04-21 | [Hubert S](https://github.com/ThisisHubert) |
##### Video tutorials
| Deliverable | Date | Author |
| ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ |
| [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-30 | [Second State](https://github.com/second-state) |
| [只需 24G 显存，用 vllm 跑起来 Yi-34B 中英双语大模型](https://www.bilibili.com/video/BV17t4y1f7Ee/) | 2023-12-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
| [Dolphin Yi 34b - Brand New Foundational Model TESTED](https://www.youtube.com/watch?v=On3Zuv27V3k&t=85s) | 2023-11-27 | [Matthew Berman](https://www.youtube.com/@matthew_berman) |
| [Yi-VL-34B 多模态大模型 - 用两张 A40 显卡跑起来](https://www.bilibili.com/video/BV1Q5411y7AG/) | 2024-01-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [4060Ti 16G显卡安装零一万物最新开源的Yi-1.5版大语言模型](https://www.bilibili.com/video/BV16i421X7Jx/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-14 | [titan909](https://space.bilibili.com/526393761) |
| [Yi-1.5: True Apache 2.0 Competitor to LLAMA-3](https://www.youtube.com/watch?v=KCDYrfWeTRc) | 2024-05-13 | [Prompt Engineering](https://www.youtube.com/@engineerprompt) |
| [Install Yi-1.5 Model Locally - Beats Llama 3 in Various Benchmarks](https://www.youtube.com/watch?v=Ba-G7Il0UkA) | 2024-05-13 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
| [how to install Ollama and run Yi 6B](https://www.youtube.com/watch?v=4Jnar7OUHqQ) | 2024-05-13 | [Ridaa Davids](https://www.youtube.com/@quantanovabusiness) |
| [地表最强混合智能AI助手：llama3_70B+Yi_34B+Qwen1.5_110B](https://www.bilibili.com/video/BV1Xm411C7V1/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-04 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
| [ChatDoc学术论文辅助--基于Yi-34B和langchain进行PDF知识库问答](https://www.bilibili.com/video/BV11i421C7B5/?spm_id_from=333.999.0.0&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-03 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
| [基于Yi-34B的领域知识问答项目演示](https://www.bilibili.com/video/BV1zZ42177ZA/?spm_id_from=333.999.0.0&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-02 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
| [使用RTX4090+GaLore算法 全参微调Yi-6B大模型](https://www.bilibili.com/video/BV1ax4y1U7Ep/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-03-24 | [小工蚂创始人](https://space.bilibili.com/478674499?spm_id_from=333.788.0.0) |
| [无内容审查NSFW大语言模型Yi-34B-Chat蒸馏版测试,RolePlay,《天龙八部》马夫人康敏,本地GPU,CPU运行](https://www.youtube.com/watch?v=VL-W0TnLCns) | 2024-03-20 | [刘悦的技术博客](https://v3u.cn/) |
| [无内容审查NSFW大语言模型整合包,Yi-34B-Chat,本地CPU运行,角色扮演潘金莲](https://www.youtube.com/watch?v=rBvbgwz3oHM) | 2024-03-16 | [刘悦的技术博客](https://v3u.cn/) |
| [量化 Yi-34B-Chat 并在单卡 RTX 4090 使用 vLLM 部署](https://www.bilibili.com/video/BV1jx421y7xj/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-03-05 | [白鸽巢](https://space.bilibili.com/138938660?spm_id_from=333.788.0.0) |
| [Yi-VL-34B（5）：使用3个3090显卡24G版本，运行Yi-VL-34B模型，支持命令行和web界面方式，理解图片的内容转换成文字](https://www.bilibili.com/video/BV1BB421z7oA/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-27 | [fly-iot](https://gitee.com/fly-iot) |
| [Win环境KoboldCpp本地部署大语言模型进行各种角色扮演游戏](https://www.bilibili.com/video/BV14J4m1e77f/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-25 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
| [无需显卡本地部署Yi-34B-Chat进行角色扮演游戏 P2](https://www.bilibili.com/video/BV19v421677y/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-23 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
| [【wails】（2）：使用go-llama.cpp 运行 yi-01-6b大模型，使用本地CPU运行，速度还可以，等待下一版本更新](https://www.bilibili.com/video/BV194421F7Fy/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-20 | [fly-iot](https://gitee.com/fly-iot) |
| [【xinference】（6）：在autodl上，使用xinference部署yi-vl-chat和qwen-vl-chat模型，可以使用openai调用成功](https://www.bilibili.com/video/BV19Z421z7cv/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-06 | [fly-iot](https://gitee.com/fly-iot) |
| [无需显卡本地部署Yi-34B-Chat进行角色扮演游戏 P1](https://www.bilibili.com/video/BV1tU421o7Co/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-05 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
| [2080Ti部署YI-34B大模型 xinference-oneapi-fastGPT本地知识库使用指南](https://www.bilibili.com/video/BV1hC411z7xu/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-30 | [小饭护法要转码](https://space.bilibili.com/39486865?spm_id_from=333.788.0.0) |
| [Best Story Writing AI Model - Install Yi 6B 200K Locally on Windows](https://www.youtube.com/watch?v=cZs2jRtl0bs) | 2024-01-22 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
| [Mac 本地运行大语言模型方法与常见问题指南（Yi 34B 模型+32 GB 内存测试）](https://www.bilibili.com/video/BV1VT4y1b7Th/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-21 | [小吴苹果机器人](https://space.bilibili.com/1732749682?spm_id_from=333.788.0.0) |
| [【Dify知识库】（11）：Dify0.4.9改造支持MySQL，成功接入yi-6b 做对话，本地使用fastchat启动，占8G显存，完成知识库配置](https://www.bilibili.com/video/BV1ia4y1y7JH/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-21 | [fly-iot](https://gitee.com/fly-iot) |
| [这位LLM先生有点暴躁,用的是YI-6B的某个量化版,#LLM #大语言模型 #暴躁老哥](https://www.youtube.com/watch?v=eahXJrdtQuc) | 2024-01-20 | [晓漫吧](https://www.youtube.com/@xiaomanba) |
| [大模型推理 NvLink 桥接器有用吗｜双卡 A6000 测试一下](https://www.bilibili.com/video/BV1AW4y1w7DC/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-17 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [大模型推理 A40 vs A6000 谁更强 - 对比 Yi-34B 的单、双卡推理性能](https://www.bilibili.com/video/BV1aK4y1z7GF/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-15 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [C-Eval 大语言模型评测基准- 用 LM Evaluation Harness + vLLM 跑起来](https://www.bilibili.com/video/BV1Yw411g7ZL/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-11 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [双显卡部署 Yi-34B 大模型 - vLLM + Gradio 踩坑记录](https://www.bilibili.com/video/BV1p94y1c7ak/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-01 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [手把手教学！使用 vLLM 快速部署 Yi-34B-Chat](https://www.bilibili.com/video/BV1ew41157Mk/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-26 | [白鸽巢](https://space.bilibili.com/138938660?spm_id_from=333.788.0.0) |
| [如何训练企业自己的大语言模型？Yi-6B LORA微调演示 #小工蚁](https://www.bilibili.com/video/BV1uc41117zz/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-21 | [小工蚂创始人](https://space.bilibili.com/478674499?spm_id_from=333.788.0.0) |
| [Yi-34B（4）：使用4个2080Ti显卡11G版本，运行Yi-34B模型，5年前老显卡是支持的，可以正常运行，速度 21 words/s](https://www.bilibili.com/video/BV1nj41157L3/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-02 | [fly-iot](https://gitee.com/fly-iot) |
| [使用autodl服务器，RTX 3090 * 3 显卡上运行， Yi-34B-Chat模型，显存占用60G](https://www.bilibili.com/video/BV1BM411R7ae/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [fly-iot](https://gitee.com/fly-iot) |
| [使用autodl服务器，两个3090显卡上运行， Yi-34B-Chat-int4模型，用vllm优化，增加 --num-gpu 2，速度23 words/s](https://www.bilibili.com/video/BV1Hu4y1L7BH/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [fly-iot](https://gitee.com/fly-iot) |
| [Yi大模型一键本地部署 技术小白玩转AI](https://www.bilibili.com/video/BV16H4y117md/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [技术小白玩转AI](https://space.bilibili.com/3546586137234288?spm_id_from=333.788.0.0) |
| [01.AI's Yi-6B: Overview and Fine-Tuning](https://www.youtube.com/watch?v=mye-UOkAliQ) | 2023-11-28 | [AI Makerspace](https://www.youtube.com/@AI-Makerspace) |
| [Yi 34B Chat LLM outperforms Llama 70B](https://www.youtube.com/watch?v=RYtrF-R5jDc) | 2023-11-27 | [DLExplorer](https://www.youtube.com/@DLExplorers-lg7dt) |
| [How to run open source models on mac Yi 34b on m3 Max](https://www.youtube.com/watch?v=GAo-dopkgjI) | 2023-11-26 | [TECHNO PREMIUM](https://www.youtube.com/@technopremium91) |
| [Yi-34B - 200K - The BEST & NEW CONTEXT WINDOW KING ](https://www.youtube.com/watch?v=7WBojwwv5Qo) | 2023-11-24 | [Prompt Engineering](https://www.youtube.com/@engineerprompt) |
| [Yi 34B : The Rise of Powerful Mid-Sized Models - Base,200k & Chat](https://www.youtube.com/watch?v=bWCjwtu_tHs) | 2023-11-24 | [Sam Witteveen](https://www.youtube.com/@samwitteveenai) |
| [在IoT设备运行破解版李开复大模型dolphin-2.2-yi-34b（还可作为私有OpenAI API服务器）](https://www.bilibili.com/video/BV1SQ4y18744/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-11-15 | [Second State](https://github.com/second-state) |
| [Run dolphin-2.2-yi-34b on IoT Devices (Also works as a Private OpenAI API Server)](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-14 | [Second State](https://github.com/second-state) |
| [How to Install Yi 34B 200K Llamafied on Windows Laptop](https://www.youtube.com/watch?v=enoha4K4HkQ) | 2023-11-11 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
</details>
# Why Yi?
- [Ecosystem](#ecosystem)
- [Upstream](#upstream)
- [Downstream](#downstream)
- [Serving](#serving)
- [Quantization](#quantization-1)
- [Fine-tuning](#fine-tuning-1)
- [API](#api)
- [Benchmarks](#benchmarks)
- [Chat model performance](#chat-model-performance)
- [Base model performance](#base-model-performance)
- [Yi-34B and Yi-34B-200K](#yi-34b-and-yi-34b-200k)
- [Yi-9B](#yi-9b)
## Ecosystem
Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity.
- [Upstream](#upstream)
- [Downstream](#downstream)
- [Serving](#serving)
- [Quantization](#quantization-1)
- [Fine-tuning](#fine-tuning-1)
- [API](#api)
### Upstream
The Yi series models follow the same model architecture as Llama. By choosing Yi, you can leverage existing tools, libraries, and resources within the Llama ecosystem, eliminating the need to create new tools and enhancing development efficiency.
For example, the Yi series models are saved in the format of the Llama model. You can directly use `LlamaForCausalLM` and `LlamaTokenizer` to load the model. For more information, see [Use the chat model](#31-use-the-chat-model).
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34b", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34b", device_map="auto")
```
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Downstream
> 💡 Tip
>
> - Feel free to create a PR and share the fantastic work you've built using the Yi series models.
>
> - To help others quickly understand your work, it is recommended to use the format of `<model-name>: <model-intro> + <model-highlights>`.
#### Serving
If you want to get up with Yi in a few minutes, you can use the following services built upon Yi.
- Yi-34B-Chat: you can chat with Yi using one of the following platforms:
- [Yi-34B-Chat | Hugging Face](https://huggingface.co/spaces/01-ai/Yi-34B-Chat)
- [Yi-34B-Chat | Yi Platform](https://platform.lingyiwanwu.com/): **Note** that currently it's available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)) and experience it firsthand!
- [Yi-6B-Chat (Replicate)](https://replicate.com/01-ai): you can use this model with more options by setting additional parameters and calling APIs.
- [ScaleLLM](https://github.com/vectorch-ai/ScaleLLM#supported-models): you can use this service to run Yi models locally with added flexibility and customization.
#### Quantization
If you have limited computational capabilities, you can use Yi's quantized models as follows.
These quantized models have reduced precision but offer increased efficiency, such as faster inference speed and smaller RAM usage.
- [TheBloke/Yi-34B-GPTQ](https://huggingface.co/TheBloke/Yi-34B-GPTQ)
- [TheBloke/Yi-34B-GGUF](https://huggingface.co/TheBloke/Yi-34B-GGUF)
- [TheBloke/Yi-34B-AWQ](https://huggingface.co/TheBloke/Yi-34B-AWQ)
#### Fine-tuning
If you're seeking to explore the diverse capabilities within Yi's thriving family, you can delve into Yi's fine-tuned models as below.
- [TheBloke Models](https://huggingface.co/TheBloke): this site hosts numerous fine-tuned models derived from various LLMs including Yi.
This is not an exhaustive list for Yi, but to name a few sorted on downloads:
- [TheBloke/dolphin-2_2-yi-34b-AWQ](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-AWQ)
- [TheBloke/Yi-34B-Chat-AWQ](https://huggingface.co/TheBloke/Yi-34B-Chat-AWQ)
- [TheBloke/Yi-34B-Chat-GPTQ](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ)
- [SUSTech/SUS-Chat-34B](https://huggingface.co/SUSTech/SUS-Chat-34B): this model ranked first among all models below 70B and outperformed the twice larger deepseek-llm-67b-chat. You can check the result on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
- [OrionStarAI/OrionStar-Yi-34B-Chat-Llama](https://huggingface.co/OrionStarAI/OrionStar-Yi-34B-Chat-Llama): this model excelled beyond other models (such as GPT-4, Qwen-14B-Chat, Baichuan2-13B-Chat) in C-Eval and CMMLU evaluations on the [OpenCompass LLM Leaderboard](https://opencompass.org.cn/leaderboard-llm).
- [NousResearch/Nous-Capybara-34B](https://huggingface.co/NousResearch/Nous-Capybara-34B): this model is trained with 200K context length and 3 epochs on the Capybara dataset.
#### API
- [amazing-openai-api](https://github.com/soulteary/amazing-openai-api): this tool converts Yi model APIs into the OpenAI API format out of the box.
- [LlamaEdge](https://www.secondstate.io/articles/yi-34b/#create-an-openai-compatible-api-service-for-the-yi-34b-chat-model): this tool builds an OpenAI-compatible API server for Yi-34B-Chat using a portable Wasm (WebAssembly) file, powered by Rust.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
## Tech report
For detailed capabilities of the Yi series model, see [Yi: Open Foundation Models by 01.AI](https://arxiv.org/abs/2403.04652).
### Citation
```
@misc{ai2024yi,
title={Yi: Open Foundation Models by 01.AI},
author={01. AI and : and Alex Young and Bei Chen and Chao Li and Chengen Huang and Ge Zhang and Guanwei Zhang and Heng Li and Jiangcheng Zhu and Jianqun Chen and Jing Chang and Kaidong Yu and Peng Liu and Qiang Liu and Shawn Yue and Senbin Yang and Shiming Yang and Tao Yu and Wen Xie and Wenhao Huang and Xiaohui Hu and Xiaoyi Ren and Xinyao Niu and Pengcheng Nie and Yuchi Xu and Yudong Liu and Yue Wang and Yuxuan Cai and Zhenyu Gu and Zhiyuan Liu and Zonghong Dai},
year={2024},
eprint={2403.04652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## Benchmarks
- [Chat model performance](#chat-model-performance)
- [Base model performance](#base-model-performance)
### Chat model performance
Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more.
<details>
<summary> Evaluation methods and challenges. ⬇️ </summary>
- **Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA.
- **Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed.
- **Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text.
- **Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results.
<strong>*</strong>: C-Eval results are evaluated on the validation datasets
</details>
### Base model performance
#### Yi-34B and Yi-34B-200K
The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMMLU, common-sense reasoning, reading comprehension, and more.
<details>
<summary> Evaluation methods. ⬇️</summary>
- **Disparity in results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass.
- **Investigation findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences.
- **Uniform benchmarking process**: our methodology aligns with the original benchmarks—consistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content.
- **Efforts to retrieve unreported scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline.
- **Extensive model evaluation**: to evaluate the model’s capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension.
- **Special configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code".
- **Falcon-180B caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated.
</details>
#### Yi-9B
Yi-9B is almost the best among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension.
- In terms of **overall** ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B.
- In terms of **coding** ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B.
- In terms of **math** ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B.
- In terms of **common sense and reasoning** ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
# Who can use Yi?
Everyone! 🙌 ✅
The code and weights of the Yi series models are distributed under the [Apache 2.0 license](https://github.com/01-ai/Yi/blob/main/LICENSE), which means the Yi series models are free for personal usage, academic purposes, and commercial use.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
# Misc.
### Acknowledgments
A heartfelt thank you to each of you who have made contributions to the Yi community! You have helped Yi not just a project, but a vibrant, growing home for innovation.
[](https://github.com/01-ai/yi/graphs/contributors)
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Disclaimer
We use data compliance checking algorithms during the training process, to
ensure the compliance of the trained model to the best of our ability. Due to
complex data and the diversity of language model usage scenarios, we cannot
guarantee that the model will generate correct, and reasonable output in all
scenarios. Please be aware that there is still a risk of the model producing
problematic outputs. We will not be responsible for any risks and issues
resulting from misuse, misguidance, illegal usage, and related misinformation,
as well as any associated data security concerns.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### License
The code and weights of the Yi-1.5 series models are distributed under the [Apache 2.0 license](https://github.com/01-ai/Yi/blob/main/LICENSE).
If you create derivative works based on this model, please include the following attribution in your derivative works:
This work is a derivative of [The Yi Series Model You Base On] by 01.AI, used under the Apache 2.0 License.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
| null |
Non_BioNLP
|
<div align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_dark.svg" width="200px">
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="200px">
<img alt="specify theme context for images" src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg">
</picture>
</br>
</br>
<div style="display: inline-block;">
<a href="https://github.com/01-ai/Yi/actions/workflows/build_docker_image.yml">
<img src="https://github.com/01-ai/Yi/actions/workflows/build_docker_image.yml/badge.svg">
</a>
</div>
<div style="display: inline-block;">
<a href="mailto:[email protected]">
<img src="https://img.shields.io/badge/✉️[email protected]">
</a>
</div>
</div>
<div align="center">
<h3 align="center">Building the Next Generation of Open-Source and Bilingual LLMs</h3>
</div>
<p align="center">
🤗 <a href="https://huggingface.co/01-ai" target="_blank">Hugging Face</a> • 🤖 <a href="https://www.modelscope.cn/organization/01ai/" target="_blank">ModelScope</a> • ✡️ <a href="https://wisemodel.cn/organization/01.AI" target="_blank">WiseModel</a>
</p>
<p align="center">
👩🚀 Ask questions or discuss ideas on <a href="https://github.com/01-ai/Yi/discussions" target="_blank"> GitHub </a>
</p>
<p align="center">
👋 Join us on <a href="https://discord.gg/hYUwWddeAu" target="_blank"> 👾 Discord </a> or <a href="有官方的微信群嘛 · Issue #43 · 01-ai/Yi" target="_blank"> 💬 WeChat </a>
</p>
<p align="center">
📝 Check out <a href="https://arxiv.org/abs/2403.04652"> Yi Tech Report </a>
</p>
<p align="center">
📚 Grow at <a href="#learning-hub"> Yi Learning Hub </a>
</p>
<!-- DO NOT REMOVE ME -->
<hr>
<details open>
<summary></b>📕 Table of Contents</b></summary>
- [What is Yi?](#what-is-yi)
- [Introduction](#introduction)
- [Models](#models)
- [Chat models](#chat-models)
- [Base models](#base-models)
- [Model info](#model-info)
- [News](#news)
- [How to use Yi?](#how-to-use-yi)
- [Quick start](#quick-start)
- [Choose your path](#choose-your-path)
- [pip](#quick-start---pip)
- [docker](#quick-start---docker)
- [llama.cpp](#quick-start---llamacpp)
- [conda-lock](#quick-start---conda-lock)
- [Web demo](#web-demo)
- [Fine-tuning](#fine-tuning)
- [Quantization](#quantization)
- [Deployment](#deployment)
- [FAQ](#faq)
- [Learning hub](#learning-hub)
- [Why Yi?](#why-yi)
- [Ecosystem](#ecosystem)
- [Upstream](#upstream)
- [Downstream](#downstream)
- [Serving](#serving)
- [Quantization](#quantization-1)
- [Fine-tuning](#fine-tuning-1)
- [API](#api)
- [Benchmarks](#benchmarks)
- [Base model performance](#base-model-performance)
- [Chat model performance](#chat-model-performance)
- [Tech report](#tech-report)
- [Citation](#citation)
- [Who can use Yi?](#who-can-use-yi)
- [Misc.](#misc)
- [Acknowledgements](#acknowledgments)
- [Disclaimer](#disclaimer)
- [License](#license)
</details>
<hr>
# What is Yi?
## Introduction
- 🤖 The Yi series models are the next generation of open-source large language models trained from scratch by [01.AI](https://01.ai/).
- 🙌 Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example,
- Yi-34B-Chat model **landed in second place (following GPT-4 Turbo)**, outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024).
- Yi-34B model **ranked first among all existing open-source models** (such as Falcon-180B, Llama-70B, Claude) in **both English and Chinese** on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023).
- 🙏 (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem.
<details style="display: inline;"><summary> If you're interested in Yi's adoption of Llama architecture and license usage policy, see <span style="color: green;">Yi's relation with Llama.</span> ⬇️</summary> <ul> <br>
> 💡 TL;DR
>
> The Yi series models adopt the same model architecture as Llama but are **NOT** derivatives of Llama.
- Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018.
- Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi.
- Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems.
- However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights.
- As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure.
- Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the [Alpaca Leaderboard in Dec 2023](https://tatsu-lab.github.io/alpaca_eval/).
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
## News
<details>
<summary>🔥 <b>2024-07-29</b>: The <a href="https://github.com/Haijian06/Yi/tree/main/Cookbook">Yi Cookbook 1.0 </a> is released, featuring tutorials and examples in both Chinese and English.</summary>
</details>
<details>
<summary>🎯 <b>2024-05-13</b>: The <a href="https://github.com/01-ai/Yi-1.5">Yi-1.5 series models </a> are open-sourced, further improving coding, math, reasoning, and instruction-following abilities.</summary>
</details>
<details>
<summary>🎯 <b>2024-03-16</b>: The <code>Yi-9B-200K</code> is open-sourced and available to the public.</summary>
</details>
<details>
<summary>🎯 <b>2024-03-08</b>: <a href="https://arxiv.org/abs/2403.04652">Yi Tech Report</a> is published! </summary>
</details>
<details open>
<summary>🔔 <b>2024-03-07</b>: The long text capability of the Yi-34B-200K has been enhanced. </summary>
<br>
In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance.
</details>
<details open>
<summary>🎯 <b>2024-03-06</b>: The <code>Yi-9B</code> is open-sourced and available to the public.</summary>
<br>
<code>Yi-9B</code> stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension.
</details>
<details open>
<summary>🎯 <b>2024-01-23</b>: The Yi-VL models, <code><a href="https://huggingface.co/01-ai/Yi-VL-34B">Yi-VL-34B</a></code> and <code><a href="https://huggingface.co/01-ai/Yi-VL-6B">Yi-VL-6B</a></code>, are open-sourced and available to the public.</summary>
<br>
<code><a href="https://huggingface.co/01-ai/Yi-VL-34B">Yi-VL-34B</a></code> has ranked <strong>first</strong> among all existing open-source models in the latest benchmarks, including <a href="https://arxiv.org/abs/2311.16502">MMMU</a> and <a href="https://arxiv.org/abs/2401.11944">CMMMU</a> (based on data available up to January 2024).</li>
</details>
<details>
<summary>🎯 <b>2023-11-23</b>: <a href="#chat-models">Chat models</a> are open-sourced and available to the public.</summary>
<br>This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ.
- `Yi-34B-Chat`
- `Yi-34B-Chat-4bits`
- `Yi-34B-Chat-8bits`
- `Yi-6B-Chat`
- `Yi-6B-Chat-4bits`
- `Yi-6B-Chat-8bits`
You can try some of them interactively at:
- [Hugging Face](https://huggingface.co/spaces/01-ai/Yi-34B-Chat)
- [Replicate](https://replicate.com/01-ai)
</details>
<details>
<summary>🔔 <b>2023-11-23</b>: The Yi Series Models Community License Agreement is updated to <a href="https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt">v2.1</a>.</summary>
</details>
<details>
<summary>🔥 <b>2023-11-08</b>: Invited test of Yi-34B chat model.</summary>
<br>Application form:
- [English](https://cn.mikecrm.com/l91ODJf)
- [Chinese](https://cn.mikecrm.com/gnEZjiQ)
</details>
<details>
<summary>🎯 <b>2023-11-05</b>: <a href="#base-models">The base models, </a><code>Yi-6B-200K</code> and <code>Yi-34B-200K</code>, are open-sourced and available to the public.</summary>
<br>This release contains two base models with the same parameter sizes as the previous
release, except that the context window is extended to 200K.
</details>
<details>
<summary>🎯 <b>2023-11-02</b>: <a href="#base-models">The base models, </a><code>Yi-6B</code> and <code>Yi-34B</code>, are open-sourced and available to the public.</summary>
<br>The first public release contains two bilingual (English/Chinese) base models
with the parameter sizes of 6B and 34B. Both of them are trained with 4K
sequence length and can be extended to 32K during inference time.
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
## Models
Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements.
If you want to deploy Yi models, make sure you meet the [software and hardware requirements](#deployment).
### Chat models
| Model | Download |
|---|---|
|Yi-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-34B-Chat) |
|Yi-34B-Chat-4bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-4bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-4bits/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-34B-Chat-4bits) |
|Yi-34B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-8bits/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-34B-Chat-8bits) |
|Yi-6B-Chat| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat) |
|Yi-6B-Chat-4bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-4bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-4bits/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-4bits) |
|Yi-6B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-8bits/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
<sub><sup> - 4-bit series models are quantized by AWQ. <br> - 8-bit series models are quantized by GPTQ <br> - All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). </sup></sub>
### Base models
| Model | Download |
|---|---|
|Yi-34B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
|Yi-34B-200K|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-200K/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits)|
|Yi-9B|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-9B) • [🤖 ModelScope](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-9B)|
|Yi-9B-200K | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-9B-200K) • [🤖 ModelScope](https://wisemodel.cn/models/01.AI/Yi-9B-200K) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
|Yi-6B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
|Yi-6B-200K | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-200K/summary) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-6B-Chat-8bits) |
<sub><sup> - 200k is roughly equivalent to 400,000 Chinese characters. <br> - If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run `git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf` to download the weight. </sup></sub>
### Model info
- For chat and base models
<table>
<thead>
<tr>
<th>Model</th>
<th>Intro</th>
<th>Default context window</th>
<th>Pretrained tokens</th>
<th>Training Data Date</th>
</tr>
</thead>
<tbody><tr>
<td>6B series models</td>
<td>They are suitable for personal and academic use.</td>
<td rowspan="3">4K</td>
<td>3T</td>
<td rowspan="3">Up to June 2023</td>
</tr>
<tr>
<td>9B series models</td>
<td>It is the best at coding and math in the Yi series models.</td>
<td>Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens.</td>
</tr>
<tr>
<td>34B series models</td>
<td>They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability.</td>
<td>3T</td>
</tr>
</tbody></table>
- For chat models
<details style="display: inline;"><summary>For chat model limitations, see the explanations below. ⬇️</summary>
<ul>
<br>The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training.
<br>However, this higher diversity might amplify certain existing issues, including:
<li>Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning.</li>
<li>Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions.</li>
<li>Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc.</li>
<li>To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top_p, or top_k. These adjustments can help in the balance between creativity and coherence in the model's outputs.</li>
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
# How to use Yi?
- [Quick start](#quick-start)
- [Choose your path](#choose-your-path)
- [pip](#quick-start---pip)
- [docker](#quick-start---docker)
- [conda-lock](#quick-start---conda-lock)
- [llama.cpp](#quick-start---llamacpp)
- [Web demo](#web-demo)
- [Fine-tuning](#fine-tuning)
- [Quantization](#quantization)
- [Deployment](#deployment)
- [FAQ](#faq)
- [Learning hub](#learning-hub)
## Quick start
> **💡 Tip**: If you want to get started with the Yi model and explore different methods for inference, check out the [Yi Cookbook](https://github.com/01-ai/Yi/tree/main/Cookbook).
### Choose your path
Select one of the following paths to begin your journey with Yi!
#### 🎯 Deploy Yi locally
If you prefer to deploy Yi models locally,
- 🙋♀️ and you have **sufficient** resources (for example, NVIDIA A800 80GB), you can choose one of the following methods:
- [pip](#quick-start---pip)
- [Docker](#quick-start---docker)
- [conda-lock](#quick-start---conda-lock)
- 🙋♀️ and you have **limited** resources (for example, a MacBook Pro), you can use [llama.cpp](#quick-start---llamacpp).
#### 🎯 Not to deploy Yi locally
If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options.
##### 🙋♀️ Run Yi with APIs
If you want to explore more features of Yi, you can adopt one of these methods:
- Yi APIs (Yi official)
- [Early access has been granted](https://x.com/01AI_Yi/status/1735728934560600536?s=20) to some applicants. Stay tuned for the next round of access!
- [Yi APIs](https://replicate.com/01-ai/yi-34b-chat/api?tab=nodejs) (Replicate)
##### 🙋♀️ Run Yi in playground
If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options:
- [Yi-34B-Chat-Playground](https://platform.lingyiwanwu.com/prompt/playground) (Yi official)
- Access is available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)).
- [Yi-34B-Chat-Playground](https://replicate.com/01-ai/yi-34b-chat) (Replicate)
##### 🙋♀️ Chat with Yi
If you want to chat with Yi, you can use one of these online services, which offer a similar user experience:
- [Yi-34B-Chat](https://huggingface.co/spaces/01-ai/Yi-34B-Chat) (Yi official on Hugging Face)
- No registration is required.
- [Yi-34B-Chat](https://platform.lingyiwanwu.com/) (Yi official beta)
- Access is available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)).
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Quick start - pip
This tutorial guides you through every step of running **Yi-34B-Chat locally on an A800 (80G)** and then performing inference.
#### Step 0: Prerequisites
- Make sure Python 3.10 or a later version is installed.
- If you want to run other Yi models, see [software and hardware requirements](#deployment).
#### Step 1: Prepare your environment
To set up the environment and install the required packages, execute the following command.
```bash
git clone https://github.com/01-ai/Yi.git
cd yi
pip install -r requirements.txt
```
#### Step 2: Download the Yi model
You can download the weights and tokenizer of Yi models from the following sources:
- [Hugging Face](https://huggingface.co/01-ai)
- [ModelScope](https://www.modelscope.cn/organization/01ai/)
- [WiseModel](https://wisemodel.cn/organization/01.AI)
#### Step 3: Perform inference
You can perform inference with Yi chat or base models as below.
##### Perform inference with Yi chat model
1. Create a file named `quick_start.py` and copy the following content to it.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = '<your-model-path>'
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
# Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM.
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
```
2. Run `quick_start.py`.
```bash
python quick_start.py
```
Then you can see an output similar to the one below. 🥳
```bash
Hello! How can I assist you today?
```
##### Perform inference with Yi base model
- Yi-34B
The steps are similar to [pip - Perform inference with Yi chat model](#perform-inference-with-yi-chat-model).
You can use the existing file [`text_generation.py`](https://github.com/01-ai/Yi/tree/main/demo).
```bash
python demo/text_generation.py --model <your-model-path>
```
Then you can see an output similar to the one below. 🥳
<details>
<summary>Output. ⬇️ </summary>
<br>
**Prompt**: Let me tell you an interesting story about cat Tom and mouse Jerry,
**Generation**: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldn’t get up because there were too many people around him! He kept trying for several minutes before finally giving up...
</details>
- Yi-9B
Input
```bash
from transformers import AutoModelForCausalLM, AutoTokenizer
MODEL_DIR = "01-ai/Yi-9B"
model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False)
input_text = "# write the quick sort algorithm"
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
Output
```bash
# write the quick sort algorithm
def quick_sort(arr):
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quick_sort(left) + middle + quick_sort(right)
# test the quick sort algorithm
print(quick_sort([3, 6, 8, 10, 1, 2, 1]))
```
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Quick start - Docker
<details>
<summary> Run Yi-34B-chat locally with Docker: a step-by-step guide. ⬇️</summary>
<br>This tutorial guides you through every step of running <strong>Yi-34B-Chat on an A800 GPU</strong> or <strong>4*4090</strong> locally and then performing inference.
<h4>Step 0: Prerequisites</h4>
<p>Make sure you've installed <a href="https://docs.docker.com/engine/install/?open_in_browser=true">Docker</a> and <a href="https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html">nvidia-container-toolkit</a>.</p>
<h4> Step 1: Start Docker </h4>
<pre><code>docker run -it --gpus all \
-v <your-model-path>: /models
ghcr.io/01-ai/yi:latest
</code></pre>
<p>Alternatively, you can pull the Yi Docker image from <code>registry.lingyiwanwu.com/ci/01-ai/yi:latest</code>.</p>
<h4>Step 2: Perform inference</h4>
<p>You can perform inference with Yi chat or base models as below.</p>
<h5>Perform inference with Yi chat model</h5>
<p>The steps are similar to <a href="#perform-inference-with-yi-chat-model">pip - Perform inference with Yi chat model</a>.</p>
<p><strong>Note</strong> that the only difference is to set <code>model_path = '<your-model-mount-path>'</code> instead of <code>model_path = '<your-model-path>'</code>.</p>
<h5>Perform inference with Yi base model</h5>
<p>The steps are similar to <a href="#perform-inference-with-yi-base-model">pip - Perform inference with Yi base model</a>.</p>
<p><strong>Note</strong> that the only difference is to set <code>--model <your-model-mount-path>'</code> instead of <code>model <your-model-path></code>.</p>
</details>
### Quick start - conda-lock
<details>
<summary>You can use <code><a href="https://github.com/conda/conda-lock">conda-lock</a></code> to generate fully reproducible lock files for conda environments. ⬇️</summary>
<br>
You can refer to <a href="https://github.com/01-ai/Yi/blob/ebba23451d780f35e74a780987ad377553134f68/conda-lock.yml">conda-lock.yml</a> for the exact versions of the dependencies. Additionally, you can utilize <code><a href="https://mamba.readthedocs.io/en/latest/user_guide/micromamba.html">micromamba</a></code> for installing these dependencies.
<br>
To install the dependencies, follow these steps:
1. Install micromamba by following the instructions available <a href="https://mamba.readthedocs.io/en/latest/installation/micromamba-installation.html">here</a>.
2. Execute <code>micromamba install -y -n yi -f conda-lock.yml</code> to create a conda environment named <code>yi</code> and install the necessary dependencies.
</details>
### Quick start - llama.cpp
<a href="https://github.com/01-ai/Yi/blob/main/docs/README_llama.cpp.md">The following tutorial </a> will guide you through every step of running a quantized model (<a href="https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main">Yi-chat-6B-2bits</a>) locally and then performing inference.
<details>
<summary> Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. ⬇️</summary>
<br><a href="https://github.com/01-ai/Yi/blob/main/docs/README_llama.cpp.md">This tutorial</a> guides you through every step of running a quantized model (<a href="https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main">Yi-chat-6B-2bits</a>) locally and then performing inference.</p>
- [Step 0: Prerequisites](#step-0-prerequisites)
- [Step 1: Download llama.cpp](#step-1-download-llamacpp)
- [Step 2: Download Yi model](#step-2-download-yi-model)
- [Step 3: Perform inference](#step-3-perform-inference)
#### Step 0: Prerequisites
- This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip.
- Make sure [`git-lfs`](https://git-lfs.com/) is installed on your machine.
#### Step 1: Download `llama.cpp`
To clone the [`llama.cpp`](https://github.com/ggerganov/llama.cpp) repository, run the following command.
```bash
git clone [email protected]:ggerganov/llama.cpp.git
```
#### Step 2: Download Yi model
2.1 To clone [XeIaso/yi-chat-6B-GGUF](https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main) with just pointers, run the following command.
```bash
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF
```
2.2 To download a quantized Yi model ([yi-chat-6b.Q2_K.gguf](https://huggingface.co/XeIaso/yi-chat-6B-GGUF/blob/main/yi-chat-6b.Q2_K.gguf)), run the following command.
```bash
git-lfs pull --include yi-chat-6b.Q2_K.gguf
```
#### Step 3: Perform inference
To perform inference with the Yi model, you can use one of the following methods.
- [Method 1: Perform inference in terminal](#method-1-perform-inference-in-terminal)
- [Method 2: Perform inference in web](#method-2-perform-inference-in-web)
##### Method 1: Perform inference in terminal
To compile `llama.cpp` using 4 threads and then conduct inference, navigate to the `llama.cpp` directory, and run the following command.
> ##### Tips
>
> - Replace `/Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf` with the actual path of your model.
>
> - By default, the model operates in completion mode.
>
> - For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run `./main -h` to check detailed descriptions and usage.
```bash
make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e
...
How do you feed your pet fox? Please answer this question in 6 simple steps:
Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables.
Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day.
Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise.
Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress.
Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections.
Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care.
...
```
Now you have successfully asked a question to the Yi model and got an answer! 🥳
##### Method 2: Perform inference in web
1. To initialize a lightweight and swift chatbot, run the following command.
```bash
cd llama.cpp
./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf
```
Then you can get an output like this:
```bash
...
llama_new_context_with_model: n_ctx = 2048
llama_new_context_with_model: freq_base = 5000000.0
llama_new_context_with_model: freq_scale = 1
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M2 Pro
ggml_metal_init: picking default device: Apple M2 Pro
ggml_metal_init: ggml.metallib not found, loading from source
ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil
ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal'
ggml_metal_init: GPU name: Apple M2 Pro
ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008)
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB
ggml_metal_init: maxTransferRate = built-in GPU
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67)
llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67)
llama_build_graph: non-view tensors processed: 676/676
llama_new_context_with_model: compute buffer total size = 159.19 MiB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67)
Available slots:
-> Slot 0 - max context: 2048
llama server listening at http://0.0.0.0:8080
```
2. To access the chatbot interface, open your web browser and enter `http://0.0.0.0:8080` into the address bar.
3. Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer.
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Web demo
You can build a web UI demo for Yi **chat** models (note that Yi base models are not supported in this senario).
[Step 1: Prepare your environment](#step-1-prepare-your-environment).
[Step 2: Download the Yi model](#step-2-download-the-yi-model).
Step 3. To start a web service locally, run the following command.
```bash
python demo/web_demo.py -c <your-model-path>
```
You can access the web UI by entering the address provided in the console into your browser.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Fine-tuning
```bash
bash finetune/scripts/run_sft_Yi_6b.sh
```
Once finished, you can compare the finetuned model and the base model with the following command:
```bash
bash finetune/scripts/run_eval.sh
```
<details style="display: inline;"><summary>For advanced usage (like fine-tuning based on your custom data), see the explanations below. ⬇️ </summary> <ul>
### Finetune code for Yi 6B and 34B
#### Preparation
##### From Image
By default, we use a small dataset from [BAAI/COIG](https://huggingface.co/datasets/BAAI/COIG) to finetune the base model.
You can also prepare your customized dataset in the following `jsonl` format:
```json
{ "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." }
```
And then mount them in the container to replace the default ones:
```bash
docker run -it \
-v /path/to/save/finetuned/model/:/finetuned-model \
-v /path/to/train.jsonl:/yi/finetune/data/train.json \
-v /path/to/eval.jsonl:/yi/finetune/data/eval.json \
ghcr.io/01-ai/yi:latest \
bash finetune/scripts/run_sft_Yi_6b.sh
```
##### From Local Server
Make sure you have conda. If not, use
```bash
mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm -rf ~/miniconda3/miniconda.sh
~/miniconda3/bin/conda init bash
source ~/.bashrc
```
Then, create a conda env:
```bash
conda create -n dev_env python=3.10 -y
conda activate dev_env
pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7
```
#### Hardware Setup
For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended.
For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA_VISIBLE_DEVICES to limit the number of GPUs (as shown in scripts/run_sft_Yi_34b.sh).
A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA_VISIBLE_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB.
#### Quick Start
Download a LLM-base model to MODEL_PATH (6B and 34B). A typical folder of models is like:
```bash
|-- $MODEL_PATH
| |-- config.json
| |-- pytorch_model-00001-of-00002.bin
| |-- pytorch_model-00002-of-00002.bin
| |-- pytorch_model.bin.index.json
| |-- tokenizer_config.json
| |-- tokenizer.model
| |-- ...
```
Download a dataset from huggingface to local storage DATA_PATH, e.g. Dahoas/rm-static.
```bash
|-- $DATA_PATH
| |-- data
| | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet
| | |-- test-00000-of-00001-8c7c51afc6d45980.parquet
| |-- dataset_infos.json
| |-- README.md
```
`finetune/yi_example_dataset` has example datasets, which are modified from [BAAI/COIG](https://huggingface.co/datasets/BAAI/COIG)
```bash
|-- $DATA_PATH
|--data
|-- train.jsonl
|-- eval.jsonl
```
`cd` into the scripts folder, copy and paste the script, and run. For example:
```bash
cd finetune/scripts
bash run_sft_Yi_6b.sh
```
For the Yi-6B base model, setting training_debug_steps=20 and num_train_epochs=4 can output a chat model, which takes about 20 minutes.
For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient.
#### Evaluation
```bash
cd finetune/scripts
bash run_eval.sh
```
Then you'll see the answer from both the base model and the finetuned model.
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Quantization
#### GPT-Q
```bash
python quantization/gptq/quant_autogptq.py \
--model /base_model \
--output_dir /quantized_model \
--trust_remote_code
```
Once finished, you can then evaluate the resulting model as follows:
```bash
python quantization/gptq/eval_quantized_model.py \
--model /quantized_model \
--trust_remote_code
```
<details style="display: inline;"><summary>For details, see the explanations below. ⬇️</summary> <ul>
#### GPT-Q quantization
[GPT-Q](https://github.com/IST-DASLab/gptq) is a PTQ (Post-Training Quantization)
method. It saves memory and provides potential speedups while retaining the accuracy
of the model.
Yi models can be GPT-Q quantized without a lot of efforts.
We provide a step-by-step tutorial below.
To run GPT-Q, we will use [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) and
[exllama](https://github.com/turboderp/exllama).
And the huggingface transformers has integrated optimum and auto-gptq to perform
GPTQ quantization on language models.
##### Do Quantization
The `quant_autogptq.py` script is provided for you to perform GPT-Q quantization:
```bash
python quant_autogptq.py --model /base_model \
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
```
##### Run Quantized Model
You can run a quantized model using the `eval_quantized_model.py`:
```bash
python eval_quantized_model.py --model /quantized_model --trust_remote_code
```
</ul>
</details>
#### AWQ
```bash
python quantization/awq/quant_autoawq.py \
--model /base_model \
--output_dir /quantized_model \
--trust_remote_code
```
Once finished, you can then evaluate the resulting model as follows:
```bash
python quantization/awq/eval_quantized_model.py \
--model /quantized_model \
--trust_remote_code
```
<details style="display: inline;"><summary>For details, see the explanations below. ⬇️</summary> <ul>
#### AWQ quantization
[AWQ](https://github.com/mit-han-lab/llm-awq) is a PTQ (Post-Training Quantization)
method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs.
Yi models can be AWQ quantized without a lot of efforts.
We provide a step-by-step tutorial below.
To run AWQ, we will use [AutoAWQ](https://github.com/casper-hansen/AutoAWQ).
##### Do Quantization
The `quant_autoawq.py` script is provided for you to perform AWQ quantization:
```bash
python quant_autoawq.py --model /base_model \
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
```
##### Run Quantized Model
You can run a quantized model using the `eval_quantized_model.py`:
```bash
python eval_quantized_model.py --model /quantized_model --trust_remote_code
```
</ul>
</details>
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Deployment
If you want to deploy Yi models, make sure you meet the software and hardware requirements.
#### Software requirements
Before using Yi quantized models, make sure you've installed the correct software listed below.
| Model | Software
|---|---
Yi 4-bit quantized models | [AWQ and CUDA](https://github.com/casper-hansen/AutoAWQ?tab=readme-ov-file#install-from-pypi)
Yi 8-bit quantized models | [GPTQ and CUDA](https://github.com/PanQiWei/AutoGPTQ?tab=readme-ov-file#quick-installation)
#### Hardware requirements
Before deploying Yi in your environment, make sure your hardware meets the following requirements.
##### Chat models
| Model | Minimum VRAM | Recommended GPU Example |
|:----------------------|:--------------|:-------------------------------------:|
| Yi-6B-Chat | 15 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) |
| Yi-6B-Chat-4bits | 4 GB | 1 x RTX 3060 (12 GB)<br> 1 x RTX 4060 (8 GB) |
| Yi-6B-Chat-8bits | 8 GB | 1 x RTX 3070 (8 GB) <br> 1 x RTX 4060 (8 GB) |
| Yi-34B-Chat | 72 GB | 4 x RTX 4090 (24 GB)<br> 1 x A800 (80GB) |
| Yi-34B-Chat-4bits | 20 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) <br> 1 x A100 (40 GB) |
| Yi-34B-Chat-8bits | 38 GB | 2 x RTX 3090 (24 GB) <br> 2 x RTX 4090 (24 GB)<br> 1 x A800 (40 GB) |
Below are detailed minimum VRAM requirements under different batch use cases.
| Model | batch=1 | batch=4 | batch=16 | batch=32 |
| ----------------------- | ------- | ------- | -------- | -------- |
| Yi-6B-Chat | 12 GB | 13 GB | 15 GB | 18 GB |
| Yi-6B-Chat-4bits | 4 GB | 5 GB | 7 GB | 10 GB |
| Yi-6B-Chat-8bits | 7 GB | 8 GB | 10 GB | 14 GB |
| Yi-34B-Chat | 65 GB | 68 GB | 76 GB | > 80 GB |
| Yi-34B-Chat-4bits | 19 GB | 20 GB | 30 GB | 40 GB |
| Yi-34B-Chat-8bits | 35 GB | 37 GB | 46 GB | 58 GB |
##### Base models
| Model | Minimum VRAM | Recommended GPU Example |
|----------------------|--------------|:-------------------------------------:|
| Yi-6B | 15 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) |
| Yi-6B-200K | 50 GB | 1 x A800 (80 GB) |
| Yi-9B | 20 GB | 1 x RTX 4090 (24 GB) |
| Yi-34B | 72 GB | 4 x RTX 4090 (24 GB) <br> 1 x A800 (80 GB) |
| Yi-34B-200K | 200 GB | 4 x A800 (80 GB) |
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### FAQ
<details>
<summary> If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. ⬇️</summary>
<br>
#### 💡Fine-tuning
- <strong>Base model or Chat model - which to fine-tune?</strong>
<br>The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task.
- If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice.
- On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice.
- It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements.
- <strong>Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?</strong>
<br>
The key distinction between full-scale fine-tuning on `Yi-34B`and `Yi-34B-Chat` comes down to the fine-tuning approach and outcomes.
- Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely.
- The Base model's fine-tuning is more versatile, with a relatively high performance potential.
- If you are confident in the quality of your data, fine-tuning with `Yi-34B` could be your go-to.
- If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, `Yi-34B-Chat` might be your best bet.
#### 💡Quantization
- <strong>Quantized model versus original model - what is the performance gap?</strong>
- The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points.
- Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results.
#### 💡General
- <strong>Where can I source fine-tuning question answering datasets?</strong>
- You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like [m-a-p/COIG-CQIA](https://huggingface.co/datasets/m-a-p/COIG-CQIA) readily available.
- Additionally, Github offers fine-tuning frameworks, such as [hiyouga/LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory), which integrates pre-made datasets.
- <strong>What is the GPU memory requirement for fine-tuning Yi-34B FP16?</strong>
<br>
The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out [hiyouga/LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory). Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance.
- <strong>Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?</strong>
<br>
If you're looking for third-party Chats, options include [fireworks.ai](https://fireworks.ai/login?callbackURL=https://fireworks.ai/models/fireworks/yi-34b-chat).
</details>
### Learning hub
<details>
<summary> If you want to learn Yi, you can find a wealth of helpful educational resources here. ⬇️</summary>
<br>
Welcome to the Yi learning hub!
Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more.
The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions!
At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below.
With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳
#### Tutorials
##### Blog tutorials
| Deliverable | Date | Author |
| ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ |
| [使用 Dify、Meilisearch、零一万物模型实现最简单的 RAG 应用（三）：AI 电影推荐](https://mp.weixin.qq.com/s/Ri2ap9_5EMzdfiBhSSL_MQ) | 2024-05-20 | [苏洋](https://github.com/soulteary) |
| [使用autodl服务器，在A40显卡上运行， Yi-34B-Chat-int4模型，并使用vllm优化加速，显存占用42G，速度18 words-s](https://blog.csdn.net/freewebsys/article/details/134698597?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-17-134698597-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-05-20 | [fly-iot](https://gitee.com/fly-iot) |
| [Yi-VL 最佳实践](https://modelscope.cn/docs/yi-vl最佳实践) | 2024-05-20 | [ModelScope](https://github.com/modelscope) |
| [一键运行零一万物新鲜出炉Yi-1.5-9B-Chat大模型](https://mp.weixin.qq.com/s/ntMs2G_XdWeM3I6RUOBJrA) | 2024-05-13 | [Second State](https://github.com/second-state) |
| [零一万物开源Yi-1.5系列大模型](https://mp.weixin.qq.com/s/d-ogq4hcFbsuL348ExJxpA) | 2024-05-13 | [刘聪](https://github.com/liucongg) |
| [零一万物Yi-1.5系列模型发布并开源！ 34B-9B-6B 多尺寸，魔搭社区推理微调最佳实践教程来啦！](https://mp.weixin.qq.com/s/3wD-0dCgXB646r720o8JAg) | 2024-05-13 | [ModelScope](https://github.com/modelscope) |
| [Yi-34B 本地部署简单测试](https://blog.csdn.net/arkohut/article/details/135331469?ops_request_misc=%7B%22request%5Fid%22%3A%22171636390616800185813639%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636390616800185813639&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-10-135331469-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-05-13 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [驾辰龙跨Llama持Wasm，玩转Yi模型迎新春过大年（上）](https://blog.csdn.net/weixin_53443275/article/details/136091398?ops_request_misc=%7B%22request%5Fid%22%3A%22171636390616800185813639%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636390616800185813639&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-5-136091398-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-05-13 | [Words worth](https://blog.csdn.net/weixin_53443275?type=blog) |
| [驾辰龙跨Llama持Wasm，玩转Yi模型迎新春过大年（下篇）](https://blog.csdn.net/weixin_53443275/article/details/136096309) | 2024-05-13 | [Words worth](https://blog.csdn.net/weixin_53443275?type=blog) |
| [Ollama新增两个命令，开始支持零一万物Yi-1.5系列模型](https://mp.weixin.qq.com/s/bBgzGJvUqIohodcy9U-pFw) | 2024-05-13 | AI工程师笔记 |
| [使用零一万物 200K 模型和 Dify 快速搭建模型应用](https://zhuanlan.zhihu.com/p/686774859) | 2024-05-13 | [苏洋](https://github.com/soulteary) |
| [(持更) 零一万物模型折腾笔记：社区 Yi-34B 微调模型使用](https://zhuanlan.zhihu.com/p/671549900) | 2024-05-13 | [苏洋](https://github.com/soulteary) |
| [Python+ERNIE-4.0-8K-Yi-34B-Chat大模型初探](https://mp.weixin.qq.com/s/WaygSfn5T8ZPB1mPdGADEQ) | 2024-05-11 | 江湖评谈 |
| [技术布道 Vue及Python调用零一万物模型和Prompt模板（通过百度千帆大模型平台）](https://blog.csdn.net/ucloud2012/article/details/137187469) | 2024-05-11 | [MumuLab](https://blog.csdn.net/ucloud2012?type=blog) |
| [多模态大模型Yi-VL-plus体验 效果很棒](https://zhuanlan.zhihu.com/p/694736111) | 2024-04-27 | [大家好我是爱因](https://www.zhihu.com/people/iamein) |
| [使用autodl服务器，两个3090显卡上运行， Yi-34B-Chat-int4模型，并使用vllm优化加速，显存占用42G，速度23 words-s](https://blog.csdn.net/freewebsys/article/details/134725765?ops_request_misc=%7B%22request%5Fid%22%3A%22171636356716800211598950%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636356716800211598950&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-9-134725765-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-04-27 | [fly-iot](https://gitee.com/fly-iot) |
| [Getting Started with Yi-1.5-9B-Chat](https://www.secondstate.io/articles/yi-1.5-9b-chat/) | 2024-04-27 | [Second State](https://github.com/second-state) |
| [基于零一万物yi-vl-plus大模型简单几步就能批量生成Anki图片笔记](https://mp.weixin.qq.com/s/_ea6g0pzzeO4WyYtuWycWQ) | 2024-04-24 | [正经人王同学](https://github.com/zjrwtx) |
| [【AI开发：语言】一、Yi-34B超大模型本地部署CPU和GPU版](https://blog.csdn.net/alarey/article/details/137769471?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-16-137769471-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-04-21 | [My的梦想已实现](https://blog.csdn.net/alarey?type=blog) |
| [【Yi-34B-Chat-Int4】使用4个2080Ti显卡11G版本，运行Yi-34B模型，5年前老显卡是支持的，可以正常运行，速度 21 words-s，vllm要求算力在7以上的显卡就可以](https://blog.csdn.net/freewebsys/article/details/134754086) | 2024-03-22 | [fly-iot](https://gitee.com/fly-iot) |
| [零一万物大模型部署+微调总结](https://blog.csdn.net/v_wus/article/details/135704126?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-18-135704126-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-22 | [v_wus](https://blog.csdn.net/v_wus?type=blog) |
| [零一万物Yi大模型vllm推理时Yi-34B或Yi-6bchat重复输出的解决方案](https://blog.csdn.net/qq_39667443/article/details/136028776?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-6-136028776-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-02 | [郝铠锋](https://blog.csdn.net/qq_39667443?type=blog) |
| [Yi-34B微调训练](https://blog.csdn.net/lsjlnd/article/details/135336984?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-12-135336984-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-03-02 | [lsjlnd](https://blog.csdn.net/lsjlnd?type=blog) |
| [实测零一万物Yi-VL多模态语言模型：能准确“识图吃瓜”](https://mp.weixin.qq.com/s/fu4O9XvJ03JhimsEyI-SsQ) | 2024-02-02 | [苏洋](https://github.com/soulteary) |
| [零一万物开源Yi-VL多模态大模型，魔搭社区推理&微调最佳实践来啦！](https://zhuanlan.zhihu.com/p/680098411) | 2024-01-26 | [ModelScope](https://github.com/modelscope) |
| [单卡 3 小时训练 Yi-6B 大模型 Agent：基于 Llama Factory 实战](https://zhuanlan.zhihu.com/p/678989191) | 2024-01-22 | [郑耀威](https://github.com/hiyouga) |
| [零一科技Yi-34B Chat大模型环境搭建&推理](https://blog.csdn.net/zzq1989_/article/details/135597181?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-8-135597181-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-15 | [要养家的程序员](https://blog.csdn.net/zzq1989_?type=blog) |
| [基于LLaMA Factory，单卡3小时训练专属大模型 Agent](https://blog.csdn.net/m0_59596990/article/details/135760285?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-10-135760285-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-15 | [机器学习社区](https://blog.csdn.net/m0_59596990?type=blog) |
| [双卡 3080ti 部署 Yi-34B 大模型 - Gradio + vLLM 踩坑全记录](https://blog.csdn.net/arkohut/article/details/135321242?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-10-135321242-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-02 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [【大模型部署实践-3】3个能在3090上跑起来的4bits量化Chat模型（baichuan2-13b、InternLM-20b、Yi-34b）](https://blog.csdn.net/qq_40302568/article/details/135040985?ops_request_misc=%7B%22request%5Fid%22%3A%22171636168816800227489911%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636168816800227489911&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-30-135040985-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2024-01-02 | [aq_Seabiscuit](https://blog.csdn.net/qq_40302568?type=blog) |
| [只需 24G 显存，用 vllm 跑起来 Yi-34B 中英双语大模型](https://blog.csdn.net/arkohut/article/details/135274973) | 2023-12-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [零一万物模型官方 Yi-34B 模型本地离线运行部署使用笔记（物理机和docker两种部署方式），200K 超长文本内容，34B 干翻一众 70B 模型，打榜分数那么高，这模型到底行不行？](https://blog.csdn.net/u014374009/article/details/136327696) | 2023-12-28 | [代码讲故事](https://blog.csdn.net/u014374009?type=blog) |
| [LLM - 大模型速递之 Yi-34B 入门与 LoRA 微调](https://blog.csdn.net/BIT_666/article/details/134990402) | 2023-12-18 | [BIT_666](https://bitddd.blog.csdn.net/?type=blog) |
| [通过vllm框架进行大模型推理](https://blog.csdn.net/weixin_45920955/article/details/135300561?ops_request_misc=%7B%22request%5Fid%22%3A%22171636343416800188513953%22%2C%22scm%22%3A%2220140713.130102334.pc%5Fblog.%22%7D&request_id=171636343416800188513953&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~times_rank-13-135300561-null-null.nonecase&utm_term=Yi大模型&spm=1018.2226.3001.4450) | 2023-12-18 | [土山炮](https://blog.csdn.net/weixin_45920955?type=blog) |
| [CPU 混合推理，非常见大模型量化方案：“二三五六” 位量化方案](https://zhuanlan.zhihu.com/p/671698216) | 2023-12-12 | [苏洋](https://github.com/soulteary) |
| [零一万物模型折腾笔记：官方 Yi-34B 模型基础使用](https://zhuanlan.zhihu.com/p/671387298) | 2023-12-10 | [苏洋](https://github.com/soulteary) |
| [Running Yi-34B-Chat locally using LlamaEdge](https://www.secondstate.io/articles/yi-34b/) | 2023-11-30 | [Second State](https://github.com/second-state) |
| [本地运行零一万物 34B 大模型，使用 Llama.cpp & 21G 显存](https://zhuanlan.zhihu.com/p/668921042) | 2023-11-26 | [苏洋](https://github.com/soulteary) |
##### GitHub Project
| Deliverable | Date | Author |
| ------------------------------------------------------------ | ---------- | ------------------------------------------- |
| [yi-openai-proxy](https://github.com/soulteary/yi-openai-proxy) | 2024-05-11 | [苏洋](https://github.com/soulteary) |
| [基于零一万物 Yi 模型和 B 站构建大语言模型高质量训练数据集](https://github.com/zjrwtx/bilibiliQA_databuilder) | 2024-04-29 | [正经人王同学](https://github.com/zjrwtx) |
| [基于视频网站和零一万物大模型构建大语言模型高质量训练数据集](https://github.com/zjrwtx/VideoQA_databuilder) | 2024-04-25 | [正经人王同学](https://github.com/zjrwtx) |
| [基于零一万物yi-34b-chat-200k输入任意文章地址，点击按钮即可生成无广告或推广内容的简要笔记，并生成分享图给好友](https://github.com/zjrwtx/open_summary) | 2024-04-24 | [正经人王同学](https://github.com/zjrwtx) |
| [Food-GPT-Yi-model](https://github.com/ThisisHubert/FoodGPT-Yi-model) | 2024-04-21 | [Hubert S](https://github.com/ThisisHubert) |
##### Video tutorials
| Deliverable | Date | Author |
| ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ |
| [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-30 | [Second State](https://github.com/second-state) |
| [只需 24G 显存，用 vllm 跑起来 Yi-34B 中英双语大模型](https://www.bilibili.com/video/BV17t4y1f7Ee/) | 2023-12-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
| [Dolphin Yi 34b - Brand New Foundational Model TESTED](https://www.youtube.com/watch?v=On3Zuv27V3k&t=85s) | 2023-11-27 | [Matthew Berman](https://www.youtube.com/@matthew_berman) |
| [Yi-VL-34B 多模态大模型 - 用两张 A40 显卡跑起来](https://www.bilibili.com/video/BV1Q5411y7AG/) | 2024-01-28 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [4060Ti 16G显卡安装零一万物最新开源的Yi-1.5版大语言模型](https://www.bilibili.com/video/BV16i421X7Jx/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-14 | [titan909](https://space.bilibili.com/526393761) |
| [Yi-1.5: True Apache 2.0 Competitor to LLAMA-3](https://www.youtube.com/watch?v=KCDYrfWeTRc) | 2024-05-13 | [Prompt Engineering](https://www.youtube.com/@engineerprompt) |
| [Install Yi-1.5 Model Locally - Beats Llama 3 in Various Benchmarks](https://www.youtube.com/watch?v=Ba-G7Il0UkA) | 2024-05-13 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
| [how to install Ollama and run Yi 6B](https://www.youtube.com/watch?v=4Jnar7OUHqQ) | 2024-05-13 | [Ridaa Davids](https://www.youtube.com/@quantanovabusiness) |
| [地表最强混合智能AI助手：llama3_70B+Yi_34B+Qwen1.5_110B](https://www.bilibili.com/video/BV1Xm411C7V1/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-04 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
| [ChatDoc学术论文辅助--基于Yi-34B和langchain进行PDF知识库问答](https://www.bilibili.com/video/BV11i421C7B5/?spm_id_from=333.999.0.0&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-03 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
| [基于Yi-34B的领域知识问答项目演示](https://www.bilibili.com/video/BV1zZ42177ZA/?spm_id_from=333.999.0.0&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-05-02 | [朱扎特](https://space.bilibili.com/494512200?spm_id_from=333.788.0.0) |
| [使用RTX4090+GaLore算法 全参微调Yi-6B大模型](https://www.bilibili.com/video/BV1ax4y1U7Ep/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-03-24 | [小工蚂创始人](https://space.bilibili.com/478674499?spm_id_from=333.788.0.0) |
| [无内容审查NSFW大语言模型Yi-34B-Chat蒸馏版测试,RolePlay,《天龙八部》马夫人康敏,本地GPU,CPU运行](https://www.youtube.com/watch?v=VL-W0TnLCns) | 2024-03-20 | [刘悦的技术博客](https://v3u.cn/) |
| [无内容审查NSFW大语言模型整合包,Yi-34B-Chat,本地CPU运行,角色扮演潘金莲](https://www.youtube.com/watch?v=rBvbgwz3oHM) | 2024-03-16 | [刘悦的技术博客](https://v3u.cn/) |
| [量化 Yi-34B-Chat 并在单卡 RTX 4090 使用 vLLM 部署](https://www.bilibili.com/video/BV1jx421y7xj/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-03-05 | [白鸽巢](https://space.bilibili.com/138938660?spm_id_from=333.788.0.0) |
| [Yi-VL-34B（5）：使用3个3090显卡24G版本，运行Yi-VL-34B模型，支持命令行和web界面方式，理解图片的内容转换成文字](https://www.bilibili.com/video/BV1BB421z7oA/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-27 | [fly-iot](https://gitee.com/fly-iot) |
| [Win环境KoboldCpp本地部署大语言模型进行各种角色扮演游戏](https://www.bilibili.com/video/BV14J4m1e77f/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-25 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
| [无需显卡本地部署Yi-34B-Chat进行角色扮演游戏 P2](https://www.bilibili.com/video/BV19v421677y/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-23 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
| [【wails】（2）：使用go-llama.cpp 运行 yi-01-6b大模型，使用本地CPU运行，速度还可以，等待下一版本更新](https://www.bilibili.com/video/BV194421F7Fy/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-20 | [fly-iot](https://gitee.com/fly-iot) |
| [【xinference】（6）：在autodl上，使用xinference部署yi-vl-chat和qwen-vl-chat模型，可以使用openai调用成功](https://www.bilibili.com/video/BV19Z421z7cv/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-06 | [fly-iot](https://gitee.com/fly-iot) |
| [无需显卡本地部署Yi-34B-Chat进行角色扮演游戏 P1](https://www.bilibili.com/video/BV1tU421o7Co/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-02-05 | [魚蟲蟲](https://space.bilibili.com/431981179?spm_id_from=333.788.0.0) |
| [2080Ti部署YI-34B大模型 xinference-oneapi-fastGPT本地知识库使用指南](https://www.bilibili.com/video/BV1hC411z7xu/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-30 | [小饭护法要转码](https://space.bilibili.com/39486865?spm_id_from=333.788.0.0) |
| [Best Story Writing AI Model - Install Yi 6B 200K Locally on Windows](https://www.youtube.com/watch?v=cZs2jRtl0bs) | 2024-01-22 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
| [Mac 本地运行大语言模型方法与常见问题指南（Yi 34B 模型+32 GB 内存测试）](https://www.bilibili.com/video/BV1VT4y1b7Th/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-21 | [小吴苹果机器人](https://space.bilibili.com/1732749682?spm_id_from=333.788.0.0) |
| [【Dify知识库】（11）：Dify0.4.9改造支持MySQL，成功接入yi-6b 做对话，本地使用fastchat启动，占8G显存，完成知识库配置](https://www.bilibili.com/video/BV1ia4y1y7JH/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-21 | [fly-iot](https://gitee.com/fly-iot) |
| [这位LLM先生有点暴躁,用的是YI-6B的某个量化版,#LLM #大语言模型 #暴躁老哥](https://www.youtube.com/watch?v=eahXJrdtQuc) | 2024-01-20 | [晓漫吧](https://www.youtube.com/@xiaomanba) |
| [大模型推理 NvLink 桥接器有用吗｜双卡 A6000 测试一下](https://www.bilibili.com/video/BV1AW4y1w7DC/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-17 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [大模型推理 A40 vs A6000 谁更强 - 对比 Yi-34B 的单、双卡推理性能](https://www.bilibili.com/video/BV1aK4y1z7GF/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-15 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [C-Eval 大语言模型评测基准- 用 LM Evaluation Harness + vLLM 跑起来](https://www.bilibili.com/video/BV1Yw411g7ZL/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-11 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [双显卡部署 Yi-34B 大模型 - vLLM + Gradio 踩坑记录](https://www.bilibili.com/video/BV1p94y1c7ak/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2024-01-01 | [漆妮妮](https://space.bilibili.com/1262370256) |
| [手把手教学！使用 vLLM 快速部署 Yi-34B-Chat](https://www.bilibili.com/video/BV1ew41157Mk/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-26 | [白鸽巢](https://space.bilibili.com/138938660?spm_id_from=333.788.0.0) |
| [如何训练企业自己的大语言模型？Yi-6B LORA微调演示 #小工蚁](https://www.bilibili.com/video/BV1uc41117zz/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-21 | [小工蚂创始人](https://space.bilibili.com/478674499?spm_id_from=333.788.0.0) |
| [Yi-34B（4）：使用4个2080Ti显卡11G版本，运行Yi-34B模型，5年前老显卡是支持的，可以正常运行，速度 21 words/s](https://www.bilibili.com/video/BV1nj41157L3/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-02 | [fly-iot](https://gitee.com/fly-iot) |
| [使用autodl服务器，RTX 3090 * 3 显卡上运行， Yi-34B-Chat模型，显存占用60G](https://www.bilibili.com/video/BV1BM411R7ae/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [fly-iot](https://gitee.com/fly-iot) |
| [使用autodl服务器，两个3090显卡上运行， Yi-34B-Chat-int4模型，用vllm优化，增加 --num-gpu 2，速度23 words/s](https://www.bilibili.com/video/BV1Hu4y1L7BH/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [fly-iot](https://gitee.com/fly-iot) |
| [Yi大模型一键本地部署 技术小白玩转AI](https://www.bilibili.com/video/BV16H4y117md/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-12-01 | [技术小白玩转AI](https://space.bilibili.com/3546586137234288?spm_id_from=333.788.0.0) |
| [01.AI's Yi-6B: Overview and Fine-Tuning](https://www.youtube.com/watch?v=mye-UOkAliQ) | 2023-11-28 | [AI Makerspace](https://www.youtube.com/@AI-Makerspace) |
| [Yi 34B Chat LLM outperforms Llama 70B](https://www.youtube.com/watch?v=RYtrF-R5jDc) | 2023-11-27 | [DLExplorer](https://www.youtube.com/@DLExplorers-lg7dt) |
| [How to run open source models on mac Yi 34b on m3 Max](https://www.youtube.com/watch?v=GAo-dopkgjI) | 2023-11-26 | [TECHNO PREMIUM](https://www.youtube.com/@technopremium91) |
| [Yi-34B - 200K - The BEST & NEW CONTEXT WINDOW KING ](https://www.youtube.com/watch?v=7WBojwwv5Qo) | 2023-11-24 | [Prompt Engineering](https://www.youtube.com/@engineerprompt) |
| [Yi 34B : The Rise of Powerful Mid-Sized Models - Base,200k & Chat](https://www.youtube.com/watch?v=bWCjwtu_tHs) | 2023-11-24 | [Sam Witteveen](https://www.youtube.com/@samwitteveenai) |
| [在IoT设备运行破解版李开复大模型dolphin-2.2-yi-34b（还可作为私有OpenAI API服务器）](https://www.bilibili.com/video/BV1SQ4y18744/?spm_id_from=333.337.search-card.all.click&vd_source=ab85f93e294a2f6be11db57c29c6d706) | 2023-11-15 | [Second State](https://github.com/second-state) |
| [Run dolphin-2.2-yi-34b on IoT Devices (Also works as a Private OpenAI API Server)](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-14 | [Second State](https://github.com/second-state) |
| [How to Install Yi 34B 200K Llamafied on Windows Laptop](https://www.youtube.com/watch?v=enoha4K4HkQ) | 2023-11-11 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
</details>
# Why Yi?
- [Ecosystem](#ecosystem)
- [Upstream](#upstream)
- [Downstream](#downstream)
- [Serving](#serving)
- [Quantization](#quantization-1)
- [Fine-tuning](#fine-tuning-1)
- [API](#api)
- [Benchmarks](#benchmarks)
- [Chat model performance](#chat-model-performance)
- [Base model performance](#base-model-performance)
- [Yi-34B and Yi-34B-200K](#yi-34b-and-yi-34b-200k)
- [Yi-9B](#yi-9b)
## Ecosystem
Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity.
