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
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
HPLT/translate-zh_hant-en-v1.0-hplt_opus
|
HPLT
|
translation
|
[
"transformers",
"pytorch",
"marian",
"text2text-generation",
"translation",
"zh",
"en",
"license:cc-by-4.0",
"autotrain_compatible",
"region:us"
] | 2024-02-27T11:29:56Z |
2024-03-14T00:56:58+00:00
| 26 | 0 |
---
language:
- zh
- en
license: cc-by-4.0
tags:
- translation
inference: false
---
## HPLT MT release v1.0
This repository contains the translation model for Traditional Chinese-English trained with OPUS and HPLT data. The model is available in both Marian and Hugging Face formats.
### Model Info
* Source language: Traditional Chinese
* Target language: English
* Dataset: OPUS and HPLT data
* Model architecture: Transformer-base
* Tokenizer: SentencePiece (Unigram)
* Cleaning: We used [OpusCleaner](https://github.com/hplt-project/OpusCleaner) with a set of basic rules. Details can be found in the filter files [here](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0/data/en-zh_hant/raw/v2).
You can check out our [deliverable report](https://hplt-project.org/HPLT_D5_1___Translation_models_for_select_language_pairs.pdf), [GitHub repository](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0), and [website](https://hplt-project.org) for more details.
### Usage
The model has been trained with [MarianNMT](https://github.com/marian-nmt/marian) and the weights are in the Marian format. We have also converted the model into the Hugging Face format so it is compatible with `transformers`.
#### Using Marian
To run inference with MarianNMT, refer to the [Inference/Decoding/Translation](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0#inferencedecodingtranslation) section of our GitHub repository. You will need the model file `model.npz.best-chrf.npz` and the vocabulary file `model.zh_hant-en.spm` from this repository.
#### Using transformers
We have also converted this model to the Hugging Face format and you can get started with the script below. **Note** that due a [known issue](https://github.com/huggingface/transformers/issues/26216) in weight conversion, the checkpoint cannot work with transformer versions <4.26 or >4.30. We tested and suggest `pip install transformers==4.28`.
```
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("HPLT/translate-zh_hant-en-v1.0-hplt_opus")
model = AutoModelForSeq2SeqLM.from_pretrained("HPLT/translate-zh_hant-en-v1.0-hplt_opus")
inputs = ["Input goes here.", "Make sure the language is right."]
batch_tokenized = tokenizer(inputs, return_tensors="pt", padding=True)
model_output = model.generate(
**batch_tokenized, num_beams=6, max_new_tokens=512
)
batch_detokenized = tokenizer.batch_decode(
model_output,
skip_special_tokens=True,
)
print(batch_detokenized)
```
### Benchmarks
When decoded using Marian, the model has the following test scores.
| Test set | BLEU | chrF++ | COMET22 |
| -------------------------------------- | ---- | ----- | ----- |
| FLORES200 | 21.0 | 47.8 | 0.8259 |
| NTREX | 19.9 | 45.8 | 0.8 |
### Acknowledgements
This project has received funding from the European Union's Horizon Europe research and innovation programme under grant agreement No 101070350 and from UK Research and Innovation (UKRI) under the UK government's Horizon Europe funding guarantee [grant number 10052546]
Brought to you by researchers from the University of Edinburgh and Charles University in Prague with support from the whole HPLT consortium.
| null |
Non_BioNLP
|
## HPLT MT release v1.0
This repository contains the translation model for Traditional Chinese-English trained with OPUS and HPLT data. The model is available in both Marian and Hugging Face formats.
### Model Info
* Source language: Traditional Chinese
* Target language: English
* Dataset: OPUS and HPLT data
* Model architecture: Transformer-base
* Tokenizer: SentencePiece (Unigram)
* Cleaning: We used [OpusCleaner](https://github.com/hplt-project/OpusCleaner) with a set of basic rules. Details can be found in the filter files [here](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0/data/en-zh_hant/raw/v2).
You can check out our [deliverable report](https://hplt-project.org/HPLT_D5_1___Translation_models_for_select_language_pairs.pdf), [GitHub repository](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0), and [website](https://hplt-project.org) for more details.
### Usage
The model has been trained with [MarianNMT](https://github.com/marian-nmt/marian) and the weights are in the Marian format. We have also converted the model into the Hugging Face format so it is compatible with `transformers`.
#### Using Marian
To run inference with MarianNMT, refer to the [Inference/Decoding/Translation](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0#inferencedecodingtranslation) section of our GitHub repository. You will need the model file `model.npz.best-chrf.npz` and the vocabulary file `model.zh_hant-en.spm` from this repository.
#### Using transformers
We have also converted this model to the Hugging Face format and you can get started with the script below. **Note** that due a [known issue](https://github.com/huggingface/transformers/issues/26216) in weight conversion, the checkpoint cannot work with transformer versions <4.26 or >4.30. We tested and suggest `pip install transformers==4.28`.
```
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("HPLT/translate-zh_hant-en-v1.0-hplt_opus")
model = AutoModelForSeq2SeqLM.from_pretrained("HPLT/translate-zh_hant-en-v1.0-hplt_opus")
inputs = ["Input goes here.", "Make sure the language is right."]
batch_tokenized = tokenizer(inputs, return_tensors="pt", padding=True)
model_output = model.generate(
**batch_tokenized, num_beams=6, max_new_tokens=512
)
batch_detokenized = tokenizer.batch_decode(
model_output,
skip_special_tokens=True,
)
print(batch_detokenized)
```
### Benchmarks
When decoded using Marian, the model has the following test scores.
| Test set | BLEU | chrF++ | COMET22 |
| -------------------------------------- | ---- | ----- | ----- |
| FLORES200 | 21.0 | 47.8 | 0.8259 |
| NTREX | 19.9 | 45.8 | 0.8 |
### Acknowledgements
This project has received funding from the European Union's Horizon Europe research and innovation programme under grant agreement No 101070350 and from UK Research and Innovation (UKRI) under the UK government's Horizon Europe funding guarantee [grant number 10052546]
Brought to you by researchers from the University of Edinburgh and Charles University in Prague with support from the whole HPLT consortium.
|
{"language": ["zh", "en"], "license": "cc-by-4.0", "tags": ["translation"], "inference": false}
|
task
|
[
"TRANSLATION"
] | 43,792 |
macadeliccc/SOLAR-10.7b-Instruct-dpo
|
macadeliccc
|
text-generation
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-01-24T04:11:08Z |
2024-03-04T19:25:20+00:00
| 74 | 1 |
---
library_name: transformers
license: cc-by-nc-4.0
model-index:
- name: SOLAR-10.7b-Instruct-dpo
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 71.76
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 88.08
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 66.06
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 71.98
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 82.32
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 61.03
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo
name: Open LLM Leaderboard
---
# SOLAR-10.7b-Instruct-dpo
This model is a finetune of upstage/SOLAR-10.7B-Instruct-v1.0 using Intel/orca_dpo_pairs
## Chat Template
This model follows the chatML chat template.
## Evaluations
### EQ Bench comparison with base model
These scores are the average of 3 iterations.
----Benchmark Complete----
+ 2024-01-25 04:41:01
+ Time taken: 236.1 mins
+ Prompt Format: ChatML
+ Model: macadeliccc/SOLAR-10.7b-Instruct-dpo
+ Score (v2): 72.79
+ Parseable: 165.67
---------------
Batch completed
Time taken: 236.1 mins
---------------
as compared to the original model:
----Benchmark Complete----
+ 2024-01-25 08:45:02
+ Time taken: 244.0 mins
+ Prompt Format: ChatML
+ Model: [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
+ Score (v2): 71.03
+ Parseable: 165.67
---------------
Batch completed
Time taken: 480.1 mins
---------------
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|---------------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[SOLAR-10.7b-Instruct-dpo](https://huggingface.co/macadeliccc/SOLAR-10.7b-Instruct-dpo)| 47.57| 74.3| 72.73| 45.76| 60.09|
### AGIEval
| Task |Version| Metric |Value| |Stderr|
|------------------------------|------:|--------|----:|---|-----:|
|agieval_aqua_rat | 0|acc |27.56|± | 2.81|
| | |acc_norm|26.77|± | 2.78|
|agieval_logiqa_en | 0|acc |41.63|± | 1.93|
| | |acc_norm|41.32|± | 1.93|
|agieval_lsat_ar | 0|acc |25.22|± | 2.87|
| | |acc_norm|24.35|± | 2.84|
|agieval_lsat_lr | 0|acc |54.12|± | 2.21|
| | |acc_norm|54.31|± | 2.21|
|agieval_lsat_rc | 0|acc |68.77|± | 2.83|
| | |acc_norm|69.14|± | 2.82|
|agieval_sat_en | 0|acc |79.13|± | 2.84|
| | |acc_norm|79.13|± | 2.84|
|agieval_sat_en_without_passage| 0|acc |44.66|± | 3.47|
| | |acc_norm|44.66|± | 3.47|
|agieval_sat_math | 0|acc |40.45|± | 3.32|
| | |acc_norm|40.91|± | 3.32|
Average: 47.57%
### GPT4All
| Task |Version| Metric |Value| |Stderr|
|-------------|------:|--------|----:|---|-----:|
|arc_challenge| 0|acc |60.49|± | 1.43|
| | |acc_norm|63.74|± | 1.40|
|arc_easy | 0|acc |82.07|± | 0.79|
| | |acc_norm|79.92|± | 0.82|
|boolq | 1|acc |88.56|± | 0.56|
|hellaswag | 0|acc |68.47|± | 0.46|
| | |acc_norm|86.06|± | 0.35|
|openbookqa | 0|acc |36.20|± | 2.15|
| | |acc_norm|46.60|± | 2.23|
|piqa | 0|acc |79.38|± | 0.94|
| | |acc_norm|79.71|± | 0.94|
|winogrande | 0|acc |75.53|± | 1.21|
Average: 74.3%
### TruthfulQA
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |57.77|± | 1.73|
| | |mc2 |72.73|± | 1.49|
Average: 72.73%
### Bigbench
| Task |Version| Metric |Value| |Stderr|
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|55.26|± | 3.62|
|bigbench_date_understanding | 0|multiple_choice_grade|62.87|± | 2.52|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|46.51|± | 3.11|
|bigbench_geometric_shapes | 0|multiple_choice_grade|25.63|± | 2.31|
| | |exact_str_match | 0.00|± | 0.00|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|28.00|± | 2.01|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|20.57|± | 1.53|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|46.67|± | 2.89|
|bigbench_movie_recommendation | 0|multiple_choice_grade|41.80|± | 2.21|
|bigbench_navigate | 0|multiple_choice_grade|64.00|± | 1.52|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|60.00|± | 1.10|
|bigbench_ruin_names | 0|multiple_choice_grade|39.96|± | 2.32|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|47.90|± | 1.58|
|bigbench_snarks | 0|multiple_choice_grade|64.09|± | 3.58|
|bigbench_sports_understanding | 0|multiple_choice_grade|71.10|± | 1.44|
|bigbench_temporal_sequences | 0|multiple_choice_grade|59.90|± | 1.55|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|24.96|± | 1.22|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|17.89|± | 0.92|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|46.67|± | 2.89|
Average: 45.76%
Average score: 60.09%
Elapsed time: 02:10:16
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_macadeliccc__SOLAR-10.7b-Instruct-dpo)
| Metric |Value|
|---------------------------------|----:|
|Avg. |73.54|
|AI2 Reasoning Challenge (25-Shot)|71.76|
|HellaSwag (10-Shot) |88.08|
|MMLU (5-Shot) |66.06|
|TruthfulQA (0-shot) |71.98|
|Winogrande (5-shot) |82.32|
|GSM8k (5-shot) |61.03|
| null |
Non_BioNLP
|
# SOLAR-10.7b-Instruct-dpo
This model is a finetune of upstage/SOLAR-10.7B-Instruct-v1.0 using Intel/orca_dpo_pairs
## Chat Template
This model follows the chatML chat template.
## Evaluations
### EQ Bench comparison with base model
These scores are the average of 3 iterations.
----Benchmark Complete----
+ 2024-01-25 04:41:01
+ Time taken: 236.1 mins
+ Prompt Format: ChatML
+ Model: macadeliccc/SOLAR-10.7b-Instruct-dpo
+ Score (v2): 72.79
+ Parseable: 165.67
---------------
Batch completed
Time taken: 236.1 mins
---------------
as compared to the original model:
----Benchmark Complete----
+ 2024-01-25 08:45:02
+ Time taken: 244.0 mins
+ Prompt Format: ChatML
+ Model: [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
+ Score (v2): 71.03
+ Parseable: 165.67
---------------
Batch completed
Time taken: 480.1 mins
---------------
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|---------------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[SOLAR-10.7b-Instruct-dpo](https://huggingface.co/macadeliccc/SOLAR-10.7b-Instruct-dpo)| 47.57| 74.3| 72.73| 45.76| 60.09|
### AGIEval
| Task |Version| Metric |Value| |Stderr|
|------------------------------|------:|--------|----:|---|-----:|
|agieval_aqua_rat | 0|acc |27.56|± | 2.81|
| | |acc_norm|26.77|± | 2.78|
|agieval_logiqa_en | 0|acc |41.63|± | 1.93|
| | |acc_norm|41.32|± | 1.93|
|agieval_lsat_ar | 0|acc |25.22|± | 2.87|
| | |acc_norm|24.35|± | 2.84|
|agieval_lsat_lr | 0|acc |54.12|± | 2.21|
| | |acc_norm|54.31|± | 2.21|
|agieval_lsat_rc | 0|acc |68.77|± | 2.83|
| | |acc_norm|69.14|± | 2.82|
|agieval_sat_en | 0|acc |79.13|± | 2.84|
| | |acc_norm|79.13|± | 2.84|
|agieval_sat_en_without_passage| 0|acc |44.66|± | 3.47|
| | |acc_norm|44.66|± | 3.47|
|agieval_sat_math | 0|acc |40.45|± | 3.32|
| | |acc_norm|40.91|± | 3.32|
Average: 47.57%
### GPT4All
| Task |Version| Metric |Value| |Stderr|
|-------------|------:|--------|----:|---|-----:|
|arc_challenge| 0|acc |60.49|± | 1.43|
| | |acc_norm|63.74|± | 1.40|
|arc_easy | 0|acc |82.07|± | 0.79|
| | |acc_norm|79.92|± | 0.82|
|boolq | 1|acc |88.56|± | 0.56|
|hellaswag | 0|acc |68.47|± | 0.46|
| | |acc_norm|86.06|± | 0.35|
|openbookqa | 0|acc |36.20|± | 2.15|
| | |acc_norm|46.60|± | 2.23|
|piqa | 0|acc |79.38|± | 0.94|
| | |acc_norm|79.71|± | 0.94|
|winogrande | 0|acc |75.53|± | 1.21|
Average: 74.3%
### TruthfulQA
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |57.77|± | 1.73|
| | |mc2 |72.73|± | 1.49|
Average: 72.73%
### Bigbench
| Task |Version| Metric |Value| |Stderr|
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|55.26|± | 3.62|
|bigbench_date_understanding | 0|multiple_choice_grade|62.87|± | 2.52|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|46.51|± | 3.11|
|bigbench_geometric_shapes | 0|multiple_choice_grade|25.63|± | 2.31|
| | |exact_str_match | 0.00|± | 0.00|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|28.00|± | 2.01|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|20.57|± | 1.53|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|46.67|± | 2.89|
|bigbench_movie_recommendation | 0|multiple_choice_grade|41.80|± | 2.21|
|bigbench_navigate | 0|multiple_choice_grade|64.00|± | 1.52|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|60.00|± | 1.10|
|bigbench_ruin_names | 0|multiple_choice_grade|39.96|± | 2.32|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|47.90|± | 1.58|
|bigbench_snarks | 0|multiple_choice_grade|64.09|± | 3.58|
|bigbench_sports_understanding | 0|multiple_choice_grade|71.10|± | 1.44|
|bigbench_temporal_sequences | 0|multiple_choice_grade|59.90|± | 1.55|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|24.96|± | 1.22|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|17.89|± | 0.92|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|46.67|± | 2.89|
Average: 45.76%
Average score: 60.09%
Elapsed time: 02:10:16
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_macadeliccc__SOLAR-10.7b-Instruct-dpo)
| Metric |Value|
|---------------------------------|----:|
|Avg. |73.54|
|AI2 Reasoning Challenge (25-Shot)|71.76|
|HellaSwag (10-Shot) |88.08|
|MMLU (5-Shot) |66.06|
|TruthfulQA (0-shot) |71.98|
|Winogrande (5-shot) |82.32|
|GSM8k (5-shot) |61.03|
|
{"library_name": "transformers", "license": "cc-by-nc-4.0", "model-index": [{"name": "SOLAR-10.7b-Instruct-dpo", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 71.76, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 88.08, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 66.06, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "TruthfulQA (0-shot)", "type": "truthful_qa", "config": "multiple_choice", "split": "validation", "args": {"num_few_shot": 0}}, "metrics": [{"type": "mc2", "value": 71.98}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Winogrande (5-shot)", "type": "winogrande", "config": "winogrande_xl", "split": "validation", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 82.32, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "GSM8k (5-shot)", "type": "gsm8k", "config": "main", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 61.03, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-10.7b-Instruct-dpo", "name": "Open LLM Leaderboard"}}]}]}
|
task
|
[
"TRANSLATION"
] | 43,793 |
gokuls/hBERTv1_new_pretrain_48_emb_com_mrpc
|
gokuls
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"hybridbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-06-14T16:05:56Z |
2023-06-14T16:16:39+00:00
| 10 | 0 |
---
datasets:
- glue
language:
- en
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: hBERTv1_new_pretrain_48_emb_com_mrpc
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE MRPC
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- type: accuracy
value: 0.7083333333333334
name: Accuracy
- type: f1
value: 0.8172043010752688
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. -->
# hBERTv1_new_pretrain_48_emb_com_mrpc
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5831
- Accuracy: 0.7083
- F1: 0.8172
- Combined Score: 0.7628
## 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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6776 | 1.0 | 29 | 0.6052 | 0.7010 | 0.8146 | 0.7578 |
| 0.6271 | 2.0 | 58 | 0.6112 | 0.6961 | 0.8025 | 0.7493 |
| 0.58 | 3.0 | 87 | 0.5831 | 0.7083 | 0.8172 | 0.7628 |
| 0.5494 | 4.0 | 116 | 0.6458 | 0.7010 | 0.8094 | 0.7552 |
| 0.5148 | 5.0 | 145 | 0.6067 | 0.6838 | 0.7882 | 0.7360 |
| 0.4573 | 6.0 | 174 | 0.6267 | 0.6863 | 0.7935 | 0.7399 |
| 0.395 | 7.0 | 203 | 0.7897 | 0.6275 | 0.7295 | 0.6785 |
| 0.3102 | 8.0 | 232 | 0.9040 | 0.6593 | 0.7599 | 0.7096 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- 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. -->
# hBERTv1_new_pretrain_48_emb_com_mrpc
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5831
- Accuracy: 0.7083
- F1: 0.8172
- Combined Score: 0.7628
## 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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6776 | 1.0 | 29 | 0.6052 | 0.7010 | 0.8146 | 0.7578 |
| 0.6271 | 2.0 | 58 | 0.6112 | 0.6961 | 0.8025 | 0.7493 |
| 0.58 | 3.0 | 87 | 0.5831 | 0.7083 | 0.8172 | 0.7628 |
| 0.5494 | 4.0 | 116 | 0.6458 | 0.7010 | 0.8094 | 0.7552 |
| 0.5148 | 5.0 | 145 | 0.6067 | 0.6838 | 0.7882 | 0.7360 |
| 0.4573 | 6.0 | 174 | 0.6267 | 0.6863 | 0.7935 | 0.7399 |
| 0.395 | 7.0 | 203 | 0.7897 | 0.6275 | 0.7295 | 0.6785 |
| 0.3102 | 8.0 | 232 | 0.9040 | 0.6593 | 0.7599 | 0.7096 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
|
{"datasets": ["glue"], "language": ["en"], "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "hBERTv1_new_pretrain_48_emb_com_mrpc", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE MRPC", "type": "glue", "config": "mrpc", "split": "validation", "args": "mrpc"}, "metrics": [{"type": "accuracy", "value": 0.7083333333333334, "name": "Accuracy"}, {"type": "f1", "value": 0.8172043010752688, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,794 |
Lots-of-LoRAs/Mistral-7B-Instruct-v0.2-4b-r16-task1435
|
Lots-of-LoRAs
| null |
[
"pytorch",
"safetensors",
"en",
"arxiv:1910.09700",
"arxiv:2407.00066",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:finetune:mistralai/Mistral-7B-Instruct-v0.2",
"license:mit",
"region:us"
] | 2025-01-02T14:24:50Z |
2025-01-02T14:24:57+00:00
| 0 | 0 |
---
base_model: mistralai/Mistral-7B-Instruct-v0.2
language: en
library_name: pytorch
license: mit
---
# Model Card for Mistral-7B-Instruct-v0.2-4b-r16-task1435
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
LoRA trained on task1435_ro_sts_parallel_language_translation_ro_to_en
- **Developed by:** bruel
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** LoRA
- **Language(s) (NLP):** en
- **License:** mit
- **Finetuned from model [optional]:** mistralai/Mistral-7B-Instruct-v0.2
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/bruel-gabrielsson
- **Paper [optional]:** "Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead" (2024), Rickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin and Justin Solomon
- **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. -->
https://huggingface.co/datasets/Lots-of-LoRAs/task1435_ro_sts_parallel_language_translation_ro_to_en sourced from https://github.com/allenai/natural-instructions
### 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:**
@misc{brüelgabrielsson2024compressserveservingthousands,
title={Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead},
author={Rickard Brüel-Gabrielsson and Jiacheng Zhu and Onkar Bhardwaj and Leshem Choshen and Kristjan Greenewald and Mikhail Yurochkin and Justin Solomon},
year={2024},
eprint={2407.00066},
archivePrefix={arXiv},
primaryClass={cs.DC},
url={https://arxiv.org/abs/2407.00066},
}
**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 Mistral-7B-Instruct-v0.2-4b-r16-task1435
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
LoRA trained on task1435_ro_sts_parallel_language_translation_ro_to_en
- **Developed by:** bruel
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** LoRA
- **Language(s) (NLP):** en
- **License:** mit
- **Finetuned from model [optional]:** mistralai/Mistral-7B-Instruct-v0.2
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/bruel-gabrielsson
- **Paper [optional]:** "Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead" (2024), Rickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin and Justin Solomon
- **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. -->
https://huggingface.co/datasets/Lots-of-LoRAs/task1435_ro_sts_parallel_language_translation_ro_to_en sourced from https://github.com/allenai/natural-instructions
### 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:**
@misc{brüelgabrielsson2024compressserveservingthousands,
title={Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead},
author={Rickard Brüel-Gabrielsson and Jiacheng Zhu and Onkar Bhardwaj and Leshem Choshen and Kristjan Greenewald and Mikhail Yurochkin and Justin Solomon},
year={2024},
eprint={2407.00066},
archivePrefix={arXiv},
primaryClass={cs.DC},
url={https://arxiv.org/abs/2407.00066},
}
**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": "mistralai/Mistral-7B-Instruct-v0.2", "language": "en", "library_name": "pytorch", "license": "mit"}
|
task
|
[
"TRANSLATION"
] | 43,795 |
allenai/PRIMERA-arxiv
|
allenai
|
text2text-generation
|
[
"transformers",
"pytorch",
"led",
"text2text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-11T00:49:18Z |
2023-01-24T17:03:04+00:00
| 117 | 2 |
---
license: apache-2.0
---
HF-version model for PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization (ACL 2022).
The original code can be found [here](https://github.com/allenai/PRIMER). You can find the script and notebook to train/evaluate the model in the original github repo.
* Note: due to the difference between the implementations of the original Longformer and the Huggingface LED model, the results of converted models are slightly different. We run a sanity check on both fine-tuned and non fine-tuned models on the **MultiNews dataset**, and show the results below:
| Model | Rouge-1 | Rouge-2 | Rouge-L |
| --- | ----------- |----------- |----------- |
| PRIMERA | 42.0 | 13.6 | 20.8|
| PRIMERA-hf | 41.7 |13.6 | 20.5|
| PRIMERA(finetuned) | 49.9 | 21.1 | 25.9|
| PRIMERA-hf(finetuned) | 49.9 | 20.9 | 25.8|
You can use it by
```
from transformers import (
AutoTokenizer,
LEDConfig,
LEDForConditionalGeneration,
)
tokenizer = AutoTokenizer.from_pretrained('allenai/PRIMERA')
config=LEDConfig.from_pretrained('allenai/PRIMERA')
model = LEDForConditionalGeneration.from_pretrained('allenai/PRIMERA')
```
| null |
Non_BioNLP
|
HF-version model for PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization (ACL 2022).
The original code can be found [here](https://github.com/allenai/PRIMER). You can find the script and notebook to train/evaluate the model in the original github repo.
* Note: due to the difference between the implementations of the original Longformer and the Huggingface LED model, the results of converted models are slightly different. We run a sanity check on both fine-tuned and non fine-tuned models on the **MultiNews dataset**, and show the results below:
| Model | Rouge-1 | Rouge-2 | Rouge-L |
| --- | ----------- |----------- |----------- |
| PRIMERA | 42.0 | 13.6 | 20.8|
| PRIMERA-hf | 41.7 |13.6 | 20.5|
| PRIMERA(finetuned) | 49.9 | 21.1 | 25.9|
| PRIMERA-hf(finetuned) | 49.9 | 20.9 | 25.8|
You can use it by
```
from transformers import (
AutoTokenizer,
LEDConfig,
LEDForConditionalGeneration,
)
tokenizer = AutoTokenizer.from_pretrained('allenai/PRIMERA')
config=LEDConfig.from_pretrained('allenai/PRIMERA')
model = LEDForConditionalGeneration.from_pretrained('allenai/PRIMERA')
```
|
{"license": "apache-2.0"}
|
task
|
[
"SUMMARIZATION"
] | 43,796 |
japanese-denim/mbart-50-finetuned-naga-to-eng
|
japanese-denim
|
translation
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"base_model:facebook/mbart-large-50",
"base_model:finetune:facebook/mbart-large-50",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-09-30T21:27:04Z |
2023-11-16T01:08:12+00:00
| 26 | 0 |
---
base_model: facebook/mbart-large-50
license: mit
metrics:
- bleu
tags:
- translation
- generated_from_trainer
model-index:
- name: mbart-50-finetuned-eng-to-naga
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. -->
# mbart-50-finetuned-eng-to-naga
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6053
- Bleu: 27.9236
## 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: 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
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.15.0
| 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. -->
# mbart-50-finetuned-eng-to-naga
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6053
- Bleu: 27.9236
## 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: 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
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.15.0
|
{"base_model": "facebook/mbart-large-50", "license": "mit", "metrics": ["bleu"], "tags": ["translation", "generated_from_trainer"], "model-index": [{"name": "mbart-50-finetuned-eng-to-naga", "results": []}]}
|
task
|
[
"TRANSLATION"
] | 43,797 |
facebook/textless_sm_et_es
|
facebook
|
audio-to-audio
|
[
"fairseq",
"audio",
"audio-to-audio",
"speech-to-speech-translation",
"license:cc-by-nc-4.0",
"region:us"
] | 2022-10-16T01:22:43Z |
2022-10-17T23:06:02+00:00
| 3 | 0 |
---
library_name: fairseq
license: cc-by-nc-4.0
tags:
- fairseq
- audio
- audio-to-audio
- speech-to-speech-translation
task: audio-to-audio
---
You can try out the model on the right of the page by uploading or recording.
For model usage, please refer to https://huggingface.co/facebook/textless_sm_cs_en
| null |
Non_BioNLP
|
You can try out the model on the right of the page by uploading or recording.
For model usage, please refer to https://huggingface.co/facebook/textless_sm_cs_en
|
{"library_name": "fairseq", "license": "cc-by-nc-4.0", "tags": ["fairseq", "audio", "audio-to-audio", "speech-to-speech-translation"], "task": "audio-to-audio"}
|
task
|
[
"TRANSLATION"
] | 43,798 |
samant/medical-ner
|
samant
|
token-classification
|
[
"transformers",
"pytorch",
"safetensors",
"distilbert",
"token-classification",
"medical",
"NER",
"healthcare",
"en",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2025-01-24T04:06:49Z |
2025-01-31T05:33:41+00:00
| 17 | 0 |
---
base_model:
- google-bert/bert-base-uncased
language:
- en
library_name: transformers
metrics:
- precision
- recall
- f1-score
- support
tags:
- medical
- NER
- healthcare
---
# Model Card for Medical NER Model
This model is a high-performance Named Entity Recognition (NER) model designed specifically for medical text. It identifies entities such as diseases, symptoms, procedures, medications, and healthcare providers with high precision and recall, making it ideal for clinical and healthcare applications.
### Model Description
- **Model type:** Named Entity Recognition (NER)
- **Language(s) (NLP):** English (en)
- **Finetuned from model :** google-bert/bert-base-uncased
This model has been fine-tuned on a medical dataset to achieve high accuracy in extracting key entities from healthcare documents.
## Uses
### Direct Use
This model is intended for extracting medical entities from clinical or healthcare-related text. It can be used for:
- Automating medical document analysis.
- Structuring unstructured healthcare data.
- Supporting healthcare AI applications.
### Downstream Use
The model can be further fine-tuned for:
- Specific medical subdomains.
- Entity classification in multi-lingual healthcare datasets.
### Out-of-Scope Use
This model is not designed for:
- General NER tasks outside the healthcare domain.
- Identifying non-medical entities or handling multi-lingual text without fine-tuning.
## Bias, Risks, and Limitations
### Risks:
- Misclassification of entities in ambiguous or highly noisy text.
- Potential underperformance on unseen medical terms or rare conditions.
### Limitations:
- The model is optimized for English and may not perform well on other languages.
- It requires clean text inputs with minimal OCR errors for best performance.
### Recommendations
Users should validate extracted entities before use in critical applications, such as medical decision-making.
## How to Get Started with the Model
```python
from transformers import pipeline
# Load the model
ner_pipeline = pipeline("ner", model="samant/medical-ner")
# Example usage
text = "The patient has been diagnosed with Type 2 Diabetes and prescribed Metformin."
entities = ner_pipeline(text)
print(entities)
| null |
BioNLP
|
# Model Card for Medical NER Model
This model is a high-performance Named Entity Recognition (NER) model designed specifically for medical text. It identifies entities such as diseases, symptoms, procedures, medications, and healthcare providers with high precision and recall, making it ideal for clinical and healthcare applications.
### Model Description
- **Model type:** Named Entity Recognition (NER)
- **Language(s) (NLP):** English (en)
- **Finetuned from model :** google-bert/bert-base-uncased
This model has been fine-tuned on a medical dataset to achieve high accuracy in extracting key entities from healthcare documents.
## Uses
### Direct Use
This model is intended for extracting medical entities from clinical or healthcare-related text. It can be used for:
- Automating medical document analysis.
- Structuring unstructured healthcare data.
- Supporting healthcare AI applications.
### Downstream Use
The model can be further fine-tuned for:
- Specific medical subdomains.
- Entity classification in multi-lingual healthcare datasets.
### Out-of-Scope Use
This model is not designed for:
- General NER tasks outside the healthcare domain.
- Identifying non-medical entities or handling multi-lingual text without fine-tuning.
## Bias, Risks, and Limitations
### Risks:
- Misclassification of entities in ambiguous or highly noisy text.
- Potential underperformance on unseen medical terms or rare conditions.
### Limitations:
- The model is optimized for English and may not perform well on other languages.
- It requires clean text inputs with minimal OCR errors for best performance.
### Recommendations
Users should validate extracted entities before use in critical applications, such as medical decision-making.
## How to Get Started with the Model
```python
from transformers import pipeline
# Load the model
ner_pipeline = pipeline("ner", model="samant/medical-ner")
# Example usage
text = "The patient has been diagnosed with Type 2 Diabetes and prescribed Metformin."
entities = ner_pipeline(text)
print(entities)
|
{"base_model": ["google-bert/bert-base-uncased"], "language": ["en"], "library_name": "transformers", "metrics": ["precision", "recall", "f1-score", "support"], "tags": ["medical", "NER", "healthcare"]}
|
task
|
[
"NAMED_ENTITY_RECOGNITION"
] | 43,799 |
carver63/distilbert-base-uncased-finetuned-emotion
|
carver63
|
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"
] | 2024-03-02T10:42:41Z |
2024-03-02T10:42:57+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
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: train[:2000]
args: split
metrics:
- type: accuracy
value: 0.885
name: Accuracy
- type: f1
value: 0.8861263581139357
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: 0.5342
- Accuracy: 0.885
- Balanced accuracy: 0.8457
- F1: 0.8861
## 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: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Balanced accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:------:|
| 1.6372 | 1.0 | 25 | 1.4302 | 0.53 | 0.2661 | 0.4247 |
| 1.3152 | 2.0 | 50 | 1.1864 | 0.57 | 0.2892 | 0.4648 |
| 1.0588 | 3.0 | 75 | 1.0524 | 0.605 | 0.3390 | 0.5390 |
| 0.8495 | 4.0 | 100 | 0.8517 | 0.76 | 0.5691 | 0.7315 |
| 0.6198 | 5.0 | 125 | 0.6699 | 0.79 | 0.6073 | 0.7671 |
| 0.4309 | 6.0 | 150 | 0.5773 | 0.835 | 0.7656 | 0.8382 |
| 0.2887 | 7.0 | 175 | 0.5278 | 0.84 | 0.7435 | 0.8391 |
| 0.203 | 8.0 | 200 | 0.4942 | 0.865 | 0.8268 | 0.8669 |
| 0.1459 | 9.0 | 225 | 0.4451 | 0.885 | 0.8189 | 0.8847 |
| 0.1053 | 10.0 | 250 | 0.4940 | 0.865 | 0.7809 | 0.8641 |
| 0.0786 | 11.0 | 275 | 0.5234 | 0.865 | 0.7746 | 0.8629 |
| 0.0659 | 12.0 | 300 | 0.5266 | 0.86 | 0.7944 | 0.8601 |
| 0.0591 | 13.0 | 325 | 0.5427 | 0.845 | 0.7628 | 0.8461 |
| 0.0456 | 14.0 | 350 | 0.5309 | 0.86 | 0.8072 | 0.8620 |
| 0.0352 | 15.0 | 375 | 0.5377 | 0.87 | 0.8119 | 0.8711 |
| 0.032 | 16.0 | 400 | 0.5320 | 0.87 | 0.7908 | 0.8690 |
| 0.0274 | 17.0 | 425 | 0.5240 | 0.87 | 0.8119 | 0.8698 |
| 0.0247 | 18.0 | 450 | 0.5326 | 0.88 | 0.8429 | 0.8812 |
| 0.0231 | 19.0 | 475 | 0.5309 | 0.88 | 0.8384 | 0.8802 |
| 0.0227 | 20.0 | 500 | 0.5342 | 0.885 | 0.8457 | 0.8861 |
### 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. -->
# 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: 0.5342
- Accuracy: 0.885
- Balanced accuracy: 0.8457
- F1: 0.8861
## 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: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Balanced accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:------:|
| 1.6372 | 1.0 | 25 | 1.4302 | 0.53 | 0.2661 | 0.4247 |
| 1.3152 | 2.0 | 50 | 1.1864 | 0.57 | 0.2892 | 0.4648 |
| 1.0588 | 3.0 | 75 | 1.0524 | 0.605 | 0.3390 | 0.5390 |
| 0.8495 | 4.0 | 100 | 0.8517 | 0.76 | 0.5691 | 0.7315 |
| 0.6198 | 5.0 | 125 | 0.6699 | 0.79 | 0.6073 | 0.7671 |
| 0.4309 | 6.0 | 150 | 0.5773 | 0.835 | 0.7656 | 0.8382 |
| 0.2887 | 7.0 | 175 | 0.5278 | 0.84 | 0.7435 | 0.8391 |
| 0.203 | 8.0 | 200 | 0.4942 | 0.865 | 0.8268 | 0.8669 |
| 0.1459 | 9.0 | 225 | 0.4451 | 0.885 | 0.8189 | 0.8847 |
| 0.1053 | 10.0 | 250 | 0.4940 | 0.865 | 0.7809 | 0.8641 |
| 0.0786 | 11.0 | 275 | 0.5234 | 0.865 | 0.7746 | 0.8629 |
| 0.0659 | 12.0 | 300 | 0.5266 | 0.86 | 0.7944 | 0.8601 |
| 0.0591 | 13.0 | 325 | 0.5427 | 0.845 | 0.7628 | 0.8461 |
| 0.0456 | 14.0 | 350 | 0.5309 | 0.86 | 0.8072 | 0.8620 |
| 0.0352 | 15.0 | 375 | 0.5377 | 0.87 | 0.8119 | 0.8711 |
| 0.032 | 16.0 | 400 | 0.5320 | 0.87 | 0.7908 | 0.8690 |
| 0.0274 | 17.0 | 425 | 0.5240 | 0.87 | 0.8119 | 0.8698 |
| 0.0247 | 18.0 | 450 | 0.5326 | 0.88 | 0.8429 | 0.8812 |
| 0.0231 | 19.0 | 475 | 0.5309 | 0.88 | 0.8384 | 0.8802 |
| 0.0227 | 20.0 | 500 | 0.5342 | 0.885 | 0.8457 | 0.8861 |
### 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": ["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": "train[:2000]", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.885, "name": "Accuracy"}, {"type": "f1", "value": 0.8861263581139357, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,800 |
echarlaix/distilbert-sst2-inc-dynamic-quantization-magnitude-pruning-0.1
|
echarlaix
|
text-classification
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"neural-compressor",
"int8",
"en",
"dataset:sst2",
"dataset:glue",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-06-06T09:51:12Z |
2023-06-13T08:47:40+00:00
| 9 | 0 |
---
datasets:
- sst2
- glue
language: en
license: apache-2.0
metrics:
- accuracy
tags:
- text-classification
- neural-compressor
- int8
---
# Dynamically quantized and pruned DistilBERT base uncased finetuned SST-2
## Table of Contents
- [Model Details](#model-details)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
## Model Details
**Model Description:** This model is a [DistilBERT](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) fine-tuned on SST-2 dynamically quantized and pruned using a magnitude pruning strategy to obtain a sparsity of 10% with [optimum-intel](https://github.com/huggingface/optimum-intel) through the usage of [Intel® Neural Compressor](https://github.com/intel/neural-compressor).
- **Model Type:** Text Classification
- **Language(s):** English
- **License:** Apache-2.0
- **Parent Model:** For more details on the original model, we encourage users to check out [this](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) model card.
## How to Get Started With the Model
This requires to install Optimum :
`pip install optimum[neural-compressor]`
To load the quantized model and run inference using the Transformers [pipelines](https://huggingface.co/docs/transformers/main/en/main_classes/pipelines), you can do as follows:
```python
from transformers import AutoTokenizer, pipeline
from optimum.intel import INCModelForSequenceClassification
model_id = "echarlaix/distilbert-sst2-inc-dynamic-quantization-magnitude-pruning-0.1"
model = INCModelForSequenceClassification.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
cls_pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
text = "He's a dreadful magician."
outputs = cls_pipe(text)
```
| null |
Non_BioNLP
|
# Dynamically quantized and pruned DistilBERT base uncased finetuned SST-2
## Table of Contents
- [Model Details](#model-details)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
## Model Details
**Model Description:** This model is a [DistilBERT](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) fine-tuned on SST-2 dynamically quantized and pruned using a magnitude pruning strategy to obtain a sparsity of 10% with [optimum-intel](https://github.com/huggingface/optimum-intel) through the usage of [Intel® Neural Compressor](https://github.com/intel/neural-compressor).
- **Model Type:** Text Classification
- **Language(s):** English
- **License:** Apache-2.0
- **Parent Model:** For more details on the original model, we encourage users to check out [this](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) model card.
## How to Get Started With the Model
This requires to install Optimum :
`pip install optimum[neural-compressor]`
To load the quantized model and run inference using the Transformers [pipelines](https://huggingface.co/docs/transformers/main/en/main_classes/pipelines), you can do as follows:
```python
from transformers import AutoTokenizer, pipeline
from optimum.intel import INCModelForSequenceClassification
model_id = "echarlaix/distilbert-sst2-inc-dynamic-quantization-magnitude-pruning-0.1"
model = INCModelForSequenceClassification.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
cls_pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
text = "He's a dreadful magician."
outputs = cls_pipe(text)
```
|
{"datasets": ["sst2", "glue"], "language": "en", "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["text-classification", "neural-compressor", "int8"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,801 |
fine-tuned/askubuntu-c-256-24
|
fine-tuned
|
feature-extraction
|
[
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"Ubuntu",
"Technical",
"Troubleshooting",
"Forum",
"Operating System",
"custom_code",
"en",
"dataset:fine-tuned/askubuntu-c-256-24",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 2024-05-15T10:45:07Z |
2024-05-15T10:45:21+00:00
| 6 | 0 |
---
datasets:
- fine-tuned/askubuntu-c-256-24
- allenai/c4
language:
- en
license: apache-2.0
pipeline_tag: feature-extraction
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
- Ubuntu
- Technical
- Troubleshooting
- Forum
- Operating System
---
This model is a fine-tuned version of [**jinaai/jina-embeddings-v2-base-en**](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) designed for the following use case:
Technical troubleshooting forum search engine for Ubuntu
## 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/askubuntu-c-256-24',
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 [**jinaai/jina-embeddings-v2-base-en**](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) designed for the following use case:
Technical troubleshooting forum search engine for Ubuntu
## 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/askubuntu-c-256-24',
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/askubuntu-c-256-24", "allenai/c4"], "language": ["en"], "license": "apache-2.0", "pipeline_tag": "feature-extraction", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity", "mteb", "Ubuntu", "Technical", "Troubleshooting", "Forum", "Operating System"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,802 |
anantkrsingh/Test
|
anantkrsingh
| null |
[
"region:us"
] | 2024-07-19T14:05:52Z |
2024-07-19T15:10:07+00:00
| 0 | 0 |
---
{}
---
# YouTube Transcript Summarizer: Flask Back-End Repository
### <i><b>Caution:</b> There is no open source license attached to this repository, which means that you can not copy/make changes without the author's permission. This repository is only for any future improvements or suggestions if someone wants to add to this project.
### So, if you are planning to use this repository for your own final year minor/major projects, then, unfortunately, you can not use this repository to submit because it was already submitted by me in the first place. This repository is only made available by me for any improvements you want to add or suggest. If I get to know that someone is using this repository as their project, then, unfortunately I would have to report this "unauthorised copying/project already built scenario" to your university/college.
### So, kindly do not fork this repository if you want to use it as your project. This repository is the author's own intellectual property, and it is only made available for the purpose of knowledge-sharing; and not unauthorised ownership.</i>
##
### This back-end also hosts the web version of the online summarizer [here](https://ytsum.herokuapp.com/web/).
**YouTube Video Transcript Summarization over Flask:** This back-end uses Flask framework to receive API calls from the client and then respond with the summarized text response. This API can work only on those YouTube videos which have well-formatted closed captions in it. The same backend also hosts a web version of the Summarizer to make those API calls in simple way and show the output within the webpage.
*Pre-requisite Knowledge:* YouTube is an American free to use online video sharing and social media platform launched in February 2005. It is currently one of the biggest video platforms where its users watch more than 1 billion hours of videos every day.\
Closed captions are the text derived from the video which are intended for adding more details (such as dialogues, speech translation, non-speech elements) for the viewer. They are widely used to understand video without understanding its audio.
*Use case Scenario:* YouTube has very large number of videos which has transcripts. Summarization would be especially helpful in the cases where videos are longer in length and different parts might have varying importance. In this sense, Summarization of the video might be useful in saving the viewer’s time. It will help in improving user productivity since they will focus only on the important text spoken in video.
## Aim
By our project, we would be building functionality for summarizing those YouTube videos in which captions are added by their owner, to generate a summarized text response through various summarization techniques. The Summarizer should be accessible to the end user in an easy way, and that is why we would be generating summary in many accessible ways.\
We will be hosting a Flask back-end server which will receive a **`GET Request`** along with the `YouTube Video Id`, selected `Algorithm Choice`, and required `ratio` of the summarized response. This server will ensure *avoiding the summarization processing at user end*.\
This approach also has scope of improving algorithm directly later, users have no need to update at their ends, thus saving users’ resources as well.
The client could be accessing this API from anywhere (say a Chrome extension) which will request our server. We would be also creating a web version of this summarizer as well as a GUI Program based on Tkinter with Command Line Integration that asks for required data and process on it directly.
In this way, we would make summarizer accessible in many ways, and reducing user’s time and effort to get the text summary on the basis of their request.
### More information about the backend
There are four endpoints:
* `/` (Root Endpoint): It displays a general purpose introductory webpage and also provides links to web summarizer and API information. You can go to this point [here](https://ytsum.herokuapp.com/).
* `/web/` (Web Summarizer Endpoint): It displays the web version of the summarizer tool. The webpage has input elements and a summarize button. After clicking summarize, the `API` is called and the response is displayed to the user. You can go to this endpoint by directly clicking [here](https://ytsum.herokuapp.com/web/).
* `/api/` (API Description Endpoint): The webpage at this endpoint describes basic API information in case you would like to use it. Feel free to learn and use our API in your projects.
You can go to this endpoint by directly clicking [here](https://ytsum.herokuapp.com/api/).
* `/summarize/` (API Endpoint): This endpoint is for **API purposes only**. That is why, the response type of the **`GET Request`** at this endpoint is in JSON format.\
More details about using our API is written below:
#### Sending request to our API
The query (or API request) to our backend can be made using following three variables only. They are:
* **`id`** : Video ID of the YouTube Video. Each video has its own unique ID in its URL.\
For example, *9No-FiEInLA* is the Video ID in *https://www.youtube.com/watch?v=9No-FiEInLA.*
* **`choice`** : Algorithm Choice for the summarizing the Transcript. There are only six accepted values in this variable.\
These choices are written along with algorithm names as follows:
* `gensim-sum` : Text Rank Algorithm Based using Gensim
* `spacy-sum` : Frequency Based Approach using Spacy.
* `nltk-sum` : Frequency Based Summarization using NLTK.
* `sumy-lsa-sum` : Latent Semantic Analysis Based using Sumy.
* `sumy-luhn-sum` : Luhn Algorithm Based using Sumy.
* `sumy-text-rank-sum` : Text Rank Algorithm Based using Sumy.
* **`percent`** : The percentage is used to present the summary in approx. `X% lines` of the available transcript.
These values in the query to our server can be used in following manner:
```
https://ytsum.herokuapp.com/summarize/?id=your-video-id&percent=your-percent&choice=your-summary-choice
```
More similar details about sending API request can also be found [here](https://ytsum.herokuapp.com/api/).
#### Receiving request from our API
Once you send a successful API request, our server will take that request and process it. After successful processing, the server will send back the relevant response to the made request. The response sent is always in the **`JSON Format`** and very much similar to below snippet:
```json
{
"message": "Subtitles for this video was fetched and summarized successfully.",
"response": {
"length_original": 32792,
"length_summary": 6087,
"processed_summary": "Your summary will be here :)",
"sentence_original": 438,
"sentence_summary": 43
},
"success": true
}
```
There might be cases, where summarization couldn't be performed (Say subtitles are not available, or subtitles are badly formatted). In this case, the JSON response would be simiiar like this:
```json
{
"message": "TranscriptsDisabled: Subtitles are disabled for this video.",
"response": null,
"success": false
}
```
### More information about the front-end
The image below shows the front-end of the web version of the summarizer.
As before mentioned, this back-end repository also hosts the web summmarizer. This basic HTML+CSS+JS webpage takes input which is required for making API requests. The webpage is self explanatory. Once you click on summarize button, the JS script makes an API request to the back-end. Once the request is completed, the received response is displayed to the user in the formatted mannner.
#### Feel free to improve this back-end, add comments and ask any queries if you have any.
##### The back-end uses an undocumented part of the YouTube API, which is called by the YouTube web-client. So there is no guarantee that it would stop working tomorrow, if they change how things work. In case that happens, I will do my best to make things work again as soon as possible if that happens. So if it stops working, let me know!
##### This is not an official tool from YouTube. I have built this package for my final year project.
| null |
Non_BioNLP
|
# YouTube Transcript Summarizer: Flask Back-End Repository
### <i><b>Caution:</b> There is no open source license attached to this repository, which means that you can not copy/make changes without the author's permission. This repository is only for any future improvements or suggestions if someone wants to add to this project.
### So, if you are planning to use this repository for your own final year minor/major projects, then, unfortunately, you can not use this repository to submit because it was already submitted by me in the first place. This repository is only made available by me for any improvements you want to add or suggest. If I get to know that someone is using this repository as their project, then, unfortunately I would have to report this "unauthorised copying/project already built scenario" to your university/college.
### So, kindly do not fork this repository if you want to use it as your project. This repository is the author's own intellectual property, and it is only made available for the purpose of knowledge-sharing; and not unauthorised ownership.</i>
##
### This back-end also hosts the web version of the online summarizer [here](https://ytsum.herokuapp.com/web/).
**YouTube Video Transcript Summarization over Flask:** This back-end uses Flask framework to receive API calls from the client and then respond with the summarized text response. This API can work only on those YouTube videos which have well-formatted closed captions in it. The same backend also hosts a web version of the Summarizer to make those API calls in simple way and show the output within the webpage.
*Pre-requisite Knowledge:* YouTube is an American free to use online video sharing and social media platform launched in February 2005. It is currently one of the biggest video platforms where its users watch more than 1 billion hours of videos every day.\
Closed captions are the text derived from the video which are intended for adding more details (such as dialogues, speech translation, non-speech elements) for the viewer. They are widely used to understand video without understanding its audio.
*Use case Scenario:* YouTube has very large number of videos which has transcripts. Summarization would be especially helpful in the cases where videos are longer in length and different parts might have varying importance. In this sense, Summarization of the video might be useful in saving the viewer’s time. It will help in improving user productivity since they will focus only on the important text spoken in video.
## Aim
By our project, we would be building functionality for summarizing those YouTube videos in which captions are added by their owner, to generate a summarized text response through various summarization techniques. The Summarizer should be accessible to the end user in an easy way, and that is why we would be generating summary in many accessible ways.\
We will be hosting a Flask back-end server which will receive a **`GET Request`** along with the `YouTube Video Id`, selected `Algorithm Choice`, and required `ratio` of the summarized response. This server will ensure *avoiding the summarization processing at user end*.\
This approach also has scope of improving algorithm directly later, users have no need to update at their ends, thus saving users’ resources as well.
The client could be accessing this API from anywhere (say a Chrome extension) which will request our server. We would be also creating a web version of this summarizer as well as a GUI Program based on Tkinter with Command Line Integration that asks for required data and process on it directly.
In this way, we would make summarizer accessible in many ways, and reducing user’s time and effort to get the text summary on the basis of their request.
### More information about the backend
There are four endpoints:
* `/` (Root Endpoint): It displays a general purpose introductory webpage and also provides links to web summarizer and API information. You can go to this point [here](https://ytsum.herokuapp.com/).
* `/web/` (Web Summarizer Endpoint): It displays the web version of the summarizer tool. The webpage has input elements and a summarize button. After clicking summarize, the `API` is called and the response is displayed to the user. You can go to this endpoint by directly clicking [here](https://ytsum.herokuapp.com/web/).
* `/api/` (API Description Endpoint): The webpage at this endpoint describes basic API information in case you would like to use it. Feel free to learn and use our API in your projects.
You can go to this endpoint by directly clicking [here](https://ytsum.herokuapp.com/api/).
* `/summarize/` (API Endpoint): This endpoint is for **API purposes only**. That is why, the response type of the **`GET Request`** at this endpoint is in JSON format.\
More details about using our API is written below:
#### Sending request to our API
The query (or API request) to our backend can be made using following three variables only. They are:
* **`id`** : Video ID of the YouTube Video. Each video has its own unique ID in its URL.\
For example, *9No-FiEInLA* is the Video ID in *https://www.youtube.com/watch?v=9No-FiEInLA.*
* **`choice`** : Algorithm Choice for the summarizing the Transcript. There are only six accepted values in this variable.\
These choices are written along with algorithm names as follows:
* `gensim-sum` : Text Rank Algorithm Based using Gensim
* `spacy-sum` : Frequency Based Approach using Spacy.
* `nltk-sum` : Frequency Based Summarization using NLTK.
* `sumy-lsa-sum` : Latent Semantic Analysis Based using Sumy.
* `sumy-luhn-sum` : Luhn Algorithm Based using Sumy.
* `sumy-text-rank-sum` : Text Rank Algorithm Based using Sumy.
* **`percent`** : The percentage is used to present the summary in approx. `X% lines` of the available transcript.
These values in the query to our server can be used in following manner:
```
https://ytsum.herokuapp.com/summarize/?id=your-video-id&percent=your-percent&choice=your-summary-choice
```
More similar details about sending API request can also be found [here](https://ytsum.herokuapp.com/api/).
#### Receiving request from our API
Once you send a successful API request, our server will take that request and process it. After successful processing, the server will send back the relevant response to the made request. The response sent is always in the **`JSON Format`** and very much similar to below snippet:
```json
{
"message": "Subtitles for this video was fetched and summarized successfully.",
"response": {
"length_original": 32792,
"length_summary": 6087,
"processed_summary": "Your summary will be here :)",
"sentence_original": 438,
"sentence_summary": 43
},
"success": true
}
```
There might be cases, where summarization couldn't be performed (Say subtitles are not available, or subtitles are badly formatted). In this case, the JSON response would be simiiar like this:
```json
{
"message": "TranscriptsDisabled: Subtitles are disabled for this video.",
"response": null,
"success": false
}
```
### More information about the front-end
The image below shows the front-end of the web version of the summarizer.
As before mentioned, this back-end repository also hosts the web summmarizer. This basic HTML+CSS+JS webpage takes input which is required for making API requests. The webpage is self explanatory. Once you click on summarize button, the JS script makes an API request to the back-end. Once the request is completed, the received response is displayed to the user in the formatted mannner.
#### Feel free to improve this back-end, add comments and ask any queries if you have any.
##### The back-end uses an undocumented part of the YouTube API, which is called by the YouTube web-client. So there is no guarantee that it would stop working tomorrow, if they change how things work. In case that happens, I will do my best to make things work again as soon as possible if that happens. So if it stops working, let me know!
##### This is not an official tool from YouTube. I have built this package for my final year project.
|
{}
|
task
|
[
"TRANSLATION",
"SUMMARIZATION"
] | 43,803 |
flaviagiammarino/pubmed-clip-vit-base-patch32
|
flaviagiammarino
|
zero-shot-image-classification
|
[
"transformers",
"pytorch",
"tf",
"jax",
"clip",
"zero-shot-image-classification",
"medical",
"vision",
"en",
"arxiv:2112.13906",
"license:mit",
"endpoints_compatible",
"region:us"
] | 2023-06-13T16:18:14Z |
2023-12-28T12:36:18+00:00
| 40,174 | 18 |
---
language:
- en
license: mit
tags:
- medical
- vision
widget:
- src: https://huggingface.co/flaviagiammarino/pubmed-clip-vit-base-patch32/resolve/main/scripts/input.jpeg
candidate_labels: Chest X-Ray, Brain MRI, Abdomen CT Scan
example_title: Abdomen CT Scan
---
# Model Card for PubMedCLIP
PubMedCLIP is a fine-tuned version of [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) for the medical domain.
## Model Description
PubMedCLIP was trained on the [Radiology Objects in COntext (ROCO)](https://github.com/razorx89/roco-dataset) dataset, a large-scale multimodal medical imaging dataset.
The ROCO dataset includes diverse imaging modalities (such as X-Ray, MRI, ultrasound, fluoroscopy, etc.) from various human body regions (such as head, spine, chest, abdomen, etc.)
captured from open-access [PubMed](https://pubmed.ncbi.nlm.nih.gov/) articles.<br>
PubMedCLIP was trained for 50 epochs with a batch size of 64 using the Adam optimizer with a learning rate of 10−5.
The authors have released three different pre-trained models at this [link](https://1drv.ms/u/s!ApXgPqe9kykTgwD4Np3-f7ODAot8?e=zLVlJ2)
which use ResNet-50, ResNet-50x4 and ViT32 as image encoders. This repository includes only the ViT32 variant of the PubMedCLIP model.<br>
- **Repository:** [PubMedCLIP Official GitHub Repository](https://github.com/sarahESL/PubMedCLIP)
- **Paper:** [Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?](https://arxiv.org/abs/2112.13906)
## Usage
```python
import requests
from PIL import Image
import matplotlib.pyplot as plt
from transformers import CLIPProcessor, CLIPModel
model = CLIPModel.from_pretrained("flaviagiammarino/pubmed-clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("flaviagiammarino/pubmed-clip-vit-base-patch32")
url = "https://huggingface.co/flaviagiammarino/pubmed-clip-vit-base-patch32/resolve/main/scripts/input.jpeg"
image = Image.open(requests.get(url, stream=True).raw)
text = ["Chest X-Ray", "Brain MRI", "Abdominal CT Scan"]
inputs = processor(text=text, images=image, return_tensors="pt", padding=True)
probs = model(**inputs).logits_per_image.softmax(dim=1).squeeze()
plt.subplots()
plt.imshow(image)
plt.title("".join([x[0] + ": " + x[1] + "\n" for x in zip(text, [format(prob, ".4%") for prob in probs])]))
plt.axis("off")
plt.tight_layout()
plt.show()
```
## Additional Information
### Licensing Information
The authors have released the model code and pre-trained checkpoints under the [MIT License](https://github.com/sarahESL/PubMedCLIP/blob/main/LICENSE).
### Citation Information
```
@article{eslami2021does,
title={Does clip benefit visual question answering in the medical domain as much as it does in the general domain?},
author={Eslami, Sedigheh and de Melo, Gerard and Meinel, Christoph},
journal={arXiv preprint arXiv:2112.13906},
year={2021}
}
```
| null |
Non_BioNLP
|
# Model Card for PubMedCLIP
PubMedCLIP is a fine-tuned version of [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) for the medical domain.
## Model Description
PubMedCLIP was trained on the [Radiology Objects in COntext (ROCO)](https://github.com/razorx89/roco-dataset) dataset, a large-scale multimodal medical imaging dataset.
The ROCO dataset includes diverse imaging modalities (such as X-Ray, MRI, ultrasound, fluoroscopy, etc.) from various human body regions (such as head, spine, chest, abdomen, etc.)
captured from open-access [PubMed](https://pubmed.ncbi.nlm.nih.gov/) articles.<br>
PubMedCLIP was trained for 50 epochs with a batch size of 64 using the Adam optimizer with a learning rate of 10−5.
The authors have released three different pre-trained models at this [link](https://1drv.ms/u/s!ApXgPqe9kykTgwD4Np3-f7ODAot8?e=zLVlJ2)
which use ResNet-50, ResNet-50x4 and ViT32 as image encoders. This repository includes only the ViT32 variant of the PubMedCLIP model.<br>
- **Repository:** [PubMedCLIP Official GitHub Repository](https://github.com/sarahESL/PubMedCLIP)
- **Paper:** [Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?](https://arxiv.org/abs/2112.13906)
## Usage
```python
import requests
from PIL import Image
import matplotlib.pyplot as plt
from transformers import CLIPProcessor, CLIPModel
model = CLIPModel.from_pretrained("flaviagiammarino/pubmed-clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("flaviagiammarino/pubmed-clip-vit-base-patch32")
url = "https://huggingface.co/flaviagiammarino/pubmed-clip-vit-base-patch32/resolve/main/scripts/input.jpeg"
image = Image.open(requests.get(url, stream=True).raw)
text = ["Chest X-Ray", "Brain MRI", "Abdominal CT Scan"]
inputs = processor(text=text, images=image, return_tensors="pt", padding=True)
probs = model(**inputs).logits_per_image.softmax(dim=1).squeeze()
plt.subplots()
plt.imshow(image)
plt.title("".join([x[0] + ": " + x[1] + "\n" for x in zip(text, [format(prob, ".4%") for prob in probs])]))
plt.axis("off")
plt.tight_layout()
plt.show()
```
## Additional Information
### Licensing Information
The authors have released the model code and pre-trained checkpoints under the [MIT License](https://github.com/sarahESL/PubMedCLIP/blob/main/LICENSE).
### Citation Information
```
@article{eslami2021does,
title={Does clip benefit visual question answering in the medical domain as much as it does in the general domain?},
author={Eslami, Sedigheh and de Melo, Gerard and Meinel, Christoph},
journal={arXiv preprint arXiv:2112.13906},
year={2021}
}
```
|
{"language": ["en"], "license": "mit", "tags": ["medical", "vision"], "widget": [{"src": "https://huggingface.co/flaviagiammarino/pubmed-clip-vit-base-patch32/resolve/main/scripts/input.jpeg", "candidate_labels": "Chest X-Ray, Brain MRI, Abdomen CT Scan", "example_title": "Abdomen CT Scan"}]}
|
task
|
[
"QUESTION_ANSWERING"
] | 43,804 |
Helsinki-NLP/opus-mt-de-fj
|
Helsinki-NLP
|
translation
|
[
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"de",
"fj",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2023-08-16T11:27:52+00:00
| 51 | 0 |
---
license: apache-2.0
tags:
- translation
---
### opus-mt-de-fj
* source languages: de
* target languages: fj
* OPUS readme: [de-fj](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-fj/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-20.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-fj/opus-2020-01-20.zip)
* test set translations: [opus-2020-01-20.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-fj/opus-2020-01-20.test.txt)
* test set scores: [opus-2020-01-20.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-fj/opus-2020-01-20.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.de.fj | 24.6 | 0.470 |
| null |
Non_BioNLP
|
### opus-mt-de-fj
* source languages: de
* target languages: fj
* OPUS readme: [de-fj](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-fj/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-20.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-fj/opus-2020-01-20.zip)
* test set translations: [opus-2020-01-20.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-fj/opus-2020-01-20.test.txt)
* test set scores: [opus-2020-01-20.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-fj/opus-2020-01-20.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.de.fj | 24.6 | 0.470 |
|
{"license": "apache-2.0", "tags": ["translation"]}
|
task
|
[
"TRANSLATION"
] | 43,805 |
assamim/t5-small-english
|
assamim
|
text2text-generation
|
[
"transformers",
"tf",
"tensorboard",
"t5",
"text2text-generation",
"generated_from_keras_callback",
"Summarization",
"T5-Small",
"dataset:Xsum",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-06-10T10:42:01Z |
2022-06-13T11:38:39+00:00
| 13 | 0 |
---
datasets:
- Xsum
tags:
- generated_from_keras_callback
- Summarization
- T5-Small
model-index:
- name: assamim/mt5-pukulenam-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. -->
# assamim/mt5-pukulenam-summarization
This model is a fine-tuned version of [T5-Small](https://huggingface.co/t5-small) on an [XSUM](https://huggingface.co/datasets/xsum) dataset
## Using this model in `transformers` (tested on 4.19.2)
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import re
news = """
The full cost of damage in Newton Stewart, one of the areas worst affected, is still being assessed.\nRepair work is ongoing in Hawick and many roads in Peeblesshire remain badly affected by standing water.\nTrains on the west coast mainline face disruption due to damage at the Lamington Viaduct.\nMany businesses and householders were affected by flooding in Newton Stewart after the River Cree overflowed into the town.\nFirst Minister Nicola Sturgeon visited the area to inspect the damage.\nThe waters breached a retaining wall, flooding many commercial properties on Victoria Street - the main shopping thoroughfare.\nJeanette Tate, who owns the Cinnamon Cafe which was badly affected, said she could not fault the multi-agency response once the flood hit.\nHowever, she said more preventative work could have been carried out to ensure the retaining wall did not fail.\n"It is difficult but I do think there is so much publicity for Dumfries and the Nith - and I totally appreciate that - but it is almost like we\'re neglected or forgotten," she said.\n"That may not be true but it is perhaps my perspective over the last few days.\n"Why were you not ready to help us a bit more when the warning and the alarm alerts had gone out?"\nMeanwhile, a flood alert remains in place across the Borders because of the constant rain.\nPeebles was badly hit by problems, sparking calls to introduce more defences in the area.\nScottish Borders Council has put a list on its website of the roads worst affected and drivers have been urged not to ignore closure signs.\nThe Labour Party\'s deputy Scottish leader Alex Rowley was in Hawick on Monday to see the situation first hand.\nHe said it was important to get the flood protection plan right but backed calls to speed up the process.\n"I was quite taken aback by the amount of damage that has been done," he said.\n"Obviously it is heart-breaking for people who have been forced out of their homes and the impact on businesses."\nHe said it was important that "immediate steps" were taken to protect the areas most vulnerable and a clear timetable put in place for flood prevention plans.\nHave you been affected by flooding in Dumfries and Galloway or the Borders? Tell us about your experience of the situation and how it was handled. Email us on [email protected] or [email protected].
"""
tokenizer = AutoTokenizer.from_pretrained("assamim/t5-small-english")
model = AutoModelForSeq2SeqLM.from_pretrained("assamim/t5-small-english", from_tf=True)
WHITESPACE_HANDLER = lambda k: re.sub('\s+', ' ', re.sub('\n+', ' ', k.strip()))
input_ids = tokenizer.encode(WHITESPACE_HANDLER(news1), return_tensors='pt')
summary_ids = model.generate(input_ids,
min_length=20,
max_length=200,
num_beams=7,
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)
```
### Framework versions
- Transformers 4.19.2
- TensorFlow 2.8.2
- Datasets 2.2.2
- Tokenizers 0.12.1
| 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. -->
# assamim/mt5-pukulenam-summarization
This model is a fine-tuned version of [T5-Small](https://huggingface.co/t5-small) on an [XSUM](https://huggingface.co/datasets/xsum) dataset
## Using this model in `transformers` (tested on 4.19.2)
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import re
news = """
The full cost of damage in Newton Stewart, one of the areas worst affected, is still being assessed.\nRepair work is ongoing in Hawick and many roads in Peeblesshire remain badly affected by standing water.\nTrains on the west coast mainline face disruption due to damage at the Lamington Viaduct.\nMany businesses and householders were affected by flooding in Newton Stewart after the River Cree overflowed into the town.\nFirst Minister Nicola Sturgeon visited the area to inspect the damage.\nThe waters breached a retaining wall, flooding many commercial properties on Victoria Street - the main shopping thoroughfare.\nJeanette Tate, who owns the Cinnamon Cafe which was badly affected, said she could not fault the multi-agency response once the flood hit.\nHowever, she said more preventative work could have been carried out to ensure the retaining wall did not fail.\n"It is difficult but I do think there is so much publicity for Dumfries and the Nith - and I totally appreciate that - but it is almost like we\'re neglected or forgotten," she said.\n"That may not be true but it is perhaps my perspective over the last few days.\n"Why were you not ready to help us a bit more when the warning and the alarm alerts had gone out?"\nMeanwhile, a flood alert remains in place across the Borders because of the constant rain.\nPeebles was badly hit by problems, sparking calls to introduce more defences in the area.\nScottish Borders Council has put a list on its website of the roads worst affected and drivers have been urged not to ignore closure signs.\nThe Labour Party\'s deputy Scottish leader Alex Rowley was in Hawick on Monday to see the situation first hand.\nHe said it was important to get the flood protection plan right but backed calls to speed up the process.\n"I was quite taken aback by the amount of damage that has been done," he said.\n"Obviously it is heart-breaking for people who have been forced out of their homes and the impact on businesses."\nHe said it was important that "immediate steps" were taken to protect the areas most vulnerable and a clear timetable put in place for flood prevention plans.\nHave you been affected by flooding in Dumfries and Galloway or the Borders? Tell us about your experience of the situation and how it was handled. Email us on [email protected] or [email protected].
"""
tokenizer = AutoTokenizer.from_pretrained("assamim/t5-small-english")
model = AutoModelForSeq2SeqLM.from_pretrained("assamim/t5-small-english", from_tf=True)
WHITESPACE_HANDLER = lambda k: re.sub('\s+', ' ', re.sub('\n+', ' ', k.strip()))
input_ids = tokenizer.encode(WHITESPACE_HANDLER(news1), return_tensors='pt')
summary_ids = model.generate(input_ids,
min_length=20,
max_length=200,
num_beams=7,
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)
```
### Framework versions
- Transformers 4.19.2
- TensorFlow 2.8.2
- Datasets 2.2.2
- Tokenizers 0.12.1
|
{"datasets": ["Xsum"], "tags": ["generated_from_keras_callback", "Summarization", "T5-Small"], "model-index": [{"name": "assamim/mt5-pukulenam-summarization", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 43,806 |
PoseyATX/FoxHunter_PigIron
|
PoseyATX
|
summarization
|
[
"transformers",
"pytorch",
"pegasus",
"text2text-generation",
"autotrain",
"summarization",
"unk",
"dataset:PoseyATX/autotrain-data-foxhunterirontesting",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-01-13T20:12:45Z |
2023-01-13T20:25:36+00:00
| 116 | 0 |
---
datasets:
- PoseyATX/autotrain-data-foxhunterirontesting
language:
- unk
tags:
- autotrain
- summarization
widget:
- text: I love AutoTrain 🤗
co2_eq_emissions:
emissions: 25.447577064303335
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 2874884135
- CO2 Emissions (in grams): 25.4476
## Validation Metrics
- Loss: 1.027
- Rouge1: 60.232
- Rouge2: 42.909
- RougeL: 47.915
- RougeLsum: 54.128
- Gen Len: 193.351
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/PoseyATX/autotrain-foxhunterirontesting-2874884135
```
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 2874884135
- CO2 Emissions (in grams): 25.4476
## Validation Metrics
- Loss: 1.027
- Rouge1: 60.232
- Rouge2: 42.909
- RougeL: 47.915
- RougeLsum: 54.128
- Gen Len: 193.351
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/PoseyATX/autotrain-foxhunterirontesting-2874884135
```
|
{"datasets": ["PoseyATX/autotrain-data-foxhunterirontesting"], "language": ["unk"], "tags": ["autotrain", "summarization"], "widget": [{"text": "I love AutoTrain 🤗"}], "co2_eq_emissions": {"emissions": 25.447577064303335}}
|
task
|
[
"SUMMARIZATION"
] | 43,807 |
spacemanidol/flan-t5-base-3-6-xsum
|
spacemanidol
|
text2text-generation
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:xsum",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2023-02-28T14:56:14Z |
2023-03-07T21:09:12+00:00
| 11 | 0 |
---
datasets:
- xsum
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: base-3-6
results:
- task:
type: summarization
name: Summarization
dataset:
name: xsum
type: xsum
config: default
split: validation
args: default
metrics:
- type: rouge
value: 36.4476
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-3-6
This model is a fine-tuned version of [x/base-3-6/](https://huggingface.co/x/base-3-6/) on the xsum dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7755
- Rouge1: 36.4476
- Rouge2: 13.8377
- Rougel: 28.9631
- Rougelsum: 28.9578
- Gen Len: 27.2105
## 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: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- 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 1.12.1+cu113
- 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. -->
# base-3-6
This model is a fine-tuned version of [x/base-3-6/](https://huggingface.co/x/base-3-6/) on the xsum dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7755
- Rouge1: 36.4476
- Rouge2: 13.8377
- Rougel: 28.9631
- Rougelsum: 28.9578
- Gen Len: 27.2105
## 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: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- 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 1.12.1+cu113
- Datasets 2.10.0
- Tokenizers 0.13.2
|
{"datasets": ["xsum"], "metrics": ["rouge"], "tags": ["generated_from_trainer"], "model-index": [{"name": "base-3-6", "results": [{"task": {"type": "summarization", "name": "Summarization"}, "dataset": {"name": "xsum", "type": "xsum", "config": "default", "split": "validation", "args": "default"}, "metrics": [{"type": "rouge", "value": 36.4476, "name": "Rouge1"}]}]}]}
|
task
|
[
"SUMMARIZATION"
] | 43,808 |
datamaran/news_fp_disambiguation_model
|
datamaran
|
text-classification
|
[
"setfit",
"safetensors",
"bert",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:TaylorAI/bge-micro-v2",
"base_model:finetune:TaylorAI/bge-micro-v2",
"region:us"
] | 2024-02-23T22:37:13Z |
2024-02-27T15:57:28+00:00
| 14 | 0 |
---
base_model: TaylorAI/bge-micro-v2
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
Base model: model_dataset_training_golden_records_jj_23022024_v4
dataset test: test_filter_golden_records_jj_23022024_test_dataset_v4
Accuracy: 0.84
Precision_weighted: 0.8401744186046513
Precision_micro: 0.84
Precision_macro: 0.8404796511627908
Recall: 0.84
F1-score: 0.8394805194805195
widget: []
inference: true
---
library_name: setfit
Base model: model_dataset_training_golden_records_jj_23022024_v4
dataset test: test_filter_golden_records_jj_23022024_test_dataset_v4
# SetFit with TaylorAI/bge-micro-v2
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [TaylorAI/bge-micro-v2](https://huggingface.co/TaylorAI/bge-micro-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
library_name: setfit
Base model: model_dataset_training_golden_records_jj_23022024_v4
dataset test: test_filter_golden_records_jj_23022024_test_dataset_v4
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [TaylorAI/bge-micro-v2](https://huggingface.co/TaylorAI/bge-micro-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
<!-- - **Number of Classes:** Unknown -->
<!-- - **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)
## 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("davidAtdm/model_dataset_training_golden_records_jj_23022024_v4")
# Run inference
preds = model("I loved the spiderman movie!")
```
<!--
### 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
### Framework Versions
- Python: 3.9.16
- SetFit: 1.0.3
- Sentence Transformers: 2.4.0
- Transformers: 4.38.1
- PyTorch: 2.2.1+cu121
- Datasets: 2.17.1
- Tokenizers: 0.15.2
## 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
|
library_name: setfit
Base model: model_dataset_training_golden_records_jj_23022024_v4
dataset test: test_filter_golden_records_jj_23022024_test_dataset_v4
# SetFit with TaylorAI/bge-micro-v2
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [TaylorAI/bge-micro-v2](https://huggingface.co/TaylorAI/bge-micro-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
library_name: setfit
Base model: model_dataset_training_golden_records_jj_23022024_v4
dataset test: test_filter_golden_records_jj_23022024_test_dataset_v4
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [TaylorAI/bge-micro-v2](https://huggingface.co/TaylorAI/bge-micro-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
<!-- - **Number of Classes:** Unknown -->
<!-- - **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)
## 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("davidAtdm/model_dataset_training_golden_records_jj_23022024_v4")
# Run inference
preds = model("I loved the spiderman movie!")
```
<!--
### 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
### Framework Versions
- Python: 3.9.16
- SetFit: 1.0.3
- Sentence Transformers: 2.4.0
- Transformers: 4.38.1
- PyTorch: 2.2.1+cu121
- Datasets: 2.17.1
- Tokenizers: 0.15.2
## 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": "TaylorAI/bge-micro-v2", "library_name": "setfit", "metrics": ["accuracy"], "pipeline_tag": "text-classification", "tags": ["setfit", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "Base model": "model_dataset_training_golden_records_jj_23022024_v4", "dataset test": "test_filter_golden_records_jj_23022024_test_dataset_v4", "Accuracy": 0.84, "Precision_weighted": 0.8401744186046513, "Precision_micro": 0.84, "Precision_macro": 0.8404796511627908, "Recall": 0.84, "F1-score": 0.8394805194805195, "widget": [], "inference": true}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,809 |
gokuls/distilbert_sa_GLUE_Experiment_mrpc_384
|
gokuls
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-01-25T04:41:54Z |
2023-01-25T04:43:52+00:00
| 132 | 0 |
---
datasets:
- glue
language:
- en
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert_sa_GLUE_Experiment_mrpc_384
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE MRPC
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- type: accuracy
value: 0.6838235294117647
name: Accuracy
- type: f1
value: 0.8122270742358079
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_sa_GLUE_Experiment_mrpc_384
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6089
- Accuracy: 0.6838
- F1: 0.8122
- Combined Score: 0.7480
## 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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6363 | 1.0 | 15 | 0.6257 | 0.6838 | 0.8122 | 0.7480 |
| 0.6306 | 2.0 | 30 | 0.6230 | 0.6838 | 0.8122 | 0.7480 |
| 0.6302 | 3.0 | 45 | 0.6227 | 0.6838 | 0.8122 | 0.7480 |
| 0.6217 | 4.0 | 60 | 0.6089 | 0.6838 | 0.8122 | 0.7480 |
| 0.5729 | 5.0 | 75 | 0.6097 | 0.6838 | 0.7817 | 0.7328 |
| 0.4868 | 6.0 | 90 | 0.6395 | 0.6789 | 0.7791 | 0.7290 |
| 0.3906 | 7.0 | 105 | 0.7014 | 0.6838 | 0.7725 | 0.7282 |
| 0.3014 | 8.0 | 120 | 0.7773 | 0.6814 | 0.7735 | 0.7274 |
| 0.2538 | 9.0 | 135 | 0.8550 | 0.6789 | 0.7730 | 0.7259 |
### Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- 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_sa_GLUE_Experiment_mrpc_384
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6089
- Accuracy: 0.6838
- F1: 0.8122
- Combined Score: 0.7480
## 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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6363 | 1.0 | 15 | 0.6257 | 0.6838 | 0.8122 | 0.7480 |
| 0.6306 | 2.0 | 30 | 0.6230 | 0.6838 | 0.8122 | 0.7480 |
| 0.6302 | 3.0 | 45 | 0.6227 | 0.6838 | 0.8122 | 0.7480 |
| 0.6217 | 4.0 | 60 | 0.6089 | 0.6838 | 0.8122 | 0.7480 |
| 0.5729 | 5.0 | 75 | 0.6097 | 0.6838 | 0.7817 | 0.7328 |
| 0.4868 | 6.0 | 90 | 0.6395 | 0.6789 | 0.7791 | 0.7290 |
| 0.3906 | 7.0 | 105 | 0.7014 | 0.6838 | 0.7725 | 0.7282 |
| 0.3014 | 8.0 | 120 | 0.7773 | 0.6814 | 0.7735 | 0.7274 |
| 0.2538 | 9.0 | 135 | 0.8550 | 0.6789 | 0.7730 | 0.7259 |
### Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2
|
{"datasets": ["glue"], "language": ["en"], "license": "apache-2.0", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert_sa_GLUE_Experiment_mrpc_384", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE MRPC", "type": "glue", "config": "mrpc", "split": "validation", "args": "mrpc"}, "metrics": [{"type": "accuracy", "value": 0.6838235294117647, "name": "Accuracy"}, {"type": "f1", "value": 0.8122270742358079, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,810 |
gokulsrinivasagan/distilbert_lda_100_v1_mrpc
|
gokulsrinivasagan
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokulsrinivasagan/distilbert_lda_100_v1",
"base_model:finetune:gokulsrinivasagan/distilbert_lda_100_v1",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-11-26T19:44:34Z |
2024-12-04T13:00:03+00:00
| 5 | 0 |
---
base_model: gokulsrinivasagan/distilbert_lda_100_v1
datasets:
- glue
language:
- en
library_name: transformers
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert_lda_100_v1_mrpc
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- type: accuracy
value: 0.7083333333333334
name: Accuracy
- type: f1
value: 0.7986463620981388
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_lda_100_v1_mrpc
This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5833
- Accuracy: 0.7083
- F1: 0.7986
- Combined Score: 0.7535
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6373 | 1.0 | 15 | 0.5942 | 0.6961 | 0.7905 | 0.7433 |
| 0.5826 | 2.0 | 30 | 0.5833 | 0.7083 | 0.7986 | 0.7535 |
| 0.5649 | 3.0 | 45 | 0.6127 | 0.7034 | 0.8207 | 0.7621 |
| 0.5344 | 4.0 | 60 | 0.5919 | 0.6912 | 0.7684 | 0.7298 |
| 0.4336 | 5.0 | 75 | 0.6949 | 0.7206 | 0.8230 | 0.7718 |
| 0.3053 | 6.0 | 90 | 0.7441 | 0.6936 | 0.7731 | 0.7334 |
| 0.1738 | 7.0 | 105 | 0.9240 | 0.6887 | 0.7728 | 0.7308 |
### 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_lda_100_v1_mrpc
This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5833
- Accuracy: 0.7083
- F1: 0.7986
- Combined Score: 0.7535
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6373 | 1.0 | 15 | 0.5942 | 0.6961 | 0.7905 | 0.7433 |
| 0.5826 | 2.0 | 30 | 0.5833 | 0.7083 | 0.7986 | 0.7535 |
| 0.5649 | 3.0 | 45 | 0.6127 | 0.7034 | 0.8207 | 0.7621 |
| 0.5344 | 4.0 | 60 | 0.5919 | 0.6912 | 0.7684 | 0.7298 |
| 0.4336 | 5.0 | 75 | 0.6949 | 0.7206 | 0.8230 | 0.7718 |
| 0.3053 | 6.0 | 90 | 0.7441 | 0.6936 | 0.7731 | 0.7334 |
| 0.1738 | 7.0 | 105 | 0.9240 | 0.6887 | 0.7728 | 0.7308 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
|
{"base_model": "gokulsrinivasagan/distilbert_lda_100_v1", "datasets": ["glue"], "language": ["en"], "library_name": "transformers", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert_lda_100_v1_mrpc", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE MRPC", "type": "glue", "args": "mrpc"}, "metrics": [{"type": "accuracy", "value": 0.7083333333333334, "name": "Accuracy"}, {"type": "f1", "value": 0.7986463620981388, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,812 |
davidberenstein1957/autotrain-aymp0-qk028
|
davidberenstein1957
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"autotrain",
"exbert",
"en",
"dataset:davidberenstein1957/follow-the-money-imdb",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2025-01-21T07:23:18Z |
2025-01-21T07:38:21+00:00
| 25 | 0 |
---
base_model: google-bert/bert-base-uncased
datasets:
- davidberenstein1957/follow-the-money-imdb
language:
- en
library_name: transformers
license: apache-2.0
tags:
- autotrain
- text-classification
- exbert
widget:
- text: I love AutoTrain
---
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
No validation metrics available
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
No validation metrics available
|
{"base_model": "google-bert/bert-base-uncased", "datasets": ["davidberenstein1957/follow-the-money-imdb"], "language": ["en"], "library_name": "transformers", "license": "apache-2.0", "tags": ["autotrain", "text-classification", "exbert"], "widget": [{"text": "I love AutoTrain"}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,813 |
thrunlab/t5-base_cola_moe_ex38_epochs-3_decoder_all_sparsity20_mare_mlp
|
thrunlab
|
text-classification
|
[
"transformers",
"pytorch",
"t5",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"base_model:google-t5/t5-base",
"base_model:finetune:google-t5/t5-base",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2023-10-26T19:46:51Z |
2023-10-26T19:55:40+00:00
| 35 | 0 |
---
base_model: t5-base
datasets:
- glue
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: t5-base_cola_moe_ex38_epochs-3_decoder_all_sparsity20_mare_mlp
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
config: cola
split: validation
args: cola
metrics:
- type: accuracy
value: 0.835091083413231
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. -->
# t5-base_cola_moe_ex38_epochs-3_decoder_all_sparsity20_mare_mlp
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6107
- Accuracy: 0.8351
## 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: 16
- eval_batch_size: 32
- seed: 1
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.54 | 0.19 | 50 | 0.9351 | 0.8178 |
| 0.508 | 0.37 | 100 | 0.7150 | 0.8332 |
| 0.5206 | 0.56 | 150 | 0.6512 | 0.8265 |
| 0.4831 | 0.75 | 200 | 0.6504 | 0.8274 |
| 0.5094 | 0.93 | 250 | 0.5474 | 0.8313 |
| 0.3632 | 1.12 | 300 | 0.6911 | 0.8226 |
| 0.3467 | 1.31 | 350 | 0.6089 | 0.8303 |
| 0.3803 | 1.5 | 400 | 0.5704 | 0.8360 |
| 0.3281 | 1.68 | 450 | 0.6079 | 0.8313 |
| 0.3239 | 1.87 | 500 | 0.5792 | 0.8284 |
| 0.2903 | 2.06 | 550 | 0.5910 | 0.8293 |
| 0.3892 | 2.24 | 600 | 0.6007 | 0.8341 |
| 0.2846 | 2.43 | 650 | 0.5993 | 0.8351 |
| 0.3209 | 2.62 | 700 | 0.6508 | 0.8360 |
| 0.2325 | 2.8 | 750 | 0.6217 | 0.8341 |
| 0.3949 | 2.99 | 800 | 0.6201 | 0.8341 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- 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. -->
# t5-base_cola_moe_ex38_epochs-3_decoder_all_sparsity20_mare_mlp
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6107
- Accuracy: 0.8351
## 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: 16
- eval_batch_size: 32
- seed: 1
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.54 | 0.19 | 50 | 0.9351 | 0.8178 |
| 0.508 | 0.37 | 100 | 0.7150 | 0.8332 |
| 0.5206 | 0.56 | 150 | 0.6512 | 0.8265 |
| 0.4831 | 0.75 | 200 | 0.6504 | 0.8274 |
| 0.5094 | 0.93 | 250 | 0.5474 | 0.8313 |
| 0.3632 | 1.12 | 300 | 0.6911 | 0.8226 |
| 0.3467 | 1.31 | 350 | 0.6089 | 0.8303 |
| 0.3803 | 1.5 | 400 | 0.5704 | 0.8360 |
| 0.3281 | 1.68 | 450 | 0.6079 | 0.8313 |
| 0.3239 | 1.87 | 500 | 0.5792 | 0.8284 |
| 0.2903 | 2.06 | 550 | 0.5910 | 0.8293 |
| 0.3892 | 2.24 | 600 | 0.6007 | 0.8341 |
| 0.2846 | 2.43 | 650 | 0.5993 | 0.8351 |
| 0.3209 | 2.62 | 700 | 0.6508 | 0.8360 |
| 0.2325 | 2.8 | 750 | 0.6217 | 0.8341 |
| 0.3949 | 2.99 | 800 | 0.6201 | 0.8341 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.14.1
|
{"base_model": "t5-base", "datasets": ["glue"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "t5-base_cola_moe_ex38_epochs-3_decoder_all_sparsity20_mare_mlp", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "config": "cola", "split": "validation", "args": "cola"}, "metrics": [{"type": "accuracy", "value": 0.835091083413231, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,814 |
AlanaBF/abf_quantized_t5_large
|
AlanaBF
| null |
[
"pytorch",
"tf",
"jax",
"safetensors",
"t5",
"license:mit",
"region:us"
] | 2024-08-04T09:07:41Z |
2024-08-04T10:32:01+00:00
| 0 | 0 |
---
license: mit
---
# Model Card for Quantized T5-Large
## Licensing
### Original Model
The base model, T5-Large, is licensed under the Apache 2.0 License. For more details, please refer to the [T5-Large Model Card](https://huggingface.co/t5-large).
### Your Model
This quantized version of T5-Large is licensed under the MIT License. The modifications include quantization and optimization for specific use cases.
#### License
This model is licensed under the [MIT License](https://opensource.org/licenses/MIT). See the `LICENSE` file for details.
### Compliance
- This model includes modifications to the original T5-Large model. The original Apache 2.0 license terms are respected, and the original license and notices are included in the distribution.
## Model Details
- **Model Description**: The Quantized T5-Large model is a version of the T5-Large model with 770 million parameters that has been quantized for a reduced memory footprint and faster inference. The T5 model is designed to handle a wide range of NLP tasks by framing all tasks as text-to-text problems.
- **Model Type**: Language model
- **Languages**: English, French, Romanian, German
- **License**: MIT
- **Related Models**: All T5 Checkpoints
- **Resources for More Information**:
- [T5 Research Paper](http://jmlr.org/papers/v21/20-074.html)
- [T5 GitHub Repo](https://github.com/google-research/text-to-text-transfer-transformer)
- [Hugging Face T5 Docs](https://huggingface.co/docs/transformers/model_doc/t5)
## Uses
- **Direct Use and Downstream Use**: This model can be used for machine translation, document summarization, question answering, and classification tasks.
- **Out-of-Scope Use**: Please refer to known limitations and consider potential biases.
## Bias, Risks, and Limitations
- **Bias and Risks**: The model may reflect biases present in the training data. Users should be aware of potential risks and limitations when applying the model to sensitive or high-stakes tasks.
## Training Details
- **Training Data**: The model is pre-trained on the Colossal Clean Crawled Corpus (C4), among other datasets.
- **Datasets Used**:
- **Unsupervised**: C4, Wiki-DPR
- **Supervised**: Various datasets for tasks like sentiment analysis, question answering, etc.
- **Training Procedure**: The T5 framework involves a comprehensive training procedure for converting every language problem into a text-to-text format. For detailed information, see the [T5 Research Paper](http://jmlr.org/papers/v21/20-074.html).
## Evaluation
- **Testing Data, Factors & Metrics**: The model was evaluated on 24 tasks. For detailed evaluation results, refer to the [T5 Research Paper](http://jmlr.org/papers/v21/20-074.html).
## Environmental Impact
- **Hardware Type**: Google Cloud TPU Pods
- **Hours Used**: [Include if available]
- **Cloud Provider**: GCP
- **Carbon Emitted**: [Include if available]
## Citation
- **BibTeX**:
```bibtex
@article{2020t5,
author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu},
title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
journal = {Journal of Machine Learning Research},
year = {2020},
volume = {21},
number = {140},
pages = {1-67},
url = {http://jmlr.org/papers/v21/20-074.html}
}
## How to Get Started With the Model
from transformers import T5Tokenizer, T5ForConditionalGeneration
# Load tokenizer and model
tokenizer = T5Tokenizer.from_pretrained("AlanaBF/abf_quantized_t5_large")
model = T5ForConditionalGeneration.from_pretrained("AlanaBF/abf_quantized_t5_large")
# Example usage
input_text = "Translate English to German: How are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
outputs = model.generate(input_ids)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
| null |
Non_BioNLP
|
# Model Card for Quantized T5-Large
## Licensing
### Original Model
The base model, T5-Large, is licensed under the Apache 2.0 License. For more details, please refer to the [T5-Large Model Card](https://huggingface.co/t5-large).
### Your Model
This quantized version of T5-Large is licensed under the MIT License. The modifications include quantization and optimization for specific use cases.
#### License
This model is licensed under the [MIT License](https://opensource.org/licenses/MIT). See the `LICENSE` file for details.
### Compliance
- This model includes modifications to the original T5-Large model. The original Apache 2.0 license terms are respected, and the original license and notices are included in the distribution.
## Model Details
- **Model Description**: The Quantized T5-Large model is a version of the T5-Large model with 770 million parameters that has been quantized for a reduced memory footprint and faster inference. The T5 model is designed to handle a wide range of NLP tasks by framing all tasks as text-to-text problems.
- **Model Type**: Language model
- **Languages**: English, French, Romanian, German
- **License**: MIT
- **Related Models**: All T5 Checkpoints
- **Resources for More Information**:
- [T5 Research Paper](http://jmlr.org/papers/v21/20-074.html)
- [T5 GitHub Repo](https://github.com/google-research/text-to-text-transfer-transformer)
- [Hugging Face T5 Docs](https://huggingface.co/docs/transformers/model_doc/t5)
## Uses
- **Direct Use and Downstream Use**: This model can be used for machine translation, document summarization, question answering, and classification tasks.
- **Out-of-Scope Use**: Please refer to known limitations and consider potential biases.
## Bias, Risks, and Limitations
- **Bias and Risks**: The model may reflect biases present in the training data. Users should be aware of potential risks and limitations when applying the model to sensitive or high-stakes tasks.
## Training Details
- **Training Data**: The model is pre-trained on the Colossal Clean Crawled Corpus (C4), among other datasets.
- **Datasets Used**:
- **Unsupervised**: C4, Wiki-DPR
- **Supervised**: Various datasets for tasks like sentiment analysis, question answering, etc.
- **Training Procedure**: The T5 framework involves a comprehensive training procedure for converting every language problem into a text-to-text format. For detailed information, see the [T5 Research Paper](http://jmlr.org/papers/v21/20-074.html).
## Evaluation
- **Testing Data, Factors & Metrics**: The model was evaluated on 24 tasks. For detailed evaluation results, refer to the [T5 Research Paper](http://jmlr.org/papers/v21/20-074.html).
## Environmental Impact
- **Hardware Type**: Google Cloud TPU Pods
- **Hours Used**: [Include if available]
- **Cloud Provider**: GCP
- **Carbon Emitted**: [Include if available]
## Citation
- **BibTeX**:
```bibtex
@article{2020t5,
author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu},
title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
journal = {Journal of Machine Learning Research},
year = {2020},
volume = {21},
number = {140},
pages = {1-67},
url = {http://jmlr.org/papers/v21/20-074.html}
}
## How to Get Started With the Model
from transformers import T5Tokenizer, T5ForConditionalGeneration
# Load tokenizer and model
tokenizer = T5Tokenizer.from_pretrained("AlanaBF/abf_quantized_t5_large")
model = T5ForConditionalGeneration.from_pretrained("AlanaBF/abf_quantized_t5_large")
# Example usage
input_text = "Translate English to German: How are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
outputs = model.generate(input_ids)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
|
{"license": "mit"}
|
task
|
[
"QUESTION_ANSWERING",
"TRANSLATION",
"SUMMARIZATION"
] | 43,815 |
HuggingFaceM4/Idefics3-8B-Llama3
|
HuggingFaceM4
|
image-text-to-text
|
[
"transformers",
"safetensors",
"idefics3",
"image-text-to-text",
"multimodal",
"vision",
"conversational",
"en",
"dataset:HuggingFaceM4/OBELICS",
"dataset:HuggingFaceM4/the_cauldron",
"dataset:HuggingFaceM4/Docmatix",
"dataset:HuggingFaceM4/WebSight",
"arxiv:2306.16527",
"arxiv:2405.02246",
"arxiv:2408.12637",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 2024-08-05T16:12:33Z |
2024-12-02T09:35:34+00:00
| 53,822 | 271 |
---
datasets:
- HuggingFaceM4/OBELICS
- HuggingFaceM4/the_cauldron
- HuggingFaceM4/Docmatix
- HuggingFaceM4/WebSight
language:
- en
library_name: transformers
license: apache-2.0
tags:
- multimodal
- vision
- image-text-to-text
---
<p align="center">
<img src="https://huggingface.co/HuggingFaceM4/idefics-80b/resolve/main/assets/IDEFICS.png" alt="Idefics-Obelics logo" width="200" height="100">
</p>
**Transformers version**: >4.46.
# Idefics3
Idefics3 is an open multimodal model that accepts arbitrary sequences of image and text inputs and produces text outputs. The model can answer questions about images, describe visual content, create stories grounded on multiple images, or simply behave as a pure language model without visual inputs. It improves upon [Idefics1](https://huggingface.co/HuggingFaceM4/idefics-80b-instruct) and [Idefics2](https://huggingface.co/HuggingFaceM4/idefics2-8b), significantly enhancing capabilities around OCR, document understanding and visual reasoning.
We release the checkpoints under the Apache 2.0.
# Model Summary
- **Developed by:** Hugging Face
- **Model type:** Multi-modal model (image+text)
- **Language(s) (NLP):** en
- **License:** Apache 2.0
- **Parent Models:** [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) and [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
- **Resources for more information:**
- Idefics1 paper: [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents
](https://huggingface.co/papers/2306.16527)
- Idefics2 paper: [What matters when building vision-language models?
](https://huggingface.co/papers/2405.02246)
- Idefics3 paper: [Building and better understanding vision-language models: insights and future directions](https://huggingface.co/papers/2408.12637)
# Uses
`Idefics3-8B` can be used to perform inference on multimodal (image + text) tasks in which the input is composed of a text query along with one (or multiple) image(s). Text and images can be arbitrarily interleaved. That includes image captioning, visual question answering, etc. These model does not support image generation.
The post-training of Idefics3-8B involves only a supervised fine-tuning stage, without RLHF alignment. As a result, the model may produce short answers or require prompt iterations to fully address the user's request. Adding a prefix to the assistant's response, such as "Let's fix this step by step" has been found to effectively influence the generated output.
To fine-tune `Idefics3-8B` on a specific task, we provide a [fine-tuning tutorial](https://github.com/merveenoyan/smol-vision/blob/main/Idefics_FT.ipynb).
Other resources for the fine-tuning of Idefics2 (can easily be adapted to Idefics3):
- With the [TRL library](https://github.com/huggingface/trl): [Script](https://gist.github.com/edbeeching/228652fc6c2b29a1641be5a5778223cb)
- With the [Hugging Face Trainer](https://huggingface.co/docs/transformers/main/en/main_classes/trainer#api-reference%20][%20transformers.Trainer): [Tutorial notebook](https://colab.research.google.com/drive/1NtcTgRbSBKN7pYD3Vdx1j9m8pt3fhFDB?usp=sharing)
# Technical summary
Idefics3 demonstrates a great improvement over Idefics2, especially in document understanding tasks. It serves as a strong foundation for various use-case specific fine-tunings.
| Model | MMMU <br>(val) | MathVista <br>(test) | MMStar <br>(val) | DocVQA <br>(test) | TextVQA <br>(val) |
|:---------------:|:----------------:|:----------------------:|:-------------------:|:--------------------:|:-----------------:|
| **Idefics2-8B** | 45.2 | 52.2 | 49.5 | 74.0 | 73.0 |
| **Idefics3-8B** | 46.6 | 58.4 | 55.9 | 87.7 | 74.9 |
**Idefics3 introduces several changes compared to Idefics2:**
- We use 169 visual tokens to encode a image of size 364x364. Each image is divided into several sub images of sizes at most 364x364, which are then encoded separately.
- For the fine-tuning datasets, we have extended [The Cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron) and added several datasets, including [Docmatix](HuggingFaceM4/Docmatix). We will push soon these datasets to the same repo of The Cauldron (TODO).
More details about the training of the model is available in our [technical report](https://huggingface.co/papers/2408.12637).
# How to Get Started
This section shows snippets of code for generation for `Idefics3-8B`.
```python
import requests
import torch
from PIL import Image
from io import BytesIO
from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image
DEVICE = "cuda:0"
# Note that passing the image urls (instead of the actual pil images) to the processor is also possible
image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
image2 = load_image("https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg")
image3 = load_image("https://cdn.britannica.com/68/170868-050-8DDE8263/Golden-Gate-Bridge-San-Francisco.jpg")
processor = AutoProcessor.from_pretrained("HuggingFaceM4/Idefics3-8B-Llama3")
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/Idefics3-8B-Llama3", torch_dtype=torch.bfloat16
).to(DEVICE)
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What do we see in this image?"},
]
},
{
"role": "assistant",
"content": [
{"type": "text", "text": "In this image, we can see the city of New York, and more specifically the Statue of Liberty."},
]
},
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "And how about this image?"},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
```
</details>
**Text generation inference**
TODO.
# Model optimizations
If your GPU allows, we first recommend loading (and running inference) in half precision (`torch.float16` or `torch.bfloat16`).
```diff
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/Idefics3-8B-Llama3",
+ torch_dtype=torch.bfloat16,
).to(DEVICE)
```
**Vision encoder efficiency**
You can choose the default resolution the images will be rescaled to by adding `size= {"longest_edge": N*364}` when initializing the processor (`AutoProcessor.from_pretrained`), with `N` your desired value.
`N=4` works best in practice (this is the default value), but for very large images, it could be interesting to pass `N=5`.
This will have an impact on the number of visual tokens passed to the language model.
If you are GPU-memory-constrained, you can decrease `N`, and choose for example `N=3` or `N=2`, especially for low resolution images.
**Using Flash-attention 2 to speed up generation**
<details><summary>Click to expand.</summary>
First, make sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) for the package installation. Simply change the snippet above with:
```diff
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/Idefics3-8B-Llama3",
+ torch_dtype=torch.bfloat16,
+ _attn_implementation="flash_attention_2",
).to(DEVICE)
```
</details>
# Misuse and Out-of-scope use
Using the model in [high-stakes](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations) settings is out of scope for this model. The model is not designed for [critical decisions](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations) nor uses with any material consequences on an individual's livelihood or wellbeing. The model outputs content that appears factual but may not be correct. Out-of-scope uses include:
- Usage for evaluating or scoring individuals, such as for employment, education, or credit
- Applying the model for critical automatic decisions, generating factual content, creating reliable summaries, or generating predictions that must be correct
Intentionally using the model for harm, violating [human rights](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations), or other kinds of malicious activities, is a misuse of this model. This includes:
- Spam generation
- Disinformation and influence operations
- Disparagement and defamation
- Harassment and abuse
- [Deception](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations)
- Unconsented impersonation and imitation
- Unconsented surveillance
# License
The model is built on top of two pre-trained models: [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) and [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct). We release the Idefics3 checkpoints under the Apache 2.0 license.
# Citation
**BibTeX:**
```bibtex
@misc{laurençon2024building,
title={Building and better understanding vision-language models: insights and future directions.},
author={Hugo Laurençon and Andrés Marafioti and Victor Sanh and Léo Tronchon},
year={2024},
eprint={2408.12637},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
# Acknowledgements
We thank @andito and @amyeroberts for helping on the integration in Transformers.
| null |
Non_BioNLP
|
<p align="center">
<img src="https://huggingface.co/HuggingFaceM4/idefics-80b/resolve/main/assets/IDEFICS.png" alt="Idefics-Obelics logo" width="200" height="100">
</p>
**Transformers version**: >4.46.
# Idefics3
Idefics3 is an open multimodal model that accepts arbitrary sequences of image and text inputs and produces text outputs. The model can answer questions about images, describe visual content, create stories grounded on multiple images, or simply behave as a pure language model without visual inputs. It improves upon [Idefics1](https://huggingface.co/HuggingFaceM4/idefics-80b-instruct) and [Idefics2](https://huggingface.co/HuggingFaceM4/idefics2-8b), significantly enhancing capabilities around OCR, document understanding and visual reasoning.
We release the checkpoints under the Apache 2.0.
# Model Summary
- **Developed by:** Hugging Face
- **Model type:** Multi-modal model (image+text)
- **Language(s) (NLP):** en
- **License:** Apache 2.0
- **Parent Models:** [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) and [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
- **Resources for more information:**
- Idefics1 paper: [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents
](https://huggingface.co/papers/2306.16527)
- Idefics2 paper: [What matters when building vision-language models?
](https://huggingface.co/papers/2405.02246)
- Idefics3 paper: [Building and better understanding vision-language models: insights and future directions](https://huggingface.co/papers/2408.12637)
# Uses
`Idefics3-8B` can be used to perform inference on multimodal (image + text) tasks in which the input is composed of a text query along with one (or multiple) image(s). Text and images can be arbitrarily interleaved. That includes image captioning, visual question answering, etc. These model does not support image generation.
The post-training of Idefics3-8B involves only a supervised fine-tuning stage, without RLHF alignment. As a result, the model may produce short answers or require prompt iterations to fully address the user's request. Adding a prefix to the assistant's response, such as "Let's fix this step by step" has been found to effectively influence the generated output.
To fine-tune `Idefics3-8B` on a specific task, we provide a [fine-tuning tutorial](https://github.com/merveenoyan/smol-vision/blob/main/Idefics_FT.ipynb).
Other resources for the fine-tuning of Idefics2 (can easily be adapted to Idefics3):
- With the [TRL library](https://github.com/huggingface/trl): [Script](https://gist.github.com/edbeeching/228652fc6c2b29a1641be5a5778223cb)
- With the [Hugging Face Trainer](https://huggingface.co/docs/transformers/main/en/main_classes/trainer#api-reference%20][%20transformers.Trainer): [Tutorial notebook](https://colab.research.google.com/drive/1NtcTgRbSBKN7pYD3Vdx1j9m8pt3fhFDB?usp=sharing)
# Technical summary
Idefics3 demonstrates a great improvement over Idefics2, especially in document understanding tasks. It serves as a strong foundation for various use-case specific fine-tunings.
| Model | MMMU <br>(val) | MathVista <br>(test) | MMStar <br>(val) | DocVQA <br>(test) | TextVQA <br>(val) |
|:---------------:|:----------------:|:----------------------:|:-------------------:|:--------------------:|:-----------------:|
| **Idefics2-8B** | 45.2 | 52.2 | 49.5 | 74.0 | 73.0 |
| **Idefics3-8B** | 46.6 | 58.4 | 55.9 | 87.7 | 74.9 |
**Idefics3 introduces several changes compared to Idefics2:**
- We use 169 visual tokens to encode a image of size 364x364. Each image is divided into several sub images of sizes at most 364x364, which are then encoded separately.
- For the fine-tuning datasets, we have extended [The Cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron) and added several datasets, including [Docmatix](HuggingFaceM4/Docmatix). We will push soon these datasets to the same repo of The Cauldron (TODO).
More details about the training of the model is available in our [technical report](https://huggingface.co/papers/2408.12637).
# How to Get Started
This section shows snippets of code for generation for `Idefics3-8B`.
```python
import requests
import torch
from PIL import Image
from io import BytesIO
from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image
DEVICE = "cuda:0"
# Note that passing the image urls (instead of the actual pil images) to the processor is also possible
image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
image2 = load_image("https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg")
image3 = load_image("https://cdn.britannica.com/68/170868-050-8DDE8263/Golden-Gate-Bridge-San-Francisco.jpg")
processor = AutoProcessor.from_pretrained("HuggingFaceM4/Idefics3-8B-Llama3")
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/Idefics3-8B-Llama3", torch_dtype=torch.bfloat16
).to(DEVICE)
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What do we see in this image?"},
]
},
{
"role": "assistant",
"content": [
{"type": "text", "text": "In this image, we can see the city of New York, and more specifically the Statue of Liberty."},
]
},
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "And how about this image?"},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
```
</details>
**Text generation inference**
TODO.
# Model optimizations
If your GPU allows, we first recommend loading (and running inference) in half precision (`torch.float16` or `torch.bfloat16`).
```diff
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/Idefics3-8B-Llama3",
+ torch_dtype=torch.bfloat16,
).to(DEVICE)
```
**Vision encoder efficiency**
You can choose the default resolution the images will be rescaled to by adding `size= {"longest_edge": N*364}` when initializing the processor (`AutoProcessor.from_pretrained`), with `N` your desired value.
`N=4` works best in practice (this is the default value), but for very large images, it could be interesting to pass `N=5`.
This will have an impact on the number of visual tokens passed to the language model.
If you are GPU-memory-constrained, you can decrease `N`, and choose for example `N=3` or `N=2`, especially for low resolution images.
**Using Flash-attention 2 to speed up generation**
<details><summary>Click to expand.</summary>
First, make sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) for the package installation. Simply change the snippet above with:
```diff
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/Idefics3-8B-Llama3",
+ torch_dtype=torch.bfloat16,
+ _attn_implementation="flash_attention_2",
).to(DEVICE)
```
</details>
# Misuse and Out-of-scope use
Using the model in [high-stakes](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations) settings is out of scope for this model. The model is not designed for [critical decisions](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations) nor uses with any material consequences on an individual's livelihood or wellbeing. The model outputs content that appears factual but may not be correct. Out-of-scope uses include:
- Usage for evaluating or scoring individuals, such as for employment, education, or credit
- Applying the model for critical automatic decisions, generating factual content, creating reliable summaries, or generating predictions that must be correct
Intentionally using the model for harm, violating [human rights](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations), or other kinds of malicious activities, is a misuse of this model. This includes:
- Spam generation
- Disinformation and influence operations
- Disparagement and defamation
- Harassment and abuse
- [Deception](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations)
- Unconsented impersonation and imitation
- Unconsented surveillance
# License
The model is built on top of two pre-trained models: [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) and [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct). We release the Idefics3 checkpoints under the Apache 2.0 license.
# Citation
**BibTeX:**
```bibtex
@misc{laurençon2024building,
title={Building and better understanding vision-language models: insights and future directions.},
author={Hugo Laurençon and Andrés Marafioti and Victor Sanh and Léo Tronchon},
year={2024},
eprint={2408.12637},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
# Acknowledgements
We thank @andito and @amyeroberts for helping on the integration in Transformers.
|
{"datasets": ["HuggingFaceM4/OBELICS", "HuggingFaceM4/the_cauldron", "HuggingFaceM4/Docmatix", "HuggingFaceM4/WebSight"], "language": ["en"], "library_name": "transformers", "license": "apache-2.0", "tags": ["multimodal", "vision", "image-text-to-text"]}
|
task
|
[
"QUESTION_ANSWERING"
] | 43,816 |
gaudi/opus-mt-lus-en-ctranslate2
|
gaudi
|
translation
|
[
"transformers",
"marian",
"ctranslate2",
"translation",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 2024-07-17T00:13:16Z |
2024-10-18T22:27:46+00:00
| 6 | 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-lus-en)
- 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-lus-en).**
## 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-lus-en --output_dir ./ctranslate2/opus-mt-lus-en-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-lus-en-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-lus-en-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-lus-en-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-lus-en) 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-lus-en)
- 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-lus-en).**
## 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-lus-en --output_dir ./ctranslate2/opus-mt-lus-en-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-lus-en-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-lus-en-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-lus-en-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-lus-en) by Helsinki-NLP.
|
{"license": "apache-2.0", "tags": ["ctranslate2", "translation"]}
|
task
|
[
"TRANSLATION"
] | 43,817 |
jpaulhunter/distilbert-base-uncased-finetuned-emotion
|
jpaulhunter
|
text-classification
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-11-15T00:19:13Z |
2023-11-15T00:22:04+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: 0.9275
name: Accuracy
- type: f1
value: 0.9275843012174648
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: 0.2144
- Accuracy: 0.9275
- F1: 0.9276
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8376 | 1.0 | 250 | 0.3132 | 0.9075 | 0.9058 |
| 0.2506 | 2.0 | 500 | 0.2144 | 0.9275 | 0.9276 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.14.6
- 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. -->
# 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: 0.2144
- Accuracy: 0.9275
- F1: 0.9276
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8376 | 1.0 | 250 | 0.3132 | 0.9075 | 0.9058 |
| 0.2506 | 2.0 | 500 | 0.2144 | 0.9275 | 0.9276 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.13.3
|
{"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": 0.9275, "name": "Accuracy"}, {"type": "f1", "value": 0.9275843012174648, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,818 |
ThuyNT03/xlm-roberta-base-Balance_Mixed-aug_backtranslation
|
ThuyNT03
|
text-classification
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-08-28T05:59:31Z |
2023-08-28T06:21:12+00:00
| 8 | 0 |
---
base_model: xlm-roberta-base
license: mit
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-base-Balance_Mixed-aug_backtranslation
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-Balance_Mixed-aug_backtranslation
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4382
- Accuracy: 0.72
- F1: 0.7219
## 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: 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: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.9831 | 1.0 | 174 | 0.9044 | 0.61 | 0.5474 |
| 0.7797 | 2.0 | 348 | 0.6469 | 0.73 | 0.7378 |
| 0.6314 | 3.0 | 522 | 0.6261 | 0.76 | 0.7619 |
| 0.4976 | 4.0 | 696 | 0.8230 | 0.72 | 0.7177 |
| 0.3719 | 5.0 | 870 | 1.0086 | 0.72 | 0.7223 |
| 0.2816 | 6.0 | 1044 | 1.3198 | 0.72 | 0.7208 |
| 0.2772 | 7.0 | 1218 | 1.3510 | 0.71 | 0.7099 |
| 0.2076 | 8.0 | 1392 | 1.4382 | 0.72 | 0.7219 |
### Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- 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. -->
# xlm-roberta-base-Balance_Mixed-aug_backtranslation
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4382
- Accuracy: 0.72
- F1: 0.7219
## 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: 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: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.9831 | 1.0 | 174 | 0.9044 | 0.61 | 0.5474 |
| 0.7797 | 2.0 | 348 | 0.6469 | 0.73 | 0.7378 |
| 0.6314 | 3.0 | 522 | 0.6261 | 0.76 | 0.7619 |
| 0.4976 | 4.0 | 696 | 0.8230 | 0.72 | 0.7177 |
| 0.3719 | 5.0 | 870 | 1.0086 | 0.72 | 0.7223 |
| 0.2816 | 6.0 | 1044 | 1.3198 | 0.72 | 0.7208 |
| 0.2772 | 7.0 | 1218 | 1.3510 | 0.71 | 0.7099 |
| 0.2076 | 8.0 | 1392 | 1.4382 | 0.72 | 0.7219 |
### Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
|
{"base_model": "xlm-roberta-base", "license": "mit", "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "xlm-roberta-base-Balance_Mixed-aug_backtranslation", "results": []}]}
|
task
|
[
"TRANSLATION"
] | 43,819 |
mogaio/pr_ebsa_fr_tran_merged25_e1_beginning_offsets_10_v3
|
mogaio
|
text-classification
|
[
"setfit",
"safetensors",
"xlm-roberta",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
"base_model:finetune:sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
"model-index",
"region:us"
] | 2024-01-02T18:32:28Z |
2024-01-02T18:33:19+00:00
| 9 | 0 |
---
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
library_name: setfit
metrics:
- '0'
- '1'
- '2'
- accuracy
- macro avg
- weighted avg
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 'Adil Hussain
Adil Hussain est reconnaissant d''avoir reçu l''enseignement de l''acteur Naseeruddin
Shah à l''époque où il fréquentait l''École nationale d''art dramatique'
- text: 'Les démocrates doivent y remporter des victoires pour gagner cinq sièges
à la Chambre et faire du député Hakeem Jeffries, de Brooklyn, le prochain président
de la Chambre des représentants Les démocrates aspirent à renverser six circonscriptions
détenues par les républicains que M. Biden a remportées en 2020, notamment celle
de M Des problèmes à venir pour les démocrates de New York en 2024 ?
Les dirigeants démocrates de New York se débattent depuis des mois avec le problème
de l''hébergement des dizaines de milliers de migrants qui ont été transportés
par bus jusqu''à New York et laissés à sa charge.
Mais une autre préoccupation se profile alors que la crise se poursuit sans qu''aucune
issue ne soit en vue : les retombées potentielles pour leur parti lors des élections
de l''année prochaine Des problèmes à venir pour les démocrates de New York en
2024 ?
Les dirigeants démocrates de New York se débattent depuis des mois avec le problème
de l''hébergement des dizaines de milliers de migrants qui ont été transportés
par bus jusqu''à New York et laissés à sa charge Les républicains ont tendance
à se sentir en sécurité lorsqu''ils parlent d''immigration - comme les démocrates
le font pour l''avortement - et sont clairement à l''attaque sur la question des
migrants à New York, tandis que les démocrates sont sur la défensive, a déclaré
Kyle Kondik, directeur de la communication pour le Centre de politique de l''Université
de Virginie, au réseau USA Today Plus de 100 000 migrants ont été transportés
à New York depuis la frontière sud depuis le printemps 2022. Environ 60 000 d''entre
eux sont hébergés dans la ville, et plus de 2 100 ont été transportés dans des
hôtels situés dans sept comtés au nord de la ville, de Yonkers à la périphérie
de Buffalo, où ils sont logés aux frais de la ville Bien que leurs opinions sur
la question de savoir si les migrants sont un avantage ou un fardeau soient plus
mitigées, de nettes majorités d''électeurs de toute la ville de New York, de la
banlieue et du nord de l''État ont déclaré que l''État devrait essayer de ralentir
l''afflux de migrants, plutôt que d''en accepter davantage et de s''efforcer d''assimiler
les nouveaux arrivants Isaac Goldberg, un stratège démocrate qui a travaillé sur
plusieurs campagnes électorales à New York, a affirmé qu''il était beaucoup trop
tôt pour prédire l''impact politique de la crise des migrants, soulignant que
les élections de 2024 n''auront lieu que dans 14 mois et que de nombreuses questions
tout aussi urgentes pourraient se poser Les publicités d''attaque des républicains
s''écrivent pratiquement d''elles-mêmes à partir d''un flot de titres et d''images
télévisées, alors que le gouverneur Kathy Hochul, le maire de New York Eric Adams
et le président Joe Biden - tous démocrates - se rejettent mutuellement la faute
et s''échangent des coups de feu pour savoir qui devrait en faire le plus Les
républicains se sont emparés de la crise des migrants, donnant un avant-goût des
campagnes de l''année prochaine Les républicains ont surenchéri : Elise Stefanik,
la New-Yorkaise qui dirige la conférence du parti démocrate à la Chambre des représentants,
Suite à la page suivante
a déclaré à Politico la semaine dernière que le parti allait consacrer 100 millions
de dollars aux campagnes dans les circonscriptions de New York'
- text: 'LE CANDIDAT A LA PRESIDENCE RAMASWAMY VEUT METTRE FIN AU SYSTEME DE VISA
H-1B AUX ETATS-UNIS
Décrivant le programme de visas H-1B comme une forme de "servitude", Vivek Ramaswamy,
candidat républicain indien-américain à l''élection présidentielle, a promis de
"vider" le système basé sur la loterie et de le remplacer par un système d''admission
méritocratique s''il remporte les élections présidentielles de 2024'
- text: 'Smith Hal Sparks Catherine Zeta-Jones son-Sampras Chris Owen Donald Glover
("Queer as Folk") a 54 ans. a 54 ans. Acteur
("Je sais ce que vous avez fait l''été dernier") a 50 ans Smith Hal Sparks Catherine
Zeta-Jones son-Sampras Chris Owen Donald Glover
("Queer as Folk") a 54 ans'
- text: 'Il a poursuivi en disant que Trump ne laisserait pas ses partisans s''approcher
de l''une de ses propriétés. "Les gens qui votent pour Trump, pour la plupart,
ne les laisseraient même pas entrer dans un putain d''hôtel [ "Les gens qui votent
pour Trump, pour la plupart, ne les laisseraient même pas entrer dans un putain
d''hôtel [...]. Allez à Mar-a-lago, voyez s''il y a des gens qui vous ressemblent"
"Combien de temps allons-nous continuer à élire des gens qui ont perdu l''élection
?"
Il a poursuivi en qualifiant les partisans de Trump de "nigauds".
"Mon Dieu, j''ai l''impression d''être dans une nation de nigauds. J''espère qu''il
y a encore des gens brillants et dynamiques qui aiment ce pays", a-t-il déclaré
"Et soudain, Trump a transformé Howard, qui était le roi de tous les médias, en
prince Harry de tous les médias. Tout le monde s''en fout Alors cette idée que
Trump est le pire type qui ait jamais marché sur la surface de la terre, pourquoi
traîniez-vous avec lui ?"
M. Failla a déclaré que cela avait "tué" M L''aversion d''Howard Stern pour Donald
Trump, c''est "tout l''ego".
Si "woke" signifie que je ne peux pas soutenir Trump, ce que je pense que cela
signifie, ou que je soutiens les personnes qui veulent être transgenres ou que
je suis pour le vaccin, appelez-moi "woke" comme vous voulez Si "woke" signifie
que je ne peux pas soutenir Trump, ce que je pense que cela signifie, ou que je
soutiens les personnes qui veulent être transgenres ou que je suis pour le vaccin,
appelez-moi "woke" comme vous voulez "Si être réveillé signifie que je ne peux
pas soutenir Trump, ce que je pense que cela signifie, ou que je soutiens les
personnes qui veulent être transgenres ou que je suis pour le vaccin, appelez-moi
réveillé comme vous le voulez" Stern a également abordé les affirmations de Trump
et de ses partisans selon lesquelles Joe Biden a remporté l''élection américaine
de 2020 grâce à des votes frauduleux "L''omnipotence médiatique de Donald Trump
a brisé Howard Stern. C''est très important", a déclaré Failla dans la vidéo (selon
OK ! Magazine). "Trump avait l''habitude de participer à l''émission de Stern
chaque semaine En réponse, Trump a partagé sur sa plateforme Truth Social un clip
de Fox News dans lequel l''animateur Jimmy Failla critique Stern.
"L''omnipotence médiatique de Donald Trump a brisé Howard Stern Mais Stern, qui
par le passé a été accusé de racisme et de sexisme dans nombre de ses sketches
à l''antenne, a été un critique virulent de Trump tout au long de sa présidence
et, plus récemment, alors qu''il se prépare à se présenter à nouveau en 2024.
En 2021, M Trump l''année prochaine.
"Je sais que je lui botterai le cul", a-t-il déclaré aux auditeurs.
L''année suivante, Stern a déclaré qu''il envisageait de se lancer dans la course
à la présidence "pour que le pays soit à nouveau juste" Trump profiter de sa célébrité
jusqu''à la Maison-Blanche.
"Cela a tué Howard parce qu''il était le roi de tous les médias "Je vais faire
la chose très simple qui remettra le pays sur le droit chemin : un vote, une personne",
a expliqué Stern, affirmant que Trump a en fait perdu l''élection de 2016 contre
Hillary Clinton qui a remporté le vote populaire - mais pas le collège électoral
Celui qui se décrit comme le "roi de tous les médias" a critiqué ouvertement l''ancien
président américain Donald Trump, les anti-vaxx et, plus récemment, Lauren Boebert,
qu''il a critiquée pour son comportement obscène dans un théâtre de Denver au
début du mois "Trump avait l''habitude de participer à l''émission de Stern chaque
semaine. Ils étaient amis. Alors cette idée que Trump est le pire type qui ait
jamais marché sur la surface de la terre, pourquoi traîniez-vous avec lui ?"
M'
inference: true
model-index:
- name: SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: '0'
value:
precision: 0.6018099547511312
recall: 0.5611814345991561
f1-score: 0.5807860262008734
support: 237
name: '0'
- type: '1'
value:
precision: 0.5602409638554217
recall: 0.6262626262626263
f1-score: 0.591414944356121
support: 297
name: '1'
- type: '2'
value:
precision: 0.7932692307692307
recall: 0.7268722466960352
f1-score: 0.7586206896551724
support: 227
name: '2'
- type: accuracy
value: 0.6360052562417872
name: Accuracy
- type: macro avg
value:
precision: 0.6517733831252612
recall: 0.6381054358526059
f1-score: 0.6436072200707222
support: 761
name: Macro Avg
- type: weighted avg
value:
precision: 0.642697294251897
recall: 0.6360052562417872
f1-score: 0.6379808452498016
support: 761
name: Weighted Avg
---
# SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-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.
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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-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:** 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 |
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| pos | <ul><li>"Xi appelle la nation à lutter pour l'unité\nLe 28 septembre, le président Xi Jinping a appelé la nation à renforcer sa confiance et à s'efforcer de rester unie dans ses efforts incessants pour construire une Chine forte et réaliser le rajeunissement national"</li><li>'"C\'est le réalisateur le plus courageux que j\'aie jamais rencontré", déclare Irwin Winkler, qui produit les films de Scorsese depuis plus de trente ans. Scorsese est peut-être surtout connu pour ses histoires policières emblématiques inspirées de sa propre éducation italo-américaine à New York, mais c\'est aussi l\'homme qui a réalisé la meilleure adaptation hollywoodienne d\'Edith Wharton, qui est passé du cadre moderne de La couleur de l\'argent à La dernière tentation du Christ et qui a dirigé une comédie musicale de Liza Minnelli reprise près de 50 ans plus tard L\'ÂGE DE L\'INNOCENCE (1993)\nAlors qu\'en 1993, Scorsese avait déjà réalisé un certain nombre de classiques new-yorkais, il se lance dans la réalisation d\'un nouveau film L\'ÂGE DE L\'INNOCENCE (1993)\nAlors qu\'en 1993, Scorsese avait déjà réalisé un certain nombre de classiques new-yorkais, il se lance dans la réalisation d\'un nouveau film.\nEn 1993, Scorsese avait déjà réalisé un certain nombre de classiques new-yorkais, mais il est entré en territoire inconnu avec ce drame romantique de l\'âge d\'or basé sur un roman Étude à l\'écran\nPour accueillir Killers of the Flower Moon à l\'écran, une étude de l\'œuvre non-Mob de Martin Scorsese.\nMARTIN SCORSESE N\'A PAS peur de ce qu\'il ne connaît pas. "C\'est le réalisateur le plus courageux que j\'aie jamais rencontré", déclare Irwin Winkler, qui produit les films de Scorsese depuis plus de trente ans SILENCE (2016)\nCe drame, qui suit des prêtres jésuites du XVIIe siècle au Japon, est peut-être le film le plus sous-estimé de Scorsese sur la foi, car il confronte les inconnus de la spiritualité. Le tournage à Taïwan s\'est déroulé dans des conditions difficiles, le temps changeant sauvagement d\'une heure à l\'autre Scorsese a dit de Silence qu\'il s\'agissait d\'un projet passionnel de plus de 25 ans.\n3. LE LOUP DE WALL STREET (2013)\nScorsese s\'est demandé si cette épopée cinétique et droguée de Wall Street était le bon film à faire à l\'époque, mais Winkler l\'a encouragé Cela n\'est pas plus évident que lorsqu\'il s\'agit des films de Scorsese qui n\'ont pas été des succès populaires, un catalogue remarquable en soi Le tournage à Taïwan s\'est déroulé dans des conditions difficiles, le temps changeant sauvagement d\'une heure à l\'autre. Scorsese a dit de Silence qu\'il s\'agissait d\'un projet passionnel de plus de 25 ans LES TUEURS DE LA FLEUR DE LUNE (2023)\nLe film est adapté du livre de David Grann sur les meurtres centenaires d\'Amérindiens Osage, mais Scorsese a considérablement élargi la perspective indigène. Il a travaillé avec Rodrigo Prieto, directeur de la photographie de ses quatre derniers films, en filmant sur les lieux de la violence et en choisissant des couleurs riches et naturalistes TAUREAU ENRAGÉ (1980)\nAu début du développement, ce brillant film de boxe avec Robert De Niro semblait voué à l\'échec. Les dirigeants le détestaient. Scorsese manquait d\'intérêt. Mais après une overdose qui l\'a conduit à l\'hôpital, le réalisateur s\'est senti à nouveau, intensément connecté à cette étude de caractère viscérale Son éclat somptueux peut être attribué au célèbre souci du détail de Scorsese. "La perfection de l\'époque", c\'est ainsi que le coiffeur Alan D\'Angerio, nommé aux Oscars, décrit le mantra de l\'équipe de conception'</li><li>"J'ai rêvé de ce jour\nCinq citoyens américains détenus depuis des années en Iran dans des conditions que les autorités américaines qualifient de brutales ont été libérés lundi et autorisés à quitter le pays par avion, à l'issue de mois de négociations secrètes, a déclaré le président Joe Biden.\nEn échange, l'Iran aura accès à 6 milliards de dollars de revenus pétroliers iraniens qui ont été gelés, et cinq citoyens iraniens emprisonnés aux États-Unis seront libérés"</li></ul> |
| obj | <ul><li>'L\'Iran a diffusé des images des deux prisonniers qui sont rentrés en République islamique dans le cadre de l\'échange, tandis que deux resteront aux États-Unis et qu\'un cinquième ira dans un pays tiers Lorsque les Américains se sont arrêtés à Doha après leur libération d\'Iran, trois d\'entre eux - Namazi, Sharghi et Morad Tahbaz - sont apparus. Ils ont serré dans leurs bras l\'ambassadeur américain au Qatar, Timmy Davis, et d\'autres personnes L\'Iran et les États-Unis ont une histoire d\'échanges de prisonniers qui remonte à la prise de l\'ambassade américaine en 1979 et à la crise des otages qui a suivi la révolution islamique Les Américains libérés par l\'Iran rentrent chez eux\nWASHINGTON >> Des Américains détenus depuis des années en Iran sont rentrés chez eux mardi, embrassant en larmes leurs proches et déclarant "Liberté !" après avoir été libérés dans le cadre d\'un accord politiquement risqué qui a vu le président Joe Biden accepter le déblocage de près de 6 milliards de dollars d\'avoirs iraniens gelés "Nous n\'avons pas connu un tel moment depuis plus de huit ans", a-t-il ajouté, en entourant de son bras son frère et son père Baquer, anciennement détenu, qui avait été libéré par l\'Iran. "C\'est incroyable.\nL\'un des autres Américains libérés, Emad Sharghi, a reçu de sa sœur, Neda, un drapeau américain et un animal en peluche qu\'elle avait offert à leur père il y a 30 ans, lorsqu\'il avait subi un pontage, a indiqué un représentant de la famille Kafrani a été inculpé en 2021 pour exportation illégale de matériel de laboratoire vers l\'Iran et blanchiment d\'argent, mais son affaire n\'a pas encore été jugée.\nSelon Nour News, Mehrdad Ansari, un Iranien condamné par les États-Unis à 63 mois de prison en 2021 pour avoir obtenu du matériel pouvant être utilisé dans des missiles, des armes électroniques, des armes nucléaires et d\'autres équipements militaires, a également été libéré Les 5,9 milliards de dollars en espèces remis à l\'Iran représentent l\'argent que la Corée du Sud devait à l\'Iran - mais qu\'elle n\'avait pas encore payé - pour du pétrole acheté avant que les États-Unis n\'imposent des sanctions sur ce type de transactions en 2019 Il est presque certain que les tensions resteront vives entre les États-Unis et l\'Iran, qui sont en conflit au sujet du programme nucléaire de Téhéran et d\'autres questions. L\'Iran affirme que son programme est pacifique, mais il enrichit aujourd\'hui de l\'uranium à un niveau plus proche que jamais de celui des armes "Aujourd\'hui, cinq Américains innocents qui étaient emprisonnés en Iran rentrent enfin chez eux", a déclaré le président démocrate dans un communiqué publié au moment où l\'avion transportant le groupe de Téhéran atterrissait à Doha, au Qatar, lundi Biden de nouvelles critiques de la part des républicains et d\'autres personnes qui estiment que l\'administration aide à stimuler l\'économie iranienne à un moment où l\'Iran représente une menace croissante pour les troupes américaines et les alliés du Moyen-Orient. Cela pourrait avoir des conséquences sur sa campagne de réélection Deux membres de la famille des Américains emprisonnés, Effie Namazi et Vida Tahbaz, qui étaient interdites de voyage en Iran, se trouvaient également dans l\'avion.\nLes 5,9 milliards de dollars en espèces remis à l\'Iran représentent l\'argent que la Corée du Sud devait à l\'Iran - mais qu\'elle n\'avait pas encore payé - pour du pétrole acheté avant que les États-Unis n\'imposent des sanctions sur ce type de transactions en 2019'</li><li>"Le ratio des prêts douteux des prêteurs philippins tombe à son niveau le plus bas depuis 4 mois\nLes prêts douteux détenus par les banques philippines ont diminué en glissement annuel à la fin du mois d'août, ramenant le ratio des prêts non performants (NPL) à son niveau le plus bas depuis quatre mois, malgré des coûts d'emprunt élevés"</li><li>'Les gouverneurs républicains du Texas et de Floride ont été critiqués pour avoir envoyé des migrants dans des villes perçues comme libérales, telles que New York et Sacramento. Mais M. Leeser, un démocrate, a déclaré que tous les migrants qui se trouvaient dans les bus d\'El Paso se rendaient volontairement dans les villes de leur choix Le maire d\'El Paso, au Texas, déclare que la ville est "au point de rupture" face à l\'afflux de migrants à la frontière\n(Reuters) - L\'afflux de migrants traversant la frontière américaine depuis le Mexique a poussé la ville d\'El Paso, au Texas, à "un point de rupture", avec plus de 2 000 personnes par jour demandant l\'asile, dépassant la capacité des refuges et mettant à rude épreuve les ressources, a déclaré son maire hier'</li></ul> |
| neg | <ul><li>'Steve Smith, directeur général de Care4Calais, a déclaré : "Aujourd\'hui, Keir Starmer avait l\'occasion d\'injecter un peu de décence et de compassion dans le débat sur les réfugiés. Au lieu de cela, il a choisi de refléter les artifices et la rhétorique de division employés par les conservateurs "Nous avons besoin d\'une plus grande tolérance à l\'égard des divergences d\'opinion dans notre politique, en particulier sur des questions sensibles telles que l\'immigration Starmer critiqué par la gauche et la droite pour son plan visant à mettre fin à la crise des petits bateaux\nKeir Starmer a été attaqué par la gauche et la droite hier soir après avoir présenté des propositions visant à résoudre la crise des petits bateaux, dans le cadre de la première intervention majeure du parti travailliste sur la question'</li><li>'Trois membres du personnel de sécurité tués au J&K\nTrois officiers - deux de l\'armée et un de la police du Jammu-et-Cachemire - ont été tués au cours d\'une opération anti-militantisme dans le district d\'Anantnag mercredi. Les forces de sécurité ont tué un militant supplémentaire au cours de l\'opération lancée mardi à Rajouri, ce qui porte leur nombre à deux Malgré le mauvais temps et un terrain hostile, le second terroriste a été poursuivi et neutralisé mercredi matin après des tirs nourris tout au long de la nuit", a déclaré un porte-parole de l\'armée basé au Jammu-et-Cachemire.\nIl a ajouté qu\'une grande quantité de matériel de guerre avait été récupérée, y compris des médicaments portant des marques pakistanaises'</li><li>'Cette annonce, bien que non confirmée, est le premier signe de l\'ampleur des enlèvements.\nOn sait que parmi les captifs se trouvent des soldats et des civils, dont des femmes, des enfants et des personnes âgées, pour la plupart des Israéliens, mais aussi des personnes d\'autres nationalités Au moins 700 personnes auraient été tuées en Israël - un bilan stupéfiant que le pays n\'avait pas connu depuis des décennies - et plus de 400 personnes auraient été tuées à Gaza En réponse, Israël a frappé plus de 800 cibles à Gaza jusqu\'à présent, a déclaré l\'armée israélienne, y compris des frappes aériennes qui ont rasé une grande partie de la ville de Beit Hanoun, dans le nord-est de l\'enclave Plusieurs médias israéliens, citant des responsables des services de secours, ont déclaré qu\'au moins 700 personnes avaient été tuées en Israël, dont 44 soldats. Le ministère de la santé de Gaza a déclaré que 413 personnes, dont 78 enfants et 41 femmes, ont été tuées dans le territoire Un responsable égyptien a déclaré qu\'Israël avait demandé l\'aide du Caire pour assurer la sécurité des otages. L\'Égypte a également discuté avec les deux parties d\'un éventuel cessez-le-feu, mais Israël n\'était pas ouvert à une trêve "à ce stade", selon ce responsable, qui a demandé à ne pas être identifié car il n\'était pas autorisé à informer les médias Une file d\'attente s\'est formée devant un poste de police du centre d\'Israël pour fournir des échantillons d\'ADN et d\'autres moyens susceptibles d\'aider à identifier des membres de la famille disparus L\'Égypte a également discuté avec les deux parties d\'un éventuel cessez-le-feu, mais Israël n\'était pas ouvert à une trêve "à ce stade", selon ce responsable, qui a demandé à ne pas être identifié car il n\'était pas autorisé à informer les médias Le Hezbollah a tiré des roquettes et des obus dimanche sur des positions israéliennes dans une zone contestée le long de la frontière, et Israël a riposté en utilisant des drones armés. L\'armée israélienne a déclaré que la situation était calme après l\'échange Israël a l\'habitude de procéder à des échanges très déséquilibrés pour ramener les Israéliens captifs chez eux.\nUn responsable égyptien a déclaré qu\'Israël avait demandé l\'aide du Caire pour assurer la sécurité des otages Au cours des quatre dernières décennies, Israël a mené des campagnes militaires de grande envergure au Liban et à Gaza, qu\'il a présentées comme des guerres, mais sans déclaration officielle Israël riposte au Hamas et le bilan s\'alourdit\nLe gouvernement israélien a officiellement déclaré la guerre et donné le feu vert à des "mesures militaires significatives" en représailles à l\'attaque surprise du Hamas Entre-temps, le Hamas et le Jihad islamique, plus petit groupe, ont affirmé avoir capturé plus de 130 personnes à l\'intérieur d\'Israël et les avoir emmenées à Gaza, déclarant qu\'elles seraient échangées contre la libération de milliers de Palestiniens emprisonnés par Israël Le nombre élevé de morts et la lenteur de la réaction à l\'assaut ont mis en évidence une défaillance majeure des services de renseignement et ébranlé l\'idée longtemps répandue selon laquelle Israël a des yeux et des oreilles partout dans le petit territoire densément peuplé qu\'il contrôle depuis des dizaines d\'années La déclaration de guerre laissait présager une intensification des combats, et l\'une des principales questions était de savoir si Israël lancerait un assaut terrestre dans la bande de Gaza, ce qui, par le passé, a entraîné une augmentation du nombre de victimes Dans le nord d\'Israël, un bref échange de frappes avec le groupe militant libanais Hezbollah a ravivé les craintes que les combats ne se transforment en une guerre régionale plus large Israël a déclaré avoir fait intervenir des forces spéciales pour tenter de reprendre le contrôle de quatre sites israéliens aux combattants du Hamas, dont deux kibboutzim dans lesquels les militants avaient pénétré plus tôt dans leurs attaques'</li></ul> |
## Evaluation
### Metrics
| Label | 0 | 1 | 2 | Accuracy | Macro Avg | Weighted Avg |
|:--------|:----------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------|:---------|:----------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|
| **all** | {'precision': 0.6018099547511312, 'recall': 0.5611814345991561, 'f1-score': 0.5807860262008734, 'support': 237} | {'precision': 0.5602409638554217, 'recall': 0.6262626262626263, 'f1-score': 0.591414944356121, 'support': 297} | {'precision': 0.7932692307692307, 'recall': 0.7268722466960352, 'f1-score': 0.7586206896551724, 'support': 227} | 0.6360 | {'precision': 0.6517733831252612, 'recall': 0.6381054358526059, 'f1-score': 0.6436072200707222, 'support': 761} | {'precision': 0.642697294251897, 'recall': 0.6360052562417872, 'f1-score': 0.6379808452498016, 'support': 761} |
## 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("mogaio/pr_ebsa_fr_tran_merged25_e1_beginning_offsets_10_v3")
# Run inference
preds = model("Adil Hussain
Adil Hussain est reconnaissant d'avoir reçu l'enseignement de l'acteur Naseeruddin Shah à l'époque où il fréquentait l'École nationale d'art dramatique")
```
<!--
### 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 | 1 | 243.9997 | 2071 |
| Label | Training Sample Count |
|:------|:----------------------|
| neg | 912 |
| obj | 1220 |
| pos | 908 |
### Training Hyperparameters
- batch_size: (8, 8)
- num_epochs: (10, 10)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 1
- 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: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:--------:|:-------------:|:---------------:|
| 0.0013 | 1 | 0.3526 | - |
| 0.0658 | 50 | 0.3825 | - |
| 0.1316 | 100 | 0.2039 | - |
| 0.1974 | 150 | 0.2579 | - |
| 0.2632 | 200 | 0.3062 | - |
| 0.3289 | 250 | 0.1744 | - |
| 0.3947 | 300 | 0.1571 | - |
| 0.4605 | 350 | 0.222 | - |
| 0.5263 | 400 | 0.2697 | - |
| 0.5921 | 450 | 0.2507 | - |
| 0.6579 | 500 | 0.311 | - |
| 0.7237 | 550 | 0.3169 | - |
| 0.7895 | 600 | 0.1766 | - |
| 0.8553 | 650 | 0.1756 | - |
| 0.9211 | 700 | 0.2497 | - |
| 0.9868 | 750 | 0.0889 | - |
| 1.0 | 760 | - | 0.2281 |
| 1.0526 | 800 | 0.1036 | - |
| 1.1184 | 850 | 0.3135 | - |
| 1.1842 | 900 | 0.1744 | - |
| 1.25 | 950 | 0.3287 | - |
| 1.3158 | 1000 | 0.1816 | - |
| 1.3816 | 1050 | 0.231 | - |
| 1.4474 | 1100 | 0.153 | - |
| 1.5132 | 1150 | 0.2131 | - |
| 1.5789 | 1200 | 0.1358 | - |
| 1.6447 | 1250 | 0.276 | - |
| 1.7105 | 1300 | 0.2646 | - |
| 1.7763 | 1350 | 0.0337 | - |
| 1.8421 | 1400 | 0.158 | - |
| 1.9079 | 1450 | 0.1123 | - |
| 1.9737 | 1500 | 0.0889 | - |
| **2.0** | **1520** | **-** | **0.2268** |
| 2.0395 | 1550 | 0.2369 | - |
| 2.1053 | 1600 | 0.196 | - |
| 2.1711 | 1650 | 0.2799 | - |
| 2.2368 | 1700 | 0.073 | - |
| 2.3026 | 1750 | 0.2392 | - |
| 2.3684 | 1800 | 0.1551 | - |
| 2.4342 | 1850 | 0.178 | - |
| 2.5 | 1900 | 0.1719 | - |
| 2.5658 | 1950 | 0.1203 | - |
| 2.6316 | 2000 | 0.1502 | - |
| 2.6974 | 2050 | 0.0963 | - |
| 2.7632 | 2100 | 0.1566 | - |
| 2.8289 | 2150 | 0.1273 | - |
| 2.8947 | 2200 | 0.264 | - |
| 2.9605 | 2250 | 0.0736 | - |
| 3.0 | 2280 | - | 0.2385 |
| 3.0263 | 2300 | 0.1577 | - |
| 3.0921 | 2350 | 0.1613 | - |
| 3.1579 | 2400 | 0.2313 | - |
| 3.2237 | 2450 | 0.1134 | - |
| 3.2895 | 2500 | 0.0593 | - |
| 3.3553 | 2550 | 0.0395 | - |
| 3.4211 | 2600 | 0.119 | - |
| 3.4868 | 2650 | 0.0152 | - |
| 3.5526 | 2700 | 0.019 | - |
| 3.6184 | 2750 | 0.1056 | - |
| 3.6842 | 2800 | 0.1355 | - |
| 3.75 | 2850 | 0.2262 | - |
| 3.8158 | 2900 | 0.102 | - |
| 3.8816 | 2950 | 0.2388 | - |
| 3.9474 | 3000 | 0.1755 | - |
| 4.0 | 3040 | - | 0.2576 |
| 4.0132 | 3050 | 0.0957 | - |
| 4.0789 | 3100 | 0.2034 | - |
| 4.1447 | 3150 | 0.0076 | - |
| 4.2105 | 3200 | 0.0431 | - |
| 4.2763 | 3250 | 0.2228 | - |
| 4.3421 | 3300 | 0.0124 | - |
| 4.4079 | 3350 | 0.2316 | - |
| 4.4737 | 3400 | 0.037 | - |
| 4.5395 | 3450 | 0.1812 | - |
| 4.6053 | 3500 | 0.2115 | - |
| 4.6711 | 3550 | 0.2534 | - |
| 4.7368 | 3600 | 0.1833 | - |
| 4.8026 | 3650 | 0.0135 | - |
| 4.8684 | 3700 | 0.1169 | - |
| 4.9342 | 3750 | 0.0093 | - |
| 5.0 | 3800 | 0.0728 | 0.2787 |
| 5.0658 | 3850 | 0.022 | - |
| 5.1316 | 3900 | 0.0586 | - |
| 5.1974 | 3950 | 0.002 | - |
| 5.2632 | 4000 | 0.1112 | - |
| 5.3289 | 4050 | 0.0902 | - |
| 5.3947 | 4100 | 0.0002 | - |
| 5.4605 | 4150 | 0.108 | - |
| 5.5263 | 4200 | 0.0158 | - |
| 5.5921 | 4250 | 0.0725 | - |
| 5.6579 | 4300 | 0.0014 | - |
| 5.7237 | 4350 | 0.2018 | - |
| 5.7895 | 4400 | 0.0023 | - |
| 5.8553 | 4450 | 0.002 | - |
| 5.9211 | 4500 | 0.213 | - |
| 5.9868 | 4550 | 0.0034 | - |
| 6.0 | 4560 | - | 0.2994 |
| 6.0526 | 4600 | 0.1203 | - |
| 6.1184 | 4650 | 0.1615 | - |
| 6.1842 | 4700 | 0.1968 | - |
| 6.25 | 4750 | 0.004 | - |
| 6.3158 | 4800 | 0.0018 | - |
| 6.3816 | 4850 | 0.048 | - |
| 6.4474 | 4900 | 0.0748 | - |
| 6.5132 | 4950 | 0.0007 | - |
| 6.5789 | 5000 | 0.0019 | - |
| 6.6447 | 5050 | 0.0015 | - |
| 6.7105 | 5100 | 0.0075 | - |
| 6.7763 | 5150 | 0.0012 | - |
| 6.8421 | 5200 | 0.0016 | - |
| 6.9079 | 5250 | 0.0009 | - |
| 6.9737 | 5300 | 0.0004 | - |
| 7.0 | 5320 | - | 0.2721 |
| 7.0395 | 5350 | 0.0142 | - |
| 7.1053 | 5400 | 0.0527 | - |
| 7.1711 | 5450 | 0.0019 | - |
| 7.2368 | 5500 | 0.0024 | - |
| 7.3026 | 5550 | 0.0002 | - |
| 7.3684 | 5600 | 0.0349 | - |
| 7.4342 | 5650 | 0.0008 | - |
| 7.5 | 5700 | 0.0008 | - |
| 7.5658 | 5750 | 0.0005 | - |
| 7.6316 | 5800 | 0.0002 | - |
| 7.6974 | 5850 | 0.0024 | - |
| 7.7632 | 5900 | 0.0017 | - |
| 7.8289 | 5950 | 0.0002 | - |
| 7.8947 | 6000 | 0.0028 | - |
| 7.9605 | 6050 | 0.0124 | - |
| 8.0 | 6080 | - | 0.3064 |
| 8.0263 | 6100 | 0.0038 | - |
| 8.0921 | 6150 | 0.064 | - |
| 8.1579 | 6200 | 0.0007 | - |
| 8.2237 | 6250 | 0.0022 | - |
| 8.2895 | 6300 | 0.0012 | - |
| 8.3553 | 6350 | 0.0103 | - |
| 8.4211 | 6400 | 0.0008 | - |
| 8.4868 | 6450 | 0.0058 | - |
| 8.5526 | 6500 | 0.0046 | - |
| 8.6184 | 6550 | 0.1061 | - |
| 8.6842 | 6600 | 0.0005 | - |
| 8.75 | 6650 | 0.1509 | - |
| 8.8158 | 6700 | 0.0027 | - |
| 8.8816 | 6750 | 0.0002 | - |
| 8.9474 | 6800 | 0.0006 | - |
| 9.0 | 6840 | - | 0.3014 |
| 9.0132 | 6850 | 0.0018 | - |
| 9.0789 | 6900 | 0.0006 | - |
| 9.1447 | 6950 | 0.0003 | - |
| 9.2105 | 7000 | 0.0007 | - |
| 9.2763 | 7050 | 0.0006 | - |
| 9.3421 | 7100 | 0.0003 | - |
| 9.4079 | 7150 | 0.1859 | - |
| 9.4737 | 7200 | 0.0009 | - |
| 9.5395 | 7250 | 0.12 | - |
| 9.6053 | 7300 | 0.0148 | - |
| 9.6711 | 7350 | 0.0002 | - |
| 9.7368 | 7400 | 0.0005 | - |
| 9.8026 | 7450 | 0.1027 | - |
| 9.8684 | 7500 | 0.0002 | - |
| 9.9342 | 7550 | 0.0004 | - |
| 10.0 | 7600 | 0.0003 | 0.3075 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.1
- Sentence Transformers: 2.2.2
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.0
## 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-mpnet-base-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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-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.
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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-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:** 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 |
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| pos | <ul><li>"Xi appelle la nation à lutter pour l'unité\nLe 28 septembre, le président Xi Jinping a appelé la nation à renforcer sa confiance et à s'efforcer de rester unie dans ses efforts incessants pour construire une Chine forte et réaliser le rajeunissement national"</li><li>'"C\'est le réalisateur le plus courageux que j\'aie jamais rencontré", déclare Irwin Winkler, qui produit les films de Scorsese depuis plus de trente ans. Scorsese est peut-être surtout connu pour ses histoires policières emblématiques inspirées de sa propre éducation italo-américaine à New York, mais c\'est aussi l\'homme qui a réalisé la meilleure adaptation hollywoodienne d\'Edith Wharton, qui est passé du cadre moderne de La couleur de l\'argent à La dernière tentation du Christ et qui a dirigé une comédie musicale de Liza Minnelli reprise près de 50 ans plus tard L\'ÂGE DE L\'INNOCENCE (1993)\nAlors qu\'en 1993, Scorsese avait déjà réalisé un certain nombre de classiques new-yorkais, il se lance dans la réalisation d\'un nouveau film L\'ÂGE DE L\'INNOCENCE (1993)\nAlors qu\'en 1993, Scorsese avait déjà réalisé un certain nombre de classiques new-yorkais, il se lance dans la réalisation d\'un nouveau film.\nEn 1993, Scorsese avait déjà réalisé un certain nombre de classiques new-yorkais, mais il est entré en territoire inconnu avec ce drame romantique de l\'âge d\'or basé sur un roman Étude à l\'écran\nPour accueillir Killers of the Flower Moon à l\'écran, une étude de l\'œuvre non-Mob de Martin Scorsese.\nMARTIN SCORSESE N\'A PAS peur de ce qu\'il ne connaît pas. "C\'est le réalisateur le plus courageux que j\'aie jamais rencontré", déclare Irwin Winkler, qui produit les films de Scorsese depuis plus de trente ans SILENCE (2016)\nCe drame, qui suit des prêtres jésuites du XVIIe siècle au Japon, est peut-être le film le plus sous-estimé de Scorsese sur la foi, car il confronte les inconnus de la spiritualité. Le tournage à Taïwan s\'est déroulé dans des conditions difficiles, le temps changeant sauvagement d\'une heure à l\'autre Scorsese a dit de Silence qu\'il s\'agissait d\'un projet passionnel de plus de 25 ans.\n3. LE LOUP DE WALL STREET (2013)\nScorsese s\'est demandé si cette épopée cinétique et droguée de Wall Street était le bon film à faire à l\'époque, mais Winkler l\'a encouragé Cela n\'est pas plus évident que lorsqu\'il s\'agit des films de Scorsese qui n\'ont pas été des succès populaires, un catalogue remarquable en soi Le tournage à Taïwan s\'est déroulé dans des conditions difficiles, le temps changeant sauvagement d\'une heure à l\'autre. Scorsese a dit de Silence qu\'il s\'agissait d\'un projet passionnel de plus de 25 ans LES TUEURS DE LA FLEUR DE LUNE (2023)\nLe film est adapté du livre de David Grann sur les meurtres centenaires d\'Amérindiens Osage, mais Scorsese a considérablement élargi la perspective indigène. Il a travaillé avec Rodrigo Prieto, directeur de la photographie de ses quatre derniers films, en filmant sur les lieux de la violence et en choisissant des couleurs riches et naturalistes TAUREAU ENRAGÉ (1980)\nAu début du développement, ce brillant film de boxe avec Robert De Niro semblait voué à l\'échec. Les dirigeants le détestaient. Scorsese manquait d\'intérêt. Mais après une overdose qui l\'a conduit à l\'hôpital, le réalisateur s\'est senti à nouveau, intensément connecté à cette étude de caractère viscérale Son éclat somptueux peut être attribué au célèbre souci du détail de Scorsese. "La perfection de l\'époque", c\'est ainsi que le coiffeur Alan D\'Angerio, nommé aux Oscars, décrit le mantra de l\'équipe de conception'</li><li>"J'ai rêvé de ce jour\nCinq citoyens américains détenus depuis des années en Iran dans des conditions que les autorités américaines qualifient de brutales ont été libérés lundi et autorisés à quitter le pays par avion, à l'issue de mois de négociations secrètes, a déclaré le président Joe Biden.\nEn échange, l'Iran aura accès à 6 milliards de dollars de revenus pétroliers iraniens qui ont été gelés, et cinq citoyens iraniens emprisonnés aux États-Unis seront libérés"</li></ul> |
| obj | <ul><li>'L\'Iran a diffusé des images des deux prisonniers qui sont rentrés en République islamique dans le cadre de l\'échange, tandis que deux resteront aux États-Unis et qu\'un cinquième ira dans un pays tiers Lorsque les Américains se sont arrêtés à Doha après leur libération d\'Iran, trois d\'entre eux - Namazi, Sharghi et Morad Tahbaz - sont apparus. Ils ont serré dans leurs bras l\'ambassadeur américain au Qatar, Timmy Davis, et d\'autres personnes L\'Iran et les États-Unis ont une histoire d\'échanges de prisonniers qui remonte à la prise de l\'ambassade américaine en 1979 et à la crise des otages qui a suivi la révolution islamique Les Américains libérés par l\'Iran rentrent chez eux\nWASHINGTON >> Des Américains détenus depuis des années en Iran sont rentrés chez eux mardi, embrassant en larmes leurs proches et déclarant "Liberté !" après avoir été libérés dans le cadre d\'un accord politiquement risqué qui a vu le président Joe Biden accepter le déblocage de près de 6 milliards de dollars d\'avoirs iraniens gelés "Nous n\'avons pas connu un tel moment depuis plus de huit ans", a-t-il ajouté, en entourant de son bras son frère et son père Baquer, anciennement détenu, qui avait été libéré par l\'Iran. "C\'est incroyable.\nL\'un des autres Américains libérés, Emad Sharghi, a reçu de sa sœur, Neda, un drapeau américain et un animal en peluche qu\'elle avait offert à leur père il y a 30 ans, lorsqu\'il avait subi un pontage, a indiqué un représentant de la famille Kafrani a été inculpé en 2021 pour exportation illégale de matériel de laboratoire vers l\'Iran et blanchiment d\'argent, mais son affaire n\'a pas encore été jugée.\nSelon Nour News, Mehrdad Ansari, un Iranien condamné par les États-Unis à 63 mois de prison en 2021 pour avoir obtenu du matériel pouvant être utilisé dans des missiles, des armes électroniques, des armes nucléaires et d\'autres équipements militaires, a également été libéré Les 5,9 milliards de dollars en espèces remis à l\'Iran représentent l\'argent que la Corée du Sud devait à l\'Iran - mais qu\'elle n\'avait pas encore payé - pour du pétrole acheté avant que les États-Unis n\'imposent des sanctions sur ce type de transactions en 2019 Il est presque certain que les tensions resteront vives entre les États-Unis et l\'Iran, qui sont en conflit au sujet du programme nucléaire de Téhéran et d\'autres questions. L\'Iran affirme que son programme est pacifique, mais il enrichit aujourd\'hui de l\'uranium à un niveau plus proche que jamais de celui des armes "Aujourd\'hui, cinq Américains innocents qui étaient emprisonnés en Iran rentrent enfin chez eux", a déclaré le président démocrate dans un communiqué publié au moment où l\'avion transportant le groupe de Téhéran atterrissait à Doha, au Qatar, lundi Biden de nouvelles critiques de la part des républicains et d\'autres personnes qui estiment que l\'administration aide à stimuler l\'économie iranienne à un moment où l\'Iran représente une menace croissante pour les troupes américaines et les alliés du Moyen-Orient. Cela pourrait avoir des conséquences sur sa campagne de réélection Deux membres de la famille des Américains emprisonnés, Effie Namazi et Vida Tahbaz, qui étaient interdites de voyage en Iran, se trouvaient également dans l\'avion.\nLes 5,9 milliards de dollars en espèces remis à l\'Iran représentent l\'argent que la Corée du Sud devait à l\'Iran - mais qu\'elle n\'avait pas encore payé - pour du pétrole acheté avant que les États-Unis n\'imposent des sanctions sur ce type de transactions en 2019'</li><li>"Le ratio des prêts douteux des prêteurs philippins tombe à son niveau le plus bas depuis 4 mois\nLes prêts douteux détenus par les banques philippines ont diminué en glissement annuel à la fin du mois d'août, ramenant le ratio des prêts non performants (NPL) à son niveau le plus bas depuis quatre mois, malgré des coûts d'emprunt élevés"</li><li>'Les gouverneurs républicains du Texas et de Floride ont été critiqués pour avoir envoyé des migrants dans des villes perçues comme libérales, telles que New York et Sacramento. Mais M. Leeser, un démocrate, a déclaré que tous les migrants qui se trouvaient dans les bus d\'El Paso se rendaient volontairement dans les villes de leur choix Le maire d\'El Paso, au Texas, déclare que la ville est "au point de rupture" face à l\'afflux de migrants à la frontière\n(Reuters) - L\'afflux de migrants traversant la frontière américaine depuis le Mexique a poussé la ville d\'El Paso, au Texas, à "un point de rupture", avec plus de 2 000 personnes par jour demandant l\'asile, dépassant la capacité des refuges et mettant à rude épreuve les ressources, a déclaré son maire hier'</li></ul> |
| neg | <ul><li>'Steve Smith, directeur général de Care4Calais, a déclaré : "Aujourd\'hui, Keir Starmer avait l\'occasion d\'injecter un peu de décence et de compassion dans le débat sur les réfugiés. Au lieu de cela, il a choisi de refléter les artifices et la rhétorique de division employés par les conservateurs "Nous avons besoin d\'une plus grande tolérance à l\'égard des divergences d\'opinion dans notre politique, en particulier sur des questions sensibles telles que l\'immigration Starmer critiqué par la gauche et la droite pour son plan visant à mettre fin à la crise des petits bateaux\nKeir Starmer a été attaqué par la gauche et la droite hier soir après avoir présenté des propositions visant à résoudre la crise des petits bateaux, dans le cadre de la première intervention majeure du parti travailliste sur la question'</li><li>'Trois membres du personnel de sécurité tués au J&K\nTrois officiers - deux de l\'armée et un de la police du Jammu-et-Cachemire - ont été tués au cours d\'une opération anti-militantisme dans le district d\'Anantnag mercredi. Les forces de sécurité ont tué un militant supplémentaire au cours de l\'opération lancée mardi à Rajouri, ce qui porte leur nombre à deux Malgré le mauvais temps et un terrain hostile, le second terroriste a été poursuivi et neutralisé mercredi matin après des tirs nourris tout au long de la nuit", a déclaré un porte-parole de l\'armée basé au Jammu-et-Cachemire.\nIl a ajouté qu\'une grande quantité de matériel de guerre avait été récupérée, y compris des médicaments portant des marques pakistanaises'</li><li>'Cette annonce, bien que non confirmée, est le premier signe de l\'ampleur des enlèvements.\nOn sait que parmi les captifs se trouvent des soldats et des civils, dont des femmes, des enfants et des personnes âgées, pour la plupart des Israéliens, mais aussi des personnes d\'autres nationalités Au moins 700 personnes auraient été tuées en Israël - un bilan stupéfiant que le pays n\'avait pas connu depuis des décennies - et plus de 400 personnes auraient été tuées à Gaza En réponse, Israël a frappé plus de 800 cibles à Gaza jusqu\'à présent, a déclaré l\'armée israélienne, y compris des frappes aériennes qui ont rasé une grande partie de la ville de Beit Hanoun, dans le nord-est de l\'enclave Plusieurs médias israéliens, citant des responsables des services de secours, ont déclaré qu\'au moins 700 personnes avaient été tuées en Israël, dont 44 soldats. Le ministère de la santé de Gaza a déclaré que 413 personnes, dont 78 enfants et 41 femmes, ont été tuées dans le territoire Un responsable égyptien a déclaré qu\'Israël avait demandé l\'aide du Caire pour assurer la sécurité des otages. L\'Égypte a également discuté avec les deux parties d\'un éventuel cessez-le-feu, mais Israël n\'était pas ouvert à une trêve "à ce stade", selon ce responsable, qui a demandé à ne pas être identifié car il n\'était pas autorisé à informer les médias Une file d\'attente s\'est formée devant un poste de police du centre d\'Israël pour fournir des échantillons d\'ADN et d\'autres moyens susceptibles d\'aider à identifier des membres de la famille disparus L\'Égypte a également discuté avec les deux parties d\'un éventuel cessez-le-feu, mais Israël n\'était pas ouvert à une trêve "à ce stade", selon ce responsable, qui a demandé à ne pas être identifié car il n\'était pas autorisé à informer les médias Le Hezbollah a tiré des roquettes et des obus dimanche sur des positions israéliennes dans une zone contestée le long de la frontière, et Israël a riposté en utilisant des drones armés. L\'armée israélienne a déclaré que la situation était calme après l\'échange Israël a l\'habitude de procéder à des échanges très déséquilibrés pour ramener les Israéliens captifs chez eux.\nUn responsable égyptien a déclaré qu\'Israël avait demandé l\'aide du Caire pour assurer la sécurité des otages Au cours des quatre dernières décennies, Israël a mené des campagnes militaires de grande envergure au Liban et à Gaza, qu\'il a présentées comme des guerres, mais sans déclaration officielle Israël riposte au Hamas et le bilan s\'alourdit\nLe gouvernement israélien a officiellement déclaré la guerre et donné le feu vert à des "mesures militaires significatives" en représailles à l\'attaque surprise du Hamas Entre-temps, le Hamas et le Jihad islamique, plus petit groupe, ont affirmé avoir capturé plus de 130 personnes à l\'intérieur d\'Israël et les avoir emmenées à Gaza, déclarant qu\'elles seraient échangées contre la libération de milliers de Palestiniens emprisonnés par Israël Le nombre élevé de morts et la lenteur de la réaction à l\'assaut ont mis en évidence une défaillance majeure des services de renseignement et ébranlé l\'idée longtemps répandue selon laquelle Israël a des yeux et des oreilles partout dans le petit territoire densément peuplé qu\'il contrôle depuis des dizaines d\'années La déclaration de guerre laissait présager une intensification des combats, et l\'une des principales questions était de savoir si Israël lancerait un assaut terrestre dans la bande de Gaza, ce qui, par le passé, a entraîné une augmentation du nombre de victimes Dans le nord d\'Israël, un bref échange de frappes avec le groupe militant libanais Hezbollah a ravivé les craintes que les combats ne se transforment en une guerre régionale plus large Israël a déclaré avoir fait intervenir des forces spéciales pour tenter de reprendre le contrôle de quatre sites israéliens aux combattants du Hamas, dont deux kibboutzim dans lesquels les militants avaient pénétré plus tôt dans leurs attaques'</li></ul> |
## Evaluation
### Metrics
| Label | 0 | 1 | 2 | Accuracy | Macro Avg | Weighted Avg |
|:--------|:----------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------|:---------|:----------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|
| **all** | {'precision': 0.6018099547511312, 'recall': 0.5611814345991561, 'f1-score': 0.5807860262008734, 'support': 237} | {'precision': 0.5602409638554217, 'recall': 0.6262626262626263, 'f1-score': 0.591414944356121, 'support': 297} | {'precision': 0.7932692307692307, 'recall': 0.7268722466960352, 'f1-score': 0.7586206896551724, 'support': 227} | 0.6360 | {'precision': 0.6517733831252612, 'recall': 0.6381054358526059, 'f1-score': 0.6436072200707222, 'support': 761} | {'precision': 0.642697294251897, 'recall': 0.6360052562417872, 'f1-score': 0.6379808452498016, 'support': 761} |
## 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("mogaio/pr_ebsa_fr_tran_merged25_e1_beginning_offsets_10_v3")
# Run inference
preds = model("Adil Hussain
Adil Hussain est reconnaissant d'avoir reçu l'enseignement de l'acteur Naseeruddin Shah à l'époque où il fréquentait l'École nationale d'art dramatique")
```
<!--
### 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 | 1 | 243.9997 | 2071 |
| Label | Training Sample Count |
|:------|:----------------------|
| neg | 912 |
| obj | 1220 |
| pos | 908 |
### Training Hyperparameters
- batch_size: (8, 8)
- num_epochs: (10, 10)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 1
- 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: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:--------:|:-------------:|:---------------:|
| 0.0013 | 1 | 0.3526 | - |
| 0.0658 | 50 | 0.3825 | - |
| 0.1316 | 100 | 0.2039 | - |
| 0.1974 | 150 | 0.2579 | - |
| 0.2632 | 200 | 0.3062 | - |
| 0.3289 | 250 | 0.1744 | - |
| 0.3947 | 300 | 0.1571 | - |
| 0.4605 | 350 | 0.222 | - |
| 0.5263 | 400 | 0.2697 | - |
| 0.5921 | 450 | 0.2507 | - |
| 0.6579 | 500 | 0.311 | - |
| 0.7237 | 550 | 0.3169 | - |
| 0.7895 | 600 | 0.1766 | - |
| 0.8553 | 650 | 0.1756 | - |
| 0.9211 | 700 | 0.2497 | - |
| 0.9868 | 750 | 0.0889 | - |
| 1.0 | 760 | - | 0.2281 |
| 1.0526 | 800 | 0.1036 | - |
| 1.1184 | 850 | 0.3135 | - |
| 1.1842 | 900 | 0.1744 | - |
| 1.25 | 950 | 0.3287 | - |
| 1.3158 | 1000 | 0.1816 | - |
| 1.3816 | 1050 | 0.231 | - |
| 1.4474 | 1100 | 0.153 | - |
| 1.5132 | 1150 | 0.2131 | - |
| 1.5789 | 1200 | 0.1358 | - |
| 1.6447 | 1250 | 0.276 | - |
| 1.7105 | 1300 | 0.2646 | - |
| 1.7763 | 1350 | 0.0337 | - |
| 1.8421 | 1400 | 0.158 | - |
| 1.9079 | 1450 | 0.1123 | - |
| 1.9737 | 1500 | 0.0889 | - |
| **2.0** | **1520** | **-** | **0.2268** |
| 2.0395 | 1550 | 0.2369 | - |
| 2.1053 | 1600 | 0.196 | - |
| 2.1711 | 1650 | 0.2799 | - |
| 2.2368 | 1700 | 0.073 | - |
| 2.3026 | 1750 | 0.2392 | - |
| 2.3684 | 1800 | 0.1551 | - |
| 2.4342 | 1850 | 0.178 | - |
| 2.5 | 1900 | 0.1719 | - |
| 2.5658 | 1950 | 0.1203 | - |
| 2.6316 | 2000 | 0.1502 | - |
| 2.6974 | 2050 | 0.0963 | - |
| 2.7632 | 2100 | 0.1566 | - |
| 2.8289 | 2150 | 0.1273 | - |
| 2.8947 | 2200 | 0.264 | - |
| 2.9605 | 2250 | 0.0736 | - |
| 3.0 | 2280 | - | 0.2385 |
| 3.0263 | 2300 | 0.1577 | - |
| 3.0921 | 2350 | 0.1613 | - |
| 3.1579 | 2400 | 0.2313 | - |
| 3.2237 | 2450 | 0.1134 | - |
| 3.2895 | 2500 | 0.0593 | - |
| 3.3553 | 2550 | 0.0395 | - |
| 3.4211 | 2600 | 0.119 | - |
| 3.4868 | 2650 | 0.0152 | - |
| 3.5526 | 2700 | 0.019 | - |
| 3.6184 | 2750 | 0.1056 | - |
| 3.6842 | 2800 | 0.1355 | - |
| 3.75 | 2850 | 0.2262 | - |
| 3.8158 | 2900 | 0.102 | - |
| 3.8816 | 2950 | 0.2388 | - |
| 3.9474 | 3000 | 0.1755 | - |
| 4.0 | 3040 | - | 0.2576 |
| 4.0132 | 3050 | 0.0957 | - |
| 4.0789 | 3100 | 0.2034 | - |
| 4.1447 | 3150 | 0.0076 | - |
| 4.2105 | 3200 | 0.0431 | - |
| 4.2763 | 3250 | 0.2228 | - |
| 4.3421 | 3300 | 0.0124 | - |
| 4.4079 | 3350 | 0.2316 | - |
| 4.4737 | 3400 | 0.037 | - |
| 4.5395 | 3450 | 0.1812 | - |
| 4.6053 | 3500 | 0.2115 | - |
| 4.6711 | 3550 | 0.2534 | - |
| 4.7368 | 3600 | 0.1833 | - |
| 4.8026 | 3650 | 0.0135 | - |
| 4.8684 | 3700 | 0.1169 | - |
| 4.9342 | 3750 | 0.0093 | - |
| 5.0 | 3800 | 0.0728 | 0.2787 |
| 5.0658 | 3850 | 0.022 | - |
| 5.1316 | 3900 | 0.0586 | - |
| 5.1974 | 3950 | 0.002 | - |
| 5.2632 | 4000 | 0.1112 | - |
| 5.3289 | 4050 | 0.0902 | - |
| 5.3947 | 4100 | 0.0002 | - |
| 5.4605 | 4150 | 0.108 | - |
| 5.5263 | 4200 | 0.0158 | - |
| 5.5921 | 4250 | 0.0725 | - |
| 5.6579 | 4300 | 0.0014 | - |
| 5.7237 | 4350 | 0.2018 | - |
| 5.7895 | 4400 | 0.0023 | - |
| 5.8553 | 4450 | 0.002 | - |
| 5.9211 | 4500 | 0.213 | - |
| 5.9868 | 4550 | 0.0034 | - |
| 6.0 | 4560 | - | 0.2994 |
| 6.0526 | 4600 | 0.1203 | - |
| 6.1184 | 4650 | 0.1615 | - |
| 6.1842 | 4700 | 0.1968 | - |
| 6.25 | 4750 | 0.004 | - |
| 6.3158 | 4800 | 0.0018 | - |
| 6.3816 | 4850 | 0.048 | - |
| 6.4474 | 4900 | 0.0748 | - |
| 6.5132 | 4950 | 0.0007 | - |
| 6.5789 | 5000 | 0.0019 | - |
| 6.6447 | 5050 | 0.0015 | - |
| 6.7105 | 5100 | 0.0075 | - |
| 6.7763 | 5150 | 0.0012 | - |
| 6.8421 | 5200 | 0.0016 | - |
| 6.9079 | 5250 | 0.0009 | - |
| 6.9737 | 5300 | 0.0004 | - |
| 7.0 | 5320 | - | 0.2721 |
| 7.0395 | 5350 | 0.0142 | - |
| 7.1053 | 5400 | 0.0527 | - |
| 7.1711 | 5450 | 0.0019 | - |
| 7.2368 | 5500 | 0.0024 | - |
| 7.3026 | 5550 | 0.0002 | - |
| 7.3684 | 5600 | 0.0349 | - |
| 7.4342 | 5650 | 0.0008 | - |
| 7.5 | 5700 | 0.0008 | - |
| 7.5658 | 5750 | 0.0005 | - |
| 7.6316 | 5800 | 0.0002 | - |
| 7.6974 | 5850 | 0.0024 | - |
| 7.7632 | 5900 | 0.0017 | - |
| 7.8289 | 5950 | 0.0002 | - |
| 7.8947 | 6000 | 0.0028 | - |
| 7.9605 | 6050 | 0.0124 | - |
| 8.0 | 6080 | - | 0.3064 |
| 8.0263 | 6100 | 0.0038 | - |
| 8.0921 | 6150 | 0.064 | - |
| 8.1579 | 6200 | 0.0007 | - |
| 8.2237 | 6250 | 0.0022 | - |
| 8.2895 | 6300 | 0.0012 | - |
| 8.3553 | 6350 | 0.0103 | - |
| 8.4211 | 6400 | 0.0008 | - |
| 8.4868 | 6450 | 0.0058 | - |
| 8.5526 | 6500 | 0.0046 | - |
| 8.6184 | 6550 | 0.1061 | - |
| 8.6842 | 6600 | 0.0005 | - |
| 8.75 | 6650 | 0.1509 | - |
| 8.8158 | 6700 | 0.0027 | - |
| 8.8816 | 6750 | 0.0002 | - |
| 8.9474 | 6800 | 0.0006 | - |
| 9.0 | 6840 | - | 0.3014 |
| 9.0132 | 6850 | 0.0018 | - |
| 9.0789 | 6900 | 0.0006 | - |
| 9.1447 | 6950 | 0.0003 | - |
| 9.2105 | 7000 | 0.0007 | - |
| 9.2763 | 7050 | 0.0006 | - |
| 9.3421 | 7100 | 0.0003 | - |
| 9.4079 | 7150 | 0.1859 | - |
| 9.4737 | 7200 | 0.0009 | - |
| 9.5395 | 7250 | 0.12 | - |
| 9.6053 | 7300 | 0.0148 | - |
| 9.6711 | 7350 | 0.0002 | - |
| 9.7368 | 7400 | 0.0005 | - |
| 9.8026 | 7450 | 0.1027 | - |
| 9.8684 | 7500 | 0.0002 | - |
| 9.9342 | 7550 | 0.0004 | - |
| 10.0 | 7600 | 0.0003 | 0.3075 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.1
- Sentence Transformers: 2.2.2
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.0
## 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-mpnet-base-v2", "library_name": "setfit", "metrics": ["0", "1", "2", "accuracy", "macro avg", "weighted avg"], "pipeline_tag": "text-classification", "tags": ["setfit", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "widget": [{"text": "Adil Hussain\nAdil Hussain est reconnaissant d'avoir reçu l'enseignement de l'acteur Naseeruddin Shah à l'époque où il fréquentait l'École nationale d'art dramatique"}, {"text": "Les démocrates doivent y remporter des victoires pour gagner cinq sièges à la Chambre et faire du député Hakeem Jeffries, de Brooklyn, le prochain président de la Chambre des représentants Les démocrates aspirent à renverser six circonscriptions détenues par les républicains que M. Biden a remportées en 2020, notamment celle de M Des problèmes à venir pour les démocrates de New York en 2024 ?\nLes dirigeants démocrates de New York se débattent depuis des mois avec le problème de l'hébergement des dizaines de milliers de migrants qui ont été transportés par bus jusqu'à New York et laissés à sa charge.\nMais une autre préoccupation se profile alors que la crise se poursuit sans qu'aucune issue ne soit en vue : les retombées potentielles pour leur parti lors des élections de l'année prochaine Des problèmes à venir pour les démocrates de New York en 2024 ?\nLes dirigeants démocrates de New York se débattent depuis des mois avec le problème de l'hébergement des dizaines de milliers de migrants qui ont été transportés par bus jusqu'à New York et laissés à sa charge Les républicains ont tendance à se sentir en sécurité lorsqu'ils parlent d'immigration - comme les démocrates le font pour l'avortement - et sont clairement à l'attaque sur la question des migrants à New York, tandis que les démocrates sont sur la défensive, a déclaré Kyle Kondik, directeur de la communication pour le Centre de politique de l'Université de Virginie, au réseau USA Today Plus de 100 000 migrants ont été transportés à New York depuis la frontière sud depuis le printemps 2022. Environ 60 000 d'entre eux sont hébergés dans la ville, et plus de 2 100 ont été transportés dans des hôtels situés dans sept comtés au nord de la ville, de Yonkers à la périphérie de Buffalo, où ils sont logés aux frais de la ville Bien que leurs opinions sur la question de savoir si les migrants sont un avantage ou un fardeau soient plus mitigées, de nettes majorités d'électeurs de toute la ville de New York, de la banlieue et du nord de l'État ont déclaré que l'État devrait essayer de ralentir l'afflux de migrants, plutôt que d'en accepter davantage et de s'efforcer d'assimiler les nouveaux arrivants Isaac Goldberg, un stratège démocrate qui a travaillé sur plusieurs campagnes électorales à New York, a affirmé qu'il était beaucoup trop tôt pour prédire l'impact politique de la crise des migrants, soulignant que les élections de 2024 n'auront lieu que dans 14 mois et que de nombreuses questions tout aussi urgentes pourraient se poser Les publicités d'attaque des républicains s'écrivent pratiquement d'elles-mêmes à partir d'un flot de titres et d'images télévisées, alors que le gouverneur Kathy Hochul, le maire de New York Eric Adams et le président Joe Biden - tous démocrates - se rejettent mutuellement la faute et s'échangent des coups de feu pour savoir qui devrait en faire le plus Les républicains se sont emparés de la crise des migrants, donnant un avant-goût des campagnes de l'année prochaine Les républicains ont surenchéri : Elise Stefanik, la New-Yorkaise qui dirige la conférence du parti démocrate à la Chambre des représentants,\nSuite à la page suivante\na déclaré à Politico la semaine dernière que le parti allait consacrer 100 millions de dollars aux campagnes dans les circonscriptions de New York"}, {"text": "LE CANDIDAT A LA PRESIDENCE RAMASWAMY VEUT METTRE FIN AU SYSTEME DE VISA H-1B AUX ETATS-UNIS\nDécrivant le programme de visas H-1B comme une forme de \"servitude\", Vivek Ramaswamy, candidat républicain indien-américain à l'élection présidentielle, a promis de \"vider\" le système basé sur la loterie et de le remplacer par un système d'admission méritocratique s'il remporte les élections présidentielles de 2024"}, {"text": "Smith Hal Sparks Catherine Zeta-Jones son-Sampras Chris Owen Donald Glover\n(\"Queer as Folk\") a 54 ans. a 54 ans. Acteur\n(\"Je sais ce que vous avez fait l'été dernier\") a 50 ans Smith Hal Sparks Catherine Zeta-Jones son-Sampras Chris Owen Donald Glover\n(\"Queer as Folk\") a 54 ans"}, {"text": "Il a poursuivi en disant que Trump ne laisserait pas ses partisans s'approcher de l'une de ses propriétés. \"Les gens qui votent pour Trump, pour la plupart, ne les laisseraient même pas entrer dans un putain d'hôtel [ \"Les gens qui votent pour Trump, pour la plupart, ne les laisseraient même pas entrer dans un putain d'hôtel [...]. Allez à Mar-a-lago, voyez s'il y a des gens qui vous ressemblent\" \"Combien de temps allons-nous continuer à élire des gens qui ont perdu l'élection ?\"\nIl a poursuivi en qualifiant les partisans de Trump de \"nigauds\".\n\"Mon Dieu, j'ai l'impression d'être dans une nation de nigauds. J'espère qu'il y a encore des gens brillants et dynamiques qui aiment ce pays\", a-t-il déclaré \"Et soudain, Trump a transformé Howard, qui était le roi de tous les médias, en prince Harry de tous les médias. Tout le monde s'en fout Alors cette idée que Trump est le pire type qui ait jamais marché sur la surface de la terre, pourquoi traîniez-vous avec lui ?\"\nM. Failla a déclaré que cela avait \"tué\" M L'aversion d'Howard Stern pour Donald Trump, c'est \"tout l'ego\".\nSi \"woke\" signifie que je ne peux pas soutenir Trump, ce que je pense que cela signifie, ou que je soutiens les personnes qui veulent être transgenres ou que je suis pour le vaccin, appelez-moi \"woke\" comme vous voulez Si \"woke\" signifie que je ne peux pas soutenir Trump, ce que je pense que cela signifie, ou que je soutiens les personnes qui veulent être transgenres ou que je suis pour le vaccin, appelez-moi \"woke\" comme vous voulez \"Si être réveillé signifie que je ne peux pas soutenir Trump, ce que je pense que cela signifie, ou que je soutiens les personnes qui veulent être transgenres ou que je suis pour le vaccin, appelez-moi réveillé comme vous le voulez\" Stern a également abordé les affirmations de Trump et de ses partisans selon lesquelles Joe Biden a remporté l'élection américaine de 2020 grâce à des votes frauduleux \"L'omnipotence médiatique de Donald Trump a brisé Howard Stern. C'est très important\", a déclaré Failla dans la vidéo (selon OK ! Magazine). \"Trump avait l'habitude de participer à l'émission de Stern chaque semaine En réponse, Trump a partagé sur sa plateforme Truth Social un clip de Fox News dans lequel l'animateur Jimmy Failla critique Stern.\n\"L'omnipotence médiatique de Donald Trump a brisé Howard Stern Mais Stern, qui par le passé a été accusé de racisme et de sexisme dans nombre de ses sketches à l'antenne, a été un critique virulent de Trump tout au long de sa présidence et, plus récemment, alors qu'il se prépare à se présenter à nouveau en 2024.\nEn 2021, M Trump l'année prochaine.\n\"Je sais que je lui botterai le cul\", a-t-il déclaré aux auditeurs.\nL'année suivante, Stern a déclaré qu'il envisageait de se lancer dans la course à la présidence \"pour que le pays soit à nouveau juste\" Trump profiter de sa célébrité jusqu'à la Maison-Blanche.\n\"Cela a tué Howard parce qu'il était le roi de tous les médias \"Je vais faire la chose très simple qui remettra le pays sur le droit chemin : un vote, une personne\", a expliqué Stern, affirmant que Trump a en fait perdu l'élection de 2016 contre Hillary Clinton qui a remporté le vote populaire - mais pas le collège électoral Celui qui se décrit comme le \"roi de tous les médias\" a critiqué ouvertement l'ancien président américain Donald Trump, les anti-vaxx et, plus récemment, Lauren Boebert, qu'il a critiquée pour son comportement obscène dans un théâtre de Denver au début du mois \"Trump avait l'habitude de participer à l'émission de Stern chaque semaine. Ils étaient amis. Alors cette idée que Trump est le pire type qui ait jamais marché sur la surface de la terre, pourquoi traîniez-vous avec lui ?\"\nM"}], "inference": true, "model-index": [{"name": "SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-v2", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "Unknown", "type": "unknown", "split": "test"}, "metrics": [{"type": "0", "value": {"precision": 0.6018099547511312, "recall": 0.5611814345991561, "f1-score": 0.5807860262008734, "support": 237}, "name": "0"}, {"type": "1", "value": {"precision": 0.5602409638554217, "recall": 0.6262626262626263, "f1-score": 0.591414944356121, "support": 297}, "name": "1"}, {"type": "2", "value": {"precision": 0.7932692307692307, "recall": 0.7268722466960352, "f1-score": 0.7586206896551724, "support": 227}, "name": "2"}, {"type": "accuracy", "value": 0.6360052562417872, "name": "Accuracy"}, {"type": "macro avg", "value": {"precision": 0.6517733831252612, "recall": 0.6381054358526059, "f1-score": 0.6436072200707222, "support": 761}, "name": "Macro Avg"}, {"type": "weighted avg", "value": {"precision": 0.642697294251897, "recall": 0.6360052562417872, "f1-score": 0.6379808452498016, "support": 761}, "name": "Weighted Avg"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,820 |
abhishek/autotrain-imgadvtest3-14049
|
abhishek
|
image-classification
|
[
"transformers",
"pytorch",
"swin",
"image-classification",
"autotrain",
"dataset:abhishek/autotrain-data-imgadvtest3",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-04-13T12:02:53Z |
2023-04-13T12:14:19+00:00
| 39 | 0 |
---
datasets:
- abhishek/autotrain-data-imgadvtest3
tags:
- autotrain
- image-classification
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
example_title: Tiger
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
example_title: Teapot
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
example_title: Palace
co2_eq_emissions:
emissions: 0
---
# Model Trained Using AutoTrain
- Problem type: Text Classification
- CO2 Emissions (in grams): 0.0000
## Validation Metrics
loss: 0.14338010549545288
f1_macro: 0.940526140757593
f1_micro: 0.94
f1_weighted: 0.9398044781162052
precision_macro: 0.940964983321917
precision_micro: 0.94
precision_weighted: 0.9410628287317604
recall_macro: 0.9414679313146717
recall_micro: 0.94
recall_weighted: 0.94
accuracy: 0.94
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Text Classification
- CO2 Emissions (in grams): 0.0000
## Validation Metrics
loss: 0.14338010549545288
f1_macro: 0.940526140757593
f1_micro: 0.94
f1_weighted: 0.9398044781162052
precision_macro: 0.940964983321917
precision_micro: 0.94
precision_weighted: 0.9410628287317604
recall_macro: 0.9414679313146717
recall_micro: 0.94
recall_weighted: 0.94
accuracy: 0.94
|
{"datasets": ["abhishek/autotrain-data-imgadvtest3"], "tags": ["autotrain", "image-classification"], "widget": [{"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg", "example_title": "Tiger"}, {"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg", "example_title": "Teapot"}, {"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg", "example_title": "Palace"}], "co2_eq_emissions": {"emissions": 0}}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,821 |
Rajesh222/distilbert-base-uncased-finetuned-emotion
|
Rajesh222
|
text-classification
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-06-16T06:57:32Z |
2022-06-16T14:05:04+00:00
| 104 | 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
args: default
metrics:
- type: accuracy
value: 0.9265
name: Accuracy
- type: f1
value: 0.9265425929085783
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: 0.2133
- Accuracy: 0.9265
- F1: 0.9265
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8085 | 1.0 | 250 | 0.3033 | 0.9065 | 0.9037 |
| 0.2458 | 2.0 | 500 | 0.2133 | 0.9265 | 0.9265 |
### Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.3.0
- Tokenizers 0.11.6
| 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: 0.2133
- Accuracy: 0.9265
- F1: 0.9265
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8085 | 1.0 | 250 | 0.3033 | 0.9065 | 0.9037 |
| 0.2458 | 2.0 | 500 | 0.2133 | 0.9265 | 0.9265 |
### Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.3.0
- Tokenizers 0.11.6
|
{"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", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.9265, "name": "Accuracy"}, {"type": "f1", "value": 0.9265425929085783, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,822 |
VTSNLP/trans_model_vi_en
|
VTSNLP
| null |
[
"tensorboard",
"safetensors",
"t5",
"generated_from_trainer",
"base_model:VietAI/envit5-translation",
"base_model:finetune:VietAI/envit5-translation",
"license:openrail",
"region:us"
] | 2024-11-01T09:30:13Z |
2024-11-01T09:30:58+00:00
| 7 | 1 |
---
base_model: VietAI/envit5-translation
license: openrail
tags:
- generated_from_trainer
model-index:
- name: trans_model_vi_en
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. -->
# trans_model_vi_en
This model is a fine-tuned version of [VietAI/envit5-translation](https://huggingface.co/VietAI/envit5-translation) on the None 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 4
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- 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. -->
# trans_model_vi_en
This model is a fine-tuned version of [VietAI/envit5-translation](https://huggingface.co/VietAI/envit5-translation) on the None 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 4
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
{"base_model": "VietAI/envit5-translation", "license": "openrail", "tags": ["generated_from_trainer"], "model-index": [{"name": "trans_model_vi_en", "results": []}]}
|
task
|
[
"TRANSLATION"
] | 43,823 |
persiannlp/mt5-small-parsinlu-opus-translation_fa_en
|
persiannlp
|
text2text-generation
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"machine-translation",
"persian",
"farsi",
"fa",
"multilingual",
"dataset:parsinlu",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2021-09-23T16:20:36+00:00
| 63,260 | 1 |
---
datasets:
- parsinlu
language:
- fa
- multilingual
license: cc-by-nc-sa-4.0
metrics:
- sacrebleu
tags:
- machine-translation
- mt5
- persian
- farsi
thumbnail: https://upload.wikimedia.org/wikipedia/commons/a/a2/Farsi.svg
---
# Machine Translation (ترجمهی ماشینی)
This is an mT5-based model for machine translation (Persian -> English).
Here is an example of how you can run this model:
```python
from transformers import MT5ForConditionalGeneration, MT5Tokenizer
model_size = "small"
model_name = f"persiannlp/mt5-{model_size}-parsinlu-opus-translation_fa_en"
tokenizer = MT5Tokenizer.from_pretrained(model_name)
model = MT5ForConditionalGeneration.from_pretrained(model_name)
def run_model(input_string, **generator_args):
input_ids = tokenizer.encode(input_string, return_tensors="pt")
res = model.generate(input_ids, **generator_args)
output = tokenizer.batch_decode(res, skip_special_tokens=True)
print(output)
return output
run_model("ستایش خدای را که پروردگار جهانیان است.")
run_model("در هاید پارک کرنر بر گلدانی ایستاده موعظه میکند؛")
run_model("وی از تمامی بلاگرها، سازمانها و افرادی که از وی پشتیبانی کردهاند، تشکر کرد.")
run_model("مشابه سال ۲۰۰۱، تولید آمونیاک بی آب در ایالات متحده در سال ۲۰۰۰ تقریباً ۱۷،۴۰۰،۰۰۰ تن (معادل بدون آب) با مصرف ظاهری ۲۲،۰۰۰،۰۰۰ تن و حدود ۴۶۰۰۰۰۰ با واردات خالص مواجه شد. ")
run_model("می خواهم دکترای علوم کامپیوتر راجع به شبکه های اجتماعی را دنبال کنم، چالش حل نشده در شبکه های اجتماعی چیست؟")
```
For more details, visit this page: https://github.com/persiannlp/parsinlu/
| null |
Non_BioNLP
|
# Machine Translation (ترجمهی ماشینی)
This is an mT5-based model for machine translation (Persian -> English).
Here is an example of how you can run this model:
```python
from transformers import MT5ForConditionalGeneration, MT5Tokenizer
model_size = "small"
model_name = f"persiannlp/mt5-{model_size}-parsinlu-opus-translation_fa_en"
tokenizer = MT5Tokenizer.from_pretrained(model_name)
model = MT5ForConditionalGeneration.from_pretrained(model_name)
def run_model(input_string, **generator_args):
input_ids = tokenizer.encode(input_string, return_tensors="pt")
res = model.generate(input_ids, **generator_args)
output = tokenizer.batch_decode(res, skip_special_tokens=True)
print(output)
return output
run_model("ستایش خدای را که پروردگار جهانیان است.")
run_model("در هاید پارک کرنر بر گلدانی ایستاده موعظه میکند؛")
run_model("وی از تمامی بلاگرها، سازمانها و افرادی که از وی پشتیبانی کردهاند، تشکر کرد.")
run_model("مشابه سال ۲۰۰۱، تولید آمونیاک بی آب در ایالات متحده در سال ۲۰۰۰ تقریباً ۱۷،۴۰۰،۰۰۰ تن (معادل بدون آب) با مصرف ظاهری ۲۲،۰۰۰،۰۰۰ تن و حدود ۴۶۰۰۰۰۰ با واردات خالص مواجه شد. ")
run_model("می خواهم دکترای علوم کامپیوتر راجع به شبکه های اجتماعی را دنبال کنم، چالش حل نشده در شبکه های اجتماعی چیست؟")
```
For more details, visit this page: https://github.com/persiannlp/parsinlu/
|
{"datasets": ["parsinlu"], "language": ["fa", "multilingual"], "license": "cc-by-nc-sa-4.0", "metrics": ["sacrebleu"], "tags": ["machine-translation", "mt5", "persian", "farsi"], "thumbnail": "https://upload.wikimedia.org/wikipedia/commons/a/a2/Farsi.svg"}
|
task
|
[
"TRANSLATION"
] | 43,824 |
DigitalUmuganda/joeynmt-en-kin
|
DigitalUmuganda
| null |
[
"doi:10.57967/hf/0054",
"region:us"
] | 2022-07-25T10:34:05Z |
2022-07-27T08:50:17+00:00
| 0 | 0 |
---
{}
---
# English-to-Kinyarwanda Machine Translation
This model is an English-to-Kinyarwanda machine translation model, it was built and trained using JoeyNMT framework. The translation model uses transformer encoder-decoder based architecture. It was trained on a 47,211 long English-Kinyarwanda bitext dataset prepared by Digital Umuganda.
## Model architecture
**Encoder && Decoder**
> Type: Transformer
Num_layer: 6
Num_heads: 8
Embedding_dim: 256
ff_size: 1024
Dropout: 0.1
Layer_norm: post
Initializer: xavier
Total params: 12563968
## Pre-processing
Tokenizer_type: subword-nmt
num_merges: 4000
BPE encoding learned on the bitext, separate vocabularies for each language
Pretokenizer: None
No lowercase applied
## Training
Optimizer: Adam
Loss: crossentropy
Epochs: 30
Batch_size: 256
Number of GPUs: 1
## Evaluation
Evaluation_metrics: Blue_score, chrf
Tokenization: None
Beam_width: 15
Beam_alpha: 1.0
## Tools
* joeyNMT 2.0.0
* datasets
* pandas
* numpy
* transformers
* sentencepiece
* pytorch(with cuda)
* sacrebleu
* protobuf>=3.20.1
## How to train
[Use the following link for more information](https://github.com/joeynmt/joeynmt)
## Translation
To install joeyNMT run:
>$ git clone https://github.com/joeynmt/joeynmt.git
$ cd joeynmt
$ pip install . -e
Interactive translation(stdin):
>$ python -m joeynmt translate args.yaml
File translation:
>$ python -m joeynmt translate args.yaml < src_lang.txt > hypothesis_trg_lang.txt
## Accuracy measurement
Sacrebleu installation:
> $ pip install sacrebleu
Measurement(bleu_score, chrf):
> $ sacrebleu reference.tsv -i hypothesis.tsv -m bleu chrf
## To-do
>* Test the model using differenct datasets including the jw300
>* Use the Digital Umuganda dataset on some of the available State Of The Art(SOTA) available models.
>* Expand the dataset
## Result
The following result were obtained on using the sacrebleu.
English-to-Kinyarwanda:
>Blue: 56.5
Chrf: 75.2
| null |
Non_BioNLP
|
# English-to-Kinyarwanda Machine Translation
This model is an English-to-Kinyarwanda machine translation model, it was built and trained using JoeyNMT framework. The translation model uses transformer encoder-decoder based architecture. It was trained on a 47,211 long English-Kinyarwanda bitext dataset prepared by Digital Umuganda.
## Model architecture
**Encoder && Decoder**
> Type: Transformer
Num_layer: 6
Num_heads: 8
Embedding_dim: 256
ff_size: 1024
Dropout: 0.1
Layer_norm: post
Initializer: xavier
Total params: 12563968
## Pre-processing
Tokenizer_type: subword-nmt
num_merges: 4000
BPE encoding learned on the bitext, separate vocabularies for each language
Pretokenizer: None
No lowercase applied
## Training
Optimizer: Adam
Loss: crossentropy
Epochs: 30
Batch_size: 256
Number of GPUs: 1
## Evaluation
Evaluation_metrics: Blue_score, chrf
Tokenization: None
Beam_width: 15
Beam_alpha: 1.0
## Tools
* joeyNMT 2.0.0
* datasets
* pandas
* numpy
* transformers
* sentencepiece
* pytorch(with cuda)
* sacrebleu
* protobuf>=3.20.1
## How to train
[Use the following link for more information](https://github.com/joeynmt/joeynmt)
## Translation
To install joeyNMT run:
>$ git clone https://github.com/joeynmt/joeynmt.git
$ cd joeynmt
$ pip install . -e
Interactive translation(stdin):
>$ python -m joeynmt translate args.yaml
File translation:
>$ python -m joeynmt translate args.yaml < src_lang.txt > hypothesis_trg_lang.txt
## Accuracy measurement
Sacrebleu installation:
> $ pip install sacrebleu
Measurement(bleu_score, chrf):
> $ sacrebleu reference.tsv -i hypothesis.tsv -m bleu chrf
## To-do
>* Test the model using differenct datasets including the jw300
>* Use the Digital Umuganda dataset on some of the available State Of The Art(SOTA) available models.
>* Expand the dataset
## Result
The following result were obtained on using the sacrebleu.
English-to-Kinyarwanda:
>Blue: 56.5
Chrf: 75.2
|
{}
|
task
|
[
"TRANSLATION"
] | 43,825 |
HPLT/hplt_bert_base_en
|
HPLT
|
fill-mask
|
[
"transformers",
"pytorch",
"safetensors",
"fill-mask",
"BERT",
"HPLT",
"encoder",
"custom_code",
"en",
"dataset:HPLT/hplt_monolingual_v1_2",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | 2024-04-21T23:54:45Z |
2025-01-14T14:39:22+00:00
| 62 | 1 |
---
datasets:
- HPLT/hplt_monolingual_v1_2
language:
- en
license: apache-2.0
tags:
- BERT
- HPLT
- encoder
inference: false
---
# HPLT Bert for English
<img src="https://hplt-project.org/_next/static/media/logo-hplt.d5e16ca5.svg" width=12.5%>
This is one of the encoder-only monolingual language models trained as a first release by the [HPLT project](https://hplt-project.org/).
It is a so called masked language model. In particular, we used the modification of the classic BERT model named [LTG-BERT](https://aclanthology.org/2023.findings-eacl.146/).
A monolingual LTG-BERT model is trained for every major language in the [HPLT 1.2 data release](https://hplt-project.org/datasets/v1.2) (*75* models total).
All the HPLT encoder-only models use the same hyper-parameters, roughly following the BERT-base setup:
- hidden size: 768
- attention heads: 12
- layers: 12
- vocabulary size: 32768
Every model uses its own tokenizer trained on language-specific HPLT data.
See sizes of the training corpora, evaluation results and more in our [language model training report](https://hplt-project.org/HPLT_D4_1___First_language_models_trained.pdf).
[The training code](https://github.com/hplt-project/HPLT-WP4).
[The training statistics of all 75 runs](https://api.wandb.ai/links/ltg/kduj7mjn)
## Example usage
This model currently needs a custom wrapper from `modeling_ltgbert.py`, you should therefore load the model with `trust_remote_code=True`.
```python
import torch
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("HPLT/hplt_bert_base_en")
model = AutoModelForMaskedLM.from_pretrained("HPLT/hplt_bert_base_en", trust_remote_code=True)
mask_id = tokenizer.convert_tokens_to_ids("[MASK]")
input_text = tokenizer("It's a beautiful[MASK].", return_tensors="pt")
output_p = model(**input_text)
output_text = torch.where(input_text.input_ids == mask_id, output_p.logits.argmax(-1), input_text.input_ids)
# should output: '[CLS] It's a beautiful place.[SEP]'
print(tokenizer.decode(output_text[0].tolist()))
```
The following classes are currently implemented: `AutoModel`, `AutoModelMaskedLM`, `AutoModelForSequenceClassification`, `AutoModelForTokenClassification`, `AutoModelForQuestionAnswering` and `AutoModeltForMultipleChoice`.
## Intermediate checkpoints
We are releasing 10 intermediate checkpoints for each model at intervals of every 3125 training steps in separate branches. The naming convention is `stepXXX`: for example, `step18750`.