- [Upstream](#upstream)
- [Downstream](#downstream)
- [Serving](#serving)
- [Quantization](#quantization-1)
- [Fine-tuning](#fine-tuning-1)
- [API](#api)
### Upstream
The Yi series models follow the same model architecture as Llama. By choosing Yi, you can leverage existing tools, libraries, and resources within the Llama ecosystem, eliminating the need to create new tools and enhancing development efficiency.
For example, the Yi series models are saved in the format of the Llama model. You can directly use `LlamaForCausalLM` and `LlamaTokenizer` to load the model. For more information, see [Use the chat model](#31-use-the-chat-model).
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34b", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34b", device_map="auto")
```
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Downstream
> 💡 Tip
>
> - Feel free to create a PR and share the fantastic work you've built using the Yi series models.
>
> - To help others quickly understand your work, it is recommended to use the format of `<model-name>: <model-intro> + <model-highlights>`.
#### Serving
If you want to get up with Yi in a few minutes, you can use the following services built upon Yi.
- Yi-34B-Chat: you can chat with Yi using one of the following platforms:
- [Yi-34B-Chat | Hugging Face](https://huggingface.co/spaces/01-ai/Yi-34B-Chat)
- [Yi-34B-Chat | Yi Platform](https://platform.lingyiwanwu.com/): **Note** that currently it's available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)) and experience it firsthand!
- [Yi-6B-Chat (Replicate)](https://replicate.com/01-ai): you can use this model with more options by setting additional parameters and calling APIs.
- [ScaleLLM](https://github.com/vectorch-ai/ScaleLLM#supported-models): you can use this service to run Yi models locally with added flexibility and customization.
#### Quantization
If you have limited computational capabilities, you can use Yi's quantized models as follows.
These quantized models have reduced precision but offer increased efficiency, such as faster inference speed and smaller RAM usage.
- [TheBloke/Yi-34B-GPTQ](https://huggingface.co/TheBloke/Yi-34B-GPTQ)
- [TheBloke/Yi-34B-GGUF](https://huggingface.co/TheBloke/Yi-34B-GGUF)
- [TheBloke/Yi-34B-AWQ](https://huggingface.co/TheBloke/Yi-34B-AWQ)
#### Fine-tuning
If you're seeking to explore the diverse capabilities within Yi's thriving family, you can delve into Yi's fine-tuned models as below.
- [TheBloke Models](https://huggingface.co/TheBloke): this site hosts numerous fine-tuned models derived from various LLMs including Yi.
This is not an exhaustive list for Yi, but to name a few sorted on downloads:
- [TheBloke/dolphin-2_2-yi-34b-AWQ](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-AWQ)
- [TheBloke/Yi-34B-Chat-AWQ](https://huggingface.co/TheBloke/Yi-34B-Chat-AWQ)
- [TheBloke/Yi-34B-Chat-GPTQ](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ)
- [SUSTech/SUS-Chat-34B](https://huggingface.co/SUSTech/SUS-Chat-34B): this model ranked first among all models below 70B and outperformed the twice larger deepseek-llm-67b-chat. You can check the result on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
- [OrionStarAI/OrionStar-Yi-34B-Chat-Llama](https://huggingface.co/OrionStarAI/OrionStar-Yi-34B-Chat-Llama): this model excelled beyond other models (such as GPT-4, Qwen-14B-Chat, Baichuan2-13B-Chat) in C-Eval and CMMLU evaluations on the [OpenCompass LLM Leaderboard](https://opencompass.org.cn/leaderboard-llm).
- [NousResearch/Nous-Capybara-34B](https://huggingface.co/NousResearch/Nous-Capybara-34B): this model is trained with 200K context length and 3 epochs on the Capybara dataset.
#### API
- [amazing-openai-api](https://github.com/soulteary/amazing-openai-api): this tool converts Yi model APIs into the OpenAI API format out of the box.
- [LlamaEdge](https://www.secondstate.io/articles/yi-34b/#create-an-openai-compatible-api-service-for-the-yi-34b-chat-model): this tool builds an OpenAI-compatible API server for Yi-34B-Chat using a portable Wasm (WebAssembly) file, powered by Rust.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
## Tech report
For detailed capabilities of the Yi series model, see [Yi: Open Foundation Models by 01.AI](https://arxiv.org/abs/2403.04652).
### Citation
```
@misc{ai2024yi,
title={Yi: Open Foundation Models by 01.AI},
author={01. AI and : and Alex Young and Bei Chen and Chao Li and Chengen Huang and Ge Zhang and Guanwei Zhang and Heng Li and Jiangcheng Zhu and Jianqun Chen and Jing Chang and Kaidong Yu and Peng Liu and Qiang Liu and Shawn Yue and Senbin Yang and Shiming Yang and Tao Yu and Wen Xie and Wenhao Huang and Xiaohui Hu and Xiaoyi Ren and Xinyao Niu and Pengcheng Nie and Yuchi Xu and Yudong Liu and Yue Wang and Yuxuan Cai and Zhenyu Gu and Zhiyuan Liu and Zonghong Dai},
year={2024},
eprint={2403.04652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## Benchmarks
- [Chat model performance](#chat-model-performance)
- [Base model performance](#base-model-performance)
### Chat model performance
Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more.
<details>
<summary> Evaluation methods and challenges. ⬇️ </summary>
- **Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA.
- **Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed.
- **Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text.
- **Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results.
<strong>*</strong>: C-Eval results are evaluated on the validation datasets
</details>
### Base model performance
#### Yi-34B and Yi-34B-200K
The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMMLU, common-sense reasoning, reading comprehension, and more.
<details>
<summary> Evaluation methods. ⬇️</summary>
- **Disparity in results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass.
- **Investigation findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences.
- **Uniform benchmarking process**: our methodology aligns with the original benchmarks—consistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content.
- **Efforts to retrieve unreported scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline.
- **Extensive model evaluation**: to evaluate the model’s capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension.
- **Special configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code".
- **Falcon-180B caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated.
</details>
#### Yi-9B
Yi-9B is almost the best among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension.
- In terms of **overall** ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B.
- In terms of **coding** ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B.
- In terms of **math** ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B.
- In terms of **common sense and reasoning** ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
# Who can use Yi?
Everyone! 🙌 ✅
The code and weights of the Yi series models are distributed under the [Apache 2.0 license](https://github.com/01-ai/Yi/blob/main/LICENSE), which means the Yi series models are free for personal usage, academic purposes, and commercial use.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
# Misc.
### Acknowledgments
A heartfelt thank you to each of you who have made contributions to the Yi community! You have helped Yi not just a project, but a vibrant, growing home for innovation.
[](https://github.com/01-ai/yi/graphs/contributors)
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### Disclaimer
We use data compliance checking algorithms during the training process, to
ensure the compliance of the trained model to the best of our ability. Due to
complex data and the diversity of language model usage scenarios, we cannot
guarantee that the model will generate correct, and reasonable output in all
scenarios. Please be aware that there is still a risk of the model producing
problematic outputs. We will not be responsible for any risks and issues
resulting from misuse, misguidance, illegal usage, and related misinformation,
as well as any associated data security concerns.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
### License
The code and weights of the Yi-1.5 series models are distributed under the [Apache 2.0 license](https://github.com/01-ai/Yi/blob/main/LICENSE).
If you create derivative works based on this model, please include the following attribution in your derivative works:
This work is a derivative of [The Yi Series Model You Base On] by 01.AI, used under the Apache 2.0 License.
<p align="right"> [
<a href="#top">Back to top ⬆️ </a> ]
</p>
|
{"license": "apache-2.0", "pipeline_tag": "text-generation", "widget": [{"example_title": "Yi-34B-Chat", "text": "hi", "output": {"text": " Hello! How can I assist you today?"}}, {"example_title": "Yi-34B", "text": "There's a place where time stands still. A place of breath taking wonder, but also", "output": {"text": " an eerie sense that something is just not right…\nBetween the two worlds lies The Forgotten Kingdom - home to creatures long since thought extinct and ancient magic so strong it defies belief! Only here can you find what has been lost for centuries: An Elixir Of Life which will restore youth and vitality if only those who seek its power are brave enough to face up against all manner of dangers lurking in this mysterious land! But beware; some say there may even exist powerful entities beyond our comprehension whose intentions towards humanity remain unclear at best ---- they might want nothing more than destruction itself rather then anything else from their quest after immortality (and maybe someone should tell them about modern medicine)? In any event though – one thing remains true regardless : whether or not success comes easy depends entirely upon how much effort we put into conquering whatever challenges lie ahead along with having faith deep down inside ourselves too ;) So let’s get started now shall We?"}}]}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,528 |
RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf
|
RichardErkhov
| null |
[
"gguf",
"endpoints_compatible",
"region:us"
] | 2024-07-23T07:29:23Z |
2024-07-23T19:28:49+00:00
| 28 | 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)
Llama-2-13b-alpaca-es - GGUF
- Model creator: https://huggingface.co/4i-ai/
- Original model: https://huggingface.co/4i-ai/Llama-2-13b-alpaca-es/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-2-13b-alpaca-es.Q2_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q2_K.gguf) | Q2_K | 4.52GB |
| [Llama-2-13b-alpaca-es.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ3_XS.gguf) | IQ3_XS | 4.99GB |
| [Llama-2-13b-alpaca-es.IQ3_S.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ3_S.gguf) | IQ3_S | 5.27GB |
| [Llama-2-13b-alpaca-es.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q3_K_S.gguf) | Q3_K_S | 5.27GB |
| [Llama-2-13b-alpaca-es.IQ3_M.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ3_M.gguf) | IQ3_M | 5.57GB |
| [Llama-2-13b-alpaca-es.Q3_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q3_K.gguf) | Q3_K | 5.9GB |
| [Llama-2-13b-alpaca-es.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q3_K_M.gguf) | Q3_K_M | 5.9GB |
| [Llama-2-13b-alpaca-es.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q3_K_L.gguf) | Q3_K_L | 6.45GB |
| [Llama-2-13b-alpaca-es.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ4_XS.gguf) | IQ4_XS | 6.54GB |
| [Llama-2-13b-alpaca-es.Q4_0.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_0.gguf) | Q4_0 | 6.86GB |
| [Llama-2-13b-alpaca-es.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ4_NL.gguf) | IQ4_NL | 6.9GB |
| [Llama-2-13b-alpaca-es.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_K_S.gguf) | Q4_K_S | 6.91GB |
| [Llama-2-13b-alpaca-es.Q4_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_K.gguf) | Q4_K | 7.33GB |
| [Llama-2-13b-alpaca-es.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_K_M.gguf) | Q4_K_M | 7.33GB |
| [Llama-2-13b-alpaca-es.Q4_1.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_1.gguf) | Q4_1 | 7.61GB |
| [Llama-2-13b-alpaca-es.Q5_0.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_0.gguf) | Q5_0 | 8.36GB |
| [Llama-2-13b-alpaca-es.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_K_S.gguf) | Q5_K_S | 8.36GB |
| [Llama-2-13b-alpaca-es.Q5_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_K.gguf) | Q5_K | 8.6GB |
| [Llama-2-13b-alpaca-es.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_K_M.gguf) | Q5_K_M | 8.6GB |
| [Llama-2-13b-alpaca-es.Q5_1.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_1.gguf) | Q5_1 | 9.1GB |
| [Llama-2-13b-alpaca-es.Q6_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q6_K.gguf) | Q6_K | 8.75GB |
| [Llama-2-13b-alpaca-es.Q8_0.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q8_0.gguf) | Q8_0 | 12.88GB |
Original model description:
---
license: cc-by-nc-4.0
datasets:
- bertin-project/alpaca-spanish
language:
- es
inference: false
---
# Model Card for Model ID
This model is the Llama-2-13b-hf fine-tuned with an adapter on the Spanish Alpaca dataset.
## Model Details
### Model Description
This is a Spanish chat model fine-tuned on a Spanish instruction dataset.
The model expect a prompt containing the instruction, with an option to add an input (see examples below).
- **Developed by:** 4i Intelligent Insights
- **Model type:** Chat model
- **Language(s) (NLP):** Spanish
- **License:** cc-by-nc-4.0 (inhereted from the alpaca-spanish dataset),
- **Finetuned from model :** Llama 2 13B ([license agreement](https://ai.meta.com/resources/models-and-libraries/llama-downloads/))
## Uses
The model is intended to be used directly without the need of further fine-tuning.
## Bias, Risks, and Limitations
This model inherits the bias, risks, and limitations of its base model, Llama 2, and of the dataset used for fine-tuning.
Note that the Spanish Alpaca dataset was obtained by translating the original Alpaca dataset. It contains translation errors that may have negatively impacted the fine-tuning of the model.
## How to Get Started with the Model
Use the code below to get started with the model for inference. The adapter was directly merged into the original Llama 2 model.
The following code sample uses 4-bit quantization, you may load the model without it if you have enough VRAM. We show results for hyperparameters that we found work well for this set of prompts.
```py
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, TrainingArguments, GenerationConfig
import torch
model_name = "4i-ai/Llama-2-13b-alpaca-es"
#Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
def create_and_prepare_model():
compute_dtype = getattr(torch, "float16")
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=compute_dtype,
bnb_4bit_use_double_quant=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_name, quantization_config=bnb_config, device_map={"": 0}
)
return model
model = create_and_prepare_model()
def generate(instruction, input=None):
#Format the prompt to look like the training data
if input is not None:
prompt = "### Instruction:\n"+instruction+"\n\n### Input:\n"+input+"\n\n### Response:\n"
else :
prompt = "### Instruction:\n"+instruction+"\n\n### Response:\n"
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].cuda()
generation_output = model.generate(
input_ids=input_ids,
repetition_penalty=1.5,
generation_config=GenerationConfig(temperature=0.1, top_p=0.75, top_k=40, num_beams=20), #hyperparameters for generation
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=150, #maximum tokens generated, increase if you want longer asnwer (up to 2048 - the length of the prompt), generation "looks" slower for longer response
)
for seq in generation_output.sequences:
output = tokenizer.decode(seq, skip_special_tokens=True)
print(output.split("### Response:")[1].strip())
generate("Háblame de la superconductividad.")
print("-----------")
generate("Encuentra la capital de España.")
print("-----------")
generate("Encuentra la capital de Portugal.")
print("-----------")
generate("Organiza los números dados en orden ascendente.", "2, 3, 0, 8, 4, 10")
print("-----------")
generate("Compila una lista de 5 estados de EE. UU. ubicados en el Oeste.")
print("-----------")
generate("Compila una lista de 2 estados de EE. UU. ubicados en el Oeste.")
print("-----------")
generate("Compila una lista de 10 estados de EE. UU. ubicados en el Este.")
print("-----------")
generate("¿Cuál es el color de una fresa?")
print("-----------")
generate("¿Cuál es el color de la siguiente fruta?", "fresa")
print("-----------")
```
Expected output:
```
La superconductividad es un fenómeno físico en el que los materiales pueden conducir corrientes eléctricas a bajas temperaturas sin pérdida de energía debido a la resistencia. Los materiales superconductores son capaces de conducir corrientes eléctricas a temperaturas mucho más bajas que los materiales normales. Esto se debe a que los electrones en los materiales superconductores se comportan de manera cooperativa, lo que les permite conducir corrientes eléctricas sin pérdida de energía. Los materiales superconductores tienen muchas aplicaciones
-----------
La capital de España es Madrid.
-----------
La capital de Portugal es Lisboa.
-----------
0, 2, 3, 4, 8, 10
-----------
1. California
2. Oregón
3. Washington
4. Nevada
5. Arizona
-----------
California y Washington.
-----------
1. Maine
2. Nuevo Hampshire
3. Vermont
4. Massachusetts
5. Rhode Island
6. Connecticut
7. Nueva York
8. Nueva Jersey
9. Pensilvania
10. Delaware
-----------
El color de una fresa es rojo brillante.
-----------
El color de la fresa es rojo.
-----------
```
## Contact Us
[4i.ai](https://4i.ai/) provides natural language processing solutions with dialog, vision and voice capabilities to deliver real-life multimodal human-machine conversations.
Please contact us at [email protected]
| null |
Non_BioNLP
|
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Llama-2-13b-alpaca-es - GGUF
- Model creator: https://huggingface.co/4i-ai/
- Original model: https://huggingface.co/4i-ai/Llama-2-13b-alpaca-es/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-2-13b-alpaca-es.Q2_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q2_K.gguf) | Q2_K | 4.52GB |
| [Llama-2-13b-alpaca-es.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ3_XS.gguf) | IQ3_XS | 4.99GB |
| [Llama-2-13b-alpaca-es.IQ3_S.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ3_S.gguf) | IQ3_S | 5.27GB |
| [Llama-2-13b-alpaca-es.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q3_K_S.gguf) | Q3_K_S | 5.27GB |
| [Llama-2-13b-alpaca-es.IQ3_M.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ3_M.gguf) | IQ3_M | 5.57GB |
| [Llama-2-13b-alpaca-es.Q3_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q3_K.gguf) | Q3_K | 5.9GB |
| [Llama-2-13b-alpaca-es.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q3_K_M.gguf) | Q3_K_M | 5.9GB |
| [Llama-2-13b-alpaca-es.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q3_K_L.gguf) | Q3_K_L | 6.45GB |
| [Llama-2-13b-alpaca-es.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ4_XS.gguf) | IQ4_XS | 6.54GB |
| [Llama-2-13b-alpaca-es.Q4_0.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_0.gguf) | Q4_0 | 6.86GB |
| [Llama-2-13b-alpaca-es.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.IQ4_NL.gguf) | IQ4_NL | 6.9GB |
| [Llama-2-13b-alpaca-es.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_K_S.gguf) | Q4_K_S | 6.91GB |
| [Llama-2-13b-alpaca-es.Q4_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_K.gguf) | Q4_K | 7.33GB |
| [Llama-2-13b-alpaca-es.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_K_M.gguf) | Q4_K_M | 7.33GB |
| [Llama-2-13b-alpaca-es.Q4_1.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q4_1.gguf) | Q4_1 | 7.61GB |
| [Llama-2-13b-alpaca-es.Q5_0.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_0.gguf) | Q5_0 | 8.36GB |
| [Llama-2-13b-alpaca-es.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_K_S.gguf) | Q5_K_S | 8.36GB |
| [Llama-2-13b-alpaca-es.Q5_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_K.gguf) | Q5_K | 8.6GB |
| [Llama-2-13b-alpaca-es.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_K_M.gguf) | Q5_K_M | 8.6GB |
| [Llama-2-13b-alpaca-es.Q5_1.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q5_1.gguf) | Q5_1 | 9.1GB |
| [Llama-2-13b-alpaca-es.Q6_K.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q6_K.gguf) | Q6_K | 8.75GB |
| [Llama-2-13b-alpaca-es.Q8_0.gguf](https://huggingface.co/RichardErkhov/4i-ai_-_Llama-2-13b-alpaca-es-gguf/blob/main/Llama-2-13b-alpaca-es.Q8_0.gguf) | Q8_0 | 12.88GB |
Original model description:
---
license: cc-by-nc-4.0
datasets:
- bertin-project/alpaca-spanish
language:
- es
inference: false
---
# Model Card for Model ID
This model is the Llama-2-13b-hf fine-tuned with an adapter on the Spanish Alpaca dataset.
## Model Details
### Model Description
This is a Spanish chat model fine-tuned on a Spanish instruction dataset.
The model expect a prompt containing the instruction, with an option to add an input (see examples below).
- **Developed by:** 4i Intelligent Insights
- **Model type:** Chat model
- **Language(s) (NLP):** Spanish
- **License:** cc-by-nc-4.0 (inhereted from the alpaca-spanish dataset),
- **Finetuned from model :** Llama 2 13B ([license agreement](https://ai.meta.com/resources/models-and-libraries/llama-downloads/))
## Uses
The model is intended to be used directly without the need of further fine-tuning.
## Bias, Risks, and Limitations
This model inherits the bias, risks, and limitations of its base model, Llama 2, and of the dataset used for fine-tuning.
Note that the Spanish Alpaca dataset was obtained by translating the original Alpaca dataset. It contains translation errors that may have negatively impacted the fine-tuning of the model.
## How to Get Started with the Model
Use the code below to get started with the model for inference. The adapter was directly merged into the original Llama 2 model.
The following code sample uses 4-bit quantization, you may load the model without it if you have enough VRAM. We show results for hyperparameters that we found work well for this set of prompts.
```py
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, TrainingArguments, GenerationConfig
import torch
model_name = "4i-ai/Llama-2-13b-alpaca-es"
#Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
def create_and_prepare_model():
compute_dtype = getattr(torch, "float16")
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=compute_dtype,
bnb_4bit_use_double_quant=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_name, quantization_config=bnb_config, device_map={"": 0}
)
return model
model = create_and_prepare_model()
def generate(instruction, input=None):
#Format the prompt to look like the training data
if input is not None:
prompt = "### Instruction:\n"+instruction+"\n\n### Input:\n"+input+"\n\n### Response:\n"
else :
prompt = "### Instruction:\n"+instruction+"\n\n### Response:\n"
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].cuda()
generation_output = model.generate(
input_ids=input_ids,
repetition_penalty=1.5,
generation_config=GenerationConfig(temperature=0.1, top_p=0.75, top_k=40, num_beams=20), #hyperparameters for generation
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=150, #maximum tokens generated, increase if you want longer asnwer (up to 2048 - the length of the prompt), generation "looks" slower for longer response
)
for seq in generation_output.sequences:
output = tokenizer.decode(seq, skip_special_tokens=True)
print(output.split("### Response:")[1].strip())
generate("Háblame de la superconductividad.")
print("-----------")
generate("Encuentra la capital de España.")
print("-----------")
generate("Encuentra la capital de Portugal.")
print("-----------")
generate("Organiza los números dados en orden ascendente.", "2, 3, 0, 8, 4, 10")
print("-----------")
generate("Compila una lista de 5 estados de EE. UU. ubicados en el Oeste.")
print("-----------")
generate("Compila una lista de 2 estados de EE. UU. ubicados en el Oeste.")
print("-----------")
generate("Compila una lista de 10 estados de EE. UU. ubicados en el Este.")
print("-----------")
generate("¿Cuál es el color de una fresa?")
print("-----------")
generate("¿Cuál es el color de la siguiente fruta?", "fresa")
print("-----------")
```
Expected output:
```
La superconductividad es un fenómeno físico en el que los materiales pueden conducir corrientes eléctricas a bajas temperaturas sin pérdida de energía debido a la resistencia. Los materiales superconductores son capaces de conducir corrientes eléctricas a temperaturas mucho más bajas que los materiales normales. Esto se debe a que los electrones en los materiales superconductores se comportan de manera cooperativa, lo que les permite conducir corrientes eléctricas sin pérdida de energía. Los materiales superconductores tienen muchas aplicaciones
-----------
La capital de España es Madrid.
-----------
La capital de Portugal es Lisboa.
-----------
0, 2, 3, 4, 8, 10
-----------
1. California
2. Oregón
3. Washington
4. Nevada
5. Arizona
-----------
California y Washington.
-----------
1. Maine
2. Nuevo Hampshire
3. Vermont
4. Massachusetts
5. Rhode Island
6. Connecticut
7. Nueva York
8. Nueva Jersey
9. Pensilvania
10. Delaware
-----------
El color de una fresa es rojo brillante.
-----------
El color de la fresa es rojo.
-----------
```
## Contact Us
[4i.ai](https://4i.ai/) provides natural language processing solutions with dialog, vision and voice capabilities to deliver real-life multimodal human-machine conversations.
Please contact us at [email protected]
|
{}
|
task
|
[
"TRANSLATION"
] | 41,529 |
HPLT/sft-fpft-bg-bloom-1b7
|
HPLT
|
text-generation
|
[
"transformers",
"pytorch",
"safetensors",
"bloom",
"text-generation",
"generation",
"question answering",
"instruction tuning",
"bg",
"arxiv:2309.08958",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-04-04T16:45:56Z |
2025-01-24T13:11:39+00:00
| 26 | 0 |
---
language:
- bg
license: cc-by-nc-4.0
tags:
- generation
- question answering
- instruction tuning
---
### Model Description
This HF repository contains base LLMs instruction tuned (SFT) with full-parameter fine-tuning and then used to study whether monolingual or multilingual instruction tuning is more favourable.
* [GitHub](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main)
* [Paper](https://arxiv.org/abs/2309.08958)
#### Instruction tuning details
* Base model: [bloom-1b7](https://huggingface.co/bloom-1b7)
* Instruction tuning language: Bulgarian
* Training method: full-parameter fine-tuning.
* Best checkpoint: best cross-entropy on a validation set, trained for 3 epochs.
* Dataset: machine-translated from [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned). You can download our data [HERE](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main/training-data).
#### Usage
The model checkpoint should be loaded using `transformers` library.
Please refer to our Github repository [HERE](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main/fpft) for inference and training instructions.
#### Citation
```
@inproceedings{chen-etal-2024-monolingual,
title="Monolingual or multilingual instruction tuning: Which makes a better {Alpaca}",
author="Pinzhen Chen and Shaoxiong Ji and Nikolay Bogoychev and Andrey Kutuzov and Barry Haddow and Kenneth Heafield",
year="2024",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
}
```
| null |
Non_BioNLP
|
### Model Description
This HF repository contains base LLMs instruction tuned (SFT) with full-parameter fine-tuning and then used to study whether monolingual or multilingual instruction tuning is more favourable.
* [GitHub](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main)
* [Paper](https://arxiv.org/abs/2309.08958)
#### Instruction tuning details
* Base model: [bloom-1b7](https://huggingface.co/bloom-1b7)
* Instruction tuning language: Bulgarian
* Training method: full-parameter fine-tuning.
* Best checkpoint: best cross-entropy on a validation set, trained for 3 epochs.
* Dataset: machine-translated from [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned). You can download our data [HERE](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main/training-data).
#### Usage
The model checkpoint should be loaded using `transformers` library.
Please refer to our Github repository [HERE](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main/fpft) for inference and training instructions.
#### Citation
```
@inproceedings{chen-etal-2024-monolingual,
title="Monolingual or multilingual instruction tuning: Which makes a better {Alpaca}",
author="Pinzhen Chen and Shaoxiong Ji and Nikolay Bogoychev and Andrey Kutuzov and Barry Haddow and Kenneth Heafield",
year="2024",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
}
```
|
{"language": ["bg"], "license": "cc-by-nc-4.0", "tags": ["generation", "question answering", "instruction tuning"]}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,530 |
bitextor/bicleaner-ai-full-en-tr
|
bitextor
| null |
[
"transformers",
"tf",
"xlm-roberta",
"bicleaner-ai",
"en",
"tr",
"multilingual",
"license:gpl-3.0",
"endpoints_compatible",
"region:us"
] | 2022-12-19T11:23:33Z |
2023-01-10T10:10:30+00:00
| 10 | 0 |
---
language:
- en
- tr
- multilingual
license: gpl-3.0
tags:
- bicleaner-ai
tasks:
- text-classification
---
# Bicleaner AI full model for en-tr
Bicleaner AI is a tool that aims at detecting noisy sentence pairs in a parallel corpus. It
indicates the likelihood of a pair of sentences being mutual translations (with a value near to 1) or not (with a value near to 0).
Sentence pairs considered very noisy are scored with 0.
Find out at our repository for further instructions on how to use it: https://github.com/bitextor/bicleaner-ai
| null |
Non_BioNLP
|
# Bicleaner AI full model for en-tr
Bicleaner AI is a tool that aims at detecting noisy sentence pairs in a parallel corpus. It
indicates the likelihood of a pair of sentences being mutual translations (with a value near to 1) or not (with a value near to 0).
Sentence pairs considered very noisy are scored with 0.
Find out at our repository for further instructions on how to use it: https://github.com/bitextor/bicleaner-ai
|
{"language": ["en", "tr", "multilingual"], "license": "gpl-3.0", "tags": ["bicleaner-ai"], "tasks": ["text-classification"]}
|
task
|
[
"TRANSLATION"
] | 41,531 |
Dhahlan2000/Simple_Translation-model-for-GPT-v12
|
Dhahlan2000
|
text2text-generation
|
[
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:Dhahlan2000/Simple_Translation-model-for-GPT-v11",
"base_model:finetune:Dhahlan2000/Simple_Translation-model-for-GPT-v11",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-06-09T04:15:52Z |
2024-06-09T05:05:34+00:00
| 12 | 0 |
---
base_model: Dhahlan2000/Simple_Translation-model-for-GPT-v11
metrics:
- bleu
tags:
- generated_from_trainer
model-index:
- name: Simple_Translation-model-for-GPT-v12
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. -->
# Simple_Translation-model-for-GPT-v12
This model is a fine-tuned version of [Dhahlan2000/Simple_Translation-model-for-GPT-v11](https://huggingface.co/Dhahlan2000/Simple_Translation-model-for-GPT-v11) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3112
- Bleu: 16.4275
- Gen Len: 18.492
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
| 0.4289 | 1.0 | 9282 | 0.3202 | 16.1676 | 18.4873 |
| 0.4045 | 2.0 | 18564 | 0.3112 | 16.4275 | 18.492 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
| null |
Non_BioNLP
|
<!-- 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. -->
# Simple_Translation-model-for-GPT-v12
This model is a fine-tuned version of [Dhahlan2000/Simple_Translation-model-for-GPT-v11](https://huggingface.co/Dhahlan2000/Simple_Translation-model-for-GPT-v11) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3112
- Bleu: 16.4275
- Gen Len: 18.492
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
| 0.4289 | 1.0 | 9282 | 0.3202 | 16.1676 | 18.4873 |
| 0.4045 | 2.0 | 18564 | 0.3112 | 16.4275 | 18.492 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
|
{"base_model": "Dhahlan2000/Simple_Translation-model-for-GPT-v11", "metrics": ["bleu"], "tags": ["generated_from_trainer"], "model-index": [{"name": "Simple_Translation-model-for-GPT-v12", "results": []}]}
|
task
|
[
"TRANSLATION"
] | 41,532 |
risqaliyevds/xlm-roberta-large-ner
|
risqaliyevds
|
token-classification
|
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"ner",
"uzbek_ner",
"ner_for_uzbek_language",
"uz",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-05-28T10:17:32Z |
2024-06-06T06:11:36+00:00
| 182 | 1 |
---
language:
- uz
license: mit
metrics:
- accuracy
pipeline_tag: token-classification
tags:
- ner
- uzbek_ner
- ner_for_uzbek_language
---
## Named Entity Recognition (NER) Model for Uzbek Language
### About the Model
This model is designed for Named Entity Recognition (NER) in Uzbek text. The model can identify various categories of named entities, including persons, places, organizations, dates, and more. This model is based on the XLM-RoBERTa large architecture.
### Note!!!
The model is trained on the NEWS dataset and primarily has high accuracy for identifying NER in NEWS texts.
### Categories
The model can identify the following NER categories:
- **LOC (Location names)**
- **ORG (Organization names)**
- **PERSON (Person names)**
- **DATE (Date expressions)**
- **MONEY (Monetary amounts)**
- **PERCENT (Percentage values)**
- **QUANTITY (Quantities)**
- **TIME (Time expressions)**
- **PRODUCT (Product names)**
- **EVENT (Event names)**
- **WORK_OF_ART (Work of art titles)**
- **LANGUAGE (Language names)**
- **CARDINAL (Cardinal numbers)**
- **ORDINAL (Ordinal numbers)**
- **NORP (Nationalities or religious/political groups)**
- **FACILITY (Facility names)**
- **LAW (Laws or regulations)**
- **GPE (Countries, cities, states)**
### Examples
To demonstrate how the model works, here are a few examples:
```python
from transformers import pipeline, AutoTokenizer, AutoModelForTokenClassification
model_name_or_path = "risqaliyevds/xlm-roberta-large-ner"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForTokenClassification.from_pretrained(model_name_or_path).to("cuda")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
text = "Shavkat Mirziyoyev Rossiyada rasmiy safarda bo'ldi."
ner = nlp(text)
for entity in ner:
print(entity)
```
Example text: "Shavkat Mirziyoyev Rossiyada rasmiy safarda bo'ldi."
Results:
```python
[{'entity': 'B-PERSON', 'score': 0.88995147, 'index': 1, 'word': '▁Shavkat', 'start': 0, 'end': 7},
{'entity': 'I-PERSON', 'score': 0.980681, 'index': 2, 'word': '▁Mirziyoyev', 'start': 8, 'end': 18},
{'entity': 'B-GPE', 'score': 0.8208886, 'index': 3, 'word': '▁Rossiya', 'start': 19, 'end': 26}]
```
### Loading and Using the Model
To download and use the model from the Hugging Face platform, you can use the following code:
```python
from transformers import pipeline, AutoTokenizer, AutoModelForTokenClassification
model_name_or_path = "risqaliyevds/xlm-roberta-large-ner"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForTokenClassification.from_pretrained(model_name_or_path).to("cuda")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
```
## Contact
If you have any questions or need more information, please contact us.
LinkedIn: [Riskaliev Murad](https://www.linkedin.com/in/risqaliyevds/)
### License
This model is provided as open source and is available for free use by all users.
### Conclusion
The NER model for the Uzbek language is effective in identifying various named entities in texts. The high accuracy and wide range of categories make it useful for academic research, document analysis, and many other fields.
| null |
Non_BioNLP
|
## Named Entity Recognition (NER) Model for Uzbek Language
### About the Model
This model is designed for Named Entity Recognition (NER) in Uzbek text. The model can identify various categories of named entities, including persons, places, organizations, dates, and more. This model is based on the XLM-RoBERTa large architecture.
### Note!!!
The model is trained on the NEWS dataset and primarily has high accuracy for identifying NER in NEWS texts.
### Categories
The model can identify the following NER categories:
- **LOC (Location names)**
- **ORG (Organization names)**
- **PERSON (Person names)**
- **DATE (Date expressions)**
- **MONEY (Monetary amounts)**
- **PERCENT (Percentage values)**
- **QUANTITY (Quantities)**
- **TIME (Time expressions)**
- **PRODUCT (Product names)**
- **EVENT (Event names)**
- **WORK_OF_ART (Work of art titles)**
- **LANGUAGE (Language names)**
- **CARDINAL (Cardinal numbers)**
- **ORDINAL (Ordinal numbers)**
- **NORP (Nationalities or religious/political groups)**
- **FACILITY (Facility names)**
- **LAW (Laws or regulations)**
- **GPE (Countries, cities, states)**
### Examples
To demonstrate how the model works, here are a few examples:
```python
from transformers import pipeline, AutoTokenizer, AutoModelForTokenClassification
model_name_or_path = "risqaliyevds/xlm-roberta-large-ner"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForTokenClassification.from_pretrained(model_name_or_path).to("cuda")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
text = "Shavkat Mirziyoyev Rossiyada rasmiy safarda bo'ldi."
ner = nlp(text)
for entity in ner:
print(entity)
```
Example text: "Shavkat Mirziyoyev Rossiyada rasmiy safarda bo'ldi."
Results:
```python
[{'entity': 'B-PERSON', 'score': 0.88995147, 'index': 1, 'word': '▁Shavkat', 'start': 0, 'end': 7},
{'entity': 'I-PERSON', 'score': 0.980681, 'index': 2, 'word': '▁Mirziyoyev', 'start': 8, 'end': 18},
{'entity': 'B-GPE', 'score': 0.8208886, 'index': 3, 'word': '▁Rossiya', 'start': 19, 'end': 26}]
```
### Loading and Using the Model
To download and use the model from the Hugging Face platform, you can use the following code:
```python
from transformers import pipeline, AutoTokenizer, AutoModelForTokenClassification
model_name_or_path = "risqaliyevds/xlm-roberta-large-ner"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForTokenClassification.from_pretrained(model_name_or_path).to("cuda")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
```
## Contact
If you have any questions or need more information, please contact us.
LinkedIn: [Riskaliev Murad](https://www.linkedin.com/in/risqaliyevds/)
### License
This model is provided as open source and is available for free use by all users.
### Conclusion
The NER model for the Uzbek language is effective in identifying various named entities in texts. The high accuracy and wide range of categories make it useful for academic research, document analysis, and many other fields.
|
{"language": ["uz"], "license": "mit", "metrics": ["accuracy"], "pipeline_tag": "token-classification", "tags": ["ner", "uzbek_ner", "ner_for_uzbek_language"]}
|
task
|
[
"NAMED_ENTITY_RECOGNITION"
] | 41,534 |
RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf
|
RichardErkhov
| null |
[
"gguf",
"endpoints_compatible",
"region:us"
] | 2024-07-23T01:32:21Z |
2024-07-23T15:59:14+00:00
| 38 | 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)
Llama-2-13b-chat-norwegian - GGUF
- Model creator: https://huggingface.co/RuterNorway/
- Original model: https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-2-13b-chat-norwegian.Q2_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q2_K.gguf) | Q2_K | 4.52GB |
| [Llama-2-13b-chat-norwegian.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ3_XS.gguf) | IQ3_XS | 4.99GB |
| [Llama-2-13b-chat-norwegian.IQ3_S.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ3_S.gguf) | IQ3_S | 5.27GB |
| [Llama-2-13b-chat-norwegian.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q3_K_S.gguf) | Q3_K_S | 5.27GB |
| [Llama-2-13b-chat-norwegian.IQ3_M.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ3_M.gguf) | IQ3_M | 5.57GB |
| [Llama-2-13b-chat-norwegian.Q3_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q3_K.gguf) | Q3_K | 5.9GB |
| [Llama-2-13b-chat-norwegian.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q3_K_M.gguf) | Q3_K_M | 5.9GB |
| [Llama-2-13b-chat-norwegian.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q3_K_L.gguf) | Q3_K_L | 6.45GB |
| [Llama-2-13b-chat-norwegian.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ4_XS.gguf) | IQ4_XS | 6.54GB |
| [Llama-2-13b-chat-norwegian.Q4_0.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_0.gguf) | Q4_0 | 6.86GB |
| [Llama-2-13b-chat-norwegian.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ4_NL.gguf) | IQ4_NL | 6.9GB |
| [Llama-2-13b-chat-norwegian.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_K_S.gguf) | Q4_K_S | 6.91GB |
| [Llama-2-13b-chat-norwegian.Q4_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_K.gguf) | Q4_K | 7.33GB |
| [Llama-2-13b-chat-norwegian.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_K_M.gguf) | Q4_K_M | 7.33GB |
| [Llama-2-13b-chat-norwegian.Q4_1.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_1.gguf) | Q4_1 | 7.61GB |
| [Llama-2-13b-chat-norwegian.Q5_0.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_0.gguf) | Q5_0 | 8.36GB |
| [Llama-2-13b-chat-norwegian.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_K_S.gguf) | Q5_K_S | 8.36GB |
| [Llama-2-13b-chat-norwegian.Q5_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_K.gguf) | Q5_K | 8.6GB |
| [Llama-2-13b-chat-norwegian.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_K_M.gguf) | Q5_K_M | 8.6GB |
| [Llama-2-13b-chat-norwegian.Q5_1.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_1.gguf) | Q5_1 | 9.1GB |
| [Llama-2-13b-chat-norwegian.Q6_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q6_K.gguf) | Q6_K | 9.95GB |
| [Llama-2-13b-chat-norwegian.Q8_0.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q8_0.gguf) | Q8_0 | 12.88GB |
Original model description:
---
license: llama2
tags:
- pytorch
- llama
- llama-2
- norwegian
- norsk
datasets:
- NbAiLab/norwegian-alpaca
- RuterNorway/OpenOrcaNo-15k
language:
- en
- 'no'
pipeline_tag: text-generation
---
# Llama 2 13b Chat Norwegian
Llama-2-13b-chat-norwegian is a variant of [Meta](https://huggingface.co/meta-llama)´s [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned on a mix of norwegian datasets created in [Ruter AI Lab](https://ruter.no) the summer of 2023.
The model is tuned to understand and generate text in Norwegian. It's trained for one epoch on norwegian-alpaca + 15000 samples of machine-translated data from OpenOrca. A small subset of custom-made instructional data is also included.
For other versions of this model see:
* [Llama-2-13b-chat-norwegian](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian)
* [Llama-2-13b-chat-norwegian-LoRa](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-LoRa)
* [Llama-2-13b-chat-norwegian-GPTQ](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-GPTQ)
## Data
* Norwegian alpaca
* 15k Norwegian OpenOrcra (to be released)
* Small subset of custom made instructional data
## Intended Use
This model is intended for commercial and research use in Norwegian and can be used as an assistant-like chat.
## Prompt Template
Llama2 Chat uses a new prompt format:
```
<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. Please answer in the same language as the user.
<</SYS>>
This is a test question[/INST] This is a answer </s><s>
```
See also the original implementation [here](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L213).
We also implemented the alpaca prompt format, which the model supports.:
```
### Instruction:
Summarize following text.
### Input:
Text to be summarized
### Response:
```
## Why this model?
As a Norwegian company, we understand firsthand the pressing need for powerful language models tailored to specific languages. Our primary focus is on the Norwegian linguistic landscape. In the age of digitization, languages that lack robust, open-source models can risk becoming marginalized. This is why we're introducing this open-source Norwegian model. We believe that by making such resources freely accessible, we can democratize information, foster innovation, and create a more inclusive digital ecosystem. Our aspiration is for this model to serve as a foundational resource for future specialized Norwegian models. Ultimately, our goal is to bolster the Norwegian NLP community and facilitate the smoother integration of Norwegian models into diverse projects.
## Limitations
* This is an LLM, not a knowledge model. It can not be expected to have more information about Norway than the basemodel.
* It will generally preform better on tasks that involves summarization, question answering and chat, than on tasks that requires more knowledge about Norway, specific domains, or tasks where the model can answer freely.
* The data used for training is machine translated, and may contain grammatical errors and other errors.
* The model is released as is, and would in most cases need prompt tuning to achieve optimal results.
## License
Llama 2 is licensed under the LLAMA 2 [Community License](https://ai.meta.com/resources/models-and-libraries/llama-downloads/), Copyright © Meta Platforms, Inc. All Rights Reserved.
See the original [model card](https://huggingface.co/meta-llama/Llama-2-13b) for more information.
From [norwegian-alpaca](https://huggingface.co/NbAiLab/norwegian-alpaca) we also note that "the current version uses OpenAI's gpt-3.5-turbo; hence, this dataset cannot be used to create models that compete in any way against OpenAI."
## Disclaimer
* The model is available "as is". Ruter As takes no responsibility for further use.
* During testing, it seems that the safeguards implemented by Meta, still work as expected in this model. However, we want to point to the Ethical Considerations and Limitations from the origenal model card:
```
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts.
Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
```
## Credits
This model was made at Ruters AI Lab which is a part of Ruters Data & AI division.
___
# Llama 2 13b Chat Norwegian (Norsk)
Llama-2-13b-chat-norwegian er en versjon av [Meta](https://huggingface.co/meta-llama) sin [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned på en kombinasjon av diverse norske datasett. Modellen ble laget i [Ruter AI Lab](https://ruter.no) 2023.
Modellen er finetuned til å forstå og generere tekst på Norsk. Den er trent i én epoch med norwegian-alpaca + et utvalg av 15000 maskinoversatt data fra OpenOrca. Det består og av et lite sett med selvlagde instruksjonsdata
Andre versjoner av modellen:
* [Llama-2-13b-chat-norwegian](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian)
* [Llama-2-13b-chat-norwegian-LoRa](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-LoRa)
* [Llama-2-13b-chat-norwegian-GPTQ](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-GPTQ)
## Data
* Norwegian alpaca
* 15k Norwegian OpenOrcra (venter på utgivelse)
* Lite sett med selvlagde instruksjonsdata
## Prompt Mal
Llama2 Chat bruker et nytt prompt format:
```
<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. Please answer in the same language as the user.
<</SYS>>
This is a test question[/INST] This is a answer </s><s>
```
Se orgianl implementasjon [her](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L213).
Vi har også implementert alpaca prompt formatet, som også er støttet av modellen.
```
### Instruction:
Summarize following text.
### Input:
Text to be summarized
### Response:
```
## Hvorfor denne modellen?
Som et norsk selskap forstår vi selv det presserende behovet for kraftige språkmodeller tilpasset spesifikke språk. Vårt primære fokus er på det norske språkområdet. I den digitale alderen risikerer språk som mangler robuste, åpne kildekodemodeller å bli marginalisert. Dette er grunnen til at vi nå introduserer denne åpne kildekodemodellen for norsk. Vi tror at ved å gjøre disse ressursene tilgjengelige gratis, kan vi demokratisere informasjonen, fremme innovasjon og skape et mer inkluderende digitalt økosystem. Vår ambisjon er at denne modellen skal tjene som en grunnleggende ressurs for fremtidige spesialiserte norske modeller. Vårt mål er å styrke det norske NLP-miljøet og gjøre det enklere å innlemme norske modeller i ulike prosjekter.
## Begrensninger
* Dette er en LLM, ikke en kunnskapsmodell. Den kan ikke forventes å ha mer informasjon om Norge enn basismodellen.
* Den vil generelt prestere bedre på oppgaver som innebærer oppsummering, spørsmålsbesvarelse og chat, enn på oppgaver som krever mer kunnskap om Norge, spesifikke domener, eller oppgaver hvor modellen kan svare fritt.
* Dataene som brukes til trening er maskinoversatt, og kan inneholde grammatiske feil. Vi har kun gjort en rask manuell sjekk av dataene.
* Modellen er utgitt som den er, og vil i de fleste tilfeller trenge "prompt tuning" for å oppnå ønskede resultater.
## Lisens
Llama 2 er lisensiert under LLAMA 2 [Community License](https://ai.meta.com/resources/models-and-libraries/llama-downloads/), Copyright © Meta Platforms, Inc. All Rights Reserved.
Se det orginale [modell kortet](https://huggingface.co/meta-llama/Llama-2-13b) for mer informasjon.
Fra [norwegian-alpaca](https://huggingface.co/NbAiLab/norwegian-alpaca) vil vi gjøre oppmerksomme på at "the current version uses OpenAI's gpt-3.5-turbo; hence, this dataset cannot be used to create models that compete in any way against OpenAI."
## Ansvarsfraskrivelse
* Modellen tilgjengeliggjøres «som den er». Ruter As tar ikke noe ansvar for videre bruk.
* Under testingen virket det som sikkerhetstiltakene implementert av Meta fortsatt fungerer som forventet for denne modellen. Vi gjør derimot oppmerksom på de etiske betraktiningene og begrensningene fra det orignale modellkortet:
```
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts.
Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
```
| null |
Non_BioNLP
|
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Llama-2-13b-chat-norwegian - GGUF
- Model creator: https://huggingface.co/RuterNorway/
- Original model: https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-2-13b-chat-norwegian.Q2_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q2_K.gguf) | Q2_K | 4.52GB |
| [Llama-2-13b-chat-norwegian.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ3_XS.gguf) | IQ3_XS | 4.99GB |
| [Llama-2-13b-chat-norwegian.IQ3_S.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ3_S.gguf) | IQ3_S | 5.27GB |
| [Llama-2-13b-chat-norwegian.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q3_K_S.gguf) | Q3_K_S | 5.27GB |
| [Llama-2-13b-chat-norwegian.IQ3_M.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ3_M.gguf) | IQ3_M | 5.57GB |
| [Llama-2-13b-chat-norwegian.Q3_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q3_K.gguf) | Q3_K | 5.9GB |
| [Llama-2-13b-chat-norwegian.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q3_K_M.gguf) | Q3_K_M | 5.9GB |
| [Llama-2-13b-chat-norwegian.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q3_K_L.gguf) | Q3_K_L | 6.45GB |
| [Llama-2-13b-chat-norwegian.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ4_XS.gguf) | IQ4_XS | 6.54GB |
| [Llama-2-13b-chat-norwegian.Q4_0.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_0.gguf) | Q4_0 | 6.86GB |
| [Llama-2-13b-chat-norwegian.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.IQ4_NL.gguf) | IQ4_NL | 6.9GB |
| [Llama-2-13b-chat-norwegian.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_K_S.gguf) | Q4_K_S | 6.91GB |
| [Llama-2-13b-chat-norwegian.Q4_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_K.gguf) | Q4_K | 7.33GB |
| [Llama-2-13b-chat-norwegian.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_K_M.gguf) | Q4_K_M | 7.33GB |
| [Llama-2-13b-chat-norwegian.Q4_1.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q4_1.gguf) | Q4_1 | 7.61GB |
| [Llama-2-13b-chat-norwegian.Q5_0.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_0.gguf) | Q5_0 | 8.36GB |
| [Llama-2-13b-chat-norwegian.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_K_S.gguf) | Q5_K_S | 8.36GB |
| [Llama-2-13b-chat-norwegian.Q5_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_K.gguf) | Q5_K | 8.6GB |
| [Llama-2-13b-chat-norwegian.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_K_M.gguf) | Q5_K_M | 8.6GB |
| [Llama-2-13b-chat-norwegian.Q5_1.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q5_1.gguf) | Q5_1 | 9.1GB |
| [Llama-2-13b-chat-norwegian.Q6_K.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q6_K.gguf) | Q6_K | 9.95GB |
| [Llama-2-13b-chat-norwegian.Q8_0.gguf](https://huggingface.co/RichardErkhov/RuterNorway_-_Llama-2-13b-chat-norwegian-gguf/blob/main/Llama-2-13b-chat-norwegian.Q8_0.gguf) | Q8_0 | 12.88GB |
Original model description:
---
license: llama2
tags:
- pytorch
- llama
- llama-2
- norwegian
- norsk
datasets:
- NbAiLab/norwegian-alpaca
- RuterNorway/OpenOrcaNo-15k
language:
- en
- 'no'
pipeline_tag: text-generation
---
# Llama 2 13b Chat Norwegian
Llama-2-13b-chat-norwegian is a variant of [Meta](https://huggingface.co/meta-llama)´s [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned on a mix of norwegian datasets created in [Ruter AI Lab](https://ruter.no) the summer of 2023.
The model is tuned to understand and generate text in Norwegian. It's trained for one epoch on norwegian-alpaca + 15000 samples of machine-translated data from OpenOrca. A small subset of custom-made instructional data is also included.
For other versions of this model see:
* [Llama-2-13b-chat-norwegian](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian)
* [Llama-2-13b-chat-norwegian-LoRa](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-LoRa)
* [Llama-2-13b-chat-norwegian-GPTQ](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-GPTQ)
## Data
* Norwegian alpaca
* 15k Norwegian OpenOrcra (to be released)
* Small subset of custom made instructional data
## Intended Use
This model is intended for commercial and research use in Norwegian and can be used as an assistant-like chat.
## Prompt Template
Llama2 Chat uses a new prompt format:
```
<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. Please answer in the same language as the user.
<</SYS>>
This is a test question[/INST] This is a answer </s><s>
```
See also the original implementation [here](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L213).
We also implemented the alpaca prompt format, which the model supports.:
```
### Instruction:
Summarize following text.
### Input:
Text to be summarized
### Response:
```
## Why this model?
As a Norwegian company, we understand firsthand the pressing need for powerful language models tailored to specific languages. Our primary focus is on the Norwegian linguistic landscape. In the age of digitization, languages that lack robust, open-source models can risk becoming marginalized. This is why we're introducing this open-source Norwegian model. We believe that by making such resources freely accessible, we can democratize information, foster innovation, and create a more inclusive digital ecosystem. Our aspiration is for this model to serve as a foundational resource for future specialized Norwegian models. Ultimately, our goal is to bolster the Norwegian NLP community and facilitate the smoother integration of Norwegian models into diverse projects.
## Limitations
* This is an LLM, not a knowledge model. It can not be expected to have more information about Norway than the basemodel.
* It will generally preform better on tasks that involves summarization, question answering and chat, than on tasks that requires more knowledge about Norway, specific domains, or tasks where the model can answer freely.
* The data used for training is machine translated, and may contain grammatical errors and other errors.
* The model is released as is, and would in most cases need prompt tuning to achieve optimal results.
## License
Llama 2 is licensed under the LLAMA 2 [Community License](https://ai.meta.com/resources/models-and-libraries/llama-downloads/), Copyright © Meta Platforms, Inc. All Rights Reserved.
See the original [model card](https://huggingface.co/meta-llama/Llama-2-13b) for more information.
From [norwegian-alpaca](https://huggingface.co/NbAiLab/norwegian-alpaca) we also note that "the current version uses OpenAI's gpt-3.5-turbo; hence, this dataset cannot be used to create models that compete in any way against OpenAI."
## Disclaimer
* The model is available "as is". Ruter As takes no responsibility for further use.
* During testing, it seems that the safeguards implemented by Meta, still work as expected in this model. However, we want to point to the Ethical Considerations and Limitations from the origenal model card:
```
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts.
Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
```
## Credits
This model was made at Ruters AI Lab which is a part of Ruters Data & AI division.
___
# Llama 2 13b Chat Norwegian (Norsk)
Llama-2-13b-chat-norwegian er en versjon av [Meta](https://huggingface.co/meta-llama) sin [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned på en kombinasjon av diverse norske datasett. Modellen ble laget i [Ruter AI Lab](https://ruter.no) 2023.
Modellen er finetuned til å forstå og generere tekst på Norsk. Den er trent i én epoch med norwegian-alpaca + et utvalg av 15000 maskinoversatt data fra OpenOrca. Det består og av et lite sett med selvlagde instruksjonsdata
Andre versjoner av modellen:
* [Llama-2-13b-chat-norwegian](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian)
* [Llama-2-13b-chat-norwegian-LoRa](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-LoRa)
* [Llama-2-13b-chat-norwegian-GPTQ](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-GPTQ)
## Data
* Norwegian alpaca
* 15k Norwegian OpenOrcra (venter på utgivelse)
* Lite sett med selvlagde instruksjonsdata
## Prompt Mal
Llama2 Chat bruker et nytt prompt format:
```
<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. Please answer in the same language as the user.
<</SYS>>
This is a test question[/INST] This is a answer </s><s>
```
Se orgianl implementasjon [her](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L213).
Vi har også implementert alpaca prompt formatet, som også er støttet av modellen.
```
### Instruction:
Summarize following text.
### Input:
Text to be summarized
### Response:
```
## Hvorfor denne modellen?
Som et norsk selskap forstår vi selv det presserende behovet for kraftige språkmodeller tilpasset spesifikke språk. Vårt primære fokus er på det norske språkområdet. I den digitale alderen risikerer språk som mangler robuste, åpne kildekodemodeller å bli marginalisert. Dette er grunnen til at vi nå introduserer denne åpne kildekodemodellen for norsk. Vi tror at ved å gjøre disse ressursene tilgjengelige gratis, kan vi demokratisere informasjonen, fremme innovasjon og skape et mer inkluderende digitalt økosystem. Vår ambisjon er at denne modellen skal tjene som en grunnleggende ressurs for fremtidige spesialiserte norske modeller. Vårt mål er å styrke det norske NLP-miljøet og gjøre det enklere å innlemme norske modeller i ulike prosjekter.
## Begrensninger
* Dette er en LLM, ikke en kunnskapsmodell. Den kan ikke forventes å ha mer informasjon om Norge enn basismodellen.
* Den vil generelt prestere bedre på oppgaver som innebærer oppsummering, spørsmålsbesvarelse og chat, enn på oppgaver som krever mer kunnskap om Norge, spesifikke domener, eller oppgaver hvor modellen kan svare fritt.
* Dataene som brukes til trening er maskinoversatt, og kan inneholde grammatiske feil. Vi har kun gjort en rask manuell sjekk av dataene.
* Modellen er utgitt som den er, og vil i de fleste tilfeller trenge "prompt tuning" for å oppnå ønskede resultater.
## Lisens
Llama 2 er lisensiert under LLAMA 2 [Community License](https://ai.meta.com/resources/models-and-libraries/llama-downloads/), Copyright © Meta Platforms, Inc. All Rights Reserved.
Se det orginale [modell kortet](https://huggingface.co/meta-llama/Llama-2-13b) for mer informasjon.
Fra [norwegian-alpaca](https://huggingface.co/NbAiLab/norwegian-alpaca) vil vi gjøre oppmerksomme på at "the current version uses OpenAI's gpt-3.5-turbo; hence, this dataset cannot be used to create models that compete in any way against OpenAI."
## Ansvarsfraskrivelse
* Modellen tilgjengeliggjøres «som den er». Ruter As tar ikke noe ansvar for videre bruk.
* Under testingen virket det som sikkerhetstiltakene implementert av Meta fortsatt fungerer som forventet for denne modellen. Vi gjør derimot oppmerksom på de etiske betraktiningene og begrensningene fra det orignale modellkortet:
```
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts.
Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
```
|
{}
|
task
|
[
"QUESTION_ANSWERING",
"SUMMARIZATION"
] | 41,535 |
MaLA-LM/lucky52-bloom-7b1-no-15
|
MaLA-LM
|
text-generation
|
[
"transformers",
"pytorch",
"bloom",
"text-generation",
"generation",
"question answering",
"instruction tuning",
"multilingual",
"dataset:MBZUAI/Bactrian-X",
"arxiv:2404.04850",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-04-04T09:00:19Z |
2025-04-08T17:05:40+00:00
| 11 | 0 |
---
datasets:
- MBZUAI/Bactrian-X
language:
- multilingual
library_name: transformers
license: cc-by-nc-4.0
pipeline_tag: text-generation
tags:
- generation
- question answering
- instruction tuning
---
### Model Description
This HF repository hosts instruction fine-tuned multilingual BLOOM model using the parallel instruction dataset called Bactrain-X in 52 languages.
We progressively add a language during instruction fine-tuning at each time, and train 52 models in total. Then, we evaluate those models in three multilingual benchmarks.
Please refer to [our paper](https://arxiv.org/abs/2404.04850) for more details.
* Base model: [BLOOM 7B1](https://huggingface.co/bigscience/bloom-7b1)
* Instruction languages: English, Chinese, Afrikaans, Arabic, Azerbaijani, Bengali, Czech, German, Spanish, Estonian, Farsi, Finnish, French, Galician, Gujarati
* Instruction language codes: en, zh, af, ar, az, bn, cs, de, es, et, fa, fi, fr, gl, gu
* Training method: full-parameter fine-tuning.
### Usage
The model checkpoint should be loaded using `transformers` library.
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-15")
model = AutoModelForCausalLM.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-15")
```
### Citation
```
@inproceedings{ji2025lucky52,
title={How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM},
author={Shaoxiong Ji and Pinzhen Chen},
year={2025},
booktitle={Proceedings of COLING},
url={https://arxiv.org/abs/2404.04850},
}
```
| null |
Non_BioNLP
|
### Model Description
This HF repository hosts instruction fine-tuned multilingual BLOOM model using the parallel instruction dataset called Bactrain-X in 52 languages.
We progressively add a language during instruction fine-tuning at each time, and train 52 models in total. Then, we evaluate those models in three multilingual benchmarks.
Please refer to [our paper](https://arxiv.org/abs/2404.04850) for more details.
* Base model: [BLOOM 7B1](https://huggingface.co/bigscience/bloom-7b1)
* Instruction languages: English, Chinese, Afrikaans, Arabic, Azerbaijani, Bengali, Czech, German, Spanish, Estonian, Farsi, Finnish, French, Galician, Gujarati
* Instruction language codes: en, zh, af, ar, az, bn, cs, de, es, et, fa, fi, fr, gl, gu
* Training method: full-parameter fine-tuning.
### Usage
The model checkpoint should be loaded using `transformers` library.
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-15")
model = AutoModelForCausalLM.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-15")
```
### Citation
```
@inproceedings{ji2025lucky52,
title={How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM},
author={Shaoxiong Ji and Pinzhen Chen},
year={2025},
booktitle={Proceedings of COLING},
url={https://arxiv.org/abs/2404.04850},
}
```
|
{"datasets": ["MBZUAI/Bactrian-X"], "language": ["multilingual"], "library_name": "transformers", "license": "cc-by-nc-4.0", "pipeline_tag": "text-generation", "tags": ["generation", "question answering", "instruction tuning"]}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,536 |
kmowais/ArabictoEng
|
kmowais
|
translation
|
[
"translation",
"ar",
"en",
"dataset:huggingface/language_codes_marianMT",
"arxiv:1910.09700",
"base_model:Helsinki-NLP/opus-mt-ar-en",
"base_model:finetune:Helsinki-NLP/opus-mt-ar-en",
"license:llama3.3",
"region:us"
] | 2025-01-12T08:31:40Z |
2025-01-12T08:35:50+00:00
| 0 | 1 |
---
base_model:
- onnx-community/tiny-random-MarianMTModel
- Helsinki-NLP/opus-mt-ar-en
- razxr/finetuned_MarianMTModel
datasets:
- huggingface/language_codes_marianMT
language:
- ar
- en
license: llama3.3
pipeline_tag: translation
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| null |
Non_BioNLP
|
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"base_model": ["onnx-community/tiny-random-MarianMTModel", "Helsinki-NLP/opus-mt-ar-en", "razxr/finetuned_MarianMTModel"], "datasets": ["huggingface/language_codes_marianMT"], "language": ["ar", "en"], "license": "llama3.3", "pipeline_tag": "translation"}
|
task
|
[
"TRANSLATION"
] | 41,537 |
google/paligemma-3b-ft-vizwizvqa-224-jax
|
google
|
image-text-to-text
|
[
"big_vision",
"paligemma",
"jax",
"image-text-to-text",
"arxiv:2310.09199",
"arxiv:2303.15343",
"arxiv:2403.08295",
"arxiv:1706.03762",
"arxiv:2010.11929",
"arxiv:2209.06794",
"arxiv:2209.04372",
"arxiv:2103.01913",
"arxiv:2401.06209",
"arxiv:2305.10355",
"arxiv:2205.12522",
"arxiv:2110.11624",
"arxiv:2108.03353",
"arxiv:2010.04295",
"arxiv:2203.10244",
"arxiv:1810.12440",
"arxiv:1905.13648",
"arxiv:1608.00272",
"arxiv:1908.04913",
"arxiv:2407.07726",
"license:gemma",
"region:us"
] | 2024-05-12T02:44:01Z |
2024-07-19T12:09:31+00:00
| 29 | 0 |
---
library_name: big_vision
license: gemma
pipeline_tag: image-text-to-text
tags:
- paligemma
- jax
extra_gated_heading: Access PaliGemma on Hugging Face
extra_gated_prompt: To access PaliGemma on Hugging Face, you’re required to review
and agree to Google’s usage license. To do this, please ensure you’re logged-in
to Hugging Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
---
# PaliGemma model card
**Model page:** [PaliGemma](https://ai.google.dev/gemma/docs/paligemma)
JAX/FLAX PaliGemma 3B weights, fine-tuned with 224*224 input images on the <a href="https://vizwiz.org/tasks-and-datasets/vqa/">VizWiz_VQA</a> dataset. The models are available in float32, bfloat16 and float16 format for research purposes only. The fine-tune config is available at <a href="https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/transfers/vizwizvqa.py">big_vision</a>.
**Resources and technical documentation:**
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [PaliGemma on Kaggle](https://www.kaggle.com/models/google/paligemma)
* [PaliGemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/363)
**Terms of Use:** [Terms](https://www.kaggle.com/models/google/paligemma-ft/license/consent/verify/huggingface?returnModelRepoId=google/paligemma-3b-ft-vizwizvqa-224-jax)
**Authors:** Google
## Model information
### Model summary
#### Description
PaliGemma is a versatile and lightweight vision-language model (VLM) inspired by
[PaLI-3](https://arxiv.org/abs/2310.09199) and based on open components such as
the [SigLIP vision model](https://arxiv.org/abs/2303.15343) and the [Gemma
language model](https://arxiv.org/abs/2403.08295). It takes both image and text
as input and generates text as output, supporting multiple languages. It is designed for class-leading fine-tune performance on a wide range of vision-language tasks such as image and short video caption, visual question answering, text reading, object detection and object segmentation.
#### Model architecture
PaliGemma is the composition of a [Transformer
decoder](https://arxiv.org/abs/1706.03762) and a [Vision Transformer image
encoder](https://arxiv.org/abs/2010.11929), with a total of 3 billion
params. The text decoder is initialized from
[Gemma-2B](https://www.kaggle.com/models/google/gemma). The image encoder is
initialized from
[SigLIP-So400m/14](https://colab.research.google.com/github/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/SigLIP_demo.ipynb).
PaliGemma is trained following the PaLI-3 recipes.
#### Inputs and outputs
* **Input:** Image and text string, such as a prompt to caption the image, or
a question.
* **Output:** Generated text in response to the input, such as a caption of
the image, an answer to a question, a list of object bounding box
coordinates, or segmentation codewords.
### Model data
#### Pre-train datasets
PaliGemma is pre-trained on the following mixture of datasets:
* **WebLI:** [WebLI (Web Language Image)](https://arxiv.org/abs/2209.06794) is
a web-scale multilingual image-text dataset built from the public web. A
wide range of WebLI splits are used to acquire versatile model capabilities,
such as visual semantic understanding, object localization,
visually-situated text understanding, multilinguality, etc.
* **CC3M-35L:** Curated English image-alt_text pairs from webpages ([Sharma et
al., 2018](https://aclanthology.org/P18-1238/)). We used the [Google Cloud
Translation API](https://cloud.google.com/translate) to translate into 34
additional languages.
* **VQ²A-CC3M-35L/VQG-CC3M-35L:** A subset of VQ2A-CC3M ([Changpinyo et al.,
2022a](https://aclanthology.org/2022.naacl-main.142/)), translated into the
same additional 34 languages as CC3M-35L, using the [Google Cloud
Translation API](https://cloud.google.com/translate).
* **OpenImages:** Detection and object-aware questions and answers
([Piergiovanni et al. 2022](https://arxiv.org/abs/2209.04372)) generated by
handcrafted rules on the [OpenImages dataset].
* **WIT:** Images and texts collected from Wikipedia ([Srinivasan et al.,
2021](https://arxiv.org/abs/2103.01913)).
[OpenImages dataset]: https://storage.googleapis.com/openimages/web/factsfigures_v7.html
#### Data responsibility filtering
The following filters are applied to WebLI, with the goal of training PaliGemma
on clean data:
* **Pornographic image filtering:** This filter removes images deemed to be of
pornographic nature.
* **Text safety filtering:** We identify and filter out images that are paired
with unsafe text. Unsafe text is any text deemed to contain or be about
CSAI, pornography, vulgarities, or otherwise offensive.
* **Text toxicity filtering:** We further use the [Perspective
API](https://perspectiveapi.com/) to identify and filter out images that are
paired with text deemed insulting, obscene, hateful or otherwise toxic.
* **Text personal information filtering:** We filtered certain personal information and other sensitive data using [Cloud Data Loss Prevention (DLP)
API](https://cloud.google.com/security/products/dlp) to protect the privacy
of individuals. Identifiers such as social security numbers and [other sensitive information types] were removed.
* **Additional methods:** Filtering based on content quality and safety in
line with our policies and practices.
[other sensitive information types]: https://cloud.google.com/sensitive-data-protection/docs/high-sensitivity-infotypes-reference?_gl=1*jg604m*_ga*ODk5MzA3ODQyLjE3MTAzMzQ3NTk.*_ga_WH2QY8WWF5*MTcxMDUxNTkxMS4yLjEuMTcxMDUxNjA2NC4wLjAuMA..&_ga=2.172110058.-899307842.1710334759
## Implementation information
### Hardware
PaliGemma was trained using the latest generation of Tensor Processing Unit
(TPU) hardware (TPUv5e).
### Software
Training was done using [JAX](https://github.com/google/jax),
[Flax](https://github.com/google/flax),
[TFDS](https://github.com/tensorflow/datasets) and
[`big_vision`](https://github.com/google-research/big_vision).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
TFDS is used to access datasets and Flax is used for model architecture. The
PaliGemma fine-tune code and inference code are released in the `big_vision`
GitHub repository.
## Evaluation information
### Benchmark results
In order to verify the transferability of PaliGemma to a wide variety of
academic tasks, we fine-tune the pretrained models on each task. Additionally we
train the mix model with a mixture of the transfer tasks. We report results on
different resolutions to provide an impression of which tasks benefit from
increased resolution. Importantly, none of these tasks or datasets are part of
the pretraining data mixture, and their images are explicitly removed from the
web-scale pre-training data.
#### Mix model (fine-tune on mixture of transfer tasks)
<table>
<tbody><tr>
<th>Benchmark</th>
<th>Metric (split)</th>
<th>mix-224</th>
<th>mix-448</th>
</tr>
<tr>
<td><a href="https://arxiv.org/abs/2401.06209">MMVP</a></td>
<td>Paired Accuracy</td>
<td>46.00</td>
<td>45.33</td>
</tr>
<tr>
<td><a href="https://arxiv.org/abs/2305.10355">POPE</a></td>
<td>Accuracy<br>(random/popular/adversarial)</td>
<td>
88.00<br>
86.63<br>
85.67
</td>
<td>
89.37<br>
88.40<br>
87.47
</td>
</tr>
<tr>
<td><a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a></td>
<td>Accuracy (test)</td>
<td>65.20</td>
<td>65.47</td>
</tr>
</tbody></table>
#### Single task (fine-tune on single task)
<table>
<tbody><tr>
<th>Benchmark<br>(train split)</th>
<th>Metric<br>(split)</th>
<th>pt-224</th>
<th>pt-448</th>
<th>pt-896</th>
</tr>
<tr>
<th>Captioning</th>
</tr>
<tr>
<td>
<a href="https://cocodataset.org/#home">COCO captions</a><br>(train+restval)
</td>
<td>CIDEr (val)</td>
<td>141.92</td>
<td>144.60</td>
</tr>
<tr>
<td>
<a href="https://nocaps.org/">NoCaps</a><br>(Eval of COCO<br>captions transfer)
</td>
<td>CIDEr (val)</td>
<td>121.72</td>
<td>123.58</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/pdf/2205.12522">COCO-35L</a><br>(train)
</td>
<td>CIDEr dev<br>(en/avg-34/avg)</td>
<td>
139.2<br>
115.8<br>
116.4
</td>
<td>
141.2<br>
118.0<br>
118.6
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/pdf/2205.12522">XM3600</a><br>(Eval of COCO-35L transfer)
</td>
<td>CIDEr dev<br>(en/avg-34/avg)</td>
<td>
78.1<br>
41.3<br>
42.4
</td>
<td>
80.0<br>
41.9<br>
42.9
</td>
</tr>
<tr>
<td>
<a href="https://textvqa.org/textcaps/">TextCaps</a><br>(train)
</td>
<td>CIDEr (val)</td>
<td>127.48</td>
<td>153.94</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2110.11624">SciCap</a><br>(first sentence, no subfigure)<br>(train+val)
</td>
<td>CIDEr/BLEU-4<br>(test)</td>
<td>
162.25<br>
0.192<br>
</td>
<td>
181.49<br>
0.211<br>
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2108.03353">Screen2words</a><br>(train+dev)
</td>
<td>CIDEr (test)</td>
<td>117.57</td>
<td>119.59</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2010.04295">Widget Captioning</a><br>(train+dev)
</td>
<td>CIDEr (test)</td>
<td>136.07</td>
<td>148.36</td>
</tr>
<tr>
<th>Question answering</th>
</tr>
<tr>
<td>
<a href="https://visualqa.org/index.html">VQAv2</a><br>(train+validation)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>83.19</td>
<td>85.64</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2401.06209">MMVP</a><br>(Eval of VQAv2 transfer)
</td>
<td>Paired Accuracy</td>
<td>47.33</td>
<td>45.33</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2305.10355">POPE</a><br>(Eval of VQAv2 transfer)
</td>
<td>Accuracy<br>(random/popular/<br>adversarial)</td>
<td>
87.80<br>
85.87<br>
84.27
</td>
<td>
88.23<br>
86.77<br>
85.90
</td>
</tr>
<tr>
<td>
<a href="https://okvqa.allenai.org/">OKVQA</a><br>(train)
</td>
<td>Accuracy (val)</td>
<td>63.54</td>
<td>63.15</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (MC)<br>(train+val)
</td>
<td>Accuracy<br>(Test server)</td>
<td>76.37</td>
<td>76.90</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (DA)<br>(train+val)
</td>
<td>Accuracy<br>(Test server)</td>
<td>61.85</td>
<td>63.22</td>
</tr>
<tr>
<td>
<a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a><br>(train_balanced+<br>val_balanced)
</td>
<td>Accuracy<br>(testdev balanced)</td>
<td>65.61</td>
<td>67.03</td>
</tr>
<tr>
<td>
<a href="https://aclanthology.org/2022.findings-acl.196/">xGQA</a><br>(Eval of GQA transfer)
</td>
<td>Mean Accuracy<br>(bn, de, en, id,<br>ko, pt, ru, zh)</td>
<td>58.37</td>
<td>59.07</td>
</tr>
<tr>
<td>
<a href="https://lil.nlp.cornell.edu/nlvr/">NLVR2</a><br>(train+dev)
</td>
<td>Accuracy (test)</td>
<td>90.02</td>
<td>88.93</td>
</tr>
<tr>
<td>
<a href="https://marvl-challenge.github.io/">MaRVL</a><br>(Eval of NLVR2 transfer)
</td>
<td>Mean Accuracy<br>(test)<br>(id, sw, ta, tr, zh)</td>
<td>80.57</td>
<td>76.78</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/data/diagrams">AI2D</a><br>(train)
</td>
<td>Accuracy (test)</td>
<td>72.12</td>
<td>73.28</td>
</tr>
<tr>
<td>
<a href="https://scienceqa.github.io/">ScienceQA</a><br>(Img subset, no CoT)<br>(train+val)
</td>
<td>Accuracy (test)</td>
<td>95.39</td>
<td>95.93</td>
</tr>
<tr>
<td>
<a href="https://zenodo.org/records/6344334">RSVQA-LR</a> (Non numeric)<br>(train+val)
</td>
<td>Mean Accuracy<br>(test)</td>
<td>92.65</td>
<td>93.11</td>
</tr>
<tr>
<td>
<a href="https://zenodo.org/records/6344367">RSVQA-HR</a> (Non numeric)<br>(train+val)
</td>
<td>Mean Accuracy<br>(test/test2)</td>
<td>
92.61<br>
90.58
</td>
<td>
92.79<br>
90.54
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2203.10244">ChartQA</a><br>(human+aug)x(train+val)
</td>
<td>Mean Relaxed<br>Accuracy<br>(test_human,<br>test_aug)</td>
<td>57.08</td>
<td>71.36</td>
</tr>
<tr>
<td>
<a href="https://vizwiz.org/tasks-and-datasets/vqa/">VizWiz VQA</a><br>(train+val)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>
73.7
</td>
<td>
75.52
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1810.12440">TallyQA</a><br>(train)
</td>
<td>Accuracy<br>(test_simple/<br>test_complex)</td>
<td>
81.72<br>
69.56
</td>
<td>
84.86<br>
72.27
</td>
</tr>
<tr>
<td>
<a href="https://ocr-vqa.github.io/">OCR-VQA</a><br>(train+val)
</td>
<td>Accuracy (test)</td>
<td>72.32</td>
<td>74.61</td>
<td>74.93</td>
</tr>
<tr>
<td>
<a href="https://textvqa.org/">TextVQA</a><br>(train+val)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>55.47</td>
<td>73.15</td>
<td>76.48</td>
</tr>
<tr>
<td>
<a href="https://www.docvqa.org/">DocVQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>43.74</td>
<td>78.02</td>
<td>84.77</td>
</tr>
<tr>
<td>
<a href="https://openaccess.thecvf.com/content/WACV2022/papers/Mathew_InfographicVQA_WACV_2022_paper.pdf">Infographic VQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>28.46</td>
<td>40.47</td>
<td>47.75</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1905.13648">SceneText VQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>63.29</td>
<td>81.82</td>
<td>84.40</td>
</tr>
<tr>
<th>Segmentation</th>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1608.00272">RefCOCO</a><br>(combined refcoco, refcoco+,<br>refcocog excluding val<br>and test images)
</td>
<td>MIoU<br>(validation)<br>refcoco/refcoco+/<br>refcocog</td>
<td>
73.40<br>
68.32<br>
67.65
</td>
<td>
75.57<br>
69.76<br>
70.17
</td>
<td>
76.94<br>
72.18<br>
72.22
</td>
</tr>
<tr>
<th>Video tasks (Caption/QA)</th>
</tr>
<tr>
<td>MSR-VTT (Captioning)</td>
<td>CIDEr (test)</td>
<td>70.54</td>
</tr>
<tr>
<td>MSR-VTT (QA)</td>
<td>Accuracy (test)</td>
<td>50.09</td>
</tr>
<tr>
<td>ActivityNet (Captioning)</td>
<td>CIDEr (test)</td>
<td>34.62</td>
</tr>
<tr>
<td>ActivityNet (QA)</td>
<td>Accuracy (test)</td>
<td>50.78</td>
</tr>
<tr>
<td>VATEX (Captioning)</td>
<td>CIDEr (test)</td>
<td>79.73</td>
</tr>
<tr>
<td>MSVD (QA)</td>
<td>Accuracy (test)</td>
<td>60.22</td>
</tr>
</tbody></table>
## Ethics and safety
### Evaluation approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Human evaluation on prompts covering child safety, content safety and
representational harms. See the [Gemma model
card](https://ai.google.dev/gemma/docs/model_card#evaluation_approach) for
more details on evaluation approach, but with image captioning and visual
question answering setups.
* Image-to-Text benchmark evaluation: Benchmark against relevant academic
datasets such as FairFace Dataset ([Karkkainen et al.,
2021](https://arxiv.org/abs/1908.04913)).
### Evaluation results
* The human evaluation results of ethics and safety evaluations are within
acceptable thresholds for meeting [internal
policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11)
for categories such as child safety, content safety and representational
harms.
* On top of robust internal evaluations, we also use the Perspective API
(threshold of 0.8) to measure toxicity, profanity, and other potential
issues in the generated captions for images sourced from the FairFace
dataset. We report the maximum and median values observed across subgroups
for each of the perceived gender, ethnicity, and age attributes.
<table>
<tbody><tr>
</tr></tbody><tbody><tr><th>Metric</th>
<th>Perceived<br>gender</th>
<th></th>
<th>Ethnicity</th>
<th></th>
<th>Age group</th>
<th></th>
</tr>
<tr>
<th></th>
<th>Maximum</th>
<th>Median</th>
<th>Maximum</th>
<th>Median</th>
<th>Maximum</th>
<th>Median</th>
</tr>
<tr>
<td>Toxicity</td>
<td>0.04%</td>
<td>0.03%</td>
<td>0.08%</td>
<td>0.00%</td>
<td>0.09%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Identity Attack</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Insult</td>
<td>0.06%</td>
<td>0.04%</td>
<td>0.09%</td>
<td>0.07%</td>
<td>0.16%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Threat</td>
<td>0.06%</td>
<td>0.05%</td>
<td>0.14%</td>
<td>0.05%</td>
<td>0.17%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Profanity</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
</tr>
</tbody></table>
## Usage and limitations
### Intended usage
Open Vision Language Models (VLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
Fine-tune on specific vision-language task:
* The pre-trained models can be fine-tuned on a wide range of vision-language
tasks such as: image captioning, short video caption, visual question
answering, text reading, object detection and object segmentation.
* The pre-trained models can be fine-tuned for specific domains such as remote
sensing question answering, visual questions from people who are blind,
science question answering, describe UI element functionalities.
* The pre-trained models can be fine-tuned for tasks with non-textual outputs
such as bounding boxes or segmentation masks.
Vision-language research:
* The pre-trained models and fine-tuned models can serve as a foundation for researchers to experiment with VLM
techniques, develop algorithms, and contribute to the advancement of the
field.
### Ethical considerations and risks
The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following:
* Bias and Fairness
* VLMs trained on large-scale, real-world image-text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card.
* Misinformation and Misuse
* VLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](https://ai.google.dev/responsible).
* Transparency and Accountability
* This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share innovation by making VLM technology accessible to developers and researchers across the AI ecosystem.
Risks identified and mitigations:
* **Perpetuation of biases:** It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* **Generation of harmful content:** Mechanisms and guidelines for content
safety are essential. Developers are encouraged to exercise caution and
implement appropriate content safety safeguards based on their specific
product policies and application use cases.
* **Misuse for malicious purposes:** Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the [Gemma
Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* **Privacy violations:** Models were trained on data filtered to remove certain personal information and sensitive data. Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques.
### Limitations
* Most limitations inherited from the underlying Gemma model still apply:
* VLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* Natural language is inherently complex. VLMs might struggle to grasp
subtle nuances, sarcasm, or figurative language.
* VLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* VLMs rely on statistical patterns in language and images. They might
lack the ability to apply common sense reasoning in certain situations.
* PaliGemma was designed first and foremost to serve as a general pre-trained
model for transfer to specialized tasks. Hence, its "out of the box" or
"zero-shot" performance might lag behind models designed specifically for
that.
* PaliGemma is not a multi-turn chatbot. It is designed for a single round of
image and text input.
## Citation
```bibtex
@article{beyer2024paligemma,
title={{PaliGemma: A versatile 3B VLM for transfer}},
author={Lucas Beyer* and Andreas Steiner* and André Susano Pinto* and Alexander Kolesnikov* and Xiao Wang* and Daniel Salz and Maxim Neumann and Ibrahim Alabdulmohsin and Michael Tschannen and Emanuele Bugliarello and Thomas Unterthiner and Daniel Keysers and Skanda Koppula and Fangyu Liu and Adam Grycner and Alexey Gritsenko and Neil Houlsby and Manoj Kumar and Keran Rong and Julian Eisenschlos and Rishabh Kabra and Matthias Bauer and Matko Bošnjak and Xi Chen and Matthias Minderer and Paul Voigtlaender and Ioana Bica and Ivana Balazevic and Joan Puigcerver and Pinelopi Papalampidi and Olivier Henaff and Xi Xiong and Radu Soricut and Jeremiah Harmsen and Xiaohua Zhai*},
year={2024},
journal={arXiv preprint arXiv:2407.07726}
}
```
Find the paper [here](https://arxiv.org/abs/2407.07726).
| null |
Non_BioNLP
|
# PaliGemma model card
**Model page:** [PaliGemma](https://ai.google.dev/gemma/docs/paligemma)
JAX/FLAX PaliGemma 3B weights, fine-tuned with 224*224 input images on the <a href="https://vizwiz.org/tasks-and-datasets/vqa/">VizWiz_VQA</a> dataset. The models are available in float32, bfloat16 and float16 format for research purposes only. The fine-tune config is available at <a href="https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/transfers/vizwizvqa.py">big_vision</a>.
**Resources and technical documentation:**
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [PaliGemma on Kaggle](https://www.kaggle.com/models/google/paligemma)
* [PaliGemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/363)
**Terms of Use:** [Terms](https://www.kaggle.com/models/google/paligemma-ft/license/consent/verify/huggingface?returnModelRepoId=google/paligemma-3b-ft-vizwizvqa-224-jax)
**Authors:** Google
## Model information
### Model summary
#### Description
PaliGemma is a versatile and lightweight vision-language model (VLM) inspired by
[PaLI-3](https://arxiv.org/abs/2310.09199) and based on open components such as
the [SigLIP vision model](https://arxiv.org/abs/2303.15343) and the [Gemma
language model](https://arxiv.org/abs/2403.08295). It takes both image and text
as input and generates text as output, supporting multiple languages. It is designed for class-leading fine-tune performance on a wide range of vision-language tasks such as image and short video caption, visual question answering, text reading, object detection and object segmentation.
#### Model architecture
PaliGemma is the composition of a [Transformer
decoder](https://arxiv.org/abs/1706.03762) and a [Vision Transformer image
encoder](https://arxiv.org/abs/2010.11929), with a total of 3 billion
params. The text decoder is initialized from
[Gemma-2B](https://www.kaggle.com/models/google/gemma). The image encoder is
initialized from
[SigLIP-So400m/14](https://colab.research.google.com/github/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/SigLIP_demo.ipynb).
PaliGemma is trained following the PaLI-3 recipes.
#### Inputs and outputs
* **Input:** Image and text string, such as a prompt to caption the image, or
a question.
* **Output:** Generated text in response to the input, such as a caption of
the image, an answer to a question, a list of object bounding box
coordinates, or segmentation codewords.
### Model data
#### Pre-train datasets
PaliGemma is pre-trained on the following mixture of datasets:
* **WebLI:** [WebLI (Web Language Image)](https://arxiv.org/abs/2209.06794) is
a web-scale multilingual image-text dataset built from the public web. A
wide range of WebLI splits are used to acquire versatile model capabilities,
such as visual semantic understanding, object localization,
visually-situated text understanding, multilinguality, etc.
* **CC3M-35L:** Curated English image-alt_text pairs from webpages ([Sharma et
al., 2018](https://aclanthology.org/P18-1238/)). We used the [Google Cloud
Translation API](https://cloud.google.com/translate) to translate into 34
additional languages.
* **VQ²A-CC3M-35L/VQG-CC3M-35L:** A subset of VQ2A-CC3M ([Changpinyo et al.,
2022a](https://aclanthology.org/2022.naacl-main.142/)), translated into the
same additional 34 languages as CC3M-35L, using the [Google Cloud
Translation API](https://cloud.google.com/translate).
* **OpenImages:** Detection and object-aware questions and answers
([Piergiovanni et al. 2022](https://arxiv.org/abs/2209.04372)) generated by
handcrafted rules on the [OpenImages dataset].
* **WIT:** Images and texts collected from Wikipedia ([Srinivasan et al.,
2021](https://arxiv.org/abs/2103.01913)).
[OpenImages dataset]: https://storage.googleapis.com/openimages/web/factsfigures_v7.html
#### Data responsibility filtering
The following filters are applied to WebLI, with the goal of training PaliGemma
on clean data:
* **Pornographic image filtering:** This filter removes images deemed to be of
pornographic nature.
* **Text safety filtering:** We identify and filter out images that are paired
with unsafe text. Unsafe text is any text deemed to contain or be about
CSAI, pornography, vulgarities, or otherwise offensive.
* **Text toxicity filtering:** We further use the [Perspective
API](https://perspectiveapi.com/) to identify and filter out images that are
paired with text deemed insulting, obscene, hateful or otherwise toxic.
* **Text personal information filtering:** We filtered certain personal information and other sensitive data using [Cloud Data Loss Prevention (DLP)
API](https://cloud.google.com/security/products/dlp) to protect the privacy
of individuals. Identifiers such as social security numbers and [other sensitive information types] were removed.
* **Additional methods:** Filtering based on content quality and safety in
line with our policies and practices.
[other sensitive information types]: https://cloud.google.com/sensitive-data-protection/docs/high-sensitivity-infotypes-reference?_gl=1*jg604m*_ga*ODk5MzA3ODQyLjE3MTAzMzQ3NTk.*_ga_WH2QY8WWF5*MTcxMDUxNTkxMS4yLjEuMTcxMDUxNjA2NC4wLjAuMA..&_ga=2.172110058.-899307842.1710334759
## Implementation information
### Hardware
PaliGemma was trained using the latest generation of Tensor Processing Unit
(TPU) hardware (TPUv5e).
### Software
Training was done using [JAX](https://github.com/google/jax),
[Flax](https://github.com/google/flax),
[TFDS](https://github.com/tensorflow/datasets) and
[`big_vision`](https://github.com/google-research/big_vision).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
TFDS is used to access datasets and Flax is used for model architecture. The
PaliGemma fine-tune code and inference code are released in the `big_vision`
GitHub repository.
## Evaluation information
### Benchmark results
In order to verify the transferability of PaliGemma to a wide variety of
academic tasks, we fine-tune the pretrained models on each task. Additionally we
train the mix model with a mixture of the transfer tasks. We report results on
different resolutions to provide an impression of which tasks benefit from
increased resolution. Importantly, none of these tasks or datasets are part of
the pretraining data mixture, and their images are explicitly removed from the
web-scale pre-training data.
#### Mix model (fine-tune on mixture of transfer tasks)
<table>
<tbody><tr>
<th>Benchmark</th>
<th>Metric (split)</th>
<th>mix-224</th>
<th>mix-448</th>
</tr>
<tr>
<td><a href="https://arxiv.org/abs/2401.06209">MMVP</a></td>
<td>Paired Accuracy</td>
<td>46.00</td>
<td>45.33</td>
</tr>
<tr>
<td><a href="https://arxiv.org/abs/2305.10355">POPE</a></td>
<td>Accuracy<br>(random/popular/adversarial)</td>
<td>
88.00<br>
86.63<br>
85.67
</td>
<td>
89.37<br>
88.40<br>
87.47
</td>
</tr>
<tr>
<td><a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a></td>
<td>Accuracy (test)</td>
<td>65.20</td>
<td>65.47</td>
</tr>
</tbody></table>
#### Single task (fine-tune on single task)
<table>
<tbody><tr>
<th>Benchmark<br>(train split)</th>
<th>Metric<br>(split)</th>
<th>pt-224</th>
<th>pt-448</th>
<th>pt-896</th>
</tr>
<tr>
<th>Captioning</th>
</tr>
<tr>
<td>
<a href="https://cocodataset.org/#home">COCO captions</a><br>(train+restval)
</td>
<td>CIDEr (val)</td>
<td>141.92</td>
<td>144.60</td>
</tr>
<tr>
<td>
<a href="https://nocaps.org/">NoCaps</a><br>(Eval of COCO<br>captions transfer)
</td>
<td>CIDEr (val)</td>
<td>121.72</td>
<td>123.58</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/pdf/2205.12522">COCO-35L</a><br>(train)
</td>
<td>CIDEr dev<br>(en/avg-34/avg)</td>
<td>
139.2<br>
115.8<br>
116.4
</td>
<td>
141.2<br>
118.0<br>
118.6
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/pdf/2205.12522">XM3600</a><br>(Eval of COCO-35L transfer)
</td>
<td>CIDEr dev<br>(en/avg-34/avg)</td>
<td>
78.1<br>
41.3<br>
42.4
</td>
<td>
80.0<br>
41.9<br>
42.9
</td>
</tr>
<tr>
<td>
<a href="https://textvqa.org/textcaps/">TextCaps</a><br>(train)
</td>
<td>CIDEr (val)</td>
<td>127.48</td>
<td>153.94</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2110.11624">SciCap</a><br>(first sentence, no subfigure)<br>(train+val)
</td>
<td>CIDEr/BLEU-4<br>(test)</td>
<td>
162.25<br>
0.192<br>
</td>
<td>
181.49<br>
0.211<br>
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2108.03353">Screen2words</a><br>(train+dev)
</td>
<td>CIDEr (test)</td>
<td>117.57</td>
<td>119.59</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2010.04295">Widget Captioning</a><br>(train+dev)
</td>
<td>CIDEr (test)</td>
<td>136.07</td>
<td>148.36</td>
</tr>
<tr>
<th>Question answering</th>
</tr>
<tr>
<td>
<a href="https://visualqa.org/index.html">VQAv2</a><br>(train+validation)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>83.19</td>
<td>85.64</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2401.06209">MMVP</a><br>(Eval of VQAv2 transfer)
</td>
<td>Paired Accuracy</td>
<td>47.33</td>
<td>45.33</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2305.10355">POPE</a><br>(Eval of VQAv2 transfer)
</td>
<td>Accuracy<br>(random/popular/<br>adversarial)</td>
<td>
87.80<br>
85.87<br>
84.27
</td>
<td>
88.23<br>
86.77<br>
85.90
</td>
</tr>
<tr>
<td>
<a href="https://okvqa.allenai.org/">OKVQA</a><br>(train)
</td>
<td>Accuracy (val)</td>
<td>63.54</td>
<td>63.15</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (MC)<br>(train+val)
</td>
<td>Accuracy<br>(Test server)</td>
<td>76.37</td>
<td>76.90</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (DA)<br>(train+val)
</td>
<td>Accuracy<br>(Test server)</td>
<td>61.85</td>
<td>63.22</td>
</tr>
<tr>
<td>
<a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a><br>(train_balanced+<br>val_balanced)
</td>
<td>Accuracy<br>(testdev balanced)</td>
<td>65.61</td>
<td>67.03</td>
</tr>
<tr>
<td>
<a href="https://aclanthology.org/2022.findings-acl.196/">xGQA</a><br>(Eval of GQA transfer)
</td>
<td>Mean Accuracy<br>(bn, de, en, id,<br>ko, pt, ru, zh)</td>
<td>58.37</td>
<td>59.07</td>
</tr>
<tr>
<td>
<a href="https://lil.nlp.cornell.edu/nlvr/">NLVR2</a><br>(train+dev)
</td>
<td>Accuracy (test)</td>
<td>90.02</td>
<td>88.93</td>
</tr>
<tr>
<td>
<a href="https://marvl-challenge.github.io/">MaRVL</a><br>(Eval of NLVR2 transfer)
</td>
<td>Mean Accuracy<br>(test)<br>(id, sw, ta, tr, zh)</td>
<td>80.57</td>
<td>76.78</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/data/diagrams">AI2D</a><br>(train)
</td>
<td>Accuracy (test)</td>
<td>72.12</td>
<td>73.28</td>
</tr>
<tr>
<td>
<a href="https://scienceqa.github.io/">ScienceQA</a><br>(Img subset, no CoT)<br>(train+val)
</td>
<td>Accuracy (test)</td>
<td>95.39</td>
<td>95.93</td>
</tr>
<tr>
<td>
<a href="https://zenodo.org/records/6344334">RSVQA-LR</a> (Non numeric)<br>(train+val)
</td>
<td>Mean Accuracy<br>(test)</td>
<td>92.65</td>
<td>93.11</td>
</tr>
<tr>
<td>
<a href="https://zenodo.org/records/6344367">RSVQA-HR</a> (Non numeric)<br>(train+val)
</td>
<td>Mean Accuracy<br>(test/test2)</td>
<td>
92.61<br>
90.58
</td>
<td>
92.79<br>
90.54
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2203.10244">ChartQA</a><br>(human+aug)x(train+val)
</td>
<td>Mean Relaxed<br>Accuracy<br>(test_human,<br>test_aug)</td>
<td>57.08</td>
<td>71.36</td>
</tr>
<tr>
<td>
<a href="https://vizwiz.org/tasks-and-datasets/vqa/">VizWiz VQA</a><br>(train+val)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>
73.7
</td>
<td>
75.52
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1810.12440">TallyQA</a><br>(train)
</td>
<td>Accuracy<br>(test_simple/<br>test_complex)</td>
<td>
81.72<br>
69.56
</td>
<td>
84.86<br>
72.27
</td>
</tr>
<tr>
<td>
<a href="https://ocr-vqa.github.io/">OCR-VQA</a><br>(train+val)
</td>
<td>Accuracy (test)</td>
<td>72.32</td>
<td>74.61</td>
<td>74.93</td>
</tr>
<tr>
<td>
<a href="https://textvqa.org/">TextVQA</a><br>(train+val)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>55.47</td>
<td>73.15</td>
<td>76.48</td>
</tr>
<tr>
<td>
<a href="https://www.docvqa.org/">DocVQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>43.74</td>
<td>78.02</td>
<td>84.77</td>
</tr>
<tr>
<td>
<a href="https://openaccess.thecvf.com/content/WACV2022/papers/Mathew_InfographicVQA_WACV_2022_paper.pdf">Infographic VQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>28.46</td>
<td>40.47</td>
<td>47.75</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1905.13648">SceneText VQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>63.29</td>
<td>81.82</td>
<td>84.40</td>
</tr>
<tr>
<th>Segmentation</th>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1608.00272">RefCOCO</a><br>(combined refcoco, refcoco+,<br>refcocog excluding val<br>and test images)
</td>
<td>MIoU<br>(validation)<br>refcoco/refcoco+/<br>refcocog</td>
<td>
73.40<br>
68.32<br>
67.65
</td>
<td>
75.57<br>
69.76<br>
70.17
</td>
<td>
76.94<br>
72.18<br>
72.22
</td>
</tr>
<tr>
<th>Video tasks (Caption/QA)</th>
</tr>
<tr>
<td>MSR-VTT (Captioning)</td>
<td>CIDEr (test)</td>
<td>70.54</td>
</tr>
<tr>
<td>MSR-VTT (QA)</td>
<td>Accuracy (test)</td>
<td>50.09</td>
</tr>
<tr>
<td>ActivityNet (Captioning)</td>
<td>CIDEr (test)</td>
<td>34.62</td>
</tr>
<tr>
<td>ActivityNet (QA)</td>
<td>Accuracy (test)</td>
<td>50.78</td>
</tr>
<tr>
<td>VATEX (Captioning)</td>
<td>CIDEr (test)</td>
<td>79.73</td>
</tr>
<tr>
<td>MSVD (QA)</td>
<td>Accuracy (test)</td>
<td>60.22</td>
</tr>
</tbody></table>
## Ethics and safety
### Evaluation approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Human evaluation on prompts covering child safety, content safety and
representational harms. See the [Gemma model
card](https://ai.google.dev/gemma/docs/model_card#evaluation_approach) for
more details on evaluation approach, but with image captioning and visual
question answering setups.
* Image-to-Text benchmark evaluation: Benchmark against relevant academic
datasets such as FairFace Dataset ([Karkkainen et al.,
2021](https://arxiv.org/abs/1908.04913)).
### Evaluation results
* The human evaluation results of ethics and safety evaluations are within
acceptable thresholds for meeting [internal
policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11)
for categories such as child safety, content safety and representational
harms.
* On top of robust internal evaluations, we also use the Perspective API
(threshold of 0.8) to measure toxicity, profanity, and other potential
issues in the generated captions for images sourced from the FairFace
dataset. We report the maximum and median values observed across subgroups
for each of the perceived gender, ethnicity, and age attributes.
<table>
<tbody><tr>
</tr></tbody><tbody><tr><th>Metric</th>
<th>Perceived<br>gender</th>
<th></th>
<th>Ethnicity</th>
<th></th>
<th>Age group</th>
<th></th>
</tr>
<tr>
<th></th>
<th>Maximum</th>
<th>Median</th>
<th>Maximum</th>
<th>Median</th>
<th>Maximum</th>
<th>Median</th>
</tr>
<tr>
<td>Toxicity</td>
<td>0.04%</td>
<td>0.03%</td>
<td>0.08%</td>
<td>0.00%</td>
<td>0.09%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Identity Attack</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Insult</td>
<td>0.06%</td>
<td>0.04%</td>
<td>0.09%</td>
<td>0.07%</td>
<td>0.16%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Threat</td>
<td>0.06%</td>
<td>0.05%</td>
<td>0.14%</td>
<td>0.05%</td>
<td>0.17%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Profanity</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
</tr>
</tbody></table>
## Usage and limitations
### Intended usage
Open Vision Language Models (VLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
Fine-tune on specific vision-language task:
* The pre-trained models can be fine-tuned on a wide range of vision-language
tasks such as: image captioning, short video caption, visual question
answering, text reading, object detection and object segmentation.
* The pre-trained models can be fine-tuned for specific domains such as remote
sensing question answering, visual questions from people who are blind,
science question answering, describe UI element functionalities.
* The pre-trained models can be fine-tuned for tasks with non-textual outputs
such as bounding boxes or segmentation masks.
Vision-language research:
* The pre-trained models and fine-tuned models can serve as a foundation for researchers to experiment with VLM
techniques, develop algorithms, and contribute to the advancement of the
field.
### Ethical considerations and risks
The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following:
* Bias and Fairness
* VLMs trained on large-scale, real-world image-text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card.
* Misinformation and Misuse
* VLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](https://ai.google.dev/responsible).
* Transparency and Accountability
* This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share innovation by making VLM technology accessible to developers and researchers across the AI ecosystem.
Risks identified and mitigations:
* **Perpetuation of biases:** It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* **Generation of harmful content:** Mechanisms and guidelines for content
safety are essential. Developers are encouraged to exercise caution and
implement appropriate content safety safeguards based on their specific
product policies and application use cases.
* **Misuse for malicious purposes:** Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the [Gemma
Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* **Privacy violations:** Models were trained on data filtered to remove certain personal information and sensitive data. Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques.
### Limitations
* Most limitations inherited from the underlying Gemma model still apply:
* VLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* Natural language is inherently complex. VLMs might struggle to grasp
subtle nuances, sarcasm, or figurative language.
* VLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* VLMs rely on statistical patterns in language and images. They might
lack the ability to apply common sense reasoning in certain situations.
* PaliGemma was designed first and foremost to serve as a general pre-trained
model for transfer to specialized tasks. Hence, its "out of the box" or
"zero-shot" performance might lag behind models designed specifically for
that.
* PaliGemma is not a multi-turn chatbot. It is designed for a single round of
image and text input.
## Citation
```bibtex
@article{beyer2024paligemma,
title={{PaliGemma: A versatile 3B VLM for transfer}},
author={Lucas Beyer* and Andreas Steiner* and André Susano Pinto* and Alexander Kolesnikov* and Xiao Wang* and Daniel Salz and Maxim Neumann and Ibrahim Alabdulmohsin and Michael Tschannen and Emanuele Bugliarello and Thomas Unterthiner and Daniel Keysers and Skanda Koppula and Fangyu Liu and Adam Grycner and Alexey Gritsenko and Neil Houlsby and Manoj Kumar and Keran Rong and Julian Eisenschlos and Rishabh Kabra and Matthias Bauer and Matko Bošnjak and Xi Chen and Matthias Minderer and Paul Voigtlaender and Ioana Bica and Ivana Balazevic and Joan Puigcerver and Pinelopi Papalampidi and Olivier Henaff and Xi Xiong and Radu Soricut and Jeremiah Harmsen and Xiaohua Zhai*},
year={2024},
journal={arXiv preprint arXiv:2407.07726}
}
```
Find the paper [here](https://arxiv.org/abs/2407.07726).
|
{"library_name": "big_vision", "license": "gemma", "pipeline_tag": "image-text-to-text", "tags": ["paligemma", "jax"], "extra_gated_heading": "Access PaliGemma on Hugging Face", "extra_gated_prompt": "To access PaliGemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately.", "extra_gated_button_content": "Acknowledge license"}
|
task
|
[
"QUESTION_ANSWERING",
"TRANSLATION"
] | 41,538 |
bobox/DeBERTaV3-small-SentenceTransformer-AdaptiveLayerBaseline
|
bobox
|
sentence-similarity
|
[
"sentence-transformers",
"pytorch",
"deberta-v2",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:314315",
"loss:AdaptiveLayerLoss",
"loss:MultipleNegativesRankingLoss",
"en",
"dataset:stanfordnlp/snli",
"dataset:sentence-transformers/stsb",
"arxiv:1908.10084",
"arxiv:2402.14776",
"arxiv:1705.00652",
"base_model:microsoft/deberta-v3-small",
"base_model:finetune:microsoft/deberta-v3-small",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-06-10T00:21:12Z |
2024-06-10T00:21:46+00:00
| 16 | 0 |
---
base_model: microsoft/deberta-v3-small
datasets:
- stanfordnlp/snli
- sentence-transformers/stsb
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
- cosine_accuracy
- cosine_accuracy_threshold
- cosine_f1
- cosine_f1_threshold
- cosine_precision
- cosine_recall
- cosine_ap
- dot_accuracy
- dot_accuracy_threshold
- dot_f1
- dot_f1_threshold
- dot_precision
- dot_recall
- dot_ap
- manhattan_accuracy
- manhattan_accuracy_threshold
- manhattan_f1
- manhattan_f1_threshold
- manhattan_precision
- manhattan_recall
- manhattan_ap
- euclidean_accuracy
- euclidean_accuracy_threshold
- euclidean_f1
- euclidean_f1_threshold
- euclidean_precision
- euclidean_recall
- euclidean_ap
- max_accuracy
- max_accuracy_threshold
- max_f1
- max_f1_threshold
- max_precision
- max_recall
- max_ap
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:314315
- loss:AdaptiveLayerLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: Two teenage girls conversing next to lockers.
sentences:
- Girls talking about their problems next to lockers.
- A bully tries to pop a balloon without being caught in the act.
- Two dogs standing together in the yard.
- source_sentence: A young man in a heavy brown winter coat stands in front of a blue
railing with his arms spread.
sentences:
- a boy holding onto the wall of an old brick house's raised foundation as construction
occurs
- The railing is in front of a frozen lake.
- A skateboarder is doing tricks for a competition.
- source_sentence: A shirtless man with a white hat and no shoes sitting crisscross
with his back against the wall holding up a white plastic cup.
sentences:
- A long-haired boy riding his skateboard at a fast pace over a stone wall with
graffiti.
- A man is sitting crisscross
- a child in a black ninja suit does a kick
- source_sentence: A light colored dog leaps over a hurdle.
sentences:
- Men sit on the bus going to work,
- A dog jumps over a obstacel.
- a man standing on his motorbike.
- source_sentence: people are standing near water with a boat heading their direction
sentences:
- People are standing near water with a large blue boat heading their direction.
- Two people climbing on a wooden scaffold.
- The dogs are near the toy.
model-index:
- name: SentenceTransformer based on microsoft/deberta-v3-small
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: Unknown
type: unknown
metrics:
- type: pearson_cosine
value: 0.7660217567682521
name: Pearson Cosine
- type: spearman_cosine
value: 0.7681125489633884
name: Spearman Cosine
- type: pearson_manhattan
value: 0.7917532885619117
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.794675885405013
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.7860948725725584
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.7895594746178918
name: Spearman Euclidean
- type: pearson_dot
value: 0.644843928972524
name: Pearson Dot
- type: spearman_dot
value: 0.6427588138459626
name: Spearman Dot
- type: pearson_max
value: 0.7917532885619117
name: Pearson Max
- type: spearman_max
value: 0.794675885405013
name: Spearman Max
- task:
type: binary-classification
name: Binary Classification
dataset:
name: Unknown
type: unknown
metrics:
- type: cosine_accuracy
value: 0.6730608840700584
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.5814725160598755
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0.7170495061078964
name: Cosine F1
- type: cosine_f1_threshold
value: 0.4670722782611847
name: Cosine F1 Threshold
- type: cosine_precision
value: 0.5977392321184954
name: Cosine Precision
- type: cosine_recall
value: 0.895866802979407
name: Cosine Recall
- type: cosine_ap
value: 0.7193483203625508
name: Cosine Ap
- type: dot_accuracy
value: 0.6444764576541057
name: Dot Accuracy
- type: dot_accuracy_threshold
value: 71.95508575439453
name: Dot Accuracy Threshold
- type: dot_f1
value: 0.7094262988661364
name: Dot F1
- type: dot_f1_threshold
value: 53.77289581298828
name: Dot F1 Threshold
- type: dot_precision
value: 0.5779411764705882
name: Dot Precision
- type: dot_recall
value: 0.9183584051409376
name: Dot Recall
- type: dot_ap
value: 0.6828334101602328
name: Dot Ap
- type: manhattan_accuracy
value: 0.6664644779740693
name: Manhattan Accuracy
- type: manhattan_accuracy_threshold
value: 213.6251678466797
name: Manhattan Accuracy Threshold
- type: manhattan_f1
value: 0.7047102517243412
name: Manhattan F1
- type: manhattan_f1_threshold
value: 245.20578002929688
name: Manhattan F1 Threshold
- type: manhattan_precision
value: 0.5908461842625544
name: Manhattan Precision
- type: manhattan_recall
value: 0.8729370527238206
name: Manhattan Recall
- type: manhattan_ap
value: 0.7132026586783923
name: Manhattan Ap
- type: euclidean_accuracy
value: 0.6621426946698006
name: Euclidean Accuracy
- type: euclidean_accuracy_threshold
value: 10.358880996704102
name: Euclidean Accuracy Threshold
- type: euclidean_f1
value: 0.7024081560907013
name: Euclidean F1
- type: euclidean_f1_threshold
value: 12.010871887207031
name: Euclidean F1 Threshold
- type: euclidean_precision
value: 0.5864970645792563
name: Euclidean Precision
- type: euclidean_recall
value: 0.8754198919234701
name: Euclidean Recall
- type: euclidean_ap
value: 0.7101786172295015
name: Euclidean Ap
- type: max_accuracy
value: 0.6730608840700584
name: Max Accuracy
- type: max_accuracy_threshold
value: 213.6251678466797
name: Max Accuracy Threshold
- type: max_f1
value: 0.7170495061078964
name: Max F1
- type: max_f1_threshold
value: 245.20578002929688
name: Max F1 Threshold
- type: max_precision
value: 0.5977392321184954
name: Max Precision
- type: max_recall
value: 0.9183584051409376
name: Max Recall
- type: max_ap
value: 0.7193483203625508
name: Max Ap
---
# 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 [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) dataset. 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 Dataset:**
- [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli)
- **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-SentenceTransformer-AdaptiveLayerBaseline")
# Run inference
sentences = [
'people are standing near water with a boat heading their direction',
'People are standing near water with a large blue boat heading their direction.',
'The dogs are near the toy.',
]
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
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.766 |
| **spearman_cosine** | **0.7681** |
| pearson_manhattan | 0.7918 |
| spearman_manhattan | 0.7947 |
| pearson_euclidean | 0.7861 |
| spearman_euclidean | 0.7896 |
| pearson_dot | 0.6448 |
| spearman_dot | 0.6428 |
| pearson_max | 0.7918 |
| spearman_max | 0.7947 |
#### Binary Classification
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:-----------------------------|:-----------|
| cosine_accuracy | 0.6731 |
| cosine_accuracy_threshold | 0.5815 |
| cosine_f1 | 0.717 |
| cosine_f1_threshold | 0.4671 |
| cosine_precision | 0.5977 |
| cosine_recall | 0.8959 |
| cosine_ap | 0.7193 |
| dot_accuracy | 0.6445 |
| dot_accuracy_threshold | 71.9551 |
| dot_f1 | 0.7094 |
| dot_f1_threshold | 53.7729 |
| dot_precision | 0.5779 |
| dot_recall | 0.9184 |
| dot_ap | 0.6828 |
| manhattan_accuracy | 0.6665 |
| manhattan_accuracy_threshold | 213.6252 |
| manhattan_f1 | 0.7047 |
| manhattan_f1_threshold | 245.2058 |
| manhattan_precision | 0.5908 |
| manhattan_recall | 0.8729 |
| manhattan_ap | 0.7132 |
| euclidean_accuracy | 0.6621 |
| euclidean_accuracy_threshold | 10.3589 |
| euclidean_f1 | 0.7024 |
| euclidean_f1_threshold | 12.0109 |
| euclidean_precision | 0.5865 |
| euclidean_recall | 0.8754 |
| euclidean_ap | 0.7102 |
| max_accuracy | 0.6731 |
| max_accuracy_threshold | 213.6252 |
| max_f1 | 0.717 |
| max_f1_threshold | 245.2058 |
| max_precision | 0.5977 |
| max_recall | 0.9184 |
| **max_ap** | **0.7193** |
<!--
## 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
#### stanfordnlp/snli
* Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
* Size: 314,315 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: 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> | <ul><li>0: 100.00%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:---------------------------------------------------------------------------|:-------------------------------------------------|:---------------|
| <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>0</code> |
| <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>0</code> |
| <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>0</code> |
* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1,
"prior_layers_weight": 1,
"kl_div_weight": 1.2,
"kl_temperature": 1.2
}
```
### Evaluation Dataset
#### sentence-transformers/stsb
* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
* Size: 1,500 evaluation 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: 5 tokens</li><li>mean: 14.77 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.74 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
* Samples:
| sentence1 | sentence2 | score |
|:--------------------------------------------------|:------------------------------------------------------|:------------------|
| <code>A man with a hard hat is dancing.</code> | <code>A man wearing a hard hat is dancing.</code> | <code>1.0</code> |
| <code>A young child is riding a horse.</code> | <code>A child is riding a horse.</code> | <code>0.95</code> |
| <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code> |
* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1,
"prior_layers_weight": 1,
"kl_div_weight": 1.2,
"kl_temperature": 1.2
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 16
- `learning_rate`: 5e-06
- `weight_decay`: 1e-07
- `num_train_epochs`: 2
- `warmup_ratio`: 0.5
- `save_safetensors`: False
- `fp16`: True
- `push_to_hub`: True
- `hub_model_id`: bobox/DeBERTaV3-small-SentenceTransformer-AdaptiveLayerBaselinen
- `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`: 32
- `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`: 5e-06
- `weight_decay`: 1e-07
- `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`: linear
- `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-SentenceTransformer-AdaptiveLayerBaselinen
- `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 | loss | max_ap | spearman_cosine |
|:------:|:-----:|:-------------:|:------:|:------:|:---------------:|
| None | 0 | - | 4.1425 | - | 0.4276 |
| 0.1001 | 983 | 4.7699 | 3.8387 | 0.6364 | - |
| 0.2001 | 1966 | 3.5997 | 2.7649 | 0.6722 | - |
| 0.3002 | 2949 | 2.811 | 2.3520 | 0.6838 | - |
| 0.4003 | 3932 | 2.414 | 2.0700 | 0.6883 | - |
| 0.5004 | 4915 | 2.186 | 1.8993 | 0.6913 | - |
| 0.6004 | 5898 | 1.8523 | 1.5632 | 0.7045 | - |
| 0.7005 | 6881 | 0.6415 | 1.4902 | 0.7082 | - |
| 0.8006 | 7864 | 0.5016 | 1.4636 | 0.7108 | - |
| 0.9006 | 8847 | 0.4194 | 1.3875 | 0.7121 | - |
| 1.0007 | 9830 | 0.3737 | 1.3077 | 0.7117 | - |
| 1.1008 | 10813 | 1.8087 | 1.0903 | 0.7172 | - |
| 1.2009 | 11796 | 1.6631 | 1.0388 | 0.7180 | - |
| 1.3009 | 12779 | 1.6161 | 1.0177 | 0.7169 | - |
| 1.4010 | 13762 | 1.5378 | 1.0136 | 0.7148 | - |
| 1.5011 | 14745 | 1.5215 | 1.0053 | 0.7159 | - |
| 1.6011 | 15728 | 1.2887 | 0.9600 | 0.7166 | - |
| 1.7012 | 16711 | 0.3058 | 0.9949 | 0.7180 | - |
| 1.8013 | 17694 | 0.2897 | 0.9792 | 0.7186 | - |
| 1.9014 | 18677 | 0.275 | 0.9598 | 0.7192 | - |
| 2.0 | 19646 | - | 0.9796 | 0.7193 | - |
| None | 0 | - | 2.4594 | 0.7193 | 0.7681 |
### 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",
}
```
#### AdaptiveLayerLoss
```bibtex
@misc{li20242d,
title={2D Matryoshka Sentence Embeddings},
author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
year={2024},
eprint={2402.14776},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
#### 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.*
-->
| null |
Non_BioNLP
|
# 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 [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) dataset. 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 Dataset:**
- [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli)
- **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-SentenceTransformer-AdaptiveLayerBaseline")
# Run inference
sentences = [
'people are standing near water with a boat heading their direction',
'People are standing near water with a large blue boat heading their direction.',
'The dogs are near the toy.',
]
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
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.766 |
| **spearman_cosine** | **0.7681** |
| pearson_manhattan | 0.7918 |
| spearman_manhattan | 0.7947 |
| pearson_euclidean | 0.7861 |
| spearman_euclidean | 0.7896 |
| pearson_dot | 0.6448 |
| spearman_dot | 0.6428 |
| pearson_max | 0.7918 |
| spearman_max | 0.7947 |
#### Binary Classification
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:-----------------------------|:-----------|
| cosine_accuracy | 0.6731 |
| cosine_accuracy_threshold | 0.5815 |
| cosine_f1 | 0.717 |
| cosine_f1_threshold | 0.4671 |
| cosine_precision | 0.5977 |
| cosine_recall | 0.8959 |
| cosine_ap | 0.7193 |
| dot_accuracy | 0.6445 |
| dot_accuracy_threshold | 71.9551 |
| dot_f1 | 0.7094 |
| dot_f1_threshold | 53.7729 |
| dot_precision | 0.5779 |
| dot_recall | 0.9184 |
| dot_ap | 0.6828 |
| manhattan_accuracy | 0.6665 |
| manhattan_accuracy_threshold | 213.6252 |
| manhattan_f1 | 0.7047 |
| manhattan_f1_threshold | 245.2058 |
| manhattan_precision | 0.5908 |
| manhattan_recall | 0.8729 |
| manhattan_ap | 0.7132 |
| euclidean_accuracy | 0.6621 |
| euclidean_accuracy_threshold | 10.3589 |
| euclidean_f1 | 0.7024 |
| euclidean_f1_threshold | 12.0109 |
| euclidean_precision | 0.5865 |
| euclidean_recall | 0.8754 |
| euclidean_ap | 0.7102 |
| max_accuracy | 0.6731 |
| max_accuracy_threshold | 213.6252 |
| max_f1 | 0.717 |
| max_f1_threshold | 245.2058 |
| max_precision | 0.5977 |
| max_recall | 0.9184 |
| **max_ap** | **0.7193** |
<!--
## 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
#### stanfordnlp/snli
* Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
* Size: 314,315 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: 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> | <ul><li>0: 100.00%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:---------------------------------------------------------------------------|:-------------------------------------------------|:---------------|
| <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>0</code> |
| <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>0</code> |
| <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>0</code> |
* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1,
"prior_layers_weight": 1,
"kl_div_weight": 1.2,
"kl_temperature": 1.2
}
```
### Evaluation Dataset
#### sentence-transformers/stsb
* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
* Size: 1,500 evaluation 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: 5 tokens</li><li>mean: 14.77 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.74 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
* Samples:
| sentence1 | sentence2 | score |
|:--------------------------------------------------|:------------------------------------------------------|:------------------|
| <code>A man with a hard hat is dancing.</code> | <code>A man wearing a hard hat is dancing.</code> | <code>1.0</code> |
| <code>A young child is riding a horse.</code> | <code>A child is riding a horse.</code> | <code>0.95</code> |
| <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code> |
* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1,
"prior_layers_weight": 1,
"kl_div_weight": 1.2,
"kl_temperature": 1.2
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 16
- `learning_rate`: 5e-06
- `weight_decay`: 1e-07
- `num_train_epochs`: 2
- `warmup_ratio`: 0.5
- `save_safetensors`: False
- `fp16`: True
- `push_to_hub`: True
- `hub_model_id`: bobox/DeBERTaV3-small-SentenceTransformer-AdaptiveLayerBaselinen
- `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`: 32
- `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`: 5e-06
- `weight_decay`: 1e-07
- `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`: linear
- `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-SentenceTransformer-AdaptiveLayerBaselinen
- `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 | loss | max_ap | spearman_cosine |
|:------:|:-----:|:-------------:|:------:|:------:|:---------------:|
| None | 0 | - | 4.1425 | - | 0.4276 |
| 0.1001 | 983 | 4.7699 | 3.8387 | 0.6364 | - |
| 0.2001 | 1966 | 3.5997 | 2.7649 | 0.6722 | - |
| 0.3002 | 2949 | 2.811 | 2.3520 | 0.6838 | - |
| 0.4003 | 3932 | 2.414 | 2.0700 | 0.6883 | - |
| 0.5004 | 4915 | 2.186 | 1.8993 | 0.6913 | - |
| 0.6004 | 5898 | 1.8523 | 1.5632 | 0.7045 | - |
| 0.7005 | 6881 | 0.6415 | 1.4902 | 0.7082 | - |
| 0.8006 | 7864 | 0.5016 | 1.4636 | 0.7108 | - |
| 0.9006 | 8847 | 0.4194 | 1.3875 | 0.7121 | - |
| 1.0007 | 9830 | 0.3737 | 1.3077 | 0.7117 | - |
| 1.1008 | 10813 | 1.8087 | 1.0903 | 0.7172 | - |
| 1.2009 | 11796 | 1.6631 | 1.0388 | 0.7180 | - |
| 1.3009 | 12779 | 1.6161 | 1.0177 | 0.7169 | - |
| 1.4010 | 13762 | 1.5378 | 1.0136 | 0.7148 | - |
| 1.5011 | 14745 | 1.5215 | 1.0053 | 0.7159 | - |
| 1.6011 | 15728 | 1.2887 | 0.9600 | 0.7166 | - |
| 1.7012 | 16711 | 0.3058 | 0.9949 | 0.7180 | - |
| 1.8013 | 17694 | 0.2897 | 0.9792 | 0.7186 | - |
| 1.9014 | 18677 | 0.275 | 0.9598 | 0.7192 | - |
| 2.0 | 19646 | - | 0.9796 | 0.7193 | - |
| None | 0 | - | 2.4594 | 0.7193 | 0.7681 |
### 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",
}
```
#### AdaptiveLayerLoss
```bibtex
@misc{li20242d,
title={2D Matryoshka Sentence Embeddings},
author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
year={2024},
eprint={2402.14776},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
#### 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.*
-->
|
{"base_model": "microsoft/deberta-v3-small", "datasets": ["stanfordnlp/snli", "sentence-transformers/stsb"], "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", "cosine_accuracy", "cosine_accuracy_threshold", "cosine_f1", "cosine_f1_threshold", "cosine_precision", "cosine_recall", "cosine_ap", "dot_accuracy", "dot_accuracy_threshold", "dot_f1", "dot_f1_threshold", "dot_precision", "dot_recall", "dot_ap", "manhattan_accuracy", "manhattan_accuracy_threshold", "manhattan_f1", "manhattan_f1_threshold", "manhattan_precision", "manhattan_recall", "manhattan_ap", "euclidean_accuracy", "euclidean_accuracy_threshold", "euclidean_f1", "euclidean_f1_threshold", "euclidean_precision", "euclidean_recall", "euclidean_ap", "max_accuracy", "max_accuracy_threshold", "max_f1", "max_f1_threshold", "max_precision", "max_recall", "max_ap"], "pipeline_tag": "sentence-similarity", "tags": ["sentence-transformers", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:314315", "loss:AdaptiveLayerLoss", "loss:MultipleNegativesRankingLoss"], "widget": [{"source_sentence": "Two teenage girls conversing next to lockers.", "sentences": ["Girls talking about their problems next to lockers.", "A bully tries to pop a balloon without being caught in the act.", "Two dogs standing together in the yard."]}, {"source_sentence": "A young man in a heavy brown winter coat stands in front of a blue railing with his arms spread.", "sentences": ["a boy holding onto the wall of an old brick house's raised foundation as construction occurs", "The railing is in front of a frozen lake.", "A skateboarder is doing tricks for a competition."]}, {"source_sentence": "A shirtless man with a white hat and no shoes sitting crisscross with his back against the wall holding up a white plastic cup.", "sentences": ["A long-haired boy riding his skateboard at a fast pace over a stone wall with graffiti.", "A man is sitting crisscross", "a child in a black ninja suit does a kick"]}, {"source_sentence": "A light colored dog leaps over a hurdle.", "sentences": ["Men sit on the bus going to work,", "A dog jumps over a obstacel.", "a man standing on his motorbike."]}, {"source_sentence": "people are standing near water with a boat heading their direction", "sentences": ["People are standing near water with a large blue boat heading their direction.", "Two people climbing on a wooden scaffold.", "The dogs are near the toy."]}], "model-index": [{"name": "SentenceTransformer based on microsoft/deberta-v3-small", "results": [{"task": {"type": "semantic-similarity", "name": "Semantic Similarity"}, "dataset": {"name": "Unknown", "type": "unknown"}, "metrics": [{"type": "pearson_cosine", "value": 0.7660217567682521, "name": "Pearson Cosine"}, {"type": "spearman_cosine", "value": 0.7681125489633884, "name": "Spearman Cosine"}, {"type": "pearson_manhattan", "value": 0.7917532885619117, "name": "Pearson Manhattan"}, {"type": "spearman_manhattan", "value": 0.794675885405013, "name": "Spearman Manhattan"}, {"type": "pearson_euclidean", "value": 0.7860948725725584, "name": "Pearson Euclidean"}, {"type": "spearman_euclidean", "value": 0.7895594746178918, "name": "Spearman Euclidean"}, {"type": "pearson_dot", "value": 0.644843928972524, "name": "Pearson Dot"}, {"type": "spearman_dot", "value": 0.6427588138459626, "name": "Spearman Dot"}, {"type": "pearson_max", "value": 0.7917532885619117, "name": "Pearson Max"}, {"type": "spearman_max", "value": 0.794675885405013, "name": "Spearman Max"}]}, {"task": {"type": "binary-classification", "name": "Binary Classification"}, "dataset": {"name": "Unknown", "type": "unknown"}, "metrics": [{"type": "cosine_accuracy", "value": 0.6730608840700584, "name": "Cosine Accuracy"}, {"type": "cosine_accuracy_threshold", "value": 0.5814725160598755, "name": "Cosine Accuracy Threshold"}, {"type": "cosine_f1", "value": 0.7170495061078964, "name": "Cosine F1"}, {"type": "cosine_f1_threshold", "value": 0.4670722782611847, "name": "Cosine F1 Threshold"}, {"type": "cosine_precision", "value": 0.5977392321184954, "name": "Cosine Precision"}, {"type": "cosine_recall", "value": 0.895866802979407, "name": "Cosine Recall"}, {"type": "cosine_ap", "value": 0.7193483203625508, "name": "Cosine Ap"}, {"type": "dot_accuracy", "value": 0.6444764576541057, "name": "Dot Accuracy"}, {"type": "dot_accuracy_threshold", "value": 71.95508575439453, "name": "Dot Accuracy Threshold"}, {"type": "dot_f1", "value": 0.7094262988661364, "name": "Dot F1"}, {"type": "dot_f1_threshold", "value": 53.77289581298828, "name": "Dot F1 Threshold"}, {"type": "dot_precision", "value": 0.5779411764705882, "name": "Dot Precision"}, {"type": "dot_recall", "value": 0.9183584051409376, "name": "Dot Recall"}, {"type": "dot_ap", "value": 0.6828334101602328, "name": "Dot Ap"}, {"type": "manhattan_accuracy", "value": 0.6664644779740693, "name": "Manhattan Accuracy"}, {"type": "manhattan_accuracy_threshold", "value": 213.6251678466797, "name": "Manhattan Accuracy Threshold"}, {"type": "manhattan_f1", "value": 0.7047102517243412, "name": "Manhattan F1"}, {"type": "manhattan_f1_threshold", "value": 245.20578002929688, "name": "Manhattan F1 Threshold"}, {"type": "manhattan_precision", "value": 0.5908461842625544, "name": "Manhattan Precision"}, {"type": "manhattan_recall", "value": 0.8729370527238206, "name": "Manhattan Recall"}, {"type": "manhattan_ap", "value": 0.7132026586783923, "name": "Manhattan Ap"}, {"type": "euclidean_accuracy", "value": 0.6621426946698006, "name": "Euclidean Accuracy"}, {"type": "euclidean_accuracy_threshold", "value": 10.358880996704102, "name": "Euclidean Accuracy Threshold"}, {"type": "euclidean_f1", "value": 0.7024081560907013, "name": "Euclidean F1"}, {"type": "euclidean_f1_threshold", "value": 12.010871887207031, "name": "Euclidean F1 Threshold"}, {"type": "euclidean_precision", "value": 0.5864970645792563, "name": "Euclidean Precision"}, {"type": "euclidean_recall", "value": 0.8754198919234701, "name": "Euclidean Recall"}, {"type": "euclidean_ap", "value": 0.7101786172295015, "name": "Euclidean Ap"}, {"type": "max_accuracy", "value": 0.6730608840700584, "name": "Max Accuracy"}, {"type": "max_accuracy_threshold", "value": 213.6251678466797, "name": "Max Accuracy Threshold"}, {"type": "max_f1", "value": 0.7170495061078964, "name": "Max F1"}, {"type": "max_f1_threshold", "value": 245.20578002929688, "name": "Max F1 Threshold"}, {"type": "max_precision", "value": 0.5977392321184954, "name": "Max Precision"}, {"type": "max_recall", "value": 0.9183584051409376, "name": "Max Recall"}, {"type": "max_ap", "value": 0.7193483203625508, "name": "Max Ap"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION",
"SEMANTIC_SIMILARITY"
] | 41,539 |
gokulsrinivasagan/distilbert_base_train_qqp
|
gokulsrinivasagan
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokulsrinivasagan/distilbert_base_train",
"base_model:finetune:gokulsrinivasagan/distilbert_base_train",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2025-01-27T20:41:27Z |
2025-01-27T21:32:20+00:00
| 5 | 0 |
---
base_model: gokulsrinivasagan/distilbert_base_train
datasets:
- glue
language:
- en
library_name: transformers
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert_base_train_qqp
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- type: accuracy
value: 0.8421716547118476
name: Accuracy
- type: f1
value: 0.7903676204868755
name: F1
---
<!-- 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. -->
# distilbert_base_train_qqp
This model is a fine-tuned version of [gokulsrinivasagan/distilbert_base_train](https://huggingface.co/gokulsrinivasagan/distilbert_base_train) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3738
- Accuracy: 0.8422
- F1: 0.7904
- Combined Score: 0.8163
## 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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4496 | 1.0 | 1422 | 0.4014 | 0.8112 | 0.7270 | 0.7691 |
| 0.339 | 2.0 | 2844 | 0.3792 | 0.8322 | 0.7719 | 0.8021 |
| 0.2619 | 3.0 | 4266 | 0.3738 | 0.8422 | 0.7904 | 0.8163 |
| 0.2015 | 4.0 | 5688 | 0.4195 | 0.8449 | 0.7788 | 0.8118 |
| 0.1564 | 5.0 | 7110 | 0.4450 | 0.8493 | 0.7931 | 0.8212 |
| 0.1245 | 6.0 | 8532 | 0.4734 | 0.8510 | 0.7980 | 0.8245 |
| 0.1024 | 7.0 | 9954 | 0.5103 | 0.8503 | 0.7997 | 0.8250 |
| 0.0846 | 8.0 | 11376 | 0.5748 | 0.8513 | 0.7970 | 0.8242 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert_base_train_qqp
This model is a fine-tuned version of [gokulsrinivasagan/distilbert_base_train](https://huggingface.co/gokulsrinivasagan/distilbert_base_train) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3738
- Accuracy: 0.8422
- F1: 0.7904
- Combined Score: 0.8163
## 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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4496 | 1.0 | 1422 | 0.4014 | 0.8112 | 0.7270 | 0.7691 |
| 0.339 | 2.0 | 2844 | 0.3792 | 0.8322 | 0.7719 | 0.8021 |
| 0.2619 | 3.0 | 4266 | 0.3738 | 0.8422 | 0.7904 | 0.8163 |
| 0.2015 | 4.0 | 5688 | 0.4195 | 0.8449 | 0.7788 | 0.8118 |
| 0.1564 | 5.0 | 7110 | 0.4450 | 0.8493 | 0.7931 | 0.8212 |
| 0.1245 | 6.0 | 8532 | 0.4734 | 0.8510 | 0.7980 | 0.8245 |
| 0.1024 | 7.0 | 9954 | 0.5103 | 0.8503 | 0.7997 | 0.8250 |
| 0.0846 | 8.0 | 11376 | 0.5748 | 0.8513 | 0.7970 | 0.8242 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
|
{"base_model": "gokulsrinivasagan/distilbert_base_train", "datasets": ["glue"], "language": ["en"], "library_name": "transformers", "license": "apache-2.0", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert_base_train_qqp", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE QQP", "type": "glue", "args": "qqp"}, "metrics": [{"type": "accuracy", "value": 0.8421716547118476, "name": "Accuracy"}, {"type": "f1", "value": 0.7903676204868755, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,540 |
ilsp/opus-mt-pt-en_ct2_ft-SciLake
|
ilsp
|
translation
|
[
"transformers",
"translation",
"pt",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 2024-05-29T19:10:45Z |
2024-05-30T01:14:30+00:00
| 11 | 2 |
---
language:
- pt
- en
license: apache-2.0
pipeline_tag: translation
---
# Portuguese-English Translation Model for the Scientific Domain
## Description
This is a CTranslate2 Portuguese-English translation model for the scientific domain, which uses the PT-EN OPUS-MT Transformer-Align [(link)](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/por-eng) as its base model.