You can load a specific model revision with `transformers` using the argument `revision`:
```python
model = AutoModelForMaskedLM.from_pretrained("HPLT/hplt_bert_base_en", revision="step21875", trust_remote_code=True)
```
You can access all the revisions for the models with the following code:
```python
from huggingface_hub import list_repo_refs
out = list_repo_refs("HPLT/hplt_bert_base_en")
print([b.name for b in out.branches])
```
## Cite us
```bibtex
@inproceedings{samuel-etal-2023-trained,
title = "Trained on 100 million words and still in shape: {BERT} meets {B}ritish {N}ational {C}orpus",
author = "Samuel, David and
Kutuzov, Andrey and
{\O}vrelid, Lilja and
Velldal, Erik",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.146",
doi = "10.18653/v1/2023.findings-eacl.146",
pages = "1954--1974"
})
```
```bibtex
@inproceedings{de-gibert-etal-2024-new-massive,
title = "A New Massive Multilingual Dataset for High-Performance Language Technologies",
author = {de Gibert, Ona and
Nail, Graeme and
Arefyev, Nikolay and
Ba{\~n}{\'o}n, Marta and
van der Linde, Jelmer and
Ji, Shaoxiong and
Zaragoza-Bernabeu, Jaume and
Aulamo, Mikko and
Ram{\'\i}rez-S{\'a}nchez, Gema and
Kutuzov, Andrey and
Pyysalo, Sampo and
Oepen, Stephan and
Tiedemann, J{\"o}rg},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.100",
pages = "1116--1128",
abstract = "We present the HPLT (High Performance Language Technologies) language resources, a new massive multilingual dataset including both monolingual and bilingual corpora extracted from CommonCrawl and previously unused web crawls from the Internet Archive. We describe our methods for data acquisition, management and processing of large corpora, which rely on open-source software tools and high-performance computing. Our monolingual collection focuses on low- to medium-resourced languages and covers 75 languages and a total of {\mbox{$\approx$}} 5.6 trillion word tokens de-duplicated on the document level. Our English-centric parallel corpus is derived from its monolingual counterpart and covers 18 language pairs and more than 96 million aligned sentence pairs with roughly 1.4 billion English tokens. The HPLT language resources are one of the largest open text corpora ever released, providing a great resource for language modeling and machine translation training. We publicly release the corpora, the software, and the tools used in this work.",
}
```
| null |
Non_BioNLP
|
# HPLT Bert for English
<img src="https://hplt-project.org/_next/static/media/logo-hplt.d5e16ca5.svg" width=12.5%>
This is one of the encoder-only monolingual language models trained as a first release by the [HPLT project](https://hplt-project.org/).
It is a so called masked language model. In particular, we used the modification of the classic BERT model named [LTG-BERT](https://aclanthology.org/2023.findings-eacl.146/).
A monolingual LTG-BERT model is trained for every major language in the [HPLT 1.2 data release](https://hplt-project.org/datasets/v1.2) (*75* models total).
All the HPLT encoder-only models use the same hyper-parameters, roughly following the BERT-base setup:
- hidden size: 768
- attention heads: 12
- layers: 12
- vocabulary size: 32768
Every model uses its own tokenizer trained on language-specific HPLT data.
See sizes of the training corpora, evaluation results and more in our [language model training report](https://hplt-project.org/HPLT_D4_1___First_language_models_trained.pdf).
[The training code](https://github.com/hplt-project/HPLT-WP4).
[The training statistics of all 75 runs](https://api.wandb.ai/links/ltg/kduj7mjn)
## Example usage
This model currently needs a custom wrapper from `modeling_ltgbert.py`, you should therefore load the model with `trust_remote_code=True`.
```python
import torch
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("HPLT/hplt_bert_base_en")
model = AutoModelForMaskedLM.from_pretrained("HPLT/hplt_bert_base_en", trust_remote_code=True)
mask_id = tokenizer.convert_tokens_to_ids("[MASK]")
input_text = tokenizer("It's a beautiful[MASK].", return_tensors="pt")
output_p = model(**input_text)
output_text = torch.where(input_text.input_ids == mask_id, output_p.logits.argmax(-1), input_text.input_ids)
# should output: '[CLS] It's a beautiful place.[SEP]'
print(tokenizer.decode(output_text[0].tolist()))
```
The following classes are currently implemented: `AutoModel`, `AutoModelMaskedLM`, `AutoModelForSequenceClassification`, `AutoModelForTokenClassification`, `AutoModelForQuestionAnswering` and `AutoModeltForMultipleChoice`.
## Intermediate checkpoints
We are releasing 10 intermediate checkpoints for each model at intervals of every 3125 training steps in separate branches. The naming convention is `stepXXX`: for example, `step18750`.
You can load a specific model revision with `transformers` using the argument `revision`:
```python
model = AutoModelForMaskedLM.from_pretrained("HPLT/hplt_bert_base_en", revision="step21875", trust_remote_code=True)
```
You can access all the revisions for the models with the following code:
```python
from huggingface_hub import list_repo_refs
out = list_repo_refs("HPLT/hplt_bert_base_en")
print([b.name for b in out.branches])
```
## Cite us
```bibtex
@inproceedings{samuel-etal-2023-trained,
title = "Trained on 100 million words and still in shape: {BERT} meets {B}ritish {N}ational {C}orpus",
author = "Samuel, David and
Kutuzov, Andrey and
{\O}vrelid, Lilja and
Velldal, Erik",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.146",
doi = "10.18653/v1/2023.findings-eacl.146",
pages = "1954--1974"
})
```
```bibtex
@inproceedings{de-gibert-etal-2024-new-massive,
title = "A New Massive Multilingual Dataset for High-Performance Language Technologies",
author = {de Gibert, Ona and
Nail, Graeme and
Arefyev, Nikolay and
Ba{\~n}{\'o}n, Marta and
van der Linde, Jelmer and
Ji, Shaoxiong and
Zaragoza-Bernabeu, Jaume and
Aulamo, Mikko and
Ram{\'\i}rez-S{\'a}nchez, Gema and
Kutuzov, Andrey and
Pyysalo, Sampo and
Oepen, Stephan and
Tiedemann, J{\"o}rg},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.100",
pages = "1116--1128",
abstract = "We present the HPLT (High Performance Language Technologies) language resources, a new massive multilingual dataset including both monolingual and bilingual corpora extracted from CommonCrawl and previously unused web crawls from the Internet Archive. We describe our methods for data acquisition, management and processing of large corpora, which rely on open-source software tools and high-performance computing. Our monolingual collection focuses on low- to medium-resourced languages and covers 75 languages and a total of {\mbox{$\approx$}} 5.6 trillion word tokens de-duplicated on the document level. Our English-centric parallel corpus is derived from its monolingual counterpart and covers 18 language pairs and more than 96 million aligned sentence pairs with roughly 1.4 billion English tokens. The HPLT language resources are one of the largest open text corpora ever released, providing a great resource for language modeling and machine translation training. We publicly release the corpora, the software, and the tools used in this work.",
}
```
|
{"datasets": ["HPLT/hplt_monolingual_v1_2"], "language": ["en"], "license": "apache-2.0", "tags": ["BERT", "HPLT", "encoder"], "inference": false}
|
task
|
[
"TRANSLATION"
] | 43,826 |
Helsinki-NLP/opus-mt-ty-fr
|
Helsinki-NLP
|
translation
|
[
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"ty",
"fr",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2023-08-16T12:07:56+00:00
| 37 | 0 |
---
license: apache-2.0
tags:
- translation
---
### opus-mt-ty-fr
* source languages: ty
* target languages: fr
* OPUS readme: [ty-fr](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/ty-fr/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/ty-fr/opus-2020-01-16.zip)
* test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/ty-fr/opus-2020-01-16.test.txt)
* test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/ty-fr/opus-2020-01-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.ty.fr | 30.2 | 0.480 |
| null |
Non_BioNLP
|
### opus-mt-ty-fr
* source languages: ty
* target languages: fr
* OPUS readme: [ty-fr](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/ty-fr/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/ty-fr/opus-2020-01-16.zip)
* test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/ty-fr/opus-2020-01-16.test.txt)
* test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/ty-fr/opus-2020-01-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.ty.fr | 30.2 | 0.480 |
|
{"license": "apache-2.0", "tags": ["translation"]}
|
task
|
[
"TRANSLATION"
] | 43,827 |
mrm8488/data2vec-text-base-finetuned-mnli
|
mrm8488
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"data2vec-text",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-04-29T16:27:18Z |
2022-08-31T10:25:23+00:00
| 17 | 0 |
---
datasets:
- glue
license: mit
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: data2vec-text-base-finetuned-mnli
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
args: mnli
metrics:
- type: accuracy
value: 0.7862455425369332
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. -->
# data2vec-text-base-finetuned-mnli
This model is a fine-tuned version of [facebook/data2vec-text-base](https://huggingface.co/facebook/data2vec-text-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5521
- Accuracy: 0.7862
## 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 |
|:-------------:|:-----:|:------:|:---------------:|:--------:|
| 1.099 | 1.0 | 24544 | 1.0987 | 0.3182 |
| 1.0993 | 2.0 | 49088 | 1.0979 | 0.3545 |
| 0.7481 | 3.0 | 73632 | 0.7197 | 0.7046 |
| 0.5671 | 4.0 | 98176 | 0.5862 | 0.7728 |
| 0.5505 | 5.0 | 122720 | 0.5521 | 0.7862 |
### Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- 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. -->
# data2vec-text-base-finetuned-mnli
This model is a fine-tuned version of [facebook/data2vec-text-base](https://huggingface.co/facebook/data2vec-text-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5521
- Accuracy: 0.7862
## 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 |
|:-------------:|:-----:|:------:|:---------------:|:--------:|
| 1.099 | 1.0 | 24544 | 1.0987 | 0.3182 |
| 1.0993 | 2.0 | 49088 | 1.0979 | 0.3545 |
| 0.7481 | 3.0 | 73632 | 0.7197 | 0.7046 |
| 0.5671 | 4.0 | 98176 | 0.5862 | 0.7728 |
| 0.5505 | 5.0 | 122720 | 0.5521 | 0.7862 |
### Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
|
{"datasets": ["glue"], "license": "mit", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "data2vec-text-base-finetuned-mnli", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "args": "mnli"}, "metrics": [{"type": "accuracy", "value": 0.7862455425369332, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,828 |
YakovElm/Jira20SetFitModel_Train_balance_ratio_3
|
YakovElm
|
text-classification
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 2023-06-10T20:00:18Z |
2023-06-10T20:00:52+00:00
| 8 | 0 |
---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# YakovElm/Jira20SetFitModel_Train_balance_ratio_3
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("YakovElm/Jira20SetFitModel_Train_balance_ratio_3")
# 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
|
# YakovElm/Jira20SetFitModel_Train_balance_ratio_3
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("YakovElm/Jira20SetFitModel_Train_balance_ratio_3")
# 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"
] | 43,829 |
LoneStriker/gemma-7b-8.0bpw-h8-exl2
|
LoneStriker
|
text-generation
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:2305.14314",
"arxiv:2312.11805",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2304.06364",
"arxiv:2206.04615",
"arxiv:1804.06876",
"arxiv:2110.08193",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:2203.09509",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-02-22T16:04:19Z |
2024-02-22T16:08:39+00:00
| 8 | 0 |
---
library_name: transformers
license: other
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
tags: []
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: To access Gemma 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
---
# Gemma Model Card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
This model card corresponds to the 7B base version of the Gemma model. You can also visit the model card of the [2B base model](https://huggingface.co/google/gemma-2b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it).
**Resources and Technical Documentation**:
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-7b-gg-hf)
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Usage
Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase.
#### Fine-tuning examples
You can find fine-tuning notebooks under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples). We provide:
* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using [QLoRA](https://huggingface.co/papers/2305.14314)
* A script to perform SFT using FSDP on TPU devices
* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset
#### Running the model on a CPU
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a single / multi GPU
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a GPU using different precisions
* _Using `torch.float16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.float16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using `torch.bfloat16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.bfloat16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Quantized Versions through `bitsandbytes`
* _Using 8-bit precision (int8)_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using 4-bit precision_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Other optimizations
* _Flash Attention 2_
First make sure to install `flash-attn` in your environment `pip install flash-attn`
```diff
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
+ attn_implementation="flash_attention_2"
).to(0)
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety
of sources, totaling 6 trillion tokens. Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safely in line with
[our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/).
### Software
Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models](https://ai.google/discover/foundation-models/), including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 |
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 |
| [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 |
| [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 59.7 | 51.8 |
| [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 |
| [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 |
| [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 |
| [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 |
| [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 |
| [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 |
| [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 |
| [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | - | 23 |
| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 |
| [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 |
| [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 |
| [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 |
| [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 |
| [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 |
| ------------------------------ | ------------- | ----------- | --------- |
| **Average** | | **54.0** | **56.4** |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### 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:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2).
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The 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, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 |
| [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 |
| [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 |
| [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 |
| [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 |
| [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 |
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 44.84 | 31.81 |
| [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 |
| [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 |
| [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 |
| ------------------------------ | ------------- | ----------- | --------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) 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.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs 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.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world 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
* LLMs 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](http://ai.google.dev/gemma/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 LLM 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 for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
| null |
Non_BioNLP
|
# Gemma Model Card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
This model card corresponds to the 7B base version of the Gemma model. You can also visit the model card of the [2B base model](https://huggingface.co/google/gemma-2b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it).
**Resources and Technical Documentation**:
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-7b-gg-hf)
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Usage
Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase.
#### Fine-tuning examples
You can find fine-tuning notebooks under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples). We provide:
* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using [QLoRA](https://huggingface.co/papers/2305.14314)
* A script to perform SFT using FSDP on TPU devices
* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset
#### Running the model on a CPU
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a single / multi GPU
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a GPU using different precisions
* _Using `torch.float16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.float16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using `torch.bfloat16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.bfloat16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Quantized Versions through `bitsandbytes`
* _Using 8-bit precision (int8)_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using 4-bit precision_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Other optimizations
* _Flash Attention 2_
First make sure to install `flash-attn` in your environment `pip install flash-attn`
```diff
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
+ attn_implementation="flash_attention_2"
).to(0)
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety
of sources, totaling 6 trillion tokens. Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safely in line with
[our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/).
### Software
Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models](https://ai.google/discover/foundation-models/), including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 |
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 |
| [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 |
| [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 59.7 | 51.8 |
| [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 |
| [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 |
| [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 |
| [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 |
| [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 |
| [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 |
| [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 |
| [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | - | 23 |
| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 |
| [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 |
| [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 |
| [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 |
| [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 |
| [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 |
| ------------------------------ | ------------- | ----------- | --------- |
| **Average** | | **54.0** | **56.4** |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### 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:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2).
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The 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, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 |
| [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 |
| [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 |
| [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 |
| [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 |
| [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 |
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 44.84 | 31.81 |
| [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 |
| [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 |
| [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 |
| ------------------------------ | ------------- | ----------- | --------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) 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.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs 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.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world 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
* LLMs 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](http://ai.google.dev/gemma/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 LLM 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 for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
|
{"library_name": "transformers", "license": "other", "license_name": "gemma-terms-of-use", "license_link": "https://ai.google.dev/gemma/terms", "tags": [], "extra_gated_heading": "Access Gemma on Hugging Face", "extra_gated_prompt": "To access Gemma 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",
"SUMMARIZATION"
] | 43,831 |
Corran/all-mini-v2-L6-ft
|
Corran
|
text-classification
|
[
"sentence-transformers",
"pytorch",
"bert",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 2023-07-11T15:50:16Z |
2023-07-11T15:50:19+00:00
| 9 | 0 |
---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# Corran/all-mini-v2-L6-ft
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("Corran/all-mini-v2-L6-ft")
# 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
|
# Corran/all-mini-v2-L6-ft
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("Corran/all-mini-v2-L6-ft")
# 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"
] | 43,832 |
mini1013/master_cate_sl26
|
mini1013
|
text-classification
|
[
"setfit",
"safetensors",
"roberta",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:mini1013/master_domain",
"base_model:finetune:mini1013/master_domain",
"model-index",
"region:us"
] | 2025-01-21T13:11:16Z |
2025-01-21T13:11:44+00:00
| 137 | 0 |
---
base_model: mini1013/master_domain
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 스타스포츠 스타 루카스 스포츠용품 운동신발 족구화 스포츠/레저>족구>족구화
- text: 스텝 레더 축구 연습 훈련 사다리 순발력 족구 연습기 스포츠/레저>족구>기타족구용품
- text: 낫소 족구공 큐스팩트A T패널 적용 EVA FORM 쿠션감 스포츠/레저>족구>족구공
- text: 더블레이어 고탄력 터치감 족구공 족구동호회 족구볼 스포츠/레저>족구>족구공
- text: 라인기 운동장 경기장 선긋기 트랙 축구장 족구장 주차장 스포츠/레저>족구>기타족구용품
inference: true
model-index:
- name: SetFit with mini1013/master_domain
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 1.0
name: Accuracy
---
# SetFit with mini1013/master_domain
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [mini1013/master_domain](https://huggingface.co/mini1013/master_domain) 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:** [mini1013/master_domain](https://huggingface.co/mini1013/master_domain)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 5 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 |
|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 4.0 | <ul><li>'족구화 발볼넓은 JOMA 호머 축구 신발 남성 MG 짧은 손톱 조마 학생 성인 프리스비 스포츠/레저>족구>족구화'</li><li>'신신상사 스타스포츠 스타 에너제틱 족구화 선수용 JS6200-03 245 스포츠/레저>족구>족구화'</li><li>'스타스포츠 스타 레독스R 족구화 입문자 동호회용 JS5970 스포츠/레저>족구>족구화'</li></ul> |
| 1.0 | <ul><li>'신신상사 스타스포츠 스타스포츠 족구공 사인볼 하이브리드 8판넬방식 스포츠/레저>족구>족구공'</li><li>'신신상사 스타스포츠 족구공 풋살공 축구공 족구공 더 윙 태극 8판넬 JB435 스포츠/레저>족구>족구공'</li><li>'스타스포츠 스타스포츠 태극 족구공 동계용 방수코팅 족구 시합구 스포츠/레저>족구>족구공'</li></ul> |
| 0.0 | <ul><li>'족구타격기 발차기 훈련 스탠드 연습 운동 레슨 스포츠/레저>족구>기타족구용품'</li><li>'스타 족구 심판대 의자 심판 발판대 라인기 코트경계망 스코어보드 지주세트 네트 번호판 스포츠/레저>족구>기타족구용품'</li><li>'ZIPPO 라이터 Figurehead GD 신명글로빅스 ZPM3MA007R 스포츠/레저>족구>기타족구용품'</li></ul> |
| 3.0 | <ul><li>'브럼비 족구유니폼 사이트 21시즌 디자인 피오드 - 2 스포츠/레저>족구>족구의류'</li><li>'브럼비 축구유니폼 사이트 24시즌 디자인 로마-2 스포츠/레저>족구>족구의류'</li><li>'족구 유니폼제작 전사팀복 221007 스포츠/레저>족구>족구의류'</li></ul> |
| 2.0 | <ul><li>'낫소 일반형 족구네트 NSJ-N105 스포츠/레저>족구>족구네트'</li><li>'오레인 족구 네트 OJG-N224 스포츠/레저>족구>족구네트'</li><li>'엔포유 N4U-B500 배드민턴 족구 다용도네트 스포츠/레저>족구>족구네트'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 1.0 |
## 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("mini1013/master_cate_sl26")
# Run inference
preds = model("스타스포츠 스타 루카스 스포츠용품 운동신발 족구화 스포츠/레저>족구>족구화")
```
<!--
### 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 | 2 | 8.0441 | 19 |
| Label | Training Sample Count |
|:------|:----------------------|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 15 |
| 3.0 | 70 |
| 4.0 | 70 |
### Training Hyperparameters
- batch_size: (256, 256)
- num_epochs: (30, 30)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 50
- 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 |
|:-------:|:----:|:-------------:|:---------------:|
| 0.0172 | 1 | 0.4882 | - |
| 0.8621 | 50 | 0.4668 | - |
| 1.7241 | 100 | 0.1034 | - |
| 2.5862 | 150 | 0.0002 | - |
| 3.4483 | 200 | 0.0 | - |
| 4.3103 | 250 | 0.0 | - |
| 5.1724 | 300 | 0.0 | - |
| 6.0345 | 350 | 0.0 | - |
| 6.8966 | 400 | 0.0 | - |
| 7.7586 | 450 | 0.0 | - |
| 8.6207 | 500 | 0.0 | - |
| 9.4828 | 550 | 0.0 | - |
| 10.3448 | 600 | 0.0 | - |
| 11.2069 | 650 | 0.0 | - |
| 12.0690 | 700 | 0.0 | - |
| 12.9310 | 750 | 0.0 | - |
| 13.7931 | 800 | 0.0 | - |
| 14.6552 | 850 | 0.0 | - |
| 15.5172 | 900 | 0.0 | - |
| 16.3793 | 950 | 0.0 | - |
| 17.2414 | 1000 | 0.0 | - |
| 18.1034 | 1050 | 0.0 | - |
| 18.9655 | 1100 | 0.0 | - |
| 19.8276 | 1150 | 0.0 | - |
| 20.6897 | 1200 | 0.0 | - |
| 21.5517 | 1250 | 0.0 | - |
| 22.4138 | 1300 | 0.0 | - |
| 23.2759 | 1350 | 0.0 | - |
| 24.1379 | 1400 | 0.0 | - |
| 25.0 | 1450 | 0.0 | - |
| 25.8621 | 1500 | 0.0 | - |
| 26.7241 | 1550 | 0.0 | - |
| 27.5862 | 1600 | 0.0 | - |
| 28.4483 | 1650 | 0.0 | - |
| 29.3103 | 1700 | 0.0 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.3.1
- Transformers: 4.44.2
- PyTorch: 2.2.0a0+81ea7a4
- Datasets: 3.2.0
- 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 mini1013/master_domain
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [mini1013/master_domain](https://huggingface.co/mini1013/master_domain) 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:** [mini1013/master_domain](https://huggingface.co/mini1013/master_domain)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 5 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 |
|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 4.0 | <ul><li>'족구화 발볼넓은 JOMA 호머 축구 신발 남성 MG 짧은 손톱 조마 학생 성인 프리스비 스포츠/레저>족구>족구화'</li><li>'신신상사 스타스포츠 스타 에너제틱 족구화 선수용 JS6200-03 245 스포츠/레저>족구>족구화'</li><li>'스타스포츠 스타 레독스R 족구화 입문자 동호회용 JS5970 스포츠/레저>족구>족구화'</li></ul> |
| 1.0 | <ul><li>'신신상사 스타스포츠 스타스포츠 족구공 사인볼 하이브리드 8판넬방식 스포츠/레저>족구>족구공'</li><li>'신신상사 스타스포츠 족구공 풋살공 축구공 족구공 더 윙 태극 8판넬 JB435 스포츠/레저>족구>족구공'</li><li>'스타스포츠 스타스포츠 태극 족구공 동계용 방수코팅 족구 시합구 스포츠/레저>족구>족구공'</li></ul> |
| 0.0 | <ul><li>'족구타격기 발차기 훈련 스탠드 연습 운동 레슨 스포츠/레저>족구>기타족구용품'</li><li>'스타 족구 심판대 의자 심판 발판대 라인기 코트경계망 스코어보드 지주세트 네트 번호판 스포츠/레저>족구>기타족구용품'</li><li>'ZIPPO 라이터 Figurehead GD 신명글로빅스 ZPM3MA007R 스포츠/레저>족구>기타족구용품'</li></ul> |
| 3.0 | <ul><li>'브럼비 족구유니폼 사이트 21시즌 디자인 피오드 - 2 스포츠/레저>족구>족구의류'</li><li>'브럼비 축구유니폼 사이트 24시즌 디자인 로마-2 스포츠/레저>족구>족구의류'</li><li>'족구 유니폼제작 전사팀복 221007 스포츠/레저>족구>족구의류'</li></ul> |
| 2.0 | <ul><li>'낫소 일반형 족구네트 NSJ-N105 스포츠/레저>족구>족구네트'</li><li>'오레인 족구 네트 OJG-N224 스포츠/레저>족구>족구네트'</li><li>'엔포유 N4U-B500 배드민턴 족구 다용도네트 스포츠/레저>족구>족구네트'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 1.0 |
## 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("mini1013/master_cate_sl26")
# Run inference
preds = model("스타스포츠 스타 루카스 스포츠용품 운동신발 족구화 스포츠/레저>족구>족구화")
```
<!--
### 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 | 2 | 8.0441 | 19 |
| Label | Training Sample Count |
|:------|:----------------------|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 15 |
| 3.0 | 70 |
| 4.0 | 70 |
### Training Hyperparameters
- batch_size: (256, 256)
- num_epochs: (30, 30)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 50
- 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 |
|:-------:|:----:|:-------------:|:---------------:|
| 0.0172 | 1 | 0.4882 | - |
| 0.8621 | 50 | 0.4668 | - |
| 1.7241 | 100 | 0.1034 | - |
| 2.5862 | 150 | 0.0002 | - |
| 3.4483 | 200 | 0.0 | - |
| 4.3103 | 250 | 0.0 | - |
| 5.1724 | 300 | 0.0 | - |
| 6.0345 | 350 | 0.0 | - |
| 6.8966 | 400 | 0.0 | - |
| 7.7586 | 450 | 0.0 | - |
| 8.6207 | 500 | 0.0 | - |
| 9.4828 | 550 | 0.0 | - |
| 10.3448 | 600 | 0.0 | - |
| 11.2069 | 650 | 0.0 | - |
| 12.0690 | 700 | 0.0 | - |
| 12.9310 | 750 | 0.0 | - |
| 13.7931 | 800 | 0.0 | - |
| 14.6552 | 850 | 0.0 | - |
| 15.5172 | 900 | 0.0 | - |
| 16.3793 | 950 | 0.0 | - |
| 17.2414 | 1000 | 0.0 | - |
| 18.1034 | 1050 | 0.0 | - |
| 18.9655 | 1100 | 0.0 | - |
| 19.8276 | 1150 | 0.0 | - |
| 20.6897 | 1200 | 0.0 | - |
| 21.5517 | 1250 | 0.0 | - |
| 22.4138 | 1300 | 0.0 | - |
| 23.2759 | 1350 | 0.0 | - |
| 24.1379 | 1400 | 0.0 | - |
| 25.0 | 1450 | 0.0 | - |
| 25.8621 | 1500 | 0.0 | - |
| 26.7241 | 1550 | 0.0 | - |
| 27.5862 | 1600 | 0.0 | - |
| 28.4483 | 1650 | 0.0 | - |
| 29.3103 | 1700 | 0.0 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.3.1
- Transformers: 4.44.2
- PyTorch: 2.2.0a0+81ea7a4
- Datasets: 3.2.0
- 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": "mini1013/master_domain", "library_name": "setfit", "metrics": ["accuracy"], "pipeline_tag": "text-classification", "tags": ["setfit", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "widget": [{"text": "스타스포츠 스타 루카스 스포츠용품 운동신발 족구화 스포츠/레저>족구>족구화"}, {"text": "스텝 레더 축구 연습 훈련 사다리 순발력 족구 연습기 스포츠/레저>족구>기타족구용품"}, {"text": "낫소 족구공 큐스팩트A T패널 적용 EVA FORM 쿠션감 스포츠/레저>족구>족구공"}, {"text": "더블레이어 고탄력 터치감 족구공 족구동호회 족구볼 스포츠/레저>족구>족구공"}, {"text": "라인기 운동장 경기장 선긋기 트랙 축구장 족구장 주차장 스포츠/레저>족구>기타족구용품"}], "inference": true, "model-index": [{"name": "SetFit with mini1013/master_domain", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "Unknown", "type": "unknown", "split": "test"}, "metrics": [{"type": "accuracy", "value": 1.0, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,833 |
fine-tuned/ArguAna-512-192-gpt-4o-2024-05-13-34917964
|
fine-tuned
|
feature-extraction
|
[
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"en",
"dataset:fine-tuned/ArguAna-512-192-gpt-4o-2024-05-13-34917964",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 2024-05-28T18:55:04Z |
2024-05-28T18:55:41+00:00
| 6 | 0 |
---
datasets:
- fine-tuned/ArguAna-512-192-gpt-4o-2024-05-13-34917964
- 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-large-en-v1.5**](https://huggingface.co/BAAI/bge-large-en-v1.5) 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/ArguAna-512-192-gpt-4o-2024-05-13-34917964',
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-large-en-v1.5**](https://huggingface.co/BAAI/bge-large-en-v1.5) 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/ArguAna-512-192-gpt-4o-2024-05-13-34917964',
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/ArguAna-512-192-gpt-4o-2024-05-13-34917964", "allenai/c4"], "language": ["en", "en"], "license": "apache-2.0", "pipeline_tag": "feature-extraction", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity", "mteb"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,834 |
zkava01/NewFeb10
|
zkava01
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"autotrain",
"base_model:cardiffnlp/twitter-roberta-base-sentiment-latest",
"base_model:finetune:cardiffnlp/twitter-roberta-base-sentiment-latest",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2025-02-10T15:11:07Z |
2025-02-10T15:33:39+00:00
| 5 | 0 |
---
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
library_name: transformers
tags:
- autotrain
- text-classification
widget:
- text: I love AutoTrain
---
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.5433340668678284
f1_macro: 0.7923048789408237
f1_micro: 0.7935483870967742
f1_weighted: 0.793657966828771
precision_macro: 0.7877265563435776
precision_micro: 0.7935483870967742
precision_weighted: 0.794431098909479
recall_macro: 0.7976015913611821
recall_micro: 0.7935483870967742
recall_weighted: 0.7935483870967742
accuracy: 0.7935483870967742
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.5433340668678284
f1_macro: 0.7923048789408237
f1_micro: 0.7935483870967742
f1_weighted: 0.793657966828771
precision_macro: 0.7877265563435776
precision_micro: 0.7935483870967742
precision_weighted: 0.794431098909479
recall_macro: 0.7976015913611821
recall_micro: 0.7935483870967742
recall_weighted: 0.7935483870967742
accuracy: 0.7935483870967742
|
{"base_model": "cardiffnlp/twitter-roberta-base-sentiment-latest", "library_name": "transformers", "tags": ["autotrain", "text-classification"], "widget": [{"text": "I love AutoTrain"}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,835 |
emonty777/QLoRA-Flan-T5-Small
|
emonty777
| null |
[
"peft",
"pytorch",
"tensorboard",
"generated_from_trainer",
"t5",
"flan",
"small",
"QLoRA",
"cnn_dailymail",
"dataset:cnn_dailymail",
"license:apache-2.0",
"region:us"
] | 2023-10-01T00:41:46Z |
2023-10-03T06:08:38+00:00
| 7 | 0 |
---
datasets:
- cnn_dailymail
license: apache-2.0
metrics:
- rouge
tags:
- generated_from_trainer
- t5
- flan
- small
- peft
- QLoRA
- cnn_dailymail
model-index:
- name: QLoRA-Flan-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. -->
# QLoRA-Flan-T5-Small
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the cnn_dailymail dataset. It achieves the following on the test set:
- ROUGE-1: 0.3484265780526604
- ROUGE-2: 0.14343059577230782
- ROUGE-l: 0.32809541498574013
## Model description
This model was fine-tuned with the purpose of performing the task of abstractive summarization.
## Training and evaluation data
Fine-tuned on cnn_dailymail training set
Evaluated on cnn_dailymail test set
## How to use model
1. Loading the model
```python
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
# Load peft config for pre-trained checkpoint etc.
peft_model_id = "emonty777/QLoRA-Flan-T5-Small"
config = PeftConfig.from_pretrained(peft_model_id)
# load base LLM model and tokenizer / runs on CPU
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# load base LLM model and tokenizer for GPU
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path, load_in_8bit=True, device_map={"":0})
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id, device_map={"":0})
model.eval()
```
2. Generating summaries
```python
text = "Your text goes here..."
# If you want to use CPU
input_ids = tokenizer(text, return_tensors="pt", truncation=True).input_ids
# If you want to use GPU
input_ids = tokenizer(text, return_tensors="pt", truncation=True).input_ids.cuda()
# Adjust max_new_tokens based on size. This is set up for articles of text
outputs = model.generate(input_ids=input_ids, max_new_tokens=120, do_sample=False)
print(f"input sentence: {sample['article']}\n{'---'* 20}")
print(f"summary:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]}")
```
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-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: 4
### Training results
Evaluated on full CNN Dailymail test set
- ROUGE-1: 0.3484265780526604
- ROUGE-2: 0.14343059577230782
- ROUGE-l: 0.32809541498574013
### Framework versions
- Transformers 4.27.1
- Pytorch 2.0.1+cu118
- Datasets 2.9.0
- 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. -->
# QLoRA-Flan-T5-Small
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the cnn_dailymail dataset. It achieves the following on the test set:
- ROUGE-1: 0.3484265780526604
- ROUGE-2: 0.14343059577230782
- ROUGE-l: 0.32809541498574013
## Model description
This model was fine-tuned with the purpose of performing the task of abstractive summarization.
## Training and evaluation data
Fine-tuned on cnn_dailymail training set
Evaluated on cnn_dailymail test set
## How to use model
1. Loading the model
```python
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
# Load peft config for pre-trained checkpoint etc.
peft_model_id = "emonty777/QLoRA-Flan-T5-Small"
config = PeftConfig.from_pretrained(peft_model_id)
# load base LLM model and tokenizer / runs on CPU
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# load base LLM model and tokenizer for GPU
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path, load_in_8bit=True, device_map={"":0})
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id, device_map={"":0})
model.eval()
```
2. Generating summaries
```python
text = "Your text goes here..."
# If you want to use CPU
input_ids = tokenizer(text, return_tensors="pt", truncation=True).input_ids
# If you want to use GPU
input_ids = tokenizer(text, return_tensors="pt", truncation=True).input_ids.cuda()
# Adjust max_new_tokens based on size. This is set up for articles of text
outputs = model.generate(input_ids=input_ids, max_new_tokens=120, do_sample=False)
print(f"input sentence: {sample['article']}\n{'---'* 20}")
print(f"summary:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]}")
```
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-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: 4
### Training results
Evaluated on full CNN Dailymail test set
- ROUGE-1: 0.3484265780526604
- ROUGE-2: 0.14343059577230782
- ROUGE-l: 0.32809541498574013
### Framework versions
- Transformers 4.27.1
- Pytorch 2.0.1+cu118
- Datasets 2.9.0
- Tokenizers 0.13.3
|
{"datasets": ["cnn_dailymail"], "license": "apache-2.0", "metrics": ["rouge"], "tags": ["generated_from_trainer", "t5", "flan", "small", "peft", "QLoRA", "cnn_dailymail"], "model-index": [{"name": "QLoRA-Flan-T5-Small", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 43,836 |
lamm-mit/Cephalo-Idefics-2-vision-8b-beta
|
lamm-mit
|
image-text-to-text
|
[
"transformers",
"safetensors",
"idefics2",
"image-text-to-text",
"nlp",
"code",
"vision",
"chemistry",
"engineering",
"biology",
"bio-inspired",
"text-generation-inference",
"materials science",
"conversational",
"multilingual",
"arxiv:2405.19076",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 2024-05-23T20:03:21Z |
2025-04-16T13:16:20+00:00
| 31 | 3 |
---
language:
- multilingual
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
- nlp
- code
- vision
- chemistry
- engineering
- biology
- bio-inspired
- text-generation-inference
- materials science
inference:
parameters:
temperature: 0.3
widget:
- messages:
- role: user
content: <|image_1|>Can you describe what you see in the image?
---
## Model Summary
Cephalo is a series of multimodal materials science focused vision large language models (V-LLMs) designed to integrate visual and linguistic data for advanced understanding and interaction in human-AI or multi-agent AI frameworks.
A novel aspect of Cephalo's development is the innovative dataset generation method. The extraction process employs advanced algorithms to accurately detect and separate images and their corresponding textual descriptions from complex PDF documents. It involves extracting images and captions from PDFs to create well-reasoned image-text pairs, utilizing large language models (LLMs) for natural language processing. These image-text pairs are then refined and validated through LLM-based NLP processing, ensuring high-quality and contextually relevant data for training.
Cephalo can interpret complex visual scenes and generating contextually accurate language descriptions and answer queries.
The model is developed to process diverse inputs, including images and text, facilitating a broad range of applications such as image captioning, visual question answering, and multimodal content generation. The architecture combines a vision encoder model and an autoregressive transformer to process complex natural language understanding.
Cephalo provides a robust framework for multimodal interaction and understanding, including the development of complex generative pipelines to create 2D and 3D renderings of material microstructures as input for additive manufacturing methods.
This version of Cephalo, lamm-mit/Cephalo-Idefics-2-vision-8b-beta, is based on the HuggingFaceM4/idefics2-8b-chatty model. The model was trained on a combination of scientific text-image data extracted from Wikipedia and scientific papers. For further details on the base model, see: https://huggingface.co/HuggingFaceM4/idefics2-8b-chatty. More details about technical aspects of the model, training and example applications to materials science problems are provided in the paper (reference at the bottom).
### Chat Format
The lamm-mit/Cephalo-Idefics-2-vision-8b-beta is suiteable for one or more image inputs, wih prompts using the chat format as follows:
```raw
User: You carefully study the image, and respond accurately, but succinctly. Think step-by-step.
<image>What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI.<end_of_utterance>
Assistant:
```
where the model generates the text after `Assistant:` . For multi-turn conversations, the prompt should be formatted as follows:
```raw
User: You carefully study the image, and respond accurately, but succinctly. Think step-by-step.
<image>What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI.<end_of_utterance>
Assistant: The image depicts ants climbing a vertical surface using their legs and claws. This behavior is observed in nature and can inspire the design of multi-agent AI systems that mimic the coordinated movement of these insects. The relevance lies in the potential application of such systems in robotics and materials science, where efficient and adaptive movement is crucial.<end_of_utterance>
User: How could this be used to design a fracture resistant material?<end_of_utterance>
Assistant:
```
If you need to manually set the chat template:
```
IDEFICS2_CHAT_TEMPLATE = "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
```
### Sample inference code
This code snippets show how to get quickly started on a GPU:
```python
from PIL import Image
import requests
DEVICE='cuda:0'
from transformers import AutoProcessor, Idefics2ForConditionalGeneration
from tqdm.notebook import tqdm
model_id='lamm-mit/Cephalo-Idefics-2-vision-8b-beta'
model = Idefics2ForConditionalGeneration.from_pretrained( model_id,
torch_dtype=torch.bfloat16, #if your GPU allows
_attn_implementation="flash_attention_2", #make sure Flash Attention 2 is installed
trust_remote_code=True,
).to (DEVICE)
processor = AutoProcessor.from_pretrained(
f"{model_id}",
do_image_splitting=True
)
```
See section towards the end for more comments on model optimization, including quantization.
If you need to manually set the chat template:
```python
IDEFICS2_CHAT_TEMPLATE = "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
tokenizer = AutoTokenizer.from_pretrained(base_model_id, use_fast=True)
tokenizer.chat_template = IDEFICS2_CHAT_TEMPLATE
processor.tokenizer = tokenizer
```
Simple inference example:
```
from transformers.image_utils import load_image
image = load_image("https://d2r55xnwy6nx47.cloudfront.net/uploads/2018/02/Ants_Lede1300.jpg")
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI."},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
# Get inputs using the processor
inputs = processor(text=prompt, images=[image], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
```
Next we provide a convenience function for inference. This function takes the model, processor, question, and images, along with messages and images objects for repeated chat-like interactions with the model.
```python
def ask_about_image (model, processor, question,
images_input=[],
verbatim=False,
temperature=0.1,
show_image=False,
system="You are a biomaterials scientist who responds accurately. ",
init_instr = "",
show_conversation=True,
max_new_tokens=256,
messages=[],
images=[],
use_Markdown=False,
):
query = question
images_input=ensure_list(images_input)
if len (images)==0:
if len (images_input)>0:
for image in tqdm (images_input) :
if is_url(image):
image= load_image(image)
images.append (image)
if show_image:
display ( image )
if len (messages)==0:
base_message = {
"role": "user",
"content": [
{"type": "text", "text": system + init_instr},
# Image messages will be added dynamically here
{"type": "text", "text": query}
]
}
# Ensure the images_input is a list
images_input = ensure_list(images_input)
# Add image messages dynamically
image_messages = [{"type": "image"} for _ in images_input]
base_message["content"][1:1] = image_messages # Insert image messages before the last text message
# Append the constructed message to messages list
messages.append(base_message)
else:
messages.append (
{
"role": "user",
"content": [
{"type": "text", "text": query
}
]
}
)
if verbatim:
print (messages)
text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=[text.strip()], images=images, return_tensors="pt", padding=True).to(DEVICE)
generated_ids = model.generate(**inputs, max_new_tokens=max_new_tokens, temperature=temperature, do_sample=True)
generated_texts = processor.batch_decode(generated_ids[:, inputs["input_ids"].size(1):], skip_special_tokens=True)
messages.append (
{
"role": "assistant",
"content": [ {"type": "text", "text": generated_texts[0]}, ]
}
)
formatted_conversation = format_conversation(messages, images)
# Display the formatted conversation, e.g. in Jupyter Notebook
if show_conversation:
if use_Markdown:
display(Markdown(formatted_conversation))
else:
display(HTML(formatted_conversation))
return generated_texts, messages, images
question = "What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI."
url1 = "https://d2r55xnwy6nx47.cloudfront.net/uploads/2018/02/Ants_Lede1300.jpg"
response, messages,images= ask_about_image ( model, processor, question,
images_input=[url1,],
temperature=0.1,
system= '', init_instr='You carefully study the image, and respond accurately, but succinctly. Think step-by-step.\n\n',
show_conversation=True,
max_new_tokens=512, messages=[], images=[])
```
Sample output:
<small>Image by [Vaishakh Manohar](https://www.quantamagazine.org/the-simple-algorithm-that-ants-use-to-build-bridges-20180226/)</small>
<pre style="white-space: pre-wrap;">
The image depicts a group of ants moving in a coordinated manner, demonstrating their ability to navigate complex environments and adapt to changing conditions. This behavior is relevant for materials design because it highlights the potential of multi-agent AI systems to mimic natural systems and develop new materials with enhanced properties.
Multi-agent AI refers to the use of multiple autonomous agents working together to solve complex problems. These agents can learn from each other and adapt to new situations, similar to how ants can navigate their environment and communicate with one another. By applying these principles to materials design, researchers can develop new materials that exhibit improved performance, such as enhanced strength, flexibility, and adaptability.
The relevance of this image for materials design lies in the inspiration it provides for developing new materials that can mimic the natural efficiency and adaptability of ants. By studying the behavior of ants, researchers can gain insights into how to design materials that can respond dynamically to changes in their environment, leading to improved performance and functionality.
</pre>
## Dataset generation
The schematic below shows a visualization of the approach to generate datasets for training the vision model. The extraction process employs advanced algorithms to accurately detect and separate images and their corresponding textual descriptions from complex PDF documents. It involves extracting images and captions from PDFs to create well-reasoned image-text pairs, utilizing large language models (LLMs) for natural language processing. These image-text pairs are then refined and validated through LLM-based NLP processing, ensuring high-quality and contextually relevant data for training.
The image below shows reproductions of two representative pages of the scientific article (here, Spivak, Buehler, et al., 2011), and how they are used to extract visual scientific data for training the Cephalo model.
# Further model optimizations
If your GPU allows, load and run inference in half precision (`torch.float16` or `torch.bfloat16`).
```diff
model = AutoModelForVision2Seq.from_pretrained(
"lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+ torch_dtype=torch.float16,
).to(DEVICE)
```
**Vision encoder efficiency**
Given the high resolution supported, the vision part of the model can be memory hungry depending on your configuration. If you are GPU-memory-constrained, you can:
- **deactivate the image splitting.** To do so, add `do_image_splitting=False` when initializing the processor (`AutoProcessor.from_pretrained`). There are no changes required on the model side. Note that only the sft model has been trained with image splitting.
- **decrease the maximum image resolution.** To do so, add `size= {"longest_edge": 448, "shortest_edge": 378}` when initializing the processor (`AutoProcessor.from_pretrained`). In particular, the `longest_edge` value can be adapted to fit the need (the default value is `980`). We recommend using values that are multiples of 14. There are no changes required on the model side.
`do_image_splitting=True` is especially needed to boost performance on complex tasks where a very large image is used as input. The model was fine-tuned with image splitting turned on. For simple tasks, this argument can be safely set to `False`.
**Using Flash-attention 2 to speed up generation**
<details><summary>Click to expand.</summary>
Mke sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) for the package installation. Simply change the snippet above with:
```diff
model = AutoModelForVision2Seq.from_pretrained(
"lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+ torch_dtype=torch.bfloat16,
+ _attn_implementation="flash_attention_2",
).to(DEVICE)
```
</details>
**4 bit quantization with bitsandbytes**
<details><summary>Click to expand.</summary>
It is possible to load Idefics2 in 4bits with `bitsandbytes`. Make sure that you have `accelerate` and `bitsandbytes` installed.
```diff
+ from transformers import BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16
)
model = AutoModelForVision2Seq.from_pretrained(
"lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+ torch_dtype=torch.bfloat16,
+ quantization_config=quantization_config,
).to(DEVICE)
```
</details>
## Citation
Please cite as:
```bibtex
@article{Buehler_Cephalo_2024,
title={Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design},
author={Markus J. Buehler},
journal={arXiv preprint arXiv:2405.19076},
year={2024}
}
```
| null |
Non_BioNLP
|
## Model Summary
Cephalo is a series of multimodal materials science focused vision large language models (V-LLMs) designed to integrate visual and linguistic data for advanced understanding and interaction in human-AI or multi-agent AI frameworks.
A novel aspect of Cephalo's development is the innovative dataset generation method. The extraction process employs advanced algorithms to accurately detect and separate images and their corresponding textual descriptions from complex PDF documents. It involves extracting images and captions from PDFs to create well-reasoned image-text pairs, utilizing large language models (LLMs) for natural language processing. These image-text pairs are then refined and validated through LLM-based NLP processing, ensuring high-quality and contextually relevant data for training.
Cephalo can interpret complex visual scenes and generating contextually accurate language descriptions and answer queries.
The model is developed to process diverse inputs, including images and text, facilitating a broad range of applications such as image captioning, visual question answering, and multimodal content generation. The architecture combines a vision encoder model and an autoregressive transformer to process complex natural language understanding.
Cephalo provides a robust framework for multimodal interaction and understanding, including the development of complex generative pipelines to create 2D and 3D renderings of material microstructures as input for additive manufacturing methods.
This version of Cephalo, lamm-mit/Cephalo-Idefics-2-vision-8b-beta, is based on the HuggingFaceM4/idefics2-8b-chatty model. The model was trained on a combination of scientific text-image data extracted from Wikipedia and scientific papers. For further details on the base model, see: https://huggingface.co/HuggingFaceM4/idefics2-8b-chatty. More details about technical aspects of the model, training and example applications to materials science problems are provided in the paper (reference at the bottom).
### Chat Format
The lamm-mit/Cephalo-Idefics-2-vision-8b-beta is suiteable for one or more image inputs, wih prompts using the chat format as follows:
```raw
User: You carefully study the image, and respond accurately, but succinctly. Think step-by-step.
<image>What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI.<end_of_utterance>
Assistant:
```
where the model generates the text after `Assistant:` . For multi-turn conversations, the prompt should be formatted as follows:
```raw
User: You carefully study the image, and respond accurately, but succinctly. Think step-by-step.
<image>What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI.<end_of_utterance>
Assistant: The image depicts ants climbing a vertical surface using their legs and claws. This behavior is observed in nature and can inspire the design of multi-agent AI systems that mimic the coordinated movement of these insects. The relevance lies in the potential application of such systems in robotics and materials science, where efficient and adaptive movement is crucial.<end_of_utterance>
User: How could this be used to design a fracture resistant material?<end_of_utterance>
Assistant:
```
If you need to manually set the chat template:
```
IDEFICS2_CHAT_TEMPLATE = "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
```
### Sample inference code
This code snippets show how to get quickly started on a GPU:
```python
from PIL import Image
import requests
DEVICE='cuda:0'
from transformers import AutoProcessor, Idefics2ForConditionalGeneration
from tqdm.notebook import tqdm
model_id='lamm-mit/Cephalo-Idefics-2-vision-8b-beta'
model = Idefics2ForConditionalGeneration.from_pretrained( model_id,
torch_dtype=torch.bfloat16, #if your GPU allows
_attn_implementation="flash_attention_2", #make sure Flash Attention 2 is installed
trust_remote_code=True,
).to (DEVICE)
processor = AutoProcessor.from_pretrained(
f"{model_id}",
do_image_splitting=True
)
```
See section towards the end for more comments on model optimization, including quantization.
If you need to manually set the chat template:
```python
IDEFICS2_CHAT_TEMPLATE = "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
tokenizer = AutoTokenizer.from_pretrained(base_model_id, use_fast=True)
tokenizer.chat_template = IDEFICS2_CHAT_TEMPLATE
processor.tokenizer = tokenizer
```
Simple inference example:
```
from transformers.image_utils import load_image
image = load_image("https://d2r55xnwy6nx47.cloudfront.net/uploads/2018/02/Ants_Lede1300.jpg")
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI."},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
# Get inputs using the processor
inputs = processor(text=prompt, images=[image], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
```
Next we provide a convenience function for inference. This function takes the model, processor, question, and images, along with messages and images objects for repeated chat-like interactions with the model.
```python
def ask_about_image (model, processor, question,
images_input=[],
verbatim=False,
temperature=0.1,
show_image=False,
system="You are a biomaterials scientist who responds accurately. ",
init_instr = "",
show_conversation=True,
max_new_tokens=256,
messages=[],
images=[],
use_Markdown=False,
):
query = question
images_input=ensure_list(images_input)
if len (images)==0:
if len (images_input)>0:
for image in tqdm (images_input) :
if is_url(image):
image= load_image(image)
images.append (image)
if show_image:
display ( image )
if len (messages)==0:
base_message = {
"role": "user",
"content": [
{"type": "text", "text": system + init_instr},
# Image messages will be added dynamically here
{"type": "text", "text": query}
]
}
# Ensure the images_input is a list
images_input = ensure_list(images_input)
# Add image messages dynamically
image_messages = [{"type": "image"} for _ in images_input]
base_message["content"][1:1] = image_messages # Insert image messages before the last text message
# Append the constructed message to messages list
messages.append(base_message)
else:
messages.append (
{
"role": "user",
"content": [
{"type": "text", "text": query
}
]
}
)
if verbatim:
print (messages)
text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=[text.strip()], images=images, return_tensors="pt", padding=True).to(DEVICE)
generated_ids = model.generate(**inputs, max_new_tokens=max_new_tokens, temperature=temperature, do_sample=True)
generated_texts = processor.batch_decode(generated_ids[:, inputs["input_ids"].size(1):], skip_special_tokens=True)
messages.append (
{
"role": "assistant",
"content": [ {"type": "text", "text": generated_texts[0]}, ]
}
)
formatted_conversation = format_conversation(messages, images)
# Display the formatted conversation, e.g. in Jupyter Notebook
if show_conversation:
if use_Markdown:
display(Markdown(formatted_conversation))
else:
display(HTML(formatted_conversation))
return generated_texts, messages, images
question = "What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI."
url1 = "https://d2r55xnwy6nx47.cloudfront.net/uploads/2018/02/Ants_Lede1300.jpg"
response, messages,images= ask_about_image ( model, processor, question,
images_input=[url1,],
temperature=0.1,
system= '', init_instr='You carefully study the image, and respond accurately, but succinctly. Think step-by-step.\n\n',
show_conversation=True,
max_new_tokens=512, messages=[], images=[])
```
Sample output:
<small>Image by [Vaishakh Manohar](https://www.quantamagazine.org/the-simple-algorithm-that-ants-use-to-build-bridges-20180226/)</small>
<pre style="white-space: pre-wrap;">
The image depicts a group of ants moving in a coordinated manner, demonstrating their ability to navigate complex environments and adapt to changing conditions. This behavior is relevant for materials design because it highlights the potential of multi-agent AI systems to mimic natural systems and develop new materials with enhanced properties.
Multi-agent AI refers to the use of multiple autonomous agents working together to solve complex problems. These agents can learn from each other and adapt to new situations, similar to how ants can navigate their environment and communicate with one another. By applying these principles to materials design, researchers can develop new materials that exhibit improved performance, such as enhanced strength, flexibility, and adaptability.
The relevance of this image for materials design lies in the inspiration it provides for developing new materials that can mimic the natural efficiency and adaptability of ants. By studying the behavior of ants, researchers can gain insights into how to design materials that can respond dynamically to changes in their environment, leading to improved performance and functionality.
</pre>
## Dataset generation
The schematic below shows a visualization of the approach to generate datasets for training the vision model. The extraction process employs advanced algorithms to accurately detect and separate images and their corresponding textual descriptions from complex PDF documents. It involves extracting images and captions from PDFs to create well-reasoned image-text pairs, utilizing large language models (LLMs) for natural language processing. These image-text pairs are then refined and validated through LLM-based NLP processing, ensuring high-quality and contextually relevant data for training.
The image below shows reproductions of two representative pages of the scientific article (here, Spivak, Buehler, et al., 2011), and how they are used to extract visual scientific data for training the Cephalo model.
# Further model optimizations
If your GPU allows, load and run inference in half precision (`torch.float16` or `torch.bfloat16`).
```diff
model = AutoModelForVision2Seq.from_pretrained(
"lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+ torch_dtype=torch.float16,
).to(DEVICE)
```
**Vision encoder efficiency**
Given the high resolution supported, the vision part of the model can be memory hungry depending on your configuration. If you are GPU-memory-constrained, you can:
- **deactivate the image splitting.** To do so, add `do_image_splitting=False` when initializing the processor (`AutoProcessor.from_pretrained`). There are no changes required on the model side. Note that only the sft model has been trained with image splitting.
- **decrease the maximum image resolution.** To do so, add `size= {"longest_edge": 448, "shortest_edge": 378}` when initializing the processor (`AutoProcessor.from_pretrained`). In particular, the `longest_edge` value can be adapted to fit the need (the default value is `980`). We recommend using values that are multiples of 14. There are no changes required on the model side.
`do_image_splitting=True` is especially needed to boost performance on complex tasks where a very large image is used as input. The model was fine-tuned with image splitting turned on. For simple tasks, this argument can be safely set to `False`.
**Using Flash-attention 2 to speed up generation**
<details><summary>Click to expand.</summary>
Mke sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) for the package installation. Simply change the snippet above with:
```diff
model = AutoModelForVision2Seq.from_pretrained(
"lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+ torch_dtype=torch.bfloat16,
+ _attn_implementation="flash_attention_2",
).to(DEVICE)
```
</details>
**4 bit quantization with bitsandbytes**
<details><summary>Click to expand.</summary>
It is possible to load Idefics2 in 4bits with `bitsandbytes`. Make sure that you have `accelerate` and `bitsandbytes` installed.
```diff
+ from transformers import BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16
)
model = AutoModelForVision2Seq.from_pretrained(
"lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+ torch_dtype=torch.bfloat16,
+ quantization_config=quantization_config,
).to(DEVICE)
```
</details>
## Citation
Please cite as:
```bibtex
@article{Buehler_Cephalo_2024,
title={Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design},
author={Markus J. Buehler},
journal={arXiv preprint arXiv:2405.19076},
year={2024}
}
```
```bibtex
@article{Buehler_Cephalo_2024_journal,
title={Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design},
author={Markus J. Buehler},
journal={Advanced Functional Materials},
year={2024},
volume={34},
issue={49},
doi={2409531},
url={https://advanced.onlinelibrary.wiley.com/doi/full/10.1002/adfm.202409531}
}
```
|
{"language": ["multilingual"], "library_name": "transformers", "license": "apache-2.0", "pipeline_tag": "image-text-to-text", "tags": ["nlp", "code", "vision", "chemistry", "engineering", "biology", "bio-inspired", "text-generation-inference", "materials science"], "inference": {"parameters": {"temperature": 0.3}}, "widget": [{"messages": [{"role": "user", "content": "<|image_1|>Can you describe what you see in the image?"}]}]}
|
task
|
[
"QUESTION_ANSWERING"
] | 43,837 |
philschmid/mt5-small-prompted-germanquad-1
|
philschmid
|
summarization
|
[
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"summarization",
"dataset:philschmid/prompted-germanquad",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2021-12-24T11:10:03+00:00
| 29 | 0 |
---
datasets:
- philschmid/prompted-germanquad
license: apache-2.0
metrics:
- rouge
tags:
- summarization
widget:
- text: 'Philipp ist 26 Jahre alt und lebt in Nürnberg, Deutschland. Derzeit arbeitet
er als Machine Learning Engineer und Tech Lead bei Hugging Face, um künstliche
Intelligenz durch Open Source und Open Science zu demokratisieren.
Welches Ziel hat Hugging Face?
'
model-index:
- name: mt5-small-prompted-germanquad-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-prompted-germanquad-1
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an [philschmid/prompted-germanquad](https://huggingface.co/datasets/philschmid/prompted-germanquad) dataset. A prompt datasets using the [BigScience PromptSource library](https://github.com/bigscience-workshop/promptsource). The dataset is a copy of [germanquad](https://huggingface.co/datasets/deepset/germanquad) with applying the `squad` template and translated it to german. [TEMPLATE](https://github.com/philschmid/promptsource/blob/main/promptsource/templates/germanquad/templates.yaml).
This is a first test if it is possible to fine-tune `mt5` models to solve similar tasks than `T0` of big science but for the German language.
It achieves the following results on the evaluation set:
- Loss: 1.6835
- Rouge1: 27.7309
- Rouge2: 18.7311
- Rougel: 27.4704
- Rougelsum: 27.4818
## 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: 5.6e-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: 500
- num_epochs: 7
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:-------:|:---------:|
| 3.3795 | 1.0 | 17496 | 2.0693 | 15.8652 | 9.2569 | 15.6237 | 15.6142 |
| 2.3582 | 2.0 | 34992 | 1.9057 | 21.9348 | 14.0057 | 21.6769 | 21.6825 |
| 2.1809 | 3.0 | 52488 | 1.8143 | 24.3401 | 16.0354 | 24.0862 | 24.0914 |
| 2.0721 | 4.0 | 69984 | 1.7563 | 25.8672 | 17.2442 | 25.5854 | 25.6051 |
| 2.0004 | 5.0 | 87480 | 1.7152 | 27.0275 | 18.0548 | 26.7561 | 26.7685 |
| 1.9531 | 6.0 | 104976 | 1.6939 | 27.4702 | 18.5156 | 27.2027 | 27.2107 |
| 1.9218 | 7.0 | 122472 | 1.6835 | 27.7309 | 18.7311 | 27.4704 | 27.4818 |
### Framework versions
- Transformers 4.14.1
- Pytorch 1.10.1+cu102
- 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. -->
# mt5-small-prompted-germanquad-1
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an [philschmid/prompted-germanquad](https://huggingface.co/datasets/philschmid/prompted-germanquad) dataset. A prompt datasets using the [BigScience PromptSource library](https://github.com/bigscience-workshop/promptsource). The dataset is a copy of [germanquad](https://huggingface.co/datasets/deepset/germanquad) with applying the `squad` template and translated it to german. [TEMPLATE](https://github.com/philschmid/promptsource/blob/main/promptsource/templates/germanquad/templates.yaml).
This is a first test if it is possible to fine-tune `mt5` models to solve similar tasks than `T0` of big science but for the German language.