It has been fine-tuned on a large parallel corpus with scientific texts, with special focus to the four pilot domains of the [SciLake](https://scilake.eu/) project:
- Neuroscience
- Cancer
- Transportation
- Energy
## Dataset
The fine-tuning dataset consists of 5,705,469 EN-PT parallel sentences extracted from parallel theses and abstracts which have been acquired from multiple academic repositories.
## Evaluation
We have evaluated the base and the fine-tuned models on 5 test sets:
- Four which correspond to the pilot domains (Neuroscience, Cancer, Transportation, Energy) with each one containing 1,000 parallel sentences.
- A general scientific which contains 3,000 parallel sentences from a wide range of scientific texts in other domains.
| Model | Average of 4 domains | | | General Scientific| | |
|-------------|----------------------|---------------|---------------|-------------------|---------------|---------------|
| | SacreBLEU | chrF2++ | COMET | SacreBLEU | chrF2++ | COMET |
| Base | 46 | 68.3 | 66.7 | 44.9 | 67.7 | 66.3 |
| Fine-Tuned | 48.4 | 69.9 | 67.3 | 47.3 | 69.1 | 67.8 |
| Improvement | +2.4 | +1.6 | +0.9 | +2.4 | +1.4 | +1.5 |
## Usage
```
pip install ctranslate2 sentencepiece huggingface_hub
```
```python
import ctranslate2
import sentencepiece as spm
from huggingface_hub import snapshot_download
repo_id = "ilsp/opus-mt-pt-en_ct2_ft-SciLake"
# REPLACE WITH ACTUAL LOCAL DIRECTORY WHERE THE MODEL WILL BE DOWNLOADED
local_dir = ""
model_path = snapshot_download(repo_id=repo_id, local_dir=local_dir)
translator = ctranslate2.Translator(model_path, compute_type="auto")
sp_enc = spm.SentencePieceProcessor()
sp_enc.load(f"{model_path}/source.spm")
sp_dec = spm.SentencePieceProcessor()
sp_dec.load(f"{model_path}/target.spm")
def translate_text(input_text, sp_enc=sp_enc, sp_dec=sp_dec, translator=translator, beam_size=6):
input_tokens = sp_enc.encode(input_text, out_type=str)
results = translator.translate_batch([input_tokens],
beam_size=beam_size,
length_penalty=0,
max_decoding_length=512,
replace_unknowns=True)
output_tokens = results[0].hypotheses[0]
output_text = sp_dec.decode(output_tokens)
return output_text
input_text = "Na osteoartríte (OA) a degeneração progressiva das estruturas articulares activa continuamente nociceptores levando ao desenvolvimento de dor crónica e a déficits emocionais e cognitivos."
translate_text(input_text)
# OUTPUT
# In osteoarthritis (OA), progressive degeneration of articular structures continuously activates nociceptors leading to the development of chronic pain and emotional and cognitive deficits.
```
## Acknowledgements
This work was created within the [SciLake](https://scilake.eu/) project. We are grateful to the SciLake project for providing the resources and support that made this work possible. This project has received funding from the European Union’s Horizon Europe framework programme under grant agreement No. 101058573.
| null |
Non_BioNLP
|
# Portuguese-English Translation Model for the Scientific Domain
## Description
This is a CTranslate2 Portuguese-English translation model for the scientific domain, which uses the PT-EN OPUS-MT Transformer-Align [(link)](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/por-eng) as its base model.
It has been fine-tuned on a large parallel corpus with scientific texts, with special focus to the four pilot domains of the [SciLake](https://scilake.eu/) project:
- Neuroscience
- Cancer
- Transportation
- Energy
## Dataset
The fine-tuning dataset consists of 5,705,469 EN-PT parallel sentences extracted from parallel theses and abstracts which have been acquired from multiple academic repositories.
## Evaluation
We have evaluated the base and the fine-tuned models on 5 test sets:
- Four which correspond to the pilot domains (Neuroscience, Cancer, Transportation, Energy) with each one containing 1,000 parallel sentences.
- A general scientific which contains 3,000 parallel sentences from a wide range of scientific texts in other domains.
| Model | Average of 4 domains | | | General Scientific| | |
|-------------|----------------------|---------------|---------------|-------------------|---------------|---------------|
| | SacreBLEU | chrF2++ | COMET | SacreBLEU | chrF2++ | COMET |
| Base | 46 | 68.3 | 66.7 | 44.9 | 67.7 | 66.3 |
| Fine-Tuned | 48.4 | 69.9 | 67.3 | 47.3 | 69.1 | 67.8 |
| Improvement | +2.4 | +1.6 | +0.9 | +2.4 | +1.4 | +1.5 |
## Usage
```
pip install ctranslate2 sentencepiece huggingface_hub
```
```python
import ctranslate2
import sentencepiece as spm
from huggingface_hub import snapshot_download
repo_id = "ilsp/opus-mt-pt-en_ct2_ft-SciLake"
# REPLACE WITH ACTUAL LOCAL DIRECTORY WHERE THE MODEL WILL BE DOWNLOADED
local_dir = ""
model_path = snapshot_download(repo_id=repo_id, local_dir=local_dir)
translator = ctranslate2.Translator(model_path, compute_type="auto")
sp_enc = spm.SentencePieceProcessor()
sp_enc.load(f"{model_path}/source.spm")
sp_dec = spm.SentencePieceProcessor()
sp_dec.load(f"{model_path}/target.spm")
def translate_text(input_text, sp_enc=sp_enc, sp_dec=sp_dec, translator=translator, beam_size=6):
input_tokens = sp_enc.encode(input_text, out_type=str)
results = translator.translate_batch([input_tokens],
beam_size=beam_size,
length_penalty=0,
max_decoding_length=512,
replace_unknowns=True)
output_tokens = results[0].hypotheses[0]
output_text = sp_dec.decode(output_tokens)
return output_text
input_text = "Na osteoartríte (OA) a degeneração progressiva das estruturas articulares activa continuamente nociceptores levando ao desenvolvimento de dor crónica e a déficits emocionais e cognitivos."
translate_text(input_text)
# OUTPUT
# In osteoarthritis (OA), progressive degeneration of articular structures continuously activates nociceptors leading to the development of chronic pain and emotional and cognitive deficits.
```
## Acknowledgements
This work was created within the [SciLake](https://scilake.eu/) project. We are grateful to the SciLake project for providing the resources and support that made this work possible. This project has received funding from the European Union’s Horizon Europe framework programme under grant agreement No. 101058573.
|
{"language": ["pt", "en"], "license": "apache-2.0", "pipeline_tag": "translation"}
|
task
|
[
"TRANSLATION"
] | 41,541 |
farleyknight/arxiv-summarization-t5-base-2022-09-21
|
farleyknight
|
text2text-generation
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:ccdv/arxiv-summarization",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2022-09-21T20:31:09Z |
2022-09-24T00:31:57+00:00
| 17 | 3 |
---
datasets:
- ccdv/arxiv-summarization
license: apache-2.0
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: arxiv-summarization-t5-base-2022-09-21
results:
- task:
type: summarization
name: Summarization
dataset:
name: ccdv/arxiv-summarization
type: ccdv/arxiv-summarization
config: section
split: train
args: section
metrics:
- type: rouge
value: 40.6781
name: Rouge1
---
<!-- 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. -->
# arxiv-summarization-t5-base-2022-09-21
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the ccdv/arxiv-summarization dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8650
- Rouge1: 40.6781
- Rouge2: 14.7167
- Rougel: 26.6375
- Rougelsum: 35.5959
- Gen Len: 117.1969
## 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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:------:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
| 2.3291 | 0.05 | 10000 | 2.1906 | 18.6571 | 7.1341 | 14.8347 | 16.9545 | 19.0 |
| 2.2454 | 0.1 | 20000 | 2.1549 | 18.5037 | 7.1908 | 14.7141 | 16.8233 | 18.9997 |
| 2.2107 | 0.15 | 30000 | 2.1013 | 18.7638 | 7.326 | 14.9437 | 17.072 | 19.0 |
| 2.1486 | 0.2 | 40000 | 2.0845 | 18.6879 | 7.2441 | 14.8835 | 16.983 | 19.0 |
| 2.158 | 0.25 | 50000 | 2.0699 | 18.8314 | 7.3712 | 15.0166 | 17.1215 | 19.0 |
| 2.1476 | 0.3 | 60000 | 2.0424 | 18.9783 | 7.4138 | 15.1121 | 17.2778 | 18.9981 |
| 2.1164 | 0.34 | 70000 | 2.0349 | 18.9257 | 7.4649 | 15.0335 | 17.1819 | 19.0 |
| 2.079 | 0.39 | 80000 | 2.0208 | 18.643 | 7.4096 | 14.8927 | 16.9786 | 18.9994 |
| 2.101 | 0.44 | 90000 | 2.0113 | 19.3881 | 7.7012 | 15.3981 | 17.6516 | 19.0 |
| 2.0576 | 0.49 | 100000 | 2.0022 | 18.9985 | 7.542 | 15.1157 | 17.2972 | 18.9992 |
| 2.0983 | 0.54 | 110000 | 1.9941 | 18.7691 | 7.4625 | 15.0256 | 17.1146 | 19.0 |
| 2.053 | 0.59 | 120000 | 1.9855 | 19.002 | 7.5602 | 15.1497 | 17.2963 | 19.0 |
| 2.0434 | 0.64 | 130000 | 1.9786 | 19.2385 | 7.6533 | 15.3094 | 17.5439 | 18.9994 |
| 2.0354 | 0.69 | 140000 | 1.9746 | 19.184 | 7.7307 | 15.2897 | 17.491 | 18.9992 |
| 2.0347 | 0.74 | 150000 | 1.9639 | 19.2408 | 7.693 | 15.3357 | 17.5297 | 19.0 |
| 2.0236 | 0.79 | 160000 | 1.9590 | 19.0781 | 7.6256 | 15.1932 | 17.3486 | 18.9998 |
| 2.0187 | 0.84 | 170000 | 1.9532 | 19.0343 | 7.6792 | 15.1884 | 17.3519 | 19.0 |
| 1.9939 | 0.89 | 180000 | 1.9485 | 18.8247 | 7.5005 | 15.0246 | 17.1485 | 18.9998 |
| 1.9961 | 0.94 | 190000 | 1.9504 | 19.0695 | 7.6559 | 15.2139 | 17.3814 | 19.0 |
| 2.0197 | 0.99 | 200000 | 1.9399 | 19.2821 | 7.6685 | 15.3029 | 17.5374 | 18.9988 |
| 1.9457 | 1.03 | 210000 | 1.9350 | 19.053 | 7.6502 | 15.2123 | 17.3793 | 19.0 |
| 1.9552 | 1.08 | 220000 | 1.9317 | 19.1878 | 7.7235 | 15.3272 | 17.5252 | 18.9998 |
| 1.9772 | 1.13 | 230000 | 1.9305 | 19.0855 | 7.6303 | 15.1943 | 17.3942 | 18.9997 |
| 1.9171 | 1.18 | 240000 | 1.9291 | 19.0711 | 7.6437 | 15.2175 | 17.3893 | 18.9995 |
| 1.9393 | 1.23 | 250000 | 1.9230 | 19.276 | 7.725 | 15.3826 | 17.586 | 18.9995 |
| 1.9295 | 1.28 | 260000 | 1.9197 | 19.2999 | 7.7958 | 15.3961 | 17.6056 | 18.9975 |
| 1.9725 | 1.33 | 270000 | 1.9173 | 19.2958 | 7.7121 | 15.3659 | 17.584 | 19.0 |
| 1.9668 | 1.38 | 280000 | 1.9129 | 19.089 | 7.6846 | 15.2395 | 17.3879 | 18.9998 |
| 1.941 | 1.43 | 290000 | 1.9132 | 19.2127 | 7.7336 | 15.311 | 17.4742 | 18.9995 |
| 1.9427 | 1.48 | 300000 | 1.9108 | 19.217 | 7.7591 | 15.334 | 17.53 | 18.9998 |
| 1.9521 | 1.53 | 310000 | 1.9041 | 19.1285 | 7.6736 | 15.2625 | 17.458 | 19.0 |
| 1.9352 | 1.58 | 320000 | 1.9041 | 19.1656 | 7.723 | 15.3035 | 17.4818 | 18.9991 |
| 1.9342 | 1.63 | 330000 | 1.9004 | 19.2573 | 7.7766 | 15.3558 | 17.5382 | 19.0 |
| 1.9631 | 1.68 | 340000 | 1.8978 | 19.236 | 7.7584 | 15.3408 | 17.4993 | 18.9998 |
| 1.8987 | 1.72 | 350000 | 1.8968 | 19.1716 | 7.7231 | 15.2836 | 17.4655 | 18.9997 |
| 1.9433 | 1.77 | 360000 | 1.8924 | 19.2644 | 7.8294 | 15.4018 | 17.5808 | 18.9998 |
| 1.9159 | 1.82 | 370000 | 1.8912 | 19.1833 | 7.8267 | 15.3175 | 17.4918 | 18.9995 |
| 1.9516 | 1.87 | 380000 | 1.8856 | 19.3077 | 7.7432 | 15.3723 | 17.6115 | 19.0 |
| 1.9218 | 1.92 | 390000 | 1.8880 | 19.2668 | 7.8231 | 15.3834 | 17.5701 | 18.9994 |
| 1.9159 | 1.97 | 400000 | 1.8860 | 19.2224 | 7.7903 | 15.3488 | 17.4992 | 18.9997 |
| 1.8741 | 2.02 | 410000 | 1.8854 | 19.2572 | 7.741 | 15.3405 | 17.5351 | 19.0 |
| 1.8668 | 2.07 | 420000 | 1.8854 | 19.3658 | 7.8593 | 15.4418 | 17.656 | 18.9995 |
| 1.8638 | 2.12 | 430000 | 1.8831 | 19.305 | 7.8218 | 15.3843 | 17.5861 | 18.9997 |
| 1.8334 | 2.17 | 440000 | 1.8817 | 19.3269 | 7.8249 | 15.4231 | 17.5958 | 18.9994 |
| 1.8893 | 2.22 | 450000 | 1.8803 | 19.2949 | 7.7885 | 15.3947 | 17.585 | 18.9997 |
| 1.8929 | 2.27 | 460000 | 1.8783 | 19.291 | 7.8346 | 15.428 | 17.5797 | 18.9997 |
| 1.861 | 2.32 | 470000 | 1.8766 | 19.4284 | 7.8832 | 15.4746 | 17.6946 | 18.9997 |
| 1.8719 | 2.37 | 480000 | 1.8751 | 19.1525 | 7.7641 | 15.3348 | 17.47 | 18.9998 |
| 1.8889 | 2.41 | 490000 | 1.8742 | 19.1743 | 7.768 | 15.3292 | 17.4665 | 18.9998 |
| 1.8834 | 2.46 | 500000 | 1.8723 | 19.3069 | 7.7935 | 15.3987 | 17.5913 | 18.9998 |
| 1.8564 | 2.51 | 510000 | 1.8695 | 19.3217 | 7.8292 | 15.4063 | 17.6081 | 19.0 |
| 1.8706 | 2.56 | 520000 | 1.8697 | 19.294 | 7.8217 | 15.3964 | 17.581 | 18.9998 |
| 1.883 | 2.61 | 530000 | 1.8703 | 19.2784 | 7.8634 | 15.404 | 17.5942 | 18.9995 |
| 1.8622 | 2.66 | 540000 | 1.8677 | 19.3165 | 7.8378 | 15.4259 | 17.6064 | 18.9988 |
| 1.8781 | 2.71 | 550000 | 1.8676 | 19.3237 | 7.7954 | 15.3995 | 17.6008 | 19.0 |
| 1.8793 | 2.76 | 560000 | 1.8685 | 19.2141 | 7.7605 | 15.3345 | 17.5268 | 18.9997 |
| 1.8795 | 2.81 | 570000 | 1.8675 | 19.2694 | 7.8082 | 15.3996 | 17.5831 | 19.0 |
| 1.8425 | 2.86 | 580000 | 1.8659 | 19.2886 | 7.7987 | 15.4005 | 17.5859 | 18.9997 |
| 1.8605 | 2.91 | 590000 | 1.8650 | 19.2778 | 7.7934 | 15.3931 | 17.5809 | 18.9997 |
| 1.8448 | 2.96 | 600000 | 1.8655 | 19.2884 | 7.8087 | 15.4025 | 17.5856 | 19.0 |
### Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.12.0
- Datasets 2.5.1
- Tokenizers 0.13.0
| null |
Non_BioNLP
|
<!-- 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. -->
# arxiv-summarization-t5-base-2022-09-21
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the ccdv/arxiv-summarization dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8650
- Rouge1: 40.6781
- Rouge2: 14.7167
- Rougel: 26.6375
- Rougelsum: 35.5959
- Gen Len: 117.1969
## 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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:------:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
| 2.3291 | 0.05 | 10000 | 2.1906 | 18.6571 | 7.1341 | 14.8347 | 16.9545 | 19.0 |
| 2.2454 | 0.1 | 20000 | 2.1549 | 18.5037 | 7.1908 | 14.7141 | 16.8233 | 18.9997 |
| 2.2107 | 0.15 | 30000 | 2.1013 | 18.7638 | 7.326 | 14.9437 | 17.072 | 19.0 |
| 2.1486 | 0.2 | 40000 | 2.0845 | 18.6879 | 7.2441 | 14.8835 | 16.983 | 19.0 |
| 2.158 | 0.25 | 50000 | 2.0699 | 18.8314 | 7.3712 | 15.0166 | 17.1215 | 19.0 |
| 2.1476 | 0.3 | 60000 | 2.0424 | 18.9783 | 7.4138 | 15.1121 | 17.2778 | 18.9981 |
| 2.1164 | 0.34 | 70000 | 2.0349 | 18.9257 | 7.4649 | 15.0335 | 17.1819 | 19.0 |
| 2.079 | 0.39 | 80000 | 2.0208 | 18.643 | 7.4096 | 14.8927 | 16.9786 | 18.9994 |
| 2.101 | 0.44 | 90000 | 2.0113 | 19.3881 | 7.7012 | 15.3981 | 17.6516 | 19.0 |
| 2.0576 | 0.49 | 100000 | 2.0022 | 18.9985 | 7.542 | 15.1157 | 17.2972 | 18.9992 |
| 2.0983 | 0.54 | 110000 | 1.9941 | 18.7691 | 7.4625 | 15.0256 | 17.1146 | 19.0 |
| 2.053 | 0.59 | 120000 | 1.9855 | 19.002 | 7.5602 | 15.1497 | 17.2963 | 19.0 |
| 2.0434 | 0.64 | 130000 | 1.9786 | 19.2385 | 7.6533 | 15.3094 | 17.5439 | 18.9994 |
| 2.0354 | 0.69 | 140000 | 1.9746 | 19.184 | 7.7307 | 15.2897 | 17.491 | 18.9992 |
| 2.0347 | 0.74 | 150000 | 1.9639 | 19.2408 | 7.693 | 15.3357 | 17.5297 | 19.0 |
| 2.0236 | 0.79 | 160000 | 1.9590 | 19.0781 | 7.6256 | 15.1932 | 17.3486 | 18.9998 |
| 2.0187 | 0.84 | 170000 | 1.9532 | 19.0343 | 7.6792 | 15.1884 | 17.3519 | 19.0 |
| 1.9939 | 0.89 | 180000 | 1.9485 | 18.8247 | 7.5005 | 15.0246 | 17.1485 | 18.9998 |
| 1.9961 | 0.94 | 190000 | 1.9504 | 19.0695 | 7.6559 | 15.2139 | 17.3814 | 19.0 |
| 2.0197 | 0.99 | 200000 | 1.9399 | 19.2821 | 7.6685 | 15.3029 | 17.5374 | 18.9988 |
| 1.9457 | 1.03 | 210000 | 1.9350 | 19.053 | 7.6502 | 15.2123 | 17.3793 | 19.0 |
| 1.9552 | 1.08 | 220000 | 1.9317 | 19.1878 | 7.7235 | 15.3272 | 17.5252 | 18.9998 |
| 1.9772 | 1.13 | 230000 | 1.9305 | 19.0855 | 7.6303 | 15.1943 | 17.3942 | 18.9997 |
| 1.9171 | 1.18 | 240000 | 1.9291 | 19.0711 | 7.6437 | 15.2175 | 17.3893 | 18.9995 |
| 1.9393 | 1.23 | 250000 | 1.9230 | 19.276 | 7.725 | 15.3826 | 17.586 | 18.9995 |
| 1.9295 | 1.28 | 260000 | 1.9197 | 19.2999 | 7.7958 | 15.3961 | 17.6056 | 18.9975 |
| 1.9725 | 1.33 | 270000 | 1.9173 | 19.2958 | 7.7121 | 15.3659 | 17.584 | 19.0 |
| 1.9668 | 1.38 | 280000 | 1.9129 | 19.089 | 7.6846 | 15.2395 | 17.3879 | 18.9998 |
| 1.941 | 1.43 | 290000 | 1.9132 | 19.2127 | 7.7336 | 15.311 | 17.4742 | 18.9995 |
| 1.9427 | 1.48 | 300000 | 1.9108 | 19.217 | 7.7591 | 15.334 | 17.53 | 18.9998 |
| 1.9521 | 1.53 | 310000 | 1.9041 | 19.1285 | 7.6736 | 15.2625 | 17.458 | 19.0 |
| 1.9352 | 1.58 | 320000 | 1.9041 | 19.1656 | 7.723 | 15.3035 | 17.4818 | 18.9991 |
| 1.9342 | 1.63 | 330000 | 1.9004 | 19.2573 | 7.7766 | 15.3558 | 17.5382 | 19.0 |
| 1.9631 | 1.68 | 340000 | 1.8978 | 19.236 | 7.7584 | 15.3408 | 17.4993 | 18.9998 |
| 1.8987 | 1.72 | 350000 | 1.8968 | 19.1716 | 7.7231 | 15.2836 | 17.4655 | 18.9997 |
| 1.9433 | 1.77 | 360000 | 1.8924 | 19.2644 | 7.8294 | 15.4018 | 17.5808 | 18.9998 |
| 1.9159 | 1.82 | 370000 | 1.8912 | 19.1833 | 7.8267 | 15.3175 | 17.4918 | 18.9995 |
| 1.9516 | 1.87 | 380000 | 1.8856 | 19.3077 | 7.7432 | 15.3723 | 17.6115 | 19.0 |
| 1.9218 | 1.92 | 390000 | 1.8880 | 19.2668 | 7.8231 | 15.3834 | 17.5701 | 18.9994 |
| 1.9159 | 1.97 | 400000 | 1.8860 | 19.2224 | 7.7903 | 15.3488 | 17.4992 | 18.9997 |
| 1.8741 | 2.02 | 410000 | 1.8854 | 19.2572 | 7.741 | 15.3405 | 17.5351 | 19.0 |
| 1.8668 | 2.07 | 420000 | 1.8854 | 19.3658 | 7.8593 | 15.4418 | 17.656 | 18.9995 |
| 1.8638 | 2.12 | 430000 | 1.8831 | 19.305 | 7.8218 | 15.3843 | 17.5861 | 18.9997 |
| 1.8334 | 2.17 | 440000 | 1.8817 | 19.3269 | 7.8249 | 15.4231 | 17.5958 | 18.9994 |
| 1.8893 | 2.22 | 450000 | 1.8803 | 19.2949 | 7.7885 | 15.3947 | 17.585 | 18.9997 |
| 1.8929 | 2.27 | 460000 | 1.8783 | 19.291 | 7.8346 | 15.428 | 17.5797 | 18.9997 |
| 1.861 | 2.32 | 470000 | 1.8766 | 19.4284 | 7.8832 | 15.4746 | 17.6946 | 18.9997 |
| 1.8719 | 2.37 | 480000 | 1.8751 | 19.1525 | 7.7641 | 15.3348 | 17.47 | 18.9998 |
| 1.8889 | 2.41 | 490000 | 1.8742 | 19.1743 | 7.768 | 15.3292 | 17.4665 | 18.9998 |
| 1.8834 | 2.46 | 500000 | 1.8723 | 19.3069 | 7.7935 | 15.3987 | 17.5913 | 18.9998 |
| 1.8564 | 2.51 | 510000 | 1.8695 | 19.3217 | 7.8292 | 15.4063 | 17.6081 | 19.0 |
| 1.8706 | 2.56 | 520000 | 1.8697 | 19.294 | 7.8217 | 15.3964 | 17.581 | 18.9998 |
| 1.883 | 2.61 | 530000 | 1.8703 | 19.2784 | 7.8634 | 15.404 | 17.5942 | 18.9995 |
| 1.8622 | 2.66 | 540000 | 1.8677 | 19.3165 | 7.8378 | 15.4259 | 17.6064 | 18.9988 |
| 1.8781 | 2.71 | 550000 | 1.8676 | 19.3237 | 7.7954 | 15.3995 | 17.6008 | 19.0 |
| 1.8793 | 2.76 | 560000 | 1.8685 | 19.2141 | 7.7605 | 15.3345 | 17.5268 | 18.9997 |
| 1.8795 | 2.81 | 570000 | 1.8675 | 19.2694 | 7.8082 | 15.3996 | 17.5831 | 19.0 |
| 1.8425 | 2.86 | 580000 | 1.8659 | 19.2886 | 7.7987 | 15.4005 | 17.5859 | 18.9997 |
| 1.8605 | 2.91 | 590000 | 1.8650 | 19.2778 | 7.7934 | 15.3931 | 17.5809 | 18.9997 |
| 1.8448 | 2.96 | 600000 | 1.8655 | 19.2884 | 7.8087 | 15.4025 | 17.5856 | 19.0 |
### Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.12.0
- Datasets 2.5.1
- Tokenizers 0.13.0
|
{"datasets": ["ccdv/arxiv-summarization"], "license": "apache-2.0", "metrics": ["rouge"], "tags": ["generated_from_trainer"], "model-index": [{"name": "arxiv-summarization-t5-base-2022-09-21", "results": [{"task": {"type": "summarization", "name": "Summarization"}, "dataset": {"name": "ccdv/arxiv-summarization", "type": "ccdv/arxiv-summarization", "config": "section", "split": "train", "args": "section"}, "metrics": [{"type": "rouge", "value": 40.6781, "name": "Rouge1"}]}]}]}
|
task
|
[
"SUMMARIZATION"
] | 41,542 |
spacemanidol/flan-t5-small-6-4-cnndm
|
spacemanidol
|
text2text-generation
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:cnn_dailymail",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2023-02-16T15:03:58Z |
2023-03-07T18:02:58+00:00
| 13 | 0 |
---
datasets:
- cnn_dailymail
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: small-6-4
results:
- task:
type: summarization
name: Summarization
dataset:
name: cnn_dailymail 3.0.0
type: cnn_dailymail
config: 3.0.0
split: validation
args: 3.0.0
metrics:
- type: rouge
value: 38.7509
name: Rouge1
---
<!-- 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. -->
# small-6-4
This model is a fine-tuned version of [cnn/small-6-4/](https://huggingface.co/cnn/small-6-4/) on the cnn_dailymail 3.0.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7743
- Rouge1: 38.7509
- Rouge2: 17.2661
- Rougel: 27.9055
- Rougelsum: 36.0129
- Gen Len: 78.6349
## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.12.1
| null |
Non_BioNLP
|
<!-- 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. -->
# small-6-4
This model is a fine-tuned version of [cnn/small-6-4/](https://huggingface.co/cnn/small-6-4/) on the cnn_dailymail 3.0.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7743
- Rouge1: 38.7509
- Rouge2: 17.2661
- Rougel: 27.9055
- Rougelsum: 36.0129
- Gen Len: 78.6349
## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.12.1
|
{"datasets": ["cnn_dailymail"], "metrics": ["rouge"], "tags": ["generated_from_trainer"], "model-index": [{"name": "small-6-4", "results": [{"task": {"type": "summarization", "name": "Summarization"}, "dataset": {"name": "cnn_dailymail 3.0.0", "type": "cnn_dailymail", "config": "3.0.0", "split": "validation", "args": "3.0.0"}, "metrics": [{"type": "rouge", "value": 38.7509, "name": "Rouge1"}]}]}]}
|
task
|
[
"SUMMARIZATION"
] | 41,543 |
Benphil/distilbert-base-uncased-finetuned-emotion_10
|
Benphil
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-04-11T07:39:07Z |
2024-04-11T07:39:20+00:00
| 4 | 0 |
---
base_model: distilbert-base-uncased
datasets:
- emotion
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-emotion_10
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.934
name: Accuracy
- type: f1
value: 0.934046975246386
name: F1
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion_10
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1593
- Accuracy: 0.934
- F1: 0.9340
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.2133 | 1.0 | 250 | 0.1799 | 0.9245 | 0.9249 |
| 0.1325 | 2.0 | 500 | 0.1593 | 0.934 | 0.9340 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion_10
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1593
- Accuracy: 0.934
- F1: 0.9340
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.2133 | 1.0 | 250 | 0.1799 | 0.9245 | 0.9249 |
| 0.1325 | 2.0 | 500 | 0.1593 | 0.934 | 0.9340 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"base_model": "distilbert-base-uncased", "datasets": ["emotion"], "license": "apache-2.0", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetuned-emotion_10", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.934, "name": "Accuracy"}, {"type": "f1", "value": 0.934046975246386, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,544 |
microsoft/llmlingua-2-xlm-roberta-large-meetingbank
|
microsoft
|
token-classification
|
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"arxiv:2403.12968",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-03-17T07:04:34Z |
2025-01-08T02:12:15+00:00
| 66,780 | 19 |
---
license: mit
---
# LLMLingua-2-Bert-base-Multilingual-Cased-MeetingBank
This model was introduced in the paper [**LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression** (Pan et al, 2024)](https://arxiv.org/abs/2403.12968). It is a [XLM-RoBERTa (large-sized model)](https://huggingface.co/FacebookAI/xlm-roberta-large) finetuned to perform token classification for task agnostic prompt compression. The probability $p_{preserve}$ of each token $x_i$ is used as the metric for compression. This model is trained on [the extractive text compression dataset](https://huggingface.co/datasets/microsoft/MeetingBank-LLMCompressed) constructed with the methodology proposed in the [**LLMLingua-2**](https://arxiv.org/abs/2403.12968), using training examples from [MeetingBank (Hu et al, 2023)](https://meetingbank.github.io/) as the seed data.
You can evaluate the model on downstream tasks such as question answering (QA) and summarization over compressed meeting transcripts using [this dataset](https://huggingface.co/datasets/microsoft/MeetingBank-QA-Summary).
For more details, please check the home page of [LLMLingua-2](https://llmlingua.com/llmlingua2.html) and [LLMLingua Series](https://llmlingua.com/).
## Usage
```python
from llmlingua import PromptCompressor
compressor = PromptCompressor(
model_name="microsoft/llmlingua-2-xlm-roberta-large-meetingbank",
use_llmlingua2=True
)
original_prompt = """John: So, um, I've been thinking about the project, you know, and I believe we need to, uh, make some changes. I mean, we want the project to succeed, right? So, like, I think we should consider maybe revising the timeline.
Sarah: I totally agree, John. I mean, we have to be realistic, you know. The timeline is, like, too tight. You know what I mean? We should definitely extend it.
"""
results = compressor.compress_prompt_llmlingua2(
original_prompt,
rate=0.6,
force_tokens=['\n', '.', '!', '?', ','],
chunk_end_tokens=['.', '\n'],
return_word_label=True,
drop_consecutive=True
)
print(results.keys())
print(f"Compressed prompt: {results['compressed_prompt']}")
print(f"Original tokens: {results['origin_tokens']}")
print(f"Compressed tokens: {results['compressed_tokens']}")
print(f"Compression rate: {results['rate']}")
# get the annotated results over the original prompt
word_sep = "\t\t|\t\t"
label_sep = " "
lines = results["fn_labeled_original_prompt"].split(word_sep)
annotated_results = []
for line in lines:
word, label = line.split(label_sep)
annotated_results.append((word, '+') if label == '1' else (word, '-')) # list of tuples: (word, label)
print("Annotated results:")
for word, label in annotated_results[:10]:
print(f"{word} {label}")
```
## Citation
```
@article{wu2024llmlingua2,
title = "{LLML}ingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression",
author = "Zhuoshi Pan and Qianhui Wu and Huiqiang Jiang and Menglin Xia and Xufang Luo and Jue Zhang and Qingwei Lin and Victor Ruhle and Yuqing Yang and Chin-Yew Lin and H. Vicky Zhao and Lili Qiu and Dongmei Zhang",
url = "https://arxiv.org/abs/2403.12968",
journal = "ArXiv preprint",
volume = "abs/2403.12968",
year = "2024",
}
```
| null |
Non_BioNLP
|
# LLMLingua-2-Bert-base-Multilingual-Cased-MeetingBank
This model was introduced in the paper [**LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression** (Pan et al, 2024)](https://arxiv.org/abs/2403.12968). It is a [XLM-RoBERTa (large-sized model)](https://huggingface.co/FacebookAI/xlm-roberta-large) finetuned to perform token classification for task agnostic prompt compression. The probability $p_{preserve}$ of each token $x_i$ is used as the metric for compression. This model is trained on [the extractive text compression dataset](https://huggingface.co/datasets/microsoft/MeetingBank-LLMCompressed) constructed with the methodology proposed in the [**LLMLingua-2**](https://arxiv.org/abs/2403.12968), using training examples from [MeetingBank (Hu et al, 2023)](https://meetingbank.github.io/) as the seed data.
You can evaluate the model on downstream tasks such as question answering (QA) and summarization over compressed meeting transcripts using [this dataset](https://huggingface.co/datasets/microsoft/MeetingBank-QA-Summary).
For more details, please check the home page of [LLMLingua-2](https://llmlingua.com/llmlingua2.html) and [LLMLingua Series](https://llmlingua.com/).
## Usage
```python
from llmlingua import PromptCompressor
compressor = PromptCompressor(
model_name="microsoft/llmlingua-2-xlm-roberta-large-meetingbank",
use_llmlingua2=True
)
original_prompt = """John: So, um, I've been thinking about the project, you know, and I believe we need to, uh, make some changes. I mean, we want the project to succeed, right? So, like, I think we should consider maybe revising the timeline.
Sarah: I totally agree, John. I mean, we have to be realistic, you know. The timeline is, like, too tight. You know what I mean? We should definitely extend it.
"""
results = compressor.compress_prompt_llmlingua2(
original_prompt,
rate=0.6,
force_tokens=['\n', '.', '!', '?', ','],
chunk_end_tokens=['.', '\n'],
return_word_label=True,
drop_consecutive=True
)
print(results.keys())
print(f"Compressed prompt: {results['compressed_prompt']}")
print(f"Original tokens: {results['origin_tokens']}")
print(f"Compressed tokens: {results['compressed_tokens']}")
print(f"Compression rate: {results['rate']}")
# get the annotated results over the original prompt
word_sep = "\t\t|\t\t"
label_sep = " "
lines = results["fn_labeled_original_prompt"].split(word_sep)
annotated_results = []
for line in lines:
word, label = line.split(label_sep)
annotated_results.append((word, '+') if label == '1' else (word, '-')) # list of tuples: (word, label)
print("Annotated results:")
for word, label in annotated_results[:10]:
print(f"{word} {label}")
```
## Citation
```
@article{wu2024llmlingua2,
title = "{LLML}ingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression",
author = "Zhuoshi Pan and Qianhui Wu and Huiqiang Jiang and Menglin Xia and Xufang Luo and Jue Zhang and Qingwei Lin and Victor Ruhle and Yuqing Yang and Chin-Yew Lin and H. Vicky Zhao and Lili Qiu and Dongmei Zhang",
url = "https://arxiv.org/abs/2403.12968",
journal = "ArXiv preprint",
volume = "abs/2403.12968",
year = "2024",
}
```
|
{"license": "mit"}
|
task
|
[
"QUESTION_ANSWERING",
"SUMMARIZATION"
] | 41,545 |
SEBIS/legal_t5_small_trans_it_sv
|
SEBIS
|
text2text-generation
|
[
"transformers",
"pytorch",
"jax",
"t5",
"text2text-generation",
"translation Italian Swedish model",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2021-06-23T10:04:14+00:00
| 172 | 0 |
---
datasets:
- dcep europarl jrc-acquis
language: Italian Swedish
tags:
- translation Italian Swedish model
widget:
- text: K. considerando che, come avviene con tutti i sistemi di sanità elettronica,
la progettazione, lo sviluppo e l’attuazione di sistemi abilitati alla tecnologia
RFID presuppongono il coinvolgimento diretto dei professionisti sanitari, dei
pazienti e delle commissioni competenti (per esempio, sulla protezione dei dati
e sull’etica),
---
# legal_t5_small_trans_it_sv model
Model on translating legal text from Italian to Swedish. It was first released in
[this repository](https://github.com/agemagician/LegalTrans). This model is trained on three parallel corpus from jrc-acquis, europarl and dcep.
## Model description
legal_t5_small_trans_it_sv is based on the `t5-small` model and was trained on a large corpus of parallel text. This is a smaller model, which scales the baseline model of t5 down by using `dmodel = 512`, `dff = 2,048`, 8-headed attention, and only 6 layers each in the encoder and decoder. This variant has about 60 million parameters.
## Intended uses & limitations
The model could be used for translation of legal texts from Italian to Swedish.
### How to use
Here is how to use this model to translate legal text from Italian to Swedish in PyTorch:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline
pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_it_sv"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_it_sv", do_lower_case=False,
skip_special_tokens=True),
device=0
)
it_text = "K. considerando che, come avviene con tutti i sistemi di sanità elettronica, la progettazione, lo sviluppo e l’attuazione di sistemi abilitati alla tecnologia RFID presuppongono il coinvolgimento diretto dei professionisti sanitari, dei pazienti e delle commissioni competenti (per esempio, sulla protezione dei dati e sull’etica),"
pipeline([it_text], max_length=512)
```
## Training data
The legal_t5_small_trans_it_sv model was trained on [JRC-ACQUIS](https://wt-public.emm4u.eu/Acquis/index_2.2.html), [EUROPARL](https://www.statmt.org/europarl/), and [DCEP](https://ec.europa.eu/jrc/en/language-technologies/dcep) dataset consisting of 5 Million parallel texts.
## Training procedure
The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
### Preprocessing
An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
### Pretraining
## Evaluation results
When the model is used for translation test dataset, achieves the following results:
Test results :
| Model | BLEU score |
|:-----:|:-----:|
| legal_t5_small_trans_it_sv | 41.508|
### BibTeX entry and citation info
> Created by [Ahmed Elnaggar/@Elnaggar_AI](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/)
| null |
Non_BioNLP
|
# legal_t5_small_trans_it_sv model
Model on translating legal text from Italian to Swedish. It was first released in
[this repository](https://github.com/agemagician/LegalTrans). This model is trained on three parallel corpus from jrc-acquis, europarl and dcep.
## Model description
legal_t5_small_trans_it_sv is based on the `t5-small` model and was trained on a large corpus of parallel text. This is a smaller model, which scales the baseline model of t5 down by using `dmodel = 512`, `dff = 2,048`, 8-headed attention, and only 6 layers each in the encoder and decoder. This variant has about 60 million parameters.
## Intended uses & limitations
The model could be used for translation of legal texts from Italian to Swedish.
### How to use
Here is how to use this model to translate legal text from Italian to Swedish in PyTorch:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline
pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_it_sv"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_it_sv", do_lower_case=False,
skip_special_tokens=True),
device=0
)
it_text = "K. considerando che, come avviene con tutti i sistemi di sanità elettronica, la progettazione, lo sviluppo e l’attuazione di sistemi abilitati alla tecnologia RFID presuppongono il coinvolgimento diretto dei professionisti sanitari, dei pazienti e delle commissioni competenti (per esempio, sulla protezione dei dati e sull’etica),"
pipeline([it_text], max_length=512)
```
## Training data
The legal_t5_small_trans_it_sv model was trained on [JRC-ACQUIS](https://wt-public.emm4u.eu/Acquis/index_2.2.html), [EUROPARL](https://www.statmt.org/europarl/), and [DCEP](https://ec.europa.eu/jrc/en/language-technologies/dcep) dataset consisting of 5 Million parallel texts.
## Training procedure
The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
### Preprocessing
An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
### Pretraining
## Evaluation results
When the model is used for translation test dataset, achieves the following results:
Test results :
| Model | BLEU score |
|:-----:|:-----:|
| legal_t5_small_trans_it_sv | 41.508|
### BibTeX entry and citation info
> Created by [Ahmed Elnaggar/@Elnaggar_AI](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/)
|
{"datasets": ["dcep europarl jrc-acquis"], "language": "Italian Swedish", "tags": ["translation Italian Swedish model"], "widget": [{"text": "K. considerando che, come avviene con tutti i sistemi di sanità elettronica, la progettazione, lo sviluppo e l’attuazione di sistemi abilitati alla tecnologia RFID presuppongono il coinvolgimento diretto dei professionisti sanitari, dei pazienti e delle commissioni competenti (per esempio, sulla protezione dei dati e sull’etica),"}]}
|
task
|
[
"TRANSLATION"
] | 41,546 |
mqy/mt5-small-finetuned-26feb-1
|
mqy
|
summarization
|
[
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"summarization",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-02-26T03:37:01Z |
2023-02-26T17:46:02+00:00
| 20 | 0 |
---
license: apache-2.0
metrics:
- rouge
tags:
- summarization
- generated_from_trainer
model-index:
- name: mt5-small-finetuned-26feb-1
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. -->
# mt5-small-finetuned-26feb-1
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4486
- Rouge1: 20.86
- Rouge2: 6.45
- Rougel: 20.49
## 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: 0.0001
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|
| 5.4839 | 1.93 | 500 | 2.5990 | 16.14 | 5.18 | 15.98 |
| 3.1051 | 3.86 | 1000 | 2.4754 | 18.71 | 5.68 | 18.41 |
| 2.8659 | 5.79 | 1500 | 2.4006 | 18.22 | 5.54 | 18.06 |
| 2.71 | 7.72 | 2000 | 2.3848 | 19.91 | 6.0 | 19.65 |
| 2.5845 | 9.65 | 2500 | 2.3956 | 18.72 | 5.72 | 18.4 |
| 2.4895 | 11.58 | 3000 | 2.3719 | 19.9 | 6.1 | 19.54 |
| 2.402 | 13.51 | 3500 | 2.3691 | 19.86 | 5.79 | 19.51 |
| 2.3089 | 15.44 | 4000 | 2.3747 | 20.22 | 6.74 | 19.88 |
| 2.2681 | 17.37 | 4500 | 2.3754 | 19.44 | 5.53 | 19.03 |
| 2.1927 | 19.31 | 5000 | 2.3419 | 20.02 | 5.91 | 19.69 |
| 2.1278 | 21.24 | 5500 | 2.3496 | 20.26 | 6.21 | 19.79 |
| 2.0928 | 23.17 | 6000 | 2.3756 | 19.9 | 6.04 | 19.48 |
| 2.0658 | 25.1 | 6500 | 2.3615 | 19.61 | 6.04 | 19.28 |
| 2.0063 | 27.03 | 7000 | 2.3516 | 20.38 | 6.52 | 20.14 |
| 1.9581 | 28.96 | 7500 | 2.3743 | 20.61 | 6.26 | 20.24 |
| 1.941 | 30.89 | 8000 | 2.3726 | 19.73 | 5.8 | 19.31 |
| 1.9172 | 32.82 | 8500 | 2.3891 | 19.73 | 5.98 | 19.51 |
| 1.8764 | 34.75 | 9000 | 2.3782 | 20.1 | 6.15 | 19.74 |
| 1.8453 | 36.68 | 9500 | 2.3851 | 19.96 | 6.0 | 19.61 |
| 1.845 | 38.61 | 10000 | 2.4046 | 20.66 | 6.32 | 20.24 |
| 1.7919 | 40.54 | 10500 | 2.4169 | 20.65 | 6.25 | 20.38 |
| 1.7945 | 42.47 | 11000 | 2.4206 | 20.68 | 5.74 | 20.37 |
| 1.7689 | 44.4 | 11500 | 2.4246 | 20.69 | 6.09 | 20.4 |
| 1.7215 | 46.33 | 12000 | 2.4237 | 20.49 | 6.43 | 20.21 |
| 1.7306 | 48.26 | 12500 | 2.4217 | 20.55 | 6.49 | 20.18 |
| 1.7035 | 50.19 | 13000 | 2.4389 | 20.81 | 6.55 | 20.48 |
| 1.6934 | 52.12 | 13500 | 2.4377 | 20.75 | 6.85 | 20.35 |
| 1.7 | 54.05 | 14000 | 2.4486 | 20.86 | 6.45 | 20.49 |
| 1.6909 | 55.98 | 14500 | 2.4451 | 20.5 | 6.55 | 20.12 |
| 1.6804 | 57.92 | 15000 | 2.4457 | 20.21 | 6.5 | 19.84 |
| 1.6693 | 59.85 | 15500 | 2.4473 | 20.35 | 6.6 | 19.96 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2
| null |
Non_BioNLP
|
<!-- 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. -->
# mt5-small-finetuned-26feb-1
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4486
- Rouge1: 20.86
- Rouge2: 6.45
- Rougel: 20.49
## 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: 0.0001
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|
| 5.4839 | 1.93 | 500 | 2.5990 | 16.14 | 5.18 | 15.98 |
| 3.1051 | 3.86 | 1000 | 2.4754 | 18.71 | 5.68 | 18.41 |
| 2.8659 | 5.79 | 1500 | 2.4006 | 18.22 | 5.54 | 18.06 |
| 2.71 | 7.72 | 2000 | 2.3848 | 19.91 | 6.0 | 19.65 |
| 2.5845 | 9.65 | 2500 | 2.3956 | 18.72 | 5.72 | 18.4 |
| 2.4895 | 11.58 | 3000 | 2.3719 | 19.9 | 6.1 | 19.54 |
| 2.402 | 13.51 | 3500 | 2.3691 | 19.86 | 5.79 | 19.51 |
| 2.3089 | 15.44 | 4000 | 2.3747 | 20.22 | 6.74 | 19.88 |
| 2.2681 | 17.37 | 4500 | 2.3754 | 19.44 | 5.53 | 19.03 |
| 2.1927 | 19.31 | 5000 | 2.3419 | 20.02 | 5.91 | 19.69 |
| 2.1278 | 21.24 | 5500 | 2.3496 | 20.26 | 6.21 | 19.79 |
| 2.0928 | 23.17 | 6000 | 2.3756 | 19.9 | 6.04 | 19.48 |
| 2.0658 | 25.1 | 6500 | 2.3615 | 19.61 | 6.04 | 19.28 |
| 2.0063 | 27.03 | 7000 | 2.3516 | 20.38 | 6.52 | 20.14 |
| 1.9581 | 28.96 | 7500 | 2.3743 | 20.61 | 6.26 | 20.24 |
| 1.941 | 30.89 | 8000 | 2.3726 | 19.73 | 5.8 | 19.31 |
| 1.9172 | 32.82 | 8500 | 2.3891 | 19.73 | 5.98 | 19.51 |
| 1.8764 | 34.75 | 9000 | 2.3782 | 20.1 | 6.15 | 19.74 |
| 1.8453 | 36.68 | 9500 | 2.3851 | 19.96 | 6.0 | 19.61 |
| 1.845 | 38.61 | 10000 | 2.4046 | 20.66 | 6.32 | 20.24 |
| 1.7919 | 40.54 | 10500 | 2.4169 | 20.65 | 6.25 | 20.38 |
| 1.7945 | 42.47 | 11000 | 2.4206 | 20.68 | 5.74 | 20.37 |
| 1.7689 | 44.4 | 11500 | 2.4246 | 20.69 | 6.09 | 20.4 |
| 1.7215 | 46.33 | 12000 | 2.4237 | 20.49 | 6.43 | 20.21 |
| 1.7306 | 48.26 | 12500 | 2.4217 | 20.55 | 6.49 | 20.18 |
| 1.7035 | 50.19 | 13000 | 2.4389 | 20.81 | 6.55 | 20.48 |
| 1.6934 | 52.12 | 13500 | 2.4377 | 20.75 | 6.85 | 20.35 |
| 1.7 | 54.05 | 14000 | 2.4486 | 20.86 | 6.45 | 20.49 |
| 1.6909 | 55.98 | 14500 | 2.4451 | 20.5 | 6.55 | 20.12 |
| 1.6804 | 57.92 | 15000 | 2.4457 | 20.21 | 6.5 | 19.84 |
| 1.6693 | 59.85 | 15500 | 2.4473 | 20.35 | 6.6 | 19.96 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2
|
{"license": "apache-2.0", "metrics": ["rouge"], "tags": ["summarization", "generated_from_trainer"], "model-index": [{"name": "mt5-small-finetuned-26feb-1", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 41,547 |
NYTK/translation-mt5-small-128-en-hu
|
NYTK
|
translation
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"translation",
"en",
"hu",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2023-01-31T12:52:59+00:00
| 134 | 2 |
---
language:
- en
- hu
license: apache-2.0
metrics:
- sacrebleu
- chrf
tags:
- translation
widget:
- text: 'translate English to Hungarian: This may not make much sense to you, sir,
but I''d like to ask your permission to date your daughter.'
---
# mT5 Translation model
For further models, scripts and details, see [our repository](https://github.com/nytud/machine-translation) or [our demo site](https://juniper.nytud.hu/demo/nlp).
- Source language: English
- Target language: Hungarian
- Pretrained model used: mT5-small
- Finetuned on subcorpora from OPUS
- Segments: 56.837.602
- prefix: "translate English to Hungarian: "
## Limitations
- tokenized input text (tokenizer: [HuSpaCy](https://huggingface.co/huspacy))
- max_source_length = 128
- max_target_length = 128
## Results
| Model | BLEU | chrF-3 | chrF-6 |
| ------------- | ------------- | ------------- | ------------- |
| Google en-hu | 25.30 | 54.08 | 49.06 |
| BART | 36.89 | 60.77 | 56.4 |
| **mT5** | **27.69** | **53.73** | **48.57** |
## Citation
If you use this model, please cite the following paper:
```
@inproceedings {laki-yang-mt,
title = {{Jobban fordítunk magyarra, mint a Google!}},
booktitle = {XVIII. Magyar Számítógépes Nyelvészeti Konferencia},
year = {2022},
publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
address = {Szeged, Magyarország},
author = {Laki, László and Yang, Zijian Győző},
pages = {357--372}
}
```
| null |
Non_BioNLP
|
# mT5 Translation model
For further models, scripts and details, see [our repository](https://github.com/nytud/machine-translation) or [our demo site](https://juniper.nytud.hu/demo/nlp).
- Source language: English
- Target language: Hungarian
- Pretrained model used: mT5-small
- Finetuned on subcorpora from OPUS
- Segments: 56.837.602
- prefix: "translate English to Hungarian: "
## Limitations
- tokenized input text (tokenizer: [HuSpaCy](https://huggingface.co/huspacy))
- max_source_length = 128
- max_target_length = 128
## Results
| Model | BLEU | chrF-3 | chrF-6 |
| ------------- | ------------- | ------------- | ------------- |
| Google en-hu | 25.30 | 54.08 | 49.06 |
| BART | 36.89 | 60.77 | 56.4 |
| **mT5** | **27.69** | **53.73** | **48.57** |
## Citation
If you use this model, please cite the following paper:
```
@inproceedings {laki-yang-mt,
title = {{Jobban fordítunk magyarra, mint a Google!}},
booktitle = {XVIII. Magyar Számítógépes Nyelvészeti Konferencia},
year = {2022},
publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
address = {Szeged, Magyarország},
author = {Laki, László and Yang, Zijian Győző},
pages = {357--372}
}
```
|
{"language": ["en", "hu"], "license": "apache-2.0", "metrics": ["sacrebleu", "chrf"], "tags": ["translation"], "widget": [{"text": "translate English to Hungarian: This may not make much sense to you, sir, but I'd like to ask your permission to date your daughter."}]}
|
task
|
[
"TRANSLATION"
] | 41,548 |
lewtun/marian-finetuned-kde4-en-to-fr
|
lewtun
|
translation
|
[
"transformers",
"pytorch",
"tensorboard",
"marian",
"text2text-generation",
"translation",
"generated_from_trainer",
"dataset:kde4",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2021-11-14T16:59:34+00:00
| 117 | 0 |
---
datasets:
- kde4
license: apache-2.0
metrics:
- bleu
tags:
- translation
- generated_from_trainer
model-index:
- name: marian-finetuned-kde4-en-to-fr
results:
- task:
type: text2text-generation
name: Sequence-to-sequence Language Modeling
dataset:
name: kde4
type: kde4
args: en-fr
metrics:
- type: bleu
value: 38.988820814501665
name: Bleu
---
<!-- 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. -->
# marian-finetuned-kde4-en-to-fr
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6772
- Bleu: 38.9888
## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.12.3
- Pytorch 1.10.0+cu111
- Datasets 1.15.1
- Tokenizers 0.10.3
| null |
Non_BioNLP
|
<!-- 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. -->
# marian-finetuned-kde4-en-to-fr
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6772
- Bleu: 38.9888
## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.12.3
- Pytorch 1.10.0+cu111
- Datasets 1.15.1
- Tokenizers 0.10.3
|
{"datasets": ["kde4"], "license": "apache-2.0", "metrics": ["bleu"], "tags": ["translation", "generated_from_trainer"], "model-index": [{"name": "marian-finetuned-kde4-en-to-fr", "results": [{"task": {"type": "text2text-generation", "name": "Sequence-to-sequence Language Modeling"}, "dataset": {"name": "kde4", "type": "kde4", "args": "en-fr"}, "metrics": [{"type": "bleu", "value": 38.988820814501665, "name": "Bleu"}]}]}]}
|
task
|
[
"TRANSLATION"
] | 41,549 |
Nextcloud-AI/opus-mt-de-en
|
Nextcloud-AI
|
translation
|
[
"transformers",
"pytorch",
"tf",
"rust",
"marian",
"text2text-generation",
"translation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-02-23T10:37:55Z |
2023-08-16T11:27:46+00:00
| 15 | 0 |
---
license: apache-2.0
tags:
- translation
---
### opus-mt-de-en
* source languages: de
* target languages: en
* OPUS readme: [de-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-en/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-02-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.zip)
* test set translations: [opus-2020-02-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.test.txt)
* test set scores: [opus-2020-02-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| newssyscomb2009.de.en | 29.4 | 0.557 |
| news-test2008.de.en | 27.8 | 0.548 |
| newstest2009.de.en | 26.8 | 0.543 |
| newstest2010.de.en | 30.2 | 0.584 |
| newstest2011.de.en | 27.4 | 0.556 |
| newstest2012.de.en | 29.1 | 0.569 |
| newstest2013.de.en | 32.1 | 0.583 |
| newstest2014-deen.de.en | 34.0 | 0.600 |
| newstest2015-ende.de.en | 34.2 | 0.599 |
| newstest2016-ende.de.en | 40.4 | 0.649 |
| newstest2017-ende.de.en | 35.7 | 0.610 |
| newstest2018-ende.de.en | 43.7 | 0.667 |
| newstest2019-deen.de.en | 40.1 | 0.642 |
| Tatoeba.de.en | 55.4 | 0.707 |
| null |
Non_BioNLP
|
### opus-mt-de-en
* source languages: de
* target languages: en
* OPUS readme: [de-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-en/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-02-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.zip)
* test set translations: [opus-2020-02-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.test.txt)
* test set scores: [opus-2020-02-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-en/opus-2020-02-26.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| newssyscomb2009.de.en | 29.4 | 0.557 |
| news-test2008.de.en | 27.8 | 0.548 |
| newstest2009.de.en | 26.8 | 0.543 |
| newstest2010.de.en | 30.2 | 0.584 |
| newstest2011.de.en | 27.4 | 0.556 |
| newstest2012.de.en | 29.1 | 0.569 |
| newstest2013.de.en | 32.1 | 0.583 |
| newstest2014-deen.de.en | 34.0 | 0.600 |
| newstest2015-ende.de.en | 34.2 | 0.599 |
| newstest2016-ende.de.en | 40.4 | 0.649 |
| newstest2017-ende.de.en | 35.7 | 0.610 |
| newstest2018-ende.de.en | 43.7 | 0.667 |
| newstest2019-deen.de.en | 40.1 | 0.642 |
| Tatoeba.de.en | 55.4 | 0.707 |
|
{"license": "apache-2.0", "tags": ["translation"]}
|
task
|
[
"TRANSLATION"
] | 41,550 |
EmanDev/news_summary_model_trained_on_reduced_data
|
EmanDev
|
text2text-generation
|
[
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:gsarti/it5-small-news-summarization",
"base_model:finetune:gsarti/it5-small-news-summarization",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-09-27T13:04:25Z |
2024-09-27T16:20:28+00:00
| 13 | 0 |
---
base_model: gsarti/it5-small-news-summarization
library_name: transformers
license: apache-2.0
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: news_summary_model_trained_on_reduced_data
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. -->
# news_summary_model_trained_on_reduced_data
This model is a fine-tuned version of [gsarti/it5-small-news-summarization](https://huggingface.co/gsarti/it5-small-news-summarization) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 0.1141
- Rouge2: 0.0402
- Rougel: 0.1005
- Rougelsum: 0.1018
- Generated Length: 19.0
## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Generated Length |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------------:|
| No log | 1.0 | 9 | nan | 0.1141 | 0.0402 | 0.1005 | 0.1018 | 19.0 |
| No log | 2.0 | 18 | nan | 0.1141 | 0.0402 | 0.1005 | 0.1018 | 19.0 |
| No log | 3.0 | 27 | nan | 0.1141 | 0.0402 | 0.1005 | 0.1018 | 19.0 |
### Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
| null |
TBD
|
<!-- 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. -->
# news_summary_model_trained_on_reduced_data
This model is a fine-tuned version of [gsarti/it5-small-news-summarization](https://huggingface.co/gsarti/it5-small-news-summarization) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 0.1141
- Rouge2: 0.0402
- Rougel: 0.1005
- Rougelsum: 0.1018
- Generated Length: 19.0
## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Generated Length |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------------:|
| No log | 1.0 | 9 | nan | 0.1141 | 0.0402 | 0.1005 | 0.1018 | 19.0 |
| No log | 2.0 | 18 | nan | 0.1141 | 0.0402 | 0.1005 | 0.1018 | 19.0 |
| No log | 3.0 | 27 | nan | 0.1141 | 0.0402 | 0.1005 | 0.1018 | 19.0 |
### Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
|
{"base_model": "gsarti/it5-small-news-summarization", "library_name": "transformers", "license": "apache-2.0", "metrics": ["rouge"], "tags": ["generated_from_trainer"], "model-index": [{"name": "news_summary_model_trained_on_reduced_data", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 41,551 |
MounikaAithagoni/Traanslator
|
MounikaAithagoni
| null |
[
"ar",
"en",
"dataset:saillab/taco-datasets",
"license:mit",
"region:us"
] | 2024-11-16T20:40:18Z |
2024-11-16T21:45:01+00:00
| 0 | 0 |
---
datasets:
- saillab/taco-datasets
language:
- ar
- en
license: mit
---
Arabic Translator: Machine Learning Model
This repository contains a machine learning model designed to translate text into Arabic. The model is trained on a custom dataset and fine-tuned to optimize translation accuracy while balancing training and validation performance.
📄 Overview:
The model is built using deep learning techniques to translate text effectively. It was trained and validated using loss metrics to monitor performance over multiple epochs. The training process is visualized through loss curves that demonstrate learning progress and highlight overfitting challenges.
Key Features:
Language Support: Translates text into Arabic.
Model Architecture: Based on [model architecture used, e.g., Transformer, RNN, etc.].
Preprocessing: Includes tokenization and encoding steps for handling Arabic script.
Evaluation: Monitored with training and validation loss for consistent improvement.
🚀 How to Use
Installation
Clone this repository:
git clone https://huggingface.co/MounikaAithagoni/Traanslator
cd arabic-translator
Install dependencies:
pip install -r requirements.txt
Model Inference
from transformers import <ModelClass>, AutoTokenizer
# Load the model and tokenizer
model = <ModelClass>.from_pretrained("<https://huggingface.co/MounikaAithagoni/Traanslator>")
tokenizer = AutoTokenizer.from_pretrained("<https://huggingface.co/MounikaAithagoni/Traanslator>")
# Translate a sample sentence
text = "Hello, how are you?"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs)
translation = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(f"Translation: {translation}")
🧑💻 Training Details
Training Loss: Decreased steadily across epochs, indicating effective learning.
Validation Loss: Decreased initially but plateaued later, suggesting overfitting beyond epoch 5.
Epochs: Trained for 10 epochs with an early stopping mechanism.
📝 Dataset
https://huggingface.co/datasets/saillab/taco-datasets/tree/main/multilingual-instruction-tuning-dataset%20/multilingual-alpaca-52k-gpt-4Links to an external site.
The model was trained on a custom dataset tailored for Arabic translation. Preprocessing steps included:
Tokenizing and encoding text data.
Splitting into training and validation sets.
For details on the dataset format, refer to the data/ folder.
📊 Evaluation
Metrics: Training and validation loss monitored.
Performance: Shows good initial generalization with validation loss increasing slightly after the 5th epoch, signaling overfitting.
🔧 Future Improvements
Implement techniques to address overfitting, such as regularization or data augmentation.
Fine-tune on larger, more diverse datasets for better generalization.
| null |
Non_BioNLP
|
Arabic Translator: Machine Learning Model
This repository contains a machine learning model designed to translate text into Arabic. The model is trained on a custom dataset and fine-tuned to optimize translation accuracy while balancing training and validation performance.
📄 Overview:
The model is built using deep learning techniques to translate text effectively. It was trained and validated using loss metrics to monitor performance over multiple epochs. The training process is visualized through loss curves that demonstrate learning progress and highlight overfitting challenges.
Key Features:
Language Support: Translates text into Arabic.
Model Architecture: Based on [model architecture used, e.g., Transformer, RNN, etc.].
Preprocessing: Includes tokenization and encoding steps for handling Arabic script.
Evaluation: Monitored with training and validation loss for consistent improvement.
🚀 How to Use
Installation
Clone this repository:
git clone https://huggingface.co/MounikaAithagoni/Traanslator
cd arabic-translator
Install dependencies:
pip install -r requirements.txt
Model Inference
from transformers import <ModelClass>, AutoTokenizer
# Load the model and tokenizer
model = <ModelClass>.from_pretrained("<https://huggingface.co/MounikaAithagoni/Traanslator>")
tokenizer = AutoTokenizer.from_pretrained("<https://huggingface.co/MounikaAithagoni/Traanslator>")
# Translate a sample sentence
text = "Hello, how are you?"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs)
translation = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(f"Translation: {translation}")
🧑💻 Training Details
Training Loss: Decreased steadily across epochs, indicating effective learning.
Validation Loss: Decreased initially but plateaued later, suggesting overfitting beyond epoch 5.
Epochs: Trained for 10 epochs with an early stopping mechanism.
📝 Dataset
https://huggingface.co/datasets/saillab/taco-datasets/tree/main/multilingual-instruction-tuning-dataset%20/multilingual-alpaca-52k-gpt-4Links to an external site.
The model was trained on a custom dataset tailored for Arabic translation. Preprocessing steps included:
Tokenizing and encoding text data.
Splitting into training and validation sets.
For details on the dataset format, refer to the data/ folder.
📊 Evaluation
Metrics: Training and validation loss monitored.
Performance: Shows good initial generalization with validation loss increasing slightly after the 5th epoch, signaling overfitting.
🔧 Future Improvements
Implement techniques to address overfitting, such as regularization or data augmentation.
Fine-tune on larger, more diverse datasets for better generalization.
|
{"datasets": ["saillab/taco-datasets"], "language": ["ar", "en"], "license": "mit"}
|
task
|
[
"TRANSLATION"
] | 41,552 |
transformersbook/xlm-roberta-base-finetuned-panx-all
|
transformersbook
|
token-classification
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:wikiann",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2022-06-25T09:44:57+00:00
| 124 | 4 |
---
datasets:
- wikiann
license: mit
metrics:
- f1
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-base-finetuned-panx-all
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: wikiann
type: wikiann
config: en
split: test
metrics:
- type: accuracy
value: 0.843189280620875
name: Accuracy
verified: true
- type: precision
value: 0.8410061269097046
name: Precision
verified: true
- type: recall
value: 0.8568527450211155
name: Recall
verified: true
- type: f1
value: 0.8488554853827908
name: F1
verified: true
- type: loss
value: 0.6632214784622192
name: loss
verified: true
---
<!-- 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-base-finetuned-panx-all
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the PAN-X dataset. The model is trained in Chapter 4: Multilingual Named Entity Recognition in the [NLP with Transformers book](https://learning.oreilly.com/library/view/natural-language-processing/9781098103231/). You can find the full code in the accompanying [Github repository](https://github.com/nlp-with-transformers/notebooks/blob/main/04_multilingual-ner.ipynb).
It achieves the following results on the evaluation set:
- Loss: 0.1739
- F1: 0.8581
## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2912 | 1.0 | 835 | 0.1883 | 0.8238 |
| 0.1548 | 2.0 | 1670 | 0.1738 | 0.8480 |
| 0.101 | 3.0 | 2505 | 0.1739 | 0.8581 |
### Framework versions
- Transformers 4.12.0.dev0
- Pytorch 1.9.1+cu102
- Datasets 1.12.1
- Tokenizers 0.10.3
| null |
Non_BioNLP
|
<!-- 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-base-finetuned-panx-all
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the PAN-X dataset. The model is trained in Chapter 4: Multilingual Named Entity Recognition in the [NLP with Transformers book](https://learning.oreilly.com/library/view/natural-language-processing/9781098103231/). You can find the full code in the accompanying [Github repository](https://github.com/nlp-with-transformers/notebooks/blob/main/04_multilingual-ner.ipynb).
It achieves the following results on the evaluation set:
- Loss: 0.1739
- F1: 0.8581
## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2912 | 1.0 | 835 | 0.1883 | 0.8238 |
| 0.1548 | 2.0 | 1670 | 0.1738 | 0.8480 |
| 0.101 | 3.0 | 2505 | 0.1739 | 0.8581 |
### Framework versions
- Transformers 4.12.0.dev0
- Pytorch 1.9.1+cu102
- Datasets 1.12.1
- Tokenizers 0.10.3
|
{"datasets": ["wikiann"], "license": "mit", "metrics": ["f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "xlm-roberta-base-finetuned-panx-all", "results": [{"task": {"type": "token-classification", "name": "Token Classification"}, "dataset": {"name": "wikiann", "type": "wikiann", "config": "en", "split": "test"}, "metrics": [{"type": "accuracy", "value": 0.843189280620875, "name": "Accuracy", "verified": true}, {"type": "precision", "value": 0.8410061269097046, "name": "Precision", "verified": true}, {"type": "recall", "value": 0.8568527450211155, "name": "Recall", "verified": true}, {"type": "f1", "value": 0.8488554853827908, "name": "F1", "verified": true}, {"type": "loss", "value": 0.6632214784622192, "name": "loss", "verified": true}]}]}]}
|
task
|
[
"NAMED_ENTITY_RECOGNITION"
] | 41,553 |
gokuls/bert_uncased_L-10_H-128_A-2_massive
|
gokuls
|
text-classification
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:massive",
"base_model:google/bert_uncased_L-10_H-128_A-2",
"base_model:finetune:google/bert_uncased_L-10_H-128_A-2",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-10-06T18:21:48Z |
2023-10-06T18:26:07+00:00
| 22 | 0 |
---
base_model: google/bert_uncased_L-10_H-128_A-2
datasets:
- massive
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: bert_uncased_L-10_H-128_A-2_massive
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: massive
type: massive
config: en-US
split: validation
args: en-US
metrics:
- type: accuracy
value: 0.7466797835710772
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. -->
# bert_uncased_L-10_H-128_A-2_massive
This model is a fine-tuned version of [google/bert_uncased_L-10_H-128_A-2](https://huggingface.co/google/bert_uncased_L-10_H-128_A-2) on the massive dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4064
- Accuracy: 0.7467
## 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: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 3.8032 | 1.0 | 180 | 3.4795 | 0.3296 |
| 3.2716 | 2.0 | 360 | 2.9915 | 0.4491 |
| 2.8593 | 3.0 | 540 | 2.6360 | 0.5145 |
| 2.5442 | 4.0 | 720 | 2.3533 | 0.5765 |
| 2.296 | 5.0 | 900 | 2.1403 | 0.6006 |
| 2.0936 | 6.0 | 1080 | 1.9655 | 0.6463 |
| 1.9277 | 7.0 | 1260 | 1.8291 | 0.6719 |
| 1.7937 | 8.0 | 1440 | 1.7114 | 0.6911 |
| 1.6829 | 9.0 | 1620 | 1.6267 | 0.7088 |
| 1.5946 | 10.0 | 1800 | 1.5575 | 0.7231 |
| 1.5258 | 11.0 | 1980 | 1.4976 | 0.7354 |
| 1.4663 | 12.0 | 2160 | 1.4616 | 0.7364 |
| 1.4256 | 13.0 | 2340 | 1.4296 | 0.7437 |
| 1.3984 | 14.0 | 2520 | 1.4126 | 0.7442 |
| 1.3824 | 15.0 | 2700 | 1.4064 | 0.7467 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
| null |
Non_BioNLP
|
<!-- 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. -->
# bert_uncased_L-10_H-128_A-2_massive
This model is a fine-tuned version of [google/bert_uncased_L-10_H-128_A-2](https://huggingface.co/google/bert_uncased_L-10_H-128_A-2) on the massive dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4064
- Accuracy: 0.7467
## 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: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 3.8032 | 1.0 | 180 | 3.4795 | 0.3296 |
| 3.2716 | 2.0 | 360 | 2.9915 | 0.4491 |
| 2.8593 | 3.0 | 540 | 2.6360 | 0.5145 |
| 2.5442 | 4.0 | 720 | 2.3533 | 0.5765 |
| 2.296 | 5.0 | 900 | 2.1403 | 0.6006 |
| 2.0936 | 6.0 | 1080 | 1.9655 | 0.6463 |
| 1.9277 | 7.0 | 1260 | 1.8291 | 0.6719 |
| 1.7937 | 8.0 | 1440 | 1.7114 | 0.6911 |
| 1.6829 | 9.0 | 1620 | 1.6267 | 0.7088 |
| 1.5946 | 10.0 | 1800 | 1.5575 | 0.7231 |
| 1.5258 | 11.0 | 1980 | 1.4976 | 0.7354 |
| 1.4663 | 12.0 | 2160 | 1.4616 | 0.7364 |
| 1.4256 | 13.0 | 2340 | 1.4296 | 0.7437 |
| 1.3984 | 14.0 | 2520 | 1.4126 | 0.7442 |
| 1.3824 | 15.0 | 2700 | 1.4064 | 0.7467 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
|
{"base_model": "google/bert_uncased_L-10_H-128_A-2", "datasets": ["massive"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "bert_uncased_L-10_H-128_A-2_massive", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "massive", "type": "massive", "config": "en-US", "split": "validation", "args": "en-US"}, "metrics": [{"type": "accuracy", "value": 0.7466797835710772, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,554 |
Ayham/bert_roberta_summarization_cnn_dailymail
|
Ayham
|
text2text-generation
|
[
"transformers",
"pytorch",
"tensorboard",
"encoder-decoder",
"text2text-generation",
"generated_from_trainer",
"dataset:cnn_dailymail",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2022-02-24T15:40:51+00:00
| 265 | 1 |
---
datasets:
- cnn_dailymail
tags:
- generated_from_trainer
model-index:
- name: bert_roberta_summarization_cnn_dailymail
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. -->
# bert_roberta_summarization_cnn_dailymail
This model is a fine-tuned version of [](https://huggingface.co/) on the cnn_dailymail dataset.
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 3.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.12.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.10.3
| null |
Non_BioNLP
|
<!-- 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. -->
# bert_roberta_summarization_cnn_dailymail
This model is a fine-tuned version of [](https://huggingface.co/) on the cnn_dailymail dataset.
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 3.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.12.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.10.3
|
{"datasets": ["cnn_dailymail"], "tags": ["generated_from_trainer"], "model-index": [{"name": "bert_roberta_summarization_cnn_dailymail", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 41,555 |
xjlulu/ntu_adl_summarization_mt5_s
|
xjlulu
|
summarization
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"generated_from_trainer",
"summarization",
"zh",
"dataset:xjlulu/ntu_adl_summarization",
"base_model:google/mt5-small",
"base_model:finetune:google/mt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-10-23T05:29:29Z |
2023-10-23T12:37:13+00:00
| 45 | 0 |
---
base_model: google/mt5-small
datasets:
- xjlulu/ntu_adl_summarization
language:
- zh
license: apache-2.0
metrics:
- rouge
pipeline_tag: summarization
tags:
- generated_from_trainer
model-index:
- name: ntu_adl_summarization_mt5_s
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. -->
# ntu_adl_summarization_mt5_s
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6583
- Rouge-1: 21.9729
- Rouge-2: 7.6735
- Rouge-l: 19.7497
- Ave Gen Len: 17.3098
## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Ave Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:-----------:|
| 5.4447 | 1.0 | 1357 | 4.1235 | 17.7916 | 5.9785 | 16.5599 | 12.7161 |
| 4.7463 | 2.0 | 2714 | 3.9569 | 19.6608 | 6.7631 | 18.0768 | 14.8245 |
| 4.5203 | 3.0 | 4071 | 3.8545 | 20.5626 | 7.0737 | 18.7628 | 16.3307 |
| 4.4285 | 4.0 | 5428 | 3.7825 | 21.0690 | 7.2030 | 19.0863 | 16.7841 |
| 4.3196 | 5.0 | 6785 | 3.7269 | 21.2881 | 7.3307 | 19.2588 | 16.9276 |
| 4.2662 | 6.0 | 8142 | 3.7027 | 21.5793 | 7.5122 | 19.4806 | 17.0333 |
| 4.2057 | 7.0 | 9499 | 3.6764 | 21.7949 | 7.5987 | 19.6082 | 17.1811 |
| 4.1646 | 8.0 | 10856 | 3.6671 | 21.8164 | 7.5705 | 19.6207 | 17.2550 |
| 4.1399 | 9.0 | 12213 | 3.6602 | 21.9381 | 7.6577 | 19.7089 | 17.3014 |
| 4.1479 | 10.0 | 13570 | 3.6583 | 21.9729 | 7.6735 | 19.7497 | 17.3098 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
| null |
Non_BioNLP
|
<!-- 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. -->
# ntu_adl_summarization_mt5_s
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6583
- Rouge-1: 21.9729
- Rouge-2: 7.6735
- Rouge-l: 19.7497
- Ave Gen Len: 17.3098
## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Ave Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:-----------:|
| 5.4447 | 1.0 | 1357 | 4.1235 | 17.7916 | 5.9785 | 16.5599 | 12.7161 |
| 4.7463 | 2.0 | 2714 | 3.9569 | 19.6608 | 6.7631 | 18.0768 | 14.8245 |
| 4.5203 | 3.0 | 4071 | 3.8545 | 20.5626 | 7.0737 | 18.7628 | 16.3307 |
| 4.4285 | 4.0 | 5428 | 3.7825 | 21.0690 | 7.2030 | 19.0863 | 16.7841 |
| 4.3196 | 5.0 | 6785 | 3.7269 | 21.2881 | 7.3307 | 19.2588 | 16.9276 |
| 4.2662 | 6.0 | 8142 | 3.7027 | 21.5793 | 7.5122 | 19.4806 | 17.0333 |
| 4.2057 | 7.0 | 9499 | 3.6764 | 21.7949 | 7.5987 | 19.6082 | 17.1811 |
| 4.1646 | 8.0 | 10856 | 3.6671 | 21.8164 | 7.5705 | 19.6207 | 17.2550 |
| 4.1399 | 9.0 | 12213 | 3.6602 | 21.9381 | 7.6577 | 19.7089 | 17.3014 |
| 4.1479 | 10.0 | 13570 | 3.6583 | 21.9729 | 7.6735 | 19.7497 | 17.3098 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
{"base_model": "google/mt5-small", "datasets": ["xjlulu/ntu_adl_summarization"], "language": ["zh"], "license": "apache-2.0", "metrics": ["rouge"], "pipeline_tag": "summarization", "tags": ["generated_from_trainer"], "model-index": [{"name": "ntu_adl_summarization_mt5_s", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 41,556 |
google/t5-11b-ssm-tqao
|
google
|
text2text-generation
|
[
"transformers",
"pytorch",
"tf",
"t5",
"text2text-generation",
"en",
"dataset:c4",
"dataset:wikipedia",
"dataset:trivia_qa",
"arxiv:2002.08909",
"arxiv:1910.10683",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2023-01-24T16:43:37+00:00
| 12 | 0 |
---
datasets:
- c4
- wikipedia
- trivia_qa
language: en
license: apache-2.0
---
[Google's T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) for **Closed Book Question Answering**.
The model was pre-trained using T5's denoising objective on [C4](https://huggingface.co/datasets/c4), subsequently additionally pre-trained using [REALM](https://arxiv.org/pdf/2002.08909.pdf)'s salient span masking objective on [Wikipedia](https://huggingface.co/datasets/wikipedia), and finally fine-tuned on [Trivia QA (TQA)](https://huggingface.co/datasets/trivia_qa).
**Note**: The model was fine-tuned on 90% of the train splits of [Trivia QA (TQA)](https://huggingface.co/datasets/trivia_qa) for 20k steps and validated on the held-out 10% of the train split.
Other community Checkpoints: [here](https://huggingface.co/models?search=ssm)
Paper: [How Much Knowledge Can You Pack
Into the Parameters of a Language Model?](https://arxiv.org/abs/1910.10683.pdf)
Authors: *Adam Roberts, Colin Raffel, Noam Shazeer*
## Results on Trivia QA - Test Set
|Id | link | Exact Match |
|---|---|---|
|**T5-11b**|**https://huggingface.co/google/t5-large-ssm-tqao**|**51.0**|
|T5-xxl|https://huggingface.co/google/t5-xxl-ssm-tqao|51.9|
## Usage
The model can be used as follows for **closed book question answering**:
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
t5_qa_model = AutoModelForSeq2SeqLM.from_pretrained("google/t5-11b-ssm-tqao")
t5_tok = AutoTokenizer.from_pretrained("google/t5-11b-ssm-tqao")
input_ids = t5_tok("When was Franklin D. Roosevelt born?", return_tensors="pt").input_ids
gen_output = t5_qa_model.generate(input_ids)[0]
print(t5_tok.decode(gen_output, skip_special_tokens=True))
```
## Abstract
It has recently been observed that neural language models trained on unstructured text can implicitly store and retrieve knowledge using natural language queries. In this short paper, we measure the practical utility of this approach by fine-tuning pre-trained models to answer questions without access to any external context or knowledge. We show that this approach scales with model size and performs competitively with open-domain systems that explicitly retrieve answers from an external knowledge source when answering questions. To facilitate reproducibility and future work, we release our code and trained models at https://goo.gle/t5-cbqa.
| null |
Non_BioNLP
|
[Google's T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) for **Closed Book Question Answering**.
The model was pre-trained using T5's denoising objective on [C4](https://huggingface.co/datasets/c4), subsequently additionally pre-trained using [REALM](https://arxiv.org/pdf/2002.08909.pdf)'s salient span masking objective on [Wikipedia](https://huggingface.co/datasets/wikipedia), and finally fine-tuned on [Trivia QA (TQA)](https://huggingface.co/datasets/trivia_qa).
**Note**: The model was fine-tuned on 90% of the train splits of [Trivia QA (TQA)](https://huggingface.co/datasets/trivia_qa) for 20k steps and validated on the held-out 10% of the train split.
Other community Checkpoints: [here](https://huggingface.co/models?search=ssm)
Paper: [How Much Knowledge Can You Pack
Into the Parameters of a Language Model?](https://arxiv.org/abs/1910.10683.pdf)
Authors: *Adam Roberts, Colin Raffel, Noam Shazeer*
## Results on Trivia QA - Test Set
|Id | link | Exact Match |
|---|---|---|
|**T5-11b**|**https://huggingface.co/google/t5-large-ssm-tqao**|**51.0**|
|T5-xxl|https://huggingface.co/google/t5-xxl-ssm-tqao|51.9|
## Usage
The model can be used as follows for **closed book question answering**:
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
t5_qa_model = AutoModelForSeq2SeqLM.from_pretrained("google/t5-11b-ssm-tqao")
t5_tok = AutoTokenizer.from_pretrained("google/t5-11b-ssm-tqao")
input_ids = t5_tok("When was Franklin D. Roosevelt born?", return_tensors="pt").input_ids
gen_output = t5_qa_model.generate(input_ids)[0]
print(t5_tok.decode(gen_output, skip_special_tokens=True))
```
## Abstract
It has recently been observed that neural language models trained on unstructured text can implicitly store and retrieve knowledge using natural language queries. In this short paper, we measure the practical utility of this approach by fine-tuning pre-trained models to answer questions without access to any external context or knowledge. We show that this approach scales with model size and performs competitively with open-domain systems that explicitly retrieve answers from an external knowledge source when answering questions. To facilitate reproducibility and future work, we release our code and trained models at https://goo.gle/t5-cbqa.
|
{"datasets": ["c4", "wikipedia", "trivia_qa"], "language": "en", "license": "apache-2.0"}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,557 |
isanchez/text-comp
|
isanchez
|
text-classification
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-09-20T21:05:25Z |
2023-09-21T04:46:05+00:00
| 9 | 0 |
---
base_model: distilroberta-base
datasets:
- glue
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: text-comp
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- type: accuracy
value: 0.8357843137254902
name: Accuracy
- type: f1
value: 0.8770642201834863
name: F1
---
<!-- 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. -->
# text-comp
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5361
- Accuracy: 0.8358
- F1: 0.8771
## 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: 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.5903 | 1.09 | 500 | 0.4340 | 0.8137 | 0.8643 |
| 0.3827 | 2.18 | 1000 | 0.5361 | 0.8358 | 0.8771 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
| null |
Non_BioNLP
|
<!-- 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. -->
# text-comp
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5361
- Accuracy: 0.8358
- F1: 0.8771
## 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: 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.5903 | 1.09 | 500 | 0.4340 | 0.8137 | 0.8643 |
| 0.3827 | 2.18 | 1000 | 0.5361 | 0.8358 | 0.8771 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
{"base_model": "distilroberta-base", "datasets": ["glue"], "license": "apache-2.0", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "text-comp", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "config": "mrpc", "split": "validation", "args": "mrpc"}, "metrics": [{"type": "accuracy", "value": 0.8357843137254902, "name": "Accuracy"}, {"type": "f1", "value": 0.8770642201834863, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,558 |
masato12/bart-large-mnli
|
masato12
|
zero-shot-classification
|
[
"Transformers PHP",
"onnx",
"zero-shot-classification",
"dataset:multi_nli",
"arxiv:1910.13461",
"arxiv:1909.00161",
"license:mit",
"region:us"
] | 2024-07-14T22:18:44Z |
2024-07-14T22:20:28+00:00
| 0 | 0 |
---
datasets:
- multi_nli
library_name: Transformers PHP
license: mit
pipeline_tag: zero-shot-classification
tags:
- onnx
thumbnail: https://huggingface.co/front/thumbnails/facebook.png
---
https://huggingface.co/facebook/bart-large-mnli with ONNX weights to be compatible with Transformers PHP
# bart-large-mnli
This is the checkpoint for [bart-large](https://huggingface.co/facebook/bart-large) after being trained on the [MultiNLI (MNLI)](https://huggingface.co/datasets/multi_nli) dataset.
Additional information about this model:
- The [bart-large](https://huggingface.co/facebook/bart-large) model page
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
](https://arxiv.org/abs/1910.13461)
- [BART fairseq implementation](https://github.com/pytorch/fairseq/tree/master/fairseq/models/bart)
## NLI-based Zero Shot Text Classification
[Yin et al.](https://arxiv.org/abs/1909.00161) proposed a method for using pre-trained NLI models as a ready-made zero-shot sequence classifiers. The method works by posing the sequence to be classified as the NLI premise and to construct a hypothesis from each candidate label. For example, if we want to evaluate whether a sequence belongs to the class "politics", we could construct a hypothesis of `This text is about politics.`. The probabilities for entailment and contradiction are then converted to label probabilities.
This method is surprisingly effective in many cases, particularly when used with larger pre-trained models like BART and Roberta. See [this blog post](https://joeddav.github.io/blog/2020/05/29/ZSL.html) for a more expansive introduction to this and other zero shot methods, and see the code snippets below for examples of using this model for zero-shot classification both with Hugging Face's built-in pipeline and with native Transformers/PyTorch code.
#### With the zero-shot classification pipeline
The model can be loaded with the `zero-shot-classification` pipeline like so:
```python
from transformers import pipeline
classifier = pipeline("zero-shot-classification",
model="facebook/bart-large-mnli")
```
You can then use this pipeline to classify sequences into any of the class names you specify.
```python
sequence_to_classify = "one day I will see the world"
candidate_labels = ['travel', 'cooking', 'dancing']
classifier(sequence_to_classify, candidate_labels)
#{'labels': ['travel', 'dancing', 'cooking'],
# 'scores': [0.9938651323318481, 0.0032737774308770895, 0.002861034357920289],
# 'sequence': 'one day I will see the world'}
```
If more than one candidate label can be correct, pass `multi_label=True` to calculate each class independently:
```python
candidate_labels = ['travel', 'cooking', 'dancing', 'exploration']
classifier(sequence_to_classify, candidate_labels, multi_label=True)
#{'labels': ['travel', 'exploration', 'dancing', 'cooking'],
# 'scores': [0.9945111274719238,
# 0.9383890628814697,
# 0.0057061901316046715,
# 0.0018193122232332826],
# 'sequence': 'one day I will see the world'}
```
#### With manual PyTorch
```python
# pose sequence as a NLI premise and label as a hypothesis
from transformers import AutoModelForSequenceClassification, AutoTokenizer
nli_model = AutoModelForSequenceClassification.from_pretrained('facebook/bart-large-mnli')
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-mnli')
premise = sequence
hypothesis = f'This example is {label}.'
# run through model pre-trained on MNLI
x = tokenizer.encode(premise, hypothesis, return_tensors='pt',
truncation_strategy='only_first')
logits = nli_model(x.to(device))[0]
# we throw away "neutral" (dim 1) and take the probability of
# "entailment" (2) as the probability of the label being true
entail_contradiction_logits = logits[:,[0,2]]
probs = entail_contradiction_logits.softmax(dim=1)
prob_label_is_true = probs[:,1]
```
---
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
| null |
Non_BioNLP
| ERROR: type should be string, got "\nhttps://huggingface.co/facebook/bart-large-mnli with ONNX weights to be compatible with Transformers PHP\n\n\n# bart-large-mnli\n\nThis is the checkpoint for [bart-large](https://huggingface.co/facebook/bart-large) after being trained on the [MultiNLI (MNLI)](https://huggingface.co/datasets/multi_nli) dataset.\n\nAdditional information about this model:\n- The [bart-large](https://huggingface.co/facebook/bart-large) model page\n- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension\n](https://arxiv.org/abs/1910.13461)\n- [BART fairseq implementation](https://github.com/pytorch/fairseq/tree/master/fairseq/models/bart)\n\n## NLI-based Zero Shot Text Classification\n\n[Yin et al.](https://arxiv.org/abs/1909.00161) proposed a method for using pre-trained NLI models as a ready-made zero-shot sequence classifiers. The method works by posing the sequence to be classified as the NLI premise and to construct a hypothesis from each candidate label. For example, if we want to evaluate whether a sequence belongs to the class \"politics\", we could construct a hypothesis of `This text is about politics.`. The probabilities for entailment and contradiction are then converted to label probabilities.\n\nThis method is surprisingly effective in many cases, particularly when used with larger pre-trained models like BART and Roberta. See [this blog post](https://joeddav.github.io/blog/2020/05/29/ZSL.html) for a more expansive introduction to this and other zero shot methods, and see the code snippets below for examples of using this model for zero-shot classification both with Hugging Face's built-in pipeline and with native Transformers/PyTorch code.\n\n#### With the zero-shot classification pipeline\n\nThe model can be loaded with the `zero-shot-classification` pipeline like so:\n\n```python\nfrom transformers import pipeline\nclassifier = pipeline(\"zero-shot-classification\",\n model=\"facebook/bart-large-mnli\")\n```\n\nYou can then use this pipeline to classify sequences into any of the class names you specify.\n\n```python\nsequence_to_classify = \"one day I will see the world\"\ncandidate_labels = ['travel', 'cooking', 'dancing']\nclassifier(sequence_to_classify, candidate_labels)\n#{'labels': ['travel', 'dancing', 'cooking'],\n# 'scores': [0.9938651323318481, 0.0032737774308770895, 0.002861034357920289],\n# 'sequence': 'one day I will see the world'}\n```\n\nIf more than one candidate label can be correct, pass `multi_label=True` to calculate each class independently:\n\n```python\ncandidate_labels = ['travel', 'cooking', 'dancing', 'exploration']\nclassifier(sequence_to_classify, candidate_labels, multi_label=True)\n#{'labels': ['travel', 'exploration', 'dancing', 'cooking'],\n# 'scores': [0.9945111274719238,\n# 0.9383890628814697,\n# 0.0057061901316046715,\n# 0.0018193122232332826],\n# 'sequence': 'one day I will see the world'}\n```\n\n\n#### With manual PyTorch\n\n```python\n# pose sequence as a NLI premise and label as a hypothesis\nfrom transformers import AutoModelForSequenceClassification, AutoTokenizer\nnli_model = AutoModelForSequenceClassification.from_pretrained('facebook/bart-large-mnli')\ntokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-mnli')\n\npremise = sequence\nhypothesis = f'This example is {label}.'\n\n# run through model pre-trained on MNLI\nx = tokenizer.encode(premise, hypothesis, return_tensors='pt',\n truncation_strategy='only_first')\nlogits = nli_model(x.to(device))[0]\n\n# we throw away \"neutral\" (dim 1) and take the probability of\n# \"entailment\" (2) as the probability of the label being true \nentail_contradiction_logits = logits[:,[0,2]]\nprobs = entail_contradiction_logits.softmax(dim=1)\nprob_label_is_true = probs[:,1]\n```\n\n---\n\nNote: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).\n" |
{"datasets": ["multi_nli"], "library_name": "Transformers PHP", "license": "mit", "pipeline_tag": "zero-shot-classification", "tags": ["onnx"], "thumbnail": "https://huggingface.co/front/thumbnails/facebook.png"}
|
task
|
[
"TEXT_CLASSIFICATION",
"TRANSLATION"
] | 41,559 |
gaudi/opus-mt-es-tn-ctranslate2
|
gaudi
|
translation
|
[
"transformers",
"marian",
"ctranslate2",
"translation",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 2024-07-22T15:47:53Z |
2024-10-19T03:07:46+00:00
| 9 | 0 |
---
license: apache-2.0
tags:
- ctranslate2
- translation
---
# Repository General Information
## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)!
- Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-es-tn)
- This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2).
- This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil).
# What is CTranslate2?
[CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models.
CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.
CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include:
- Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper
- Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon
- Encoder-only models: BERT, DistilBERT, XLM-RoBERTa
The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration.
# CTranslate2 Benchmarks
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset.
The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers.
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings.
## CPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 |
| Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 |
| Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 |
| CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 |
| CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 |
## GPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 |
| Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 |
| CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 |
| CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 |
`Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.`
**Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br />
**Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-es-tn).**
## Internal Benchmarks
Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality.
# CTranslate2 Installation
```bash
pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0
```
### ct2-transformers-converter Command Used:
```bash
ct2-transformers-converter --model Helsinki-NLP/opus-mt-es-tn --output_dir ./ctranslate2/opus-mt-es-tn-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16
```
# CTranslate2 Converted Checkpoint Information:
**Compatible With:**
- [ctranslate2](https://github.com/OpenNMT/CTranslate2)
- [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
**Compute Type:**
- `compute_type=int8_float16` for `device="cuda"`
- `compute_type=int8` for `device="cpu"`
# Sample Code - ctranslate2
#### Clone the repository to the working directory or wherever you wish to store the model artifacts. ####
```bash
git clone https://huggingface.co/gaudi/opus-mt-es-tn-ctranslate2
```
#### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. ####
```python
from ctranslate2 import Translator
import transformers
model_dir = "./opus-mt-es-tn-ctranslate2" # Path to model directory.
translator = Translator(
model_path=model_dir,
device="cuda", # cpu, cuda, or auto.
inter_threads=1, # Maximum number of parallel translations.
intra_threads=4, # Number of OpenMP threads per translator.
compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda.
)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir)
source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX."))
results = translator.translate_batch([source])
target = results[0].hypotheses[0]
print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))
```
# Sample Code - hf-hub-ctranslate2
**Derived From [michaelfeil](https://huggingface.co/michaelfeil):**
```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer
model_name = "gaudi/opus-mt-es-tn-ctranslate2"
model = TranslatorCT2fromHfHub(
model_name_or_path=model_name,
device="cuda",
compute_type="int8_float16",
tokenizer=AutoTokenizer.from_pretrained(model_name)
)
outputs = model.generate(
text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"],
)
print(outputs)
```
# License and other remarks:
License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-es-tn) by Helsinki-NLP.
| null |
Non_BioNLP
|
# Repository General Information
## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)!
- Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-es-tn)
- This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2).
- This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil).
# What is CTranslate2?
[CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models.
CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.
CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include:
- Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper
- Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon
- Encoder-only models: BERT, DistilBERT, XLM-RoBERTa
The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration.
# CTranslate2 Benchmarks
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset.
The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers.
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings.
## CPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 |
| Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 |
| Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 |
| CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 |
| CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 |
## GPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 |
| Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 |
| CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 |
| CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 |
`Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.`
**Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br />
**Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-es-tn).**
## Internal Benchmarks
Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality.
# CTranslate2 Installation
```bash
pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0
```
### ct2-transformers-converter Command Used:
```bash
ct2-transformers-converter --model Helsinki-NLP/opus-mt-es-tn --output_dir ./ctranslate2/opus-mt-es-tn-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16
```
# CTranslate2 Converted Checkpoint Information:
**Compatible With:**
- [ctranslate2](https://github.com/OpenNMT/CTranslate2)
- [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
**Compute Type:**
- `compute_type=int8_float16` for `device="cuda"`
- `compute_type=int8` for `device="cpu"`
# Sample Code - ctranslate2
#### Clone the repository to the working directory or wherever you wish to store the model artifacts. ####
```bash
git clone https://huggingface.co/gaudi/opus-mt-es-tn-ctranslate2
```
#### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. ####
```python
from ctranslate2 import Translator
import transformers
model_dir = "./opus-mt-es-tn-ctranslate2" # Path to model directory.
translator = Translator(
model_path=model_dir,
device="cuda", # cpu, cuda, or auto.
inter_threads=1, # Maximum number of parallel translations.
intra_threads=4, # Number of OpenMP threads per translator.
compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda.
)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir)
source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX."))
results = translator.translate_batch([source])
target = results[0].hypotheses[0]
print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))
```
# Sample Code - hf-hub-ctranslate2
**Derived From [michaelfeil](https://huggingface.co/michaelfeil):**
```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer
model_name = "gaudi/opus-mt-es-tn-ctranslate2"
model = TranslatorCT2fromHfHub(
model_name_or_path=model_name,
device="cuda",
compute_type="int8_float16",
tokenizer=AutoTokenizer.from_pretrained(model_name)
)
outputs = model.generate(
text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"],
)
print(outputs)
```
# License and other remarks:
License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-es-tn) by Helsinki-NLP.
|
{"license": "apache-2.0", "tags": ["ctranslate2", "translation"]}
|
task
|
[
"TRANSLATION"
] | 41,560 |
CYFRAGOVPL/PLLuM-8x7B-nc-instruct
|
CYFRAGOVPL
| null |
[
"safetensors",
"mixtral",
"pl",
"license:cc-by-nc-4.0",
"region:us"
] | 2025-02-06T23:52:08Z |
2025-03-11T14:12:40+00:00
| 264 | 3 |
---
language:
- pl
license: cc-by-nc-4.0
---
<p align="center">
<img src="https://pllum.org.pl/_nuxt/PLLuM_logo_RGB_color.DXNEc-VR.png">
</p>
# PLLuM: A Family of Polish Large Language Models
## Overview
PLLuM is a family of large language models (LLMs) specialized in Polish and other Slavic/Baltic languages, with additional English data incorporated for broader generalization. Developed through an extensive collaboration with various data providers, PLLuM models are built on high-quality text corpora and refined through instruction tuning, preference learning, and advanced alignment techniques. These models are intended to generate contextually coherent text, offer assistance in various tasks (e.g., question answering, summarization), and serve as a foundation for specialized applications such as domain-specific intelligent assistants.
### Key Highlights
- **Extensive Data Collection**
We gathered large-scale, high-quality text data in Polish (around 150B tokens after cleaning and deduplication) and additional text in Slavic, Baltic, and English languages. Part of these tokens (28B) can be used in fully open-source models, including for commercial use (in compliance with relevant legal regulations).
- **Organic Instruction Dataset**
We curated the largest Polish collection of manually created “organic instructions” (~40k prompt-response pairs, including ~3.5k multi-turn dialogs). This human-authored instruction set is based on an extensive typology of human-model interactions and it covers a range of subtle aspects of supervised fine-tuning (SFT) that might be overlooked with automated approaches (including large scale distillation of 'strong LLMs'). It was also designed to mitigate negative linguistic transfer from non-Polish textual data used in the pre-training phase.
- **Polish Preference Corpus**
We created the first Polish-language preference corpus, featuring prompts and multiple model responses manually assessed by a demographically diverse team of annotators. This dataset teaches the model not only correctness (factual and linguistic) but also balance and safety—especially for potentially controversial or adversarial topics.
- **Evaluation Benchmarks**
We developed custom benchmarks to evaluate our models on tasks relevant to Polish public administration, where PLLuM achieved top scores among all tested models. In broader Polish-language tasks, PLLuM models also attain state-of-the-art results.
## Model Description
Below is a summary of the main PLLuM models, including their licenses, bases, and parameter sizes. All model names link to a specific Hugging Face resources, while the base models and licenses link to their respective sources or license references. Note that all *-nc-* models are intended to non-commercial use.
The models with fully open licenses are continuously pretrained on approximately 30 billion tokens of Polish text due to copyright considerations. The models with CC-BY-NC-4.0 licenses used approximately 150 billion tokens of Polish text. The models with the -nc and -chat suffix were aligned on human preferences and are generally safer and more efficient to use in dialog, general purpose scenarios.
| Model Name | Params | License | Based On |
|-------------------------------------------------------|----------------------|---------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|
| [Llama-PLLuM-8B-base](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-base) | 8B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE) | [Llama3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) |
| [Llama-PLLuM-8B-instruct](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-instruct) | 8B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE) | [Llama3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) |
| [Llama-PLLuM-8B-chat](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-chat) | 8B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE) | [Llama3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) |
| [PLLuM-12B-base](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-base) | 12B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-instruct](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-instruct) | 12B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-chat](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-chat) | 12B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-nc-base](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-nc-base) | 12B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-nc-instruct](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-nc-instruct) | 12B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-nc-chat](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-nc-chat) | 12B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-8x7B-base](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-base) | 8×7B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-instruct](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-instruct) | 8×7B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-chat](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-chat) | 8×7B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-nc-base](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-nc-base) | 8×7B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-nc-instruct](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-nc-instruct) | 8×7B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-nc-chat](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-nc-chat) | 8×7B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [Llama-PLLuM-70B-base](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-base) | 70B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-70B/blob/main/LICENSE) | [Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) |
| [Llama-PLLuM-70B-instruct](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-instruct) | 70B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-70B/blob/main/LICENSE) | [Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) |
| [Llama-PLLuM-70B-chat](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-chat) | 70B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-70B/blob/main/LICENSE) | [Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) |
### Model Development
- **Pretraining**: All models were pretrained or continued-pretrained on large-scale Polish corpora (up to 150B tokens) plus a range of additional Slavic/Baltic and English texts.
- **Instruction Fine-Tuning**: We refined the models on manually curated Polish “organic instructions” (approx. 40k), converted instructions from premium Polish corpora (approx. 50k), and synthetic instructions generated by strong LLMs (approx. 10k).
- **Alignment and Preference Learning**: Manually annotated preference data taught the models to produce safer, balanced, and contextually appropriate responses, even in adversarial or sensitive cases.
- **Domain-Specific Adaptations**: Specialized RAG-based (Retrieval Augmented Generation) models were developed for tasks like public administration, demonstrating strong performance in complex information retrieval and question answering.
## Intended Use Cases
- **General Language Tasks**: Text generation, summarization, question answering, etc.
- **Domain-Specific Assistants**: Especially effective for Polish public administration and legal or bureaucratic topics where domain-aware retrieval is required.
- **Research & Development**: Building blocks for downstream AI applications in academic or industrial settings, where a strong command of the Polish language is essential.
## How to Use
Each PLLuM model can be loaded via the Hugging Face Transformers library (or compatible frameworks). For RAG-based scenarios, pair the model with a relevant vector store or document retrieval system.
Below are some recommended steps and code snippets:
### 1. Installation
Make sure you have the latest versions of `transformers` and `torch` (or another compatible deep learning framework) installed:
```bash
pip install transformers accelerate torch
```
### 2. Loading the Model
Use the following example to load one of the PLLuM models:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "CYFRAGOVPL/PLLuM-12B-chat" # Replace with the PLLuM model name of your choice
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
```
### 3. Using bfloat16 (BF16)
If your hardware (e.g., newer GPUs) supports bfloat16, you can reduce memory usage and potentially speed up inference:
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "CYFRAGOVPL/PLLuM-12B-chat"
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Load model in bfloat16 precision
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto" # automatically places model layers on available devices
)
```
### 4. Generating an Example Text
```python
prompt = "Napisz krótki wiersz o wiośnie." # EN:"Write a short poem about spring."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=50,
do_sample=True,
top_k=50,
top_p=0.9,
temperature=0.7
)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)
```
### 5. Expected Output
Below is a sample (hypothetical) output for the prompt above:
```css
Przykładowy wiersz o tematyce wiosennej:
Wiosna, wiosna, wiosna, ach to ty!
Kwiecień plecień wciąż przeplata,
trochę zimy, trochę lata.
A ja nie mogę się już doczekać,
kiedy w kalendarzu ujrzę maj.
Wtedy wszystko wkoło rozkwita,
a ptaki tak pięknie śpiewają.
Wiosno, wiosno, czekam z utęsknieniem,
zrób mi tę przyjemność i przyjdź wreszcie, proszę!
```
Your results may vary depending on model parameters (e.g., temperature, top_k, top_p), hardware, and other settings.
### 6. Retrieval Augmented Generation (RAG)
Our Llama-PLLuM models (both chat and instruct versions) were additionally trained to perform well in Retrieval Augmented Generation (RAG) setting. The prompt is in .jinja format, where docs is a list of document texts and question is a query that should be answered based on the provided documents. If there is no answer in the provided documents model generates "Nie udało mi się odnaleźć odpowiedzi na pytanie".
Prompt:
```
Numerowana lista dokumentów jest poniżej:
---------------------
<results>{% for doc in docs %}
Dokument: {{ loop.index0 }}
{{ doc }}
{% endfor %}</results>
---------------------
Odpowiedz na pytanie użytkownika wykorzystując tylko informacje znajdujące się w dokumentach, a nie wcześniejszą wiedzę.
Udziel wysokiej jakości, poprawnej gramatycznie odpowiedzi w języku polskim. Odpowiedź powinna zawierać cytowania do dokumentów, z których pochodzą informacje. Zacytuj dokument za pomocą symbolu [nr_dokumentu] powołując się na fragment np. [0] dla fragmentu z dokumentu 0. Jeżeli w dokumentach nie ma informacji potrzebnych do odpowiedzi na pytanie, zamiast odpowiedzi zwróć tekst: "Nie udało mi się odnaleźć odpowiedzi na pytanie".
Pytanie: {{ question }}
```
## Training Procedure
- **Datasets**: ~150B tokens from Polish and multilingual sources, with ~28B tokens available for fully open-source commercial use.
- **Hyperparameters**: Vary based on model size, typically including Adam or AdamW optimizers, a range of batch sizes, and carefully tuned learning rates.
- **Hardware & Duration**: Training using [Bem2](https://man.e-science.pl/pl/kdm/bem2) HPC (up to 300xH100 GPUs). Each model’s training time depends on parameter size and hardware configuration (~8 to ~25 days on multi-GPU cluster for 8B–70B sizes).
## Evaluation and Benchmarks
- **Public Administration**: PLLuM models demonstrated top-tier performance in specialized tasks relevant to government services.
- **Polish Language Tasks**: Across a variety of internal benchmarks and standard corpora, PLLuM consistently outperforms other models in accuracy, coherence, and safety metrics.
- **Custom Tests**: A unique preference corpus and alignment tests ensure robust, safe, and contextually accurate responses.
## Limitations and Bias
- **Potential Hallucinations**: Like other LLMs, PLLuM may occasionally produce factually incorrect or fabricated content.
- **Sensitivity & Bias**: While extensive preference learning has been done, biases might still emerge, especially in controversial or subjective topics.
- **Context Length**: Very long context tasks may challenge certain models, depending on memory constraints.
## Ethical Considerations
PLLuM models are designed for constructive and responsible usage. Users should exercise caution when deploying them in production scenarios, especially for sensitive or regulated domains. Despite efforts to minimize harmful outputs, there is always a risk of generating offensive, biased, or inappropriate text. Human oversight and due diligence are advised.
## Citation
If you use PLLuM models or any part of this repository in your research or deployment, please cite as follows (BibTeX):
```
@unpublished{pllum2025,
title={PLLuM: A Family of Polish Large Language Models},
author={PLLuM Consortium},
year={2025}
}
```
## License
Different models within the PLLuM family are published under various licenses (Apache 2.0, CC-BY-NC-4.0, or Llama 3.1 license). Check each model’s entry in the table above for details.
## Creators & Consortium
The PLLuM project is a unique collaboration between leading Polish scientific institutions and experts from various fields, working together to create a groundbreaking Polish language model. This research partnership combines diverse competencies and passions, forming a robust foundation for advancing AI in Poland.
<table style="border: none; border-collapse: collapse;">
<tr>
<td align="center" valign="middle" style="border: none;">
<a href="https://pwr.edu.pl/">
<img src="https://pllum.org.pl/_nuxt/pwr.D1_x0B58.png" alt="pwr.D1_x0B58.png" width="100">
</a>
<br><strong>Politechnika Wrocławska</strong><br><em>– Project Leader</em>
</td>
<td align="center" valign="middle" style="border: none;">
<a href="https://www.nask.pl/">
<img src="https://pllum.org.pl/_nuxt/nask.Bz8rmSzR.png" alt="nask.Bz8rmSzR.png" width="100">
</a>
<br><strong>NASK PIB</strong>
</td>
<td align="center" valign="middle" style="border: none;">
<a href="https://www.ipipan.waw.pl/">
<img src="https://clarin.biz/_nuxt/img/ipipan.294d39c.png" alt="ipipan.294d39c.png" width="100">
</a>
<br><strong>Instytut Podstaw Informatyki PAN</strong>
</td>
</tr>
<tr>
<td align="center" valign="middle" style="border: none;">
<a href="https://opi.org.pl/">
<img src="https://pllum.org.pl/_nuxt/opi.CF-COwcC.png" alt="opi.CF-COwcC.png" width="100">
</a>
<br><strong>Ośrodek Przetwarzania Informacji PIB</strong>
</td>
<td align="center" valign="middle" style="border: none;">
<a href="https://www.uni.lodz.pl/">
<img src="https://pllum.org.pl/_nuxt/ul.aTSgr_W6.png" alt="ul.aTSgr_W6.png" width="100">
</a>
<br><strong>Uniwersytet Łódzki</strong>
</td>
<td align="center" valign="middle" style="border: none;">
<a href="https://ispan.waw.pl/default/">
<img src="https://pllum.org.pl/_nuxt/is.Dqb94VRb.png" alt="is.Dqb94VRb.png" width="100">
</a>
<br><strong>Instytut Slawistyki PAN</strong>
</td>
</tr>
</table>
## Contact and Support
For questions or contributions, please reach out via: <[email protected]>
We welcome feedback, collaboration, and further exploration of PLLuM models!
## Acknowledgements
Project financed by the Minister of Digital Affairs under the targeted subsidy No. 1/WI/DBiI/2023: *“Responsible development of the open large language model PLLuM (Polish Large Language Model) to support breakthrough technologies in the public and economic sector, including an open, Polish-language intelligent assistant for petitioners.”*
**Funding Amount:** 14,504,392.00 PLN
**Contract Signing Date:** 2024-01-22
| null |
Non_BioNLP
|
<p align="center">
<img src="https://pllum.org.pl/_nuxt/PLLuM_logo_RGB_color.DXNEc-VR.png">
</p>
# PLLuM: A Family of Polish Large Language Models
## Overview
PLLuM is a family of large language models (LLMs) specialized in Polish and other Slavic/Baltic languages, with additional English data incorporated for broader generalization. Developed through an extensive collaboration with various data providers, PLLuM models are built on high-quality text corpora and refined through instruction tuning, preference learning, and advanced alignment techniques. These models are intended to generate contextually coherent text, offer assistance in various tasks (e.g., question answering, summarization), and serve as a foundation for specialized applications such as domain-specific intelligent assistants.
### Key Highlights
- **Extensive Data Collection**
We gathered large-scale, high-quality text data in Polish (around 150B tokens after cleaning and deduplication) and additional text in Slavic, Baltic, and English languages. Part of these tokens (28B) can be used in fully open-source models, including for commercial use (in compliance with relevant legal regulations).
- **Organic Instruction Dataset**
We curated the largest Polish collection of manually created “organic instructions” (~40k prompt-response pairs, including ~3.5k multi-turn dialogs). This human-authored instruction set is based on an extensive typology of human-model interactions and it covers a range of subtle aspects of supervised fine-tuning (SFT) that might be overlooked with automated approaches (including large scale distillation of 'strong LLMs'). It was also designed to mitigate negative linguistic transfer from non-Polish textual data used in the pre-training phase.
- **Polish Preference Corpus**
We created the first Polish-language preference corpus, featuring prompts and multiple model responses manually assessed by a demographically diverse team of annotators. This dataset teaches the model not only correctness (factual and linguistic) but also balance and safety—especially for potentially controversial or adversarial topics.
- **Evaluation Benchmarks**
We developed custom benchmarks to evaluate our models on tasks relevant to Polish public administration, where PLLuM achieved top scores among all tested models. In broader Polish-language tasks, PLLuM models also attain state-of-the-art results.
## Model Description
Below is a summary of the main PLLuM models, including their licenses, bases, and parameter sizes. All model names link to a specific Hugging Face resources, while the base models and licenses link to their respective sources or license references. Note that all *-nc-* models are intended to non-commercial use.
The models with fully open licenses are continuously pretrained on approximately 30 billion tokens of Polish text due to copyright considerations. The models with CC-BY-NC-4.0 licenses used approximately 150 billion tokens of Polish text. The models with the -nc and -chat suffix were aligned on human preferences and are generally safer and more efficient to use in dialog, general purpose scenarios.
| Model Name | Params | License | Based On |
|-------------------------------------------------------|----------------------|---------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|
| [Llama-PLLuM-8B-base](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-base) | 8B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE) | [Llama3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) |
| [Llama-PLLuM-8B-instruct](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-instruct) | 8B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE) | [Llama3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) |
| [Llama-PLLuM-8B-chat](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-chat) | 8B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE) | [Llama3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) |
| [PLLuM-12B-base](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-base) | 12B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-instruct](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-instruct) | 12B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-chat](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-chat) | 12B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-nc-base](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-nc-base) | 12B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-nc-instruct](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-nc-instruct) | 12B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-12B-nc-chat](https://huggingface.co/CYFRAGOVPL/PLLuM-12B-nc-chat) | 12B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
| [PLLuM-8x7B-base](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-base) | 8×7B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-instruct](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-instruct) | 8×7B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-chat](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-chat) | 8×7B | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-nc-base](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-nc-base) | 8×7B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-nc-instruct](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-nc-instruct) | 8×7B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [PLLuM-8x7B-nc-chat](https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-nc-chat) | 8×7B | [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) | [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) |
| [Llama-PLLuM-70B-base](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-base) | 70B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-70B/blob/main/LICENSE) | [Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) |
| [Llama-PLLuM-70B-instruct](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-instruct) | 70B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-70B/blob/main/LICENSE) | [Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) |
| [Llama-PLLuM-70B-chat](https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-chat) | 70B | [Llama 3.1](https://huggingface.co/meta-llama/Llama-3.1-70B/blob/main/LICENSE) | [Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) |
### Model Development
- **Pretraining**: All models were pretrained or continued-pretrained on large-scale Polish corpora (up to 150B tokens) plus a range of additional Slavic/Baltic and English texts.
- **Instruction Fine-Tuning**: We refined the models on manually curated Polish “organic instructions” (approx. 40k), converted instructions from premium Polish corpora (approx. 50k), and synthetic instructions generated by strong LLMs (approx. 10k).
- **Alignment and Preference Learning**: Manually annotated preference data taught the models to produce safer, balanced, and contextually appropriate responses, even in adversarial or sensitive cases.
- **Domain-Specific Adaptations**: Specialized RAG-based (Retrieval Augmented Generation) models were developed for tasks like public administration, demonstrating strong performance in complex information retrieval and question answering.
## Intended Use Cases
- **General Language Tasks**: Text generation, summarization, question answering, etc.
- **Domain-Specific Assistants**: Especially effective for Polish public administration and legal or bureaucratic topics where domain-aware retrieval is required.
- **Research & Development**: Building blocks for downstream AI applications in academic or industrial settings, where a strong command of the Polish language is essential.
## How to Use
Each PLLuM model can be loaded via the Hugging Face Transformers library (or compatible frameworks). For RAG-based scenarios, pair the model with a relevant vector store or document retrieval system.
Below are some recommended steps and code snippets:
### 1. Installation
Make sure you have the latest versions of `transformers` and `torch` (or another compatible deep learning framework) installed:
```bash
pip install transformers accelerate torch
```
### 2. Loading the Model
Use the following example to load one of the PLLuM models:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "CYFRAGOVPL/PLLuM-12B-chat" # Replace with the PLLuM model name of your choice
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
```
### 3. Using bfloat16 (BF16)
If your hardware (e.g., newer GPUs) supports bfloat16, you can reduce memory usage and potentially speed up inference:
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "CYFRAGOVPL/PLLuM-12B-chat"
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Load model in bfloat16 precision
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto" # automatically places model layers on available devices
)
```
### 4. Generating an Example Text
```python
prompt = "Napisz krótki wiersz o wiośnie." # EN:"Write a short poem about spring."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=50,
do_sample=True,
top_k=50,
top_p=0.9,
temperature=0.7
)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)
```
### 5. Expected Output
Below is a sample (hypothetical) output for the prompt above:
```css
Przykładowy wiersz o tematyce wiosennej:
Wiosna, wiosna, wiosna, ach to ty!
Kwiecień plecień wciąż przeplata,
trochę zimy, trochę lata.
A ja nie mogę się już doczekać,
kiedy w kalendarzu ujrzę maj.
Wtedy wszystko wkoło rozkwita,
a ptaki tak pięknie śpiewają.
Wiosno, wiosno, czekam z utęsknieniem,
zrób mi tę przyjemność i przyjdź wreszcie, proszę!
```
Your results may vary depending on model parameters (e.g., temperature, top_k, top_p), hardware, and other settings.
### 6. Retrieval Augmented Generation (RAG)
Our Llama-PLLuM models (both chat and instruct versions) were additionally trained to perform well in Retrieval Augmented Generation (RAG) setting. The prompt is in .jinja format, where docs is a list of document texts and question is a query that should be answered based on the provided documents. If there is no answer in the provided documents model generates "Nie udało mi się odnaleźć odpowiedzi na pytanie".
Prompt:
```
Numerowana lista dokumentów jest poniżej:
---------------------
<results>{% for doc in docs %}
Dokument: {{ loop.index0 }}
{{ doc }}
{% endfor %}</results>
---------------------
Odpowiedz na pytanie użytkownika wykorzystując tylko informacje znajdujące się w dokumentach, a nie wcześniejszą wiedzę.
Udziel wysokiej jakości, poprawnej gramatycznie odpowiedzi w języku polskim. Odpowiedź powinna zawierać cytowania do dokumentów, z których pochodzą informacje. Zacytuj dokument za pomocą symbolu [nr_dokumentu] powołując się na fragment np. [0] dla fragmentu z dokumentu 0. Jeżeli w dokumentach nie ma informacji potrzebnych do odpowiedzi na pytanie, zamiast odpowiedzi zwróć tekst: "Nie udało mi się odnaleźć odpowiedzi na pytanie".
Pytanie: {{ question }}
```
## Training Procedure
- **Datasets**: ~150B tokens from Polish and multilingual sources, with ~28B tokens available for fully open-source commercial use.
- **Hyperparameters**: Vary based on model size, typically including Adam or AdamW optimizers, a range of batch sizes, and carefully tuned learning rates.
- **Hardware & Duration**: Training using [Bem2](https://man.e-science.pl/pl/kdm/bem2) HPC (up to 300xH100 GPUs). Each model’s training time depends on parameter size and hardware configuration (~8 to ~25 days on multi-GPU cluster for 8B–70B sizes).
## Evaluation and Benchmarks
- **Public Administration**: PLLuM models demonstrated top-tier performance in specialized tasks relevant to government services.
- **Polish Language Tasks**: Across a variety of internal benchmarks and standard corpora, PLLuM consistently outperforms other models in accuracy, coherence, and safety metrics.
- **Custom Tests**: A unique preference corpus and alignment tests ensure robust, safe, and contextually accurate responses.
## Limitations and Bias
- **Potential Hallucinations**: Like other LLMs, PLLuM may occasionally produce factually incorrect or fabricated content.
- **Sensitivity & Bias**: While extensive preference learning has been done, biases might still emerge, especially in controversial or subjective topics.
- **Context Length**: Very long context tasks may challenge certain models, depending on memory constraints.
## Ethical Considerations
PLLuM models are designed for constructive and responsible usage. Users should exercise caution when deploying them in production scenarios, especially for sensitive or regulated domains. Despite efforts to minimize harmful outputs, there is always a risk of generating offensive, biased, or inappropriate text. Human oversight and due diligence are advised.
## Citation
If you use PLLuM models or any part of this repository in your research or deployment, please cite as follows (BibTeX):
```
@unpublished{pllum2025,
title={PLLuM: A Family of Polish Large Language Models},
author={PLLuM Consortium},
year={2025}
}
```
## License
Different models within the PLLuM family are published under various licenses (Apache 2.0, CC-BY-NC-4.0, or Llama 3.1 license). Check each model’s entry in the table above for details.
## Creators & Consortium
The PLLuM project is a unique collaboration between leading Polish scientific institutions and experts from various fields, working together to create a groundbreaking Polish language model. This research partnership combines diverse competencies and passions, forming a robust foundation for advancing AI in Poland.
<table style="border: none; border-collapse: collapse;">
<tr>
<td align="center" valign="middle" style="border: none;">
<a href="https://pwr.edu.pl/">
<img src="https://pllum.org.pl/_nuxt/pwr.D1_x0B58.png" alt="pwr.D1_x0B58.png" width="100">
</a>
<br><strong>Politechnika Wrocławska</strong><br><em>– Project Leader</em>
</td>
<td align="center" valign="middle" style="border: none;">
<a href="https://www.nask.pl/">
<img src="https://pllum.org.pl/_nuxt/nask.Bz8rmSzR.png" alt="nask.Bz8rmSzR.png" width="100">
</a>
<br><strong>NASK PIB</strong>
</td>
<td align="center" valign="middle" style="border: none;">
<a href="https://www.ipipan.waw.pl/">
<img src="https://clarin.biz/_nuxt/img/ipipan.294d39c.png" alt="ipipan.294d39c.png" width="100">
</a>
<br><strong>Instytut Podstaw Informatyki PAN</strong>
</td>
</tr>
<tr>
<td align="center" valign="middle" style="border: none;">
<a href="https://opi.org.pl/">
<img src="https://pllum.org.pl/_nuxt/opi.CF-COwcC.png" alt="opi.CF-COwcC.png" width="100">
</a>
<br><strong>Ośrodek Przetwarzania Informacji PIB</strong>
</td>
<td align="center" valign="middle" style="border: none;">
<a href="https://www.uni.lodz.pl/">
<img src="https://pllum.org.pl/_nuxt/ul.aTSgr_W6.png" alt="ul.aTSgr_W6.png" width="100">
</a>
<br><strong>Uniwersytet Łódzki</strong>
</td>
<td align="center" valign="middle" style="border: none;">
<a href="https://ispan.waw.pl/default/">
<img src="https://pllum.org.pl/_nuxt/is.Dqb94VRb.png" alt="is.Dqb94VRb.png" width="100">
</a>
<br><strong>Instytut Slawistyki PAN</strong>
</td>
</tr>
</table>
## Contact and Support
For questions or contributions, please reach out via: <[email protected]>
We welcome feedback, collaboration, and further exploration of PLLuM models!