It achieves the following results on the evaluation set:
- Loss: 1.6835
- Rouge1: 27.7309
- Rouge2: 18.7311
- Rougel: 27.4704
- Rougelsum: 27.4818
## 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: 5.6e-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: 500
- num_epochs: 7
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:-------:|:---------:|
| 3.3795 | 1.0 | 17496 | 2.0693 | 15.8652 | 9.2569 | 15.6237 | 15.6142 |
| 2.3582 | 2.0 | 34992 | 1.9057 | 21.9348 | 14.0057 | 21.6769 | 21.6825 |
| 2.1809 | 3.0 | 52488 | 1.8143 | 24.3401 | 16.0354 | 24.0862 | 24.0914 |
| 2.0721 | 4.0 | 69984 | 1.7563 | 25.8672 | 17.2442 | 25.5854 | 25.6051 |
| 2.0004 | 5.0 | 87480 | 1.7152 | 27.0275 | 18.0548 | 26.7561 | 26.7685 |
| 1.9531 | 6.0 | 104976 | 1.6939 | 27.4702 | 18.5156 | 27.2027 | 27.2107 |
| 1.9218 | 7.0 | 122472 | 1.6835 | 27.7309 | 18.7311 | 27.4704 | 27.4818 |
### Framework versions
- Transformers 4.14.1
- Pytorch 1.10.1+cu102
- Datasets 1.16.1
- Tokenizers 0.10.3
|
{"datasets": ["philschmid/prompted-germanquad"], "license": "apache-2.0", "metrics": ["rouge"], "tags": ["summarization"], "widget": [{"text": "Philipp ist 26 Jahre alt und lebt in Nürnberg, Deutschland. Derzeit arbeitet er als Machine Learning Engineer und Tech Lead bei Hugging Face, um künstliche Intelligenz durch Open Source und Open Science zu demokratisieren.\n\nWelches Ziel hat Hugging Face?\n"}], "model-index": [{"name": "mt5-small-prompted-germanquad-1", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 43,838 |
gokuls/sa_BERT_no_pretrain_sst2
|
gokuls
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-05-29T13:35:42Z |
2023-06-15T07:48:32+00:00
| 9 | 0 |
---
datasets:
- glue
language:
- en
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: sa_BERT_no_pretrain_sst2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE SST2
type: glue
config: sst2
split: validation
args: sst2
metrics:
- type: accuracy
value: 0.8027522935779816
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. -->
# sa_BERT_no_pretrain_sst2
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE SST2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4637
- Accuracy: 0.8028
## 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: 4e-05
- train_batch_size: 96
- eval_batch_size: 96
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4863 | 1.0 | 702 | 0.4747 | 0.7890 |
| 0.2723 | 2.0 | 1404 | 0.4974 | 0.7901 |
| 0.2219 | 3.0 | 2106 | 0.4637 | 0.8028 |
| 0.1848 | 4.0 | 2808 | 0.7501 | 0.7833 |
| 0.1591 | 5.0 | 3510 | 0.5357 | 0.8005 |
| 0.1346 | 6.0 | 4212 | 0.5450 | 0.7833 |
| 0.1148 | 7.0 | 4914 | 0.8002 | 0.7741 |
| 0.1034 | 8.0 | 5616 | 0.8853 | 0.7821 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- 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. -->
# sa_BERT_no_pretrain_sst2
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE SST2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4637
- Accuracy: 0.8028
## 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: 4e-05
- train_batch_size: 96
- eval_batch_size: 96
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4863 | 1.0 | 702 | 0.4747 | 0.7890 |
| 0.2723 | 2.0 | 1404 | 0.4974 | 0.7901 |
| 0.2219 | 3.0 | 2106 | 0.4637 | 0.8028 |
| 0.1848 | 4.0 | 2808 | 0.7501 | 0.7833 |
| 0.1591 | 5.0 | 3510 | 0.5357 | 0.8005 |
| 0.1346 | 6.0 | 4212 | 0.5450 | 0.7833 |
| 0.1148 | 7.0 | 4914 | 0.8002 | 0.7741 |
| 0.1034 | 8.0 | 5616 | 0.8853 | 0.7821 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
|
{"datasets": ["glue"], "language": ["en"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "sa_BERT_no_pretrain_sst2", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE SST2", "type": "glue", "config": "sst2", "split": "validation", "args": "sst2"}, "metrics": [{"type": "accuracy", "value": 0.8027522935779816, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,839 |
gokuls/tiny-bert-sst2-1_mobilebert_2_bert_3_gold_labels-distillation
|
gokuls
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-08-21T14:56:56Z |
2022-08-21T15:08:54+00:00
| 9 | 0 |
---
datasets:
- glue
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: tiny-bert-sst2-1_mobilebert_2_bert_3_gold_labels-distillation
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
config: sst2
split: train
args: sst2
metrics:
- type: accuracy
value: 0.8188073394495413
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. -->
# tiny-bert-sst2-1_mobilebert_2_bert_3_gold_labels-distillation
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9350
- Accuracy: 0.8188
## 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: 16
- eval_batch_size: 16
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.1041 | 1.0 | 4210 | 0.9350 | 0.8188 |
| 0.1166 | 2.0 | 8420 | 0.9179 | 0.8188 |
| 0.1127 | 3.0 | 12630 | 0.9083 | 0.8142 |
| 0.1163 | 4.0 | 16840 | 0.9087 | 0.8165 |
### Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- 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. -->
# tiny-bert-sst2-1_mobilebert_2_bert_3_gold_labels-distillation
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9350
- Accuracy: 0.8188
## 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: 16
- eval_batch_size: 16
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.1041 | 1.0 | 4210 | 0.9350 | 0.8188 |
| 0.1166 | 2.0 | 8420 | 0.9179 | 0.8188 |
| 0.1127 | 3.0 | 12630 | 0.9083 | 0.8142 |
| 0.1163 | 4.0 | 16840 | 0.9087 | 0.8165 |
### Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
|
{"datasets": ["glue"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "tiny-bert-sst2-1_mobilebert_2_bert_3_gold_labels-distillation", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "glue", "type": "glue", "config": "sst2", "split": "train", "args": "sst2"}, "metrics": [{"type": "accuracy", "value": 0.8188073394495413, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,840 |
kahlebr/1
|
kahlebr
|
summarization
|
[
"summarization",
"region:us"
] | 2023-05-13T21:28:42Z |
2023-05-13T21:29:31+00:00
| 0 | 0 |
---
pipeline_tag: summarization
---
| null |
Non_BioNLP
|
{"pipeline_tag": "summarization"}
|
task
|
[
"SUMMARIZATION"
] | 43,842 |
|
Infomaniak-AI/onnx-opus-mt-de-it
|
Infomaniak-AI
|
translation
|
[
"onnx",
"marian",
"translation",
"de",
"it",
"base_model:Helsinki-NLP/opus-mt-de-it",
"base_model:quantized:Helsinki-NLP/opus-mt-de-it",
"license:apache-2.0",
"region:us"
] | 2024-08-13T16:11:14Z |
2024-08-13T16:12:06+00:00
| 18 | 0 |
---
base_model: Helsinki-NLP/opus-mt-de-it
language:
- de
- it
license: apache-2.0
pipeline_tag: translation
tags:
- translation
- onnx
---
### opus-mt-de-it
* source languages: de
* target languages: it
* OPUS readme: [de-it](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-it/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-20.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.zip)
* test set translations: [opus-2020-01-20.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.test.txt)
* test set scores: [opus-2020-01-20.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba.de.it | 45.3 | 0.671 |
| null |
Non_BioNLP
|
### opus-mt-de-it
* source languages: de
* target languages: it
* OPUS readme: [de-it](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-it/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-20.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.zip)
* test set translations: [opus-2020-01-20.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.test.txt)
* test set scores: [opus-2020-01-20.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba.de.it | 45.3 | 0.671 |
|
{"base_model": "Helsinki-NLP/opus-mt-de-it", "language": ["de", "it"], "license": "apache-2.0", "pipeline_tag": "translation", "tags": ["translation", "onnx"]}
|
task
|
[
"TRANSLATION"
] | 43,843 |
luukschmitz/Geodeberta2
|
luukschmitz
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"deberta-v2",
"text-classification",
"autotrain",
"base_model:microsoft/deberta-v3-base",
"base_model:finetune:microsoft/deberta-v3-base",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-07-13T14:58:36Z |
2024-07-13T15:02:08+00:00
| 110 | 0 |
---
base_model: microsoft/deberta-v3-base
tags:
- autotrain
- text-classification
widget:
- text: I love AutoTrain
---
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.9531590342521667
f1_macro: 0.4940971741477817
f1_micro: 0.6548117154811716
f1_weighted: 0.628735443682528
precision_macro: 0.6898690717515761
precision_micro: 0.6548117154811716
precision_weighted: 0.6835107777099136
recall_macro: 0.47932568993970953
recall_micro: 0.6548117154811716
recall_weighted: 0.6548117154811716
accuracy: 0.6548117154811716
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.9531590342521667
f1_macro: 0.4940971741477817
f1_micro: 0.6548117154811716
f1_weighted: 0.628735443682528
precision_macro: 0.6898690717515761
precision_micro: 0.6548117154811716
precision_weighted: 0.6835107777099136
recall_macro: 0.47932568993970953
recall_micro: 0.6548117154811716
recall_weighted: 0.6548117154811716
accuracy: 0.6548117154811716
|
{"base_model": "microsoft/deberta-v3-base", "tags": ["autotrain", "text-classification"], "widget": [{"text": "I love AutoTrain"}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,844 |
hopkins/eng-deu-centroids.sent_budget
|
hopkins
|
translation
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-07-27T04:37:43Z |
2023-07-27T04:55:59+00:00
| 8 | 0 |
---
metrics:
- bleu
tags:
- translation
- generated_from_trainer
model-index:
- name: eng-deu-centroids.sent_budget
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. -->
# eng-deu-centroids.sent_budget
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6604
- Bleu: 21.1838
## 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: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- 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. -->
# eng-deu-centroids.sent_budget
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6604
- Bleu: 21.1838
## 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: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
{"metrics": ["bleu"], "tags": ["translation", "generated_from_trainer"], "model-index": [{"name": "eng-deu-centroids.sent_budget", "results": []}]}
|
task
|
[
"TRANSLATION"
] | 43,846 |
hopkins/mbart-finetuned-eng-kor-23
|
hopkins
|
translation
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-07-02T23:02:17Z |
2023-07-02T23:15:43+00:00
| 8 | 0 |
---
metrics:
- bleu
tags:
- translation
- generated_from_trainer
model-index:
- name: mbart-finetuned-eng-kor-23
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. -->
# mbart-finetuned-eng-kor-23
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9903
- Bleu: 6.8736
## 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: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- 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. -->
# mbart-finetuned-eng-kor-23
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9903
- Bleu: 6.8736
## 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: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
{"metrics": ["bleu"], "tags": ["translation", "generated_from_trainer"], "model-index": [{"name": "mbart-finetuned-eng-kor-23", "results": []}]}
|
task
|
[
"TRANSLATION"
] | 43,847 |
Izzet/qa_tquad_convbert-base-turkish
|
Izzet
|
question-answering
|
[
"transformers",
"pytorch",
"convbert",
"question-answering",
"license:mit",
"endpoints_compatible",
"region:us"
] | 2022-09-04T13:14:54Z |
2022-09-04T13:51:55+00:00
| 11 | 0 |
---
license: mit
widget:
- text: Ankara'da korumaya alınmış alanlar var mıdır?
context: Ankara kara iklimine sahiptir. Şehir dışındaki il topraklarının büyük kısmı
tahıl tarlalarıyla kaplı platolardan oluşur. İlin çeşitli yerlerindeki doğal güzellikler
korumaya alınmış, dinlenme ve eğlence amaçlı kullanıma sunulmuştur. İlin adını
taşıyan tavşanı, keçisi, atı ve kedisi dünya çapında bilinir, armudu, çiğdemi,
yerel yemeklerden Ankara tavası ve Kızılcahamam ve Beypazarı'nın maden suyu ise
ülke çapında tanınır.
example_title: Ankara 1
- text: Ankara toprakları nelerden oluşur?
context: Ankara kara iklimine sahiptir. Şehir dışındaki il topraklarının büyük kısmı
tahıl tarlalarıyla kaplı platolardan oluşur. İlin çeşitli yerlerindeki doğal güzellikler
korumaya alınmış, dinlenme ve eğlence amaçlı kullanıma sunulmuştur. İlin adını
taşıyan tavşanı, keçisi, atı ve kedisi dünya çapında bilinir, armudu, çiğdemi,
yerel yemeklerden Ankara tavası ve Kızılcahamam ve Beypazarı'nın maden suyu ise
ülke çapında tanınır.
example_title: Ankara 2
---
# Question Answering Model Fine-Tuned with TQuad Dataset
You can find detailed explanation about dataset [here](https://github.com/izzetkalic/botcuk-dataset-analyze/tree/main/datasets/qa-tquad).
| null |
Non_BioNLP
|
# Question Answering Model Fine-Tuned with TQuad Dataset
You can find detailed explanation about dataset [here](https://github.com/izzetkalic/botcuk-dataset-analyze/tree/main/datasets/qa-tquad).
|
{"license": "mit", "widget": [{"text": "Ankara'da korumaya alınmış alanlar var mıdır?", "context": "Ankara kara iklimine sahiptir. Şehir dışındaki il topraklarının büyük kısmı tahıl tarlalarıyla kaplı platolardan oluşur. İlin çeşitli yerlerindeki doğal güzellikler korumaya alınmış, dinlenme ve eğlence amaçlı kullanıma sunulmuştur. İlin adını taşıyan tavşanı, keçisi, atı ve kedisi dünya çapında bilinir, armudu, çiğdemi, yerel yemeklerden Ankara tavası ve Kızılcahamam ve Beypazarı'nın maden suyu ise ülke çapında tanınır.", "example_title": "Ankara 1"}, {"text": "Ankara toprakları nelerden oluşur?", "context": "Ankara kara iklimine sahiptir. Şehir dışındaki il topraklarının büyük kısmı tahıl tarlalarıyla kaplı platolardan oluşur. İlin çeşitli yerlerindeki doğal güzellikler korumaya alınmış, dinlenme ve eğlence amaçlı kullanıma sunulmuştur. İlin adını taşıyan tavşanı, keçisi, atı ve kedisi dünya çapında bilinir, armudu, çiğdemi, yerel yemeklerden Ankara tavası ve Kızılcahamam ve Beypazarı'nın maden suyu ise ülke çapında tanınır.", "example_title": "Ankara 2"}]}
|
task
|
[
"QUESTION_ANSWERING"
] | 43,848 |
estrogen/ModernBERT-base-marco
|
estrogen
|
sentence-similarity
|
[
"sentence-transformers",
"safetensors",
"modernbert",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:19139199",
"loss:MatryoshkaLoss",
"loss:MultipleNegativesRankingLoss",
"en",
"dataset:sentence-transformers/msmarco-bm25",
"arxiv:1908.10084",
"arxiv:2205.13147",
"arxiv:1705.00652",
"base_model:answerdotai/ModernBERT-base",
"base_model:finetune:answerdotai/ModernBERT-base",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-12-20T02:59:15Z |
2024-12-20T03:09:06+00:00
| 12 | 0 |
---
base_model: answerdotai/ModernBERT-base
datasets:
- sentence-transformers/msmarco-bm25
language:
- en
library_name: sentence-transformers
metrics:
- cosine_accuracy
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:19139199
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: '[unused0]what period do we live in'
sentences:
- "[unused1]The answer depends on what you want in a cruise experience. If youâ\x80\
\x99re interested in lively entertainment, drinking and parties, and crazy excitement\
\ for more festive cruise experience, and the best time to go on a Caribbean cruise\
\ is between mid February through much of March."
- '[unused1]Earth is currently in the Quaternary Period of the Cenozoic Era.'
- '[unused1]If we did not live in a structured society with other people, laws would
not be necessary. We would simply do as we please, with little regard for others.
But ever since individuals began to associate with other people -- to live in
society --laws have been the glue that has kept society together.lmost everything
we do is governed by some set of rules. There are rules for games, for social
clubs, for sports and for adults in the workplace. There are also rules imposed
by morality and custom that play an important role in telling us what we should
and should not do.'
- source_sentence: '[unused0]how different religion define christology'
sentences:
- "[unused1]Find origin, gender, rashi, nakshatra, zodiac signs, moon signs, religion,\
\ caste, compatibility and astrology behind the name Janhavi, Find what name Janhavi\
\ means in different region, in different religion, in different rashi, for different\
\ planets, and in different nakshatraâ\x80\x99s."
- '[unused1]Christianity is an Abrahamic religion that began as a Second Temple
Judaic sect in the mid-1st century. Originating in Judea, it quickly spread to
Europe, Syria, Mesopotamia, Asia Minor, Transcaucasia, Egypt, Ethiopia, and India,
and by the end of the 4th century had become the official state church of the
Roman Empire.'
- "[unused1]The answer depends on what you want in a cruise experience. If youâ\x80\
\x99re interested in lively entertainment, drinking and parties, and crazy excitement\
\ for more festive cruise experience, and the best time to go on a Caribbean cruise\
\ is between mid February through much of March."
- source_sentence: '[unused0]what was juliet morgan family'
sentences:
- '[unused1]Famous Financier. Financier, art collector and philanthropist John Pierpont
Morgan, best known as J.P. Morgan, was born on April 17, 1837, in Hartford, Connecticut.
The son of a banker, Morgan went into the family business and became one of the
most famous financiers in history.'
- '[unused1]Juliet Pierpont Morgan was born on month day 1847, at birth place, Connecticut,
to Junius Spencer Morgan and Juliet Morgan (born Pierpont). Junius was born on
April 14 1813, in Holyoke, Hampden County, Massachusetts, USA.'
- '[unused1]Juliette Hampton Morgan was a librarian and civil rights activist in
Montgomery, Alabama. The only daughter from a well-to-do white family, Morgan
was an early member of the community that pushed for integration. As a librarian
she often spoke out against the acts of injustice she witnessed against African-Americans
by writing letters to the Montgomery Advertiser, the local newspaper. She was
castigated by the community for her racial views and was targeted by segregationists
who broke her windo'
- source_sentence: '[unused0]how different religion define christology'
sentences:
- '[unused1]Carbon Monoxide is produced from gas appliances in your home. Carbon
Dioxide is produced from the exhaust fumes from your automobile. Either of these
gases can be harmful to a human. These gases can be even more harmful to small
animals in your home. Depending on the size of your home you should have a carbon
monoxide detector on every level of your home.'
- '[unused1]Doctrine is a set of accepted beliefs held by a group. In religion,
it is the set of true beliefs that define the parameters of that belief system.'
- '[unused1]Christianity is an Abrahamic religion that began as a Second Temple
Judaic sect in the mid-1st century. Originating in Judea, it quickly spread to
Europe, Syria, Mesopotamia, Asia Minor, Transcaucasia, Egypt, Ethiopia, and India,
and by the end of the 4th century had become the official state church of the
Roman Empire.'
- source_sentence: '[unused0]what period do we live in'
sentences:
- "[unused1]Thereâ\x80\x99s a big difference in drive time depending on what part\
\ of Ewa Beach you live in â\x80\x94 the homes in Ocean Point (most southern part\
\ of Ewa) have a 20 minute longer drive than we do, even though we both live in\
\ the town of Ewa Beach."
- '[unused1]Save. Bankruptcy does not automatically disqualify someone for receiving
security clearances, but it will slow the process down--as will any derogatory
financial information. If you are applying for top-secret clearance, background
investigators will review the reasons for your bankruptcy.'
- '[unused1]Earth is currently in the Quaternary Period of the Cenozoic Era.'
model-index:
- name: SentenceTransformer based on estrogen/ModernBERT-base-sbert-initialized
results:
- task:
type: triplet
name: Triplet
dataset:
name: ms marco
type: ms_marco
metrics:
- type: cosine_accuracy
value: 0.9537
name: Cosine Accuracy
- type: cosine_accuracy
value: 0.9587
name: Cosine Accuracy
---
# SentenceTransformer based on estrogen/ModernBERT-base-sbert-initialized
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [estrogen/ModernBERT-base-sbert-initialized](https://huggingface.co/estrogen/ModernBERT-base-sbert-initialized) on the [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) 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:** [estrogen/ModernBERT-base-sbert-initialized](https://huggingface.co/estrogen/ModernBERT-base-sbert-initialized) <!-- at revision d80f2f10df59065d673fa4d9ef890aae3cbf4b68 -->
- **Maximum Sequence Length:** 8192 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25)
- **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': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel
(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("estrogen/ModernBERT-base-marco")
# Run inference
sentences = [
'[unused0]what period do we live in',
'[unused1]Earth is currently in the Quaternary Period of the Cenozoic Era.',
'[unused1]Thereâ\x80\x99s a big difference in drive time depending on what part of Ewa Beach you live in â\x80\x94 the homes in Ocean Point (most southern part of Ewa) have a 20 minute longer drive than we do, even though we both live in the town of Ewa Beach.',
]
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
#### Triplet
* Dataset: `ms_marco`
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| **cosine_accuracy** | **0.9537** |
#### Triplet
* Dataset: `ms_marco`
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| **cosine_accuracy** | **0.9587** |
<!--
## 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
#### msmarco-bm25
* Dataset: [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) at [ce8a493](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25/tree/ce8a493a65af5e872c3c92f72a89e2e99e175f02)
* Size: 19,139,199 training samples
* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | query | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 10.51 tokens</li><li>max: 17 tokens</li></ul> | <ul><li>min: 45 tokens</li><li>mean: 86.37 tokens</li><li>max: 212 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 80.75 tokens</li><li>max: 222 tokens</li></ul> |
* Samples:
| query | positive | negative |
|:-------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>[unused0]what are the liberal arts?</code> | <code>[unused1]liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>[unused1]The New York State Education Department requires 60 Liberal Arts credits in a Bachelor of Science program and 90 Liberal Arts credits in a Bachelor of Arts program. In the list of course descriptions, courses which are liberal arts for all students are identified by (Liberal Arts) after the course number.</code> |
| <code>[unused0]what are the liberal arts?</code> | <code>[unused1]liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>[unused1]You can choose from an array of liberal arts majors. Most of these are offered in the liberal arts departments of colleges that belong to universities and at smaller colleges that are designated as liberal arts institutions.</code> |
| <code>[unused0]what are the liberal arts?</code> | <code>[unused1]liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>[unused1]Majors. You can choose from an array of liberal arts majors. Most of these are offered in the liberal arts departments of colleges that belong to universities and at smaller colleges that are designated as liberal arts institutions.</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
0.9,
0.81,
0.7290000000000001,
0.6561
],
"n_dims_per_step": -1
}
```
### Evaluation Dataset
#### msmarco-bm25
* Dataset: [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) at [ce8a493](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25/tree/ce8a493a65af5e872c3c92f72a89e2e99e175f02)
* Size: 19,139,199 evaluation samples
* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | query | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 5 tokens</li><li>mean: 10.42 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 80.07 tokens</li><li>max: 167 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 82.48 tokens</li><li>max: 213 tokens</li></ul> |
* Samples:
| query | positive | negative |
|:---------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>[unused0]different uses of corn</code> | <code>[unused1]Corn or maize oil is extracted from the germ of corn, and its main use is for cooking. It is also a key ingredient in margarine and other processed foods. Corn oil is also a feedstock used for biodiesel.From 2012 to 2014, the use of nonfood-grade (NFG) corn oil for biodiesel production has grown tremendously.ses of Corn Oil. Apart from serving as a less-than-ideal cooking oil, corn oil has several industrial uses, including as an addition to soap, salve, paint, ink, textiles, and insecticides. It also sometimes functions as a carrier for drug molecules in pharmaceutical products.</code> | <code>[unused1]Impact of Ethanol on Corn Prices. The U.S. produces 40 percent of the worldâs corn, [5] and ethanol production uses about 40 percent of U.S. corn production, [6] but roughly one-third of the value of the corn used in ethanol production returns to the feed market as DDGS.</code> |
| <code>[unused0]different uses of corn</code> | <code>[unused1]Corn or maize oil is extracted from the germ of corn, and its main use is for cooking. It is also a key ingredient in margarine and other processed foods. Corn oil is also a feedstock used for biodiesel.From 2012 to 2014, the use of nonfood-grade (NFG) corn oil for biodiesel production has grown tremendously.ses of Corn Oil. Apart from serving as a less-than-ideal cooking oil, corn oil has several industrial uses, including as an addition to soap, salve, paint, ink, textiles, and insecticides. It also sometimes functions as a carrier for drug molecules in pharmaceutical products.</code> | <code>[unused1]But ask different reptile keepers how long corn do corn snakes get and you won't get one standard answer. Like us humans, who may grow to little more than 5 feet tall to well over 6 feet in adults, different corn snakes attain different sizes.</code> |
| <code>[unused0]different uses of corn</code> | <code>[unused1]Corn or maize oil is extracted from the germ of corn, and its main use is for cooking. It is also a key ingredient in margarine and other processed foods. Corn oil is also a feedstock used for biodiesel.From 2012 to 2014, the use of nonfood-grade (NFG) corn oil for biodiesel production has grown tremendously.ses of Corn Oil. Apart from serving as a less-than-ideal cooking oil, corn oil has several industrial uses, including as an addition to soap, salve, paint, ink, textiles, and insecticides. It also sometimes functions as a carrier for drug molecules in pharmaceutical products.</code> | <code>[unused1]The corn system uses a large amount of natural resources. Even though it does not deliver as much food as comparable systems around the globe, the American corn system continues to use a large proportion of our countryâs natural resources.he corn system uses a large amount of natural resources. Even though it does not deliver as much food as comparable systems around the globe, the American corn system continues to use a large proportion of our countryâs natural resources.</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
0.9,
0.81,
0.7290000000000001,
0.6561
],
"n_dims_per_step": -1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 256
- `per_device_eval_batch_size`: 256
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `bf16`: True
- `prompts`: {'query': '[unused0]', 'positive': '[unused1]', 'negative': '[unused1]'}
- `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`: 256
- `per_device_eval_batch_size`: 256
- `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`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `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`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: {'query': '[unused0]', 'positive': '[unused1]', 'negative': '[unused1]'}
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | Validation Loss | ms_marco_cosine_accuracy |
|:------:|:----:|:-------------:|:---------------:|:------------------------:|
| 0 | 0 | - | - | 0.5833 |
| 0.0005 | 1 | 24.3765 | - | - |
| 0.0010 | 2 | 24.4903 | - | - |
| 0.0015 | 3 | 24.4595 | - | - |
| 0.0020 | 4 | 24.2913 | - | - |
| 0.0026 | 5 | 24.355 | - | - |
| 0.0031 | 6 | 24.2594 | - | - |
| 0.0036 | 7 | 24.1731 | - | - |
| 0.0041 | 8 | 24.135 | - | - |
| 0.0046 | 9 | 23.9455 | - | - |
| 0.0051 | 10 | 23.9964 | - | - |
| 0.0056 | 11 | 23.7097 | - | - |
| 0.0061 | 12 | 23.6735 | - | - |
| 0.0067 | 13 | 23.4437 | - | - |
| 0.0072 | 14 | 23.3786 | - | - |
| 0.0077 | 15 | 23.2145 | - | - |
| 0.0082 | 16 | 23.056 | - | - |
| 0.0087 | 17 | 22.9313 | - | - |
| 0.0092 | 18 | 22.6844 | - | - |
| 0.0097 | 19 | 22.5722 | - | - |
| 0.0102 | 20 | 22.4012 | - | - |
| 0.0107 | 21 | 22.1844 | - | - |
| 0.0113 | 22 | 21.9721 | - | - |
| 0.0118 | 23 | 21.7602 | - | - |
| 0.0123 | 24 | 21.4919 | - | - |
| 0.0128 | 25 | 21.2078 | - | - |
| 0.0133 | 26 | 20.9653 | - | - |
| 0.0138 | 27 | 20.6508 | - | - |
| 0.0143 | 28 | 20.2809 | - | - |
| 0.0148 | 29 | 19.8262 | - | - |
| 0.0154 | 30 | 19.3564 | - | - |
| 0.0159 | 31 | 18.9138 | - | - |
| 0.0164 | 32 | 18.2485 | - | - |
| 0.0169 | 33 | 17.63 | - | - |
| 0.0174 | 34 | 17.028 | - | - |
| 0.0179 | 35 | 16.2372 | - | - |
| 0.0184 | 36 | 15.3384 | - | - |
| 0.0189 | 37 | 14.3885 | - | - |
| 0.0194 | 38 | 13.4842 | - | - |
| 0.0200 | 39 | 12.6733 | - | - |
| 0.0205 | 40 | 11.8822 | - | - |
| 0.0210 | 41 | 11.2018 | - | - |
| 0.0215 | 42 | 10.2756 | - | - |
| 0.0220 | 43 | 9.2841 | - | - |
| 0.0225 | 44 | 8.8121 | - | - |
| 0.0230 | 45 | 7.973 | - | - |
| 0.0235 | 46 | 7.3955 | - | - |
| 0.0241 | 47 | 6.9961 | - | - |
| 0.0246 | 48 | 6.9545 | - | - |
| 0.0251 | 49 | 6.4636 | - | - |
| 0.0256 | 50 | 5.9562 | - | - |
| 0.0261 | 51 | 5.6653 | - | - |
| 0.0266 | 52 | 5.0228 | - | - |
| 0.0271 | 53 | 4.6302 | - | - |
| 0.0276 | 54 | 4.0535 | - | - |
| 0.0281 | 55 | 3.714 | - | - |
| 0.0287 | 56 | 3.2454 | - | - |
| 0.0292 | 57 | 2.9078 | - | - |
| 0.0297 | 58 | 2.6236 | - | - |
| 0.0302 | 59 | 2.4775 | - | - |
| 0.0307 | 60 | 2.1067 | - | - |
| 0.0312 | 61 | 2.1748 | - | - |
| 0.0317 | 62 | 1.9844 | - | - |
| 0.0322 | 63 | 1.7707 | - | - |
| 0.0328 | 64 | 1.6281 | - | - |
| 0.0333 | 65 | 1.9416 | - | - |
| 0.0338 | 66 | 1.5796 | - | - |
| 0.0343 | 67 | 1.5611 | - | - |
| 0.0348 | 68 | 1.5282 | - | - |
| 0.0353 | 69 | 1.6081 | - | - |
| 0.0358 | 70 | 1.4455 | - | - |
| 0.0363 | 71 | 1.3649 | - | - |
| 0.0368 | 72 | 1.0884 | - | - |
| 0.0374 | 73 | 0.9736 | - | - |
| 0.0379 | 74 | 0.8036 | - | - |
| 0.0384 | 75 | 0.8466 | - | - |
| 0.0389 | 76 | 0.8594 | - | - |
| 0.0394 | 77 | 0.8887 | - | - |
| 0.0399 | 78 | 0.8299 | - | - |
| 0.0404 | 79 | 0.8561 | - | - |
| 0.0409 | 80 | 1.0354 | - | - |
| 0.0415 | 81 | 1.1445 | - | - |
| 0.0420 | 82 | 1.1131 | - | - |
| 0.0425 | 83 | 1.114 | - | - |
| 0.0430 | 84 | 1.032 | - | - |
| 0.0435 | 85 | 0.8509 | - | - |
| 0.0440 | 86 | 0.7415 | - | - |
| 0.0445 | 87 | 1.1415 | - | - |
| 0.0450 | 88 | 1.1622 | - | - |
| 0.0455 | 89 | 1.2912 | - | - |
| 0.0461 | 90 | 1.0092 | - | - |
| 0.0466 | 91 | 0.7901 | - | - |
| 0.0471 | 92 | 0.7782 | - | - |
| 0.0476 | 93 | 0.6596 | - | - |
| 0.0481 | 94 | 0.5789 | - | - |
| 0.0486 | 95 | 0.8727 | - | - |
| 0.0491 | 96 | 0.6869 | - | - |
| 0.0496 | 97 | 0.7282 | - | - |
| 0.0502 | 98 | 0.6578 | - | - |
| 0.0507 | 99 | 0.6303 | - | - |
| 0.0512 | 100 | 0.4592 | 2.8360 | 0.8286 |
| 0.0517 | 101 | 0.6197 | - | - |
| 0.0522 | 102 | 0.737 | - | - |
| 0.0527 | 103 | 0.538 | - | - |
| 0.0532 | 104 | 0.435 | - | - |
| 0.0537 | 105 | 0.3955 | - | - |
| 0.0542 | 106 | 0.2621 | - | - |
| 0.0548 | 107 | 0.2742 | - | - |
| 0.0553 | 108 | 0.2802 | - | - |
| 0.0558 | 109 | 0.2681 | - | - |
| 0.0563 | 110 | 0.2489 | - | - |
| 0.0568 | 111 | 0.2985 | - | - |
| 0.0573 | 112 | 0.5011 | - | - |
| 0.0578 | 113 | 0.4239 | - | - |
| 0.0583 | 114 | 0.5619 | - | - |
| 0.0589 | 115 | 0.3498 | - | - |
| 0.0594 | 116 | 0.5731 | - | - |
| 0.0599 | 117 | 0.4297 | - | - |
| 0.0604 | 118 | 0.4703 | - | - |
| 0.0609 | 119 | 0.449 | - | - |
| 0.0614 | 120 | 0.4708 | - | - |
| 0.0619 | 121 | 0.4467 | - | - |
| 0.0624 | 122 | 0.4263 | - | - |
| 0.0629 | 123 | 0.3481 | - | - |
| 0.0635 | 124 | 0.2899 | - | - |
| 0.0640 | 125 | 0.4778 | - | - |
| 0.0645 | 126 | 0.7366 | - | - |
| 0.0650 | 127 | 0.5905 | - | - |
| 0.0655 | 128 | 0.5095 | - | - |
| 0.0660 | 129 | 0.3977 | - | - |
| 0.0665 | 130 | 0.4885 | - | - |
| 0.0670 | 131 | 0.4421 | - | - |
| 0.0676 | 132 | 0.2875 | - | - |
| 0.0681 | 133 | 0.4082 | - | - |
| 0.0686 | 134 | 0.424 | - | - |
| 0.0691 | 135 | 0.5184 | - | - |
| 0.0696 | 136 | 0.4225 | - | - |
| 0.0701 | 137 | 0.4612 | - | - |
| 0.0706 | 138 | 0.3632 | - | - |
| 0.0711 | 139 | 0.3489 | - | - |
| 0.0716 | 140 | 0.3888 | - | - |
| 0.0722 | 141 | 0.367 | - | - |
| 0.0727 | 142 | 0.3191 | - | - |
| 0.0732 | 143 | 0.4214 | - | - |
| 0.0737 | 144 | 0.3566 | - | - |
| 0.0742 | 145 | 0.2213 | - | - |
| 0.0747 | 146 | 0.2371 | - | - |
| 0.0752 | 147 | 0.2611 | - | - |
| 0.0757 | 148 | 0.1732 | - | - |
| 0.0763 | 149 | 0.223 | - | - |
| 0.0768 | 150 | 0.1442 | - | - |
| 0.0773 | 151 | 0.2201 | - | - |
| 0.0778 | 152 | 0.379 | - | - |
| 0.0783 | 153 | 0.3073 | - | - |
| 0.0788 | 154 | 0.2447 | - | - |
| 0.0793 | 155 | 0.3104 | - | - |
| 0.0798 | 156 | 0.3395 | - | - |
| 0.0803 | 157 | 0.2449 | - | - |
| 0.0809 | 158 | 0.226 | - | - |
| 0.0814 | 159 | 0.2058 | - | - |
| 0.0819 | 160 | 0.2084 | - | - |
| 0.0824 | 161 | 0.1993 | - | - |
| 0.0829 | 162 | 0.1208 | - | - |
| 0.0834 | 163 | 0.1055 | - | - |
| 0.0839 | 164 | 0.2083 | - | - |
| 0.0844 | 165 | 0.2167 | - | - |
| 0.0850 | 166 | 0.2169 | - | - |
| 0.0855 | 167 | 0.194 | - | - |
| 0.0860 | 168 | 0.2136 | - | - |
| 0.0865 | 169 | 0.2185 | - | - |
| 0.0870 | 170 | 0.2675 | - | - |
| 0.0875 | 171 | 0.2817 | - | - |
| 0.0880 | 172 | 0.3723 | - | - |
| 0.0885 | 173 | 0.5269 | - | - |
| 0.0890 | 174 | 0.2643 | - | - |
| 0.0896 | 175 | 0.2437 | - | - |
| 0.0901 | 176 | 0.1549 | - | - |
| 0.0906 | 177 | 0.1461 | - | - |
| 0.0911 | 178 | 0.1395 | - | - |
| 0.0916 | 179 | 0.1506 | - | - |
| 0.0921 | 180 | 0.2542 | - | - |
| 0.0926 | 181 | 0.2022 | - | - |
| 0.0931 | 182 | 0.1756 | - | - |
| 0.0937 | 183 | 0.2411 | - | - |
| 0.0942 | 184 | 0.3402 | - | - |
| 0.0947 | 185 | 0.3534 | - | - |
| 0.0952 | 186 | 0.2632 | - | - |
| 0.0957 | 187 | 0.3643 | - | - |
| 0.0962 | 188 | 0.4046 | - | - |
| 0.0967 | 189 | 0.2619 | - | - |
| 0.0972 | 190 | 0.1575 | - | - |
| 0.0977 | 191 | 0.12 | - | - |
| 0.0983 | 192 | 0.1157 | - | - |
| 0.0988 | 193 | 0.2453 | - | - |
| 0.0993 | 194 | 0.2406 | - | - |
| 0.0998 | 195 | 0.1784 | - | - |
| 0.1003 | 196 | 0.2226 | - | - |
| 0.1008 | 197 | 0.1963 | - | - |
| 0.1013 | 198 | 0.0964 | - | - |
| 0.1018 | 199 | 0.1413 | - | - |
| 0.1024 | 200 | 0.1467 | 1.6950 | 0.915 |
| 0.1029 | 201 | 0.322 | - | - |
| 0.1034 | 202 | 0.3444 | - | - |
| 0.1039 | 203 | 0.2968 | - | - |
| 0.1044 | 204 | 0.227 | - | - |
| 0.1049 | 205 | 0.3337 | - | - |
| 0.1054 | 206 | 0.2653 | - | - |
| 0.1059 | 207 | 0.251 | - | - |
| 0.1064 | 208 | 0.1667 | - | - |
| 0.1070 | 209 | 0.106 | - | - |
| 0.1075 | 210 | 0.1635 | - | - |
| 0.1080 | 211 | 0.1338 | - | - |
| 0.1085 | 212 | 0.1247 | - | - |
| 0.1090 | 213 | 0.12 | - | - |
| 0.1095 | 214 | 0.2283 | - | - |
| 0.1100 | 215 | 0.2245 | - | - |
| 0.1105 | 216 | 0.2821 | - | - |
| 0.1111 | 217 | 0.23 | - | - |
| 0.1116 | 218 | 0.3457 | - | - |
| 0.1121 | 219 | 0.4413 | - | - |
| 0.1126 | 220 | 0.3201 | - | - |
| 0.1131 | 221 | 0.3959 | - | - |
| 0.1136 | 222 | 0.323 | - | - |
| 0.1141 | 223 | 0.1532 | - | - |
| 0.1146 | 224 | 0.2216 | - | - |
| 0.1151 | 225 | 0.2449 | - | - |
| 0.1157 | 226 | 0.1398 | - | - |
| 0.1162 | 227 | 0.2693 | - | - |
| 0.1167 | 228 | 0.265 | - | - |
| 0.1172 | 229 | 0.2228 | - | - |
| 0.1177 | 230 | 0.2179 | - | - |
| 0.1182 | 231 | 0.1581 | - | - |
| 0.1187 | 232 | 0.2204 | - | - |
| 0.1192 | 233 | 0.1252 | - | - |
| 0.1198 | 234 | 0.2252 | - | - |
| 0.1203 | 235 | 0.2116 | - | - |
| 0.1208 | 236 | 0.1856 | - | - |
| 0.1213 | 237 | 0.1115 | - | - |
| 0.1218 | 238 | 0.0827 | - | - |
| 0.1223 | 239 | 0.2732 | - | - |
| 0.1228 | 240 | 0.2076 | - | - |
| 0.1233 | 241 | 0.1214 | - | - |
| 0.1238 | 242 | 0.1385 | - | - |
| 0.1244 | 243 | 0.3275 | - | - |
| 0.1249 | 244 | 0.307 | - | - |
| 0.1254 | 245 | 0.1637 | - | - |
| 0.1259 | 246 | 0.3614 | - | - |
| 0.1264 | 247 | 0.2571 | - | - |
| 0.1269 | 248 | 0.2131 | - | - |
| 0.1274 | 249 | 0.2254 | - | - |
| 0.1279 | 250 | 0.1677 | - | - |
| 0.1285 | 251 | 0.2697 | - | - |
| 0.1290 | 252 | 0.205 | - | - |
| 0.1295 | 253 | 0.1395 | - | - |
| 0.1300 | 254 | 0.1931 | - | - |
| 0.1305 | 255 | 0.2205 | - | - |
| 0.1310 | 256 | 0.1271 | - | - |
| 0.1315 | 257 | 0.1029 | - | - |
| 0.1320 | 258 | 0.0632 | - | - |
| 0.1325 | 259 | 0.0594 | - | - |
| 0.1331 | 260 | 0.2551 | - | - |
| 0.1336 | 261 | 0.3609 | - | - |
| 0.1341 | 262 | 0.3379 | - | - |
| 0.1346 | 263 | 0.2832 | - | - |
| 0.1351 | 264 | 0.2797 | - | - |
| 0.1356 | 265 | 0.2167 | - | - |
| 0.1361 | 266 | 0.2362 | - | - |
| 0.1366 | 267 | 0.1922 | - | - |
| 0.1372 | 268 | 0.2488 | - | - |
| 0.1377 | 269 | 0.135 | - | - |
| 0.1382 | 270 | 0.1064 | - | - |
| 0.1387 | 271 | 0.1245 | - | - |
| 0.1392 | 272 | 0.1605 | - | - |
| 0.1397 | 273 | 0.1739 | - | - |
| 0.1402 | 274 | 0.1816 | - | - |
| 0.1407 | 275 | 0.1802 | - | - |
| 0.1412 | 276 | 0.1227 | - | - |
| 0.1418 | 277 | 0.1445 | - | - |
| 0.1423 | 278 | 0.1052 | - | - |
| 0.1428 | 279 | 0.0774 | - | - |
| 0.1433 | 280 | 0.0778 | - | - |
| 0.1438 | 281 | 0.1116 | - | - |
| 0.1443 | 282 | 0.3067 | - | - |
| 0.1448 | 283 | 0.3255 | - | - |
| 0.1453 | 284 | 0.2831 | - | - |
| 0.1459 | 285 | 0.2623 | - | - |
| 0.1464 | 286 | 0.2323 | - | - |
| 0.1469 | 287 | 0.2093 | - | - |
| 0.1474 | 288 | 0.1023 | - | - |
| 0.1479 | 289 | 0.1909 | - | - |
| 0.1484 | 290 | 0.1476 | - | - |
| 0.1489 | 291 | 0.1069 | - | - |
| 0.1494 | 292 | 0.2284 | - | - |
| 0.1499 | 293 | 0.1341 | - | - |
| 0.1505 | 294 | 0.0924 | - | - |
| 0.1510 | 295 | 0.1264 | - | - |
| 0.1515 | 296 | 0.0836 | - | - |
| 0.1520 | 297 | 0.163 | - | - |
| 0.1525 | 298 | 0.0946 | - | - |
| 0.1530 | 299 | 0.0784 | - | - |
| 0.1535 | 300 | 0.2065 | 1.3301 | 0.9233 |
| 0.1540 | 301 | 0.133 | - | - |
| 0.1546 | 302 | 0.1105 | - | - |
| 0.1551 | 303 | 0.1045 | - | - |
| 0.1556 | 304 | 0.136 | - | - |
| 0.1561 | 305 | 0.0834 | - | - |
| 0.1566 | 306 | 0.0856 | - | - |
| 0.1571 | 307 | 0.1069 | - | - |
| 0.1576 | 308 | 0.2031 | - | - |
| 0.1581 | 309 | 0.1742 | - | - |
| 0.1586 | 310 | 0.1186 | - | - |
| 0.1592 | 311 | 0.0532 | - | - |
| 0.1597 | 312 | 0.0982 | - | - |
| 0.1602 | 313 | 0.1013 | - | - |
| 0.1607 | 314 | 0.1019 | - | - |
| 0.1612 | 315 | 0.1899 | - | - |
| 0.1617 | 316 | 0.133 | - | - |
| 0.1622 | 317 | 0.242 | - | - |
| 0.1627 | 318 | 0.3231 | - | - |
| 0.1633 | 319 | 0.3294 | - | - |
| 0.1638 | 320 | 0.3034 | - | - |
| 0.1643 | 321 | 0.263 | - | - |
| 0.1648 | 322 | 0.2273 | - | - |
| 0.1653 | 323 | 0.1982 | - | - |
| 0.1658 | 324 | 0.143 | - | - |
| 0.1663 | 325 | 0.317 | - | - |
| 0.1668 | 326 | 0.3259 | - | - |
| 0.1673 | 327 | 0.2158 | - | - |
| 0.1679 | 328 | 0.231 | - | - |
| 0.1684 | 329 | 0.1733 | - | - |
| 0.1689 | 330 | 0.3191 | - | - |
| 0.1694 | 331 | 0.187 | - | - |
| 0.1699 | 332 | 0.169 | - | - |
| 0.1704 | 333 | 0.2259 | - | - |
| 0.1709 | 334 | 0.2909 | - | - |
| 0.1714 | 335 | 0.3047 | - | - |
| 0.1720 | 336 | 0.2925 | - | - |
| 0.1725 | 337 | 0.2579 | - | - |
| 0.1730 | 338 | 0.2226 | - | - |
| 0.1735 | 339 | 0.3724 | - | - |
| 0.1740 | 340 | 0.2634 | - | - |
| 0.1745 | 341 | 0.1856 | - | - |
| 0.1750 | 342 | 0.1102 | - | - |
| 0.1755 | 343 | 0.1205 | - | - |
| 0.1760 | 344 | 0.1154 | - | - |
| 0.1766 | 345 | 0.1558 | - | - |
| 0.1771 | 346 | 0.0789 | - | - |
| 0.1776 | 347 | 0.1674 | - | - |
| 0.1781 | 348 | 0.1188 | - | - |
| 0.1786 | 349 | 0.163 | - | - |
| 0.1791 | 350 | 0.197 | - | - |
| 0.1796 | 351 | 0.1017 | - | - |
| 0.1801 | 352 | 0.0914 | - | - |
| 0.1807 | 353 | 0.1576 | - | - |
| 0.1812 | 354 | 0.1809 | - | - |
| 0.1817 | 355 | 0.1624 | - | - |
| 0.1822 | 356 | 0.1636 | - | - |
| 0.1827 | 357 | 0.1473 | - | - |
| 0.1832 | 358 | 0.1839 | - | - |
| 0.1837 | 359 | 0.1494 | - | - |
| 0.1842 | 360 | 0.1326 | - | - |
| 0.1847 | 361 | 0.1545 | - | - |
| 0.1853 | 362 | 0.1588 | - | - |
| 0.1858 | 363 | 0.0975 | - | - |
| 0.1863 | 364 | 0.1363 | - | - |
| 0.1868 | 365 | 0.1248 | - | - |
| 0.1873 | 366 | 0.1328 | - | - |
| 0.1878 | 367 | 0.1329 | - | - |
| 0.1883 | 368 | 0.0755 | - | - |
| 0.1888 | 369 | 0.2535 | - | - |
| 0.1894 | 370 | 0.2484 | - | - |
| 0.1899 | 371 | 0.2538 | - | - |
| 0.1904 | 372 | 0.1597 | - | - |
| 0.1909 | 373 | 0.188 | - | - |
| 0.1914 | 374 | 0.0946 | - | - |
| 0.1919 | 375 | 0.0899 | - | - |
| 0.1924 | 376 | 0.0814 | - | - |
| 0.1929 | 377 | 0.1024 | - | - |
| 0.1934 | 378 | 0.2536 | - | - |
| 0.1940 | 379 | 0.1975 | - | - |
| 0.1945 | 380 | 0.1364 | - | - |
| 0.1950 | 381 | 0.1144 | - | - |
| 0.1955 | 382 | 0.1584 | - | - |
| 0.1960 | 383 | 0.2206 | - | - |
| 0.1965 | 384 | 0.2278 | - | - |
| 0.1970 | 385 | 0.3123 | - | - |
| 0.1975 | 386 | 0.1633 | - | - |
| 0.1981 | 387 | 0.1344 | - | - |
| 0.1986 | 388 | 0.2176 | - | - |
| 0.1991 | 389 | 0.132 | - | - |
| 0.1996 | 390 | 0.1022 | - | - |
| 0.2001 | 391 | 0.1819 | - | - |
| 0.2006 | 392 | 0.1488 | - | - |
| 0.2011 | 393 | 0.0793 | - | - |
| 0.2016 | 394 | 0.1097 | - | - |
| 0.2021 | 395 | 0.0742 | - | - |
| 0.2027 | 396 | 0.1336 | - | - |
| 0.2032 | 397 | 0.102 | - | - |
| 0.2037 | 398 | 0.0837 | - | - |
| 0.2042 | 399 | 0.0948 | - | - |
| 0.2047 | 400 | 0.0911 | 1.2098 | 0.9202 |
| 0.2052 | 401 | 0.1793 | - | - |
| 0.2057 | 402 | 0.1949 | - | - |
| 0.2062 | 403 | 0.1297 | - | - |
| 0.2068 | 404 | 0.0983 | - | - |
| 0.2073 | 405 | 0.1735 | - | - |
| 0.2078 | 406 | 0.1271 | - | - |
| 0.2083 | 407 | 0.1855 | - | - |
| 0.2088 | 408 | 0.1755 | - | - |
| 0.2093 | 409 | 0.1591 | - | - |
| 0.2098 | 410 | 0.2311 | - | - |
| 0.2103 | 411 | 0.2291 | - | - |
| 0.2108 | 412 | 0.0812 | - | - |
| 0.2114 | 413 | 0.0893 | - | - |
| 0.2119 | 414 | 0.1559 | - | - |
| 0.2124 | 415 | 0.2663 | - | - |
| 0.2129 | 416 | 0.257 | - | - |
| 0.2134 | 417 | 0.1864 | - | - |
| 0.2139 | 418 | 0.1735 | - | - |
| 0.2144 | 419 | 0.1028 | - | - |
| 0.2149 | 420 | 0.1494 | - | - |
| 0.2155 | 421 | 0.1528 | - | - |
| 0.2160 | 422 | 0.3732 | - | - |
| 0.2165 | 423 | 0.2663 | - | - |
| 0.2170 | 424 | 0.2487 | - | - |
| 0.2175 | 425 | 0.28 | - | - |
| 0.2180 | 426 | 0.1857 | - | - |
| 0.2185 | 427 | 0.1069 | - | - |
| 0.2190 | 428 | 0.138 | - | - |
| 0.2195 | 429 | 0.106 | - | - |
| 0.2201 | 430 | 0.1366 | - | - |
| 0.2206 | 431 | 0.1444 | - | - |
| 0.2211 | 432 | 0.0695 | - | - |
| 0.2216 | 433 | 0.0652 | - | - |
| 0.2221 | 434 | 0.0771 | - | - |
| 0.2226 | 435 | 0.1724 | - | - |
| 0.2231 | 436 | 0.1494 | - | - |
| 0.2236 | 437 | 0.1837 | - | - |
| 0.2242 | 438 | 0.1885 | - | - |
| 0.2247 | 439 | 0.3021 | - | - |
| 0.2252 | 440 | 0.2301 | - | - |
| 0.2257 | 441 | 0.1372 | - | - |
| 0.2262 | 442 | 0.1413 | - | - |
| 0.2267 | 443 | 0.1489 | - | - |
| 0.2272 | 444 | 0.2566 | - | - |
| 0.2277 | 445 | 0.1504 | - | - |
| 0.2282 | 446 | 0.1567 | - | - |
| 0.2288 | 447 | 0.2548 | - | - |
| 0.2293 | 448 | 0.2375 | - | - |
| 0.2298 | 449 | 0.2346 | - | - |
| 0.2303 | 450 | 0.2818 | - | - |
| 0.2308 | 451 | 0.1814 | - | - |
| 0.2313 | 452 | 0.1792 | - | - |
| 0.2318 | 453 | 0.1701 | - | - |
| 0.2323 | 454 | 0.158 | - | - |
| 0.2329 | 455 | 0.0782 | - | - |
| 0.2334 | 456 | 0.0762 | - | - |
| 0.2339 | 457 | 0.1317 | - | - |
| 0.2344 | 458 | 0.1143 | - | - |
| 0.2349 | 459 | 0.0982 | - | - |
| 0.2354 | 460 | 0.1041 | - | - |
| 0.2359 | 461 | 0.0873 | - | - |
| 0.2364 | 462 | 0.1718 | - | - |
| 0.2369 | 463 | 0.2022 | - | - |
| 0.2375 | 464 | 0.4147 | - | - |
| 0.2380 | 465 | 0.3045 | - | - |
| 0.2385 | 466 | 0.2021 | - | - |
| 0.2390 | 467 | 0.2004 | - | - |
| 0.2395 | 468 | 0.1474 | - | - |
| 0.2400 | 469 | 0.2358 | - | - |
| 0.2405 | 470 | 0.2385 | - | - |
| 0.2410 | 471 | 0.2669 | - | - |
| 0.2416 | 472 | 0.1408 | - | - |
| 0.2421 | 473 | 0.1248 | - | - |
| 0.2426 | 474 | 0.0805 | - | - |
| 0.2431 | 475 | 0.0821 | - | - |
| 0.2436 | 476 | 0.0498 | - | - |
| 0.2441 | 477 | 0.0886 | - | - |
| 0.2446 | 478 | 0.066 | - | - |
| 0.2451 | 479 | 0.1148 | - | - |
| 0.2456 | 480 | 0.1282 | - | - |
| 0.2462 | 481 | 0.1113 | - | - |
| 0.2467 | 482 | 0.0992 | - | - |
| 0.2472 | 483 | 0.2702 | - | - |
| 0.2477 | 484 | 0.2504 | - | - |
| 0.2482 | 485 | 0.3917 | - | - |
| 0.2487 | 486 | 0.1506 | - | - |
| 0.2492 | 487 | 0.1238 | - | - |
| 0.2497 | 488 | 0.1337 | - | - |
| 0.2503 | 489 | 0.2255 | - | - |
| 0.2508 | 490 | 0.1447 | - | - |
| 0.2513 | 491 | 0.2208 | - | - |
| 0.2518 | 492 | 0.268 | - | - |
| 0.2523 | 493 | 0.174 | - | - |
| 0.2528 | 494 | 0.2124 | - | - |
| 0.2533 | 495 | 0.1783 | - | - |
| 0.2538 | 496 | 0.1945 | - | - |
| 0.2544 | 497 | 0.1642 | - | - |
| 0.2549 | 498 | 0.2724 | - | - |
| 0.2554 | 499 | 0.1823 | - | - |
| 0.2559 | 500 | 0.18 | 1.1056 | 0.913 |
| 0.2564 | 501 | 0.1871 | - | - |
| 0.2569 | 502 | 0.1611 | - | - |
| 0.2574 | 503 | 0.1915 | - | - |
| 0.2579 | 504 | 0.1281 | - | - |
| 0.2584 | 505 | 0.1793 | - | - |