## Acknowledgements
Project financed by the Minister of Digital Affairs under the targeted subsidy No. 1/WI/DBiI/2023: *“Responsible development of the open large language model PLLuM (Polish Large Language Model) to support breakthrough technologies in the public and economic sector, including an open, Polish-language intelligent assistant for petitioners.”*
**Funding Amount:** 14,504,392.00 PLN
**Contract Signing Date:** 2024-01-22
|
{"language": ["pl"], "license": "cc-by-nc-4.0"}
|
task
|
[
"QUESTION_ANSWERING",
"SUMMARIZATION"
] | 41,561 |
fathyshalab/domain_transfer_clinic_credit_cards-massive_social-roberta-large-v1-1-5
|
fathyshalab
|
text-classification
|
[
"sentence-transformers",
"pytorch",
"roberta",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 2023-02-12T10:30:48Z |
2023-02-12T10:31:10+00:00
| 9 | 0 |
---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# fathyshalab/domain_transfer_clinic_credit_cards-massive_social-roberta-large-v1-1-5
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("fathyshalab/domain_transfer_clinic_credit_cards-massive_social-roberta-large-v1-1-5")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
| null |
Non_BioNLP
|
# fathyshalab/domain_transfer_clinic_credit_cards-massive_social-roberta-large-v1-1-5
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("fathyshalab/domain_transfer_clinic_credit_cards-massive_social-roberta-large-v1-1-5")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
{"license": "apache-2.0", "pipeline_tag": "text-classification", "tags": ["setfit", "sentence-transformers", "text-classification"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,562 |
aijunzi/distilbert-base-uncased-finetuned-emotion
|
aijunzi
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-02-20T01:41:39Z |
2024-04-14T23:54:11+00:00
| 15 | 0 |
---
datasets:
- emotion
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.923
name: Accuracy
- type: f1
value: 0.9229406051096526
name: F1
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2196
- Accuracy: 0.923
- F1: 0.9229
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 250 | 0.3262 | 0.9035 | 0.8997 |
| No log | 2.0 | 500 | 0.2196 | 0.923 | 0.9229 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.2
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2196
- Accuracy: 0.923
- F1: 0.9229
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 250 | 0.3262 | 0.9035 | 0.8997 |
| No log | 2.0 | 500 | 0.2196 | 0.923 | 0.9229 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.2
|
{"datasets": ["emotion"], "license": "apache-2.0", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetuned-emotion", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.923, "name": "Accuracy"}, {"type": "f1", "value": 0.9229406051096526, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,563 |
TheBloke/bagel-8x7b-v0.2-GPTQ
|
TheBloke
|
text-generation
|
[
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"dataset:ai2_arc",
"dataset:jondurbin/airoboros-3.2",
"dataset:codeparrot/apps",
"dataset:facebook/belebele",
"dataset:boolq",
"dataset:jondurbin/cinematika-v0.1",
"dataset:drop",
"dataset:lmsys/lmsys-chat-1m",
"dataset:TIGER-Lab/MathInstruct",
"dataset:cais/mmlu",
"dataset:Muennighoff/natural-instructions",
"dataset:openbookqa",
"dataset:piqa",
"dataset:Vezora/Tested-22k-Python-Alpaca",
"dataset:cakiki/rosetta-code",
"dataset:Open-Orca/SlimOrca",
"dataset:spider",
"dataset:squad_v2",
"dataset:migtissera/Synthia-v1.3",
"dataset:datasets/winogrande",
"dataset:nvidia/HelpSteer",
"dataset:Intel/orca_dpo_pairs",
"dataset:unalignment/toxic-dpo-v0.1",
"dataset:jondurbin/truthy-dpo-v0.1",
"dataset:allenai/ultrafeedback_binarized_cleaned",
"dataset:Squish42/bluemoon-fandom-1-1-rp-cleaned",
"dataset:LDJnr/Capybara",
"dataset:JULIELab/EmoBank",
"dataset:kingbri/PIPPA-shareGPT",
"base_model:jondurbin/bagel-8x7b-v0.2",
"base_model:quantized:jondurbin/bagel-8x7b-v0.2",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | 2024-01-06T20:27:52Z |
2024-01-06T22:25:26+00:00
| 22 | 3 |
---
base_model: jondurbin/bagel-8x7b-v0.2
datasets:
- ai2_arc
- jondurbin/airoboros-3.2
- codeparrot/apps
- facebook/belebele
- boolq
- jondurbin/cinematika-v0.1
- drop
- lmsys/lmsys-chat-1m
- TIGER-Lab/MathInstruct
- cais/mmlu
- Muennighoff/natural-instructions
- openbookqa
- piqa
- Vezora/Tested-22k-Python-Alpaca
- cakiki/rosetta-code
- Open-Orca/SlimOrca
- spider
- squad_v2
- migtissera/Synthia-v1.3
- datasets/winogrande
- nvidia/HelpSteer
- Intel/orca_dpo_pairs
- unalignment/toxic-dpo-v0.1
- jondurbin/truthy-dpo-v0.1
- allenai/ultrafeedback_binarized_cleaned
- Squish42/bluemoon-fandom-1-1-rp-cleaned
- LDJnr/Capybara
- JULIELab/EmoBank
- kingbri/PIPPA-shareGPT
license: apache-2.0
model_name: Bagel 8X7B v0.2
inference: false
model_creator: Jon Durbin
model_type: mixtral
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
---
<!-- 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 -->
# Bagel 8X7B v0.2 - GPTQ
- Model creator: [Jon Durbin](https://huggingface.co/jondurbin)
- Original model: [Bagel 8X7B v0.2](https://huggingface.co/jondurbin/bagel-8x7b-v0.2)
<!-- description start -->
# Description
This repo contains GPTQ model files for [Jon Durbin's Bagel 8X7B v0.2](https://huggingface.co/jondurbin/bagel-8x7b-v0.2).
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.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GGUF)
* [Jon Durbin's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/bagel-8x7b-v0.2)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.
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/bagel-8x7b-v0.2-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 23.81 GB | No | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 24.70 GB | No | 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/bagel-8x7b-v0.2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 27.42 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 18.01 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 18.85 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 47.04 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 48.10 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher 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/bagel-8x7b-v0.2-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/bagel-8x7b-v0.2-GPTQ:gptq-4bit-128g-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 `bagel-8x7b-v0.2-GPTQ`:
```shell
mkdir bagel-8x7b-v0.2-GPTQ
huggingface-cli download TheBloke/bagel-8x7b-v0.2-GPTQ --local-dir bagel-8x7b-v0.2-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir bagel-8x7b-v0.2-GPTQ
huggingface-cli download TheBloke/bagel-8x7b-v0.2-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir bagel-8x7b-v0.2-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 bagel-8x7b-v0.2-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/bagel-8x7b-v0.2-GPTQ --local-dir bagel-8x7b-v0.2-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-128g-actorder_True https://huggingface.co/TheBloke/bagel-8x7b-v0.2-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/bagel-8x7b-v0.2-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/bagel-8x7b-v0.2-GPTQ:gptq-4bit-128g-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: `bagel-8x7b-v0.2-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/bagel-8x7b-v0.2-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'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(
prompt_template,
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/bagel-8x7b-v0.2-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-128g-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 = "Write a story about llamas"
system_message = "You are a story writing assistant"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
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 architecture models (including Mistral, Yi, DeepSeek, SOLAR, etc) 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**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Jon Durbin's Bagel 8X7B v0.2
# A bagel, with everything (except DPO)
## Overview
An experimental fine-tune of [mixtral-8x7b-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) using [bagel](https://github.com/jondurbin/bagel)
This is the model after the SFT phase, before DPO has been applied.
Hardware kindly provided by [Massed Compute](https://massedcompute.com/?utm_source=huggingface&utm_creative_format=model_card&utm_content=creator_jon)
### Data sources
*Yes, you will see benchmark names in the list, but this only uses the train splits, and a decontamination by cosine similarity is performed at the end as a sanity check*
- [ai2_arc](https://huggingface.co/datasets/ai2_arc)
- Abstraction and reasoning dataset, useful in measuring "intelligence" to a certain extent.
- [airoboros](https://huggingface.co/datasets/unalignment/spicy-3.1)
- Variety of categories of synthetic instructions generated by gpt-4.
- [apps](https://huggingface.co/datasets/codeparrot/apps)
- Python coding dataset with 10k problems.
- [belebele](https://huggingface.co/datasets/facebook/belebele)
- Multi-lingual reading comprehension dataset.
- [bluemoon](https://huggingface.co/datasets/Squish42/bluemoon-fandom-1-1-rp-cleaned)
- Roleplay data scraped from Bluemoon, then cleaned and formatted as ShareGPT.
- [boolq](https://huggingface.co/datasets/boolq)
- Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?)
- [capybara](https://huggingface.co/datasets/LDJnr/Capybara)
- Multi-turn dataset used to create the capybara models.
- [cinematika](https://huggingface.co/datasets/jondurbin/cinematika-v0.1) (instruction and plain text)
- RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be.
- [drop](https://huggingface.co/datasets/drop)
- More reading comprehension.
- [emobank](https://github.com/JULIELab/EmoBank)
- Emotion annotations using the Valence-Arousal-Domninance scheme.
- [gutenberg](https://www.gutenberg.org/) (plain text)
- Books/plain text, again to make the model less boring, only a handful of examples supported by [chapterize](https://github.com/JonathanReeve/chapterize)
- [lmsys_chat_1m](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) (only gpt-4 items, also used for DPO)
- Chats collected by the lmsys chat arena, containing a wide variety of chats with various models.
- [mathinstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)
- Composite dataset with a variety of math-related tasks and problem/question formats.
- [mmlu](https://huggingface.co/datasets/cais/mmlu)
- Massive Multitask Language Understanding - a wide variety of questions about various subject matters.
- [natural_instructions](https://huggingface.co/datasets/Muennighoff/natural-instructions)
- Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type)
- [openbookqa](https://huggingface.co/datasets/openbookqa)
- Question answering dataset.
- [pippa](https://huggingface.co/datasets/kingbri/PIPPA-shareGPT)
- Deduped version of [PIPPA](https://huggingface.co/datasets/PygmalionAI/PIPPA) in ShareGPT format.
- [piqa](https://huggingface.co/datasets/piqa)
- Phyiscal interaction question answering.
- [python_alpaca](https://huggingface.co/datasets/Vezora/Tested-22k-Python-Alpaca)
- Python instruction response pairs, validated as functional.
- [rosetta_code](https://huggingface.co/datasets/cakiki/rosetta-code)
- Code problems and solutions in a variety of programming languages taken from rosettacode.org.
- [slimorca](https://huggingface.co/datasets/Open-Orca/SlimOrca)
- Collection of ~500k gpt-4 verified chats from OpenOrca.
- [spider](https://huggingface.co/datasets/spider)
- SQL-targeted dataset.
- [squad_v2](https://huggingface.co/datasets/squad_v2)
- Contextual question answering (RAG).
- [synthia](https://huggingface.co/datasets/migtissera/Synthia-v1.3)
- GPT-4 generated data using advanced prompting from Migel Tissera.
- [winogrande](https://huggingface.co/datasets/winogrande)
- Fill in the blank style prompts.
Only the train splits were used (if a split was provided), and an additional pass of decontamination is performed using approximate nearest neighbor search (via faiss).
## How to easily download and use this model
[Massed Compute](https://massedcompute.com/?utm_source=huggingface&utm_creative_format=model_card&utm_content=creator_jon) has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI.
1) For this model rent the [Jon Durbin 4xA6000](https://shop.massedcompute.com/products/jon-durbin-4x-a6000?utm_source=huggingface&utm_creative_format=model_card&utm_content=creator_jon) Virtual Machine
2) After you start your rental you will receive an email with instructions on how to Login to the VM
3) Once inside the VM, open the terminal and run `conda activate text-generation-inference`
4) Then `cd Desktop/text-generation-inference/`
5) Run `volume=$PWD/data`
6) Run`model=jondurbin/bagel-8x7b-v0.2`
7) `sudo docker run --gpus '"device=0,1,2,3"' --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model`
8) The model will take some time to load...
9) Once loaded the model will be available on port 8080
Sample command within the VM
```
curl 0.0.0.0:8080/generate \
-X POST \
-d '{"inputs":"<|system|>You are a friendly chatbot.\n<|user|>What type of model are you?\n<|assistant|>","parameters":{"do_sample": true, "max_new_tokens": 100, "repetition_penalty": 1.15, "temperature": 0.7, "top_k": 20, "top_p": 0.9, "best_of": 1}}'\
-H 'Content-Type: application/json'
```
You can also access the model from outside the VM
```
curl IP_ADDRESS_PROVIDED_BY_MASSED_COMPUTE_VM:8080/generate \
-X POST \
-d '{"inputs":"<|system|>You are a friendly chatbot.\n<|user|>What type of model are you?\n<|assistant|>","parameters":{"do_sample": true, "max_new_tokens": 100, "repetition_penalty": 1.15, "temperature": 0.7, "top_k": 20, "top_p": 0.9, "best_of": 1}}'\
-H 'Content-Type: application/json
```
For assistance with the VM join the [Massed Compute Discord Server](https://discord.gg/Mj4YMQY3DA)
## Prompt formatting
In sticking with the theme of the bagel, I didn't want to use a single prompt format, so I used 4 - vicuna, llama-2, alpaca, and chat-ml (sorta).
I also didn't want to randomly select a single prompt format for each item (hoping each instruction would generalize more when used in a variety of prompt formats), so each instruction is actually converted into every prompt format.
This means each epoch of our fine-tune is really basically 4 epochs. So, for the fine-tunes, I would recommend only doing 1 epoch (or 0.75 epochs). I am testing with a single epoch using a relatively low learning rate.
### Alpaca (sort of)
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system prompt, if provided}
{instruction}
### Response:
```
The main difference here is that because of the dataset formatting and variety of data sources, it would have been much to tedious to add an `### Input:` block, so the inputs are just in the instruction section.
### Vicuna
```
{system prompt, if provided, randomly defaulting to "A chat between a user and an unbiased, uncensored assistant."}
USER: {instruction}
ASSISTANT:
```
### ChatML (sort of)
I don't really understand the point of having special tokens for `<|im_start|>` and `<|im_end|>`, because in practice they just act as BOS and EOS tokens (but, please correct me if I'm wrong).
So, instead of:
```text
{bos}<|im_start|>{role}
{text}
<|im_end|>{eos}
```
I just changed it to:
```text
{bos}{role}
{text}
{eos}
```
If you *really* want to use `<|im_start|>` and `<|im_end|>`, just update your `tokenizer_config.json` to use `<|im_start|>` instead of `<s>` and `<|im_end|>` instead of `</s>` and when tokenizing. And if you still don't like what I've done to this chat-ml-ish format, feel free to cry into your pillow or fork the code and do a new fine-tune.
### Llama-2 chat
```
[INST] <<SYS>>
{system}
<</SYS>>
{instruction} [/INST]
```
### Default via chat template
The model's `tokenizer_config.json` includes the default chat template (llama-2), so you can simply use the `apply_chat_template` method to build the full prompt.
```
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained('jondurbin/bagel-8x7b-v0.2')
chat = [
{"role": "system", "content": "You are Bob, a friendly AI assistant."},
{"role": "user", "content": "Hello, how are you?"},
{"role": "assistant", "content": "I'm doing great. How can I help you today?"},
{"role": "user", "content": "I'd like to show off how chat templating works!"},
]
print(tokenizer.apply_chat_template(chat, tokenize=False))
```
### Contribute
If you're interested in new functionality/datasets, take a look at [bagel repo](https://github.com/jondurbin/bagel) and either make a PR or open an issue with details.
To help me with the fine-tuning costs (which are extremely expensive for these large combined datasets):
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Guide for certain tasks
#### RA(G)/contextual question answering
The model was trained to ignore what it thinks it knows, and uses the context to answer the questions, when using the format below.
The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a contextual prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
__Use a very low temperature!__
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Fine-tuning information
You can find charts, and the full configuration used to fine-tune this model on [weights and biases](https://wandb.ai/jondurbin/bagel-8x7b-v0.2/runs/agxjjdso?workspace=user-jondurbin)
The model was fine-tuned on an 8x a6000 instance, for 4 days, 15 hours, 6 minutes and 42 seconds.
### Licence and usage restrictions
The base model is mixtral-8x7b-v0.1, which is licensed as apache-2.0 - no issues there.
The fine-tuning data, however, includes several datasets that have data generated at least in part by OpenAI's gpt-4.
I am not a lawyer, so I can't help determine if this is actually commercially viable, but some questions that often come up are:
- Does the OpenAI ToS apply only to the user who created the dataset initially, and not subsequent models?
- If the dataset was released under a permissive license, but actually includes OpenAI generated data, does that ToS supersede the license?
- Does the dataset fall completely under fair use anyways, since the model isn't really capable of reproducing the entire training set verbatim?
Use your best judgement and seek legal advice if you are concerned about the terms. In any case, by using this model, you agree to completely indemnify me.
| null |
Non_BioNLP
|
<!-- 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 -->
# Bagel 8X7B v0.2 - GPTQ
- Model creator: [Jon Durbin](https://huggingface.co/jondurbin)
- Original model: [Bagel 8X7B v0.2](https://huggingface.co/jondurbin/bagel-8x7b-v0.2)
<!-- description start -->
# Description
This repo contains GPTQ model files for [Jon Durbin's Bagel 8X7B v0.2](https://huggingface.co/jondurbin/bagel-8x7b-v0.2).
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.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GGUF)
* [Jon Durbin's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/bagel-8x7b-v0.2)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.
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/bagel-8x7b-v0.2-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 23.81 GB | No | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 24.70 GB | No | 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/bagel-8x7b-v0.2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 27.42 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 18.01 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 18.85 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 47.04 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/bagel-8x7b-v0.2-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 8192 | 48.10 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher 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/bagel-8x7b-v0.2-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/bagel-8x7b-v0.2-GPTQ:gptq-4bit-128g-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 `bagel-8x7b-v0.2-GPTQ`:
```shell
mkdir bagel-8x7b-v0.2-GPTQ
huggingface-cli download TheBloke/bagel-8x7b-v0.2-GPTQ --local-dir bagel-8x7b-v0.2-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir bagel-8x7b-v0.2-GPTQ
huggingface-cli download TheBloke/bagel-8x7b-v0.2-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir bagel-8x7b-v0.2-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 bagel-8x7b-v0.2-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/bagel-8x7b-v0.2-GPTQ --local-dir bagel-8x7b-v0.2-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-128g-actorder_True https://huggingface.co/TheBloke/bagel-8x7b-v0.2-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/bagel-8x7b-v0.2-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/bagel-8x7b-v0.2-GPTQ:gptq-4bit-128g-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: `bagel-8x7b-v0.2-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/bagel-8x7b-v0.2-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'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(
prompt_template,
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/bagel-8x7b-v0.2-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-128g-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 = "Write a story about llamas"
system_message = "You are a story writing assistant"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
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 architecture models (including Mistral, Yi, DeepSeek, SOLAR, etc) 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**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Jon Durbin's Bagel 8X7B v0.2
# A bagel, with everything (except DPO)
## Overview
An experimental fine-tune of [mixtral-8x7b-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) using [bagel](https://github.com/jondurbin/bagel)
This is the model after the SFT phase, before DPO has been applied.
Hardware kindly provided by [Massed Compute](https://massedcompute.com/?utm_source=huggingface&utm_creative_format=model_card&utm_content=creator_jon)
### Data sources
*Yes, you will see benchmark names in the list, but this only uses the train splits, and a decontamination by cosine similarity is performed at the end as a sanity check*
- [ai2_arc](https://huggingface.co/datasets/ai2_arc)
- Abstraction and reasoning dataset, useful in measuring "intelligence" to a certain extent.
- [airoboros](https://huggingface.co/datasets/unalignment/spicy-3.1)
- Variety of categories of synthetic instructions generated by gpt-4.
- [apps](https://huggingface.co/datasets/codeparrot/apps)
- Python coding dataset with 10k problems.
- [belebele](https://huggingface.co/datasets/facebook/belebele)
- Multi-lingual reading comprehension dataset.
- [bluemoon](https://huggingface.co/datasets/Squish42/bluemoon-fandom-1-1-rp-cleaned)
- Roleplay data scraped from Bluemoon, then cleaned and formatted as ShareGPT.
- [boolq](https://huggingface.co/datasets/boolq)
- Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?)
- [capybara](https://huggingface.co/datasets/LDJnr/Capybara)
- Multi-turn dataset used to create the capybara models.
- [cinematika](https://huggingface.co/datasets/jondurbin/cinematika-v0.1) (instruction and plain text)
- RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be.
- [drop](https://huggingface.co/datasets/drop)
- More reading comprehension.
- [emobank](https://github.com/JULIELab/EmoBank)
- Emotion annotations using the Valence-Arousal-Domninance scheme.
- [gutenberg](https://www.gutenberg.org/) (plain text)
- Books/plain text, again to make the model less boring, only a handful of examples supported by [chapterize](https://github.com/JonathanReeve/chapterize)
- [lmsys_chat_1m](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) (only gpt-4 items, also used for DPO)
- Chats collected by the lmsys chat arena, containing a wide variety of chats with various models.
- [mathinstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)
- Composite dataset with a variety of math-related tasks and problem/question formats.
- [mmlu](https://huggingface.co/datasets/cais/mmlu)
- Massive Multitask Language Understanding - a wide variety of questions about various subject matters.
- [natural_instructions](https://huggingface.co/datasets/Muennighoff/natural-instructions)
- Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type)
- [openbookqa](https://huggingface.co/datasets/openbookqa)
- Question answering dataset.
- [pippa](https://huggingface.co/datasets/kingbri/PIPPA-shareGPT)
- Deduped version of [PIPPA](https://huggingface.co/datasets/PygmalionAI/PIPPA) in ShareGPT format.
- [piqa](https://huggingface.co/datasets/piqa)
- Phyiscal interaction question answering.
- [python_alpaca](https://huggingface.co/datasets/Vezora/Tested-22k-Python-Alpaca)
- Python instruction response pairs, validated as functional.
- [rosetta_code](https://huggingface.co/datasets/cakiki/rosetta-code)
- Code problems and solutions in a variety of programming languages taken from rosettacode.org.
- [slimorca](https://huggingface.co/datasets/Open-Orca/SlimOrca)
- Collection of ~500k gpt-4 verified chats from OpenOrca.
- [spider](https://huggingface.co/datasets/spider)
- SQL-targeted dataset.
- [squad_v2](https://huggingface.co/datasets/squad_v2)
- Contextual question answering (RAG).
- [synthia](https://huggingface.co/datasets/migtissera/Synthia-v1.3)
- GPT-4 generated data using advanced prompting from Migel Tissera.
- [winogrande](https://huggingface.co/datasets/winogrande)
- Fill in the blank style prompts.
Only the train splits were used (if a split was provided), and an additional pass of decontamination is performed using approximate nearest neighbor search (via faiss).
## How to easily download and use this model
[Massed Compute](https://massedcompute.com/?utm_source=huggingface&utm_creative_format=model_card&utm_content=creator_jon) has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI.
1) For this model rent the [Jon Durbin 4xA6000](https://shop.massedcompute.com/products/jon-durbin-4x-a6000?utm_source=huggingface&utm_creative_format=model_card&utm_content=creator_jon) Virtual Machine
2) After you start your rental you will receive an email with instructions on how to Login to the VM
3) Once inside the VM, open the terminal and run `conda activate text-generation-inference`
4) Then `cd Desktop/text-generation-inference/`
5) Run `volume=$PWD/data`
6) Run`model=jondurbin/bagel-8x7b-v0.2`
7) `sudo docker run --gpus '"device=0,1,2,3"' --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model`
8) The model will take some time to load...
9) Once loaded the model will be available on port 8080
Sample command within the VM
```
curl 0.0.0.0:8080/generate \
-X POST \
-d '{"inputs":"<|system|>You are a friendly chatbot.\n<|user|>What type of model are you?\n<|assistant|>","parameters":{"do_sample": true, "max_new_tokens": 100, "repetition_penalty": 1.15, "temperature": 0.7, "top_k": 20, "top_p": 0.9, "best_of": 1}}'\
-H 'Content-Type: application/json'
```
You can also access the model from outside the VM
```
curl IP_ADDRESS_PROVIDED_BY_MASSED_COMPUTE_VM:8080/generate \
-X POST \
-d '{"inputs":"<|system|>You are a friendly chatbot.\n<|user|>What type of model are you?\n<|assistant|>","parameters":{"do_sample": true, "max_new_tokens": 100, "repetition_penalty": 1.15, "temperature": 0.7, "top_k": 20, "top_p": 0.9, "best_of": 1}}'\
-H 'Content-Type: application/json
```
For assistance with the VM join the [Massed Compute Discord Server](https://discord.gg/Mj4YMQY3DA)
## Prompt formatting
In sticking with the theme of the bagel, I didn't want to use a single prompt format, so I used 4 - vicuna, llama-2, alpaca, and chat-ml (sorta).
I also didn't want to randomly select a single prompt format for each item (hoping each instruction would generalize more when used in a variety of prompt formats), so each instruction is actually converted into every prompt format.
This means each epoch of our fine-tune is really basically 4 epochs. So, for the fine-tunes, I would recommend only doing 1 epoch (or 0.75 epochs). I am testing with a single epoch using a relatively low learning rate.
### Alpaca (sort of)
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system prompt, if provided}
{instruction}
### Response:
```
The main difference here is that because of the dataset formatting and variety of data sources, it would have been much to tedious to add an `### Input:` block, so the inputs are just in the instruction section.
### Vicuna
```
{system prompt, if provided, randomly defaulting to "A chat between a user and an unbiased, uncensored assistant."}
USER: {instruction}
ASSISTANT:
```
### ChatML (sort of)
I don't really understand the point of having special tokens for `<|im_start|>` and `<|im_end|>`, because in practice they just act as BOS and EOS tokens (but, please correct me if I'm wrong).
So, instead of:
```text
{bos}<|im_start|>{role}
{text}
<|im_end|>{eos}
```
I just changed it to:
```text
{bos}{role}
{text}
{eos}
```
If you *really* want to use `<|im_start|>` and `<|im_end|>`, just update your `tokenizer_config.json` to use `<|im_start|>` instead of `<s>` and `<|im_end|>` instead of `</s>` and when tokenizing. And if you still don't like what I've done to this chat-ml-ish format, feel free to cry into your pillow or fork the code and do a new fine-tune.
### Llama-2 chat
```
[INST] <<SYS>>
{system}
<</SYS>>
{instruction} [/INST]
```
### Default via chat template
The model's `tokenizer_config.json` includes the default chat template (llama-2), so you can simply use the `apply_chat_template` method to build the full prompt.
```
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained('jondurbin/bagel-8x7b-v0.2')
chat = [
{"role": "system", "content": "You are Bob, a friendly AI assistant."},
{"role": "user", "content": "Hello, how are you?"},
{"role": "assistant", "content": "I'm doing great. How can I help you today?"},
{"role": "user", "content": "I'd like to show off how chat templating works!"},
]
print(tokenizer.apply_chat_template(chat, tokenize=False))
```
### Contribute
If you're interested in new functionality/datasets, take a look at [bagel repo](https://github.com/jondurbin/bagel) and either make a PR or open an issue with details.
To help me with the fine-tuning costs (which are extremely expensive for these large combined datasets):
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Guide for certain tasks
#### RA(G)/contextual question answering
The model was trained to ignore what it thinks it knows, and uses the context to answer the questions, when using the format below.
The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a contextual prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
__Use a very low temperature!__
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Fine-tuning information
You can find charts, and the full configuration used to fine-tune this model on [weights and biases](https://wandb.ai/jondurbin/bagel-8x7b-v0.2/runs/agxjjdso?workspace=user-jondurbin)
The model was fine-tuned on an 8x a6000 instance, for 4 days, 15 hours, 6 minutes and 42 seconds.
### Licence and usage restrictions
The base model is mixtral-8x7b-v0.1, which is licensed as apache-2.0 - no issues there.
The fine-tuning data, however, includes several datasets that have data generated at least in part by OpenAI's gpt-4.
I am not a lawyer, so I can't help determine if this is actually commercially viable, but some questions that often come up are:
- Does the OpenAI ToS apply only to the user who created the dataset initially, and not subsequent models?
- If the dataset was released under a permissive license, but actually includes OpenAI generated data, does that ToS supersede the license?
- Does the dataset fall completely under fair use anyways, since the model isn't really capable of reproducing the entire training set verbatim?
Use your best judgement and seek legal advice if you are concerned about the terms. In any case, by using this model, you agree to completely indemnify me.
|
{"base_model": "jondurbin/bagel-8x7b-v0.2", "datasets": ["ai2_arc", "jondurbin/airoboros-3.2", "codeparrot/apps", "facebook/belebele", "boolq", "jondurbin/cinematika-v0.1", "drop", "lmsys/lmsys-chat-1m", "TIGER-Lab/MathInstruct", "cais/mmlu", "Muennighoff/natural-instructions", "openbookqa", "piqa", "Vezora/Tested-22k-Python-Alpaca", "cakiki/rosetta-code", "Open-Orca/SlimOrca", "spider", "squad_v2", "migtissera/Synthia-v1.3", "datasets/winogrande", "nvidia/HelpSteer", "Intel/orca_dpo_pairs", "unalignment/toxic-dpo-v0.1", "jondurbin/truthy-dpo-v0.1", "allenai/ultrafeedback_binarized_cleaned", "Squish42/bluemoon-fandom-1-1-rp-cleaned", "LDJnr/Capybara", "JULIELab/EmoBank", "kingbri/PIPPA-shareGPT"], "license": "apache-2.0", "model_name": "Bagel 8X7B v0.2", "inference": false, "model_creator": "Jon Durbin", "model_type": "mixtral", "prompt_template": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:\n", "quantized_by": "TheBloke"}
|
task
|
[
"QUESTION_ANSWERING",
"SUMMARIZATION"
] | 41,564 |
NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF
|
NousResearch
| null |
[
"gguf",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"merges",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Hermes-2-Pro-Llama-3-8B",
"base_model:quantized:NousResearch/Hermes-2-Pro-Llama-3-8B",
"endpoints_compatible",
"region:us",
"conversational"
] | 2024-05-13T04:36:45Z |
2024-05-14T17:31:19+00:00
| 1,861 | 86 |
---
base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
datasets:
- teknium/OpenHermes-2.5
language:
- en
tags:
- Llama-3
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- synthetic data
- distillation
- function calling
- json mode
- axolotl
- merges
widget:
- example_title: Hermes 2 Pro Llama-3 Instruct Merge
messages:
- role: system
content: You are a sentient, superintelligent artificial general intelligence,
here to teach and assist me.
- role: user
content: Write a short story about Goku discovering kirby has teamed up with Majin
Buu to destroy the world.
model-index:
- name: Hermes-2-Pro-Llama-3-Instruct-8B-Merge
results: []
---
# - Hermes-2 Θ Llama-3 8B
## Model Description
**This is the GGUF version of the Hermes 2 Θ Model. For the FP16 model, [Click Here](https://huggingface.co/NousResearch/Instruct-Hermes-2-Pro-Llama-3-8B)**
Hermes-2 Θ (Theta) is the first experimental merged model released by [Nous Research](https://nousresearch.com/), in collaboration with Charles Goddard at [Arcee](https://www.arcee.ai/), the team behind MergeKit.
Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 Θ, combining the best of both worlds of each model.
## Example Outputs
### Create New Mythos:
### Chat with a Meta-Cognitive Entity
### Ask for a structured JSON output:
# Prompt Format
Hermes 2 Θ uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt 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 Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling. While the system prompt looks complicated, we have created a GitHub repo containing code to easily build these based on real python functions.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5529|± |0.0145|
| | |acc_norm|0.5870|± |0.0144|
|arc_easy | 0|acc |0.8371|± |0.0076|
| | |acc_norm|0.8144|± |0.0080|
|boolq | 1|acc |0.8599|± |0.0061|
|hellaswag | 0|acc |0.6133|± |0.0049|
| | |acc_norm|0.7989|± |0.0040|
|openbookqa | 0|acc |0.3940|± |0.0219|
| | |acc_norm|0.4680|± |0.0223|
|piqa | 0|acc |0.8063|± |0.0092|
| | |acc_norm|0.8156|± |0.0090|
|winogrande | 0|acc |0.7372|± |0.0124|
```
Average: 72.59
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2441|± |0.0270|
| | |acc_norm|0.2441|± |0.0270|
|agieval_logiqa_en | 0|acc |0.3687|± |0.0189|
| | |acc_norm|0.3840|± |0.0191|
|agieval_lsat_ar | 0|acc |0.2304|± |0.0278|
| | |acc_norm|0.2174|± |0.0273|
|agieval_lsat_lr | 0|acc |0.5471|± |0.0221|
| | |acc_norm|0.5373|± |0.0221|
|agieval_lsat_rc | 0|acc |0.6617|± |0.0289|
| | |acc_norm|0.6357|± |0.0294|
|agieval_sat_en | 0|acc |0.7670|± |0.0295|
| | |acc_norm|0.7379|± |0.0307|
|agieval_sat_en_without_passage| 0|acc |0.4417|± |0.0347|
| | |acc_norm|0.4223|± |0.0345|
|agieval_sat_math | 0|acc |0.4000|± |0.0331|
| | |acc_norm|0.3455|± |0.0321|
```
Average: 44.05
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.6000|± |0.0356|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6585|± |0.0247|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.2340|± |0.0224|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.2980|± |0.0205|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2057|± |0.0153|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5367|± |0.0288|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4040|± |0.0220|
|bigbench_navigate | 0|multiple_choice_grade|0.4970|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7075|± |0.0102|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4821|± |0.0236|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2295|± |0.0133|
|bigbench_snarks | 0|multiple_choice_grade|0.6906|± |0.0345|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5375|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.6270|± |0.0153|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2216|± |0.0118|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1594|± |0.0088|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5367|± |0.0288|
```
Average: 44.13
**IFEval**: 72.64
**MT_Bench**: Turn 1 - 8.3875, Turn 2 - 8.00625, Average - 8.196875
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Theta-Llama-3-8B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Theta-Llama-3-8B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF
# How to cite:
```bibtext
@misc{Hermes-2-Theta-Llama-3-8B,
url={[https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B][NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B))},
title={Hermes-2-Theta-Llama-3-8B},
author={"Teknium", Charles Goddard, "interstellarninja", "theemozilla", "karan4d", "huemin_art"}
}
```
| null |
Non_BioNLP
|
# - Hermes-2 Θ Llama-3 8B
## Model Description
**This is the GGUF version of the Hermes 2 Θ Model. For the FP16 model, [Click Here](https://huggingface.co/NousResearch/Instruct-Hermes-2-Pro-Llama-3-8B)**
Hermes-2 Θ (Theta) is the first experimental merged model released by [Nous Research](https://nousresearch.com/), in collaboration with Charles Goddard at [Arcee](https://www.arcee.ai/), the team behind MergeKit.
Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 Θ, combining the best of both worlds of each model.
## Example Outputs
### Create New Mythos:
### Chat with a Meta-Cognitive Entity
### Ask for a structured JSON output:
# Prompt Format
Hermes 2 Θ uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt 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 Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling. While the system prompt looks complicated, we have created a GitHub repo containing code to easily build these based on real python functions.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5529|± |0.0145|
| | |acc_norm|0.5870|± |0.0144|
|arc_easy | 0|acc |0.8371|± |0.0076|
| | |acc_norm|0.8144|± |0.0080|
|boolq | 1|acc |0.8599|± |0.0061|
|hellaswag | 0|acc |0.6133|± |0.0049|
| | |acc_norm|0.7989|± |0.0040|
|openbookqa | 0|acc |0.3940|± |0.0219|
| | |acc_norm|0.4680|± |0.0223|
|piqa | 0|acc |0.8063|± |0.0092|
| | |acc_norm|0.8156|± |0.0090|
|winogrande | 0|acc |0.7372|± |0.0124|
```
Average: 72.59
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2441|± |0.0270|
| | |acc_norm|0.2441|± |0.0270|
|agieval_logiqa_en | 0|acc |0.3687|± |0.0189|
| | |acc_norm|0.3840|± |0.0191|
|agieval_lsat_ar | 0|acc |0.2304|± |0.0278|
| | |acc_norm|0.2174|± |0.0273|
|agieval_lsat_lr | 0|acc |0.5471|± |0.0221|
| | |acc_norm|0.5373|± |0.0221|
|agieval_lsat_rc | 0|acc |0.6617|± |0.0289|
| | |acc_norm|0.6357|± |0.0294|
|agieval_sat_en | 0|acc |0.7670|± |0.0295|
| | |acc_norm|0.7379|± |0.0307|
|agieval_sat_en_without_passage| 0|acc |0.4417|± |0.0347|
| | |acc_norm|0.4223|± |0.0345|
|agieval_sat_math | 0|acc |0.4000|± |0.0331|
| | |acc_norm|0.3455|± |0.0321|
```
Average: 44.05
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.6000|± |0.0356|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6585|± |0.0247|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.2340|± |0.0224|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.2980|± |0.0205|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2057|± |0.0153|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5367|± |0.0288|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4040|± |0.0220|
|bigbench_navigate | 0|multiple_choice_grade|0.4970|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7075|± |0.0102|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4821|± |0.0236|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2295|± |0.0133|
|bigbench_snarks | 0|multiple_choice_grade|0.6906|± |0.0345|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5375|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.6270|± |0.0153|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2216|± |0.0118|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1594|± |0.0088|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5367|± |0.0288|
```
Average: 44.13
**IFEval**: 72.64
**MT_Bench**: Turn 1 - 8.3875, Turn 2 - 8.00625, Average - 8.196875
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Theta-Llama-3-8B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Theta-Llama-3-8B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF
# How to cite:
```bibtext
@misc{Hermes-2-Theta-Llama-3-8B,
url={[https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B][NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B))},
title={Hermes-2-Theta-Llama-3-8B},
author={"Teknium", Charles Goddard, "interstellarninja", "theemozilla", "karan4d", "huemin_art"}
}
```
|
{"base_model": "NousResearch/Hermes-2-Pro-Llama-3-8B", "datasets": ["teknium/OpenHermes-2.5"], "language": ["en"], "tags": ["Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "axolotl", "merges"], "widget": [{"example_title": "Hermes 2 Pro Llama-3 Instruct Merge", "messages": [{"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."}, {"role": "user", "content": "Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world."}]}], "model-index": [{"name": "Hermes-2-Pro-Llama-3-Instruct-8B-Merge", "results": []}]}
|
task
|
[
"TRANSLATION"
] | 41,565 |
MaLA-LM/lucky52-bloom-7b1-no-34
|
MaLA-LM
|
text-generation
|
[
"transformers",
"pytorch",
"bloom",
"text-generation",
"generation",
"question answering",
"instruction tuning",
"multilingual",
"dataset:MBZUAI/Bactrian-X",
"arxiv:2404.04850",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-04-04T13:13:00Z |
2025-04-08T17:02:48+00:00
| 15 | 0 |
---
datasets:
- MBZUAI/Bactrian-X
language:
- multilingual
library_name: transformers
license: cc-by-nc-4.0
pipeline_tag: text-generation
tags:
- generation
- question answering
- instruction tuning
---
### Model Description
This HF repository hosts instruction fine-tuned multilingual BLOOM model using the parallel instruction dataset called Bactrain-X in 52 languages.
We progressively add a language during instruction fine-tuning at each time, and train 52 models in total. Then, we evaluate those models in three multilingual benchmarks.
Please refer to [our paper](https://arxiv.org/abs/2404.04850) for more details.
* Base model: [BLOOM 7B1](https://huggingface.co/bigscience/bloom-7b1)
* Instruction languages: English, Chinese, Afrikaans, Arabic, Azerbaijani, Bengali, Czech, German, Spanish, Estonian, Farsi, Finnish, French, Galician, Gujarati, Hebrew, Hindi, Croatian, Indonesian, Italian, Japanese, Georgian, Kazakh, Khmer, Korean, Lithuanian, Latvian, Macedonian, Malayalam, Mongolian, Marathi, Burmese, Nepali, Dutch
* Instruction language codes: en, zh, af, ar, az, bn, cs, de, es, et, fa, fi, fr, gl, gu, he, hi, hr, id, it, ja, ka, kk, km, ko, lt, lv, mk, ml, mn, mr, my, ne, nl
* Training method: full-parameter fine-tuning.
### Usage
The model checkpoint should be loaded using `transformers` library.
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-34")
model = AutoModelForCausalLM.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-34")
```
### Citation
```
@inproceedings{ji2025lucky52,
title={How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM},
author={Shaoxiong Ji and Pinzhen Chen},
year={2025},
booktitle={Proceedings of COLING},
url={https://arxiv.org/abs/2404.04850},
}
```
| null |
Non_BioNLP
|
### Model Description
This HF repository hosts instruction fine-tuned multilingual BLOOM model using the parallel instruction dataset called Bactrain-X in 52 languages.
We progressively add a language during instruction fine-tuning at each time, and train 52 models in total. Then, we evaluate those models in three multilingual benchmarks.
Please refer to [our paper](https://arxiv.org/abs/2404.04850) for more details.
* Base model: [BLOOM 7B1](https://huggingface.co/bigscience/bloom-7b1)
* Instruction languages: English, Chinese, Afrikaans, Arabic, Azerbaijani, Bengali, Czech, German, Spanish, Estonian, Farsi, Finnish, French, Galician, Gujarati, Hebrew, Hindi, Croatian, Indonesian, Italian, Japanese, Georgian, Kazakh, Khmer, Korean, Lithuanian, Latvian, Macedonian, Malayalam, Mongolian, Marathi, Burmese, Nepali, Dutch
* Instruction language codes: en, zh, af, ar, az, bn, cs, de, es, et, fa, fi, fr, gl, gu, he, hi, hr, id, it, ja, ka, kk, km, ko, lt, lv, mk, ml, mn, mr, my, ne, nl
* Training method: full-parameter fine-tuning.
### Usage
The model checkpoint should be loaded using `transformers` library.
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-34")
model = AutoModelForCausalLM.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-34")
```
### Citation
```
@inproceedings{ji2025lucky52,
title={How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM},
author={Shaoxiong Ji and Pinzhen Chen},
year={2025},
booktitle={Proceedings of COLING},
url={https://arxiv.org/abs/2404.04850},
}
```
|
{"datasets": ["MBZUAI/Bactrian-X"], "language": ["multilingual"], "library_name": "transformers", "license": "cc-by-nc-4.0", "pipeline_tag": "text-generation", "tags": ["generation", "question answering", "instruction tuning"]}
|
task
|
[
"QUESTION_ANSWERING"
] | 41,566 |
spacemanidol/flan-t5-base-2-2-cnndm
|
spacemanidol
|
text2text-generation
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:cnn_dailymail",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2023-02-21T18:29:57Z |
2023-02-21T18:53:39+00:00
| 10 | 0 |
---
datasets:
- cnn_dailymail
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: base-2-2-t
results:
- task:
type: summarization
name: Summarization
dataset:
name: cnn_dailymail 3.0.0
type: cnn_dailymail
config: 3.0.0
split: validation
args: 3.0.0
metrics:
- type: rouge
value: 36.9872
name: Rouge1
---
<!-- 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. -->
# base-2-2-t
This model is a fine-tuned version of [asy/cnndm/base-2-2/](https://huggingface.co/asy/cnndm/base-2-2/) on the cnn_dailymail 3.0.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8366
- Rouge1: 36.9872
- Rouge2: 15.868
- Rougel: 26.6297
- Rougelsum: 34.4335
- Gen Len: 69.0770
## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.12.1
| null |
Non_BioNLP
|
<!-- 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. -->
# base-2-2-t
This model is a fine-tuned version of [asy/cnndm/base-2-2/](https://huggingface.co/asy/cnndm/base-2-2/) on the cnn_dailymail 3.0.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8366
- Rouge1: 36.9872
- Rouge2: 15.868
- Rougel: 26.6297
- Rougelsum: 34.4335
- Gen Len: 69.0770
## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.12.1
|
{"datasets": ["cnn_dailymail"], "metrics": ["rouge"], "tags": ["generated_from_trainer"], "model-index": [{"name": "base-2-2-t", "results": [{"task": {"type": "summarization", "name": "Summarization"}, "dataset": {"name": "cnn_dailymail 3.0.0", "type": "cnn_dailymail", "config": "3.0.0", "split": "validation", "args": "3.0.0"}, "metrics": [{"type": "rouge", "value": 36.9872, "name": "Rouge1"}]}]}]}
|
task
|
[
"SUMMARIZATION"
] | 41,567 |
asadnaqvi/setfitabsa-aspect
|
asadnaqvi
|
text-classification
|
[
"setfit",
"safetensors",
"bert",
"absa",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:BAAI/bge-small-en-v1.5",
"base_model:finetune:BAAI/bge-small-en-v1.5",
"model-index",
"region:us"
] | 2024-05-05T13:00:08Z |
2024-05-06T09:49:05+00:00
| 10 | 2 |
---
base_model: BAAI/bge-small-en-v1.5
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- absa
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: closures:Runa Sarkar, a professor at the Indian Institute of Management Calcutta,
said the coal mining region most affected by mine closures is West Bengal.
- text: comment:Neither the Russian nor the Chinese defence ministries responded to
Reuters' requests for comment.
- text: 'Canada:The statements made in Canada''s parliament were finally an acknowledgement
of the reality that young Sikhs like me have lived through for decades: Sikh dissidents
expressing their support for an independent state may face the risk of imminent
harm, even in the diaspora.'
- text: France:The Paris Agreement, a legally binding international treaty on climate
change adopted by 196 parties at the UN Climate Change Conference (COP21) in Paris,
France in December 2015, aims to hold the increase in the global average temperature
to well below 2°C above pre-industrial levels.
- text: 'risk:The statements made in Canada''s parliament were finally an acknowledgement
of the reality that young Sikhs like me have lived through for decades: Sikh dissidents
expressing their support for an independent state may face the risk of imminent
harm, even in the diaspora.'
inference: false
model-index:
- name: SetFit Aspect Model with BAAI/bge-small-en-v1.5
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.7630057803468208
name: Accuracy
---
# SetFit Aspect Model with BAAI/bge-small-en-v1.5
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of filtering aspect span candidates.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
This model was trained within the context of a larger system for ABSA, which looks like so:
1. Use a spaCy model to select possible aspect span candidates.
2. **Use this SetFit model to filter these possible aspect span candidates.**
3. Use a SetFit model to classify the filtered aspect span candidates.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **spaCy Model:** en_core_web_lg
- **SetFitABSA Aspect Model:** [asadnaqvi/setfitabsa-aspect](https://huggingface.co/asadnaqvi/setfitabsa-aspect)
- **SetFitABSA Polarity Model:** [asadnaqvi/setfitabsa-polarity](https://huggingface.co/asadnaqvi/setfitabsa-polarity)
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:----------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| aspect | <ul><li>"visit:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li><li>"Mohammed bin Salman:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li><li>'legitimacy:The trip to India is evidently timed to burnish his legitimacy after the international opprobrium that followed the murder of The Washington Post journalist Jamal Khashoggi.'</li></ul> |
| no aspect | <ul><li>"Saudi Arabia:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li><li>"MBS:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li><li>"India:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.7630 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import AbsaModel
# Download from the 🤗 Hub
model = AbsaModel.from_pretrained(
"asadnaqvi/setfitabsa-aspect",
"asadnaqvi/setfitabsa-polarity",
)
# Run inference
preds = model("The food was great, but the venue is just way too busy.")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### 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.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 8 | 25.2939 | 40 |
| Label | Training Sample Count |
|:----------|:----------------------|
| no aspect | 248 |
| aspect | 99 |
### Training Hyperparameters
- batch_size: (128, 128)
- num_epochs: (5, 5)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: True
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:----------:|:-------:|:-------------:|:---------------:|
| 0.0018 | 1 | 0.2598 | - |
| 0.0893 | 50 | 0.2458 | 0.2547 |
| 0.1786 | 100 | 0.2418 | 0.2522 |
| 0.2679 | 150 | 0.2427 | 0.2452 |
| **0.3571** | **200** | **0.1272** | **0.2419** |
| 0.4464 | 250 | 0.0075 | 0.2853 |
| 0.5357 | 300 | 0.0023 | 0.3134 |
| 0.625 | 350 | 0.0021 | 0.3138 |
| 0.7143 | 400 | 0.0037 | 0.3502 |
| 0.8036 | 450 | 0.011 | 0.3437 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.7.0
- spaCy: 3.7.4
- Transformers: 4.40.1
- PyTorch: 2.2.1+cu121
- Datasets: 2.19.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## 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.*
-->
| null |
Non_BioNLP
|
# SetFit Aspect Model with BAAI/bge-small-en-v1.5
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of filtering aspect span candidates.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
This model was trained within the context of a larger system for ABSA, which looks like so:
1. Use a spaCy model to select possible aspect span candidates.
2. **Use this SetFit model to filter these possible aspect span candidates.**
3. Use a SetFit model to classify the filtered aspect span candidates.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **spaCy Model:** en_core_web_lg
- **SetFitABSA Aspect Model:** [asadnaqvi/setfitabsa-aspect](https://huggingface.co/asadnaqvi/setfitabsa-aspect)
- **SetFitABSA Polarity Model:** [asadnaqvi/setfitabsa-polarity](https://huggingface.co/asadnaqvi/setfitabsa-polarity)
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:----------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| aspect | <ul><li>"visit:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li><li>"Mohammed bin Salman:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li><li>'legitimacy:The trip to India is evidently timed to burnish his legitimacy after the international opprobrium that followed the murder of The Washington Post journalist Jamal Khashoggi.'</li></ul> |
| no aspect | <ul><li>"Saudi Arabia:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li><li>"MBS:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li><li>"India:The upcoming visit of Saudi Arabia's crown prince Mohammed bin Salman (MBS) to India is not a routine affair."</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.7630 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import AbsaModel
# Download from the 🤗 Hub
model = AbsaModel.from_pretrained(
"asadnaqvi/setfitabsa-aspect",
"asadnaqvi/setfitabsa-polarity",
)
# Run inference
preds = model("The food was great, but the venue is just way too busy.")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### 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.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 8 | 25.2939 | 40 |
| Label | Training Sample Count |
|:----------|:----------------------|
| no aspect | 248 |
| aspect | 99 |
### Training Hyperparameters
- batch_size: (128, 128)
- num_epochs: (5, 5)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: True
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:----------:|:-------:|:-------------:|:---------------:|
| 0.0018 | 1 | 0.2598 | - |
| 0.0893 | 50 | 0.2458 | 0.2547 |
| 0.1786 | 100 | 0.2418 | 0.2522 |
| 0.2679 | 150 | 0.2427 | 0.2452 |
| **0.3571** | **200** | **0.1272** | **0.2419** |
| 0.4464 | 250 | 0.0075 | 0.2853 |
| 0.5357 | 300 | 0.0023 | 0.3134 |
| 0.625 | 350 | 0.0021 | 0.3138 |
| 0.7143 | 400 | 0.0037 | 0.3502 |
| 0.8036 | 450 | 0.011 | 0.3437 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.7.0
- spaCy: 3.7.4
- Transformers: 4.40.1
- PyTorch: 2.2.1+cu121
- Datasets: 2.19.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## 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.*
-->
|
{"base_model": "BAAI/bge-small-en-v1.5", "library_name": "setfit", "metrics": ["accuracy"], "pipeline_tag": "text-classification", "tags": ["setfit", "absa", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "widget": [{"text": "closures:Runa Sarkar, a professor at the Indian Institute of Management Calcutta, said the coal mining region most affected by mine closures is West Bengal."}, {"text": "comment:Neither the Russian nor the Chinese defence ministries responded to Reuters' requests for comment."}, {"text": "Canada:The statements made in Canada's parliament were finally an acknowledgement of the reality that young Sikhs like me have lived through for decades: Sikh dissidents expressing their support for an independent state may face the risk of imminent harm, even in the diaspora."}, {"text": "France:The Paris Agreement, a legally binding international treaty on climate change adopted by 196 parties at the UN Climate Change Conference (COP21) in Paris, France in December 2015, aims to hold the increase in the global average temperature to well below 2°C above pre-industrial levels."}, {"text": "risk:The statements made in Canada's parliament were finally an acknowledgement of the reality that young Sikhs like me have lived through for decades: Sikh dissidents expressing their support for an independent state may face the risk of imminent harm, even in the diaspora."}], "inference": false, "model-index": [{"name": "SetFit Aspect Model with BAAI/bge-small-en-v1.5", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "Unknown", "type": "unknown", "split": "test"}, "metrics": [{"type": "accuracy", "value": 0.7630057803468208, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,568 |
Triangle104/Unsloth_Llama-3.2-3B-Instruct-Q8_0-GGUF
|
Triangle104
| null |
[
"transformers",
"gguf",
"llama-3",
"llama",
"meta",
"facebook",
"unsloth",
"llama-cpp",
"gguf-my-repo",
"en",
"base_model:unsloth/Llama-3.2-3B-Instruct",
"base_model:quantized:unsloth/Llama-3.2-3B-Instruct",
"license:llama3.2",
"endpoints_compatible",
"region:us",
"conversational"
] | 2024-11-11T01:46:12Z |
2025-02-17T12:09:00+00:00
| 13 | 0 |
---
base_model: unsloth/Llama-3.2-3B-Instruct
language:
- en
library_name: transformers
license: llama3.2
tags:
- llama-3
- llama
- meta
- facebook
- unsloth
- transformers
- llama-cpp
- gguf-my-repo
---
# Triangle104/Unsloth_Llama-3.2-3B-Instruct-Q8_0-GGUF
This model was converted to GGUF format from [`unsloth/Llama-3.2-3B-Instruct`](https://huggingface.co/unsloth/Llama-3.2-3B-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/unsloth/Llama-3.2-3B-Instruct) for more details on the model.
---
Model details:
-
Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
Special Thanks
A huge thank you to the Meta and Llama team for creating and releasing these models.
Model Information
The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
Model developer: Meta
Model Architecture: Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
Llama 3.2 family of models Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date: Sept 25, 2024
Status: This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
License: Use of Llama 3.2 is governed by the Llama 3.2 Community License (a custom, commercial license agreement).
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3.1 in applications, please go here.
---
## 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 Triangle104/Llama-3.2-3B-Instruct-Q8_0-GGUF --hf-file llama-3.2-3b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Llama-3.2-3B-Instruct-Q8_0-GGUF --hf-file llama-3.2-3b-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 Triangle104/Llama-3.2-3B-Instruct-Q8_0-GGUF --hf-file llama-3.2-3b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Llama-3.2-3B-Instruct-Q8_0-GGUF --hf-file llama-3.2-3b-instruct-q8_0.gguf -c 2048
```
| null |
Non_BioNLP
|
# Triangle104/Unsloth_Llama-3.2-3B-Instruct-Q8_0-GGUF
This model was converted to GGUF format from [`unsloth/Llama-3.2-3B-Instruct`](https://huggingface.co/unsloth/Llama-3.2-3B-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/unsloth/Llama-3.2-3B-Instruct) for more details on the model.
---
Model details:
-
Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
Special Thanks
A huge thank you to the Meta and Llama team for creating and releasing these models.
Model Information
The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
Model developer: Meta
Model Architecture: Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
Llama 3.2 family of models Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date: Sept 25, 2024
Status: This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
License: Use of Llama 3.2 is governed by the Llama 3.2 Community License (a custom, commercial license agreement).
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3.1 in applications, please go here.
---
## 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 Triangle104/Llama-3.2-3B-Instruct-Q8_0-GGUF --hf-file llama-3.2-3b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Llama-3.2-3B-Instruct-Q8_0-GGUF --hf-file llama-3.2-3b-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 Triangle104/Llama-3.2-3B-Instruct-Q8_0-GGUF --hf-file llama-3.2-3b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Llama-3.2-3B-Instruct-Q8_0-GGUF --hf-file llama-3.2-3b-instruct-q8_0.gguf -c 2048
```
|
{"base_model": "unsloth/Llama-3.2-3B-Instruct", "language": ["en"], "library_name": "transformers", "license": "llama3.2", "tags": ["llama-3", "llama", "meta", "facebook", "unsloth", "transformers", "llama-cpp", "gguf-my-repo"]}
|
task
|
[
"SUMMARIZATION"
] | 41,569 |
fabraz/distilbert-base-uncased-finetunned-emotion
|
fabraz
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-05-23T13:41:47Z |
2024-04-02T14:24:27+00:00
| 16 | 0 |
---
base_model: distilbert-base-uncased
datasets:
- emotion
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetunned-emotion
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
args: default
metrics:
- type: accuracy
value: 0.9285
name: Accuracy
- type: f1
value: 0.9284132954244212
name: F1
---
<!-- 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. -->
# distilbert-base-uncased-finetunned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2102
- Accuracy: 0.9285
- F1: 0.9284
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8258 | 1.0 | 250 | 0.3023 | 0.9065 | 0.9037 |
| 0.2414 | 2.0 | 500 | 0.2102 | 0.9285 | 0.9284 |
### Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetunned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2102
- Accuracy: 0.9285
- F1: 0.9284
## 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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8258 | 1.0 | 250 | 0.3023 | 0.9065 | 0.9037 |
| 0.2414 | 2.0 | 500 | 0.2102 | 0.9285 | 0.9284 |
### Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
|
{"base_model": "distilbert-base-uncased", "datasets": ["emotion"], "license": "apache-2.0", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetunned-emotion", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.9285, "name": "Accuracy"}, {"type": "f1", "value": 0.9284132954244212, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,570 |
w11wo/sundanese-roberta-base
|
w11wo
|
fill-mask
|
[
"transformers",
"pytorch",
"jax",
"tensorboard",
"safetensors",
"roberta",
"fill-mask",
"sundanese-roberta-base",
"su",
"dataset:mc4",
"dataset:cc100",
"dataset:oscar",
"dataset:wikipedia",
"arxiv:1907.11692",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2023-07-20T05:16:57+00:00
| 66 | 2 |
---
datasets:
- mc4
- cc100
- oscar
- wikipedia
language: su
license: mit
tags:
- sundanese-roberta-base
widget:
- text: Budi nuju <mask> di sakola.
---
## Sundanese RoBERTa Base
Sundanese RoBERTa Base is a masked language model based on the [RoBERTa](https://arxiv.org/abs/1907.11692) model. It was trained on four datasets: [OSCAR](https://hf.co/datasets/oscar)'s `unshuffled_deduplicated_su` subset, the Sundanese [mC4](https://hf.co/datasets/mc4) subset, the Sundanese [CC100](https://hf.co/datasets/cc100) subset, and Sundanese [Wikipedia](https://su.wikipedia.org/).
10% of the dataset is kept for evaluation purposes. The model was trained from scratch and achieved an evaluation loss of 1.952 and an evaluation accuracy of 63.98%.
This model was trained using HuggingFace's Flax framework. All necessary scripts used for training could be found in the [Files and versions](https://hf.co/w11wo/sundanese-roberta-base/tree/main) tab, as well as the [Training metrics](https://hf.co/w11wo/sundanese-roberta-base/tensorboard) logged via Tensorboard.
## Model
| Model | #params | Arch. | Training/Validation data (text) |
| ------------------------ | ------- | ------- | ------------------------------------- |
| `sundanese-roberta-base` | 124M | RoBERTa | OSCAR, mC4, CC100, Wikipedia (758 MB) |
## Evaluation Results
The model was trained for 50 epochs and the following is the final result once the training ended.
| train loss | valid loss | valid accuracy | total time |
| ---------- | ---------- | -------------- | ---------- |
| 1.965 | 1.952 | 0.6398 | 6:24:51 |
## How to Use
### As Masked Language Model
```python
from transformers import pipeline
pretrained_name = "w11wo/sundanese-roberta-base"
fill_mask = pipeline(
"fill-mask",
model=pretrained_name,
tokenizer=pretrained_name
)
fill_mask("Budi nuju <mask> di sakola.")
```
### Feature Extraction in PyTorch
```python
from transformers import RobertaModel, RobertaTokenizerFast
pretrained_name = "w11wo/sundanese-roberta-base"
model = RobertaModel.from_pretrained(pretrained_name)
tokenizer = RobertaTokenizerFast.from_pretrained(pretrained_name)
prompt = "Budi nuju diajar di sakola."
encoded_input = tokenizer(prompt, return_tensors='pt')
output = model(**encoded_input)
```
## Disclaimer
Do consider the biases which came from all four datasets that may be carried over into the results of this model.
## Author
Sundanese RoBERTa Base was trained and evaluated by [Wilson Wongso](https://w11wo.github.io/).
## Citation Information
```bib
@article{rs-907893,
author = {Wongso, Wilson
and Lucky, Henry
and Suhartono, Derwin},
journal = {Journal of Big Data},
year = {2022},
month = {Feb},
day = {26},
abstract = {The Sundanese language has over 32 million speakers worldwide, but the language has reaped little to no benefits from the recent advances in natural language understanding. Like other low-resource languages, the only alternative is to fine-tune existing multilingual models. In this paper, we pre-trained three monolingual Transformer-based language models on Sundanese data. When evaluated on a downstream text classification task, we found that most of our monolingual models outperformed larger multilingual models despite the smaller overall pre-training data. In the subsequent analyses, our models benefited strongly from the Sundanese pre-training corpus size and do not exhibit socially biased behavior. We released our models for other researchers and practitioners to use.},
issn = {2693-5015},
doi = {10.21203/rs.3.rs-907893/v1},
url = {https://doi.org/10.21203/rs.3.rs-907893/v1}
}
```
| null |
Non_BioNLP
|
## Sundanese RoBERTa Base
Sundanese RoBERTa Base is a masked language model based on the [RoBERTa](https://arxiv.org/abs/1907.11692) model. It was trained on four datasets: [OSCAR](https://hf.co/datasets/oscar)'s `unshuffled_deduplicated_su` subset, the Sundanese [mC4](https://hf.co/datasets/mc4) subset, the Sundanese [CC100](https://hf.co/datasets/cc100) subset, and Sundanese [Wikipedia](https://su.wikipedia.org/).
10% of the dataset is kept for evaluation purposes. The model was trained from scratch and achieved an evaluation loss of 1.952 and an evaluation accuracy of 63.98%.
This model was trained using HuggingFace's Flax framework. All necessary scripts used for training could be found in the [Files and versions](https://hf.co/w11wo/sundanese-roberta-base/tree/main) tab, as well as the [Training metrics](https://hf.co/w11wo/sundanese-roberta-base/tensorboard) logged via Tensorboard.
## Model
| Model | #params | Arch. | Training/Validation data (text) |
| ------------------------ | ------- | ------- | ------------------------------------- |
| `sundanese-roberta-base` | 124M | RoBERTa | OSCAR, mC4, CC100, Wikipedia (758 MB) |
## Evaluation Results
The model was trained for 50 epochs and the following is the final result once the training ended.
| train loss | valid loss | valid accuracy | total time |
| ---------- | ---------- | -------------- | ---------- |
| 1.965 | 1.952 | 0.6398 | 6:24:51 |
## How to Use
### As Masked Language Model
```python
from transformers import pipeline
pretrained_name = "w11wo/sundanese-roberta-base"
fill_mask = pipeline(
"fill-mask",
model=pretrained_name,
tokenizer=pretrained_name
)
fill_mask("Budi nuju <mask> di sakola.")
```
### Feature Extraction in PyTorch
```python
from transformers import RobertaModel, RobertaTokenizerFast
pretrained_name = "w11wo/sundanese-roberta-base"
model = RobertaModel.from_pretrained(pretrained_name)
tokenizer = RobertaTokenizerFast.from_pretrained(pretrained_name)
prompt = "Budi nuju diajar di sakola."
encoded_input = tokenizer(prompt, return_tensors='pt')
output = model(**encoded_input)
```
## Disclaimer
Do consider the biases which came from all four datasets that may be carried over into the results of this model.
## Author
Sundanese RoBERTa Base was trained and evaluated by [Wilson Wongso](https://w11wo.github.io/).
## Citation Information
```bib
@article{rs-907893,
author = {Wongso, Wilson
and Lucky, Henry
and Suhartono, Derwin},
journal = {Journal of Big Data},
year = {2022},
month = {Feb},
day = {26},
abstract = {The Sundanese language has over 32 million speakers worldwide, but the language has reaped little to no benefits from the recent advances in natural language understanding. Like other low-resource languages, the only alternative is to fine-tune existing multilingual models. In this paper, we pre-trained three monolingual Transformer-based language models on Sundanese data. When evaluated on a downstream text classification task, we found that most of our monolingual models outperformed larger multilingual models despite the smaller overall pre-training data. In the subsequent analyses, our models benefited strongly from the Sundanese pre-training corpus size and do not exhibit socially biased behavior. We released our models for other researchers and practitioners to use.},
issn = {2693-5015},
doi = {10.21203/rs.3.rs-907893/v1},
url = {https://doi.org/10.21203/rs.3.rs-907893/v1}
}
```
|
{"datasets": ["mc4", "cc100", "oscar", "wikipedia"], "language": "su", "license": "mit", "tags": ["sundanese-roberta-base"], "widget": [{"text": "Budi nuju <mask> di sakola."}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,571 |
xqewec/title_classifier
|
xqewec
|
text-classification
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"dataset:arxiv_dataset",
"license:openrail",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-06-11T01:37:11Z |
2023-06-12T01:33:13+00:00
| 26 | 1 |
---
datasets:
- arxiv_dataset
license: openrail
metrics:
- code_eval
---
Examples:
title: Generating Approximate Solutions to the TTP using a Linear Distance Relaxation
cat: cs.AI
title: Chaos Based Mixed Keystream Generation for Voice Data Encryption
cat: cs.CR
: A weaving process to define requirements for Cooperative Information System
cat: cs.SE
title: A Comparative Study of Histogram Equalization Based Image Enhancement Techniques for Brightness Preservation and Contrast Enhancement
cat: cs.CV
title: Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation
cat: cs.CL
title: SaaS CloudQual: A Quality Model for Evaluating Software as a Service on the Cloud Computing Environment
cat: cs.SE
title: The ASHRAE Great Energy Predictor III competition: Overview and results
cat: cs.CY
title: Debugging Neural Machine Translations
cat: cs.CL
| null |
Non_BioNLP
|
Examples:
title: Generating Approximate Solutions to the TTP using a Linear Distance Relaxation
cat: cs.AI
title: Chaos Based Mixed Keystream Generation for Voice Data Encryption
cat: cs.CR
: A weaving process to define requirements for Cooperative Information System
cat: cs.SE
title: A Comparative Study of Histogram Equalization Based Image Enhancement Techniques for Brightness Preservation and Contrast Enhancement
cat: cs.CV
title: Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation
cat: cs.CL
title: SaaS CloudQual: A Quality Model for Evaluating Software as a Service on the Cloud Computing Environment
cat: cs.SE
title: The ASHRAE Great Energy Predictor III competition: Overview and results
cat: cs.CY
title: Debugging Neural Machine Translations
cat: cs.CL
|
{"datasets": ["arxiv_dataset"], "license": "openrail", "metrics": ["code_eval"]}
|
task
|
[
"TRANSLATION"
] | 41,572 |
GleghornLab/SYNTERACT
|
GleghornLab
|
text-classification
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"protein language model",
"biology",
"dataset:BIOGRID",
"dataset:Negatome",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-09-12T16:16:33Z |
2025-02-11T18:05:49+00:00
| 266,593 | 4 |
---
datasets:
- BIOGRID
- Negatome
library_name: transformers
license: cc-by-nc-4.0
pipeline_tag: text-classification
tags:
- protein language model
- biology
widget:
- text: M S H S V K I Y D T C I G C T Q C V R A C P T D V L E M I P W G G C K A K
Q I A S A P R T E D C V G C K R C E S A C P T D F L S V R V Y L W H E T T R S
M G L A Y [SEP] M I N L P S L F V P L V G L L F P A V A M A S L F L H V E K R
L L F S T K K I N
example_title: Non-interacting proteins
- text: M S I N I C R D N H D P F Y R Y K M P P I Q A K V E G R G N G I K T A V L
N V A D I S H A L N R P A P Y I V K Y F G F E L G A Q T S I S V D K D R Y L V
N G V H E P A K L Q D V L D G F I N K F V L C G S C K N P E T E I I I T K D N
D L V R D C K A C G K R T P M D L R H K L S S F I L K N P P D S V S G S K K K
K K A A T A S A N V R G G G L S I S D I A Q G K S Q N A P S D G T G S S T P Q
H H D E D E D E L S R Q I K A A A S T L E D I E V K D D E W A V D M S E E A I
R A R A K E L E V N S E L T Q L D E Y G E W I L E Q A G E D K E N L P S D V E
L Y K K A A E L D V L N D P K I G C V L A Q C L F D E D I V N E I A E H N A F
F T K I L V T P E Y E K N F M G G I E R F L G L E H K D L I P L L P K I L V Q
L Y N N D I I S E E E I M R F G T K S S K K F V P K E V S K K V R R A A K P F
I T W L E T A E S D D D E E D D E [SEP] M S I E N L K S F D P F A D T G D D E
T A T S N Y I H I R I Q Q R N G R K T L T T V Q G V P E E Y D L K R I L K V L
K K D F A C N G N I V K D P E M G E I I Q L Q G D Q R A K V C E F M I S Q L G
L Q K K N I K I H G F
example_title: Interacting proteins
---
[SYNTERACT 2.0](https://huggingface.co/Synthyra/SYNTERACT2) is coming soon, please stay tuned!
<img src="https://hf.fast360.xyz/production/uploads/62f2bd3bdb7cbd214b658c48/Ro4uhQDurP-x7IHJj11xa.png" width="350">
## Model description
SYNTERACT (SYNThetic data-driven protein-protein intERACtion Transformer) is a fine-tuned version of [ProtBERT](https://huggingface.co/Rostlab/prot_bert_bfd) that attends two amino acid sequences separated by [SEP] to determine if they plausibly interact in biological context.
We utilized the multivalidated physical interaction dataset from BIORGID, Negatome, and synthetic negative samples to train our model. Check out our [preprint](https://www.biorxiv.org/content/10.1101/2023.06.07.544109v1.full) for more details.
SYNTERACT achieved unprecedented performance over vast phylogeny with 92-96% accuracy on real unseen examples, and is already being used to accelerate drug target screening and peptide therapeutic design.
## How to use
```python
# Imports
import re
import torch
import torch.nn.functional as F
from transformers import BertForSequenceClassification, BertTokenizer
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # gather device
model = BertForSequenceClassification.from_pretrained('GleghornLab/SYNTERACT', attn_implementation='sdpa').device.eval() # load model
tokenizer = BertTokenizer.from_pretrained('GleghornLab/SYNTERACT') # load tokenizer
sequence_a = 'MEKSCSIGNGREQYGWGHGEQCGTQFLECVYRNASMYSVLGDLITYVVFLGATCYAILFGFRLLLSCVRIVLKVVIALFVIRLLLALGSVDITSVSYSG' # Uniprot A1Z8T3
sequence_b = 'MRLTLLALIGVLCLACAYALDDSENNDQVVGLLDVADQGANHANDGAREARQLGGWGGGWGGRGGWGGRGGWGGRGGWGGRGGWGGGWGGRGGWGGRGGGWYGR' # Uniprot A1Z8H0
sequence_a = ' '.join(list(re.sub(r'[UZOB]', 'X', sequence_a))) # need spaces inbetween amino acids
sequence_b = ' '.join(list(re.sub(r'[UZOB]', 'X', sequence_b))) # replace rare amino acids with X
example = sequence_a + ' [SEP] ' + sequence_b # add SEP token
example = tokenizer(example, return_tensors='pt', padding=False).to(device) # tokenize example
with torch.no_grad():
logits = model(**example).logits.detach().cpu() # get logits from model
probability = F.softmax(logits, dim=-1) # use softmax to get "confidence" in the prediction
prediction = probability.argmax(dim=-1) # 0 for no interaction, 1 for interaction
```
## Intended use and limitations
We define a protein-protein interaction as physical contact that mediates chemical or conformational change, especially with non-generic function. However, due to SYNTERACT's propensity to predict false positives, we believe that it identifies plausible conformational changes caused by interactions without relevance to function.
## Our lab
The [Gleghorn lab](https://www.gleghornlab.com/) is an interdisciplinary research group at the University of Delaware that focuses on solving translational problems with our expertise in engineering, biology, and chemistry. We develop inexpensive and reliable tools to study organ development, maternal-fetal health, and drug delivery. Recently we have begun exploration into protein language models and strive to make protein design and annotation accessible.
## Please cite
```
@article {Hallee_ppi_2023,
author = {Logan Hallee and Jason P. Gleghorn},
title = {Protein-Protein Interaction Prediction is Achievable with Large Language Models},
year = {2023},
doi = {10.1101/2023.06.07.544109},
publisher = {Cold Spring Harbor Laboratory},
journal = {bioRxiv}
}
```
## A simple inference script
```python
import torch
import re
import argparse
import pandas as pd
from transformers import BertForSequenceClassification, BertTokenizer
from torch.utils.data import Dataset, DataLoader
from typing import List, Tuple, Dict
from tqdm.auto import tqdm
class PairDataset(Dataset):
def __init__(self, sequences_a: List[str], sequences_b: List[str]):
self.sequences_a = sequences_a
self.sequences_b = sequences_b
def __len__(self):
return len(self.sequences_a)
def __getitem__(self, idx: int) -> Tuple[str, str]:
return self.sequences_a[idx], self.sequences_b[idx]
class PairCollator:
def __init__(self, tokenizer, max_length=1024):
self.tokenizer = tokenizer
self.max_length = max_length
def sanitize_seq(self, seq: str) -> str:
seq = ' '.join(list(re.sub(r'[UZOB]', 'X', seq)))
return seq
def __call__(self, batch: List[Tuple[str, str]]) -> Dict[str, torch.Tensor]:
seqs_a, seqs_b, = zip(*batch)
seqs = []
for a, b in zip(seqs_a, seqs_b):
seq = self.sanitize_seq(a) + ' [SEP] ' + self.sanitize_seq(b)
seqs.append(seq)
seqs = self.tokenizer(seqs, padding='longest', truncation=True, max_length=self.max_length, return_tensors='pt')
return {
'input_ids': seqs['input_ids'],
'attention_mask': seqs['attention_mask'],
}
def main(args):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f"Using device: {device}")
print(f"Loading model from {args.model_path}")
model = BertForSequenceClassification.from_pretrained(args.model_path, attn_implementation="sdpa").eval().to(device)
# When using PyTorch >= 2.5.1 on a linux machine, spda attention will greatly speed up inference
tokenizer = BertTokenizer.from_pretrained(args.model_path)
print(f"Tokenizer loaded")
"""
Load your data into two lists of sequences, where you want the PPI for each pair sequences_a[i], sequences_b[i]
We recommend trimmed sequence pairs that sum over 1022 tokens (for the 1024 max length limit of SYNTERACT)
We also recommend sorting the sequences by length in descending order, as this will speed up inference by reducing padding
Example:
from datasets import load_dataset
data = load_dataset('Synthyra/NEGATOME', split='combined')
# Filter out examples where the total length exceeds 1022
data = data.filter(lambda x: len(x['SeqA']) + len(x['SeqB']) <= 1022)
# Add a new column 'total_length' that is the sum of lengths of SeqA and SeqB
data = data.map(lambda x: {"total_length": len(x['SeqA']) + len(x['SeqB'])})
# Sort the dataset by 'total_length' in descending order (longest sequences first)
data = data.sort("total_length", reverse=True)
# Now retrieve the sorted sequences
sequences_a = data['SeqA']
sequences_b = data['SeqB']
"""
print("Loading data...")
sequences_a = []
sequences_b = []
print("Creating torch dataset...")
pair_dataset = PairDataset(sequences_a, sequences_b)
pair_collator = PairCollator(tokenizer, max_length=1024)
data_loader = DataLoader(pair_dataset, batch_size=args.batch_size, num_workers=args.num_workers, collate_fn=pair_collator)
all_seqs_a = []
all_seqs_b = []
all_probs = []
all_preds = []
print("Starting inference...")
with torch.no_grad():
for i, batch in enumerate(tqdm(data_loader, total=len(data_loader), desc="Batches processed")):
# Because sequences are sorted, the initial estimate for time will be much longer than the actual time it will take
input_ids = batch['input_ids'].to(device)
attention_mask = batch['attention_mask'].to(device)
logits = model(input_ids, attention_mask=attention_mask).logits.detach().cpu()
prob_of_interaction = torch.softmax(logits, dim=1)[:, 1] # can do 1 - this for no interaction prob
pred = torch.argmax(logits, dim=1)
# Store results
batch_start = i * args.batch_size
batch_end = min((i + 1) * args.batch_size, len(sequences_a))
all_seqs_a.extend(sequences_a[batch_start:batch_end])
all_seqs_b.extend(sequences_b[batch_start:batch_end])
all_probs.extend(prob_of_interaction.tolist())
all_preds.extend(pred.tolist())
# round to 5 decimal places
all_probs = [round(prob, 5) for prob in all_probs]
# Create dataframe and save to CSV
results_df = pd.DataFrame({
'sequence_a': all_seqs_a,
'sequence_b': all_seqs_b,
'probabilities': all_probs,
'prediction': all_preds
})
print(f"Saving results to {args.save_path}")
results_df.to_csv(args.save_path, index=False)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--model_path', type=str, default='GleghornLab/SYNTERACT')
parser.add_argument('--save_path', type=str, default='ppi_predictions.csv')
parser.add_argument('--batch_size', type=int, default=2)
parser.add_argument('--num_workers', type=int, default=0) # can increase to use multiprocessing for dataloader, 4 is a good value usually
args = parser.parse_args()
main(args)
```
| null |
Non_BioNLP
|
[SYNTERACT 2.0](https://huggingface.co/Synthyra/SYNTERACT2) is coming soon, please stay tuned!
<img src="https://hf.fast360.xyz/production/uploads/62f2bd3bdb7cbd214b658c48/Ro4uhQDurP-x7IHJj11xa.png" width="350">
## Model description
SYNTERACT (SYNThetic data-driven protein-protein intERACtion Transformer) is a fine-tuned version of [ProtBERT](https://huggingface.co/Rostlab/prot_bert_bfd) that attends two amino acid sequences separated by [SEP] to determine if they plausibly interact in biological context.
We utilized the multivalidated physical interaction dataset from BIORGID, Negatome, and synthetic negative samples to train our model. Check out our [preprint](https://www.biorxiv.org/content/10.1101/2023.06.07.544109v1.full) for more details.
SYNTERACT achieved unprecedented performance over vast phylogeny with 92-96% accuracy on real unseen examples, and is already being used to accelerate drug target screening and peptide therapeutic design.
## How to use
```python
# Imports
import re
import torch
import torch.nn.functional as F
from transformers import BertForSequenceClassification, BertTokenizer
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # gather device
model = BertForSequenceClassification.from_pretrained('GleghornLab/SYNTERACT', attn_implementation='sdpa').device.eval() # load model
tokenizer = BertTokenizer.from_pretrained('GleghornLab/SYNTERACT') # load tokenizer
sequence_a = 'MEKSCSIGNGREQYGWGHGEQCGTQFLECVYRNASMYSVLGDLITYVVFLGATCYAILFGFRLLLSCVRIVLKVVIALFVIRLLLALGSVDITSVSYSG' # Uniprot A1Z8T3
sequence_b = 'MRLTLLALIGVLCLACAYALDDSENNDQVVGLLDVADQGANHANDGAREARQLGGWGGGWGGRGGWGGRGGWGGRGGWGGRGGWGGGWGGRGGWGGRGGGWYGR' # Uniprot A1Z8H0
sequence_a = ' '.join(list(re.sub(r'[UZOB]', 'X', sequence_a))) # need spaces inbetween amino acids
sequence_b = ' '.join(list(re.sub(r'[UZOB]', 'X', sequence_b))) # replace rare amino acids with X
example = sequence_a + ' [SEP] ' + sequence_b # add SEP token
example = tokenizer(example, return_tensors='pt', padding=False).to(device) # tokenize example
with torch.no_grad():
logits = model(**example).logits.detach().cpu() # get logits from model
probability = F.softmax(logits, dim=-1) # use softmax to get "confidence" in the prediction
prediction = probability.argmax(dim=-1) # 0 for no interaction, 1 for interaction
```
## Intended use and limitations
We define a protein-protein interaction as physical contact that mediates chemical or conformational change, especially with non-generic function. However, due to SYNTERACT's propensity to predict false positives, we believe that it identifies plausible conformational changes caused by interactions without relevance to function.
## Our lab
The [Gleghorn lab](https://www.gleghornlab.com/) is an interdisciplinary research group at the University of Delaware that focuses on solving translational problems with our expertise in engineering, biology, and chemistry. We develop inexpensive and reliable tools to study organ development, maternal-fetal health, and drug delivery. Recently we have begun exploration into protein language models and strive to make protein design and annotation accessible.
## Please cite
```
@article {Hallee_ppi_2023,
author = {Logan Hallee and Jason P. Gleghorn},
title = {Protein-Protein Interaction Prediction is Achievable with Large Language Models},
year = {2023},
doi = {10.1101/2023.06.07.544109},
publisher = {Cold Spring Harbor Laboratory},
journal = {bioRxiv}
}
```
## A simple inference script
```python
import torch
import re
import argparse
import pandas as pd
from transformers import BertForSequenceClassification, BertTokenizer
from torch.utils.data import Dataset, DataLoader
from typing import List, Tuple, Dict
from tqdm.auto import tqdm
class PairDataset(Dataset):
def __init__(self, sequences_a: List[str], sequences_b: List[str]):
self.sequences_a = sequences_a
self.sequences_b = sequences_b
def __len__(self):
return len(self.sequences_a)
def __getitem__(self, idx: int) -> Tuple[str, str]:
return self.sequences_a[idx], self.sequences_b[idx]
class PairCollator:
def __init__(self, tokenizer, max_length=1024):
self.tokenizer = tokenizer
self.max_length = max_length
def sanitize_seq(self, seq: str) -> str:
seq = ' '.join(list(re.sub(r'[UZOB]', 'X', seq)))
return seq
def __call__(self, batch: List[Tuple[str, str]]) -> Dict[str, torch.Tensor]:
seqs_a, seqs_b, = zip(*batch)
seqs = []
for a, b in zip(seqs_a, seqs_b):
seq = self.sanitize_seq(a) + ' [SEP] ' + self.sanitize_seq(b)
seqs.append(seq)
seqs = self.tokenizer(seqs, padding='longest', truncation=True, max_length=self.max_length, return_tensors='pt')
return {
'input_ids': seqs['input_ids'],
'attention_mask': seqs['attention_mask'],
}
def main(args):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f"Using device: {device}")
print(f"Loading model from {args.model_path}")
model = BertForSequenceClassification.from_pretrained(args.model_path, attn_implementation="sdpa").eval().to(device)
# When using PyTorch >= 2.5.1 on a linux machine, spda attention will greatly speed up inference
tokenizer = BertTokenizer.from_pretrained(args.model_path)
print(f"Tokenizer loaded")
"""
Load your data into two lists of sequences, where you want the PPI for each pair sequences_a[i], sequences_b[i]
We recommend trimmed sequence pairs that sum over 1022 tokens (for the 1024 max length limit of SYNTERACT)
We also recommend sorting the sequences by length in descending order, as this will speed up inference by reducing padding
Example:
from datasets import load_dataset
data = load_dataset('Synthyra/NEGATOME', split='combined')
# Filter out examples where the total length exceeds 1022
data = data.filter(lambda x: len(x['SeqA']) + len(x['SeqB']) <= 1022)
# Add a new column 'total_length' that is the sum of lengths of SeqA and SeqB
data = data.map(lambda x: {"total_length": len(x['SeqA']) + len(x['SeqB'])})
# Sort the dataset by 'total_length' in descending order (longest sequences first)
data = data.sort("total_length", reverse=True)
# Now retrieve the sorted sequences
sequences_a = data['SeqA']
sequences_b = data['SeqB']
"""
print("Loading data...")
sequences_a = []
sequences_b = []
print("Creating torch dataset...")
pair_dataset = PairDataset(sequences_a, sequences_b)
pair_collator = PairCollator(tokenizer, max_length=1024)
data_loader = DataLoader(pair_dataset, batch_size=args.batch_size, num_workers=args.num_workers, collate_fn=pair_collator)
all_seqs_a = []
all_seqs_b = []
all_probs = []
all_preds = []
print("Starting inference...")
with torch.no_grad():
for i, batch in enumerate(tqdm(data_loader, total=len(data_loader), desc="Batches processed")):
# Because sequences are sorted, the initial estimate for time will be much longer than the actual time it will take
input_ids = batch['input_ids'].to(device)
attention_mask = batch['attention_mask'].to(device)
logits = model(input_ids, attention_mask=attention_mask).logits.detach().cpu()
prob_of_interaction = torch.softmax(logits, dim=1)[:, 1] # can do 1 - this for no interaction prob
pred = torch.argmax(logits, dim=1)
# Store results
batch_start = i * args.batch_size
batch_end = min((i + 1) * args.batch_size, len(sequences_a))
all_seqs_a.extend(sequences_a[batch_start:batch_end])
all_seqs_b.extend(sequences_b[batch_start:batch_end])
all_probs.extend(prob_of_interaction.tolist())
all_preds.extend(pred.tolist())
# round to 5 decimal places
all_probs = [round(prob, 5) for prob in all_probs]
# Create dataframe and save to CSV
results_df = pd.DataFrame({
'sequence_a': all_seqs_a,
'sequence_b': all_seqs_b,
'probabilities': all_probs,
'prediction': all_preds
})
print(f"Saving results to {args.save_path}")
results_df.to_csv(args.save_path, index=False)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--model_path', type=str, default='GleghornLab/SYNTERACT')
parser.add_argument('--save_path', type=str, default='ppi_predictions.csv')
parser.add_argument('--batch_size', type=int, default=2)
parser.add_argument('--num_workers', type=int, default=0) # can increase to use multiprocessing for dataloader, 4 is a good value usually
args = parser.parse_args()
main(args)
```
|
{"datasets": ["BIOGRID", "Negatome"], "library_name": "transformers", "license": "cc-by-nc-4.0", "pipeline_tag": "text-classification", "tags": ["protein language model", "biology"], "widget": [{"text": "M S H S V K I Y D T C I G C T Q C V R A C P T D V L E M I P W G G C K A K Q I A S A P R T E D C V G C K R C E S A C P T D F L S V R V Y L W H E T T R S M G L A Y [SEP] M I N L P S L F V P L V G L L F P A V A M A S L F L H V E K R L L F S T K K I N", "example_title": "Non-interacting proteins"}, {"text": "M S I N I C R D N H D P F Y R Y K M P P I Q A K V E G R G N G I K T A V L N V A D I S H A L N R P A P Y I V K Y F G F E L G A Q T S I S V D K D R Y L V N G V H E P A K L Q D V L D G F I N K F V L C G S C K N P E T E I I I T K D N D L V R D C K A C G K R T P M D L R H K L S S F I L K N P P D S V S G S K K K K K A A T A S A N V R G G G L S I S D I A Q G K S Q N A P S D G T G S S T P Q H H D E D E D E L S R Q I K A A A S T L E D I E V K D D E W A V D M S E E A I R A R A K E L E V N S E L T Q L D E Y G E W I L E Q A G E D K E N L P S D V E L Y K K A A E L D V L N D P K I G C V L A Q C L F D E D I V N E I A E H N A F F T K I L V T P E Y E K N F M G G I E R F L G L E H K D L I P L L P K I L V Q L Y N N D I I S E E E I M R F G T K S S K K F V P K E V S K K V R R A A K P F I T W L E T A E S D D D E E D D E [SEP] M S I E N L K S F D P F A D T G D D E T A T S N Y I H I R I Q Q R N G R K T L T T V Q G V P E E Y D L K R I L K V L K K D F A C N G N I V K D P E M G E I I Q L Q G D Q R A K V C E F M I S Q L G L Q K K N I K I H G F", "example_title": "Interacting proteins"}]}
|
task
|
[
"TRANSLATION"
] | 41,573 |
henryscheible/rte
|
henryscheible
|
text-classification
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-01-09T19:42:14Z |
2023-01-09T19:46:54+00:00
| 10 | 0 |
---
datasets:
- glue
language:
- en
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: rte
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- type: accuracy
value: 0.6462093862815884
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. -->
# rte
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7912
- Accuracy: 0.6462
## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.13.1
| null |
Non_BioNLP
|
<!-- 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. -->
# rte
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7912
- Accuracy: 0.6462
## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.13.1
|
{"datasets": ["glue"], "language": ["en"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "rte", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE RTE", "type": "glue", "args": "rte"}, "metrics": [{"type": "accuracy", "value": 0.6462093862815884, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,574 |
MatMulMan/bert-base-arabertv02-75746-pretrain
|
MatMulMan
|
question-answering
|
[
"transformers",
"safetensors",
"bert",
"question-answering",
"endpoints_compatible",
"region:us"
] | 2024-09-23T15:09:24Z |
2024-09-23T15:09:50+00:00
| 10 | 0 |
---
library_name: transformers
tags: []
---
# bert-base-arabertv02-75746-pretrain
# Quran Passage Retrieval Model
This is a **fine-tuned model** on Arabic passage retrieval datasets, used for **Quran QA 2023 Task A**.
## Model Description
This model was fine-tuned to perform text classification on an Arabic dataset. The task involves identifying relevant passages from the Quran in response to specific questions, focusing on retrieval quality.
- **Base model**: Pretrained transformer-based model (e.g., AraBERT, CAMeLBERT, AraELECTRA).
- **Task**: Passage retrieval (text classification).
- **Dataset**: Fine-tuned on the Quran QA 2023 dataset.
## Intended Use
- **Language**: Arabic
- **Task**: Passage retrieval for Quran QA
- **Usage**: Use this model for ranking and retrieving relevant passages from a corpus of Arabic text, primarily for question answering tasks.
## Evaluation Results
- reported in the paper
## How to Use
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("mohammed-elkomy/quran-qa")
tokenizer = AutoTokenizer.from_pretrained("mohammed-elkomy/quran-qa")
inputs = tokenizer("Your input text", return_tensors="pt")
outputs = model(**inputs)
## Citation
If you use this model, please cite the following:
```
@inproceedings{elkomy2023quran,
title={TCE at Qur’an QA 2023 Shared Task: Low Resource Enhanced Transformer-based Ensemble Approach for Qur’anic QA},
author={Mohammed ElKomy and Amany Sarhan},
year={2023},
url={https://github.com/mohammed-elkomy/quran-qa/},
}
```
```
@inproceedings{elkomy2022quran,
title={TCE at Qur'an QA 2022: Arabic Language Question Answering Over Holy Qur'an Using a Post-Processed Ensemble of BERT-based Models},
author={Mohammed ElKomy and Amany Sarhan},
year={2022},
url={https://github.com/mohammed-elkomy/quran-qa/},
}
```
| null |
Non_BioNLP
|
# bert-base-arabertv02-75746-pretrain
# Quran Passage Retrieval Model
This is a **fine-tuned model** on Arabic passage retrieval datasets, used for **Quran QA 2023 Task A**.
## Model Description
This model was fine-tuned to perform text classification on an Arabic dataset. The task involves identifying relevant passages from the Quran in response to specific questions, focusing on retrieval quality.
- **Base model**: Pretrained transformer-based model (e.g., AraBERT, CAMeLBERT, AraELECTRA).
- **Task**: Passage retrieval (text classification).
- **Dataset**: Fine-tuned on the Quran QA 2023 dataset.
## Intended Use
- **Language**: Arabic
- **Task**: Passage retrieval for Quran QA
- **Usage**: Use this model for ranking and retrieving relevant passages from a corpus of Arabic text, primarily for question answering tasks.
## Evaluation Results
- reported in the paper
## How to Use
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("mohammed-elkomy/quran-qa")
tokenizer = AutoTokenizer.from_pretrained("mohammed-elkomy/quran-qa")
inputs = tokenizer("Your input text", return_tensors="pt")
outputs = model(**inputs)
## Citation
If you use this model, please cite the following:
```
@inproceedings{elkomy2023quran,
title={TCE at Qur’an QA 2023 Shared Task: Low Resource Enhanced Transformer-based Ensemble Approach for Qur’anic QA},
author={Mohammed ElKomy and Amany Sarhan},
year={2023},
url={https://github.com/mohammed-elkomy/quran-qa/},
}
```
```
@inproceedings{elkomy2022quran,
title={TCE at Qur'an QA 2022: Arabic Language Question Answering Over Holy Qur'an Using a Post-Processed Ensemble of BERT-based Models},
author={Mohammed ElKomy and Amany Sarhan},
year={2022},
url={https://github.com/mohammed-elkomy/quran-qa/},
}
```
|
{"library_name": "transformers", "tags": []}
|
task
|
[
"TEXT_CLASSIFICATION",
"QUESTION_ANSWERING"
] | 41,575 |
Kronk0s/autotrain-carbon-finbert
|
Kronk0s
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"autotrain",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-05-21T15:29:07Z |
2024-05-21T15:59:59+00:00
| 0 | 0 |
---
tags:
- autotrain
- text-classification
widget:
- text: I love AutoTrain
---
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.5798057317733765
f1_macro: 0.7605083088954055
f1_micro: 0.8153846153846154
f1_weighted: 0.8174148432212949
precision_macro: 0.7577751196172248
precision_micro: 0.8153846153846154
precision_weighted: 0.8199392712550607
recall_macro: 0.7637917637917638
recall_micro: 0.8153846153846154
recall_weighted: 0.8153846153846154
accuracy: 0.8153846153846154
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.5798057317733765
f1_macro: 0.7605083088954055
f1_micro: 0.8153846153846154
f1_weighted: 0.8174148432212949
precision_macro: 0.7577751196172248
precision_micro: 0.8153846153846154
precision_weighted: 0.8199392712550607
recall_macro: 0.7637917637917638
recall_micro: 0.8153846153846154
recall_weighted: 0.8153846153846154
accuracy: 0.8153846153846154
|
{"tags": ["autotrain", "text-classification"], "widget": [{"text": "I love AutoTrain"}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,576 |
TransferGraph/connectivity_bert_ft_qqp-94-finetuned-lora-tweet_eval_irony
|
TransferGraph
|
text-classification
|
[
"peft",
"safetensors",
"parquet",
"text-classification",
"dataset:tweet_eval",
"base_model:connectivity/bert_ft_qqp-94",
"base_model:adapter:connectivity/bert_ft_qqp-94",
"model-index",
"region:us"
] | 2024-02-27T17:28:07Z |
2024-02-29T13:35:21+00:00
| 0 | 0 |
---
base_model: connectivity/bert_ft_qqp-94
datasets:
- tweet_eval
library_name: peft
metrics:
- accuracy
tags:
- parquet
- text-classification
model-index:
- name: connectivity_bert_ft_qqp-94-finetuned-lora-tweet_eval_irony
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: tweet_eval
type: tweet_eval
config: irony
split: validation
args: irony
metrics:
- type: accuracy
value: 0.6303664921465969
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. -->
# connectivity_bert_ft_qqp-94-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of [connectivity/bert_ft_qqp-94](https://huggingface.co/connectivity/bert_ft_qqp-94) on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- accuracy: 0.6304
## 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: 0.0005
- 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
- num_epochs: 8
### Training results
| accuracy | train_loss | epoch |
|:--------:|:----------:|:-----:|
| 0.5194 | None | 0 |
| 0.5225 | 0.9509 | 0 |
| 0.5267 | 0.7006 | 1 |
| 0.5539 | 0.6894 | 2 |
| 0.5686 | 0.6797 | 3 |
| 0.5958 | 0.6546 | 4 |
| 0.6021 | 0.6307 | 5 |
| 0.6157 | 0.6177 | 6 |
| 0.6304 | 0.6106 | 7 |
### Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2
| null |
Non_BioNLP
|
<!-- 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. -->
# connectivity_bert_ft_qqp-94-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of [connectivity/bert_ft_qqp-94](https://huggingface.co/connectivity/bert_ft_qqp-94) on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- accuracy: 0.6304
## 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: 0.0005
- 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
- num_epochs: 8
### Training results
| accuracy | train_loss | epoch |
|:--------:|:----------:|:-----:|
| 0.5194 | None | 0 |
| 0.5225 | 0.9509 | 0 |
| 0.5267 | 0.7006 | 1 |
| 0.5539 | 0.6894 | 2 |
| 0.5686 | 0.6797 | 3 |
| 0.5958 | 0.6546 | 4 |
| 0.6021 | 0.6307 | 5 |
| 0.6157 | 0.6177 | 6 |
| 0.6304 | 0.6106 | 7 |
### Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2
|
{"base_model": "connectivity/bert_ft_qqp-94", "datasets": ["tweet_eval"], "library_name": "peft", "metrics": ["accuracy"], "tags": ["parquet", "text-classification"], "model-index": [{"name": "connectivity_bert_ft_qqp-94-finetuned-lora-tweet_eval_irony", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "tweet_eval", "type": "tweet_eval", "config": "irony", "split": "validation", "args": "irony"}, "metrics": [{"type": "accuracy", "value": 0.6303664921465969, "name": "accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,577 |
thanhnew2001/falcon7b
|
thanhnew2001
| null |
[
"transformers",
"en",
"dataset:tiiuae/falcon-refinedweb",
"arxiv:2205.14135",
"arxiv:1911.02150",
"arxiv:2101.00027",
"arxiv:2005.14165",
"arxiv:2104.09864",
"arxiv:2306.01116",
"license:apache-2.0",
"region:us"
] | 2023-10-23T07:48:28Z |
2023-10-23T08:07:43+00:00
| 5 | 0 |
---
datasets:
- tiiuae/falcon-refinedweb
language:
- en
license: apache-2.0
inference: false
---
# 🚀 Falcon-7B
**Falcon-7B is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. It is made available under the Apache 2.0 license.**
*Paper coming soon* 😊.
🤗 To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)!
## Why use Falcon-7B?
* **It outperforms comparable open-source models** (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
* **It features an architecture optimized for inference**, with FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)) and multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)).
* **It is made available under a permissive Apache 2.0 license allowing for commercial use**, without any royalties or restrictions.
⚠️ **This is a raw, pretrained model, which should be further finetuned for most usecases.** If you are looking for a version better suited to taking generic instructions in a chat format, we recommend taking a look at [Falcon-7B-Instruct](https://huggingface.co/tiiuae/falcon-7b-instruct).
🔥 **Looking for an even more powerful model?** [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) is Falcon-7B's big brother!
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model = "tiiuae/falcon-7b"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
)
sequences = pipeline(
"Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
💥 **Falcon LLMs require PyTorch 2.0 for use with `transformers`!**
For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon).
You will need **at least 16GB of memory** to swiftly run inference with Falcon-7B.
# Model Card for Falcon-7B
## Model Details
### Model Description
- **Developed by:** [https://www.tii.ae](https://www.tii.ae);
- **Model type:** Causal decoder-only;
- **Language(s) (NLP):** English, German, Spanish, French (and limited capabilities in Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish);
- **License:** Apache 2.0.
### Model Source
- **Paper:** *coming soon*.
## Uses
### Direct Use
Research on large language models; as a foundation for further specialization and finetuning for specific usecases (e.g., summarization, text generation, chatbot, etc.)
### Out-of-Scope Use
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
## Bias, Risks, and Limitations
Falcon-7B is trained on English and French data only, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
### Recommendations
We recommend users of Falcon-7B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.
## How to Get Started with the Model
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model = "tiiuae/falcon-7b"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
)
sequences = pipeline(
"Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
## Training Details
### Training Data
Falcon-7B was trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), a high-quality filtered and deduplicated web dataset which we enhanced with curated corpora. Significant components from our curated copora were inspired by The Pile ([Gao et al., 2020](https://arxiv.org/abs/2101.00027)).
| **Data source** | **Fraction** | **Tokens** | **Sources** |
|--------------------|--------------|------------|-----------------------------------|
| [RefinedWeb-English](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) | 79% | 1,185B | massive web crawl |
| Books | 7% | 110B | |
| Conversations | 6% | 85B | Reddit, StackOverflow, HackerNews |
| Code | 3% | 45B | |
| RefinedWeb-French | 3% | 45B | massive web crawl |
| Technical | 2% | 30B | arXiv, PubMed, USPTO, etc. |
The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b) tokenizer.
### Training Procedure
Falcon-7B was trained on 384 A100 40GB GPUs, using a 2D parallelism strategy (PP=2, DP=192) combined with ZeRO.
#### Training Hyperparameters
| **Hyperparameter** | **Value** | **Comment** |
|--------------------|------------|-------------------------------------------|
| Precision | `bfloat16` | |
| Optimizer | AdamW | |
| Learning rate | 6e-4 | 4B tokens warm-up, cosine decay to 1.2e-5 |
| Weight decay | 1e-1 | |
| Z-loss | 1e-4 | |
| Batch size | 2304 | 30B tokens ramp-up |
#### Speeds, Sizes, Times
Training happened in early March 2023 and took about two weeks.
## Evaluation
*Paper coming soon*.
See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for early results.
## Technical Specifications
### Model Architecture and Objective
Falcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).
The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences:
* **Positionnal embeddings:** rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864));
* **Attention:** multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135));
* **Decoder-block:** parallel attention/MLP with a single layer norm.
| **Hyperparameter** | **Value** | **Comment** |
|--------------------|-----------|----------------------------------------|
| Layers | 32 | |
| `d_model` | 4544 | Increased to compensate for multiquery |
| `head_dim` | 64 | Reduced to optimise for FlashAttention |
| Vocabulary | 65024 | |
| Sequence length | 2048 | |
### Compute Infrastructure
#### Hardware
Falcon-7B was trained on AWS SageMaker, on 384 A100 40GB GPUs in P4d instances.
#### Software
Falcon-7B was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)
## Citation
*Paper coming soon* 😊. In the meanwhile, you can use the following information to cite:
```
@article{falcon40b,
title={{Falcon-40B}: an open large language model with state-of-the-art performance},
author={Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme},
year={2023}
}
```
To learn more about the pretraining dataset, see the 📓 [RefinedWeb paper](https://arxiv.org/abs/2306.01116).
```
@article{refinedweb,
title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only},
author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay},
journal={arXiv preprint arXiv:2306.01116},
eprint={2306.01116},
eprinttype = {arXiv},
url={https://arxiv.org/abs/2306.01116},
year={2023}
}
```
## License
Falcon-7B is made available under the Apache 2.0 license.
## Contact
[email protected]
| null |
Non_BioNLP
|
# 🚀 Falcon-7B
**Falcon-7B is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. It is made available under the Apache 2.0 license.**
*Paper coming soon* 😊.
🤗 To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)!
## Why use Falcon-7B?
* **It outperforms comparable open-source models** (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
* **It features an architecture optimized for inference**, with FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)) and multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)).
* **It is made available under a permissive Apache 2.0 license allowing for commercial use**, without any royalties or restrictions.
⚠️ **This is a raw, pretrained model, which should be further finetuned for most usecases.** If you are looking for a version better suited to taking generic instructions in a chat format, we recommend taking a look at [Falcon-7B-Instruct](https://huggingface.co/tiiuae/falcon-7b-instruct).
🔥 **Looking for an even more powerful model?** [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) is Falcon-7B's big brother!
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model = "tiiuae/falcon-7b"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
)
sequences = pipeline(
"Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
💥 **Falcon LLMs require PyTorch 2.0 for use with `transformers`!**
For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon).
You will need **at least 16GB of memory** to swiftly run inference with Falcon-7B.
# Model Card for Falcon-7B
## Model Details
### Model Description
- **Developed by:** [https://www.tii.ae](https://www.tii.ae);
- **Model type:** Causal decoder-only;
- **Language(s) (NLP):** English, German, Spanish, French (and limited capabilities in Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish);
- **License:** Apache 2.0.
### Model Source
- **Paper:** *coming soon*.
## Uses
### Direct Use
Research on large language models; as a foundation for further specialization and finetuning for specific usecases (e.g., summarization, text generation, chatbot, etc.)
### Out-of-Scope Use
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
## Bias, Risks, and Limitations
Falcon-7B is trained on English and French data only, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
### Recommendations
We recommend users of Falcon-7B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.
## How to Get Started with the Model
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model = "tiiuae/falcon-7b"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
)
sequences = pipeline(
"Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
## Training Details
### Training Data
Falcon-7B was trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), a high-quality filtered and deduplicated web dataset which we enhanced with curated corpora. Significant components from our curated copora were inspired by The Pile ([Gao et al., 2020](https://arxiv.org/abs/2101.00027)).
| **Data source** | **Fraction** | **Tokens** | **Sources** |
|--------------------|--------------|------------|-----------------------------------|
| [RefinedWeb-English](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) | 79% | 1,185B | massive web crawl |
| Books | 7% | 110B | |
| Conversations | 6% | 85B | Reddit, StackOverflow, HackerNews |
| Code | 3% | 45B | |
| RefinedWeb-French | 3% | 45B | massive web crawl |
| Technical | 2% | 30B | arXiv, PubMed, USPTO, etc. |
The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b) tokenizer.
### Training Procedure
Falcon-7B was trained on 384 A100 40GB GPUs, using a 2D parallelism strategy (PP=2, DP=192) combined with ZeRO.
#### Training Hyperparameters
| **Hyperparameter** | **Value** | **Comment** |
|--------------------|------------|-------------------------------------------|
| Precision | `bfloat16` | |
| Optimizer | AdamW | |
| Learning rate | 6e-4 | 4B tokens warm-up, cosine decay to 1.2e-5 |
| Weight decay | 1e-1 | |
| Z-loss | 1e-4 | |
| Batch size | 2304 | 30B tokens ramp-up |
#### Speeds, Sizes, Times
Training happened in early March 2023 and took about two weeks.
## Evaluation
*Paper coming soon*.
See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for early results.
## Technical Specifications
### Model Architecture and Objective
Falcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).
The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences:
* **Positionnal embeddings:** rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864));
* **Attention:** multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135));
* **Decoder-block:** parallel attention/MLP with a single layer norm.
| **Hyperparameter** | **Value** | **Comment** |
|--------------------|-----------|----------------------------------------|
| Layers | 32 | |
| `d_model` | 4544 | Increased to compensate for multiquery |
| `head_dim` | 64 | Reduced to optimise for FlashAttention |
| Vocabulary | 65024 | |
| Sequence length | 2048 | |
### Compute Infrastructure
#### Hardware
Falcon-7B was trained on AWS SageMaker, on 384 A100 40GB GPUs in P4d instances.
#### Software
Falcon-7B was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)
## Citation
*Paper coming soon* 😊. In the meanwhile, you can use the following information to cite:
```
@article{falcon40b,
title={{Falcon-40B}: an open large language model with state-of-the-art performance},
author={Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme},
year={2023}
}
```
To learn more about the pretraining dataset, see the 📓 [RefinedWeb paper](https://arxiv.org/abs/2306.01116).
```
@article{refinedweb,
title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only},
author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay},
journal={arXiv preprint arXiv:2306.01116},
eprint={2306.01116},
eprinttype = {arXiv},
url={https://arxiv.org/abs/2306.01116},
year={2023}
}
```
## License
Falcon-7B is made available under the Apache 2.0 license.
## Contact
[email protected]
|
{"datasets": ["tiiuae/falcon-refinedweb"], "language": ["en"], "license": "apache-2.0", "inference": false}
|
task
|
[
"SUMMARIZATION"
] | 41,578 |
fine-tuned/FiQA2018-512-192-gpt-4o-2024-05-13-11626257
|
fine-tuned
|
feature-extraction
|
[
"sentence-transformers",
"safetensors",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"mteb",
"en",
"dataset:fine-tuned/FiQA2018-512-192-gpt-4o-2024-05-13-11626257",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 2024-05-29T02:05:47Z |
2024-05-29T02:06:43+00:00
| 6 | 0 |
---
datasets:
- fine-tuned/FiQA2018-512-192-gpt-4o-2024-05-13-11626257
- allenai/c4
language:
- en
- en
license: apache-2.0
pipeline_tag: feature-extraction
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
---
This model is a fine-tuned version of [**BAAI/bge-m3**](https://huggingface.co/BAAI/bge-m3) designed for the following use case:
None
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
'fine-tuned/FiQA2018-512-192-gpt-4o-2024-05-13-11626257',
trust_remote_code=True
)
embeddings = model.encode([
'first text to embed',
'second text to embed'
])
print(cos_sim(embeddings[0], embeddings[1]))
```
| null |
Non_BioNLP
|
This model is a fine-tuned version of [**BAAI/bge-m3**](https://huggingface.co/BAAI/bge-m3) designed for the following use case:
None
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
'fine-tuned/FiQA2018-512-192-gpt-4o-2024-05-13-11626257',
trust_remote_code=True
)
embeddings = model.encode([
'first text to embed',
'second text to embed'
])
print(cos_sim(embeddings[0], embeddings[1]))
```
|
{"datasets": ["fine-tuned/FiQA2018-512-192-gpt-4o-2024-05-13-11626257", "allenai/c4"], "language": ["en", "en"], "license": "apache-2.0", "pipeline_tag": "feature-extraction", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity", "mteb"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,579 |
omid-ebi/mt5_base_translation_fa_en
|
omid-ebi
|
translation
|
[
"transformers",
"safetensors",
"mt5",
"text2text-generation",
"translation",
"fa",
"dataset:persiannlp/parsinlu_translation_fa_en",
"arxiv:1910.09700",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-06-29T13:53:17Z |
2024-06-29T17:35:00+00:00
| 136 | 0 |
---
datasets:
- persiannlp/parsinlu_translation_fa_en
language:
- fa
library_name: transformers
license: cc-by-nc-sa-4.0
metrics:
- bleu
- chrf
- meteor
- comet
pipeline_tag: translation
---
# 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 is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| null |
Non_BioNLP
|
# 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 is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"datasets": ["persiannlp/parsinlu_translation_fa_en"], "language": ["fa"], "library_name": "transformers", "license": "cc-by-nc-sa-4.0", "metrics": ["bleu", "chrf", "meteor", "comet"], "pipeline_tag": "translation"}
|
task
|
[
"TRANSLATION"
] | 41,580 |
brahmairesearch/cerberus-v0.1
|
brahmairesearch
|
text-generation
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-06-27T19:15:08Z |
2024-06-27T23:26:38+00:00
| 14 | 1 |
---
language:
- en
library_name: transformers
license: llama3
---
# Cerberus-v0.1 Model Card
<img src="https://brahmai.in/cerberus/v0.1/cover.png" alt="Cerberus - BRAHMAI" />
## Model Details
- **Model Name:** Cerberus-v0.1
- **Company:** [BRAHMAI](https://brahmai.in)
- **Contact:** [[email protected]](mailto:[email protected])
- **Date Released:** June 2024
## Model Overview
Cerberus-v0.1 is an advanced natural language processing (NLP) model developed by BRAHMAI. It is designed to excel in a variety of NLP tasks including text generation, translation, summarization, and question answering. The model leverages a state-of-the-art transformer architecture, trained on a diverse dataset to ensure robust performance across different domains and languages.
## Intended Use
Cerberus-v0.1 is intended to be used as a versatile tool for:
- Text generation in creative writing and content creation.
- Multilingual translation services with high accuracy.
- Document summarization to extract key information efficiently.
- Question answering applications for educational and informational purposes.
## Performance Benchmarks
The performance of Cerberus-v0.1 has been evaluated across multiple benchmarks and applications:
- **Text Generation:** Achieves fluent and contextually relevant outputs suitable for various writing styles.
- **Translation:** Provides accurate translations between multiple languages, preserving the meaning and tone of the original text.
- **Summarization:** Generates concise summaries while retaining critical information from longer documents.
- **Question Answering:** Delivers precise answers to user queries based on context and available information.
## Ethical Considerations
BRAHMAI is committed to responsible AI practices:
- **Bias Mitigation:** Regular audits and bias detection measures are implemented to minimize biases in model outputs.
- **Transparency:** Clear documentation, including this model card, aims to provide users with insights into model capabilities and limitations.
- **User Safety:** Measures are in place to ensure user privacy and data security during model interactions.
## Limitations and Caveats
While Cerberus-v0.1 demonstrates strong performance in various tasks, users should be aware of:
- **Domain Specificity:** Performance may vary across different domains not extensively covered during training.
- **Contextual Limitations:** Outputs may not always reflect nuanced cultural or contextual sensitivities.
## Future Directions
Future updates to Cerberus-v0.1 may include:
- Enhanced multilingual capabilities through additional training on diverse language datasets.
- Improved fine-tuning mechanisms to adapt to specific user requirements and domains.
| null |
Non_BioNLP
|
# Cerberus-v0.1 Model Card
<img src="https://brahmai.in/cerberus/v0.1/cover.png" alt="Cerberus - BRAHMAI" />
## Model Details
- **Model Name:** Cerberus-v0.1
- **Company:** [BRAHMAI](https://brahmai.in)
- **Contact:** [[email protected]](mailto:[email protected])
- **Date Released:** June 2024
## Model Overview
Cerberus-v0.1 is an advanced natural language processing (NLP) model developed by BRAHMAI. It is designed to excel in a variety of NLP tasks including text generation, translation, summarization, and question answering. The model leverages a state-of-the-art transformer architecture, trained on a diverse dataset to ensure robust performance across different domains and languages.
## Intended Use
Cerberus-v0.1 is intended to be used as a versatile tool for:
- Text generation in creative writing and content creation.
- Multilingual translation services with high accuracy.
- Document summarization to extract key information efficiently.
- Question answering applications for educational and informational purposes.
## Performance Benchmarks
The performance of Cerberus-v0.1 has been evaluated across multiple benchmarks and applications:
- **Text Generation:** Achieves fluent and contextually relevant outputs suitable for various writing styles.
- **Translation:** Provides accurate translations between multiple languages, preserving the meaning and tone of the original text.
- **Summarization:** Generates concise summaries while retaining critical information from longer documents.
- **Question Answering:** Delivers precise answers to user queries based on context and available information.
## Ethical Considerations
BRAHMAI is committed to responsible AI practices:
- **Bias Mitigation:** Regular audits and bias detection measures are implemented to minimize biases in model outputs.
- **Transparency:** Clear documentation, including this model card, aims to provide users with insights into model capabilities and limitations.
- **User Safety:** Measures are in place to ensure user privacy and data security during model interactions.
## Limitations and Caveats
While Cerberus-v0.1 demonstrates strong performance in various tasks, users should be aware of:
- **Domain Specificity:** Performance may vary across different domains not extensively covered during training.
- **Contextual Limitations:** Outputs may not always reflect nuanced cultural or contextual sensitivities.
## Future Directions
Future updates to Cerberus-v0.1 may include:
- Enhanced multilingual capabilities through additional training on diverse language datasets.
- Improved fine-tuning mechanisms to adapt to specific user requirements and domains.
|
{"language": ["en"], "library_name": "transformers", "license": "llama3"}
|
task
|
[
"QUESTION_ANSWERING",
"TRANSLATION",
"SUMMARIZATION"
] | 41,581 |
kimhyeonseo/t5-small-custom
|
kimhyeonseo
| null |
[
"safetensors",
"t5",
"region:us"
] | 2024-09-20T03:46:23Z |
2024-09-20T03:46:31+00:00
| 5 | 0 |
---
{}
---
#
# Model Card for t5_small Summarization Model
fine-tuned version of t5_small for summarization
## Model Details
trained on CNN/Daily mail dataset
## Training Data
CNN/Daily mail dataset
## Training Procedure
- **Learning Rate**: 2e-5
- **Epochs**: 1
- **Batch Size**: 4
## How to Use
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("t5_small")
model = AutoModelForSeq2SeqLM.from_pretrained("t5_small")
input_text = "The movie was fantastic with a gripping storyline!"
inputs = tokenizer.encode(input_text, return_tensors="pt")
outputs = model(inputs)
print(outputs.logits)
```
## Evaluation
eval_rouge1: 32.13
eval_rouge2: 11.85
eval_rougeL: 23.13
eval_bleu1: 29.29
eval_bleu2: 10.02
eval_bleu4: 3.83
## Limitations
bad performance
## Ethical Considerations
model has bias by cnn dataset
| null |
Non_BioNLP
|
#
# Model Card for t5_small Summarization Model
fine-tuned version of t5_small for summarization
## Model Details
trained on CNN/Daily mail dataset
## Training Data
CNN/Daily mail dataset
## Training Procedure
- **Learning Rate**: 2e-5
- **Epochs**: 1
- **Batch Size**: 4
## How to Use
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("t5_small")
model = AutoModelForSeq2SeqLM.from_pretrained("t5_small")
input_text = "The movie was fantastic with a gripping storyline!"
inputs = tokenizer.encode(input_text, return_tensors="pt")
outputs = model(inputs)
print(outputs.logits)
```
## Evaluation
eval_rouge1: 32.13
eval_rouge2: 11.85
eval_rougeL: 23.13
eval_bleu1: 29.29
eval_bleu2: 10.02
eval_bleu4: 3.83
## Limitations
bad performance
## Ethical Considerations
model has bias by cnn dataset
|
{}
|
task
|
[
"SUMMARIZATION"
] | 41,582 |
watiforall/distilbert-base-uncased-finetuned-rte
|
watiforall
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-03-07T14:22:53Z |
2024-03-07T14:45:31+00:00
| 11 | 0 |
---
datasets:
- glue
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-rte
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
args: rte
metrics:
- type: accuracy
value: 0.6462093862815884
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. -->
# distilbert-base-uncased-finetuned-rte
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7189
- Accuracy: 0.6462
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 156 | 0.7021 | 0.4982 |
| No log | 2.0 | 312 | 0.6693 | 0.5993 |
| No log | 3.0 | 468 | 0.6689 | 0.6426 |
| 0.6061 | 4.0 | 624 | 0.7189 | 0.6462 |
| 0.6061 | 5.0 | 780 | 0.7873 | 0.6426 |
### Framework versions
- Transformers 4.16.2
- Pytorch 2.1.0+cu121
- Datasets 1.16.1
- Tokenizers 0.15.2
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetuned-rte
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7189
- Accuracy: 0.6462
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 156 | 0.7021 | 0.4982 |
| No log | 2.0 | 312 | 0.6693 | 0.5993 |
| No log | 3.0 | 468 | 0.6689 | 0.6426 |
| 0.6061 | 4.0 | 624 | 0.7189 | 0.6462 |
| 0.6061 | 5.0 | 780 | 0.7873 | 0.6426 |
### Framework versions
- Transformers 4.16.2
- Pytorch 2.1.0+cu121
- Datasets 1.16.1
- Tokenizers 0.15.2
|
{"datasets": ["glue"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetuned-rte", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "args": "rte"}, "metrics": [{"type": "accuracy", "value": 0.6462093862815884, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,583 |
gokulsrinivasagan/bert_base_lda_100_v1_mnli
|
gokulsrinivasagan
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokulsrinivasagan/bert_base_lda_100_v1",
"base_model:finetune:gokulsrinivasagan/bert_base_lda_100_v1",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-11-26T19:56:36Z |
2024-12-04T14:51:41+00:00
| 7 | 0 |
---
base_model: gokulsrinivasagan/bert_base_lda_100_v1
datasets:
- glue
language:
- en
library_name: transformers
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: bert_base_lda_100_v1_mnli
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- type: accuracy
value: 0.7162327095199349
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. -->
# bert_base_lda_100_v1_mnli
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6799
- Accuracy: 0.7162
## 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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.9588 | 1.0 | 1534 | 0.8420 | 0.6249 |
| 0.7857 | 2.0 | 3068 | 0.7451 | 0.6808 |
| 0.6825 | 3.0 | 4602 | 0.7162 | 0.6976 |
| 0.5973 | 4.0 | 6136 | 0.7056 | 0.7113 |
| 0.5208 | 5.0 | 7670 | 0.7460 | 0.7144 |
| 0.4464 | 6.0 | 9204 | 0.7907 | 0.7078 |
| 0.3775 | 7.0 | 10738 | 0.8362 | 0.7172 |
| 0.316 | 8.0 | 12272 | 0.9463 | 0.7101 |
| 0.2617 | 9.0 | 13806 | 1.0094 | 0.7111 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
| null |
Non_BioNLP
|
<!-- 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. -->
# bert_base_lda_100_v1_mnli
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6799
- Accuracy: 0.7162
## 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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.9588 | 1.0 | 1534 | 0.8420 | 0.6249 |
| 0.7857 | 2.0 | 3068 | 0.7451 | 0.6808 |
| 0.6825 | 3.0 | 4602 | 0.7162 | 0.6976 |
| 0.5973 | 4.0 | 6136 | 0.7056 | 0.7113 |
| 0.5208 | 5.0 | 7670 | 0.7460 | 0.7144 |
| 0.4464 | 6.0 | 9204 | 0.7907 | 0.7078 |
| 0.3775 | 7.0 | 10738 | 0.8362 | 0.7172 |
| 0.316 | 8.0 | 12272 | 0.9463 | 0.7101 |
| 0.2617 | 9.0 | 13806 | 1.0094 | 0.7111 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
|
{"base_model": "gokulsrinivasagan/bert_base_lda_100_v1", "datasets": ["glue"], "language": ["en"], "library_name": "transformers", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "bert_base_lda_100_v1_mnli", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE MNLI", "type": "glue", "args": "mnli"}, "metrics": [{"type": "accuracy", "value": 0.7162327095199349, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,584 |
mohammedbriman/distilbert-base-uncased-finetuned-cola
|
mohammedbriman
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-11-10T19:05:56Z |
2022-11-10T19:16:56+00:00
| 16 | 0 |
---
datasets:
- glue
license: apache-2.0
metrics:
- matthews_correlation
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-cola
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
config: cola
split: train
args: cola
metrics:
- type: matthews_correlation
value: 0.538017794243896
name: Matthews Correlation
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7303
- Matthews Correlation: 0.5380
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.2672 | 1.0 | 535 | 0.6988 | 0.4674 |
| 0.2414 | 2.0 | 1070 | 0.6748 | 0.4729 |
| 0.1682 | 3.0 | 1605 | 0.7303 | 0.5380 |
| 0.1415 | 4.0 | 2140 | 0.9895 | 0.4806 |
| 0.0971 | 5.0 | 2675 | 0.9933 | 0.5321 |
### Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2
| null |
Non_BioNLP
|
<!-- 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. -->
# distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7303
- Matthews Correlation: 0.5380
## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.2672 | 1.0 | 535 | 0.6988 | 0.4674 |
| 0.2414 | 2.0 | 1070 | 0.6748 | 0.4729 |
| 0.1682 | 3.0 | 1605 | 0.7303 | 0.5380 |
| 0.1415 | 4.0 | 2140 | 0.9895 | 0.4806 |
| 0.0971 | 5.0 | 2675 | 0.9933 | 0.5321 |
### Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2
|
{"datasets": ["glue"], "license": "apache-2.0", "metrics": ["matthews_correlation"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-finetuned-cola", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "config": "cola", "split": "train", "args": "cola"}, "metrics": [{"type": "matthews_correlation", "value": 0.538017794243896, "name": "Matthews Correlation"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,586 |
Helsinki-NLP/opus-mt-tc-base-uk-tr
|
Helsinki-NLP
|
translation
|
[
"transformers",
"pytorch",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"tr",
"uk",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-24T07:33:55Z |
2023-10-10T21:40:09+00:00
| 25 | 0 |
---
language:
- tr
- uk
license: cc-by-4.0
tags:
- translation
- opus-mt-tc
model-index:
- name: opus-mt-tc-base-uk-tr
results:
- task:
type: translation
name: Translation ukr-tur
dataset:
name: flores101-devtest
type: flores_101
args: ukr tur devtest
metrics:
- type: bleu
value: 20.5
name: BLEU
- task:
type: translation
name: Translation ukr-tur
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ukr-tur
metrics:
- type: bleu
value: 45.2
name: BLEU
---
# opus-mt-tc-base-uk-tr
Neural machine translation model for translating from Ukrainian (uk) to Turkish (tr).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-07
* source language(s): ukr
* target language(s):
* valid target language labels:
* model: transformer-align
* data: opusTCv20210807+pft ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+pft_transformer-align_2022-03-07.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-tur/opusTCv20210807+pft_transformer-align_2022-03-07.zip)
* more information released models: [OPUS-MT ukr-tur README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ukr-tur/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>><<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>tur<< Тисячі єн достатньо?",
">>tur<< Цюріх — місто у Швейцарії."
]
model_name = "pytorch-models/opus-mt-tc-base-uk-tr"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Binlerce yen yeterli mi?
# Zürih, İsviçre'de bir şehirdir.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-base-uk-tr")
print(pipe(">>tur<< Тисячі єн достатньо?"))
# expected output: Binlerce yen yeterli mi?
```
## Benchmarks
* test set translations: [opusTCv20210807+pft_transformer-align_2022-03-07.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-tur/opusTCv20210807+pft_transformer-align_2022-03-07.test.txt)
* test set scores: [opusTCv20210807+pft_transformer-align_2022-03-07.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-tur/opusTCv20210807+pft_transformer-align_2022-03-07.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| ukr-tur | tatoeba-test-v2021-08-07 | 0.70938 | 45.2 | 2520 | 11927 |
| ukr-tur | flores101-devtest | 0.54001 | 20.5 | 1012 | 20253 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Wed Mar 23 22:02:24 EET 2022
* port machine: LM0-400-22516.local
| null |
Non_BioNLP
|
# opus-mt-tc-base-uk-tr
Neural machine translation model for translating from Ukrainian (uk) to Turkish (tr).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-07
* source language(s): ukr
* target language(s):
* valid target language labels:
* model: transformer-align
* data: opusTCv20210807+pft ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+pft_transformer-align_2022-03-07.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-tur/opusTCv20210807+pft_transformer-align_2022-03-07.zip)
* more information released models: [OPUS-MT ukr-tur README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ukr-tur/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>><<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>tur<< Тисячі єн достатньо?",
">>tur<< Цюріх — місто у Швейцарії."
]
model_name = "pytorch-models/opus-mt-tc-base-uk-tr"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Binlerce yen yeterli mi?
# Zürih, İsviçre'de bir şehirdir.
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-base-uk-tr")
print(pipe(">>tur<< Тисячі єн достатньо?"))