| 0.2590 | 506 | 0.0993 | - | - |
| 0.2595 | 507 | 0.1785 | - | - |
| 0.2600 | 508 | 0.1308 | - | - |
| 0.2605 | 509 | 0.1142 | - | - |
| 0.2610 | 510 | 0.0932 | - | - |
| 0.2615 | 511 | 0.1643 | - | - |
| 0.2620 | 512 | 0.175 | - | - |
| 0.2625 | 513 | 0.2568 | - | - |
| 0.2631 | 514 | 0.1534 | - | - |
| 0.2636 | 515 | 0.105 | - | - |
| 0.2641 | 516 | 0.0964 | - | - |
| 0.2646 | 517 | 0.062 | - | - |
| 0.2651 | 518 | 0.123 | - | - |
| 0.2656 | 519 | 0.1892 | - | - |
| 0.2661 | 520 | 0.1282 | - | - |
| 0.2666 | 521 | 0.1243 | - | - |
| 0.2671 | 522 | 0.1051 | - | - |
| 0.2677 | 523 | 0.1257 | - | - |
| 0.2682 | 524 | 0.2121 | - | - |
| 0.2687 | 525 | 0.2357 | - | - |
| 0.2692 | 526 | 0.1355 | - | - |
| 0.2697 | 527 | 0.0861 | - | - |
| 0.2702 | 528 | 0.0632 | - | - |
| 0.2707 | 529 | 0.0652 | - | - |
| 0.2712 | 530 | 0.1102 | - | - |
| 0.2718 | 531 | 0.3408 | - | - |
| 0.2723 | 532 | 0.3124 | - | - |
| 0.2728 | 533 | 0.1656 | - | - |
| 0.2733 | 534 | 0.2136 | - | - |
| 0.2738 | 535 | 0.1601 | - | - |
| 0.2743 | 536 | 0.3403 | - | - |
| 0.2748 | 537 | 0.3067 | - | - |
| 0.2753 | 538 | 0.2028 | - | - |
| 0.2758 | 539 | 0.1166 | - | - |
| 0.2764 | 540 | 0.1655 | - | - |
| 0.2769 | 541 | 0.1911 | - | - |
| 0.2774 | 542 | 0.2947 | - | - |
| 0.2779 | 543 | 0.259 | - | - |
| 0.2784 | 544 | 0.1485 | - | - |
| 0.2789 | 545 | 0.2414 | - | - |
| 0.2794 | 546 | 0.1195 | - | - |
| 0.2799 | 547 | 0.128 | - | - |
| 0.2805 | 548 | 0.1484 | - | - |
| 0.2810 | 549 | 0.1338 | - | - |
| 0.2815 | 550 | 0.1516 | - | - |
| 0.2820 | 551 | 0.1856 | - | - |
| 0.2825 | 552 | 0.2027 | - | - |
| 0.2830 | 553 | 0.1686 | - | - |
| 0.2835 | 554 | 0.1355 | - | - |
| 0.2840 | 555 | 0.1367 | - | - |
| 0.2845 | 556 | 0.0977 | - | - |
| 0.2851 | 557 | 0.0916 | - | - |
| 0.2856 | 558 | 0.1016 | - | - |
| 0.2861 | 559 | 0.105 | - | - |
| 0.2866 | 560 | 0.0681 | - | - |
| 0.2871 | 561 | 0.1317 | - | - |
| 0.2876 | 562 | 0.0983 | - | - |
| 0.2881 | 563 | 0.1189 | - | - |
| 0.2886 | 564 | 0.1822 | - | - |
| 0.2892 | 565 | 0.1149 | - | - |
| 0.2897 | 566 | 0.0516 | - | - |
| 0.2902 | 567 | 0.0912 | - | - |
| 0.2907 | 568 | 0.1609 | - | - |
| 0.2912 | 569 | 0.1439 | - | - |
| 0.2917 | 570 | 0.1051 | - | - |
| 0.2922 | 571 | 0.1287 | - | - |
| 0.2927 | 572 | 0.1966 | - | - |
| 0.2932 | 573 | 0.1681 | - | - |
| 0.2938 | 574 | 0.1248 | - | - |
| 0.2943 | 575 | 0.204 | - | - |
| 0.2948 | 576 | 0.2069 | - | - |
| 0.2953 | 577 | 0.1346 | - | - |
| 0.2958 | 578 | 0.144 | - | - |
| 0.2963 | 579 | 0.1006 | - | - |
| 0.2968 | 580 | 0.0653 | - | - |
| 0.2973 | 581 | 0.0606 | - | - |
| 0.2979 | 582 | 0.0959 | - | - |
| 0.2984 | 583 | 0.2208 | - | - |
| 0.2989 | 584 | 0.2492 | - | - |
| 0.2994 | 585 | 0.224 | - | - |
| 0.2999 | 586 | 0.2556 | - | - |
| 0.3004 | 587 | 0.1741 | - | - |
| 0.3009 | 588 | 0.1486 | - | - |
| 0.3014 | 589 | 0.2298 | - | - |
| 0.3019 | 590 | 0.1557 | - | - |
| 0.3025 | 591 | 0.2844 | - | - |
| 0.3030 | 592 | 0.235 | - | - |
| 0.3035 | 593 | 0.1801 | - | - |
| 0.3040 | 594 | 0.1602 | - | - |
| 0.3045 | 595 | 0.131 | - | - |
| 0.3050 | 596 | 0.1771 | - | - |
| 0.3055 | 597 | 0.0996 | - | - |
| 0.3060 | 598 | 0.0809 | - | - |
| 0.3066 | 599 | 0.1244 | - | - |
| 0.3071 | 600 | 0.1467 | 1.1270 | 0.9164 |
| 0.3076 | 601 | 0.1539 | - | - |
| 0.3081 | 602 | 0.1627 | - | - |
| 0.3086 | 603 | 0.094 | - | - |
| 0.3091 | 604 | 0.0673 | - | - |
| 0.3096 | 605 | 0.0628 | - | - |
| 0.3101 | 606 | 0.0661 | - | - |
| 0.3106 | 607 | 0.059 | - | - |
| 0.3112 | 608 | 0.0386 | - | - |
| 0.3117 | 609 | 0.0659 | - | - |
| 0.3122 | 610 | 0.1256 | - | - |
| 0.3127 | 611 | 0.2102 | - | - |
| 0.3132 | 612 | 0.2038 | - | - |
| 0.3137 | 613 | 0.2993 | - | - |
| 0.3142 | 614 | 0.2537 | - | - |
| 0.3147 | 615 | 0.2742 | - | - |
| 0.3153 | 616 | 0.2262 | - | - |
| 0.3158 | 617 | 0.1024 | - | - |
| 0.3163 | 618 | 0.1367 | - | - |
| 0.3168 | 619 | 0.2258 | - | - |
| 0.3173 | 620 | 0.1861 | - | - |
| 0.3178 | 621 | 0.1482 | - | - |
| 0.3183 | 622 | 0.1205 | - | - |
| 0.3188 | 623 | 0.2656 | - | - |
| 0.3193 | 624 | 0.3613 | - | - |
| 0.3199 | 625 | 0.1914 | - | - |
| 0.3204 | 626 | 0.2363 | - | - |
| 0.3209 | 627 | 0.1523 | - | - |
| 0.3214 | 628 | 0.1676 | - | - |
| 0.3219 | 629 | 0.1536 | - | - |
| 0.3224 | 630 | 0.1544 | - | - |
| 0.3229 | 631 | 0.1694 | - | - |
| 0.3234 | 632 | 0.133 | - | - |
| 0.3240 | 633 | 0.163 | - | - |
| 0.3245 | 634 | 0.2706 | - | - |
| 0.3250 | 635 | 0.3171 | - | - |
| 0.3255 | 636 | 0.2479 | - | - |
| 0.3260 | 637 | 0.1399 | - | - |
| 0.3265 | 638 | 0.1158 | - | - |
| 0.3270 | 639 | 0.17 | - | - |
| 0.3275 | 640 | 0.1492 | - | - |
| 0.3280 | 641 | 0.2517 | - | - |
| 0.3286 | 642 | 0.1551 | - | - |
| 0.3291 | 643 | 0.083 | - | - |
| 0.3296 | 644 | 0.0845 | - | - |
| 0.3301 | 645 | 0.321 | - | - |
| 0.3306 | 646 | 0.2162 | - | - |
| 0.3311 | 647 | 0.1856 | - | - |
| 0.3316 | 648 | 0.2404 | - | - |
| 0.3321 | 649 | 0.2655 | - | - |
| 0.3327 | 650 | 0.1434 | - | - |
| 0.3332 | 651 | 0.0856 | - | - |
| 0.3337 | 652 | 0.1041 | - | - |
| 0.3342 | 653 | 0.2421 | - | - |
| 0.3347 | 654 | 0.2219 | - | - |
| 0.3352 | 655 | 0.1435 | - | - |
| 0.3357 | 656 | 0.1785 | - | - |
| 0.3362 | 657 | 0.1608 | - | - |
| 0.3367 | 658 | 0.1657 | - | - |
| 0.3373 | 659 | 0.1231 | - | - |
| 0.3378 | 660 | 0.1121 | - | - |
| 0.3383 | 661 | 0.1749 | - | - |
| 0.3388 | 662 | 0.166 | - | - |
| 0.3393 | 663 | 0.1778 | - | - |
| 0.3398 | 664 | 0.1772 | - | - |
| 0.3403 | 665 | 0.1969 | - | - |
| 0.3408 | 666 | 0.249 | - | - |
| 0.3414 | 667 | 0.1366 | - | - |
| 0.3419 | 668 | 0.0856 | - | - |
| 0.3424 | 669 | 0.212 | - | - |
| 0.3429 | 670 | 0.1776 | - | - |
| 0.3434 | 671 | 0.1713 | - | - |
| 0.3439 | 672 | 0.1108 | - | - |
| 0.3444 | 673 | 0.2103 | - | - |
| 0.3449 | 674 | 0.2127 | - | - |
| 0.3454 | 675 | 0.1979 | - | - |
| 0.3460 | 676 | 0.2033 | - | - |
| 0.3465 | 677 | 0.2822 | - | - |
| 0.3470 | 678 | 0.2751 | - | - |
| 0.3475 | 679 | 0.205 | - | - |
| 0.3480 | 680 | 0.1969 | - | - |
| 0.3485 | 681 | 0.3404 | - | - |
| 0.3490 | 682 | 0.2905 | - | - |
| 0.3495 | 683 | 0.2031 | - | - |
| 0.3501 | 684 | 0.1358 | - | - |
| 0.3506 | 685 | 0.1563 | - | - |
| 0.3511 | 686 | 0.1294 | - | - |
| 0.3516 | 687 | 0.1183 | - | - |
| 0.3521 | 688 | 0.0738 | - | - |
| 0.3526 | 689 | 0.088 | - | - |
| 0.3531 | 690 | 0.1325 | - | - |
| 0.3536 | 691 | 0.2572 | - | - |
| 0.3541 | 692 | 0.2373 | - | - |
| 0.3547 | 693 | 0.2355 | - | - |
| 0.3552 | 694 | 0.205 | - | - |
| 0.3557 | 695 | 0.1163 | - | - |
| 0.3562 | 696 | 0.1946 | - | - |
| 0.3567 | 697 | 0.1677 | - | - |
| 0.3572 | 698 | 0.1721 | - | - |
| 0.3577 | 699 | 0.2013 | - | - |
| 0.3582 | 700 | 0.1442 | 0.8623 | 0.9306 |
| 0.3588 | 701 | 0.1081 | - | - |
| 0.3593 | 702 | 0.0767 | - | - |
| 0.3598 | 703 | 0.1696 | - | - |
| 0.3603 | 704 | 0.1315 | - | - |
| 0.3608 | 705 | 0.0592 | - | - |
| 0.3613 | 706 | 0.1208 | - | - |
| 0.3618 | 707 | 0.2346 | - | - |
| 0.3623 | 708 | 0.192 | - | - |
| 0.3628 | 709 | 0.1038 | - | - |
| 0.3634 | 710 | 0.1107 | - | - |
| 0.3639 | 711 | 0.0839 | - | - |
| 0.3644 | 712 | 0.1804 | - | - |
| 0.3649 | 713 | 0.1581 | - | - |
| 0.3654 | 714 | 0.1469 | - | - |
| 0.3659 | 715 | 0.1384 | - | - |
| 0.3664 | 716 | 0.091 | - | - |
| 0.3669 | 717 | 0.0733 | - | - |
| 0.3675 | 718 | 0.2287 | - | - |
| 0.3680 | 719 | 0.1345 | - | - |
| 0.3685 | 720 | 0.3101 | - | - |
| 0.3690 | 721 | 0.2625 | - | - |
| 0.3695 | 722 | 0.259 | - | - |
| 0.3700 | 723 | 0.1677 | - | - |
| 0.3705 | 724 | 0.1824 | - | - |
| 0.3710 | 725 | 0.2012 | - | - |
| 0.3715 | 726 | 0.0987 | - | - |
| 0.3721 | 727 | 0.0913 | - | - |
| 0.3726 | 728 | 0.112 | - | - |
| 0.3731 | 729 | 0.077 | - | - |
| 0.3736 | 730 | 0.0999 | - | - |
| 0.3741 | 731 | 0.1413 | - | - |
| 0.3746 | 732 | 0.1158 | - | - |
| 0.3751 | 733 | 0.1236 | - | - |
| 0.3756 | 734 | 0.1163 | - | - |
| 0.3762 | 735 | 0.1935 | - | - |
| 0.3767 | 736 | 0.1443 | - | - |
| 0.3772 | 737 | 0.1393 | - | - |
| 0.3777 | 738 | 0.1496 | - | - |
| 0.3782 | 739 | 0.1925 | - | - |
| 0.3787 | 740 | 0.2229 | - | - |
| 0.3792 | 741 | 0.1062 | - | - |
| 0.3797 | 742 | 0.1529 | - | - |
| 0.3802 | 743 | 0.1309 | - | - |
| 0.3808 | 744 | 0.1259 | - | - |
| 0.3813 | 745 | 0.1203 | - | - |
| 0.3818 | 746 | 0.1636 | - | - |
| 0.3823 | 747 | 0.3181 | - | - |
| 0.3828 | 748 | 0.2253 | - | - |
| 0.3833 | 749 | 0.1559 | - | - |
| 0.3838 | 750 | 0.1206 | - | - |
| 0.3843 | 751 | 0.099 | - | - |
| 0.3849 | 752 | 0.0946 | - | - |
| 0.3854 | 753 | 0.0961 | - | - |
| 0.3859 | 754 | 0.1094 | - | - |
| 0.3864 | 755 | 0.2492 | - | - |
| 0.3869 | 756 | 0.2146 | - | - |
| 0.3874 | 757 | 0.2002 | - | - |
| 0.3879 | 758 | 0.2457 | - | - |
| 0.3884 | 759 | 0.1416 | - | - |
| 0.3889 | 760 | 0.1471 | - | - |
| 0.3895 | 761 | 0.1082 | - | - |
| 0.3900 | 762 | 0.1395 | - | - |
| 0.3905 | 763 | 0.1187 | - | - |
| 0.3910 | 764 | 0.0906 | - | - |
| 0.3915 | 765 | 0.135 | - | - |
| 0.3920 | 766 | 0.1329 | - | - |
| 0.3925 | 767 | 0.1231 | - | - |
| 0.3930 | 768 | 0.1393 | - | - |
| 0.3936 | 769 | 0.2371 | - | - |
| 0.3941 | 770 | 0.2398 | - | - |
| 0.3946 | 771 | 0.1726 | - | - |
| 0.3951 | 772 | 0.2065 | - | - |
| 0.3956 | 773 | 0.1182 | - | - |
| 0.3961 | 774 | 0.1773 | - | - |
| 0.3966 | 775 | 0.1934 | - | - |
| 0.3971 | 776 | 0.156 | - | - |
| 0.3976 | 777 | 0.1043 | - | - |
| 0.3982 | 778 | 0.111 | - | - |
| 0.3987 | 779 | 0.0814 | - | - |
| 0.3992 | 780 | 0.1229 | - | - |
| 0.3997 | 781 | 0.1041 | - | - |
| 0.4002 | 782 | 0.1793 | - | - |
| 0.4007 | 783 | 0.1291 | - | - |
| 0.4012 | 784 | 0.0874 | - | - |
| 0.4017 | 785 | 0.0509 | - | - |
| 0.4023 | 786 | 0.0774 | - | - |
| 0.4028 | 787 | 0.1298 | - | - |
| 0.4033 | 788 | 0.13 | - | - |
| 0.4038 | 789 | 0.1041 | - | - |
| 0.4043 | 790 | 0.0824 | - | - |
| 0.4048 | 791 | 0.1459 | - | - |
| 0.4053 | 792 | 0.1798 | - | - |
| 0.4058 | 793 | 0.1415 | - | - |
| 0.4063 | 794 | 0.0973 | - | - |
| 0.4069 | 795 | 0.1115 | - | - |
| 0.4074 | 796 | 0.0684 | - | - |
| 0.4079 | 797 | 0.0988 | - | - |
| 0.4084 | 798 | 0.1505 | - | - |
| 0.4089 | 799 | 0.1577 | - | - |
| 0.4094 | 800 | 0.2474 | 0.8913 | 0.9334 |
| 0.4099 | 801 | 0.3658 | - | - |
| 0.4104 | 802 | 0.2929 | - | - |
| 0.4110 | 803 | 0.246 | - | - |
| 0.4115 | 804 | 0.1213 | - | - |
| 0.4120 | 805 | 0.0929 | - | - |
| 0.4125 | 806 | 0.1291 | - | - |
| 0.4130 | 807 | 0.1502 | - | - |
| 0.4135 | 808 | 0.1575 | - | - |
| 0.4140 | 809 | 0.1395 | - | - |
| 0.4145 | 810 | 0.1421 | - | - |
| 0.4150 | 811 | 0.1795 | - | - |
| 0.4156 | 812 | 0.1592 | - | - |
| 0.4161 | 813 | 0.1621 | - | - |
| 0.4166 | 814 | 0.1877 | - | - |
| 0.4171 | 815 | 0.1868 | - | - |
| 0.4176 | 816 | 0.1564 | - | - |
| 0.4181 | 817 | 0.1047 | - | - |
| 0.4186 | 818 | 0.0857 | - | - |
| 0.4191 | 819 | 0.1159 | - | - |
| 0.4197 | 820 | 0.1519 | - | - |
| 0.4202 | 821 | 0.1976 | - | - |
| 0.4207 | 822 | 0.2072 | - | - |
| 0.4212 | 823 | 0.1719 | - | - |
| 0.4217 | 824 | 0.1046 | - | - |
| 0.4222 | 825 | 0.0568 | - | - |
| 0.4227 | 826 | 0.065 | - | - |
| 0.4232 | 827 | 0.1222 | - | - |
| 0.4237 | 828 | 0.0739 | - | - |
| 0.4243 | 829 | 0.0872 | - | - |
| 0.4248 | 830 | 0.1615 | - | - |
| 0.4253 | 831 | 0.198 | - | - |
| 0.4258 | 832 | 0.1537 | - | - |
| 0.4263 | 833 | 0.1463 | - | - |
| 0.4268 | 834 | 0.1315 | - | - |
| 0.4273 | 835 | 0.1306 | - | - |
| 0.4278 | 836 | 0.1842 | - | - |
| 0.4284 | 837 | 0.1698 | - | - |
| 0.4289 | 838 | 0.1345 | - | - |
| 0.4294 | 839 | 0.0589 | - | - |
| 0.4299 | 840 | 0.0509 | - | - |
| 0.4304 | 841 | 0.1266 | - | - |
| 0.4309 | 842 | 0.2453 | - | - |
| 0.4314 | 843 | 0.162 | - | - |
| 0.4319 | 844 | 0.0821 | - | - |
| 0.4324 | 845 | 0.1036 | - | - |
| 0.4330 | 846 | 0.1698 | - | - |
| 0.4335 | 847 | 0.2177 | - | - |
| 0.4340 | 848 | 0.188 | - | - |
| 0.4345 | 849 | 0.2167 | - | - |
| 0.4350 | 850 | 0.2258 | - | - |
| 0.4355 | 851 | 0.1215 | - | - |
| 0.4360 | 852 | 0.0806 | - | - |
| 0.4365 | 853 | 0.1588 | - | - |
| 0.4371 | 854 | 0.1657 | - | - |
| 0.4376 | 855 | 0.1623 | - | - |
| 0.4381 | 856 | 0.1522 | - | - |
| 0.4386 | 857 | 0.1239 | - | - |
| 0.4391 | 858 | 0.2135 | - | - |
| 0.4396 | 859 | 0.1132 | - | - |
| 0.4401 | 860 | 0.1357 | - | - |
| 0.4406 | 861 | 0.1371 | - | - |
| 0.4411 | 862 | 0.0788 | - | - |
| 0.4417 | 863 | 0.2182 | - | - |
| 0.4422 | 864 | 0.247 | - | - |
| 0.4427 | 865 | 0.3319 | - | - |
| 0.4432 | 866 | 0.2565 | - | - |
| 0.4437 | 867 | 0.2339 | - | - |
| 0.4442 | 868 | 0.1491 | - | - |
| 0.4447 | 869 | 0.1654 | - | - |
| 0.4452 | 870 | 0.1651 | - | - |
| 0.4458 | 871 | 0.133 | - | - |
| 0.4463 | 872 | 0.0846 | - | - |
| 0.4468 | 873 | 0.0569 | - | - |
| 0.4473 | 874 | 0.205 | - | - |
| 0.4478 | 875 | 0.1148 | - | - |
| 0.4483 | 876 | 0.1082 | - | - |
| 0.4488 | 877 | 0.2288 | - | - |
| 0.4493 | 878 | 0.1601 | - | - |
| 0.4498 | 879 | 0.1174 | - | - |
| 0.4504 | 880 | 0.0646 | - | - |
| 0.4509 | 881 | 0.0693 | - | - |
| 0.4514 | 882 | 0.1002 | - | - |
| 0.4519 | 883 | 0.1059 | - | - |
| 0.4524 | 884 | 0.1174 | - | - |
| 0.4529 | 885 | 0.0908 | - | - |
| 0.4534 | 886 | 0.0897 | - | - |
| 0.4539 | 887 | 0.3261 | - | - |
| 0.4545 | 888 | 0.3079 | - | - |
| 0.4550 | 889 | 0.4066 | - | - |
| 0.4555 | 890 | 0.236 | - | - |
| 0.4560 | 891 | 0.3301 | - | - |
| 0.4565 | 892 | 0.2789 | - | - |
| 0.4570 | 893 | 0.2218 | - | - |
| 0.4575 | 894 | 0.1181 | - | - |
| 0.4580 | 895 | 0.2813 | - | - |
| 0.4585 | 896 | 0.192 | - | - |
| 0.4591 | 897 | 0.1511 | - | - |
| 0.4596 | 898 | 0.1222 | - | - |
| 0.4601 | 899 | 0.2559 | - | - |
| 0.4606 | 900 | 0.2179 | 0.8456 | 0.9239 |
| 0.4611 | 901 | 0.2879 | - | - |
| 0.4616 | 902 | 0.1087 | - | - |
| 0.4621 | 903 | 0.1736 | - | - |
| 0.4626 | 904 | 0.1514 | - | - |
| 0.4632 | 905 | 0.1984 | - | - |
| 0.4637 | 906 | 0.2888 | - | - |
| 0.4642 | 907 | 0.1639 | - | - |
| 0.4647 | 908 | 0.1533 | - | - |
| 0.4652 | 909 | 0.1575 | - | - |
| 0.4657 | 910 | 0.1716 | - | - |
| 0.4662 | 911 | 0.2199 | - | - |
| 0.4667 | 912 | 0.2275 | - | - |
| 0.4672 | 913 | 0.2263 | - | - |
| 0.4678 | 914 | 0.2248 | - | - |
| 0.4683 | 915 | 0.1751 | - | - |
| 0.4688 | 916 | 0.3353 | - | - |
| 0.4693 | 917 | 0.2627 | - | - |
| 0.4698 | 918 | 0.1676 | - | - |
| 0.4703 | 919 | 0.1338 | - | - |
| 0.4708 | 920 | 0.0972 | - | - |
| 0.4713 | 921 | 0.2103 | - | - |
| 0.4719 | 922 | 0.3038 | - | - |
| 0.4724 | 923 | 0.2816 | - | - |
| 0.4729 | 924 | 0.1309 | - | - |
| 0.4734 | 925 | 0.1162 | - | - |
| 0.4739 | 926 | 0.1112 | - | - |
| 0.4744 | 927 | 0.2015 | - | - |
| 0.4749 | 928 | 0.2021 | - | - |
| 0.4754 | 929 | 0.2221 | - | - |
| 0.4759 | 930 | 0.203 | - | - |
| 0.4765 | 931 | 0.1194 | - | - |
| 0.4770 | 932 | 0.1535 | - | - |
| 0.4775 | 933 | 0.1551 | - | - |
| 0.4780 | 934 | 0.2792 | - | - |
| 0.4785 | 935 | 0.2597 | - | - |
| 0.4790 | 936 | 0.151 | - | - |
| 0.4795 | 937 | 0.2264 | - | - |
| 0.4800 | 938 | 0.1509 | - | - |
| 0.4806 | 939 | 0.1551 | - | - |
| 0.4811 | 940 | 0.1657 | - | - |
| 0.4816 | 941 | 0.1051 | - | - |
| 0.4821 | 942 | 0.1137 | - | - |
| 0.4826 | 943 | 0.0957 | - | - |
| 0.4831 | 944 | 0.0603 | - | - |
| 0.4836 | 945 | 0.0854 | - | - |
| 0.4841 | 946 | 0.1433 | - | - |
| 0.4846 | 947 | 0.233 | - | - |
| 0.4852 | 948 | 0.1573 | - | - |
| 0.4857 | 949 | 0.1465 | - | - |
| 0.4862 | 950 | 0.221 | - | - |
| 0.4867 | 951 | 0.3344 | - | - |
| 0.4872 | 952 | 0.1623 | - | - |
| 0.4877 | 953 | 0.1785 | - | - |
| 0.4882 | 954 | 0.1585 | - | - |
| 0.4887 | 955 | 0.1802 | - | - |
| 0.4893 | 956 | 0.1554 | - | - |
| 0.4898 | 957 | 0.2281 | - | - |
| 0.4903 | 958 | 0.1498 | - | - |
| 0.4908 | 959 | 0.1547 | - | - |
| 0.4913 | 960 | 0.1319 | - | - |
| 0.4918 | 961 | 0.0945 | - | - |
| 0.4923 | 962 | 0.086 | - | - |
| 0.4928 | 963 | 0.1023 | - | - |
| 0.4933 | 964 | 0.0859 | - | - |
| 0.4939 | 965 | 0.1245 | - | - |
| 0.4944 | 966 | 0.2234 | - | - |
| 0.4949 | 967 | 0.2334 | - | - |
| 0.4954 | 968 | 0.2788 | - | - |
| 0.4959 | 969 | 0.192 | - | - |
| 0.4964 | 970 | 0.1285 | - | - |
| 0.4969 | 971 | 0.0865 | - | - |
| 0.4974 | 972 | 0.089 | - | - |
| 0.4980 | 973 | 0.1213 | - | - |
| 0.4985 | 974 | 0.1088 | - | - |
| 0.4990 | 975 | 0.0564 | - | - |
| 0.4995 | 976 | 0.0841 | - | - |
| 0.5 | 977 | 0.1902 | - | - |
| 0.5005 | 978 | 0.2538 | - | - |
| 0.5010 | 979 | 0.2385 | - | - |
| 0.5015 | 980 | 0.2652 | - | - |
| 0.5020 | 981 | 0.1625 | - | - |
| 0.5026 | 982 | 0.1364 | - | - |
| 0.5031 | 983 | 0.1422 | - | - |
| 0.5036 | 984 | 0.1529 | - | - |
| 0.5041 | 985 | 0.1085 | - | - |
| 0.5046 | 986 | 0.1494 | - | - |
| 0.5051 | 987 | 0.1333 | - | - |
| 0.5056 | 988 | 0.2365 | - | - |
| 0.5061 | 989 | 0.2787 | - | - |
| 0.5067 | 990 | 0.1841 | - | - |
| 0.5072 | 991 | 0.1548 | - | - |
| 0.5077 | 992 | 0.1494 | - | - |
| 0.5082 | 993 | 0.1816 | - | - |
| 0.5087 | 994 | 0.1641 | - | - |
| 0.5092 | 995 | 0.1836 | - | - |
| 0.5097 | 996 | 0.2396 | - | - |
| 0.5102 | 997 | 0.2292 | - | - |
| 0.5107 | 998 | 0.1604 | - | - |
| 0.5113 | 999 | 0.1498 | - | - |
| 0.5118 | 1000 | 0.1384 | 1.0291 | 0.9411 |
| 0.5123 | 1001 | 0.1992 | - | - |
| 0.5128 | 1002 | 0.1361 | - | - |
| 0.5133 | 1003 | 0.1393 | - | - |
| 0.5138 | 1004 | 0.277 | - | - |
| 0.5143 | 1005 | 0.1861 | - | - |
| 0.5148 | 1006 | 0.1392 | - | - |
| 0.5154 | 1007 | 0.1052 | - | - |
| 0.5159 | 1008 | 0.1087 | - | - |
| 0.5164 | 1009 | 0.1393 | - | - |
| 0.5169 | 1010 | 0.2721 | - | - |
| 0.5174 | 1011 | 0.2208 | - | - |
| 0.5179 | 1012 | 0.3358 | - | - |
| 0.5184 | 1013 | 0.3529 | - | - |
| 0.5189 | 1014 | 0.2818 | - | - |
| 0.5194 | 1015 | 0.1891 | - | - |
| 0.5200 | 1016 | 0.2494 | - | - |
| 0.5205 | 1017 | 0.1279 | - | - |
| 0.5210 | 1018 | 0.1816 | - | - |
| 0.5215 | 1019 | 0.2082 | - | - |
| 0.5220 | 1020 | 0.1992 | - | - |
| 0.5225 | 1021 | 0.1557 | - | - |
| 0.5230 | 1022 | 0.1652 | - | - |
| 0.5235 | 1023 | 0.1922 | - | - |
| 0.5241 | 1024 | 0.1568 | - | - |
| 0.5246 | 1025 | 0.1523 | - | - |
| 0.5251 | 1026 | 0.0997 | - | - |
| 0.5256 | 1027 | 0.1266 | - | - |
| 0.5261 | 1028 | 0.1444 | - | - |
| 0.5266 | 1029 | 0.1271 | - | - |
| 0.5271 | 1030 | 0.1275 | - | - |
| 0.5276 | 1031 | 0.1042 | - | - |
| 0.5281 | 1032 | 0.2974 | - | - |
| 0.5287 | 1033 | 0.2318 | - | - |
| 0.5292 | 1034 | 0.219 | - | - |
| 0.5297 | 1035 | 0.2216 | - | - |
| 0.5302 | 1036 | 0.2356 | - | - |
| 0.5307 | 1037 | 0.1216 | - | - |
| 0.5312 | 1038 | 0.1155 | - | - |
| 0.5317 | 1039 | 0.116 | - | - |
| 0.5322 | 1040 | 0.136 | - | - |
| 0.5328 | 1041 | 0.1097 | - | - |
| 0.5333 | 1042 | 0.1302 | - | - |
| 0.5338 | 1043 | 0.104 | - | - |
| 0.5343 | 1044 | 0.2442 | - | - |
| 0.5348 | 1045 | 0.3245 | - | - |
| 0.5353 | 1046 | 0.2715 | - | - |
| 0.5358 | 1047 | 0.2266 | - | - |
| 0.5363 | 1048 | 0.1993 | - | - |
| 0.5368 | 1049 | 0.389 | - | - |
| 0.5374 | 1050 | 0.3285 | - | - |
| 0.5379 | 1051 | 0.1983 | - | - |
| 0.5384 | 1052 | 0.2304 | - | - |
| 0.5389 | 1053 | 0.1461 | - | - |
| 0.5394 | 1054 | 0.2071 | - | - |
| 0.5399 | 1055 | 0.1981 | - | - |
| 0.5404 | 1056 | 0.1617 | - | - |
| 0.5409 | 1057 | 0.1207 | - | - |
| 0.5415 | 1058 | 0.2387 | - | - |
| 0.5420 | 1059 | 0.1873 | - | - |
| 0.5425 | 1060 | 0.15 | - | - |
| 0.5430 | 1061 | 0.2065 | - | - |
| 0.5435 | 1062 | 0.1288 | - | - |
| 0.5440 | 1063 | 0.2415 | - | - |
| 0.5445 | 1064 | 0.2859 | - | - |
| 0.5450 | 1065 | 0.2759 | - | - |
| 0.5455 | 1066 | 0.1774 | - | - |
| 0.5461 | 1067 | 0.1699 | - | - |
| 0.5466 | 1068 | 0.1672 | - | - |
| 0.5471 | 1069 | 0.11 | - | - |
| 0.5476 | 1070 | 0.1399 | - | - |
| 0.5481 | 1071 | 0.1269 | - | - |
| 0.5486 | 1072 | 0.1486 | - | - |
| 0.5491 | 1073 | 0.1808 | - | - |
| 0.5496 | 1074 | 0.2333 | - | - |
| 0.5502 | 1075 | 0.2294 | - | - |
| 0.5507 | 1076 | 0.2353 | - | - |
| 0.5512 | 1077 | 0.2048 | - | - |
| 0.5517 | 1078 | 0.1881 | - | - |
| 0.5522 | 1079 | 0.3176 | - | - |
| 0.5527 | 1080 | 0.2117 | - | - |
| 0.5532 | 1081 | 0.1842 | - | - |
| 0.5537 | 1082 | 0.1731 | - | - |
| 0.5542 | 1083 | 0.1705 | - | - |
| 0.5548 | 1084 | 0.1573 | - | - |
| 0.5553 | 1085 | 0.2202 | - | - |
| 0.5558 | 1086 | 0.1947 | - | - |
| 0.5563 | 1087 | 0.1856 | - | - |
| 0.5568 | 1088 | 0.1789 | - | - |
| 0.5573 | 1089 | 0.1649 | - | - |
| 0.5578 | 1090 | 0.149 | - | - |
| 0.5583 | 1091 | 0.0808 | - | - |
| 0.5589 | 1092 | 0.2569 | - | - |
| 0.5594 | 1093 | 0.2677 | - | - |
| 0.5599 | 1094 | 0.2107 | - | - |
| 0.5604 | 1095 | 0.2321 | - | - |
| 0.5609 | 1096 | 0.2247 | - | - |
| 0.5614 | 1097 | 0.196 | - | - |
| 0.5619 | 1098 | 0.2243 | - | - |
| 0.5624 | 1099 | 0.1349 | - | - |
| 0.5629 | 1100 | 0.1142 | 0.8562 | 0.946 |
| 0.5635 | 1101 | 0.1154 | - | - |
| 0.5640 | 1102 | 0.131 | - | - |
| 0.5645 | 1103 | 0.1558 | - | - |
| 0.5650 | 1104 | 0.1561 | - | - |
| 0.5655 | 1105 | 0.1499 | - | - |
| 0.5660 | 1106 | 0.0855 | - | - |
| 0.5665 | 1107 | 0.1234 | - | - |
| 0.5670 | 1108 | 0.1204 | - | - |
| 0.5676 | 1109 | 0.1553 | - | - |
| 0.5681 | 1110 | 0.223 | - | - |
| 0.5686 | 1111 | 0.2299 | - | - |
| 0.5691 | 1112 | 0.255 | - | - |
| 0.5696 | 1113 | 0.2056 | - | - |
| 0.5701 | 1114 | 0.1523 | - | - |
| 0.5706 | 1115 | 0.172 | - | - |
| 0.5711 | 1116 | 0.1508 | - | - |
| 0.5716 | 1117 | 0.1798 | - | - |
| 0.5722 | 1118 | 0.1576 | - | - |
| 0.5727 | 1119 | 0.1492 | - | - |
| 0.5732 | 1120 | 0.0768 | - | - |
| 0.5737 | 1121 | 0.1951 | - | - |
| 0.5742 | 1122 | 0.2158 | - | - |
| 0.5747 | 1123 | 0.1478 | - | - |
| 0.5752 | 1124 | 0.2532 | - | - |
| 0.5757 | 1125 | 0.1836 | - | - |
| 0.5763 | 1126 | 0.1444 | - | - |
| 0.5768 | 1127 | 0.1184 | - | - |
| 0.5773 | 1128 | 0.1401 | - | - |
| 0.5778 | 1129 | 0.1703 | - | - |
| 0.5783 | 1130 | 0.1857 | - | - |
| 0.5788 | 1131 | 0.228 | - | - |
| 0.5793 | 1132 | 0.1959 | - | - |
| 0.5798 | 1133 | 0.1765 | - | - |
| 0.5803 | 1134 | 0.2443 | - | - |
| 0.5809 | 1135 | 0.2171 | - | - |
| 0.5814 | 1136 | 0.1295 | - | - |
| 0.5819 | 1137 | 0.2785 | - | - |
| 0.5824 | 1138 | 0.206 | - | - |
| 0.5829 | 1139 | 0.209 | - | - |
| 0.5834 | 1140 | 0.2066 | - | - |
| 0.5839 | 1141 | 0.1312 | - | - |
| 0.5844 | 1142 | 0.2223 | - | - |
| 0.5850 | 1143 | 0.1394 | - | - |
| 0.5855 | 1144 | 0.1158 | - | - |
| 0.5860 | 1145 | 0.1691 | - | - |
| 0.5865 | 1146 | 0.1066 | - | - |
| 0.5870 | 1147 | 0.1556 | - | - |
| 0.5875 | 1148 | 0.111 | - | - |
| 0.5880 | 1149 | 0.1396 | - | - |
| 0.5885 | 1150 | 0.1085 | - | - |
| 0.5890 | 1151 | 0.1031 | - | - |
| 0.5896 | 1152 | 0.1929 | - | - |
| 0.5901 | 1153 | 0.1603 | - | - |
| 0.5906 | 1154 | 0.1406 | - | - |
| 0.5911 | 1155 | 0.1158 | - | - |
| 0.5916 | 1156 | 0.099 | - | - |
| 0.5921 | 1157 | 0.1206 | - | - |
| 0.5926 | 1158 | 0.1012 | - | - |
| 0.5931 | 1159 | 0.1086 | - | - |
| 0.5937 | 1160 | 0.1664 | - | - |
| 0.5942 | 1161 | 0.1599 | - | - |
| 0.5947 | 1162 | 0.1043 | - | - |
| 0.5952 | 1163 | 0.1218 | - | - |
| 0.5957 | 1164 | 0.1374 | - | - |
| 0.5962 | 1165 | 0.2229 | - | - |
| 0.5967 | 1166 | 0.1296 | - | - |
| 0.5972 | 1167 | 0.2131 | - | - |
| 0.5977 | 1168 | 0.2384 | - | - |
| 0.5983 | 1169 | 0.1702 | - | - |
| 0.5988 | 1170 | 0.2961 | - | - |
| 0.5993 | 1171 | 0.2253 | - | - |
| 0.5998 | 1172 | 0.227 | - | - |
| 0.6003 | 1173 | 0.1754 | - | - |
| 0.6008 | 1174 | 0.213 | - | - |
| 0.6013 | 1175 | 0.1376 | - | - |
| 0.6018 | 1176 | 0.104 | - | - |
| 0.6024 | 1177 | 0.092 | - | - |
| 0.6029 | 1178 | 0.3563 | - | - |
| 0.6034 | 1179 | 0.3275 | - | - |
| 0.6039 | 1180 | 0.2145 | - | - |
| 0.6044 | 1181 | 0.125 | - | - |
| 0.6049 | 1182 | 0.2148 | - | - |
| 0.6054 | 1183 | 0.1757 | - | - |
| 0.6059 | 1184 | 0.1953 | - | - |
| 0.6064 | 1185 | 0.1761 | - | - |
| 0.6070 | 1186 | 0.2783 | - | - |
| 0.6075 | 1187 | 0.1437 | - | - |
| 0.6080 | 1188 | 0.153 | - | - |
| 0.6085 | 1189 | 0.1636 | - | - |
| 0.6090 | 1190 | 0.1582 | - | - |
| 0.6095 | 1191 | 0.1718 | - | - |
| 0.6100 | 1192 | 0.21 | - | - |
| 0.6105 | 1193 | 0.1488 | - | - |
| 0.6111 | 1194 | 0.1797 | - | - |
| 0.6116 | 1195 | 0.1181 | - | - |
| 0.6121 | 1196 | 0.0995 | - | - |
| 0.6126 | 1197 | 0.0782 | - | - |
| 0.6131 | 1198 | 0.2162 | - | - |
| 0.6136 | 1199 | 0.1287 | - | - |
| 0.6141 | 1200 | 0.2397 | 0.8919 | 0.9417 |
| 0.6146 | 1201 | 0.1714 | - | - |
| 0.6151 | 1202 | 0.1367 | - | - |
| 0.6157 | 1203 | 0.088 | - | - |
| 0.6162 | 1204 | 0.0878 | - | - |
| 0.6167 | 1205 | 0.2459 | - | - |
| 0.6172 | 1206 | 0.3603 | - | - |
| 0.6177 | 1207 | 0.4254 | - | - |
| 0.6182 | 1208 | 0.3086 | - | - |
| 0.6187 | 1209 | 0.2139 | - | - |
| 0.6192 | 1210 | 0.2397 | - | - |
| 0.6198 | 1211 | 0.2775 | - | - |
| 0.6203 | 1212 | 0.227 | - | - |
| 0.6208 | 1213 | 0.3257 | - | - |
| 0.6213 | 1214 | 0.3003 | - | - |
| 0.6218 | 1215 | 0.2884 | - | - |
| 0.6223 | 1216 | 0.2774 | - | - |
| 0.6228 | 1217 | 0.186 | - | - |
| 0.6233 | 1218 | 0.1779 | - | - |
| 0.6238 | 1219 | 0.1449 | - | - |
| 0.6244 | 1220 | 0.1487 | - | - |
| 0.6249 | 1221 | 0.1443 | - | - |
| 0.6254 | 1222 | 0.1495 | - | - |
| 0.6259 | 1223 | 0.1419 | - | - |
| 0.6264 | 1224 | 0.1274 | - | - |
| 0.6269 | 1225 | 0.1279 | - | - |
| 0.6274 | 1226 | 0.1687 | - | - |
| 0.6279 | 1227 | 0.1501 | - | - |
| 0.6285 | 1228 | 0.2217 | - | - |
| 0.6290 | 1229 | 0.0882 | - | - |
| 0.6295 | 1230 | 0.1099 | - | - |
| 0.6300 | 1231 | 0.1346 | - | - |
| 0.6305 | 1232 | 0.1601 | - | - |
| 0.6310 | 1233 | 0.1521 | - | - |
| 0.6315 | 1234 | 0.1676 | - | - |
| 0.6320 | 1235 | 0.1402 | - | - |
| 0.6325 | 1236 | 0.171 | - | - |
| 0.6331 | 1237 | 0.1263 | - | - |
| 0.6336 | 1238 | 0.0966 | - | - |
| 0.6341 | 1239 | 0.074 | - | - |
| 0.6346 | 1240 | 0.1244 | - | - |
| 0.6351 | 1241 | 0.2048 | - | - |
| 0.6356 | 1242 | 0.1798 | - | - |
| 0.6361 | 1243 | 0.1455 | - | - |
| 0.6366 | 1244 | 0.1741 | - | - |
| 0.6372 | 1245 | 0.121 | - | - |
| 0.6377 | 1246 | 0.1885 | - | - |
| 0.6382 | 1247 | 0.2382 | - | - |
| 0.6387 | 1248 | 0.3496 | - | - |
| 0.6392 | 1249 | 0.2415 | - | - |
| 0.6397 | 1250 | 0.3394 | - | - |
| 0.6402 | 1251 | 0.2355 | - | - |
| 0.6407 | 1252 | 0.2637 | - | - |
| 0.6412 | 1253 | 0.1075 | - | - |
| 0.6418 | 1254 | 0.139 | - | - |
| 0.6423 | 1255 | 0.179 | - | - |
| 0.6428 | 1256 | 0.192 | - | - |
| 0.6433 | 1257 | 0.2076 | - | - |
| 0.6438 | 1258 | 0.1855 | - | - |
| 0.6443 | 1259 | 0.1788 | - | - |
| 0.6448 | 1260 | 0.1077 | - | - |
| 0.6453 | 1261 | 0.1148 | - | - |
| 0.6459 | 1262 | 0.1379 | - | - |
| 0.6464 | 1263 | 0.0777 | - | - |
| 0.6469 | 1264 | 0.0775 | - | - |
| 0.6474 | 1265 | 0.0697 | - | - |
| 0.6479 | 1266 | 0.1063 | - | - |
| 0.6484 | 1267 | 0.1449 | - | - |
| 0.6489 | 1268 | 0.125 | - | - |
| 0.6494 | 1269 | 0.0831 | - | - |
| 0.6499 | 1270 | 0.0689 | - | - |
| 0.6505 | 1271 | 0.0886 | - | - |
| 0.6510 | 1272 | 0.172 | - | - |
| 0.6515 | 1273 | 0.1881 | - | - |
| 0.6520 | 1274 | 0.1712 | - | - |
| 0.6525 | 1275 | 0.1097 | - | - |
| 0.6530 | 1276 | 0.0811 | - | - |
| 0.6535 | 1277 | 0.1344 | - | - |
| 0.6540 | 1278 | 0.0939 | - | - |
| 0.6546 | 1279 | 0.114 | - | - |
| 0.6551 | 1280 | 0.1289 | - | - |
| 0.6556 | 1281 | 0.2418 | - | - |
| 0.6561 | 1282 | 0.1735 | - | - |
| 0.6566 | 1283 | 0.152 | - | - |
| 0.6571 | 1284 | 0.1477 | - | - |
| 0.6576 | 1285 | 0.277 | - | - |
| 0.6581 | 1286 | 0.1857 | - | - |
| 0.6586 | 1287 | 0.2902 | - | - |
| 0.6592 | 1288 | 0.3308 | - | - |
| 0.6597 | 1289 | 0.3731 | - | - |
| 0.6602 | 1290 | 0.1999 | - | - |
| 0.6607 | 1291 | 0.1524 | - | - |
| 0.6612 | 1292 | 0.171 | - | - |
| 0.6617 | 1293 | 0.1967 | - | - |
| 0.6622 | 1294 | 0.1741 | - | - |
| 0.6627 | 1295 | 0.4263 | - | - |
| 0.6633 | 1296 | 0.3758 | - | - |
| 0.6638 | 1297 | 0.2932 | - | - |
| 0.6643 | 1298 | 0.2372 | - | - |
| 0.6648 | 1299 | 0.2378 | - | - |
| 0.6653 | 1300 | 0.1748 | 0.9384 | 0.95 |
| 0.6658 | 1301 | 0.1687 | - | - |
| 0.6663 | 1302 | 0.1226 | - | - |
| 0.6668 | 1303 | 0.0726 | - | - |
| 0.6673 | 1304 | 0.0676 | - | - |
| 0.6679 | 1305 | 0.0745 | - | - |
| 0.6684 | 1306 | 0.0989 | - | - |
| 0.6689 | 1307 | 0.1513 | - | - |
| 0.6694 | 1308 | 0.105 | - | - |
| 0.6699 | 1309 | 0.0861 | - | - |
| 0.6704 | 1310 | 0.206 | - | - |
| 0.6709 | 1311 | 0.2329 | - | - |
| 0.6714 | 1312 | 0.2457 | - | - |
| 0.6720 | 1313 | 0.2435 | - | - |
| 0.6725 | 1314 | 0.2518 | - | - |
| 0.6730 | 1315 | 0.1494 | - | - |
| 0.6735 | 1316 | 0.1366 | - | - |
| 0.6740 | 1317 | 0.1331 | - | - |
| 0.6745 | 1318 | 0.0924 | - | - |
| 0.6750 | 1319 | 0.1809 | - | - |
| 0.6755 | 1320 | 0.2308 | - | - |
| 0.6760 | 1321 | 0.143 | - | - |
| 0.6766 | 1322 | 0.1312 | - | - |
| 0.6771 | 1323 | 0.155 | - | - |
| 0.6776 | 1324 | 0.1618 | - | - |
| 0.6781 | 1325 | 0.1136 | - | - |
| 0.6786 | 1326 | 0.2256 | - | - |
| 0.6791 | 1327 | 0.2588 | - | - |
| 0.6796 | 1328 | 0.2683 | - | - |
| 0.6801 | 1329 | 0.2722 | - | - |
| 0.6807 | 1330 | 0.1893 | - | - |
| 0.6812 | 1331 | 0.1982 | - | - |
| 0.6817 | 1332 | 0.1641 | - | - |
| 0.6822 | 1333 | 0.128 | - | - |
| 0.6827 | 1334 | 0.1075 | - | - |
| 0.6832 | 1335 | 0.1897 | - | - |
| 0.6837 | 1336 | 0.2387 | - | - |
| 0.6842 | 1337 | 0.2168 | - | - |
| 0.6847 | 1338 | 0.1373 | - | - |
| 0.6853 | 1339 | 0.1824 | - | - |
| 0.6858 | 1340 | 0.1392 | - | - |
| 0.6863 | 1341 | 0.1425 | - | - |
| 0.6868 | 1342 | 0.1798 | - | - |
| 0.6873 | 1343 | 0.2477 | - | - |
| 0.6878 | 1344 | 0.1615 | - | - |
| 0.6883 | 1345 | 0.301 | - | - |
| 0.6888 | 1346 | 0.2127 | - | - |
| 0.6894 | 1347 | 0.1629 | - | - |
| 0.6899 | 1348 | 0.1441 | - | - |
| 0.6904 | 1349 | 0.1267 | - | - |
| 0.6909 | 1350 | 0.1648 | - | - |
| 0.6914 | 1351 | 0.2091 | - | - |
| 0.6919 | 1352 | 0.1479 | - | - |
| 0.6924 | 1353 | 0.1521 | - | - |
| 0.6929 | 1354 | 0.138 | - | - |
| 0.6934 | 1355 | 0.2449 | - | - |
| 0.6940 | 1356 | 0.2294 | - | - |
| 0.6945 | 1357 | 0.2161 | - | - |
| 0.6950 | 1358 | 0.2344 | - | - |
| 0.6955 | 1359 | 0.2294 | - | - |
| 0.6960 | 1360 | 0.1281 | - | - |
| 0.6965 | 1361 | 0.1378 | - | - |
| 0.6970 | 1362 | 0.1468 | - | - |
| 0.6975 | 1363 | 0.1331 | - | - |
| 0.6981 | 1364 | 0.1237 | - | - |
| 0.6986 | 1365 | 0.1272 | - | - |
| 0.6991 | 1366 | 0.1021 | - | - |
| 0.6996 | 1367 | 0.1575 | - | - |
| 0.7001 | 1368 | 0.1118 | - | - |
| 0.7006 | 1369 | 0.2497 | - | - |
| 0.7011 | 1370 | 0.1343 | - | - |
| 0.7016 | 1371 | 0.1654 | - | - |
| 0.7021 | 1372 | 0.213 | - | - |
| 0.7027 | 1373 | 0.2429 | - | - |
| 0.7032 | 1374 | 0.256 | - | - |
| 0.7037 | 1375 | 0.2483 | - | - |
| 0.7042 | 1376 | 0.1414 | - | - |
| 0.7047 | 1377 | 0.1145 | - | - |
| 0.7052 | 1378 | 0.1057 | - | - |
| 0.7057 | 1379 | 0.1681 | - | - |
| 0.7062 | 1380 | 0.1024 | - | - |
| 0.7068 | 1381 | 0.1126 | - | - |
| 0.7073 | 1382 | 0.0643 | - | - |
| 0.7078 | 1383 | 0.1568 | - | - |
| 0.7083 | 1384 | 0.1244 | - | - |
| 0.7088 | 1385 | 0.2137 | - | - |
| 0.7093 | 1386 | 0.204 | - | - |
| 0.7098 | 1387 | 0.1821 | - | - |
| 0.7103 | 1388 | 0.3117 | - | - |
| 0.7108 | 1389 | 0.3247 | - | - |
| 0.7114 | 1390 | 0.1847 | - | - |
| 0.7119 | 1391 | 0.1467 | - | - |
| 0.7124 | 1392 | 0.1288 | - | - |
| 0.7129 | 1393 | 0.0978 | - | - |
| 0.7134 | 1394 | 0.1062 | - | - |
| 0.7139 | 1395 | 0.1502 | - | - |
| 0.7144 | 1396 | 0.1211 | - | - |
| 0.7149 | 1397 | 0.1493 | - | - |
| 0.7155 | 1398 | 0.1302 | - | - |
| 0.7160 | 1399 | 0.0987 | - | - |
| 0.7165 | 1400 | 0.1651 | 0.9160 | 0.9431 |
| 0.7170 | 1401 | 0.1728 | - | - |
| 0.7175 | 1402 | 0.1256 | - | - |
| 0.7180 | 1403 | 0.1498 | - | - |
| 0.7185 | 1404 | 0.2098 | - | - |
| 0.7190 | 1405 | 0.1515 | - | - |
| 0.7195 | 1406 | 0.261 | - | - |
| 0.7201 | 1407 | 0.1713 | - | - |
| 0.7206 | 1408 | 0.144 | - | - |
| 0.7211 | 1409 | 0.1453 | - | - |
| 0.7216 | 1410 | 0.1835 | - | - |
| 0.7221 | 1411 | 0.203 | - | - |
| 0.7226 | 1412 | 0.1583 | - | - |
| 0.7231 | 1413 | 0.2432 | - | - |
| 0.7236 | 1414 | 0.1884 | - | - |
| 0.7242 | 1415 | 0.2799 | - | - |
| 0.7247 | 1416 | 0.2761 | - | - |
| 0.7252 | 1417 | 0.2778 | - | - |
| 0.7257 | 1418 | 0.2611 | - | - |
| 0.7262 | 1419 | 0.2139 | - | - |
| 0.7267 | 1420 | 0.1985 | - | - |
| 0.7272 | 1421 | 0.1684 | - | - |
| 0.7277 | 1422 | 0.2776 | - | - |
| 0.7282 | 1423 | 0.2419 | - | - |
| 0.7288 | 1424 | 0.288 | - | - |
| 0.7293 | 1425 | 0.2441 | - | - |
| 0.7298 | 1426 | 0.1746 | - | - |
| 0.7303 | 1427 | 0.198 | - | - |
| 0.7308 | 1428 | 0.242 | - | - |
| 0.7313 | 1429 | 0.1496 | - | - |
| 0.7318 | 1430 | 0.1395 | - | - |
| 0.7323 | 1431 | 0.1684 | - | - |
| 0.7329 | 1432 | 0.1434 | - | - |
| 0.7334 | 1433 | 0.2848 | - | - |
| 0.7339 | 1434 | 0.2669 | - | - |
| 0.7344 | 1435 | 0.2773 | - | - |
| 0.7349 | 1436 | 0.2792 | - | - |
| 0.7354 | 1437 | 0.3026 | - | - |
| 0.7359 | 1438 | 0.2663 | - | - |
| 0.7364 | 1439 | 0.2701 | - | - |
| 0.7369 | 1440 | 0.1858 | - | - |
| 0.7375 | 1441 | 0.1162 | - | - |
| 0.7380 | 1442 | 0.1988 | - | - |
| 0.7385 | 1443 | 0.2179 | - | - |
| 0.7390 | 1444 | 0.1826 | - | - |
| 0.7395 | 1445 | 0.1403 | - | - |
| 0.7400 | 1446 | 0.1355 | - | - |
| 0.7405 | 1447 | 0.1481 | - | - |
| 0.7410 | 1448 | 0.2838 | - | - |
| 0.7416 | 1449 | 0.222 | - | - |
| 0.7421 | 1450 | 0.2777 | - | - |
| 0.7426 | 1451 | 0.2185 | - | - |
| 0.7431 | 1452 | 0.1763 | - | - |
| 0.7436 | 1453 | 0.2524 | - | - |
| 0.7441 | 1454 | 0.1625 | - | - |
| 0.7446 | 1455 | 0.1506 | - | - |
| 0.7451 | 1456 | 0.1469 | - | - |
| 0.7456 | 1457 | 0.2023 | - | - |
| 0.7462 | 1458 | 0.2784 | - | - |
| 0.7467 | 1459 | 0.3714 | - | - |
| 0.7472 | 1460 | 0.2349 | - | - |
| 0.7477 | 1461 | 0.1571 | - | - |
| 0.7482 | 1462 | 0.1476 | - | - |
| 0.7487 | 1463 | 0.15 | - | - |
| 0.7492 | 1464 | 0.2423 | - | - |
| 0.7497 | 1465 | 0.28 | - | - |
| 0.7503 | 1466 | 0.2623 | - | - |
| 0.7508 | 1467 | 0.2755 | - | - |
| 0.7513 | 1468 | 0.3387 | - | - |
| 0.7518 | 1469 | 0.277 | - | - |
| 0.7523 | 1470 | 0.2891 | - | - |
| 0.7528 | 1471 | 0.2561 | - | - |
| 0.7533 | 1472 | 0.183 | - | - |
| 0.7538 | 1473 | 0.2124 | - | - |
| 0.7544 | 1474 | 0.324 | - | - |
| 0.7549 | 1475 | 0.226 | - | - |
| 0.7554 | 1476 | 0.3019 | - | - |
| 0.7559 | 1477 | 0.19 | - | - |
| 0.7564 | 1478 | 0.176 | - | - |
| 0.7569 | 1479 | 0.1554 | - | - |
| 0.7574 | 1480 | 0.1085 | - | - |
| 0.7579 | 1481 | 0.1455 | - | - |
| 0.7584 | 1482 | 0.2385 | - | - |
| 0.7590 | 1483 | 0.2487 | - | - |
| 0.7595 | 1484 | 0.2457 | - | - |
| 0.7600 | 1485 | 0.2513 | - | - |
| 0.7605 | 1486 | 0.2595 | - | - |
| 0.7610 | 1487 | 0.2852 | - | - |
| 0.7615 | 1488 | 0.2745 | - | - |
| 0.7620 | 1489 | 0.2055 | - | - |
| 0.7625 | 1490 | 0.2506 | - | - |
| 0.7631 | 1491 | 0.1605 | - | - |
| 0.7636 | 1492 | 0.1309 | - | - |
| 0.7641 | 1493 | 0.1512 | - | - |
| 0.7646 | 1494 | 0.2551 | - | - |
| 0.7651 | 1495 | 0.2298 | - | - |
| 0.7656 | 1496 | 0.2101 | - | - |
| 0.7661 | 1497 | 0.2243 | - | - |
| 0.7666 | 1498 | 0.157 | - | - |
| 0.7671 | 1499 | 0.1962 | - | - |
| 0.7677 | 1500 | 0.149 | 0.8459 | 0.9388 |
| 0.7682 | 1501 | 0.1411 | - | - |
| 0.7687 | 1502 | 0.2165 | - | - |
| 0.7692 | 1503 | 0.1634 | - | - |
| 0.7697 | 1504 | 0.1771 | - | - |
| 0.7702 | 1505 | 0.2775 | - | - |
| 0.7707 | 1506 | 0.3142 | - | - |
| 0.7712 | 1507 | 0.253 | - | - |
| 0.7718 | 1508 | 0.2443 | - | - |
| 0.7723 | 1509 | 0.3289 | - | - |
| 0.7728 | 1510 | 0.3004 | - | - |
| 0.7733 | 1511 | 0.3158 | - | - |
| 0.7738 | 1512 | 0.2389 | - | - |
| 0.7743 | 1513 | 0.161 | - | - |
| 0.7748 | 1514 | 0.1752 | - | - |
| 0.7753 | 1515 | 0.1277 | - | - |
| 0.7758 | 1516 | 0.1662 | - | - |
| 0.7764 | 1517 | 0.2383 | - | - |
| 0.7769 | 1518 | 0.1823 | - | - |
| 0.7774 | 1519 | 0.3215 | - | - |
| 0.7779 | 1520 | 0.2643 | - | - |
| 0.7784 | 1521 | 0.2251 | - | - |
| 0.7789 | 1522 | 0.258 | - | - |
| 0.7794 | 1523 | 0.1986 | - | - |
| 0.7799 | 1524 | 0.1937 | - | - |
| 0.7805 | 1525 | 0.2017 | - | - |
| 0.7810 | 1526 | 0.2152 | - | - |
| 0.7815 | 1527 | 0.205 | - | - |
| 0.7820 | 1528 | 0.2045 | - | - |
| 0.7825 | 1529 | 0.1897 | - | - |
| 0.7830 | 1530 | 0.1718 | - | - |
| 0.7835 | 1531 | 0.1158 | - | - |
| 0.7840 | 1532 | 0.1807 | - | - |
| 0.7845 | 1533 | 0.2381 | - | - |
| 0.7851 | 1534 | 0.3434 | - | - |
| 0.7856 | 1535 | 0.3852 | - | - |
| 0.7861 | 1536 | 0.289 | - | - |
| 0.7866 | 1537 | 0.3242 | - | - |
| 0.7871 | 1538 | 0.2734 | - | - |
| 0.7876 | 1539 | 0.2034 | - | - |
| 0.7881 | 1540 | 0.2312 | - | - |
| 0.7886 | 1541 | 0.2406 | - | - |
| 0.7892 | 1542 | 0.2152 | - | - |
| 0.7897 | 1543 | 0.1394 | - | - |
| 0.7902 | 1544 | 0.1243 | - | - |
| 0.7907 | 1545 | 0.2377 | - | - |
| 0.7912 | 1546 | 0.1362 | - | - |
| 0.7917 | 1547 | 0.1219 | - | - |
| 0.7922 | 1548 | 0.2065 | - | - |
| 0.7927 | 1549 | 0.2249 | - | - |
| 0.7932 | 1550 | 0.2644 | - | - |
| 0.7938 | 1551 | 0.2899 | - | - |
| 0.7943 | 1552 | 0.2978 | - | - |
| 0.7948 | 1553 | 0.2584 | - | - |
| 0.7953 | 1554 | 0.4284 | - | - |
| 0.7958 | 1555 | 0.3485 | - | - |
| 0.7963 | 1556 | 0.3921 | - | - |
| 0.7968 | 1557 | 0.3097 | - | - |
| 0.7973 | 1558 | 0.2372 | - | - |
| 0.7979 | 1559 | 0.2799 | - | - |
| 0.7984 | 1560 | 0.1728 | - | - |
| 0.7989 | 1561 | 0.1616 | - | - |
| 0.7994 | 1562 | 0.0986 | - | - |
| 0.7999 | 1563 | 0.1344 | - | - |
| 0.8004 | 1564 | 0.0714 | - | - |
| 0.8009 | 1565 | 0.1967 | - | - |
| 0.8014 | 1566 | 0.2853 | - | - |
| 0.8019 | 1567 | 0.3007 | - | - |
| 0.8025 | 1568 | 0.3036 | - | - |
| 0.8030 | 1569 | 0.315 | - | - |
| 0.8035 | 1570 | 0.2196 | - | - |
| 0.8040 | 1571 | 0.183 | - | - |
| 0.8045 | 1572 | 0.1717 | - | - |
| 0.8050 | 1573 | 0.2454 | - | - |
| 0.8055 | 1574 | 0.1936 | - | - |
| 0.8060 | 1575 | 0.2392 | - | - |
| 0.8066 | 1576 | 0.1998 | - | - |
| 0.8071 | 1577 | 0.2382 | - | - |
| 0.8076 | 1578 | 0.1752 | - | - |
| 0.8081 | 1579 | 0.2791 | - | - |
| 0.8086 | 1580 | 0.1962 | - | - |
| 0.8091 | 1581 | 0.2455 | - | - |
| 0.8096 | 1582 | 0.2088 | - | - |
| 0.8101 | 1583 | 0.2779 | - | - |
| 0.8106 | 1584 | 0.2799 | - | - |
| 0.8112 | 1585 | 0.2245 | - | - |
| 0.8117 | 1586 | 0.3577 | - | - |
| 0.8122 | 1587 | 0.3454 | - | - |
| 0.8127 | 1588 | 0.2465 | - | - |
| 0.8132 | 1589 | 0.219 | - | - |
| 0.8137 | 1590 | 0.2016 | - | - |
| 0.8142 | 1591 | 0.2132 | - | - |
| 0.8147 | 1592 | 0.293 | - | - |
| 0.8153 | 1593 | 0.3512 | - | - |
| 0.8158 | 1594 | 0.299 | - | - |
| 0.8163 | 1595 | 0.2666 | - | - |
| 0.8168 | 1596 | 0.2419 | - | - |
| 0.8173 | 1597 | 0.1873 | - | - |
| 0.8178 | 1598 | 0.1393 | - | - |
| 0.8183 | 1599 | 0.1834 | - | - |
| 0.8188 | 1600 | 0.2424 | 0.7951 | 0.9384 |
| 0.8193 | 1601 | 0.3308 | - | - |
| 0.8199 | 1602 | 0.389 | - | - |
| 0.8204 | 1603 | 0.372 | - | - |
| 0.8209 | 1604 | 0.4278 | - | - |
| 0.8214 | 1605 | 0.32 | - | - |
| 0.8219 | 1606 | 0.4131 | - | - |
| 0.8224 | 1607 | 0.4209 | - | - |
| 0.8229 | 1608 | 0.3434 | - | - |
| 0.8234 | 1609 | 0.3183 | - | - |
| 0.8240 | 1610 | 0.2844 | - | - |
| 0.8245 | 1611 | 0.3242 | - | - |
| 0.8250 | 1612 | 0.2182 | - | - |
| 0.8255 | 1613 | 0.1782 | - | - |
| 0.8260 | 1614 | 0.2351 | - | - |
| 0.8265 | 1615 | 0.164 | - | - |
| 0.8270 | 1616 | 0.2148 | - | - |
| 0.8275 | 1617 | 0.1739 | - | - |
| 0.8280 | 1618 | 0.2578 | - | - |
| 0.8286 | 1619 | 0.2316 | - | - |
| 0.8291 | 1620 | 0.1719 | - | - |
| 0.8296 | 1621 | 0.1277 | - | - |
| 0.8301 | 1622 | 0.16 | - | - |
| 0.8306 | 1623 | 0.1504 | - | - |
| 0.8311 | 1624 | 0.1563 | - | - |
| 0.8316 | 1625 | 0.1938 | - | - |
| 0.8321 | 1626 | 0.1918 | - | - |
| 0.8327 | 1627 | 0.2196 | - | - |
| 0.8332 | 1628 | 0.1967 | - | - |
| 0.8337 | 1629 | 0.2586 | - | - |
| 0.8342 | 1630 | 0.1991 | - | - |
| 0.8347 | 1631 | 0.2869 | - | - |
| 0.8352 | 1632 | 0.4497 | - | - |
| 0.8357 | 1633 | 0.3518 | - | - |
| 0.8362 | 1634 | 0.3113 | - | - |
| 0.8367 | 1635 | 0.2545 | - | - |
| 0.8373 | 1636 | 0.3275 | - | - |
| 0.8378 | 1637 | 0.2098 | - | - |
| 0.8383 | 1638 | 0.2076 | - | - |
| 0.8388 | 1639 | 0.218 | - | - |
| 0.8393 | 1640 | 0.2361 | - | - |
| 0.8398 | 1641 | 0.2324 | - | - |
| 0.8403 | 1642 | 0.2245 | - | - |
| 0.8408 | 1643 | 0.2767 | - | - |
| 0.8414 | 1644 | 0.2204 | - | - |
| 0.8419 | 1645 | 0.2158 | - | - |
| 0.8424 | 1646 | 0.1711 | - | - |
| 0.8429 | 1647 | 0.2333 | - | - |
| 0.8434 | 1648 | 0.2089 | - | - |
| 0.8439 | 1649 | 0.2114 | - | - |
| 0.8444 | 1650 | 0.2712 | - | - |
| 0.8449 | 1651 | 0.3705 | - | - |
| 0.8454 | 1652 | 0.3409 | - | - |
| 0.8460 | 1653 | 0.3343 | - | - |
| 0.8465 | 1654 | 0.2467 | - | - |
| 0.8470 | 1655 | 0.2415 | - | - |
| 0.8475 | 1656 | 0.2174 | - | - |
| 0.8480 | 1657 | 0.222 | - | - |
| 0.8485 | 1658 | 0.1879 | - | - |
| 0.8490 | 1659 | 0.2461 | - | - |
| 0.8495 | 1660 | 0.2413 | - | - |
| 0.8501 | 1661 | 0.1931 | - | - |
| 0.8506 | 1662 | 0.2744 | - | - |
| 0.8511 | 1663 | 0.3202 | - | - |
| 0.8516 | 1664 | 0.3382 | - | - |
| 0.8521 | 1665 | 0.2325 | - | - |
| 0.8526 | 1666 | 0.2124 | - | - |
| 0.8531 | 1667 | 0.2321 | - | - |
| 0.8536 | 1668 | 0.1406 | - | - |
| 0.8541 | 1669 | 0.1909 | - | - |
| 0.8547 | 1670 | 0.162 | - | - |
| 0.8552 | 1671 | 0.153 | - | - |
| 0.8557 | 1672 | 0.1104 | - | - |
| 0.8562 | 1673 | 0.1914 | - | - |
| 0.8567 | 1674 | 0.1988 | - | - |
| 0.8572 | 1675 | 0.2261 | - | - |
| 0.8577 | 1676 | 0.1765 | - | - |
| 0.8582 | 1677 | 0.1269 | - | - |
| 0.8588 | 1678 | 0.1017 | - | - |
| 0.8593 | 1679 | 0.2056 | - | - |
| 0.8598 | 1680 | 0.1059 | - | - |
| 0.8603 | 1681 | 0.1901 | - | - |
| 0.8608 | 1682 | 0.2596 | - | - |
| 0.8613 | 1683 | 0.3579 | - | - |
| 0.8618 | 1684 | 0.3703 | - | - |
| 0.8623 | 1685 | 0.3352 | - | - |
| 0.8628 | 1686 | 0.3461 | - | - |
| 0.8634 | 1687 | 0.391 | - | - |
| 0.8639 | 1688 | 0.2818 | - | - |
| 0.8644 | 1689 | 0.339 | - | - |
| 0.8649 | 1690 | 0.3048 | - | - |
| 0.8654 | 1691 | 0.3521 | - | - |
| 0.8659 | 1692 | 0.3335 | - | - |
| 0.8664 | 1693 | 0.2935 | - | - |
| 0.8669 | 1694 | 0.2318 | - | - |
| 0.8675 | 1695 | 0.3297 | - | - |
| 0.8680 | 1696 | 0.2218 | - | - |
| 0.8685 | 1697 | 0.2533 | - | - |
| 0.8690 | 1698 | 0.2637 | - | - |
| 0.8695 | 1699 | 0.2106 | - | - |
| 0.8700 | 1700 | 0.2082 | 0.7336 | 0.9439 |
| 0.8705 | 1701 | 0.2165 | - | - |
| 0.8710 | 1702 | 0.1938 | - | - |
| 0.8715 | 1703 | 0.2059 | - | - |
| 0.8721 | 1704 | 0.2639 | - | - |
| 0.8726 | 1705 | 0.2104 | - | - |
| 0.8731 | 1706 | 0.2204 | - | - |
| 0.8736 | 1707 | 0.3166 | - | - |
| 0.8741 | 1708 | 0.3073 | - | - |
| 0.8746 | 1709 | 0.2907 | - | - |
| 0.8751 | 1710 | 0.2448 | - | - |
| 0.8756 | 1711 | 0.2335 | - | - |
| 0.8762 | 1712 | 0.2861 | - | - |
| 0.8767 | 1713 | 0.3016 | - | - |
| 0.8772 | 1714 | 0.3313 | - | - |
| 0.8777 | 1715 | 0.4154 | - | - |
| 0.8782 | 1716 | 0.5309 | - | - |
| 0.8787 | 1717 | 0.4596 | - | - |
| 0.8792 | 1718 | 0.5752 | - | - |
| 0.8797 | 1719 | 0.4659 | - | - |
| 0.8802 | 1720 | 0.4636 | - | - |
| 0.8808 | 1721 | 0.4933 | - | - |
| 0.8813 | 1722 | 0.4949 | - | - |
| 0.8818 | 1723 | 0.4512 | - | - |
| 0.8823 | 1724 | 0.3858 | - | - |
| 0.8828 | 1725 | 0.3943 | - | - |
| 0.8833 | 1726 | 0.3733 | - | - |
| 0.8838 | 1727 | 0.3156 | - | - |
| 0.8843 | 1728 | 0.3272 | - | - |
| 0.8849 | 1729 | 0.2644 | - | - |
| 0.8854 | 1730 | 0.3572 | - | - |
| 0.8859 | 1731 | 0.2716 | - | - |
| 0.8864 | 1732 | 0.3054 | - | - |
| 0.8869 | 1733 | 0.3884 | - | - |
| 0.8874 | 1734 | 0.3512 | - | - |
| 0.8879 | 1735 | 0.2992 | - | - |
| 0.8884 | 1736 | 0.272 | - | - |
| 0.8889 | 1737 | 0.293 | - | - |
| 0.8895 | 1738 | 0.2506 | - | - |
| 0.8900 | 1739 | 0.3214 | - | - |
| 0.8905 | 1740 | 0.3026 | - | - |
| 0.8910 | 1741 | 0.3495 | - | - |
| 0.8915 | 1742 | 0.3697 | - | - |
| 0.8920 | 1743 | 0.2535 | - | - |
| 0.8925 | 1744 | 0.2417 | - | - |
| 0.8930 | 1745 | 0.2419 | - | - |
| 0.8936 | 1746 | 0.2106 | - | - |
| 0.8941 | 1747 | 0.209 | - | - |
| 0.8946 | 1748 | 0.2587 | - | - |
| 0.8951 | 1749 | 0.19 | - | - |
| 0.8956 | 1750 | 0.2744 | - | - |
| 0.8961 | 1751 | 0.3315 | - | - |
| 0.8966 | 1752 | 0.3192 | - | - |
| 0.8971 | 1753 | 0.44 | - | - |
| 0.8976 | 1754 | 0.3511 | - | - |
| 0.8982 | 1755 | 0.4535 | - | - |
| 0.8987 | 1756 | 0.4044 | - | - |
| 0.8992 | 1757 | 0.3398 | - | - |
| 0.8997 | 1758 | 0.3599 | - | - |
| 0.9002 | 1759 | 0.3552 | - | - |
| 0.9007 | 1760 | 0.3493 | - | - |
| 0.9012 | 1761 | 0.4215 | - | - |
| 0.9017 | 1762 | 0.3116 | - | - |
| 0.9023 | 1763 | 0.3451 | - | - |
| 0.9028 | 1764 | 0.2985 | - | - |
| 0.9033 | 1765 | 0.3452 | - | - |
| 0.9038 | 1766 | 0.2489 | - | - |
| 0.9043 | 1767 | 0.2266 | - | - |
| 0.9048 | 1768 | 0.2906 | - | - |
| 0.9053 | 1769 | 0.3229 | - | - |
| 0.9058 | 1770 | 0.3264 | - | - |
| 0.9063 | 1771 | 0.326 | - | - |
| 0.9069 | 1772 | 0.4848 | - | - |
| 0.9074 | 1773 | 0.347 | - | - |
| 0.9079 | 1774 | 0.2467 | - | - |
| 0.9084 | 1775 | 0.2548 | - | - |
| 0.9089 | 1776 | 0.4412 | - | - |
| 0.9094 | 1777 | 0.3089 | - | - |
| 0.9099 | 1778 | 0.4491 | - | - |
| 0.9104 | 1779 | 0.4089 | - | - |
| 0.9110 | 1780 | 0.396 | - | - |
| 0.9115 | 1781 | 0.4404 | - | - |
| 0.9120 | 1782 | 0.4197 | - | - |
| 0.9125 | 1783 | 0.2947 | - | - |
| 0.9130 | 1784 | 0.2952 | - | - |
| 0.9135 | 1785 | 0.2941 | - | - |
| 0.9140 | 1786 | 0.3605 | - | - |
| 0.9145 | 1787 | 0.3431 | - | - |
| 0.9150 | 1788 | 0.2934 | - | - |
| 0.9156 | 1789 | 0.3605 | - | - |
| 0.9161 | 1790 | 0.3521 | - | - |
| 0.9166 | 1791 | 0.3997 | - | - |
| 0.9171 | 1792 | 0.5006 | - | - |
| 0.9176 | 1793 | 0.354 | - | - |
| 0.9181 | 1794 | 0.388 | - | - |
| 0.9186 | 1795 | 0.3895 | - | - |
| 0.9191 | 1796 | 0.4333 | - | - |
| 0.9197 | 1797 | 0.4895 | - | - |
| 0.9202 | 1798 | 0.4691 | - | - |
| 0.9207 | 1799 | 0.4145 | - | - |
| 0.9212 | 1800 | 0.3753 | 0.6788 | 0.9502 |
| 0.9217 | 1801 | 0.4704 | - | - |
| 0.9222 | 1802 | 0.441 | - | - |
| 0.9227 | 1803 | 0.3925 | - | - |
| 0.9232 | 1804 | 0.3288 | - | - |
| 0.9237 | 1805 | 0.346 | - | - |
| 0.9243 | 1806 | 0.4326 | - | - |
| 0.9248 | 1807 | 0.4024 | - | - |
| 0.9253 | 1808 | 0.6031 | - | - |
| 0.9258 | 1809 | 0.6031 | - | - |
| 0.9263 | 1810 | 0.5265 | - | - |
| 0.9268 | 1811 | 0.428 | - | - |
| 0.9273 | 1812 | 0.4373 | - | - |
| 0.9278 | 1813 | 0.3541 | - | - |
| 0.9284 | 1814 | 0.3621 | - | - |
| 0.9289 | 1815 | 0.365 | - | - |
| 0.9294 | 1816 | 0.4398 | - | - |
| 0.9299 | 1817 | 0.398 | - | - |