# expected output: Binlerce yen yeterli mi?
```
## Benchmarks
* test set translations: [opusTCv20210807+pft_transformer-align_2022-03-07.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-tur/opusTCv20210807+pft_transformer-align_2022-03-07.test.txt)
* test set scores: [opusTCv20210807+pft_transformer-align_2022-03-07.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-tur/opusTCv20210807+pft_transformer-align_2022-03-07.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| ukr-tur | tatoeba-test-v2021-08-07 | 0.70938 | 45.2 | 2520 | 11927 |
| ukr-tur | flores101-devtest | 0.54001 | 20.5 | 1012 | 20253 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: 1bdabf7
* port time: Wed Mar 23 22:02:24 EET 2022
* port machine: LM0-400-22516.local
|
{"language": ["tr", "uk"], "license": "cc-by-4.0", "tags": ["translation", "opus-mt-tc"], "model-index": [{"name": "opus-mt-tc-base-uk-tr", "results": [{"task": {"type": "translation", "name": "Translation ukr-tur"}, "dataset": {"name": "flores101-devtest", "type": "flores_101", "args": "ukr tur devtest"}, "metrics": [{"type": "bleu", "value": 20.5, "name": "BLEU"}]}, {"task": {"type": "translation", "name": "Translation ukr-tur"}, "dataset": {"name": "tatoeba-test-v2021-08-07", "type": "tatoeba_mt", "args": "ukr-tur"}, "metrics": [{"type": "bleu", "value": 45.2, "name": "BLEU"}]}]}]}
|
task
|
[
"TRANSLATION"
] | 41,587 |
Helsinki-NLP/opus-mt-az-tr
|
Helsinki-NLP
|
translation
|
[
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"az",
"tr",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2023-08-16T11:25:56+00:00
| 36 | 1 |
---
language:
- az
- tr
license: apache-2.0
tags:
- translation
---
### aze-tur
* source group: Azerbaijani
* target group: Turkish
* OPUS readme: [aze-tur](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/aze-tur/README.md)
* model: transformer-align
* source language(s): aze_Latn
* target language(s): tur
* model: transformer-align
* pre-processing: normalization + SentencePiece (spm4k,spm4k)
* download original weights: [opus-2020-06-16.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.zip)
* test set translations: [opus-2020-06-16.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.test.txt)
* test set scores: [opus-2020-06-16.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba-test.aze.tur | 24.4 | 0.529 |
### System Info:
- hf_name: aze-tur
- source_languages: aze
- target_languages: tur
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/aze-tur/README.md
- original_repo: Tatoeba-Challenge
- tags: ['translation']
- languages: ['az', 'tr']
- src_constituents: {'aze_Latn'}
- tgt_constituents: {'tur'}
- src_multilingual: False
- tgt_multilingual: False
- prepro: normalization + SentencePiece (spm4k,spm4k)
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.zip
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.test.txt
- src_alpha3: aze
- tgt_alpha3: tur
- short_pair: az-tr
- chrF2_score: 0.529
- bleu: 24.4
- brevity_penalty: 0.956
- ref_len: 5380.0
- src_name: Azerbaijani
- tgt_name: Turkish
- train_date: 2020-06-16
- src_alpha2: az
- tgt_alpha2: tr
- prefer_old: False
- long_pair: aze-tur
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
- port_machine: brutasse
- port_time: 2020-08-21-14:41
| null |
Non_BioNLP
|
### aze-tur
* source group: Azerbaijani
* target group: Turkish
* OPUS readme: [aze-tur](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/aze-tur/README.md)
* model: transformer-align
* source language(s): aze_Latn
* target language(s): tur
* model: transformer-align
* pre-processing: normalization + SentencePiece (spm4k,spm4k)
* download original weights: [opus-2020-06-16.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.zip)
* test set translations: [opus-2020-06-16.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.test.txt)
* test set scores: [opus-2020-06-16.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba-test.aze.tur | 24.4 | 0.529 |
### System Info:
- hf_name: aze-tur
- source_languages: aze
- target_languages: tur
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/aze-tur/README.md
- original_repo: Tatoeba-Challenge
- tags: ['translation']
- languages: ['az', 'tr']
- src_constituents: {'aze_Latn'}
- tgt_constituents: {'tur'}
- src_multilingual: False
- tgt_multilingual: False
- prepro: normalization + SentencePiece (spm4k,spm4k)
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.zip
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/aze-tur/opus-2020-06-16.test.txt
- src_alpha3: aze
- tgt_alpha3: tur
- short_pair: az-tr
- chrF2_score: 0.529
- bleu: 24.4
- brevity_penalty: 0.956
- ref_len: 5380.0
- src_name: Azerbaijani
- tgt_name: Turkish
- train_date: 2020-06-16
- src_alpha2: az
- tgt_alpha2: tr
- prefer_old: False
- long_pair: aze-tur
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
- port_machine: brutasse
- port_time: 2020-08-21-14:41
|
{"language": ["az", "tr"], "license": "apache-2.0", "tags": ["translation"]}
|
task
|
[
"TRANSLATION"
] | 41,588 |
NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity
|
NazmusAshrafi
|
text-classification
|
[
"setfit",
"safetensors",
"mpnet",
"absa",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:sentence-transformers/paraphrase-mpnet-base-v2",
"base_model:finetune:sentence-transformers/paraphrase-mpnet-base-v2",
"model-index",
"region:us"
] | 2024-01-28T12:16:44Z |
2024-01-28T16:45:45+00:00
| 6 | 0 |
---
base_model: sentence-transformers/paraphrase-mpnet-base-v2
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- absa
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: ; got my car in about a:Well.. I added a new 🐎 to the stable! Special thanks
to Matt at the @Tesla Clarkston location who made my Model Y order & delivery
incredibly smooth.🙏 I'm super lucky & got my car in about a week of deciding
to go for it 😳 Video coming soon about that process & more! https://t.co/PrP91xMnKk
- text: '. But the price could be cheaper:C’mon @elonmusk! Australians are busting
to buy EVs & the best one is @Tesla imho. But the price could be cheaper,
if you built a #gigafactory in Australia. 70% of the lithium in the cars is #aussie
so why not set up a #gigafactorydownunder? All the talent and minerals are here!'
- text: 'generate more net profit from legacy auto:As with previous quarters, $TSLA
will generate more net profit from legacy auto regulatory credits sales this quarter
than legacy auto will make in gross profit by selling EVs.
This just keeps adding insult to injury.'
- text: on keeping this car for 10 years:@_brivnii @Tesla I plan on keeping this car
for 10 years total (so 6 more years at least). I don't feel the need to upgrade
to a newer model even if price is no issue. This one has been reliable, and I
got a good battery (no signs of degradation so far)
- text: "The driver’s car was a @Tesla:I took an @Uber home from the airport and my\
\ bill had a fuel surcharge on it because of the current price of gasoline. \n\
\nThe driver’s car was a @Tesla… \U0001F937"
inference: false
model-index:
- name: SetFit Polarity Model with sentence-transformers/paraphrase-mpnet-base-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.44
name: Accuracy
---
# SetFit Polarity Model with sentence-transformers/paraphrase-mpnet-base-v2
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of classifying aspect polarities.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
This model was trained within the context of a larger system for ABSA, which looks like so:
1. Use a spaCy model to select possible aspect span candidates.
2. Use a SetFit model to filter these possible aspect span candidates.
3. **Use this SetFit model to classify the filtered aspect span candidates.**
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **spaCy Model:** en_core_web_lg
- **SetFitABSA Aspect Model:** [NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect](https://huggingface.co/NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect)
- **SetFitABSA Polarity Model:** [NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity](https://huggingface.co/NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity)
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 3 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:---------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| neutral | <ul><li>"i.e. just more profit for $TSLA:I'm pretty sure, all an EV tax incentive will do, is raise the price of Teslas, at least for the next few years.\n\ni.e. just more profit for $TSLA\nAs if demand wasn't abundant enough already."</li><li>"increase also increase profit and Tesla the:C'mon @SaraEisen you know as well as I do that the price increases in $TSLA vehicles is not related to any weakness in the stock today. It's purely macro today. Plus, price increase also increase profit and Tesla the only Auto maker that is making high margins on sales."</li><li>"when choosing a car. They just:The key thing people get wrong when thinking EV competition is bad for Tesla:\n\nVast majority of consumers aren't prioritizing the environment when choosing a car. They just want the best product & technology, which Tesla offers and just happens to be an EV\n\n$TSLA https://t.co/w3cKqeJkQW"</li></ul> |
| negative | <ul><li>"is raise the price of Teslas,:I'm pretty sure, all an EV tax incentive will do, is raise the price of Teslas, at least for the next few years.\n\ni.e. just more profit for $TSLA\nAs if demand wasn't abundant enough already."</li><li>'"The price of batteries for:"The price of batteries for electric vehicles looks set to rise in 2022 after many years of sharp decline. The supplies of lithium and other raw materials fail to keep up with huge demand." $NIO $TSLA $XPEV $LI\n\nhttps://t.co/2CAJCxTC2C'</li><li>'. But the price could be cheaper:C’mon @elonmusk! Australians are busting to buy EVs & the best one is @Tesla imho. But the price could be cheaper, if you built a #gigafactory in Australia. 70% of the lithium in the cars is #aussie so why not set up a #gigafactorydownunder? All the talent and minerals are here!'</li></ul> |
| positive | <ul><li>'a $30k car with $70k:John Hennessey gets a $TSLA Plaid. \nA retired OEM executive describes Tesla as a $30k car with $70k in batteries. \nThe perfect description of a Tesla https://t.co/m5J5m3AuMJ'</li><li>"want the best product &:The key thing people get wrong when thinking EV competition is bad for Tesla:\n\nVast majority of consumers aren't prioritizing the environment when choosing a car. They just want the best product & technology, which Tesla offers and just happens to be an EV\n\n$TSLA https://t.co/w3cKqeJkQW"</li><li>"the most important product on Earth;:Tesla's 4680 battery (and it's manufactuing process) will end up being the most important product on Earth; it's that important. It will enable massive scale & cost reductions over time. It will enable faster charging times & longer range EVs, both will drive adoption.\n\n$TSLA"</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.44 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import AbsaModel
# Download from the 🤗 Hub
model = AbsaModel.from_pretrained(
"NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect",
"NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity",
)
# Run inference
preds = model("The food was great, but the venue is just way too busy.")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### 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.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 26 | 46.2121 | 61 |
| Label | Training Sample Count |
|:---------|:----------------------|
| negative | 11 |
| neutral | 12 |
| positive | 10 |
### Training Hyperparameters
- batch_size: (16, 2)
- num_epochs: (1, 16)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.0217 | 1 | 0.186 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- spaCy: 3.6.1
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## 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.*
-->
| null |
Non_BioNLP
|
# SetFit Polarity Model with sentence-transformers/paraphrase-mpnet-base-v2
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of classifying aspect polarities.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
This model was trained within the context of a larger system for ABSA, which looks like so:
1. Use a spaCy model to select possible aspect span candidates.
2. Use a SetFit model to filter these possible aspect span candidates.
3. **Use this SetFit model to classify the filtered aspect span candidates.**
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **spaCy Model:** en_core_web_lg
- **SetFitABSA Aspect Model:** [NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect](https://huggingface.co/NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect)
- **SetFitABSA Polarity Model:** [NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity](https://huggingface.co/NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity)
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 3 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:---------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| neutral | <ul><li>"i.e. just more profit for $TSLA:I'm pretty sure, all an EV tax incentive will do, is raise the price of Teslas, at least for the next few years.\n\ni.e. just more profit for $TSLA\nAs if demand wasn't abundant enough already."</li><li>"increase also increase profit and Tesla the:C'mon @SaraEisen you know as well as I do that the price increases in $TSLA vehicles is not related to any weakness in the stock today. It's purely macro today. Plus, price increase also increase profit and Tesla the only Auto maker that is making high margins on sales."</li><li>"when choosing a car. They just:The key thing people get wrong when thinking EV competition is bad for Tesla:\n\nVast majority of consumers aren't prioritizing the environment when choosing a car. They just want the best product & technology, which Tesla offers and just happens to be an EV\n\n$TSLA https://t.co/w3cKqeJkQW"</li></ul> |
| negative | <ul><li>"is raise the price of Teslas,:I'm pretty sure, all an EV tax incentive will do, is raise the price of Teslas, at least for the next few years.\n\ni.e. just more profit for $TSLA\nAs if demand wasn't abundant enough already."</li><li>'"The price of batteries for:"The price of batteries for electric vehicles looks set to rise in 2022 after many years of sharp decline. The supplies of lithium and other raw materials fail to keep up with huge demand." $NIO $TSLA $XPEV $LI\n\nhttps://t.co/2CAJCxTC2C'</li><li>'. But the price could be cheaper:C’mon @elonmusk! Australians are busting to buy EVs & the best one is @Tesla imho. But the price could be cheaper, if you built a #gigafactory in Australia. 70% of the lithium in the cars is #aussie so why not set up a #gigafactorydownunder? All the talent and minerals are here!'</li></ul> |
| positive | <ul><li>'a $30k car with $70k:John Hennessey gets a $TSLA Plaid. \nA retired OEM executive describes Tesla as a $30k car with $70k in batteries. \nThe perfect description of a Tesla https://t.co/m5J5m3AuMJ'</li><li>"want the best product &:The key thing people get wrong when thinking EV competition is bad for Tesla:\n\nVast majority of consumers aren't prioritizing the environment when choosing a car. They just want the best product & technology, which Tesla offers and just happens to be an EV\n\n$TSLA https://t.co/w3cKqeJkQW"</li><li>"the most important product on Earth;:Tesla's 4680 battery (and it's manufactuing process) will end up being the most important product on Earth; it's that important. It will enable massive scale & cost reductions over time. It will enable faster charging times & longer range EVs, both will drive adoption.\n\n$TSLA"</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.44 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import AbsaModel
# Download from the 🤗 Hub
model = AbsaModel.from_pretrained(
"NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect",
"NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity",
)
# Run inference
preds = model("The food was great, but the venue is just way too busy.")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### 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.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 26 | 46.2121 | 61 |
| Label | Training Sample Count |
|:---------|:----------------------|
| negative | 11 |
| neutral | 12 |
| positive | 10 |
### Training Hyperparameters
- batch_size: (16, 2)
- num_epochs: (1, 16)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.0217 | 1 | 0.186 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- spaCy: 3.6.1
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## 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.*
-->
|
{"base_model": "sentence-transformers/paraphrase-mpnet-base-v2", "library_name": "setfit", "metrics": ["accuracy"], "pipeline_tag": "text-classification", "tags": ["setfit", "absa", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "widget": [{"text": "; got my car in about a:Well.. I added a new 🐎 to the stable! Special thanks to Matt at the @Tesla Clarkston location who made my Model Y order & delivery incredibly smooth.🙏 I'm super lucky & got my car in about a week of deciding to go for it 😳 Video coming soon about that process & more! https://t.co/PrP91xMnKk"}, {"text": ". But the price could be cheaper:C’mon @elonmusk! Australians are busting to buy EVs & the best one is @Tesla imho. But the price could be cheaper, if you built a #gigafactory in Australia. 70% of the lithium in the cars is #aussie so why not set up a #gigafactorydownunder? All the talent and minerals are here!"}, {"text": "generate more net profit from legacy auto:As with previous quarters, $TSLA will generate more net profit from legacy auto regulatory credits sales this quarter than legacy auto will make in gross profit by selling EVs.\n\nThis just keeps adding insult to injury."}, {"text": "on keeping this car for 10 years:@_brivnii @Tesla I plan on keeping this car for 10 years total (so 6 more years at least). I don't feel the need to upgrade to a newer model even if price is no issue. This one has been reliable, and I got a good battery (no signs of degradation so far)"}, {"text": "The driver’s car was a @Tesla:I took an @Uber home from the airport and my bill had a fuel surcharge on it because of the current price of gasoline. \n\nThe driver’s car was a @Tesla… 🤷"}], "inference": false, "model-index": [{"name": "SetFit Polarity Model with sentence-transformers/paraphrase-mpnet-base-v2", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "Unknown", "type": "unknown", "split": "test"}, "metrics": [{"type": "accuracy", "value": 0.44, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,589 |
keess/whisper-model-internal
|
keess
|
automatic-speech-recognition
|
[
"transformers",
"pytorch",
"tf",
"whisper",
"automatic-speech-recognition",
"audio",
"hf-asr-leaderboard",
"en",
"zh",
"de",
"es",
"ru",
"ko",
"fr",
"ja",
"pt",
"tr",
"pl",
"ca",
"nl",
"ar",
"sv",
"it",
"id",
"hi",
"fi",
"vi",
"iw",
"uk",
"el",
"ms",
"cs",
"ro",
"da",
"hu",
"ta",
"no",
"th",
"ur",
"hr",
"bg",
"lt",
"la",
"mi",
"ml",
"cy",
"sk",
"te",
"fa",
"lv",
"bn",
"sr",
"az",
"sl",
"kn",
"et",
"mk",
"br",
"eu",
"is",
"hy",
"ne",
"mn",
"bs",
"kk",
"sq",
"sw",
"gl",
"mr",
"pa",
"si",
"km",
"sn",
"yo",
"so",
"af",
"oc",
"ka",
"be",
"tg",
"sd",
"gu",
"am",
"yi",
"lo",
"uz",
"fo",
"ht",
"ps",
"tk",
"nn",
"mt",
"sa",
"lb",
"my",
"bo",
"tl",
"mg",
"as",
"tt",
"haw",
"ln",
"ha",
"ba",
"jw",
"su",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | 2023-01-21T13:19:18Z |
2023-01-24T13:49:02+00:00
| 28 | 0 |
---
language:
- en
- zh
- de
- es
- ru
- ko
- fr
- ja
- pt
- tr
- pl
- ca
- nl
- ar
- sv
- it
- id
- hi
- fi
- vi
- iw
- uk
- el
- ms
- cs
- ro
- da
- hu
- ta
- 'no'
- th
- ur
- hr
- bg
- lt
- la
- mi
- ml
- cy
- sk
- te
- fa
- lv
- bn
- sr
- az
- sl
- kn
- et
- mk
- br
- eu
- is
- hy
- ne
- mn
- bs
- kk
- sq
- sw
- gl
- mr
- pa
- si
- km
- sn
- yo
- so
- af
- oc
- ka
- be
- tg
- sd
- gu
- am
- yi
- lo
- uz
- fo
- ht
- ps
- tk
- nn
- mt
- sa
- lb
- my
- bo
- tl
- mg
- as
- tt
- haw
- ln
- ha
- ba
- jw
- su
license: apache-2.0
pipeline_tag: automatic-speech-recognition
tags:
- audio
- automatic-speech-recognition
- hf-asr-leaderboard
widget:
- example_title: Librispeech sample 1
src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
- example_title: Librispeech sample 2
src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
duplicated_from: openai/whisper-large
model-index:
- name: whisper-large
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: LibriSpeech (clean)
type: librispeech_asr
config: clean
split: test
args:
language: en
metrics:
- type: wer
value: 3
name: Test WER
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: LibriSpeech (other)
type: librispeech_asr
config: other
split: test
args:
language: en
metrics:
- type: wer
value: 5.4
name: Test WER
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: hi
split: test
args:
language: hi
metrics:
- type: wer
value: 54.8
name: Test WER
---
# Whisper
[OpenAI's Whisper](https://openai.com/blog/whisper/)
The Whisper model was proposed in [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf) by Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever.
**Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the original model card.
## Intro
The first paragraphs of the abstract read as follows :
> We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zeroshot transfer setting without the need for any finetuning.
> When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.
The original code repository can be found [here](https://github.com/openai/whisper).
## Model details
The Whisper models are trained for speech recognition and translation tasks, capable of transcribing speech audio into the text in the language it is spoken (ASR) as well as translated into English (speech translation). Researchers at OpenAI developed the models to study the robustness of speech processing systems trained under large-scale weak supervision. There are 9 models of different sizes and capabilities, summarised in the following table.
| Size | Parameters | English-only model | Multilingual model |
|:------:|:----------:|:------------------:|:------------------:|
| tiny | 39 M | ✓ | ✓ |
| base | 74 M | ✓ | ✓ |
| small | 244 M | ✓ | ✓ |
| medium | 769 M | ✓ | ✓ |
| large | 1550 M | | ✓ |
## Model description
Whisper is an auto-regressive automatic speech recognition encoder-decoder model that was trained on 680 000 hours of 16kHz sampled multilingual audio. It was fully trained in a supervised manner, with multiple tasks :
- English transcription
- Any-to-English speech translation
- Non-English transcription
- No speech prediction
To each task corresponds a sequence of tokens that are given to the decoder as *context tokens*. The beginning of a transcription always starts with `<|startoftranscript|>` which is why the `decoder_start_token` is always set to `tokenizer.encode("<|startoftranscript|>")`. The following token should be the language token, which is automatically detected in the original code. Finally, the task is define using either `<|transcribe|>` or `<|translate|>`. In addition, a `<|notimestamps|>` token is added if the task does not include timestamp prediction.
# Usage
To transcribe or translate audio files, the model has to be used along a `WhisperProcessor`. The `WhisperProcessor.get_decoder_prompt_ids` function is used to get a list of `( idx, token )` tuples, which can either be set in the config, or directly passed to the generate function, as `forced_decoder_ids`.
## Transcription
In the following example, the english only model is used. We set the `decoder_input_ids` accordingly.
### English to english
The "<|en|>" token is used to specify that the speech is in english and should be transcribed to english
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> import torch
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
>>> # load dummy dataset and read soundfiles
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> input_features = processor(ds[0]["audio"]["array"], return_tensors="pt").input_features
>>> # Generate logits
>>> logits = model(input_features, decoder_input_ids = torch.tensor([[50258]])).logits
>>> # take argmax and decode
>>> predicted_ids = torch.argmax(logits, dim=-1)
>>> transcription = processor.batch_decode(predicted_ids)
['<|en|>']
```
### French to French
In order to obtain the full transcription, the `generate()` function is used. The following example demonstrates a french to french
transcription.
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> import torch
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
>>> # load dummy dataset and read soundfiles
>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
>>> ds = ds.cast_column("audio", datasets.Audio(sampling_rate=16_000))
>>> input_speech = next(iter(ds))["audio"]["array"]
>>> model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language = "fr", task = "transcribe")
>>> input_features = processor(input_speech, return_tensors="pt").input_features
>>> predicted_ids = model.generate(input_features)
>>> transcription = processor.batch_decode(predicted_ids)
['<|startoftranscript|><|fr|><|transcribe|><|notimestamps|> Un vrai travail intéressant va enfin être mené sur ce sujet.<|endoftext|>']
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens = True)
[' Un vrai travail intéressant va enfin être mené sur ce sujet.']
```
## Translation
The "<|translate|>" is used as the first decoder input token to specify the transcription task.
### French to English
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> import torch
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
>>> # load dummy dataset and read soundfiles
>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
>>> ds = ds.cast_column("audio", datasets.Audio(sampling_rate=16_000))
>>> input_speech = next(iter(ds))["audio"]["array"]
>>> # tokenize
>>> input_features = processor(input_speech, return_tensors="pt").input_features
>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language = "fr", task = "translate")
>>> predicted_ids = model.generate(input_features, forced_decoder_ids = forced_decoder_ids)
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens = True)
[' A real interesting work will be done on this subject.']
```
## Evaluation
This code snippet shows how to evaluate **openai/whisper-large** on LibriSpeech's "clean" and "other" test data.
```python
>>> from datasets import load_dataset
>>> from transformers import WhisperForConditionalGeneration, WhisperProcessor
>>> import soundfile as sf
>>> import torch
>>> from jiwer import wer
>>> librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large").to("cuda")
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
>>> def map_to_pred(batch):
>>> input_features = processor(batch["audio"]["array"], return_tensors="pt").input_features
>>> with torch.no_grad():
>>> logits = model(input_features.to("cuda")).logits
>>> predicted_ids = torch.argmax(logits, dim=-1)
>>> transcription = processor.batch_decode(predicted_ids, normalize = True)
>>> batch['text'] = processor.tokenizer._normalize(batch['text'])
>>> batch["transcription"] = transcription
>>> return batch
>>> result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["speech"])
>>> print("WER:", wer(result["text"], result["transcription"]))
0.030003583080317572
```
### Evaluated Use
The primary intended users of these models are AI researchers studying robustness, generalization, capabilities, biases, and constraints of the current model. However, Whisper is also potentially quite useful as an ASR solution for developers, especially for English speech recognition. We recognize that once models are released, it is impossible to restrict access to only “intended” uses or to draw reasonable guidelines around what is or is not research.
The models are primarily trained and evaluated on ASR and speech translation to English tasks. They show strong ASR results in ~10 languages. They may exhibit additional capabilities, particularly if fine-tuned on certain tasks like voice activity detection, speaker classification, or speaker diarization but have not been robustly evaluated in these areas. We strongly recommend that users perform robust evaluations of the models in a particular context and domain before deploying them.
In particular, we caution against using Whisper models to transcribe recordings of individuals taken without their consent or purporting to use these models for any kind of subjective classification. We recommend against use in high-risk domains like decision-making contexts, where flaws in accuracy can lead to pronounced flaws in outcomes. The models are intended to transcribe and translate speech, use of the model for classification is not only not evaluated but also not appropriate, particularly to infer human attributes.
## Training Data
The models are trained on 680,000 hours of audio and the corresponding transcripts collected from the internet. 65% of this data (or 438,000 hours) represents English-language audio and matched English transcripts, roughly 18% (or 126,000 hours) represents non-English audio and English transcripts, while the final 17% (or 117,000 hours) represents non-English audio and the corresponding transcript. This non-English data represents 98 different languages.
As discussed in [the accompanying paper](https://cdn.openai.com/papers/whisper.pdf), we see that performance on transcription in a given language is directly correlated with the amount of training data we employ in that language.
## Performance and Limitations
Our studies show that, over many existing ASR systems, the models exhibit improved robustness to accents, background noise, technical language, as well as zero shot translation from multiple languages into English; and that accuracy on speech recognition and translation is near the state-of-the-art level.
However, because the models are trained in a weakly supervised manner using large-scale noisy data, the predictions may include texts that are not actually spoken in the audio input (i.e. hallucination). We hypothesize that this happens because, given their general knowledge of language, the models combine trying to predict the next word in audio with trying to transcribe the audio itself.
Our models perform unevenly across languages, and we observe lower accuracy on low-resource and/or low-discoverability languages or languages where we have less training data. The models also exhibit disparate performance on different accents and dialects of particular languages, which may include higher word error rate across speakers of different genders, races, ages, or other demographic criteria. Our full evaluation results are presented in [the paper accompanying this release](https://cdn.openai.com/papers/whisper.pdf).
In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. Further analysis on these limitations are provided in [the paper](https://cdn.openai.com/papers/whisper.pdf). It is likely that this behavior and hallucinations may be worse on lower-resource and/or lower-discoverability languages.
## Broader Implications
We anticipate that Whisper models’ transcription capabilities may be used for improving accessibility tools. While Whisper models cannot be used for real-time transcription out of the box – their speed and size suggest that others may be able to build applications on top of them that allow for near-real-time speech recognition and translation. The real value of beneficial applications built on top of Whisper models suggests that the disparate performance of these models may have real economic implications.
There are also potential dual use concerns that come with releasing Whisper. While we hope the technology will be used primarily for beneficial purposes, making ASR technology more accessible could enable more actors to build capable surveillance technologies or scale up existing surveillance efforts, as the speed and accuracy allow for affordable automatic transcription and translation of large volumes of audio communication. Moreover, these models may have some capabilities to recognize specific individuals out of the box, which in turn presents safety concerns related both to dual use and disparate performance. In practice, we expect that the cost of transcription is not the limiting factor of scaling up surveillance projects.
### BibTeX entry and citation info
*Since no official citation was provided, we use the following in the mean time*
```bibtex
@misc{radford2022whisper,
title={Robust Speech Recognition via Large-Scale Weak Supervision.},
author={Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever},
year={2022},
url={https://cdn.openai.com/papers/whisper.pdf},
}
```
| null |
Non_BioNLP
|
# Whisper
[OpenAI's Whisper](https://openai.com/blog/whisper/)
The Whisper model was proposed in [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf) by Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever.
**Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the original model card.
## Intro
The first paragraphs of the abstract read as follows :
> We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zeroshot transfer setting without the need for any finetuning.
> When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.
The original code repository can be found [here](https://github.com/openai/whisper).
## Model details
The Whisper models are trained for speech recognition and translation tasks, capable of transcribing speech audio into the text in the language it is spoken (ASR) as well as translated into English (speech translation). Researchers at OpenAI developed the models to study the robustness of speech processing systems trained under large-scale weak supervision. There are 9 models of different sizes and capabilities, summarised in the following table.
| Size | Parameters | English-only model | Multilingual model |
|:------:|:----------:|:------------------:|:------------------:|
| tiny | 39 M | ✓ | ✓ |
| base | 74 M | ✓ | ✓ |
| small | 244 M | ✓ | ✓ |
| medium | 769 M | ✓ | ✓ |
| large | 1550 M | | ✓ |
## Model description
Whisper is an auto-regressive automatic speech recognition encoder-decoder model that was trained on 680 000 hours of 16kHz sampled multilingual audio. It was fully trained in a supervised manner, with multiple tasks :
- English transcription
- Any-to-English speech translation
- Non-English transcription
- No speech prediction
To each task corresponds a sequence of tokens that are given to the decoder as *context tokens*. The beginning of a transcription always starts with `<|startoftranscript|>` which is why the `decoder_start_token` is always set to `tokenizer.encode("<|startoftranscript|>")`. The following token should be the language token, which is automatically detected in the original code. Finally, the task is define using either `<|transcribe|>` or `<|translate|>`. In addition, a `<|notimestamps|>` token is added if the task does not include timestamp prediction.
# Usage
To transcribe or translate audio files, the model has to be used along a `WhisperProcessor`. The `WhisperProcessor.get_decoder_prompt_ids` function is used to get a list of `( idx, token )` tuples, which can either be set in the config, or directly passed to the generate function, as `forced_decoder_ids`.
## Transcription
In the following example, the english only model is used. We set the `decoder_input_ids` accordingly.
### English to english
The "<|en|>" token is used to specify that the speech is in english and should be transcribed to english
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> import torch
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
>>> # load dummy dataset and read soundfiles
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> input_features = processor(ds[0]["audio"]["array"], return_tensors="pt").input_features
>>> # Generate logits
>>> logits = model(input_features, decoder_input_ids = torch.tensor([[50258]])).logits
>>> # take argmax and decode
>>> predicted_ids = torch.argmax(logits, dim=-1)
>>> transcription = processor.batch_decode(predicted_ids)
['<|en|>']
```
### French to French
In order to obtain the full transcription, the `generate()` function is used. The following example demonstrates a french to french
transcription.
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> import torch
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
>>> # load dummy dataset and read soundfiles
>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
>>> ds = ds.cast_column("audio", datasets.Audio(sampling_rate=16_000))
>>> input_speech = next(iter(ds))["audio"]["array"]
>>> model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language = "fr", task = "transcribe")
>>> input_features = processor(input_speech, return_tensors="pt").input_features
>>> predicted_ids = model.generate(input_features)
>>> transcription = processor.batch_decode(predicted_ids)
['<|startoftranscript|><|fr|><|transcribe|><|notimestamps|> Un vrai travail intéressant va enfin être mené sur ce sujet.<|endoftext|>']
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens = True)
[' Un vrai travail intéressant va enfin être mené sur ce sujet.']
```
## Translation
The "<|translate|>" is used as the first decoder input token to specify the transcription task.
### French to English
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> import torch
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
>>> # load dummy dataset and read soundfiles
>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
>>> ds = ds.cast_column("audio", datasets.Audio(sampling_rate=16_000))
>>> input_speech = next(iter(ds))["audio"]["array"]
>>> # tokenize
>>> input_features = processor(input_speech, return_tensors="pt").input_features
>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language = "fr", task = "translate")
>>> predicted_ids = model.generate(input_features, forced_decoder_ids = forced_decoder_ids)
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens = True)
[' A real interesting work will be done on this subject.']
```
## Evaluation
This code snippet shows how to evaluate **openai/whisper-large** on LibriSpeech's "clean" and "other" test data.
```python
>>> from datasets import load_dataset
>>> from transformers import WhisperForConditionalGeneration, WhisperProcessor
>>> import soundfile as sf
>>> import torch
>>> from jiwer import wer
>>> librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large").to("cuda")
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
>>> def map_to_pred(batch):
>>> input_features = processor(batch["audio"]["array"], return_tensors="pt").input_features
>>> with torch.no_grad():
>>> logits = model(input_features.to("cuda")).logits
>>> predicted_ids = torch.argmax(logits, dim=-1)
>>> transcription = processor.batch_decode(predicted_ids, normalize = True)
>>> batch['text'] = processor.tokenizer._normalize(batch['text'])
>>> batch["transcription"] = transcription
>>> return batch
>>> result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["speech"])
>>> print("WER:", wer(result["text"], result["transcription"]))
0.030003583080317572
```
### Evaluated Use
The primary intended users of these models are AI researchers studying robustness, generalization, capabilities, biases, and constraints of the current model. However, Whisper is also potentially quite useful as an ASR solution for developers, especially for English speech recognition. We recognize that once models are released, it is impossible to restrict access to only “intended” uses or to draw reasonable guidelines around what is or is not research.
The models are primarily trained and evaluated on ASR and speech translation to English tasks. They show strong ASR results in ~10 languages. They may exhibit additional capabilities, particularly if fine-tuned on certain tasks like voice activity detection, speaker classification, or speaker diarization but have not been robustly evaluated in these areas. We strongly recommend that users perform robust evaluations of the models in a particular context and domain before deploying them.
In particular, we caution against using Whisper models to transcribe recordings of individuals taken without their consent or purporting to use these models for any kind of subjective classification. We recommend against use in high-risk domains like decision-making contexts, where flaws in accuracy can lead to pronounced flaws in outcomes. The models are intended to transcribe and translate speech, use of the model for classification is not only not evaluated but also not appropriate, particularly to infer human attributes.
## Training Data
The models are trained on 680,000 hours of audio and the corresponding transcripts collected from the internet. 65% of this data (or 438,000 hours) represents English-language audio and matched English transcripts, roughly 18% (or 126,000 hours) represents non-English audio and English transcripts, while the final 17% (or 117,000 hours) represents non-English audio and the corresponding transcript. This non-English data represents 98 different languages.
As discussed in [the accompanying paper](https://cdn.openai.com/papers/whisper.pdf), we see that performance on transcription in a given language is directly correlated with the amount of training data we employ in that language.
## Performance and Limitations
Our studies show that, over many existing ASR systems, the models exhibit improved robustness to accents, background noise, technical language, as well as zero shot translation from multiple languages into English; and that accuracy on speech recognition and translation is near the state-of-the-art level.
However, because the models are trained in a weakly supervised manner using large-scale noisy data, the predictions may include texts that are not actually spoken in the audio input (i.e. hallucination). We hypothesize that this happens because, given their general knowledge of language, the models combine trying to predict the next word in audio with trying to transcribe the audio itself.
Our models perform unevenly across languages, and we observe lower accuracy on low-resource and/or low-discoverability languages or languages where we have less training data. The models also exhibit disparate performance on different accents and dialects of particular languages, which may include higher word error rate across speakers of different genders, races, ages, or other demographic criteria. Our full evaluation results are presented in [the paper accompanying this release](https://cdn.openai.com/papers/whisper.pdf).
In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. Further analysis on these limitations are provided in [the paper](https://cdn.openai.com/papers/whisper.pdf). It is likely that this behavior and hallucinations may be worse on lower-resource and/or lower-discoverability languages.
## Broader Implications
We anticipate that Whisper models’ transcription capabilities may be used for improving accessibility tools. While Whisper models cannot be used for real-time transcription out of the box – their speed and size suggest that others may be able to build applications on top of them that allow for near-real-time speech recognition and translation. The real value of beneficial applications built on top of Whisper models suggests that the disparate performance of these models may have real economic implications.
There are also potential dual use concerns that come with releasing Whisper. While we hope the technology will be used primarily for beneficial purposes, making ASR technology more accessible could enable more actors to build capable surveillance technologies or scale up existing surveillance efforts, as the speed and accuracy allow for affordable automatic transcription and translation of large volumes of audio communication. Moreover, these models may have some capabilities to recognize specific individuals out of the box, which in turn presents safety concerns related both to dual use and disparate performance. In practice, we expect that the cost of transcription is not the limiting factor of scaling up surveillance projects.
### BibTeX entry and citation info
*Since no official citation was provided, we use the following in the mean time*
```bibtex
@misc{radford2022whisper,
title={Robust Speech Recognition via Large-Scale Weak Supervision.},
author={Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever},
year={2022},
url={https://cdn.openai.com/papers/whisper.pdf},
}
```
|
{"language": ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "tr", "pl", "ca", "nl", "ar", "sv", "it", "id", "hi", "fi", "vi", "iw", "uk", "el", "ms", "cs", "ro", "da", "hu", "ta", "no", "th", "ur", "hr", "bg", "lt", "la", "mi", "ml", "cy", "sk", "te", "fa", "lv", "bn", "sr", "az", "sl", "kn", "et", "mk", "br", "eu", "is", "hy", "ne", "mn", "bs", "kk", "sq", "sw", "gl", "mr", "pa", "si", "km", "sn", "yo", "so", "af", "oc", "ka", "be", "tg", "sd", "gu", "am", "yi", "lo", "uz", "fo", "ht", "ps", "tk", "nn", "mt", "sa", "lb", "my", "bo", "tl", "mg", "as", "tt", "haw", "ln", "ha", "ba", "jw", "su"], "license": "apache-2.0", "pipeline_tag": "automatic-speech-recognition", "tags": ["audio", "automatic-speech-recognition", "hf-asr-leaderboard"], "widget": [{"example_title": "Librispeech sample 1", "src": "https://cdn-media.huggingface.co/speech_samples/sample1.flac"}, {"example_title": "Librispeech sample 2", "src": "https://cdn-media.huggingface.co/speech_samples/sample2.flac"}], "duplicated_from": "openai/whisper-large", "model-index": [{"name": "whisper-large", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "LibriSpeech (clean)", "type": "librispeech_asr", "config": "clean", "split": "test", "args": {"language": "en"}}, "metrics": [{"type": "wer", "value": 3, "name": "Test WER"}]}, {"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "LibriSpeech (other)", "type": "librispeech_asr", "config": "other", "split": "test", "args": {"language": "en"}}, "metrics": [{"type": "wer", "value": 5.4, "name": "Test WER"}]}, {"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "Common Voice 11.0", "type": "mozilla-foundation/common_voice_11_0", "config": "hi", "split": "test", "args": {"language": "hi"}}, "metrics": [{"type": "wer", "value": 54.8, "name": "Test WER"}]}]}]}
|
task
|
[
"TRANSLATION"
] | 41,590 |
LoneStriker/SauerkrautLM-Mixtral-8x7B-5.0bpw-h6-exl2
|
LoneStriker
|
text-generation
|
[
"transformers",
"safetensors",
"mixtral",
"text-generation",
"mistral",
"finetune",
"sft",
"dpo",
"chatml",
"augmentation",
"german",
"en",
"de",
"fr",
"it",
"es",
"dataset:Open-Orca/SlimOrca",
"dataset:argilla/distilabel-math-preference-dpo",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2023-12-25T09:11:01Z |
2023-12-25T09:23:01+00:00
| 3 | 0 |
---
datasets:
- Open-Orca/SlimOrca
- argilla/distilabel-math-preference-dpo
language:
- en
- de
- fr
- it
- es
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
- mistral
- finetune
- sft
- dpo
- chatml
- augmentation
- german
- mixtral
---
## VAGO solutions SauerkrautLM-Mixtral-8x7B
Introducing **SauerkrautLM-Mixtral-8x7B** – our Sauerkraut version of the powerful Mixtral-8x7B!
Finetuned and aligned with **SFT** and **DPO**
# Table of Contents
1. [Overview of all SauerkrautLM-Mixtral models](#all-sauerkrautlm-mixtral-models)
2. [Model Details](#model-details)
- [Prompt template](#prompt-template)
- [Training Dataset](#training-dataset)
3. [Evaluation](#evaluation)
5. [Disclaimer](#disclaimer)
6. [Contact](#contact)
7. [Collaborations](#collaborations)
8. [Acknowledgement](#acknowledgement)
## All SauerkrautLM-Mixtral Models
| Model | HF | GPTQ | GGUF | AWQ |
|-------|-------|-------|-------|-------|
| SauerkrautLM-Mixtral-8x7B | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-Mixtral-8x7B) | coming soon | coming soon | coming soon |
| SauerkrautLM-Mixtral-8x7B-Instruct | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-Mixtral-8x7B-Instruct) | coming soon | coming soon | coming soon |
## Model Details
**SauerkrautLM-Mixtral-8x7B**
- **Model Type:** SauerkrautLM-Mixtral-8x7B is a Mixture of Experts (MoE) Model based on [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)
- **Language(s):** English, German, French, Italian, Spanish
- **License:** APACHE 2.0
- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:[email protected])
### Training Dataset:
SauerkrautLM-Mixtral-8x7B was trained with mix of German data augmentation and translated data.
**SFT** with the dataset[OpenOrca/Slim-Orca](https://huggingface.co/datasets/Open-Orca/SlimOrca) and aligned through **DPO** with our **new German SauerkrautLM-DPO dataset** based on parts of the SFT SauerkrautLM dataset
as chosen answers and [Sauerkraut-7b-HerO](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-HerO) as rejected answers. Added with additional **translated Parts of the [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)** and **[argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo).**
We found, that only a simple translation of training data can lead to unnatural German phrasings.
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
### Data Contamination Test Results
Some models on the HuggingFace leaderboard had problems with wrong data getting mixed in.
We checked our SauerkrautLM-DPO dataset with a special test [1] on a smaller model for this problem.
The HuggingFace team used the same methods [2, 3].
Our results, with `result < 0.1, %:` being well below 0.9, indicate that our dataset is free from contamination.
*The data contamination test results of HellaSwag and Winograde will be added once [1] supports them.*
| Dataset | ARC | MMLU | TruthfulQA | GSM8K |
|------------------------------|-------|-------|-------|-------|
| **SauerkrautLM-DPO**| result < 0.1, %: 0.0 |result < 0.1, %: 0.09 | result < 0.1, %: 0.13 | result < 0.1, %: 0.16 |
[1] https://github.com/swj0419/detect-pretrain-code-contamination
[2] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/474#657f2245365456e362412a06
[3] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/265#657b6debf81f6b44b8966230
### Prompt Template:
```
<|im_start|>system
Du bist ein großes Sprachmodell, das höflich und kompetent antwortet. Schreibe deine Gedanken Schritt für Schritt auf, um Probleme sinnvoll zu lösen.<|im_end|>
<|im_start|>user
Wie geht es dir?<|im_end|>
<|im_start|>assistant
```
## Evaluation
*evaluated with lm-evaluation-harness v0.3.0 - mmlu coming soon
*All benchmarks were performed with a sliding window of 4096. New Benchmarks with Sliding Window null coming soon
## Disclaimer
We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.
However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. These models may be employed for commercial purposes, and the Apache 2.0 remains applicable and is included with the model files.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at [Dr. Daryoush Vaziri](mailto:[email protected]). We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startup, VAGO solutions, where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us.
## Acknowledgement
Many thanks to [OpenOrca](https://huggingface.co/Open-Orca), [argilla](https://huggingface.co/datasets/argilla) and [Huggingface](https://huggingface.co) for providing such valuable datasets to the Open-Source community. And of course a big thanks to MistralAI for providing the open source community with their latest technology!
| null |
Non_BioNLP
|
## VAGO solutions SauerkrautLM-Mixtral-8x7B
Introducing **SauerkrautLM-Mixtral-8x7B** – our Sauerkraut version of the powerful Mixtral-8x7B!
Finetuned and aligned with **SFT** and **DPO**
# Table of Contents
1. [Overview of all SauerkrautLM-Mixtral models](#all-sauerkrautlm-mixtral-models)
2. [Model Details](#model-details)
- [Prompt template](#prompt-template)
- [Training Dataset](#training-dataset)
3. [Evaluation](#evaluation)
5. [Disclaimer](#disclaimer)
6. [Contact](#contact)
7. [Collaborations](#collaborations)
8. [Acknowledgement](#acknowledgement)
## All SauerkrautLM-Mixtral Models
| Model | HF | GPTQ | GGUF | AWQ |
|-------|-------|-------|-------|-------|
| SauerkrautLM-Mixtral-8x7B | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-Mixtral-8x7B) | coming soon | coming soon | coming soon |
| SauerkrautLM-Mixtral-8x7B-Instruct | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-Mixtral-8x7B-Instruct) | coming soon | coming soon | coming soon |
## Model Details
**SauerkrautLM-Mixtral-8x7B**
- **Model Type:** SauerkrautLM-Mixtral-8x7B is a Mixture of Experts (MoE) Model based on [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)
- **Language(s):** English, German, French, Italian, Spanish
- **License:** APACHE 2.0
- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:[email protected])
### Training Dataset:
SauerkrautLM-Mixtral-8x7B was trained with mix of German data augmentation and translated data.
**SFT** with the dataset[OpenOrca/Slim-Orca](https://huggingface.co/datasets/Open-Orca/SlimOrca) and aligned through **DPO** with our **new German SauerkrautLM-DPO dataset** based on parts of the SFT SauerkrautLM dataset
as chosen answers and [Sauerkraut-7b-HerO](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-HerO) as rejected answers. Added with additional **translated Parts of the [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)** and **[argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo).**
We found, that only a simple translation of training data can lead to unnatural German phrasings.
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
### Data Contamination Test Results
Some models on the HuggingFace leaderboard had problems with wrong data getting mixed in.
We checked our SauerkrautLM-DPO dataset with a special test [1] on a smaller model for this problem.
The HuggingFace team used the same methods [2, 3].
Our results, with `result < 0.1, %:` being well below 0.9, indicate that our dataset is free from contamination.
*The data contamination test results of HellaSwag and Winograde will be added once [1] supports them.*
| Dataset | ARC | MMLU | TruthfulQA | GSM8K |
|------------------------------|-------|-------|-------|-------|
| **SauerkrautLM-DPO**| result < 0.1, %: 0.0 |result < 0.1, %: 0.09 | result < 0.1, %: 0.13 | result < 0.1, %: 0.16 |
[1] https://github.com/swj0419/detect-pretrain-code-contamination
[2] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/474#657f2245365456e362412a06
[3] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/265#657b6debf81f6b44b8966230
### Prompt Template:
```
<|im_start|>system
Du bist ein großes Sprachmodell, das höflich und kompetent antwortet. Schreibe deine Gedanken Schritt für Schritt auf, um Probleme sinnvoll zu lösen.<|im_end|>
<|im_start|>user
Wie geht es dir?<|im_end|>
<|im_start|>assistant
```
## Evaluation
*evaluated with lm-evaluation-harness v0.3.0 - mmlu coming soon
*All benchmarks were performed with a sliding window of 4096. New Benchmarks with Sliding Window null coming soon
## Disclaimer
We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.
However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. These models may be employed for commercial purposes, and the Apache 2.0 remains applicable and is included with the model files.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at [Dr. Daryoush Vaziri](mailto:[email protected]). We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startup, VAGO solutions, where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us.
## Acknowledgement
Many thanks to [OpenOrca](https://huggingface.co/Open-Orca), [argilla](https://huggingface.co/datasets/argilla) and [Huggingface](https://huggingface.co) for providing such valuable datasets to the Open-Source community. And of course a big thanks to MistralAI for providing the open source community with their latest technology!
|
{"datasets": ["Open-Orca/SlimOrca", "argilla/distilabel-math-preference-dpo"], "language": ["en", "de", "fr", "it", "es"], "library_name": "transformers", "license": "apache-2.0", "pipeline_tag": "text-generation", "tags": ["mistral", "finetune", "sft", "dpo", "chatml", "augmentation", "german", "mixtral"]}
|
task
|
[
"TRANSLATION"
] | 41,591 |
rambodazimi/bert-base-uncased-finetuned-FFT-MNLI
|
rambodazimi
| null |
[
"safetensors",
"bert",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"region:us"
] | 2024-08-16T23:42:37Z |
2024-08-17T22:49:33+00:00
| 4 | 0 |
---
datasets:
- glue
license: apache-2.0
metrics:
- matched_accuracy
- missmatched_accuracy
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-finetuned-MNLI
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
args: mnli
metrics:
- type: matched_accuracy
value: 0.8479877738155884
name: Matched Accuracy
- type: missmatched_accuracy
value: 0.8491659886086249
name: Missmatched 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. -->
# bert-base-uncased-finetuned-mnli
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Matched Accuracy: 0.8480
- Missmatched Accuracy: 0.8492
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- weight_decay: 0.01
- num_epochs: 2
| null |
Non_BioNLP
|
<!-- 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. -->
# bert-base-uncased-finetuned-mnli
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Matched Accuracy: 0.8480
- Missmatched Accuracy: 0.8492
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- weight_decay: 0.01
- num_epochs: 2
|
{"datasets": ["glue"], "license": "apache-2.0", "metrics": ["matched_accuracy", "missmatched_accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "bert-base-uncased-finetuned-MNLI", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "args": "mnli"}, "metrics": [{"type": "matched_accuracy", "value": 0.8479877738155884, "name": "Matched Accuracy"}, {"type": "missmatched_accuracy", "value": 0.8491659886086249, "name": "Missmatched Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 41,592 |
Salesforce/codet5-small
|
Salesforce
|
text2text-generation
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"codet5",
"dataset:code_search_net",
"arxiv:2109.00859",
"arxiv:1909.09436",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | 2022-03-02T23:29:04Z |
2025-01-21T09:07:26+00:00
| 27,854 | 72 |
---
datasets:
- code_search_net
license: apache-2.0
tags:
- codet5
inference: false
---
# CodeT5 (small-sized model)
Pre-trained CodeT5 model. It was introduced in the paper [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models
for Code Understanding and Generation](https://arxiv.org/abs/2109.00859) by Yue Wang, Weishi Wang, Shafiq Joty, Steven C.H. Hoi and first released in [this repository](https://github.com/salesforce/CodeT5).
Disclaimer: The team releasing CodeT5 did not write a model card for this model so this model card has been written by the Hugging Face team (more specifically, [nielsr](https://huggingface.co/nielsr)).
## Model description
From the abstract:
"We present CodeT5, a unified pre-trained encoder-decoder Transformer model that better leverages the code semantics conveyed from the developer-assigned identifiers. Our model employs a unified framework to seamlessly support both code understanding and generation tasks and allows for multi-task learning. Besides, we propose a novel identifier-aware pre-training task that enables the model to distinguish which code tokens are identifiers and to recover them when they are masked. Furthermore, we propose to exploit the user-written code comments with a bimodal dual generation task for better NL-PL alignment. Comprehensive experiments show that CodeT5 significantly outperforms prior methods on understanding tasks such as code defect detection and clone detection, and generation tasks across various directions including PL-NL, NL-PL, and PL-PL. Further analysis reveals that our model can better capture semantic information from code."
## Intended uses & limitations
This repository contains the pre-trained model only, so you can use this model for masked span prediction, as shown in the code example below. However, the main use of this model is to fine-tune it for a downstream task of interest, such as:
* code summarization
* code generation
* code translation
* code refinement
* code defect detection
* code clone detection.
See the [model hub](https://huggingface.co/models?search=salesforce/codet) to look for fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model:
```python
from transformers import RobertaTokenizer, T5ForConditionalGeneration
tokenizer = RobertaTokenizer.from_pretrained('Salesforce/codet5-small')
model = T5ForConditionalGeneration.from_pretrained('Salesforce/codet5-small')
text = "def greet(user): print(f'hello <extra_id_0>!')"
input_ids = tokenizer(text, return_tensors="pt").input_ids
# simply generate a single sequence
generated_ids = model.generate(input_ids, max_length=10)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
# this prints "user: {user.name}"
```
## Training data
The CodeT5 model was pretrained on CodeSearchNet [Husain et al., 2019](https://arxiv.org/abs/1909.09436). Additionally, the authors collected two datasets of C/CSharp from [BigQuery1](https://console.cloud.google.com/marketplace/details/github/github-repos) to ensure that all downstream tasks have overlapped programming languages with the pre-training data. In total, around 8.35 million instances are used for pretraining.
## Training procedure
### Preprocessing
This model uses a code-specific BPE (Byte-Pair Encoding) tokenizer. One can prepare text (or code) for the model using RobertaTokenizer, with the files from this repository.
## Evaluation results
For evaluation results on several downstream benchmarks, we refer to the paper.
## 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.
### BibTeX entry and citation info
```bibtex
@misc{wang2021codet5,
title={CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation},
author={Yue Wang and Weishi Wang and Shafiq Joty and Steven C. H. Hoi},
year={2021},
eprint={2109.00859},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
| null |
Non_BioNLP
|
# CodeT5 (small-sized model)
Pre-trained CodeT5 model. It was introduced in the paper [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models
for Code Understanding and Generation](https://arxiv.org/abs/2109.00859) by Yue Wang, Weishi Wang, Shafiq Joty, Steven C.H. Hoi and first released in [this repository](https://github.com/salesforce/CodeT5).
Disclaimer: The team releasing CodeT5 did not write a model card for this model so this model card has been written by the Hugging Face team (more specifically, [nielsr](https://huggingface.co/nielsr)).
## Model description
From the abstract:
"We present CodeT5, a unified pre-trained encoder-decoder Transformer model that better leverages the code semantics conveyed from the developer-assigned identifiers. Our model employs a unified framework to seamlessly support both code understanding and generation tasks and allows for multi-task learning. Besides, we propose a novel identifier-aware pre-training task that enables the model to distinguish which code tokens are identifiers and to recover them when they are masked. Furthermore, we propose to exploit the user-written code comments with a bimodal dual generation task for better NL-PL alignment. Comprehensive experiments show that CodeT5 significantly outperforms prior methods on understanding tasks such as code defect detection and clone detection, and generation tasks across various directions including PL-NL, NL-PL, and PL-PL. Further analysis reveals that our model can better capture semantic information from code."
## Intended uses & limitations
This repository contains the pre-trained model only, so you can use this model for masked span prediction, as shown in the code example below. However, the main use of this model is to fine-tune it for a downstream task of interest, such as:
* code summarization
* code generation
* code translation
* code refinement
* code defect detection
* code clone detection.
See the [model hub](https://huggingface.co/models?search=salesforce/codet) to look for fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model:
```python
from transformers import RobertaTokenizer, T5ForConditionalGeneration
tokenizer = RobertaTokenizer.from_pretrained('Salesforce/codet5-small')
model = T5ForConditionalGeneration.from_pretrained('Salesforce/codet5-small')
text = "def greet(user): print(f'hello <extra_id_0>!')"
input_ids = tokenizer(text, return_tensors="pt").input_ids
# simply generate a single sequence
generated_ids = model.generate(input_ids, max_length=10)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
# this prints "user: {user.name}"
```
## Training data
The CodeT5 model was pretrained on CodeSearchNet [Husain et al., 2019](https://arxiv.org/abs/1909.09436). Additionally, the authors collected two datasets of C/CSharp from [BigQuery1](https://console.cloud.google.com/marketplace/details/github/github-repos) to ensure that all downstream tasks have overlapped programming languages with the pre-training data. In total, around 8.35 million instances are used for pretraining.
## Training procedure
### Preprocessing
This model uses a code-specific BPE (Byte-Pair Encoding) tokenizer. One can prepare text (or code) for the model using RobertaTokenizer, with the files from this repository.
## Evaluation results
For evaluation results on several downstream benchmarks, we refer to the paper.
## 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.
### BibTeX entry and citation info
```bibtex
@misc{wang2021codet5,
title={CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation},
author={Yue Wang and Weishi Wang and Shafiq Joty and Steven C. H. Hoi},
year={2021},
eprint={2109.00859},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
{"datasets": ["code_search_net"], "license": "apache-2.0", "tags": ["codet5"], "inference": false}
|
task
|
[
"TRANSLATION",
"SUMMARIZATION"
] | 41,593 |
poltextlab/xlm-roberta-large-hungarian-execspeech-cap-v3
|
poltextlab
|
text-classification
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"hu",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-09-07T15:09:59Z |
2025-02-26T16:05:30+00:00
| 0 | 0 |
---
language:
- hu
metrics:
- accuracy
- f1-score
tags:
- text-classification
- pytorch
extra_gated_prompt: 'Our models are intended for academic use only. If you are not
affiliated with an academic institution, please provide a rationale for using our
models. Please allow us a few business days to manually review subscriptions.
If you use our models for your work or research, please cite this paper: Sebők,
M., Máté, Á., Ring, O., Kovács, V., & Lehoczki, R. (2024). Leveraging Open Large
Language Models for Multilingual Policy Topic Classification: The Babel Machine
Approach. Social Science Computer Review, 0(0). https://doi.org/10.1177/08944393241259434'
extra_gated_fields:
Name: text
Country: country
Institution: text
Institution Email: text
Please specify your academic use case: text
---
# xlm-roberta-large-hungarian-execspeech-cap-v3
## Model description
An `xlm-roberta-large` model fine-tuned on hungarian training data containing executive speeches labeled with [major topic codes](https://www.comparativeagendas.net/pages/master-codebook) from the [Comparative Agendas Project](https://www.comparativeagendas.net/).
We follow the master codebook of the Comparative Agendas Project, and all of our models use the same major topic codes.
## How to use the model
```python
from transformers import AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
pipe = pipeline(
model="poltextlab/xlm-roberta-large-hungarian-execspeech-cap-v3",
task="text-classification",
tokenizer=tokenizer,
use_fast=False,
token="<your_hf_read_only_token>"
)
text = "We will place an immediate 6-month halt on the finance driven closure of beds and wards, and set up an independent audit of needs and facilities."
pipe(text)
```
The translation table from the model results to CAP codes is the following:
```python
CAP_NUM_DICT = {
0: 1,
1: 2,
2: 3,
3: 4,
4: 5,
5: 6,
6: 7,
7: 8,
8: 9,
9: 10,
10: 12,
11: 13,
12: 14,
13: 15,
14: 16,
15: 17,
16: 18,
17: 19,
18: 20,
19: 21,
20: 23,
21: 999,
}
```
We have included a 999 label because our models are fine-tuned on training data containing the label 'None' in addition to the 21 CAP major policy topic codes, indicating that the given text contains no relevant policy content. We use the label 999 for these cases.
### Gated access
Due to the gated access, you must pass the `token` parameter when loading the model. In earlier versions of the Transformers package, you may need to use the `use_auth_token` parameter instead.
## Model performance
The model was evaluated on a test set of 16785 examples.<br>
Model accuracy is **0.66**.
| label | precision | recall | f1-score | support |
|:-------------|------------:|---------:|-----------:|----------:|
| 0 | 0.57 | 0.65 | 0.61 | 1323 |
| 1 | 0.57 | 0.52 | 0.55 | 876 |
| 2 | 0.73 | 0.75 | 0.74 | 691 |
| 3 | 0.72 | 0.6 | 0.66 | 182 |
| 4 | 0.61 | 0.56 | 0.58 | 545 |
| 5 | 0.73 | 0.55 | 0.63 | 220 |
| 6 | 0.8 | 0.56 | 0.66 | 380 |
| 7 | 0.78 | 0.67 | 0.72 | 163 |
| 8 | 0.68 | 0.6 | 0.64 | 436 |
| 9 | 0.75 | 0.72 | 0.74 | 115 |
| 10 | 0.51 | 0.54 | 0.53 | 229 |
| 11 | 0.55 | 0.39 | 0.46 | 95 |
| 12 | 0.59 | 0.39 | 0.47 | 198 |
| 13 | 0.62 | 0.44 | 0.51 | 568 |
| 14 | 0.51 | 0.53 | 0.52 | 200 |
| 15 | 0.52 | 0.54 | 0.53 | 214 |
| 16 | 0.52 | 0.29 | 0.37 | 389 |
| 17 | 0.66 | 0.65 | 0.65 | 2496 |
| 18 | 0.64 | 0.5 | 0.56 | 1486 |
| 19 | 0.56 | 0.36 | 0.44 | 182 |
| 20 | 0.55 | 0.31 | 0.4 | 151 |
| 21 | 0.7 | 0.83 | 0.76 | 5646 |
| macro avg | 0.63 | 0.54 | 0.58 | 16785 |
| weighted avg | 0.65 | 0.66 | 0.65 | 16785 |
### Fine-tuning procedure
This model was fine-tuned with the following key hyperparameters:
- **Number of Training Epochs**: 10
- **Batch Size**: 8
- **Learning Rate**: 5e-06
- **Early Stopping**: enabled with a patience of 2 epochs
## Inference platform
This model is used by the [CAP Babel Machine](https://babel.poltextlab.com), an open-source and free natural language processing tool, designed to simplify and speed up projects for comparative research.
## Cooperation
Model performance can be significantly improved by extending our training sets. We appreciate every submission of CAP-coded corpora (of any domain and language) at poltextlab{at}poltextlab{dot}com or by using the [CAP Babel Machine](https://babel.poltextlab.com).
## Reference
Sebők, M., Máté, Á., Ring, O., Kovács, V., & Lehoczki, R. (2024). Leveraging Open Large Language Models for Multilingual Policy Topic Classification: The Babel Machine Approach. Social Science Computer Review, 0(0). https://doi.org/10.1177/08944393241259434
## Debugging and issues
This architecture uses the `sentencepiece` tokenizer. In order to use the model before `transformers==4.27` you need to install it manually.
If you encounter a `RuntimeError` when loading the model using the `from_pretrained()` method, adding `ignore_mismatched_sizes=True` should solve the issue.
| null |
Non_BioNLP
|
# xlm-roberta-large-hungarian-execspeech-cap-v3
## Model description
An `xlm-roberta-large` model fine-tuned on hungarian training data containing executive speeches labeled with [major topic codes](https://www.comparativeagendas.net/pages/master-codebook) from the [Comparative Agendas Project](https://www.comparativeagendas.net/).
We follow the master codebook of the Comparative Agendas Project, and all of our models use the same major topic codes.
## How to use the model
```python
from transformers import AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
pipe = pipeline(
model="poltextlab/xlm-roberta-large-hungarian-execspeech-cap-v3",
task="text-classification",
tokenizer=tokenizer,
use_fast=False,
token="<your_hf_read_only_token>"
)
text = "We will place an immediate 6-month halt on the finance driven closure of beds and wards, and set up an independent audit of needs and facilities."
pipe(text)
```
The translation table from the model results to CAP codes is the following:
```python
CAP_NUM_DICT = {
0: 1,
1: 2,
2: 3,
3: 4,
4: 5,
5: 6,
6: 7,
7: 8,
8: 9,
9: 10,
10: 12,
11: 13,
12: 14,
13: 15,
14: 16,
15: 17,
16: 18,
17: 19,
18: 20,
19: 21,
20: 23,
21: 999,
}
```
We have included a 999 label because our models are fine-tuned on training data containing the label 'None' in addition to the 21 CAP major policy topic codes, indicating that the given text contains no relevant policy content. We use the label 999 for these cases.
### Gated access
Due to the gated access, you must pass the `token` parameter when loading the model. In earlier versions of the Transformers package, you may need to use the `use_auth_token` parameter instead.
## Model performance
The model was evaluated on a test set of 16785 examples.<br>
Model accuracy is **0.66**.
| label | precision | recall | f1-score | support |
|:-------------|------------:|---------:|-----------:|----------:|
| 0 | 0.57 | 0.65 | 0.61 | 1323 |
| 1 | 0.57 | 0.52 | 0.55 | 876 |
| 2 | 0.73 | 0.75 | 0.74 | 691 |
| 3 | 0.72 | 0.6 | 0.66 | 182 |
| 4 | 0.61 | 0.56 | 0.58 | 545 |
| 5 | 0.73 | 0.55 | 0.63 | 220 |
| 6 | 0.8 | 0.56 | 0.66 | 380 |
| 7 | 0.78 | 0.67 | 0.72 | 163 |
| 8 | 0.68 | 0.6 | 0.64 | 436 |
| 9 | 0.75 | 0.72 | 0.74 | 115 |
| 10 | 0.51 | 0.54 | 0.53 | 229 |
| 11 | 0.55 | 0.39 | 0.46 | 95 |
| 12 | 0.59 | 0.39 | 0.47 | 198 |
| 13 | 0.62 | 0.44 | 0.51 | 568 |
| 14 | 0.51 | 0.53 | 0.52 | 200 |
| 15 | 0.52 | 0.54 | 0.53 | 214 |
| 16 | 0.52 | 0.29 | 0.37 | 389 |
| 17 | 0.66 | 0.65 | 0.65 | 2496 |
| 18 | 0.64 | 0.5 | 0.56 | 1486 |
| 19 | 0.56 | 0.36 | 0.44 | 182 |
| 20 | 0.55 | 0.31 | 0.4 | 151 |
| 21 | 0.7 | 0.83 | 0.76 | 5646 |
| macro avg | 0.63 | 0.54 | 0.58 | 16785 |
| weighted avg | 0.65 | 0.66 | 0.65 | 16785 |
### Fine-tuning procedure
This model was fine-tuned with the following key hyperparameters:
- **Number of Training Epochs**: 10
- **Batch Size**: 8
- **Learning Rate**: 5e-06
- **Early Stopping**: enabled with a patience of 2 epochs
## Inference platform
This model is used by the [CAP Babel Machine](https://babel.poltextlab.com), an open-source and free natural language processing tool, designed to simplify and speed up projects for comparative research.
## Cooperation
Model performance can be significantly improved by extending our training sets. We appreciate every submission of CAP-coded corpora (of any domain and language) at poltextlab{at}poltextlab{dot}com or by using the [CAP Babel Machine](https://babel.poltextlab.com).
## Reference
Sebők, M., Máté, Á., Ring, O., Kovács, V., & Lehoczki, R. (2024). Leveraging Open Large Language Models for Multilingual Policy Topic Classification: The Babel Machine Approach. Social Science Computer Review, 0(0). https://doi.org/10.1177/08944393241259434
## Debugging and issues
This architecture uses the `sentencepiece` tokenizer. In order to use the model before `transformers==4.27` you need to install it manually.
If you encounter a `RuntimeError` when loading the model using the `from_pretrained()` method, adding `ignore_mismatched_sizes=True` should solve the issue.
|
{"language": ["hu"], "metrics": ["accuracy", "f1-score"], "tags": ["text-classification", "pytorch"], "extra_gated_prompt": "Our models are intended for academic use only. If you are not affiliated with an academic institution, please provide a rationale for using our models. Please allow us a few business days to manually review subscriptions.\nIf you use our models for your work or research, please cite this paper: Sebők, M., Máté, Á., Ring, O., Kovács, V., & Lehoczki, R. (2024). Leveraging Open Large Language Models for Multilingual Policy Topic Classification: The Babel Machine Approach. Social Science Computer Review, 0(0). https://doi.org/10.1177/08944393241259434", "extra_gated_fields": {"Name": "text", "Country": "country", "Institution": "text", "Institution Email": "text", "Please specify your academic use case": "text"}}
|
task
|
[
"TRANSLATION"
] | 41,594 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.