| 0.9304 | 1818 | 0.4375 | - | - |
| 0.9309 | 1819 | 0.3815 | - | - |
| 0.9314 | 1820 | 0.4396 | - | - |
| 0.9319 | 1821 | 0.3871 | - | - |
| 0.9324 | 1822 | 0.4421 | - | - |
| 0.9330 | 1823 | 0.3979 | - | - |
| 0.9335 | 1824 | 0.3619 | - | - |
| 0.9340 | 1825 | 0.4688 | - | - |
| 0.9345 | 1826 | 0.3951 | - | - |
| 0.9350 | 1827 | 0.3807 | - | - |
| 0.9355 | 1828 | 0.3978 | - | - |
| 0.9360 | 1829 | 0.3519 | - | - |
| 0.9365 | 1830 | 0.4019 | - | - |
| 0.9371 | 1831 | 0.3853 | - | - |
| 0.9376 | 1832 | 0.4026 | - | - |
| 0.9381 | 1833 | 0.4212 | - | - |
| 0.9386 | 1834 | 0.5422 | - | - |
| 0.9391 | 1835 | 0.4808 | - | - |
| 0.9396 | 1836 | 0.5497 | - | - |
| 0.9401 | 1837 | 0.5487 | - | - |
| 0.9406 | 1838 | 0.4814 | - | - |
| 0.9411 | 1839 | 0.497 | - | - |
| 0.9417 | 1840 | 0.4491 | - | - |
| 0.9422 | 1841 | 0.4983 | - | - |
| 0.9427 | 1842 | 0.4855 | - | - |
| 0.9432 | 1843 | 0.4256 | - | - |
| 0.9437 | 1844 | 0.3845 | - | - |
| 0.9442 | 1845 | 0.3885 | - | - |
| 0.9447 | 1846 | 0.429 | - | - |
| 0.9452 | 1847 | 0.5845 | - | - |
| 0.9458 | 1848 | 0.4565 | - | - |
| 0.9463 | 1849 | 0.4371 | - | - |
| 0.9468 | 1850 | 0.5884 | - | - |
| 0.9473 | 1851 | 0.4054 | - | - |
| 0.9478 | 1852 | 0.5583 | - | - |
| 0.9483 | 1853 | 0.4478 | - | - |
| 0.9488 | 1854 | 0.4341 | - | - |
| 0.9493 | 1855 | 0.4308 | - | - |
| 0.9498 | 1856 | 0.503 | - | - |
| 0.9504 | 1857 | 0.4396 | - | - |
| 0.9509 | 1858 | 0.5434 | - | - |
| 0.9514 | 1859 | 0.4144 | - | - |
| 0.9519 | 1860 | 0.4432 | - | - |
| 0.9524 | 1861 | 0.3656 | - | - |
| 0.9529 | 1862 | 0.3972 | - | - |
| 0.9534 | 1863 | 0.4992 | - | - |
| 0.9539 | 1864 | 0.3215 | - | - |
| 0.9545 | 1865 | 0.3741 | - | - |
| 0.9550 | 1866 | 0.4548 | - | - |
| 0.9555 | 1867 | 0.5291 | - | - |
| 0.9560 | 1868 | 0.4826 | - | - |
| 0.9565 | 1869 | 0.5447 | - | - |
| 0.9570 | 1870 | 0.6471 | - | - |
| 0.9575 | 1871 | 0.5302 | - | - |
| 0.9580 | 1872 | 0.5803 | - | - |
| 0.9585 | 1873 | 0.6097 | - | - |
| 0.9591 | 1874 | 0.6494 | - | - |
| 0.9596 | 1875 | 0.5735 | - | - |
| 0.9601 | 1876 | 0.4434 | - | - |
| 0.9606 | 1877 | 0.4713 | - | - |
| 0.9611 | 1878 | 0.496 | - | - |
| 0.9616 | 1879 | 0.4067 | - | - |
| 0.9621 | 1880 | 0.5666 | - | - |
| 0.9626 | 1881 | 0.46 | - | - |
| 0.9632 | 1882 | 0.4719 | - | - |
| 0.9637 | 1883 | 0.5055 | - | - |
| 0.9642 | 1884 | 0.5013 | - | - |
| 0.9647 | 1885 | 0.5041 | - | - |
| 0.9652 | 1886 | 0.444 | - | - |
| 0.9657 | 1887 | 0.5036 | - | - |
| 0.9662 | 1888 | 0.4842 | - | - |
| 0.9667 | 1889 | 0.4947 | - | - |
| 0.9672 | 1890 | 0.5691 | - | - |
| 0.9678 | 1891 | 0.6534 | - | - |
| 0.9683 | 1892 | 0.6255 | - | - |
| 0.9688 | 1893 | 0.5947 | - | - |
| 0.9693 | 1894 | 0.5101 | - | - |
| 0.9698 | 1895 | 0.5423 | - | - |
| 0.9703 | 1896 | 0.4088 | - | - |
| 0.9708 | 1897 | 0.5801 | - | - |
| 0.9713 | 1898 | 0.5051 | - | - |
| 0.9719 | 1899 | 0.5947 | - | - |
| 0.9724 | 1900 | 0.5611 | 0.6374 | 0.9537 |
| 0.9729 | 1901 | 0.57 | - | - |
| 0.9734 | 1902 | 0.5558 | - | - |
| 0.9739 | 1903 | 0.5192 | - | - |
| 0.9744 | 1904 | 0.5319 | - | - |
| 0.9749 | 1905 | 0.5511 | - | - |
| 0.9754 | 1906 | 0.5118 | - | - |
| 0.9759 | 1907 | 0.5721 | - | - |
| 0.9765 | 1908 | 0.6543 | - | - |
| 0.9770 | 1909 | 0.6707 | - | - |
| 0.9775 | 1910 | 0.5997 | - | - |
| 0.9780 | 1911 | 0.5712 | - | - |
| 0.9785 | 1912 | 0.6574 | - | - |
| 0.9790 | 1913 | 0.5981 | - | - |
| 0.9795 | 1914 | 0.7499 | - | - |
| 0.9800 | 1915 | 0.738 | - | - |
| 0.9806 | 1916 | 0.6731 | - | - |
| 0.9811 | 1917 | 0.7481 | - | - |
| 0.9816 | 1918 | 0.7995 | - | - |
| 0.9821 | 1919 | 0.6295 | - | - |
| 0.9826 | 1920 | 0.6599 | - | - |
| 0.9831 | 1921 | 0.5386 | - | - |
| 0.9836 | 1922 | 0.6293 | - | - |
| 0.9841 | 1923 | 0.5511 | - | - |
| 0.9846 | 1924 | 0.5737 | - | - |
| 0.9852 | 1925 | 0.5261 | - | - |
| 0.9857 | 1926 | 0.5196 | - | - |
| 0.9862 | 1927 | 0.5886 | - | - |
| 0.9867 | 1928 | 0.6642 | - | - |
| 0.9872 | 1929 | 0.5713 | - | - |
| 0.9877 | 1930 | 0.5396 | - | - |
| 0.9882 | 1931 | 0.4805 | - | - |
| 0.9887 | 1932 | 0.5228 | - | - |
| 0.9893 | 1933 | 0.6495 | - | - |
| 0.9898 | 1934 | 0.5876 | - | - |
| 0.9903 | 1935 | 0.5542 | - | - |
| 0.9908 | 1936 | 0.6024 | - | - |
| 0.9913 | 1937 | 0.5677 | - | - |
| 0.9918 | 1938 | 0.6009 | - | - |
| 0.9923 | 1939 | 0.5893 | - | - |
| 0.9928 | 1940 | 0.461 | - | - |
| 0.9933 | 1941 | 0.4467 | - | - |
| 0.9939 | 1942 | 0.5059 | - | - |
| 0.9944 | 1943 | 0.6037 | - | - |
| 0.9949 | 1944 | 0.3525 | - | - |
| 0.9954 | 1945 | 0.5509 | - | - |
| 0.9959 | 1946 | 0.4277 | - | - |
| 0.9964 | 1947 | 0.344 | - | - |
| 0.9969 | 1948 | 0.4039 | - | - |
| 0.9974 | 1949 | 0.3924 | - | - |
| 0.9980 | 1950 | 0.3328 | - | - |
| 0.9985 | 1951 | 0.3756 | - | - |
| 0.9990 | 1952 | 0.3523 | - | - |
| 0.9995 | 1953 | 0.6408 | - | - |
| 1.0 | 1954 | 0.392 | - | 0.9587 |
</details>
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.3.1
- Transformers: 4.48.0.dev0
- PyTorch: 2.1.0+cu118
- Accelerate: 1.2.1
- Datasets: 3.2.0
- Tokenizers: 0.21.0
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MatryoshkaLoss
```bibtex
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
| null |
Non_BioNLP
|
# SentenceTransformer based on estrogen/ModernBERT-base-sbert-initialized
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [estrogen/ModernBERT-base-sbert-initialized](https://huggingface.co/estrogen/ModernBERT-base-sbert-initialized) on the [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) 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:** [estrogen/ModernBERT-base-sbert-initialized](https://huggingface.co/estrogen/ModernBERT-base-sbert-initialized) <!-- at revision d80f2f10df59065d673fa4d9ef890aae3cbf4b68 -->
- **Maximum Sequence Length:** 8192 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25)
- **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': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel
(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("estrogen/ModernBERT-base-marco")
# Run inference
sentences = [
'[unused0]what period do we live in',
'[unused1]Earth is currently in the Quaternary Period of the Cenozoic Era.',
'[unused1]Thereâ\x80\x99s a big difference in drive time depending on what part of Ewa Beach you live in â\x80\x94 the homes in Ocean Point (most southern part of Ewa) have a 20 minute longer drive than we do, even though we both live in the town of Ewa Beach.',
]
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
#### Triplet
* Dataset: `ms_marco`
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| **cosine_accuracy** | **0.9537** |
#### Triplet
* Dataset: `ms_marco`
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| **cosine_accuracy** | **0.9587** |
<!--
## 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
#### msmarco-bm25
* Dataset: [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) at [ce8a493](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25/tree/ce8a493a65af5e872c3c92f72a89e2e99e175f02)
* Size: 19,139,199 training samples
* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | query | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 10.51 tokens</li><li>max: 17 tokens</li></ul> | <ul><li>min: 45 tokens</li><li>mean: 86.37 tokens</li><li>max: 212 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 80.75 tokens</li><li>max: 222 tokens</li></ul> |
* Samples:
| query | positive | negative |
|:-------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>[unused0]what are the liberal arts?</code> | <code>[unused1]liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>[unused1]The New York State Education Department requires 60 Liberal Arts credits in a Bachelor of Science program and 90 Liberal Arts credits in a Bachelor of Arts program. In the list of course descriptions, courses which are liberal arts for all students are identified by (Liberal Arts) after the course number.</code> |
| <code>[unused0]what are the liberal arts?</code> | <code>[unused1]liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>[unused1]You can choose from an array of liberal arts majors. Most of these are offered in the liberal arts departments of colleges that belong to universities and at smaller colleges that are designated as liberal arts institutions.</code> |
| <code>[unused0]what are the liberal arts?</code> | <code>[unused1]liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>[unused1]Majors. You can choose from an array of liberal arts majors. Most of these are offered in the liberal arts departments of colleges that belong to universities and at smaller colleges that are designated as liberal arts institutions.</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
0.9,
0.81,
0.7290000000000001,
0.6561
],
"n_dims_per_step": -1
}
```
### Evaluation Dataset
#### msmarco-bm25
* Dataset: [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) at [ce8a493](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25/tree/ce8a493a65af5e872c3c92f72a89e2e99e175f02)
* Size: 19,139,199 evaluation samples
* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | query | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 5 tokens</li><li>mean: 10.42 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 80.07 tokens</li><li>max: 167 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 82.48 tokens</li><li>max: 213 tokens</li></ul> |
* Samples:
| query | positive | negative |
|:---------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>[unused0]different uses of corn</code> | <code>[unused1]Corn or maize oil is extracted from the germ of corn, and its main use is for cooking. It is also a key ingredient in margarine and other processed foods. Corn oil is also a feedstock used for biodiesel.From 2012 to 2014, the use of nonfood-grade (NFG) corn oil for biodiesel production has grown tremendously.ses of Corn Oil. Apart from serving as a less-than-ideal cooking oil, corn oil has several industrial uses, including as an addition to soap, salve, paint, ink, textiles, and insecticides. It also sometimes functions as a carrier for drug molecules in pharmaceutical products.</code> | <code>[unused1]Impact of Ethanol on Corn Prices. The U.S. produces 40 percent of the worldâs corn, [5] and ethanol production uses about 40 percent of U.S. corn production, [6] but roughly one-third of the value of the corn used in ethanol production returns to the feed market as DDGS.</code> |
| <code>[unused0]different uses of corn</code> | <code>[unused1]Corn or maize oil is extracted from the germ of corn, and its main use is for cooking. It is also a key ingredient in margarine and other processed foods. Corn oil is also a feedstock used for biodiesel.From 2012 to 2014, the use of nonfood-grade (NFG) corn oil for biodiesel production has grown tremendously.ses of Corn Oil. Apart from serving as a less-than-ideal cooking oil, corn oil has several industrial uses, including as an addition to soap, salve, paint, ink, textiles, and insecticides. It also sometimes functions as a carrier for drug molecules in pharmaceutical products.</code> | <code>[unused1]But ask different reptile keepers how long corn do corn snakes get and you won't get one standard answer. Like us humans, who may grow to little more than 5 feet tall to well over 6 feet in adults, different corn snakes attain different sizes.</code> |
| <code>[unused0]different uses of corn</code> | <code>[unused1]Corn or maize oil is extracted from the germ of corn, and its main use is for cooking. It is also a key ingredient in margarine and other processed foods. Corn oil is also a feedstock used for biodiesel.From 2012 to 2014, the use of nonfood-grade (NFG) corn oil for biodiesel production has grown tremendously.ses of Corn Oil. Apart from serving as a less-than-ideal cooking oil, corn oil has several industrial uses, including as an addition to soap, salve, paint, ink, textiles, and insecticides. It also sometimes functions as a carrier for drug molecules in pharmaceutical products.</code> | <code>[unused1]The corn system uses a large amount of natural resources. Even though it does not deliver as much food as comparable systems around the globe, the American corn system continues to use a large proportion of our countryâs natural resources.he corn system uses a large amount of natural resources. Even though it does not deliver as much food as comparable systems around the globe, the American corn system continues to use a large proportion of our countryâs natural resources.</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
0.9,
0.81,
0.7290000000000001,
0.6561
],
"n_dims_per_step": -1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 256
- `per_device_eval_batch_size`: 256
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `bf16`: True
- `prompts`: {'query': '[unused0]', 'positive': '[unused1]', 'negative': '[unused1]'}
- `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`: 256
- `per_device_eval_batch_size`: 256
- `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`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `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`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: {'query': '[unused0]', 'positive': '[unused1]', 'negative': '[unused1]'}
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | Validation Loss | ms_marco_cosine_accuracy |
|:------:|:----:|:-------------:|:---------------:|:------------------------:|
| 0 | 0 | - | - | 0.5833 |
| 0.0005 | 1 | 24.3765 | - | - |
| 0.0010 | 2 | 24.4903 | - | - |
| 0.0015 | 3 | 24.4595 | - | - |
| 0.0020 | 4 | 24.2913 | - | - |
| 0.0026 | 5 | 24.355 | - | - |
| 0.0031 | 6 | 24.2594 | - | - |
| 0.0036 | 7 | 24.1731 | - | - |
| 0.0041 | 8 | 24.135 | - | - |
| 0.0046 | 9 | 23.9455 | - | - |
| 0.0051 | 10 | 23.9964 | - | - |
| 0.0056 | 11 | 23.7097 | - | - |
| 0.0061 | 12 | 23.6735 | - | - |
| 0.0067 | 13 | 23.4437 | - | - |
| 0.0072 | 14 | 23.3786 | - | - |
| 0.0077 | 15 | 23.2145 | - | - |
| 0.0082 | 16 | 23.056 | - | - |
| 0.0087 | 17 | 22.9313 | - | - |
| 0.0092 | 18 | 22.6844 | - | - |
| 0.0097 | 19 | 22.5722 | - | - |
| 0.0102 | 20 | 22.4012 | - | - |
| 0.0107 | 21 | 22.1844 | - | - |
| 0.0113 | 22 | 21.9721 | - | - |
| 0.0118 | 23 | 21.7602 | - | - |
| 0.0123 | 24 | 21.4919 | - | - |
| 0.0128 | 25 | 21.2078 | - | - |
| 0.0133 | 26 | 20.9653 | - | - |
| 0.0138 | 27 | 20.6508 | - | - |
| 0.0143 | 28 | 20.2809 | - | - |
| 0.0148 | 29 | 19.8262 | - | - |
| 0.0154 | 30 | 19.3564 | - | - |
| 0.0159 | 31 | 18.9138 | - | - |
| 0.0164 | 32 | 18.2485 | - | - |
| 0.0169 | 33 | 17.63 | - | - |
| 0.0174 | 34 | 17.028 | - | - |
| 0.0179 | 35 | 16.2372 | - | - |
| 0.0184 | 36 | 15.3384 | - | - |
| 0.0189 | 37 | 14.3885 | - | - |
| 0.0194 | 38 | 13.4842 | - | - |
| 0.0200 | 39 | 12.6733 | - | - |
| 0.0205 | 40 | 11.8822 | - | - |
| 0.0210 | 41 | 11.2018 | - | - |
| 0.0215 | 42 | 10.2756 | - | - |
| 0.0220 | 43 | 9.2841 | - | - |
| 0.0225 | 44 | 8.8121 | - | - |
| 0.0230 | 45 | 7.973 | - | - |
| 0.0235 | 46 | 7.3955 | - | - |
| 0.0241 | 47 | 6.9961 | - | - |
| 0.0246 | 48 | 6.9545 | - | - |
| 0.0251 | 49 | 6.4636 | - | - |
| 0.0256 | 50 | 5.9562 | - | - |
| 0.0261 | 51 | 5.6653 | - | - |
| 0.0266 | 52 | 5.0228 | - | - |
| 0.0271 | 53 | 4.6302 | - | - |
| 0.0276 | 54 | 4.0535 | - | - |
| 0.0281 | 55 | 3.714 | - | - |
| 0.0287 | 56 | 3.2454 | - | - |
| 0.0292 | 57 | 2.9078 | - | - |
| 0.0297 | 58 | 2.6236 | - | - |
| 0.0302 | 59 | 2.4775 | - | - |
| 0.0307 | 60 | 2.1067 | - | - |
| 0.0312 | 61 | 2.1748 | - | - |
| 0.0317 | 62 | 1.9844 | - | - |
| 0.0322 | 63 | 1.7707 | - | - |
| 0.0328 | 64 | 1.6281 | - | - |
| 0.0333 | 65 | 1.9416 | - | - |
| 0.0338 | 66 | 1.5796 | - | - |
| 0.0343 | 67 | 1.5611 | - | - |
| 0.0348 | 68 | 1.5282 | - | - |
| 0.0353 | 69 | 1.6081 | - | - |
| 0.0358 | 70 | 1.4455 | - | - |
| 0.0363 | 71 | 1.3649 | - | - |
| 0.0368 | 72 | 1.0884 | - | - |
| 0.0374 | 73 | 0.9736 | - | - |
| 0.0379 | 74 | 0.8036 | - | - |
| 0.0384 | 75 | 0.8466 | - | - |
| 0.0389 | 76 | 0.8594 | - | - |
| 0.0394 | 77 | 0.8887 | - | - |
| 0.0399 | 78 | 0.8299 | - | - |
| 0.0404 | 79 | 0.8561 | - | - |
| 0.0409 | 80 | 1.0354 | - | - |
| 0.0415 | 81 | 1.1445 | - | - |
| 0.0420 | 82 | 1.1131 | - | - |
| 0.0425 | 83 | 1.114 | - | - |
| 0.0430 | 84 | 1.032 | - | - |
| 0.0435 | 85 | 0.8509 | - | - |
| 0.0440 | 86 | 0.7415 | - | - |
| 0.0445 | 87 | 1.1415 | - | - |
| 0.0450 | 88 | 1.1622 | - | - |
| 0.0455 | 89 | 1.2912 | - | - |
| 0.0461 | 90 | 1.0092 | - | - |
| 0.0466 | 91 | 0.7901 | - | - |
| 0.0471 | 92 | 0.7782 | - | - |
| 0.0476 | 93 | 0.6596 | - | - |
| 0.0481 | 94 | 0.5789 | - | - |
| 0.0486 | 95 | 0.8727 | - | - |
| 0.0491 | 96 | 0.6869 | - | - |
| 0.0496 | 97 | 0.7282 | - | - |
| 0.0502 | 98 | 0.6578 | - | - |
| 0.0507 | 99 | 0.6303 | - | - |
| 0.0512 | 100 | 0.4592 | 2.8360 | 0.8286 |
| 0.0517 | 101 | 0.6197 | - | - |
| 0.0522 | 102 | 0.737 | - | - |
| 0.0527 | 103 | 0.538 | - | - |
| 0.0532 | 104 | 0.435 | - | - |
| 0.0537 | 105 | 0.3955 | - | - |
| 0.0542 | 106 | 0.2621 | - | - |
| 0.0548 | 107 | 0.2742 | - | - |
| 0.0553 | 108 | 0.2802 | - | - |
| 0.0558 | 109 | 0.2681 | - | - |
| 0.0563 | 110 | 0.2489 | - | - |
| 0.0568 | 111 | 0.2985 | - | - |
| 0.0573 | 112 | 0.5011 | - | - |
| 0.0578 | 113 | 0.4239 | - | - |
| 0.0583 | 114 | 0.5619 | - | - |
| 0.0589 | 115 | 0.3498 | - | - |
| 0.0594 | 116 | 0.5731 | - | - |
| 0.0599 | 117 | 0.4297 | - | - |
| 0.0604 | 118 | 0.4703 | - | - |
| 0.0609 | 119 | 0.449 | - | - |
| 0.0614 | 120 | 0.4708 | - | - |
| 0.0619 | 121 | 0.4467 | - | - |
| 0.0624 | 122 | 0.4263 | - | - |
| 0.0629 | 123 | 0.3481 | - | - |
| 0.0635 | 124 | 0.2899 | - | - |
| 0.0640 | 125 | 0.4778 | - | - |
| 0.0645 | 126 | 0.7366 | - | - |
| 0.0650 | 127 | 0.5905 | - | - |
| 0.0655 | 128 | 0.5095 | - | - |
| 0.0660 | 129 | 0.3977 | - | - |
| 0.0665 | 130 | 0.4885 | - | - |
| 0.0670 | 131 | 0.4421 | - | - |
| 0.0676 | 132 | 0.2875 | - | - |
| 0.0681 | 133 | 0.4082 | - | - |
| 0.0686 | 134 | 0.424 | - | - |
| 0.0691 | 135 | 0.5184 | - | - |
| 0.0696 | 136 | 0.4225 | - | - |
| 0.0701 | 137 | 0.4612 | - | - |
| 0.0706 | 138 | 0.3632 | - | - |
| 0.0711 | 139 | 0.3489 | - | - |
| 0.0716 | 140 | 0.3888 | - | - |
| 0.0722 | 141 | 0.367 | - | - |
| 0.0727 | 142 | 0.3191 | - | - |
| 0.0732 | 143 | 0.4214 | - | - |
| 0.0737 | 144 | 0.3566 | - | - |
| 0.0742 | 145 | 0.2213 | - | - |
| 0.0747 | 146 | 0.2371 | - | - |
| 0.0752 | 147 | 0.2611 | - | - |
| 0.0757 | 148 | 0.1732 | - | - |
| 0.0763 | 149 | 0.223 | - | - |
| 0.0768 | 150 | 0.1442 | - | - |
| 0.0773 | 151 | 0.2201 | - | - |
| 0.0778 | 152 | 0.379 | - | - |
| 0.0783 | 153 | 0.3073 | - | - |
| 0.0788 | 154 | 0.2447 | - | - |
| 0.0793 | 155 | 0.3104 | - | - |
| 0.0798 | 156 | 0.3395 | - | - |
| 0.0803 | 157 | 0.2449 | - | - |
| 0.0809 | 158 | 0.226 | - | - |
| 0.0814 | 159 | 0.2058 | - | - |
| 0.0819 | 160 | 0.2084 | - | - |
| 0.0824 | 161 | 0.1993 | - | - |
| 0.0829 | 162 | 0.1208 | - | - |
| 0.0834 | 163 | 0.1055 | - | - |
| 0.0839 | 164 | 0.2083 | - | - |
| 0.0844 | 165 | 0.2167 | - | - |
| 0.0850 | 166 | 0.2169 | - | - |
| 0.0855 | 167 | 0.194 | - | - |
| 0.0860 | 168 | 0.2136 | - | - |
| 0.0865 | 169 | 0.2185 | - | - |
| 0.0870 | 170 | 0.2675 | - | - |
| 0.0875 | 171 | 0.2817 | - | - |
| 0.0880 | 172 | 0.3723 | - | - |
| 0.0885 | 173 | 0.5269 | - | - |
| 0.0890 | 174 | 0.2643 | - | - |
| 0.0896 | 175 | 0.2437 | - | - |
| 0.0901 | 176 | 0.1549 | - | - |
| 0.0906 | 177 | 0.1461 | - | - |
| 0.0911 | 178 | 0.1395 | - | - |
| 0.0916 | 179 | 0.1506 | - | - |
| 0.0921 | 180 | 0.2542 | - | - |
| 0.0926 | 181 | 0.2022 | - | - |
| 0.0931 | 182 | 0.1756 | - | - |
| 0.0937 | 183 | 0.2411 | - | - |
| 0.0942 | 184 | 0.3402 | - | - |
| 0.0947 | 185 | 0.3534 | - | - |
| 0.0952 | 186 | 0.2632 | - | - |
| 0.0957 | 187 | 0.3643 | - | - |
| 0.0962 | 188 | 0.4046 | - | - |
| 0.0967 | 189 | 0.2619 | - | - |
| 0.0972 | 190 | 0.1575 | - | - |
| 0.0977 | 191 | 0.12 | - | - |
| 0.0983 | 192 | 0.1157 | - | - |
| 0.0988 | 193 | 0.2453 | - | - |
| 0.0993 | 194 | 0.2406 | - | - |
| 0.0998 | 195 | 0.1784 | - | - |
| 0.1003 | 196 | 0.2226 | - | - |
| 0.1008 | 197 | 0.1963 | - | - |
| 0.1013 | 198 | 0.0964 | - | - |
| 0.1018 | 199 | 0.1413 | - | - |
| 0.1024 | 200 | 0.1467 | 1.6950 | 0.915 |
| 0.1029 | 201 | 0.322 | - | - |
| 0.1034 | 202 | 0.3444 | - | - |
| 0.1039 | 203 | 0.2968 | - | - |
| 0.1044 | 204 | 0.227 | - | - |
| 0.1049 | 205 | 0.3337 | - | - |
| 0.1054 | 206 | 0.2653 | - | - |
| 0.1059 | 207 | 0.251 | - | - |
| 0.1064 | 208 | 0.1667 | - | - |
| 0.1070 | 209 | 0.106 | - | - |
| 0.1075 | 210 | 0.1635 | - | - |
| 0.1080 | 211 | 0.1338 | - | - |
| 0.1085 | 212 | 0.1247 | - | - |
| 0.1090 | 213 | 0.12 | - | - |
| 0.1095 | 214 | 0.2283 | - | - |
| 0.1100 | 215 | 0.2245 | - | - |
| 0.1105 | 216 | 0.2821 | - | - |
| 0.1111 | 217 | 0.23 | - | - |
| 0.1116 | 218 | 0.3457 | - | - |
| 0.1121 | 219 | 0.4413 | - | - |
| 0.1126 | 220 | 0.3201 | - | - |
| 0.1131 | 221 | 0.3959 | - | - |
| 0.1136 | 222 | 0.323 | - | - |
| 0.1141 | 223 | 0.1532 | - | - |
| 0.1146 | 224 | 0.2216 | - | - |
| 0.1151 | 225 | 0.2449 | - | - |
| 0.1157 | 226 | 0.1398 | - | - |
| 0.1162 | 227 | 0.2693 | - | - |
| 0.1167 | 228 | 0.265 | - | - |
| 0.1172 | 229 | 0.2228 | - | - |
| 0.1177 | 230 | 0.2179 | - | - |
| 0.1182 | 231 | 0.1581 | - | - |
| 0.1187 | 232 | 0.2204 | - | - |
| 0.1192 | 233 | 0.1252 | - | - |
| 0.1198 | 234 | 0.2252 | - | - |
| 0.1203 | 235 | 0.2116 | - | - |
| 0.1208 | 236 | 0.1856 | - | - |
| 0.1213 | 237 | 0.1115 | - | - |
| 0.1218 | 238 | 0.0827 | - | - |
| 0.1223 | 239 | 0.2732 | - | - |
| 0.1228 | 240 | 0.2076 | - | - |
| 0.1233 | 241 | 0.1214 | - | - |
| 0.1238 | 242 | 0.1385 | - | - |
| 0.1244 | 243 | 0.3275 | - | - |
| 0.1249 | 244 | 0.307 | - | - |
| 0.1254 | 245 | 0.1637 | - | - |
| 0.1259 | 246 | 0.3614 | - | - |
| 0.1264 | 247 | 0.2571 | - | - |
| 0.1269 | 248 | 0.2131 | - | - |
| 0.1274 | 249 | 0.2254 | - | - |
| 0.1279 | 250 | 0.1677 | - | - |
| 0.1285 | 251 | 0.2697 | - | - |
| 0.1290 | 252 | 0.205 | - | - |
| 0.1295 | 253 | 0.1395 | - | - |
| 0.1300 | 254 | 0.1931 | - | - |
| 0.1305 | 255 | 0.2205 | - | - |
| 0.1310 | 256 | 0.1271 | - | - |
| 0.1315 | 257 | 0.1029 | - | - |
| 0.1320 | 258 | 0.0632 | - | - |
| 0.1325 | 259 | 0.0594 | - | - |
| 0.1331 | 260 | 0.2551 | - | - |
| 0.1336 | 261 | 0.3609 | - | - |
| 0.1341 | 262 | 0.3379 | - | - |
| 0.1346 | 263 | 0.2832 | - | - |
| 0.1351 | 264 | 0.2797 | - | - |
| 0.1356 | 265 | 0.2167 | - | - |
| 0.1361 | 266 | 0.2362 | - | - |
| 0.1366 | 267 | 0.1922 | - | - |
| 0.1372 | 268 | 0.2488 | - | - |
| 0.1377 | 269 | 0.135 | - | - |
| 0.1382 | 270 | 0.1064 | - | - |
| 0.1387 | 271 | 0.1245 | - | - |
| 0.1392 | 272 | 0.1605 | - | - |
| 0.1397 | 273 | 0.1739 | - | - |
| 0.1402 | 274 | 0.1816 | - | - |
| 0.1407 | 275 | 0.1802 | - | - |
| 0.1412 | 276 | 0.1227 | - | - |
| 0.1418 | 277 | 0.1445 | - | - |
| 0.1423 | 278 | 0.1052 | - | - |
| 0.1428 | 279 | 0.0774 | - | - |
| 0.1433 | 280 | 0.0778 | - | - |
| 0.1438 | 281 | 0.1116 | - | - |
| 0.1443 | 282 | 0.3067 | - | - |
| 0.1448 | 283 | 0.3255 | - | - |
| 0.1453 | 284 | 0.2831 | - | - |
| 0.1459 | 285 | 0.2623 | - | - |
| 0.1464 | 286 | 0.2323 | - | - |
| 0.1469 | 287 | 0.2093 | - | - |
| 0.1474 | 288 | 0.1023 | - | - |
| 0.1479 | 289 | 0.1909 | - | - |
| 0.1484 | 290 | 0.1476 | - | - |
| 0.1489 | 291 | 0.1069 | - | - |
| 0.1494 | 292 | 0.2284 | - | - |
| 0.1499 | 293 | 0.1341 | - | - |
| 0.1505 | 294 | 0.0924 | - | - |
| 0.1510 | 295 | 0.1264 | - | - |
| 0.1515 | 296 | 0.0836 | - | - |
| 0.1520 | 297 | 0.163 | - | - |
| 0.1525 | 298 | 0.0946 | - | - |
| 0.1530 | 299 | 0.0784 | - | - |
| 0.1535 | 300 | 0.2065 | 1.3301 | 0.9233 |
| 0.1540 | 301 | 0.133 | - | - |
| 0.1546 | 302 | 0.1105 | - | - |
| 0.1551 | 303 | 0.1045 | - | - |
| 0.1556 | 304 | 0.136 | - | - |
| 0.1561 | 305 | 0.0834 | - | - |
| 0.1566 | 306 | 0.0856 | - | - |
| 0.1571 | 307 | 0.1069 | - | - |
| 0.1576 | 308 | 0.2031 | - | - |
| 0.1581 | 309 | 0.1742 | - | - |
| 0.1586 | 310 | 0.1186 | - | - |
| 0.1592 | 311 | 0.0532 | - | - |
| 0.1597 | 312 | 0.0982 | - | - |
| 0.1602 | 313 | 0.1013 | - | - |
| 0.1607 | 314 | 0.1019 | - | - |
| 0.1612 | 315 | 0.1899 | - | - |
| 0.1617 | 316 | 0.133 | - | - |
| 0.1622 | 317 | 0.242 | - | - |
| 0.1627 | 318 | 0.3231 | - | - |
| 0.1633 | 319 | 0.3294 | - | - |
| 0.1638 | 320 | 0.3034 | - | - |
| 0.1643 | 321 | 0.263 | - | - |
| 0.1648 | 322 | 0.2273 | - | - |
| 0.1653 | 323 | 0.1982 | - | - |
| 0.1658 | 324 | 0.143 | - | - |
| 0.1663 | 325 | 0.317 | - | - |
| 0.1668 | 326 | 0.3259 | - | - |
| 0.1673 | 327 | 0.2158 | - | - |
| 0.1679 | 328 | 0.231 | - | - |
| 0.1684 | 329 | 0.1733 | - | - |
| 0.1689 | 330 | 0.3191 | - | - |
| 0.1694 | 331 | 0.187 | - | - |
| 0.1699 | 332 | 0.169 | - | - |
| 0.1704 | 333 | 0.2259 | - | - |
| 0.1709 | 334 | 0.2909 | - | - |
| 0.1714 | 335 | 0.3047 | - | - |
| 0.1720 | 336 | 0.2925 | - | - |
| 0.1725 | 337 | 0.2579 | - | - |
| 0.1730 | 338 | 0.2226 | - | - |
| 0.1735 | 339 | 0.3724 | - | - |
| 0.1740 | 340 | 0.2634 | - | - |
| 0.1745 | 341 | 0.1856 | - | - |
| 0.1750 | 342 | 0.1102 | - | - |
| 0.1755 | 343 | 0.1205 | - | - |
| 0.1760 | 344 | 0.1154 | - | - |
| 0.1766 | 345 | 0.1558 | - | - |
| 0.1771 | 346 | 0.0789 | - | - |
| 0.1776 | 347 | 0.1674 | - | - |
| 0.1781 | 348 | 0.1188 | - | - |
| 0.1786 | 349 | 0.163 | - | - |
| 0.1791 | 350 | 0.197 | - | - |
| 0.1796 | 351 | 0.1017 | - | - |
| 0.1801 | 352 | 0.0914 | - | - |
| 0.1807 | 353 | 0.1576 | - | - |
| 0.1812 | 354 | 0.1809 | - | - |
| 0.1817 | 355 | 0.1624 | - | - |
| 0.1822 | 356 | 0.1636 | - | - |
| 0.1827 | 357 | 0.1473 | - | - |
| 0.1832 | 358 | 0.1839 | - | - |
| 0.1837 | 359 | 0.1494 | - | - |
| 0.1842 | 360 | 0.1326 | - | - |
| 0.1847 | 361 | 0.1545 | - | - |
| 0.1853 | 362 | 0.1588 | - | - |
| 0.1858 | 363 | 0.0975 | - | - |
| 0.1863 | 364 | 0.1363 | - | - |
| 0.1868 | 365 | 0.1248 | - | - |
| 0.1873 | 366 | 0.1328 | - | - |
| 0.1878 | 367 | 0.1329 | - | - |
| 0.1883 | 368 | 0.0755 | - | - |
| 0.1888 | 369 | 0.2535 | - | - |
| 0.1894 | 370 | 0.2484 | - | - |
| 0.1899 | 371 | 0.2538 | - | - |
| 0.1904 | 372 | 0.1597 | - | - |
| 0.1909 | 373 | 0.188 | - | - |
| 0.1914 | 374 | 0.0946 | - | - |
| 0.1919 | 375 | 0.0899 | - | - |
| 0.1924 | 376 | 0.0814 | - | - |
| 0.1929 | 377 | 0.1024 | - | - |
| 0.1934 | 378 | 0.2536 | - | - |
| 0.1940 | 379 | 0.1975 | - | - |
| 0.1945 | 380 | 0.1364 | - | - |
| 0.1950 | 381 | 0.1144 | - | - |
| 0.1955 | 382 | 0.1584 | - | - |
| 0.1960 | 383 | 0.2206 | - | - |
| 0.1965 | 384 | 0.2278 | - | - |
| 0.1970 | 385 | 0.3123 | - | - |
| 0.1975 | 386 | 0.1633 | - | - |
| 0.1981 | 387 | 0.1344 | - | - |
| 0.1986 | 388 | 0.2176 | - | - |
| 0.1991 | 389 | 0.132 | - | - |
| 0.1996 | 390 | 0.1022 | - | - |
| 0.2001 | 391 | 0.1819 | - | - |
| 0.2006 | 392 | 0.1488 | - | - |
| 0.2011 | 393 | 0.0793 | - | - |
| 0.2016 | 394 | 0.1097 | - | - |
| 0.2021 | 395 | 0.0742 | - | - |
| 0.2027 | 396 | 0.1336 | - | - |
| 0.2032 | 397 | 0.102 | - | - |
| 0.2037 | 398 | 0.0837 | - | - |
| 0.2042 | 399 | 0.0948 | - | - |
| 0.2047 | 400 | 0.0911 | 1.2098 | 0.9202 |
| 0.2052 | 401 | 0.1793 | - | - |
| 0.2057 | 402 | 0.1949 | - | - |
| 0.2062 | 403 | 0.1297 | - | - |
| 0.2068 | 404 | 0.0983 | - | - |
| 0.2073 | 405 | 0.1735 | - | - |
| 0.2078 | 406 | 0.1271 | - | - |
| 0.2083 | 407 | 0.1855 | - | - |
| 0.2088 | 408 | 0.1755 | - | - |
| 0.2093 | 409 | 0.1591 | - | - |
| 0.2098 | 410 | 0.2311 | - | - |
| 0.2103 | 411 | 0.2291 | - | - |
| 0.2108 | 412 | 0.0812 | - | - |
| 0.2114 | 413 | 0.0893 | - | - |
| 0.2119 | 414 | 0.1559 | - | - |
| 0.2124 | 415 | 0.2663 | - | - |
| 0.2129 | 416 | 0.257 | - | - |
| 0.2134 | 417 | 0.1864 | - | - |
| 0.2139 | 418 | 0.1735 | - | - |
| 0.2144 | 419 | 0.1028 | - | - |
| 0.2149 | 420 | 0.1494 | - | - |
| 0.2155 | 421 | 0.1528 | - | - |
| 0.2160 | 422 | 0.3732 | - | - |
| 0.2165 | 423 | 0.2663 | - | - |
| 0.2170 | 424 | 0.2487 | - | - |
| 0.2175 | 425 | 0.28 | - | - |
| 0.2180 | 426 | 0.1857 | - | - |
| 0.2185 | 427 | 0.1069 | - | - |
| 0.2190 | 428 | 0.138 | - | - |
| 0.2195 | 429 | 0.106 | - | - |
| 0.2201 | 430 | 0.1366 | - | - |
| 0.2206 | 431 | 0.1444 | - | - |
| 0.2211 | 432 | 0.0695 | - | - |
| 0.2216 | 433 | 0.0652 | - | - |
| 0.2221 | 434 | 0.0771 | - | - |
| 0.2226 | 435 | 0.1724 | - | - |
| 0.2231 | 436 | 0.1494 | - | - |
| 0.2236 | 437 | 0.1837 | - | - |
| 0.2242 | 438 | 0.1885 | - | - |
| 0.2247 | 439 | 0.3021 | - | - |
| 0.2252 | 440 | 0.2301 | - | - |
| 0.2257 | 441 | 0.1372 | - | - |
| 0.2262 | 442 | 0.1413 | - | - |
| 0.2267 | 443 | 0.1489 | - | - |
| 0.2272 | 444 | 0.2566 | - | - |
| 0.2277 | 445 | 0.1504 | - | - |
| 0.2282 | 446 | 0.1567 | - | - |
| 0.2288 | 447 | 0.2548 | - | - |
| 0.2293 | 448 | 0.2375 | - | - |
| 0.2298 | 449 | 0.2346 | - | - |
| 0.2303 | 450 | 0.2818 | - | - |
| 0.2308 | 451 | 0.1814 | - | - |
| 0.2313 | 452 | 0.1792 | - | - |
| 0.2318 | 453 | 0.1701 | - | - |
| 0.2323 | 454 | 0.158 | - | - |
| 0.2329 | 455 | 0.0782 | - | - |
| 0.2334 | 456 | 0.0762 | - | - |
| 0.2339 | 457 | 0.1317 | - | - |
| 0.2344 | 458 | 0.1143 | - | - |
| 0.2349 | 459 | 0.0982 | - | - |
| 0.2354 | 460 | 0.1041 | - | - |
| 0.2359 | 461 | 0.0873 | - | - |
| 0.2364 | 462 | 0.1718 | - | - |
| 0.2369 | 463 | 0.2022 | - | - |
| 0.2375 | 464 | 0.4147 | - | - |
| 0.2380 | 465 | 0.3045 | - | - |
| 0.2385 | 466 | 0.2021 | - | - |
| 0.2390 | 467 | 0.2004 | - | - |
| 0.2395 | 468 | 0.1474 | - | - |
| 0.2400 | 469 | 0.2358 | - | - |
| 0.2405 | 470 | 0.2385 | - | - |
| 0.2410 | 471 | 0.2669 | - | - |
| 0.2416 | 472 | 0.1408 | - | - |
| 0.2421 | 473 | 0.1248 | - | - |
| 0.2426 | 474 | 0.0805 | - | - |
| 0.2431 | 475 | 0.0821 | - | - |
| 0.2436 | 476 | 0.0498 | - | - |
| 0.2441 | 477 | 0.0886 | - | - |
| 0.2446 | 478 | 0.066 | - | - |
| 0.2451 | 479 | 0.1148 | - | - |
| 0.2456 | 480 | 0.1282 | - | - |
| 0.2462 | 481 | 0.1113 | - | - |
| 0.2467 | 482 | 0.0992 | - | - |
| 0.2472 | 483 | 0.2702 | - | - |
| 0.2477 | 484 | 0.2504 | - | - |
| 0.2482 | 485 | 0.3917 | - | - |
| 0.2487 | 486 | 0.1506 | - | - |
| 0.2492 | 487 | 0.1238 | - | - |
| 0.2497 | 488 | 0.1337 | - | - |
| 0.2503 | 489 | 0.2255 | - | - |
| 0.2508 | 490 | 0.1447 | - | - |
| 0.2513 | 491 | 0.2208 | - | - |
| 0.2518 | 492 | 0.268 | - | - |
| 0.2523 | 493 | 0.174 | - | - |
| 0.2528 | 494 | 0.2124 | - | - |
| 0.2533 | 495 | 0.1783 | - | - |
| 0.2538 | 496 | 0.1945 | - | - |
| 0.2544 | 497 | 0.1642 | - | - |
| 0.2549 | 498 | 0.2724 | - | - |
| 0.2554 | 499 | 0.1823 | - | - |
| 0.2559 | 500 | 0.18 | 1.1056 | 0.913 |
| 0.2564 | 501 | 0.1871 | - | - |
| 0.2569 | 502 | 0.1611 | - | - |
| 0.2574 | 503 | 0.1915 | - | - |
| 0.2579 | 504 | 0.1281 | - | - |
| 0.2584 | 505 | 0.1793 | - | - |
| 0.2590 | 506 | 0.0993 | - | - |
| 0.2595 | 507 | 0.1785 | - | - |
| 0.2600 | 508 | 0.1308 | - | - |
| 0.2605 | 509 | 0.1142 | - | - |
| 0.2610 | 510 | 0.0932 | - | - |
| 0.2615 | 511 | 0.1643 | - | - |
| 0.2620 | 512 | 0.175 | - | - |
| 0.2625 | 513 | 0.2568 | - | - |
| 0.2631 | 514 | 0.1534 | - | - |
| 0.2636 | 515 | 0.105 | - | - |
| 0.2641 | 516 | 0.0964 | - | - |
| 0.2646 | 517 | 0.062 | - | - |
| 0.2651 | 518 | 0.123 | - | - |
| 0.2656 | 519 | 0.1892 | - | - |
| 0.2661 | 520 | 0.1282 | - | - |
| 0.2666 | 521 | 0.1243 | - | - |
| 0.2671 | 522 | 0.1051 | - | - |
| 0.2677 | 523 | 0.1257 | - | - |
| 0.2682 | 524 | 0.2121 | - | - |
| 0.2687 | 525 | 0.2357 | - | - |
| 0.2692 | 526 | 0.1355 | - | - |
| 0.2697 | 527 | 0.0861 | - | - |
| 0.2702 | 528 | 0.0632 | - | - |
| 0.2707 | 529 | 0.0652 | - | - |
| 0.2712 | 530 | 0.1102 | - | - |
| 0.2718 | 531 | 0.3408 | - | - |
| 0.2723 | 532 | 0.3124 | - | - |
| 0.2728 | 533 | 0.1656 | - | - |
| 0.2733 | 534 | 0.2136 | - | - |
| 0.2738 | 535 | 0.1601 | - | - |
| 0.2743 | 536 | 0.3403 | - | - |
| 0.2748 | 537 | 0.3067 | - | - |
| 0.2753 | 538 | 0.2028 | - | - |
| 0.2758 | 539 | 0.1166 | - | - |
| 0.2764 | 540 | 0.1655 | - | - |
| 0.2769 | 541 | 0.1911 | - | - |
| 0.2774 | 542 | 0.2947 | - | - |
| 0.2779 | 543 | 0.259 | - | - |
| 0.2784 | 544 | 0.1485 | - | - |
| 0.2789 | 545 | 0.2414 | - | - |
| 0.2794 | 546 | 0.1195 | - | - |
| 0.2799 | 547 | 0.128 | - | - |
| 0.2805 | 548 | 0.1484 | - | - |
| 0.2810 | 549 | 0.1338 | - | - |
| 0.2815 | 550 | 0.1516 | - | - |
| 0.2820 | 551 | 0.1856 | - | - |
| 0.2825 | 552 | 0.2027 | - | - |
| 0.2830 | 553 | 0.1686 | - | - |
| 0.2835 | 554 | 0.1355 | - | - |
| 0.2840 | 555 | 0.1367 | - | - |
| 0.2845 | 556 | 0.0977 | - | - |
| 0.2851 | 557 | 0.0916 | - | - |
| 0.2856 | 558 | 0.1016 | - | - |
| 0.2861 | 559 | 0.105 | - | - |
| 0.2866 | 560 | 0.0681 | - | - |
| 0.2871 | 561 | 0.1317 | - | - |
| 0.2876 | 562 | 0.0983 | - | - |
| 0.2881 | 563 | 0.1189 | - | - |
| 0.2886 | 564 | 0.1822 | - | - |
| 0.2892 | 565 | 0.1149 | - | - |
| 0.2897 | 566 | 0.0516 | - | - |
| 0.2902 | 567 | 0.0912 | - | - |
| 0.2907 | 568 | 0.1609 | - | - |
| 0.2912 | 569 | 0.1439 | - | - |
| 0.2917 | 570 | 0.1051 | - | - |
| 0.2922 | 571 | 0.1287 | - | - |
| 0.2927 | 572 | 0.1966 | - | - |
| 0.2932 | 573 | 0.1681 | - | - |
| 0.2938 | 574 | 0.1248 | - | - |
| 0.2943 | 575 | 0.204 | - | - |
| 0.2948 | 576 | 0.2069 | - | - |
| 0.2953 | 577 | 0.1346 | - | - |
| 0.2958 | 578 | 0.144 | - | - |
| 0.2963 | 579 | 0.1006 | - | - |
| 0.2968 | 580 | 0.0653 | - | - |
| 0.2973 | 581 | 0.0606 | - | - |
| 0.2979 | 582 | 0.0959 | - | - |
| 0.2984 | 583 | 0.2208 | - | - |
| 0.2989 | 584 | 0.2492 | - | - |
| 0.2994 | 585 | 0.224 | - | - |
| 0.2999 | 586 | 0.2556 | - | - |
| 0.3004 | 587 | 0.1741 | - | - |
| 0.3009 | 588 | 0.1486 | - | - |
| 0.3014 | 589 | 0.2298 | - | - |
| 0.3019 | 590 | 0.1557 | - | - |
| 0.3025 | 591 | 0.2844 | - | - |
| 0.3030 | 592 | 0.235 | - | - |
| 0.3035 | 593 | 0.1801 | - | - |
| 0.3040 | 594 | 0.1602 | - | - |
| 0.3045 | 595 | 0.131 | - | - |
| 0.3050 | 596 | 0.1771 | - | - |
| 0.3055 | 597 | 0.0996 | - | - |
| 0.3060 | 598 | 0.0809 | - | - |
| 0.3066 | 599 | 0.1244 | - | - |
| 0.3071 | 600 | 0.1467 | 1.1270 | 0.9164 |
| 0.3076 | 601 | 0.1539 | - | - |
| 0.3081 | 602 | 0.1627 | - | - |
| 0.3086 | 603 | 0.094 | - | - |
| 0.3091 | 604 | 0.0673 | - | - |
| 0.3096 | 605 | 0.0628 | - | - |
| 0.3101 | 606 | 0.0661 | - | - |
| 0.3106 | 607 | 0.059 | - | - |
| 0.3112 | 608 | 0.0386 | - | - |
| 0.3117 | 609 | 0.0659 | - | - |
| 0.3122 | 610 | 0.1256 | - | - |
| 0.3127 | 611 | 0.2102 | - | - |
| 0.3132 | 612 | 0.2038 | - | - |
| 0.3137 | 613 | 0.2993 | - | - |
| 0.3142 | 614 | 0.2537 | - | - |
| 0.3147 | 615 | 0.2742 | - | - |
| 0.3153 | 616 | 0.2262 | - | - |
| 0.3158 | 617 | 0.1024 | - | - |
| 0.3163 | 618 | 0.1367 | - | - |
| 0.3168 | 619 | 0.2258 | - | - |
| 0.3173 | 620 | 0.1861 | - | - |
| 0.3178 | 621 | 0.1482 | - | - |
| 0.3183 | 622 | 0.1205 | - | - |
| 0.3188 | 623 | 0.2656 | - | - |
| 0.3193 | 624 | 0.3613 | - | - |
| 0.3199 | 625 | 0.1914 | - | - |
| 0.3204 | 626 | 0.2363 | - | - |
| 0.3209 | 627 | 0.1523 | - | - |
| 0.3214 | 628 | 0.1676 | - | - |
| 0.3219 | 629 | 0.1536 | - | - |
| 0.3224 | 630 | 0.1544 | - | - |
| 0.3229 | 631 | 0.1694 | - | - |
| 0.3234 | 632 | 0.133 | - | - |
| 0.3240 | 633 | 0.163 | - | - |
| 0.3245 | 634 | 0.2706 | - | - |
| 0.3250 | 635 | 0.3171 | - | - |
| 0.3255 | 636 | 0.2479 | - | - |
| 0.3260 | 637 | 0.1399 | - | - |
| 0.3265 | 638 | 0.1158 | - | - |
| 0.3270 | 639 | 0.17 | - | - |
| 0.3275 | 640 | 0.1492 | - | - |
| 0.3280 | 641 | 0.2517 | - | - |
| 0.3286 | 642 | 0.1551 | - | - |
| 0.3291 | 643 | 0.083 | - | - |
| 0.3296 | 644 | 0.0845 | - | - |
| 0.3301 | 645 | 0.321 | - | - |
| 0.3306 | 646 | 0.2162 | - | - |
| 0.3311 | 647 | 0.1856 | - | - |
| 0.3316 | 648 | 0.2404 | - | - |
| 0.3321 | 649 | 0.2655 | - | - |
| 0.3327 | 650 | 0.1434 | - | - |
| 0.3332 | 651 | 0.0856 | - | - |
| 0.3337 | 652 | 0.1041 | - | - |
| 0.3342 | 653 | 0.2421 | - | - |
| 0.3347 | 654 | 0.2219 | - | - |
| 0.3352 | 655 | 0.1435 | - | - |
| 0.3357 | 656 | 0.1785 | - | - |
| 0.3362 | 657 | 0.1608 | - | - |
| 0.3367 | 658 | 0.1657 | - | - |
| 0.3373 | 659 | 0.1231 | - | - |
| 0.3378 | 660 | 0.1121 | - | - |
| 0.3383 | 661 | 0.1749 | - | - |
| 0.3388 | 662 | 0.166 | - | - |
| 0.3393 | 663 | 0.1778 | - | - |
| 0.3398 | 664 | 0.1772 | - | - |
| 0.3403 | 665 | 0.1969 | - | - |
| 0.3408 | 666 | 0.249 | - | - |
| 0.3414 | 667 | 0.1366 | - | - |
| 0.3419 | 668 | 0.0856 | - | - |
| 0.3424 | 669 | 0.212 | - | - |
| 0.3429 | 670 | 0.1776 | - | - |
| 0.3434 | 671 | 0.1713 | - | - |
| 0.3439 | 672 | 0.1108 | - | - |
| 0.3444 | 673 | 0.2103 | - | - |
| 0.3449 | 674 | 0.2127 | - | - |
| 0.3454 | 675 | 0.1979 | - | - |
| 0.3460 | 676 | 0.2033 | - | - |
| 0.3465 | 677 | 0.2822 | - | - |
| 0.3470 | 678 | 0.2751 | - | - |
| 0.3475 | 679 | 0.205 | - | - |
| 0.3480 | 680 | 0.1969 | - | - |
| 0.3485 | 681 | 0.3404 | - | - |
| 0.3490 | 682 | 0.2905 | - | - |
| 0.3495 | 683 | 0.2031 | - | - |
| 0.3501 | 684 | 0.1358 | - | - |
| 0.3506 | 685 | 0.1563 | - | - |
| 0.3511 | 686 | 0.1294 | - | - |
| 0.3516 | 687 | 0.1183 | - | - |
| 0.3521 | 688 | 0.0738 | - | - |
| 0.3526 | 689 | 0.088 | - | - |
| 0.3531 | 690 | 0.1325 | - | - |
| 0.3536 | 691 | 0.2572 | - | - |
| 0.3541 | 692 | 0.2373 | - | - |
| 0.3547 | 693 | 0.2355 | - | - |
| 0.3552 | 694 | 0.205 | - | - |
| 0.3557 | 695 | 0.1163 | - | - |
| 0.3562 | 696 | 0.1946 | - | - |
| 0.3567 | 697 | 0.1677 | - | - |
| 0.3572 | 698 | 0.1721 | - | - |
| 0.3577 | 699 | 0.2013 | - | - |
| 0.3582 | 700 | 0.1442 | 0.8623 | 0.9306 |
| 0.3588 | 701 | 0.1081 | - | - |
| 0.3593 | 702 | 0.0767 | - | - |
| 0.3598 | 703 | 0.1696 | - | - |
| 0.3603 | 704 | 0.1315 | - | - |
| 0.3608 | 705 | 0.0592 | - | - |
| 0.3613 | 706 | 0.1208 | - | - |
| 0.3618 | 707 | 0.2346 | - | - |
| 0.3623 | 708 | 0.192 | - | - |
| 0.3628 | 709 | 0.1038 | - | - |
| 0.3634 | 710 | 0.1107 | - | - |
| 0.3639 | 711 | 0.0839 | - | - |
| 0.3644 | 712 | 0.1804 | - | - |
| 0.3649 | 713 | 0.1581 | - | - |
| 0.3654 | 714 | 0.1469 | - | - |
| 0.3659 | 715 | 0.1384 | - | - |
| 0.3664 | 716 | 0.091 | - | - |
| 0.3669 | 717 | 0.0733 | - | - |
| 0.3675 | 718 | 0.2287 | - | - |
| 0.3680 | 719 | 0.1345 | - | - |
| 0.3685 | 720 | 0.3101 | - | - |
| 0.3690 | 721 | 0.2625 | - | - |
| 0.3695 | 722 | 0.259 | - | - |
| 0.3700 | 723 | 0.1677 | - | - |
| 0.3705 | 724 | 0.1824 | - | - |
| 0.3710 | 725 | 0.2012 | - | - |
| 0.3715 | 726 | 0.0987 | - | - |
| 0.3721 | 727 | 0.0913 | - | - |
| 0.3726 | 728 | 0.112 | - | - |
| 0.3731 | 729 | 0.077 | - | - |
| 0.3736 | 730 | 0.0999 | - | - |
| 0.3741 | 731 | 0.1413 | - | - |
| 0.3746 | 732 | 0.1158 | - | - |
| 0.3751 | 733 | 0.1236 | - | - |
| 0.3756 | 734 | 0.1163 | - | - |
| 0.3762 | 735 | 0.1935 | - | - |
| 0.3767 | 736 | 0.1443 | - | - |
| 0.3772 | 737 | 0.1393 | - | - |
| 0.3777 | 738 | 0.1496 | - | - |
| 0.3782 | 739 | 0.1925 | - | - |
| 0.3787 | 740 | 0.2229 | - | - |
| 0.3792 | 741 | 0.1062 | - | - |
| 0.3797 | 742 | 0.1529 | - | - |
| 0.3802 | 743 | 0.1309 | - | - |
| 0.3808 | 744 | 0.1259 | - | - |
| 0.3813 | 745 | 0.1203 | - | - |
| 0.3818 | 746 | 0.1636 | - | - |
| 0.3823 | 747 | 0.3181 | - | - |
| 0.3828 | 748 | 0.2253 | - | - |
| 0.3833 | 749 | 0.1559 | - | - |
| 0.3838 | 750 | 0.1206 | - | - |
| 0.3843 | 751 | 0.099 | - | - |
| 0.3849 | 752 | 0.0946 | - | - |
| 0.3854 | 753 | 0.0961 | - | - |
| 0.3859 | 754 | 0.1094 | - | - |
| 0.3864 | 755 | 0.2492 | - | - |
| 0.3869 | 756 | 0.2146 | - | - |
| 0.3874 | 757 | 0.2002 | - | - |
| 0.3879 | 758 | 0.2457 | - | - |
| 0.3884 | 759 | 0.1416 | - | - |
| 0.3889 | 760 | 0.1471 | - | - |
| 0.3895 | 761 | 0.1082 | - | - |
| 0.3900 | 762 | 0.1395 | - | - |
| 0.3905 | 763 | 0.1187 | - | - |
| 0.3910 | 764 | 0.0906 | - | - |
| 0.3915 | 765 | 0.135 | - | - |
| 0.3920 | 766 | 0.1329 | - | - |
| 0.3925 | 767 | 0.1231 | - | - |
| 0.3930 | 768 | 0.1393 | - | - |
| 0.3936 | 769 | 0.2371 | - | - |
| 0.3941 | 770 | 0.2398 | - | - |
| 0.3946 | 771 | 0.1726 | - | - |
| 0.3951 | 772 | 0.2065 | - | - |
| 0.3956 | 773 | 0.1182 | - | - |
| 0.3961 | 774 | 0.1773 | - | - |
| 0.3966 | 775 | 0.1934 | - | - |
| 0.3971 | 776 | 0.156 | - | - |
| 0.3976 | 777 | 0.1043 | - | - |
| 0.3982 | 778 | 0.111 | - | - |
| 0.3987 | 779 | 0.0814 | - | - |
| 0.3992 | 780 | 0.1229 | - | - |
| 0.3997 | 781 | 0.1041 | - | - |
| 0.4002 | 782 | 0.1793 | - | - |
| 0.4007 | 783 | 0.1291 | - | - |
| 0.4012 | 784 | 0.0874 | - | - |
| 0.4017 | 785 | 0.0509 | - | - |
| 0.4023 | 786 | 0.0774 | - | - |
| 0.4028 | 787 | 0.1298 | - | - |
| 0.4033 | 788 | 0.13 | - | - |
| 0.4038 | 789 | 0.1041 | - | - |
| 0.4043 | 790 | 0.0824 | - | - |
| 0.4048 | 791 | 0.1459 | - | - |
| 0.4053 | 792 | 0.1798 | - | - |
| 0.4058 | 793 | 0.1415 | - | - |
| 0.4063 | 794 | 0.0973 | - | - |
| 0.4069 | 795 | 0.1115 | - | - |
| 0.4074 | 796 | 0.0684 | - | - |
| 0.4079 | 797 | 0.0988 | - | - |
| 0.4084 | 798 | 0.1505 | - | - |
| 0.4089 | 799 | 0.1577 | - | - |
| 0.4094 | 800 | 0.2474 | 0.8913 | 0.9334 |
| 0.4099 | 801 | 0.3658 | - | - |
| 0.4104 | 802 | 0.2929 | - | - |
| 0.4110 | 803 | 0.246 | - | - |
| 0.4115 | 804 | 0.1213 | - | - |
| 0.4120 | 805 | 0.0929 | - | - |
| 0.4125 | 806 | 0.1291 | - | - |
| 0.4130 | 807 | 0.1502 | - | - |
| 0.4135 | 808 | 0.1575 | - | - |
| 0.4140 | 809 | 0.1395 | - | - |
| 0.4145 | 810 | 0.1421 | - | - |
| 0.4150 | 811 | 0.1795 | - | - |
| 0.4156 | 812 | 0.1592 | - | - |
| 0.4161 | 813 | 0.1621 | - | - |
| 0.4166 | 814 | 0.1877 | - | - |
| 0.4171 | 815 | 0.1868 | - | - |
| 0.4176 | 816 | 0.1564 | - | - |
| 0.4181 | 817 | 0.1047 | - | - |
| 0.4186 | 818 | 0.0857 | - | - |
| 0.4191 | 819 | 0.1159 | - | - |
| 0.4197 | 820 | 0.1519 | - | - |
| 0.4202 | 821 | 0.1976 | - | - |
| 0.4207 | 822 | 0.2072 | - | - |
| 0.4212 | 823 | 0.1719 | - | - |
| 0.4217 | 824 | 0.1046 | - | - |
| 0.4222 | 825 | 0.0568 | - | - |
| 0.4227 | 826 | 0.065 | - | - |
| 0.4232 | 827 | 0.1222 | - | - |
| 0.4237 | 828 | 0.0739 | - | - |
| 0.4243 | 829 | 0.0872 | - | - |
| 0.4248 | 830 | 0.1615 | - | - |
| 0.4253 | 831 | 0.198 | - | - |
| 0.4258 | 832 | 0.1537 | - | - |
| 0.4263 | 833 | 0.1463 | - | - |
| 0.4268 | 834 | 0.1315 | - | - |
| 0.4273 | 835 | 0.1306 | - | - |
| 0.4278 | 836 | 0.1842 | - | - |
| 0.4284 | 837 | 0.1698 | - | - |
| 0.4289 | 838 | 0.1345 | - | - |
| 0.4294 | 839 | 0.0589 | - | - |
| 0.4299 | 840 | 0.0509 | - | - |
| 0.4304 | 841 | 0.1266 | - | - |
| 0.4309 | 842 | 0.2453 | - | - |
| 0.4314 | 843 | 0.162 | - | - |
| 0.4319 | 844 | 0.0821 | - | - |
| 0.4324 | 845 | 0.1036 | - | - |
| 0.4330 | 846 | 0.1698 | - | - |
| 0.4335 | 847 | 0.2177 | - | - |
| 0.4340 | 848 | 0.188 | - | - |
| 0.4345 | 849 | 0.2167 | - | - |
| 0.4350 | 850 | 0.2258 | - | - |
| 0.4355 | 851 | 0.1215 | - | - |
| 0.4360 | 852 | 0.0806 | - | - |
| 0.4365 | 853 | 0.1588 | - | - |
| 0.4371 | 854 | 0.1657 | - | - |
| 0.4376 | 855 | 0.1623 | - | - |
| 0.4381 | 856 | 0.1522 | - | - |
| 0.4386 | 857 | 0.1239 | - | - |
| 0.4391 | 858 | 0.2135 | - | - |
| 0.4396 | 859 | 0.1132 | - | - |
| 0.4401 | 860 | 0.1357 | - | - |
| 0.4406 | 861 | 0.1371 | - | - |
| 0.4411 | 862 | 0.0788 | - | - |
| 0.4417 | 863 | 0.2182 | - | - |
| 0.4422 | 864 | 0.247 | - | - |
| 0.4427 | 865 | 0.3319 | - | - |
| 0.4432 | 866 | 0.2565 | - | - |
| 0.4437 | 867 | 0.2339 | - | - |
| 0.4442 | 868 | 0.1491 | - | - |
| 0.4447 | 869 | 0.1654 | - | - |
| 0.4452 | 870 | 0.1651 | - | - |
| 0.4458 | 871 | 0.133 | - | - |
| 0.4463 | 872 | 0.0846 | - | - |
| 0.4468 | 873 | 0.0569 | - | - |
| 0.4473 | 874 | 0.205 | - | - |
| 0.4478 | 875 | 0.1148 | - | - |
| 0.4483 | 876 | 0.1082 | - | - |
| 0.4488 | 877 | 0.2288 | - | - |
| 0.4493 | 878 | 0.1601 | - | - |
| 0.4498 | 879 | 0.1174 | - | - |
| 0.4504 | 880 | 0.0646 | - | - |
| 0.4509 | 881 | 0.0693 | - | - |
| 0.4514 | 882 | 0.1002 | - | - |
| 0.4519 | 883 | 0.1059 | - | - |
| 0.4524 | 884 | 0.1174 | - | - |
| 0.4529 | 885 | 0.0908 | - | - |
| 0.4534 | 886 | 0.0897 | - | - |
| 0.4539 | 887 | 0.3261 | - | - |
| 0.4545 | 888 | 0.3079 | - | - |
| 0.4550 | 889 | 0.4066 | - | - |
| 0.4555 | 890 | 0.236 | - | - |
| 0.4560 | 891 | 0.3301 | - | - |
| 0.4565 | 892 | 0.2789 | - | - |
| 0.4570 | 893 | 0.2218 | - | - |
| 0.4575 | 894 | 0.1181 | - | - |
| 0.4580 | 895 | 0.2813 | - | - |
| 0.4585 | 896 | 0.192 | - | - |
| 0.4591 | 897 | 0.1511 | - | - |
| 0.4596 | 898 | 0.1222 | - | - |
| 0.4601 | 899 | 0.2559 | - | - |
| 0.4606 | 900 | 0.2179 | 0.8456 | 0.9239 |
| 0.4611 | 901 | 0.2879 | - | - |
| 0.4616 | 902 | 0.1087 | - | - |
| 0.4621 | 903 | 0.1736 | - | - |
| 0.4626 | 904 | 0.1514 | - | - |
| 0.4632 | 905 | 0.1984 | - | - |
| 0.4637 | 906 | 0.2888 | - | - |
| 0.4642 | 907 | 0.1639 | - | - |
| 0.4647 | 908 | 0.1533 | - | - |
| 0.4652 | 909 | 0.1575 | - | - |
| 0.4657 | 910 | 0.1716 | - | - |
| 0.4662 | 911 | 0.2199 | - | - |
| 0.4667 | 912 | 0.2275 | - | - |
| 0.4672 | 913 | 0.2263 | - | - |
| 0.4678 | 914 | 0.2248 | - | - |
| 0.4683 | 915 | 0.1751 | - | - |
| 0.4688 | 916 | 0.3353 | - | - |
| 0.4693 | 917 | 0.2627 | - | - |
| 0.4698 | 918 | 0.1676 | - | - |
| 0.4703 | 919 | 0.1338 | - | - |
| 0.4708 | 920 | 0.0972 | - | - |
| 0.4713 | 921 | 0.2103 | - | - |
| 0.4719 | 922 | 0.3038 | - | - |
| 0.4724 | 923 | 0.2816 | - | - |
| 0.4729 | 924 | 0.1309 | - | - |
| 0.4734 | 925 | 0.1162 | - | - |
| 0.4739 | 926 | 0.1112 | - | - |
| 0.4744 | 927 | 0.2015 | - | - |
| 0.4749 | 928 | 0.2021 | - | - |
| 0.4754 | 929 | 0.2221 | - | - |
| 0.4759 | 930 | 0.203 | - | - |
| 0.4765 | 931 | 0.1194 | - | - |
| 0.4770 | 932 | 0.1535 | - | - |
| 0.4775 | 933 | 0.1551 | - | - |
| 0.4780 | 934 | 0.2792 | - | - |
| 0.4785 | 935 | 0.2597 | - | - |
| 0.4790 | 936 | 0.151 | - | - |
| 0.4795 | 937 | 0.2264 | - | - |
| 0.4800 | 938 | 0.1509 | - | - |
| 0.4806 | 939 | 0.1551 | - | - |
| 0.4811 | 940 | 0.1657 | - | - |
| 0.4816 | 941 | 0.1051 | - | - |
| 0.4821 | 942 | 0.1137 | - | - |
| 0.4826 | 943 | 0.0957 | - | - |
| 0.4831 | 944 | 0.0603 | - | - |
| 0.4836 | 945 | 0.0854 | - | - |
| 0.4841 | 946 | 0.1433 | - | - |
| 0.4846 | 947 | 0.233 | - | - |
| 0.4852 | 948 | 0.1573 | - | - |
| 0.4857 | 949 | 0.1465 | - | - |
| 0.4862 | 950 | 0.221 | - | - |
| 0.4867 | 951 | 0.3344 | - | - |
| 0.4872 | 952 | 0.1623 | - | - |
| 0.4877 | 953 | 0.1785 | - | - |
| 0.4882 | 954 | 0.1585 | - | - |
| 0.4887 | 955 | 0.1802 | - | - |
| 0.4893 | 956 | 0.1554 | - | - |
| 0.4898 | 957 | 0.2281 | - | - |
| 0.4903 | 958 | 0.1498 | - | - |
| 0.4908 | 959 | 0.1547 | - | - |
| 0.4913 | 960 | 0.1319 | - | - |
| 0.4918 | 961 | 0.0945 | - | - |
| 0.4923 | 962 | 0.086 | - | - |
| 0.4928 | 963 | 0.1023 | - | - |
| 0.4933 | 964 | 0.0859 | - | - |
| 0.4939 | 965 | 0.1245 | - | - |
| 0.4944 | 966 | 0.2234 | - | - |
| 0.4949 | 967 | 0.2334 | - | - |
| 0.4954 | 968 | 0.2788 | - | - |
| 0.4959 | 969 | 0.192 | - | - |
| 0.4964 | 970 | 0.1285 | - | - |
| 0.4969 | 971 | 0.0865 | - | - |
| 0.4974 | 972 | 0.089 | - | - |
| 0.4980 | 973 | 0.1213 | - | - |
| 0.4985 | 974 | 0.1088 | - | - |
| 0.4990 | 975 | 0.0564 | - | - |
| 0.4995 | 976 | 0.0841 | - | - |
| 0.5 | 977 | 0.1902 | - | - |
| 0.5005 | 978 | 0.2538 | - | - |
| 0.5010 | 979 | 0.2385 | - | - |
| 0.5015 | 980 | 0.2652 | - | - |
| 0.5020 | 981 | 0.1625 | - | - |
| 0.5026 | 982 | 0.1364 | - | - |
| 0.5031 | 983 | 0.1422 | - | - |
| 0.5036 | 984 | 0.1529 | - | - |
| 0.5041 | 985 | 0.1085 | - | - |
| 0.5046 | 986 | 0.1494 | - | - |
| 0.5051 | 987 | 0.1333 | - | - |
| 0.5056 | 988 | 0.2365 | - | - |
| 0.5061 | 989 | 0.2787 | - | - |
| 0.5067 | 990 | 0.1841 | - | - |
| 0.5072 | 991 | 0.1548 | - | - |
| 0.5077 | 992 | 0.1494 | - | - |
| 0.5082 | 993 | 0.1816 | - | - |
| 0.5087 | 994 | 0.1641 | - | - |
| 0.5092 | 995 | 0.1836 | - | - |
| 0.5097 | 996 | 0.2396 | - | - |
| 0.5102 | 997 | 0.2292 | - | - |
| 0.5107 | 998 | 0.1604 | - | - |
| 0.5113 | 999 | 0.1498 | - | - |
| 0.5118 | 1000 | 0.1384 | 1.0291 | 0.9411 |
| 0.5123 | 1001 | 0.1992 | - | - |
| 0.5128 | 1002 | 0.1361 | - | - |
| 0.5133 | 1003 | 0.1393 | - | - |
| 0.5138 | 1004 | 0.277 | - | - |
| 0.5143 | 1005 | 0.1861 | - | - |
| 0.5148 | 1006 | 0.1392 | - | - |
| 0.5154 | 1007 | 0.1052 | - | - |
| 0.5159 | 1008 | 0.1087 | - | - |
| 0.5164 | 1009 | 0.1393 | - | - |
| 0.5169 | 1010 | 0.2721 | - | - |
| 0.5174 | 1011 | 0.2208 | - | - |
| 0.5179 | 1012 | 0.3358 | - | - |
| 0.5184 | 1013 | 0.3529 | - | - |
| 0.5189 | 1014 | 0.2818 | - | - |
| 0.5194 | 1015 | 0.1891 | - | - |
| 0.5200 | 1016 | 0.2494 | - | - |
| 0.5205 | 1017 | 0.1279 | - | - |
| 0.5210 | 1018 | 0.1816 | - | - |
| 0.5215 | 1019 | 0.2082 | - | - |
| 0.5220 | 1020 | 0.1992 | - | - |
| 0.5225 | 1021 | 0.1557 | - | - |
| 0.5230 | 1022 | 0.1652 | - | - |
| 0.5235 | 1023 | 0.1922 | - | - |
| 0.5241 | 1024 | 0.1568 | - | - |
| 0.5246 | 1025 | 0.1523 | - | - |
| 0.5251 | 1026 | 0.0997 | - | - |
| 0.5256 | 1027 | 0.1266 | - | - |
| 0.5261 | 1028 | 0.1444 | - | - |
| 0.5266 | 1029 | 0.1271 | - | - |
| 0.5271 | 1030 | 0.1275 | - | - |
| 0.5276 | 1031 | 0.1042 | - | - |
| 0.5281 | 1032 | 0.2974 | - | - |
| 0.5287 | 1033 | 0.2318 | - | - |
| 0.5292 | 1034 | 0.219 | - | - |
| 0.5297 | 1035 | 0.2216 | - | - |
| 0.5302 | 1036 | 0.2356 | - | - |
| 0.5307 | 1037 | 0.1216 | - | - |
| 0.5312 | 1038 | 0.1155 | - | - |
| 0.5317 | 1039 | 0.116 | - | - |
| 0.5322 | 1040 | 0.136 | - | - |
| 0.5328 | 1041 | 0.1097 | - | - |
| 0.5333 | 1042 | 0.1302 | - | - |
| 0.5338 | 1043 | 0.104 | - | - |
| 0.5343 | 1044 | 0.2442 | - | - |
| 0.5348 | 1045 | 0.3245 | - | - |
| 0.5353 | 1046 | 0.2715 | - | - |
| 0.5358 | 1047 | 0.2266 | - | - |
| 0.5363 | 1048 | 0.1993 | - | - |
| 0.5368 | 1049 | 0.389 | - | - |
| 0.5374 | 1050 | 0.3285 | - | - |
| 0.5379 | 1051 | 0.1983 | - | - |
| 0.5384 | 1052 | 0.2304 | - | - |
| 0.5389 | 1053 | 0.1461 | - | - |
| 0.5394 | 1054 | 0.2071 | - | - |
| 0.5399 | 1055 | 0.1981 | - | - |
| 0.5404 | 1056 | 0.1617 | - | - |
| 0.5409 | 1057 | 0.1207 | - | - |
| 0.5415 | 1058 | 0.2387 | - | - |
| 0.5420 | 1059 | 0.1873 | - | - |
| 0.5425 | 1060 | 0.15 | - | - |
| 0.5430 | 1061 | 0.2065 | - | - |
| 0.5435 | 1062 | 0.1288 | - | - |
| 0.5440 | 1063 | 0.2415 | - | - |
| 0.5445 | 1064 | 0.2859 | - | - |
| 0.5450 | 1065 | 0.2759 | - | - |
| 0.5455 | 1066 | 0.1774 | - | - |
| 0.5461 | 1067 | 0.1699 | - | - |
| 0.5466 | 1068 | 0.1672 | - | - |
| 0.5471 | 1069 | 0.11 | - | - |
| 0.5476 | 1070 | 0.1399 | - | - |
| 0.5481 | 1071 | 0.1269 | - | - |
| 0.5486 | 1072 | 0.1486 | - | - |
| 0.5491 | 1073 | 0.1808 | - | - |
| 0.5496 | 1074 | 0.2333 | - | - |
| 0.5502 | 1075 | 0.2294 | - | - |
| 0.5507 | 1076 | 0.2353 | - | - |
| 0.5512 | 1077 | 0.2048 | - | - |
| 0.5517 | 1078 | 0.1881 | - | - |
| 0.5522 | 1079 | 0.3176 | - | - |
| 0.5527 | 1080 | 0.2117 | - | - |
| 0.5532 | 1081 | 0.1842 | - | - |
| 0.5537 | 1082 | 0.1731 | - | - |
| 0.5542 | 1083 | 0.1705 | - | - |
| 0.5548 | 1084 | 0.1573 | - | - |
| 0.5553 | 1085 | 0.2202 | - | - |
| 0.5558 | 1086 | 0.1947 | - | - |
| 0.5563 | 1087 | 0.1856 | - | - |
| 0.5568 | 1088 | 0.1789 | - | - |
| 0.5573 | 1089 | 0.1649 | - | - |
| 0.5578 | 1090 | 0.149 | - | - |
| 0.5583 | 1091 | 0.0808 | - | - |
| 0.5589 | 1092 | 0.2569 | - | - |
| 0.5594 | 1093 | 0.2677 | - | - |
| 0.5599 | 1094 | 0.2107 | - | - |
| 0.5604 | 1095 | 0.2321 | - | - |
| 0.5609 | 1096 | 0.2247 | - | - |
| 0.5614 | 1097 | 0.196 | - | - |
| 0.5619 | 1098 | 0.2243 | - | - |
| 0.5624 | 1099 | 0.1349 | - | - |
| 0.5629 | 1100 | 0.1142 | 0.8562 | 0.946 |
| 0.5635 | 1101 | 0.1154 | - | - |
| 0.5640 | 1102 | 0.131 | - | - |
| 0.5645 | 1103 | 0.1558 | - | - |
| 0.5650 | 1104 | 0.1561 | - | - |
| 0.5655 | 1105 | 0.1499 | - | - |
| 0.5660 | 1106 | 0.0855 | - | - |
| 0.5665 | 1107 | 0.1234 | - | - |
| 0.5670 | 1108 | 0.1204 | - | - |
| 0.5676 | 1109 | 0.1553 | - | - |
| 0.5681 | 1110 | 0.223 | - | - |
| 0.5686 | 1111 | 0.2299 | - | - |
| 0.5691 | 1112 | 0.255 | - | - |
| 0.5696 | 1113 | 0.2056 | - | - |
| 0.5701 | 1114 | 0.1523 | - | - |
| 0.5706 | 1115 | 0.172 | - | - |
| 0.5711 | 1116 | 0.1508 | - | - |
| 0.5716 | 1117 | 0.1798 | - | - |
| 0.5722 | 1118 | 0.1576 | - | - |
| 0.5727 | 1119 | 0.1492 | - | - |
| 0.5732 | 1120 | 0.0768 | - | - |
| 0.5737 | 1121 | 0.1951 | - | - |
| 0.5742 | 1122 | 0.2158 | - | - |
| 0.5747 | 1123 | 0.1478 | - | - |
| 0.5752 | 1124 | 0.2532 | - | - |
| 0.5757 | 1125 | 0.1836 | - | - |
| 0.5763 | 1126 | 0.1444 | - | - |
| 0.5768 | 1127 | 0.1184 | - | - |
| 0.5773 | 1128 | 0.1401 | - | - |
| 0.5778 | 1129 | 0.1703 | - | - |
| 0.5783 | 1130 | 0.1857 | - | - |
| 0.5788 | 1131 | 0.228 | - | - |
| 0.5793 | 1132 | 0.1959 | - | - |
| 0.5798 | 1133 | 0.1765 | - | - |
| 0.5803 | 1134 | 0.2443 | - | - |
| 0.5809 | 1135 | 0.2171 | - | - |
| 0.5814 | 1136 | 0.1295 | - | - |
| 0.5819 | 1137 | 0.2785 | - | - |
| 0.5824 | 1138 | 0.206 | - | - |
| 0.5829 | 1139 | 0.209 | - | - |
| 0.5834 | 1140 | 0.2066 | - | - |
| 0.5839 | 1141 | 0.1312 | - | - |
| 0.5844 | 1142 | 0.2223 | - | - |
| 0.5850 | 1143 | 0.1394 | - | - |
| 0.5855 | 1144 | 0.1158 | - | - |
| 0.5860 | 1145 | 0.1691 | - | - |
| 0.5865 | 1146 | 0.1066 | - | - |
| 0.5870 | 1147 | 0.1556 | - | - |
| 0.5875 | 1148 | 0.111 | - | - |
| 0.5880 | 1149 | 0.1396 | - | - |
| 0.5885 | 1150 | 0.1085 | - | - |
| 0.5890 | 1151 | 0.1031 | - | - |
| 0.5896 | 1152 | 0.1929 | - | - |
| 0.5901 | 1153 | 0.1603 | - | - |
| 0.5906 | 1154 | 0.1406 | - | - |
| 0.5911 | 1155 | 0.1158 | - | - |
| 0.5916 | 1156 | 0.099 | - | - |
| 0.5921 | 1157 | 0.1206 | - | - |
| 0.5926 | 1158 | 0.1012 | - | - |
| 0.5931 | 1159 | 0.1086 | - | - |
| 0.5937 | 1160 | 0.1664 | - | - |
| 0.5942 | 1161 | 0.1599 | - | - |
| 0.5947 | 1162 | 0.1043 | - | - |
| 0.5952 | 1163 | 0.1218 | - | - |
| 0.5957 | 1164 | 0.1374 | - | - |
| 0.5962 | 1165 | 0.2229 | - | - |
| 0.5967 | 1166 | 0.1296 | - | - |
| 0.5972 | 1167 | 0.2131 | - | - |
| 0.5977 | 1168 | 0.2384 | - | - |
| 0.5983 | 1169 | 0.1702 | - | - |
| 0.5988 | 1170 | 0.2961 | - | - |
| 0.5993 | 1171 | 0.2253 | - | - |
| 0.5998 | 1172 | 0.227 | - | - |
| 0.6003 | 1173 | 0.1754 | - | - |
| 0.6008 | 1174 | 0.213 | - | - |
| 0.6013 | 1175 | 0.1376 | - | - |
| 0.6018 | 1176 | 0.104 | - | - |
| 0.6024 | 1177 | 0.092 | - | - |
| 0.6029 | 1178 | 0.3563 | - | - |
| 0.6034 | 1179 | 0.3275 | - | - |
| 0.6039 | 1180 | 0.2145 | - | - |
| 0.6044 | 1181 | 0.125 | - | - |
| 0.6049 | 1182 | 0.2148 | - | - |
| 0.6054 | 1183 | 0.1757 | - | - |
| 0.6059 | 1184 | 0.1953 | - | - |
| 0.6064 | 1185 | 0.1761 | - | - |
| 0.6070 | 1186 | 0.2783 | - | - |
| 0.6075 | 1187 | 0.1437 | - | - |
| 0.6080 | 1188 | 0.153 | - | - |
| 0.6085 | 1189 | 0.1636 | - | - |
| 0.6090 | 1190 | 0.1582 | - | - |
| 0.6095 | 1191 | 0.1718 | - | - |
| 0.6100 | 1192 | 0.21 | - | - |
| 0.6105 | 1193 | 0.1488 | - | - |
| 0.6111 | 1194 | 0.1797 | - | - |
| 0.6116 | 1195 | 0.1181 | - | - |
| 0.6121 | 1196 | 0.0995 | - | - |
| 0.6126 | 1197 | 0.0782 | - | - |
| 0.6131 | 1198 | 0.2162 | - | - |
| 0.6136 | 1199 | 0.1287 | - | - |
| 0.6141 | 1200 | 0.2397 | 0.8919 | 0.9417 |
| 0.6146 | 1201 | 0.1714 | - | - |
| 0.6151 | 1202 | 0.1367 | - | - |
| 0.6157 | 1203 | 0.088 | - | - |
| 0.6162 | 1204 | 0.0878 | - | - |
| 0.6167 | 1205 | 0.2459 | - | - |
| 0.6172 | 1206 | 0.3603 | - | - |
| 0.6177 | 1207 | 0.4254 | - | - |
| 0.6182 | 1208 | 0.3086 | - | - |
| 0.6187 | 1209 | 0.2139 | - | - |
| 0.6192 | 1210 | 0.2397 | - | - |
| 0.6198 | 1211 | 0.2775 | - | - |
| 0.6203 | 1212 | 0.227 | - | - |
| 0.6208 | 1213 | 0.3257 | - | - |
| 0.6213 | 1214 | 0.3003 | - | - |
| 0.6218 | 1215 | 0.2884 | - | - |
| 0.6223 | 1216 | 0.2774 | - | - |
| 0.6228 | 1217 | 0.186 | - | - |
| 0.6233 | 1218 | 0.1779 | - | - |
| 0.6238 | 1219 | 0.1449 | - | - |
| 0.6244 | 1220 | 0.1487 | - | - |
| 0.6249 | 1221 | 0.1443 | - | - |
| 0.6254 | 1222 | 0.1495 | - | - |
| 0.6259 | 1223 | 0.1419 | - | - |
| 0.6264 | 1224 | 0.1274 | - | - |
| 0.6269 | 1225 | 0.1279 | - | - |
| 0.6274 | 1226 | 0.1687 | - | - |
| 0.6279 | 1227 | 0.1501 | - | - |
| 0.6285 | 1228 | 0.2217 | - | - |
| 0.6290 | 1229 | 0.0882 | - | - |
| 0.6295 | 1230 | 0.1099 | - | - |
| 0.6300 | 1231 | 0.1346 | - | - |
| 0.6305 | 1232 | 0.1601 | - | - |
| 0.6310 | 1233 | 0.1521 | - | - |
| 0.6315 | 1234 | 0.1676 | - | - |
| 0.6320 | 1235 | 0.1402 | - | - |
| 0.6325 | 1236 | 0.171 | - | - |
| 0.6331 | 1237 | 0.1263 | - | - |
| 0.6336 | 1238 | 0.0966 | - | - |
| 0.6341 | 1239 | 0.074 | - | - |
| 0.6346 | 1240 | 0.1244 | - | - |
| 0.6351 | 1241 | 0.2048 | - | - |
| 0.6356 | 1242 | 0.1798 | - | - |
| 0.6361 | 1243 | 0.1455 | - | - |
| 0.6366 | 1244 | 0.1741 | - | - |
| 0.6372 | 1245 | 0.121 | - | - |
| 0.6377 | 1246 | 0.1885 | - | - |
| 0.6382 | 1247 | 0.2382 | - | - |
| 0.6387 | 1248 | 0.3496 | - | - |
| 0.6392 | 1249 | 0.2415 | - | - |
| 0.6397 | 1250 | 0.3394 | - | - |
| 0.6402 | 1251 | 0.2355 | - | - |
| 0.6407 | 1252 | 0.2637 | - | - |
| 0.6412 | 1253 | 0.1075 | - | - |
| 0.6418 | 1254 | 0.139 | - | - |
| 0.6423 | 1255 | 0.179 | - | - |
| 0.6428 | 1256 | 0.192 | - | - |
| 0.6433 | 1257 | 0.2076 | - | - |
| 0.6438 | 1258 | 0.1855 | - | - |
| 0.6443 | 1259 | 0.1788 | - | - |
| 0.6448 | 1260 | 0.1077 | - | - |
| 0.6453 | 1261 | 0.1148 | - | - |
| 0.6459 | 1262 | 0.1379 | - | - |
| 0.6464 | 1263 | 0.0777 | - | - |
| 0.6469 | 1264 | 0.0775 | - | - |
| 0.6474 | 1265 | 0.0697 | - | - |
| 0.6479 | 1266 | 0.1063 | - | - |
| 0.6484 | 1267 | 0.1449 | - | - |
| 0.6489 | 1268 | 0.125 | - | - |
| 0.6494 | 1269 | 0.0831 | - | - |
| 0.6499 | 1270 | 0.0689 | - | - |
| 0.6505 | 1271 | 0.0886 | - | - |
| 0.6510 | 1272 | 0.172 | - | - |
| 0.6515 | 1273 | 0.1881 | - | - |
| 0.6520 | 1274 | 0.1712 | - | - |
| 0.6525 | 1275 | 0.1097 | - | - |
| 0.6530 | 1276 | 0.0811 | - | - |
| 0.6535 | 1277 | 0.1344 | - | - |
| 0.6540 | 1278 | 0.0939 | - | - |
| 0.6546 | 1279 | 0.114 | - | - |
| 0.6551 | 1280 | 0.1289 | - | - |
| 0.6556 | 1281 | 0.2418 | - | - |
| 0.6561 | 1282 | 0.1735 | - | - |
| 0.6566 | 1283 | 0.152 | - | - |
| 0.6571 | 1284 | 0.1477 | - | - |
| 0.6576 | 1285 | 0.277 | - | - |
| 0.6581 | 1286 | 0.1857 | - | - |
| 0.6586 | 1287 | 0.2902 | - | - |
| 0.6592 | 1288 | 0.3308 | - | - |
| 0.6597 | 1289 | 0.3731 | - | - |
| 0.6602 | 1290 | 0.1999 | - | - |
| 0.6607 | 1291 | 0.1524 | - | - |
| 0.6612 | 1292 | 0.171 | - | - |
| 0.6617 | 1293 | 0.1967 | - | - |
| 0.6622 | 1294 | 0.1741 | - | - |
| 0.6627 | 1295 | 0.4263 | - | - |
| 0.6633 | 1296 | 0.3758 | - | - |
| 0.6638 | 1297 | 0.2932 | - | - |
| 0.6643 | 1298 | 0.2372 | - | - |
| 0.6648 | 1299 | 0.2378 | - | - |
| 0.6653 | 1300 | 0.1748 | 0.9384 | 0.95 |
| 0.6658 | 1301 | 0.1687 | - | - |
| 0.6663 | 1302 | 0.1226 | - | - |
| 0.6668 | 1303 | 0.0726 | - | - |
| 0.6673 | 1304 | 0.0676 | - | - |
| 0.6679 | 1305 | 0.0745 | - | - |
| 0.6684 | 1306 | 0.0989 | - | - |
| 0.6689 | 1307 | 0.1513 | - | - |
| 0.6694 | 1308 | 0.105 | - | - |
| 0.6699 | 1309 | 0.0861 | - | - |
| 0.6704 | 1310 | 0.206 | - | - |
| 0.6709 | 1311 | 0.2329 | - | - |
| 0.6714 | 1312 | 0.2457 | - | - |
| 0.6720 | 1313 | 0.2435 | - | - |
| 0.6725 | 1314 | 0.2518 | - | - |
| 0.6730 | 1315 | 0.1494 | - | - |
| 0.6735 | 1316 | 0.1366 | - | - |
| 0.6740 | 1317 | 0.1331 | - | - |
| 0.6745 | 1318 | 0.0924 | - | - |
| 0.6750 | 1319 | 0.1809 | - | - |
| 0.6755 | 1320 | 0.2308 | - | - |
| 0.6760 | 1321 | 0.143 | - | - |
| 0.6766 | 1322 | 0.1312 | - | - |
| 0.6771 | 1323 | 0.155 | - | - |
| 0.6776 | 1324 | 0.1618 | - | - |
| 0.6781 | 1325 | 0.1136 | - | - |
| 0.6786 | 1326 | 0.2256 | - | - |
| 0.6791 | 1327 | 0.2588 | - | - |
| 0.6796 | 1328 | 0.2683 | - | - |
| 0.6801 | 1329 | 0.2722 | - | - |
| 0.6807 | 1330 | 0.1893 | - | - |
| 0.6812 | 1331 | 0.1982 | - | - |
| 0.6817 | 1332 | 0.1641 | - | - |
| 0.6822 | 1333 | 0.128 | - | - |
| 0.6827 | 1334 | 0.1075 | - | - |
| 0.6832 | 1335 | 0.1897 | - | - |
| 0.6837 | 1336 | 0.2387 | - | - |
| 0.6842 | 1337 | 0.2168 | - | - |
| 0.6847 | 1338 | 0.1373 | - | - |
| 0.6853 | 1339 | 0.1824 | - | - |
| 0.6858 | 1340 | 0.1392 | - | - |
| 0.6863 | 1341 | 0.1425 | - | - |
| 0.6868 | 1342 | 0.1798 | - | - |
| 0.6873 | 1343 | 0.2477 | - | - |
| 0.6878 | 1344 | 0.1615 | - | - |
| 0.6883 | 1345 | 0.301 | - | - |
| 0.6888 | 1346 | 0.2127 | - | - |
| 0.6894 | 1347 | 0.1629 | - | - |
| 0.6899 | 1348 | 0.1441 | - | - |
| 0.6904 | 1349 | 0.1267 | - | - |
| 0.6909 | 1350 | 0.1648 | - | - |
| 0.6914 | 1351 | 0.2091 | - | - |
| 0.6919 | 1352 | 0.1479 | - | - |
| 0.6924 | 1353 | 0.1521 | - | - |
| 0.6929 | 1354 | 0.138 | - | - |
| 0.6934 | 1355 | 0.2449 | - | - |
| 0.6940 | 1356 | 0.2294 | - | - |
| 0.6945 | 1357 | 0.2161 | - | - |
| 0.6950 | 1358 | 0.2344 | - | - |
| 0.6955 | 1359 | 0.2294 | - | - |
| 0.6960 | 1360 | 0.1281 | - | - |
| 0.6965 | 1361 | 0.1378 | - | - |
| 0.6970 | 1362 | 0.1468 | - | - |
| 0.6975 | 1363 | 0.1331 | - | - |
| 0.6981 | 1364 | 0.1237 | - | - |
| 0.6986 | 1365 | 0.1272 | - | - |
| 0.6991 | 1366 | 0.1021 | - | - |
| 0.6996 | 1367 | 0.1575 | - | - |
| 0.7001 | 1368 | 0.1118 | - | - |
| 0.7006 | 1369 | 0.2497 | - | - |
| 0.7011 | 1370 | 0.1343 | - | - |
| 0.7016 | 1371 | 0.1654 | - | - |
| 0.7021 | 1372 | 0.213 | - | - |
| 0.7027 | 1373 | 0.2429 | - | - |
| 0.7032 | 1374 | 0.256 | - | - |
| 0.7037 | 1375 | 0.2483 | - | - |
| 0.7042 | 1376 | 0.1414 | - | - |
| 0.7047 | 1377 | 0.1145 | - | - |
| 0.7052 | 1378 | 0.1057 | - | - |
| 0.7057 | 1379 | 0.1681 | - | - |
| 0.7062 | 1380 | 0.1024 | - | - |
| 0.7068 | 1381 | 0.1126 | - | - |
| 0.7073 | 1382 | 0.0643 | - | - |
| 0.7078 | 1383 | 0.1568 | - | - |
| 0.7083 | 1384 | 0.1244 | - | - |
| 0.7088 | 1385 | 0.2137 | - | - |
| 0.7093 | 1386 | 0.204 | - | - |
| 0.7098 | 1387 | 0.1821 | - | - |
| 0.7103 | 1388 | 0.3117 | - | - |
| 0.7108 | 1389 | 0.3247 | - | - |
| 0.7114 | 1390 | 0.1847 | - | - |
| 0.7119 | 1391 | 0.1467 | - | - |
| 0.7124 | 1392 | 0.1288 | - | - |
| 0.7129 | 1393 | 0.0978 | - | - |
| 0.7134 | 1394 | 0.1062 | - | - |
| 0.7139 | 1395 | 0.1502 | - | - |
| 0.7144 | 1396 | 0.1211 | - | - |
| 0.7149 | 1397 | 0.1493 | - | - |
| 0.7155 | 1398 | 0.1302 | - | - |
| 0.7160 | 1399 | 0.0987 | - | - |
| 0.7165 | 1400 | 0.1651 | 0.9160 | 0.9431 |
| 0.7170 | 1401 | 0.1728 | - | - |
| 0.7175 | 1402 | 0.1256 | - | - |
| 0.7180 | 1403 | 0.1498 | - | - |
| 0.7185 | 1404 | 0.2098 | - | - |
| 0.7190 | 1405 | 0.1515 | - | - |
| 0.7195 | 1406 | 0.261 | - | - |
| 0.7201 | 1407 | 0.1713 | - | - |
| 0.7206 | 1408 | 0.144 | - | - |
| 0.7211 | 1409 | 0.1453 | - | - |
| 0.7216 | 1410 | 0.1835 | - | - |
| 0.7221 | 1411 | 0.203 | - | - |
| 0.7226 | 1412 | 0.1583 | - | - |
| 0.7231 | 1413 | 0.2432 | - | - |
| 0.7236 | 1414 | 0.1884 | - | - |
| 0.7242 | 1415 | 0.2799 | - | - |
| 0.7247 | 1416 | 0.2761 | - | - |
| 0.7252 | 1417 | 0.2778 | - | - |
| 0.7257 | 1418 | 0.2611 | - | - |
| 0.7262 | 1419 | 0.2139 | - | - |
| 0.7267 | 1420 | 0.1985 | - | - |
| 0.7272 | 1421 | 0.1684 | - | - |
| 0.7277 | 1422 | 0.2776 | - | - |
| 0.7282 | 1423 | 0.2419 | - | - |
| 0.7288 | 1424 | 0.288 | - | - |
| 0.7293 | 1425 | 0.2441 | - | - |
| 0.7298 | 1426 | 0.1746 | - | - |
| 0.7303 | 1427 | 0.198 | - | - |
| 0.7308 | 1428 | 0.242 | - | - |
| 0.7313 | 1429 | 0.1496 | - | - |
| 0.7318 | 1430 | 0.1395 | - | - |
| 0.7323 | 1431 | 0.1684 | - | - |
| 0.7329 | 1432 | 0.1434 | - | - |
| 0.7334 | 1433 | 0.2848 | - | - |
| 0.7339 | 1434 | 0.2669 | - | - |
| 0.7344 | 1435 | 0.2773 | - | - |
| 0.7349 | 1436 | 0.2792 | - | - |
| 0.7354 | 1437 | 0.3026 | - | - |
| 0.7359 | 1438 | 0.2663 | - | - |
| 0.7364 | 1439 | 0.2701 | - | - |
| 0.7369 | 1440 | 0.1858 | - | - |
| 0.7375 | 1441 | 0.1162 | - | - |
| 0.7380 | 1442 | 0.1988 | - | - |
| 0.7385 | 1443 | 0.2179 | - | - |
| 0.7390 | 1444 | 0.1826 | - | - |
| 0.7395 | 1445 | 0.1403 | - | - |
| 0.7400 | 1446 | 0.1355 | - | - |
| 0.7405 | 1447 | 0.1481 | - | - |
| 0.7410 | 1448 | 0.2838 | - | - |
| 0.7416 | 1449 | 0.222 | - | - |
| 0.7421 | 1450 | 0.2777 | - | - |
| 0.7426 | 1451 | 0.2185 | - | - |
| 0.7431 | 1452 | 0.1763 | - | - |
| 0.7436 | 1453 | 0.2524 | - | - |
| 0.7441 | 1454 | 0.1625 | - | - |
| 0.7446 | 1455 | 0.1506 | - | - |
| 0.7451 | 1456 | 0.1469 | - | - |
| 0.7456 | 1457 | 0.2023 | - | - |
| 0.7462 | 1458 | 0.2784 | - | - |
| 0.7467 | 1459 | 0.3714 | - | - |
| 0.7472 | 1460 | 0.2349 | - | - |
| 0.7477 | 1461 | 0.1571 | - | - |
| 0.7482 | 1462 | 0.1476 | - | - |
| 0.7487 | 1463 | 0.15 | - | - |
| 0.7492 | 1464 | 0.2423 | - | - |
| 0.7497 | 1465 | 0.28 | - | - |
| 0.7503 | 1466 | 0.2623 | - | - |
| 0.7508 | 1467 | 0.2755 | - | - |
| 0.7513 | 1468 | 0.3387 | - | - |
| 0.7518 | 1469 | 0.277 | - | - |
| 0.7523 | 1470 | 0.2891 | - | - |
| 0.7528 | 1471 | 0.2561 | - | - |
| 0.7533 | 1472 | 0.183 | - | - |
| 0.7538 | 1473 | 0.2124 | - | - |
| 0.7544 | 1474 | 0.324 | - | - |
| 0.7549 | 1475 | 0.226 | - | - |
| 0.7554 | 1476 | 0.3019 | - | - |
| 0.7559 | 1477 | 0.19 | - | - |
| 0.7564 | 1478 | 0.176 | - | - |
| 0.7569 | 1479 | 0.1554 | - | - |
| 0.7574 | 1480 | 0.1085 | - | - |
| 0.7579 | 1481 | 0.1455 | - | - |
| 0.7584 | 1482 | 0.2385 | - | - |
| 0.7590 | 1483 | 0.2487 | - | - |
| 0.7595 | 1484 | 0.2457 | - | - |
| 0.7600 | 1485 | 0.2513 | - | - |
| 0.7605 | 1486 | 0.2595 | - | - |
| 0.7610 | 1487 | 0.2852 | - | - |
| 0.7615 | 1488 | 0.2745 | - | - |
| 0.7620 | 1489 | 0.2055 | - | - |
| 0.7625 | 1490 | 0.2506 | - | - |
| 0.7631 | 1491 | 0.1605 | - | - |
| 0.7636 | 1492 | 0.1309 | - | - |
| 0.7641 | 1493 | 0.1512 | - | - |
| 0.7646 | 1494 | 0.2551 | - | - |
| 0.7651 | 1495 | 0.2298 | - | - |
| 0.7656 | 1496 | 0.2101 | - | - |
| 0.7661 | 1497 | 0.2243 | - | - |
| 0.7666 | 1498 | 0.157 | - | - |
| 0.7671 | 1499 | 0.1962 | - | - |
| 0.7677 | 1500 | 0.149 | 0.8459 | 0.9388 |
| 0.7682 | 1501 | 0.1411 | - | - |
| 0.7687 | 1502 | 0.2165 | - | - |
| 0.7692 | 1503 | 0.1634 | - | - |
| 0.7697 | 1504 | 0.1771 | - | - |
| 0.7702 | 1505 | 0.2775 | - | - |
| 0.7707 | 1506 | 0.3142 | - | - |
| 0.7712 | 1507 | 0.253 | - | - |
| 0.7718 | 1508 | 0.2443 | - | - |
| 0.7723 | 1509 | 0.3289 | - | - |
| 0.7728 | 1510 | 0.3004 | - | - |
| 0.7733 | 1511 | 0.3158 | - | - |
| 0.7738 | 1512 | 0.2389 | - | - |
| 0.7743 | 1513 | 0.161 | - | - |
| 0.7748 | 1514 | 0.1752 | - | - |
| 0.7753 | 1515 | 0.1277 | - | - |
| 0.7758 | 1516 | 0.1662 | - | - |
| 0.7764 | 1517 | 0.2383 | - | - |
| 0.7769 | 1518 | 0.1823 | - | - |
| 0.7774 | 1519 | 0.3215 | - | - |
| 0.7779 | 1520 | 0.2643 | - | - |
| 0.7784 | 1521 | 0.2251 | - | - |
| 0.7789 | 1522 | 0.258 | - | - |
| 0.7794 | 1523 | 0.1986 | - | - |
| 0.7799 | 1524 | 0.1937 | - | - |
| 0.7805 | 1525 | 0.2017 | - | - |
| 0.7810 | 1526 | 0.2152 | - | - |
| 0.7815 | 1527 | 0.205 | - | - |
| 0.7820 | 1528 | 0.2045 | - | - |
| 0.7825 | 1529 | 0.1897 | - | - |
| 0.7830 | 1530 | 0.1718 | - | - |
| 0.7835 | 1531 | 0.1158 | - | - |
| 0.7840 | 1532 | 0.1807 | - | - |
| 0.7845 | 1533 | 0.2381 | - | - |
| 0.7851 | 1534 | 0.3434 | - | - |
| 0.7856 | 1535 | 0.3852 | - | - |
| 0.7861 | 1536 | 0.289 | - | - |
| 0.7866 | 1537 | 0.3242 | - | - |
| 0.7871 | 1538 | 0.2734 | - | - |
| 0.7876 | 1539 | 0.2034 | - | - |
| 0.7881 | 1540 | 0.2312 | - | - |
| 0.7886 | 1541 | 0.2406 | - | - |
| 0.7892 | 1542 | 0.2152 | - | - |
| 0.7897 | 1543 | 0.1394 | - | - |
| 0.7902 | 1544 | 0.1243 | - | - |
| 0.7907 | 1545 | 0.2377 | - | - |
| 0.7912 | 1546 | 0.1362 | - | - |
| 0.7917 | 1547 | 0.1219 | - | - |
| 0.7922 | 1548 | 0.2065 | - | - |
| 0.7927 | 1549 | 0.2249 | - | - |
| 0.7932 | 1550 | 0.2644 | - | - |
| 0.7938 | 1551 | 0.2899 | - | - |
| 0.7943 | 1552 | 0.2978 | - | - |
| 0.7948 | 1553 | 0.2584 | - | - |
| 0.7953 | 1554 | 0.4284 | - | - |
| 0.7958 | 1555 | 0.3485 | - | - |
| 0.7963 | 1556 | 0.3921 | - | - |
| 0.7968 | 1557 | 0.3097 | - | - |
| 0.7973 | 1558 | 0.2372 | - | - |
| 0.7979 | 1559 | 0.2799 | - | - |
| 0.7984 | 1560 | 0.1728 | - | - |
| 0.7989 | 1561 | 0.1616 | - | - |
| 0.7994 | 1562 | 0.0986 | - | - |
| 0.7999 | 1563 | 0.1344 | - | - |
| 0.8004 | 1564 | 0.0714 | - | - |
| 0.8009 | 1565 | 0.1967 | - | - |
| 0.8014 | 1566 | 0.2853 | - | - |
| 0.8019 | 1567 | 0.3007 | - | - |
| 0.8025 | 1568 | 0.3036 | - | - |
| 0.8030 | 1569 | 0.315 | - | - |
| 0.8035 | 1570 | 0.2196 | - | - |
| 0.8040 | 1571 | 0.183 | - | - |
| 0.8045 | 1572 | 0.1717 | - | - |
| 0.8050 | 1573 | 0.2454 | - | - |
| 0.8055 | 1574 | 0.1936 | - | - |
| 0.8060 | 1575 | 0.2392 | - | - |
| 0.8066 | 1576 | 0.1998 | - | - |
| 0.8071 | 1577 | 0.2382 | - | - |
| 0.8076 | 1578 | 0.1752 | - | - |
| 0.8081 | 1579 | 0.2791 | - | - |
| 0.8086 | 1580 | 0.1962 | - | - |
| 0.8091 | 1581 | 0.2455 | - | - |
| 0.8096 | 1582 | 0.2088 | - | - |
| 0.8101 | 1583 | 0.2779 | - | - |
| 0.8106 | 1584 | 0.2799 | - | - |
| 0.8112 | 1585 | 0.2245 | - | - |
| 0.8117 | 1586 | 0.3577 | - | - |
| 0.8122 | 1587 | 0.3454 | - | - |
| 0.8127 | 1588 | 0.2465 | - | - |
| 0.8132 | 1589 | 0.219 | - | - |
| 0.8137 | 1590 | 0.2016 | - | - |
| 0.8142 | 1591 | 0.2132 | - | - |
| 0.8147 | 1592 | 0.293 | - | - |
| 0.8153 | 1593 | 0.3512 | - | - |
| 0.8158 | 1594 | 0.299 | - | - |
| 0.8163 | 1595 | 0.2666 | - | - |
| 0.8168 | 1596 | 0.2419 | - | - |
| 0.8173 | 1597 | 0.1873 | - | - |
| 0.8178 | 1598 | 0.1393 | - | - |
| 0.8183 | 1599 | 0.1834 | - | - |
| 0.8188 | 1600 | 0.2424 | 0.7951 | 0.9384 |
| 0.8193 | 1601 | 0.3308 | - | - |
| 0.8199 | 1602 | 0.389 | - | - |
| 0.8204 | 1603 | 0.372 | - | - |
| 0.8209 | 1604 | 0.4278 | - | - |
| 0.8214 | 1605 | 0.32 | - | - |
| 0.8219 | 1606 | 0.4131 | - | - |
| 0.8224 | 1607 | 0.4209 | - | - |
| 0.8229 | 1608 | 0.3434 | - | - |
| 0.8234 | 1609 | 0.3183 | - | - |
| 0.8240 | 1610 | 0.2844 | - | - |
| 0.8245 | 1611 | 0.3242 | - | - |
| 0.8250 | 1612 | 0.2182 | - | - |
| 0.8255 | 1613 | 0.1782 | - | - |
| 0.8260 | 1614 | 0.2351 | - | - |
| 0.8265 | 1615 | 0.164 | - | - |
| 0.8270 | 1616 | 0.2148 | - | - |
| 0.8275 | 1617 | 0.1739 | - | - |
| 0.8280 | 1618 | 0.2578 | - | - |
| 0.8286 | 1619 | 0.2316 | - | - |
| 0.8291 | 1620 | 0.1719 | - | - |
| 0.8296 | 1621 | 0.1277 | - | - |
| 0.8301 | 1622 | 0.16 | - | - |
| 0.8306 | 1623 | 0.1504 | - | - |
| 0.8311 | 1624 | 0.1563 | - | - |
| 0.8316 | 1625 | 0.1938 | - | - |
| 0.8321 | 1626 | 0.1918 | - | - |
| 0.8327 | 1627 | 0.2196 | - | - |
| 0.8332 | 1628 | 0.1967 | - | - |
| 0.8337 | 1629 | 0.2586 | - | - |
| 0.8342 | 1630 | 0.1991 | - | - |
| 0.8347 | 1631 | 0.2869 | - | - |
| 0.8352 | 1632 | 0.4497 | - | - |
| 0.8357 | 1633 | 0.3518 | - | - |
| 0.8362 | 1634 | 0.3113 | - | - |
| 0.8367 | 1635 | 0.2545 | - | - |
| 0.8373 | 1636 | 0.3275 | - | - |
| 0.8378 | 1637 | 0.2098 | - | - |
| 0.8383 | 1638 | 0.2076 | - | - |
| 0.8388 | 1639 | 0.218 | - | - |
| 0.8393 | 1640 | 0.2361 | - | - |
| 0.8398 | 1641 | 0.2324 | - | - |
| 0.8403 | 1642 | 0.2245 | - | - |
| 0.8408 | 1643 | 0.2767 | - | - |
| 0.8414 | 1644 | 0.2204 | - | - |
| 0.8419 | 1645 | 0.2158 | - | - |
| 0.8424 | 1646 | 0.1711 | - | - |
| 0.8429 | 1647 | 0.2333 | - | - |
| 0.8434 | 1648 | 0.2089 | - | - |
| 0.8439 | 1649 | 0.2114 | - | - |
| 0.8444 | 1650 | 0.2712 | - | - |
| 0.8449 | 1651 | 0.3705 | - | - |
| 0.8454 | 1652 | 0.3409 | - | - |
| 0.8460 | 1653 | 0.3343 | - | - |
| 0.8465 | 1654 | 0.2467 | - | - |
| 0.8470 | 1655 | 0.2415 | - | - |
| 0.8475 | 1656 | 0.2174 | - | - |
| 0.8480 | 1657 | 0.222 | - | - |
| 0.8485 | 1658 | 0.1879 | - | - |
| 0.8490 | 1659 | 0.2461 | - | - |
| 0.8495 | 1660 | 0.2413 | - | - |
| 0.8501 | 1661 | 0.1931 | - | - |
| 0.8506 | 1662 | 0.2744 | - | - |
| 0.8511 | 1663 | 0.3202 | - | - |
| 0.8516 | 1664 | 0.3382 | - | - |
| 0.8521 | 1665 | 0.2325 | - | - |
| 0.8526 | 1666 | 0.2124 | - | - |
| 0.8531 | 1667 | 0.2321 | - | - |
| 0.8536 | 1668 | 0.1406 | - | - |
| 0.8541 | 1669 | 0.1909 | - | - |
| 0.8547 | 1670 | 0.162 | - | - |
| 0.8552 | 1671 | 0.153 | - | - |
| 0.8557 | 1672 | 0.1104 | - | - |
| 0.8562 | 1673 | 0.1914 | - | - |
| 0.8567 | 1674 | 0.1988 | - | - |
| 0.8572 | 1675 | 0.2261 | - | - |
| 0.8577 | 1676 | 0.1765 | - | - |
| 0.8582 | 1677 | 0.1269 | - | - |
| 0.8588 | 1678 | 0.1017 | - | - |
| 0.8593 | 1679 | 0.2056 | - | - |
| 0.8598 | 1680 | 0.1059 | - | - |
| 0.8603 | 1681 | 0.1901 | - | - |
| 0.8608 | 1682 | 0.2596 | - | - |
| 0.8613 | 1683 | 0.3579 | - | - |
| 0.8618 | 1684 | 0.3703 | - | - |
| 0.8623 | 1685 | 0.3352 | - | - |
| 0.8628 | 1686 | 0.3461 | - | - |
| 0.8634 | 1687 | 0.391 | - | - |
| 0.8639 | 1688 | 0.2818 | - | - |
| 0.8644 | 1689 | 0.339 | - | - |
| 0.8649 | 1690 | 0.3048 | - | - |
| 0.8654 | 1691 | 0.3521 | - | - |
| 0.8659 | 1692 | 0.3335 | - | - |
| 0.8664 | 1693 | 0.2935 | - | - |
| 0.8669 | 1694 | 0.2318 | - | - |
| 0.8675 | 1695 | 0.3297 | - | - |
| 0.8680 | 1696 | 0.2218 | - | - |
| 0.8685 | 1697 | 0.2533 | - | - |
| 0.8690 | 1698 | 0.2637 | - | - |
| 0.8695 | 1699 | 0.2106 | - | - |
| 0.8700 | 1700 | 0.2082 | 0.7336 | 0.9439 |
| 0.8705 | 1701 | 0.2165 | - | - |
| 0.8710 | 1702 | 0.1938 | - | - |
| 0.8715 | 1703 | 0.2059 | - | - |
| 0.8721 | 1704 | 0.2639 | - | - |
| 0.8726 | 1705 | 0.2104 | - | - |
| 0.8731 | 1706 | 0.2204 | - | - |
| 0.8736 | 1707 | 0.3166 | - | - |
| 0.8741 | 1708 | 0.3073 | - | - |
| 0.8746 | 1709 | 0.2907 | - | - |
| 0.8751 | 1710 | 0.2448 | - | - |
| 0.8756 | 1711 | 0.2335 | - | - |
| 0.8762 | 1712 | 0.2861 | - | - |
| 0.8767 | 1713 | 0.3016 | - | - |
| 0.8772 | 1714 | 0.3313 | - | - |
| 0.8777 | 1715 | 0.4154 | - | - |
| 0.8782 | 1716 | 0.5309 | - | - |
| 0.8787 | 1717 | 0.4596 | - | - |
| 0.8792 | 1718 | 0.5752 | - | - |
| 0.8797 | 1719 | 0.4659 | - | - |
| 0.8802 | 1720 | 0.4636 | - | - |
| 0.8808 | 1721 | 0.4933 | - | - |
| 0.8813 | 1722 | 0.4949 | - | - |
| 0.8818 | 1723 | 0.4512 | - | - |
| 0.8823 | 1724 | 0.3858 | - | - |
| 0.8828 | 1725 | 0.3943 | - | - |
| 0.8833 | 1726 | 0.3733 | - | - |
| 0.8838 | 1727 | 0.3156 | - | - |
| 0.8843 | 1728 | 0.3272 | - | - |
| 0.8849 | 1729 | 0.2644 | - | - |
| 0.8854 | 1730 | 0.3572 | - | - |
| 0.8859 | 1731 | 0.2716 | - | - |
| 0.8864 | 1732 | 0.3054 | - | - |
| 0.8869 | 1733 | 0.3884 | - | - |
| 0.8874 | 1734 | 0.3512 | - | - |
| 0.8879 | 1735 | 0.2992 | - | - |
| 0.8884 | 1736 | 0.272 | - | - |
| 0.8889 | 1737 | 0.293 | - | - |
| 0.8895 | 1738 | 0.2506 | - | - |
| 0.8900 | 1739 | 0.3214 | - | - |
| 0.8905 | 1740 | 0.3026 | - | - |
| 0.8910 | 1741 | 0.3495 | - | - |
| 0.8915 | 1742 | 0.3697 | - | - |
| 0.8920 | 1743 | 0.2535 | - | - |
| 0.8925 | 1744 | 0.2417 | - | - |
| 0.8930 | 1745 | 0.2419 | - | - |
| 0.8936 | 1746 | 0.2106 | - | - |
| 0.8941 | 1747 | 0.209 | - | - |
| 0.8946 | 1748 | 0.2587 | - | - |
| 0.8951 | 1749 | 0.19 | - | - |
| 0.8956 | 1750 | 0.2744 | - | - |
| 0.8961 | 1751 | 0.3315 | - | - |
| 0.8966 | 1752 | 0.3192 | - | - |
| 0.8971 | 1753 | 0.44 | - | - |
| 0.8976 | 1754 | 0.3511 | - | - |
| 0.8982 | 1755 | 0.4535 | - | - |
| 0.8987 | 1756 | 0.4044 | - | - |
| 0.8992 | 1757 | 0.3398 | - | - |
| 0.8997 | 1758 | 0.3599 | - | - |
| 0.9002 | 1759 | 0.3552 | - | - |
| 0.9007 | 1760 | 0.3493 | - | - |
| 0.9012 | 1761 | 0.4215 | - | - |
| 0.9017 | 1762 | 0.3116 | - | - |
| 0.9023 | 1763 | 0.3451 | - | - |
| 0.9028 | 1764 | 0.2985 | - | - |
| 0.9033 | 1765 | 0.3452 | - | - |
| 0.9038 | 1766 | 0.2489 | - | - |
| 0.9043 | 1767 | 0.2266 | - | - |
| 0.9048 | 1768 | 0.2906 | - | - |
| 0.9053 | 1769 | 0.3229 | - | - |
| 0.9058 | 1770 | 0.3264 | - | - |
| 0.9063 | 1771 | 0.326 | - | - |
| 0.9069 | 1772 | 0.4848 | - | - |
| 0.9074 | 1773 | 0.347 | - | - |
| 0.9079 | 1774 | 0.2467 | - | - |
| 0.9084 | 1775 | 0.2548 | - | - |
| 0.9089 | 1776 | 0.4412 | - | - |
| 0.9094 | 1777 | 0.3089 | - | - |
| 0.9099 | 1778 | 0.4491 | - | - |
| 0.9104 | 1779 | 0.4089 | - | - |
| 0.9110 | 1780 | 0.396 | - | - |
| 0.9115 | 1781 | 0.4404 | - | - |
| 0.9120 | 1782 | 0.4197 | - | - |
| 0.9125 | 1783 | 0.2947 | - | - |
| 0.9130 | 1784 | 0.2952 | - | - |
| 0.9135 | 1785 | 0.2941 | - | - |
| 0.9140 | 1786 | 0.3605 | - | - |
| 0.9145 | 1787 | 0.3431 | - | - |
| 0.9150 | 1788 | 0.2934 | - | - |
| 0.9156 | 1789 | 0.3605 | - | - |
| 0.9161 | 1790 | 0.3521 | - | - |
| 0.9166 | 1791 | 0.3997 | - | - |
| 0.9171 | 1792 | 0.5006 | - | - |
| 0.9176 | 1793 | 0.354 | - | - |
| 0.9181 | 1794 | 0.388 | - | - |
| 0.9186 | 1795 | 0.3895 | - | - |
| 0.9191 | 1796 | 0.4333 | - | - |
| 0.9197 | 1797 | 0.4895 | - | - |
| 0.9202 | 1798 | 0.4691 | - | - |
| 0.9207 | 1799 | 0.4145 | - | - |
| 0.9212 | 1800 | 0.3753 | 0.6788 | 0.9502 |
| 0.9217 | 1801 | 0.4704 | - | - |
| 0.9222 | 1802 | 0.441 | - | - |
| 0.9227 | 1803 | 0.3925 | - | - |
| 0.9232 | 1804 | 0.3288 | - | - |
| 0.9237 | 1805 | 0.346 | - | - |
| 0.9243 | 1806 | 0.4326 | - | - |
| 0.9248 | 1807 | 0.4024 | - | - |
| 0.9253 | 1808 | 0.6031 | - | - |
| 0.9258 | 1809 | 0.6031 | - | - |
| 0.9263 | 1810 | 0.5265 | - | - |
| 0.9268 | 1811 | 0.428 | - | - |
| 0.9273 | 1812 | 0.4373 | - | - |
| 0.9278 | 1813 | 0.3541 | - | - |
| 0.9284 | 1814 | 0.3621 | - | - |
| 0.9289 | 1815 | 0.365 | - | - |
| 0.9294 | 1816 | 0.4398 | - | - |
| 0.9299 | 1817 | 0.398 | - | - |
| 0.9304 | 1818 | 0.4375 | - | - |
| 0.9309 | 1819 | 0.3815 | - | - |
| 0.9314 | 1820 | 0.4396 | - | - |
| 0.9319 | 1821 | 0.3871 | - | - |
| 0.9324 | 1822 | 0.4421 | - | - |
| 0.9330 | 1823 | 0.3979 | - | - |
| 0.9335 | 1824 | 0.3619 | - | - |
| 0.9340 | 1825 | 0.4688 | - | - |
| 0.9345 | 1826 | 0.3951 | - | - |
| 0.9350 | 1827 | 0.3807 | - | - |
| 0.9355 | 1828 | 0.3978 | - | - |
| 0.9360 | 1829 | 0.3519 | - | - |
| 0.9365 | 1830 | 0.4019 | - | - |
| 0.9371 | 1831 | 0.3853 | - | - |
| 0.9376 | 1832 | 0.4026 | - | - |
| 0.9381 | 1833 | 0.4212 | - | - |
| 0.9386 | 1834 | 0.5422 | - | - |
| 0.9391 | 1835 | 0.4808 | - | - |
| 0.9396 | 1836 | 0.5497 | - | - |
| 0.9401 | 1837 | 0.5487 | - | - |
| 0.9406 | 1838 | 0.4814 | - | - |
| 0.9411 | 1839 | 0.497 | - | - |
| 0.9417 | 1840 | 0.4491 | - | - |
| 0.9422 | 1841 | 0.4983 | - | - |
| 0.9427 | 1842 | 0.4855 | - | - |
| 0.9432 | 1843 | 0.4256 | - | - |
| 0.9437 | 1844 | 0.3845 | - | - |
| 0.9442 | 1845 | 0.3885 | - | - |
| 0.9447 | 1846 | 0.429 | - | - |
| 0.9452 | 1847 | 0.5845 | - | - |
| 0.9458 | 1848 | 0.4565 | - | - |
| 0.9463 | 1849 | 0.4371 | - | - |
| 0.9468 | 1850 | 0.5884 | - | - |
| 0.9473 | 1851 | 0.4054 | - | - |
| 0.9478 | 1852 | 0.5583 | - | - |
| 0.9483 | 1853 | 0.4478 | - | - |
| 0.9488 | 1854 | 0.4341 | - | - |
| 0.9493 | 1855 | 0.4308 | - | - |
| 0.9498 | 1856 | 0.503 | - | - |
| 0.9504 | 1857 | 0.4396 | - | - |
| 0.9509 | 1858 | 0.5434 | - | - |
| 0.9514 | 1859 | 0.4144 | - | - |
| 0.9519 | 1860 | 0.4432 | - | - |
| 0.9524 | 1861 | 0.3656 | - | - |
| 0.9529 | 1862 | 0.3972 | - | - |
| 0.9534 | 1863 | 0.4992 | - | - |
| 0.9539 | 1864 | 0.3215 | - | - |
| 0.9545 | 1865 | 0.3741 | - | - |
| 0.9550 | 1866 | 0.4548 | - | - |
| 0.9555 | 1867 | 0.5291 | - | - |
| 0.9560 | 1868 | 0.4826 | - | - |
| 0.9565 | 1869 | 0.5447 | - | - |
| 0.9570 | 1870 | 0.6471 | - | - |
| 0.9575 | 1871 | 0.5302 | - | - |
| 0.9580 | 1872 | 0.5803 | - | - |
| 0.9585 | 1873 | 0.6097 | - | - |
| 0.9591 | 1874 | 0.6494 | - | - |
| 0.9596 | 1875 | 0.5735 | - | - |
| 0.9601 | 1876 | 0.4434 | - | - |
| 0.9606 | 1877 | 0.4713 | - | - |
| 0.9611 | 1878 | 0.496 | - | - |
| 0.9616 | 1879 | 0.4067 | - | - |
| 0.9621 | 1880 | 0.5666 | - | - |
| 0.9626 | 1881 | 0.46 | - | - |
| 0.9632 | 1882 | 0.4719 | - | - |
| 0.9637 | 1883 | 0.5055 | - | - |
| 0.9642 | 1884 | 0.5013 | - | - |
| 0.9647 | 1885 | 0.5041 | - | - |
| 0.9652 | 1886 | 0.444 | - | - |
| 0.9657 | 1887 | 0.5036 | - | - |
| 0.9662 | 1888 | 0.4842 | - | - |
| 0.9667 | 1889 | 0.4947 | - | - |
| 0.9672 | 1890 | 0.5691 | - | - |
| 0.9678 | 1891 | 0.6534 | - | - |
| 0.9683 | 1892 | 0.6255 | - | - |
| 0.9688 | 1893 | 0.5947 | - | - |
| 0.9693 | 1894 | 0.5101 | - | - |
| 0.9698 | 1895 | 0.5423 | - | - |
| 0.9703 | 1896 | 0.4088 | - | - |
| 0.9708 | 1897 | 0.5801 | - | - |
| 0.9713 | 1898 | 0.5051 | - | - |
| 0.9719 | 1899 | 0.5947 | - | - |
| 0.9724 | 1900 | 0.5611 | 0.6374 | 0.9537 |
| 0.9729 | 1901 | 0.57 | - | - |
| 0.9734 | 1902 | 0.5558 | - | - |
| 0.9739 | 1903 | 0.5192 | - | - |
| 0.9744 | 1904 | 0.5319 | - | - |
| 0.9749 | 1905 | 0.5511 | - | - |
| 0.9754 | 1906 | 0.5118 | - | - |
| 0.9759 | 1907 | 0.5721 | - | - |
| 0.9765 | 1908 | 0.6543 | - | - |
| 0.9770 | 1909 | 0.6707 | - | - |
| 0.9775 | 1910 | 0.5997 | - | - |
| 0.9780 | 1911 | 0.5712 | - | - |
| 0.9785 | 1912 | 0.6574 | - | - |
| 0.9790 | 1913 | 0.5981 | - | - |
| 0.9795 | 1914 | 0.7499 | - | - |
| 0.9800 | 1915 | 0.738 | - | - |
| 0.9806 | 1916 | 0.6731 | - | - |
| 0.9811 | 1917 | 0.7481 | - | - |
| 0.9816 | 1918 | 0.7995 | - | - |
| 0.9821 | 1919 | 0.6295 | - | - |
| 0.9826 | 1920 | 0.6599 | - | - |
| 0.9831 | 1921 | 0.5386 | - | - |
| 0.9836 | 1922 | 0.6293 | - | - |
| 0.9841 | 1923 | 0.5511 | - | - |
| 0.9846 | 1924 | 0.5737 | - | - |
| 0.9852 | 1925 | 0.5261 | - | - |
| 0.9857 | 1926 | 0.5196 | - | - |
| 0.9862 | 1927 | 0.5886 | - | - |
| 0.9867 | 1928 | 0.6642 | - | - |
| 0.9872 | 1929 | 0.5713 | - | - |
| 0.9877 | 1930 | 0.5396 | - | - |
| 0.9882 | 1931 | 0.4805 | - | - |
| 0.9887 | 1932 | 0.5228 | - | - |
| 0.9893 | 1933 | 0.6495 | - | - |
| 0.9898 | 1934 | 0.5876 | - | - |
| 0.9903 | 1935 | 0.5542 | - | - |
| 0.9908 | 1936 | 0.6024 | - | - |
| 0.9913 | 1937 | 0.5677 | - | - |
| 0.9918 | 1938 | 0.6009 | - | - |
| 0.9923 | 1939 | 0.5893 | - | - |
| 0.9928 | 1940 | 0.461 | - | - |
| 0.9933 | 1941 | 0.4467 | - | - |
| 0.9939 | 1942 | 0.5059 | - | - |
| 0.9944 | 1943 | 0.6037 | - | - |
| 0.9949 | 1944 | 0.3525 | - | - |
| 0.9954 | 1945 | 0.5509 | - | - |
| 0.9959 | 1946 | 0.4277 | - | - |
| 0.9964 | 1947 | 0.344 | - | - |
| 0.9969 | 1948 | 0.4039 | - | - |
| 0.9974 | 1949 | 0.3924 | - | - |
| 0.9980 | 1950 | 0.3328 | - | - |
| 0.9985 | 1951 | 0.3756 | - | - |
| 0.9990 | 1952 | 0.3523 | - | - |
| 0.9995 | 1953 | 0.6408 | - | - |
| 1.0 | 1954 | 0.392 | - | 0.9587 |
</details>
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.3.1
- Transformers: 4.48.0.dev0
- PyTorch: 2.1.0+cu118
- Accelerate: 1.2.1
- Datasets: 3.2.0
- Tokenizers: 0.21.0
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MatryoshkaLoss
```bibtex
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
|
{"base_model": "answerdotai/ModernBERT-base", "datasets": ["sentence-transformers/msmarco-bm25"], "language": ["en"], "library_name": "sentence-transformers", "metrics": ["cosine_accuracy"], "pipeline_tag": "sentence-similarity", "tags": ["sentence-transformers", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:19139199", "loss:MatryoshkaLoss", "loss:MultipleNegativesRankingLoss"], "widget": [{"source_sentence": "[unused0]what period do we live in", "sentences": ["[unused1]The answer depends on what you want in a cruise experience. If youâre interested in lively entertainment, drinking and parties, and crazy excitement for more festive cruise experience, and the best time to go on a Caribbean cruise is between mid February through much of March.", "[unused1]Earth is currently in the Quaternary Period of the Cenozoic Era.", "[unused1]If we did not live in a structured society with other people, laws would not be necessary. We would simply do as we please, with little regard for others. But ever since individuals began to associate with other people -- to live in society --laws have been the glue that has kept society together.lmost everything we do is governed by some set of rules. There are rules for games, for social clubs, for sports and for adults in the workplace. There are also rules imposed by morality and custom that play an important role in telling us what we should and should not do."]}, {"source_sentence": "[unused0]how different religion define christology", "sentences": ["[unused1]Find origin, gender, rashi, nakshatra, zodiac signs, moon signs, religion, caste, compatibility and astrology behind the name Janhavi, Find what name Janhavi means in different region, in different religion, in different rashi, for different planets, and in different nakshatraâs.", "[unused1]Christianity is an Abrahamic religion that began as a Second Temple Judaic sect in the mid-1st century. Originating in Judea, it quickly spread to Europe, Syria, Mesopotamia, Asia Minor, Transcaucasia, Egypt, Ethiopia, and India, and by the end of the 4th century had become the official state church of the Roman Empire.", "[unused1]The answer depends on what you want in a cruise experience. If youâre interested in lively entertainment, drinking and parties, and crazy excitement for more festive cruise experience, and the best time to go on a Caribbean cruise is between mid February through much of March."]}, {"source_sentence": "[unused0]what was juliet morgan family", "sentences": ["[unused1]Famous Financier. Financier, art collector and philanthropist John Pierpont Morgan, best known as J.P. Morgan, was born on April 17, 1837, in Hartford, Connecticut. The son of a banker, Morgan went into the family business and became one of the most famous financiers in history.", "[unused1]Juliet Pierpont Morgan was born on month day 1847, at birth place, Connecticut, to Junius Spencer Morgan and Juliet Morgan (born Pierpont). Junius was born on April 14 1813, in Holyoke, Hampden County, Massachusetts, USA.", "[unused1]Juliette Hampton Morgan was a librarian and civil rights activist in Montgomery, Alabama. The only daughter from a well-to-do white family, Morgan was an early member of the community that pushed for integration. As a librarian she often spoke out against the acts of injustice she witnessed against African-Americans by writing letters to the Montgomery Advertiser, the local newspaper. She was castigated by the community for her racial views and was targeted by segregationists who broke her windo"]}, {"source_sentence": "[unused0]how different religion define christology", "sentences": ["[unused1]Carbon Monoxide is produced from gas appliances in your home. Carbon Dioxide is produced from the exhaust fumes from your automobile. Either of these gases can be harmful to a human. These gases can be even more harmful to small animals in your home. Depending on the size of your home you should have a carbon monoxide detector on every level of your home.", "[unused1]Doctrine is a set of accepted beliefs held by a group. In religion, it is the set of true beliefs that define the parameters of that belief system.", "[unused1]Christianity is an Abrahamic religion that began as a Second Temple Judaic sect in the mid-1st century. Originating in Judea, it quickly spread to Europe, Syria, Mesopotamia, Asia Minor, Transcaucasia, Egypt, Ethiopia, and India, and by the end of the 4th century had become the official state church of the Roman Empire."]}, {"source_sentence": "[unused0]what period do we live in", "sentences": ["[unused1]Thereâs a big difference in drive time depending on what part of Ewa Beach you live in â the homes in Ocean Point (most southern part of Ewa) have a 20 minute longer drive than we do, even though we both live in the town of Ewa Beach.", "[unused1]Save. Bankruptcy does not automatically disqualify someone for receiving security clearances, but it will slow the process down--as will any derogatory financial information. If you are applying for top-secret clearance, background investigators will review the reasons for your bankruptcy.", "[unused1]Earth is currently in the Quaternary Period of the Cenozoic Era."]}], "model-index": [{"name": "SentenceTransformer based on estrogen/ModernBERT-base-sbert-initialized", "results": [{"task": {"type": "triplet", "name": "Triplet"}, "dataset": {"name": "ms marco", "type": "ms_marco"}, "metrics": [{"type": "cosine_accuracy", "value": 0.9537, "name": "Cosine Accuracy"}, {"type": "cosine_accuracy", "value": 0.9587, "name": "Cosine Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,849 |
kinti/traductor-boe
|
kinti
|
summarization
|
[
"fasttext",
"summarization,",
"text2text-generation,",
"summarization",
"es",
"region:us"
] | 2024-12-22T02:30:18Z |
2024-12-22T02:48:59+00:00
| 0 | 1 |
---
language:
- es
library_name: fasttext
metrics:
- rouge
pipeline_tag: summarization
tags:
- summarization,
- text2text-generation,
---
| null |
Non_BioNLP
|
{"language": ["es"], "library_name": "fasttext", "metrics": ["rouge"], "pipeline_tag": "summarization", "tags": ["summarization,", "text2text-generation,"]}
|
task
|
[
"SUMMARIZATION"
] | 43,850 |
|
openai/whisper-medium
|
openai
|
automatic-speech-recognition
|
[
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"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",
"he",
"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",
"arxiv:2212.04356",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | 2022-09-26T06:52:52Z |
2024-02-29T10:57:42+00:00
| 439,588 | 235 |
---
language:
- en
- zh
- de
- es
- ru
- ko
- fr
- ja
- pt
- tr
- pl
- ca
- nl
- ar
- sv
- it
- id
- hi
- fi
- vi
- he
- uk
- el
- ms
- cs
- ro
- da
- hu
- ta
- false
- 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
model-index:
- name: whisper-medium
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: 2.9
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: 5.9
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: 53.87
name: Test WER
---
# Whisper
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours
of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need
for fine-tuning.
Whisper was proposed in the paper [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)
by Alec Radford et al from OpenAI. The original code repository can be found [here](https://github.com/openai/whisper).
**Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were
copied and pasted from the original model card.
## Model details
Whisper is a Transformer based encoder-decoder model, also referred to as a _sequence-to-sequence_ model.
It was trained on 680k hours of labelled speech data annotated using large-scale weak supervision.
The models were trained on either English-only data or multilingual data. The English-only models were trained
on the task of speech recognition. The multilingual models were trained on both speech recognition and speech
translation. For speech recognition, the model predicts transcriptions in the *same* language as the audio.
For speech translation, the model predicts transcriptions to a *different* language to the audio.
Whisper checkpoints come in five configurations of varying model sizes.
The smallest four are trained on either English-only or multilingual data.
The largest checkpoints are multilingual only. All ten of the pre-trained checkpoints
are available on the [Hugging Face Hub](https://huggingface.co/models?search=openai/whisper). The
checkpoints are summarised in the following table with links to the models on the Hub:
| Size | Parameters | English-only | Multilingual |
|----------|------------|------------------------------------------------------|-----------------------------------------------------|
| tiny | 39 M | [✓](https://huggingface.co/openai/whisper-tiny.en) | [✓](https://huggingface.co/openai/whisper-tiny) |
| base | 74 M | [✓](https://huggingface.co/openai/whisper-base.en) | [✓](https://huggingface.co/openai/whisper-base) |
| small | 244 M | [✓](https://huggingface.co/openai/whisper-small.en) | [✓](https://huggingface.co/openai/whisper-small) |
| medium | 769 M | [✓](https://huggingface.co/openai/whisper-medium.en) | [✓](https://huggingface.co/openai/whisper-medium) |
| large | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large) |
| large-v2 | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large-v2) |
# Usage
To transcribe audio samples, the model has to be used alongside a [`WhisperProcessor`](https://huggingface.co/docs/transformers/model_doc/whisper#transformers.WhisperProcessor).
The `WhisperProcessor` is used to:
1. Pre-process the audio inputs (converting them to log-Mel spectrograms for the model)
2. Post-process the model outputs (converting them from tokens to text)
The model is informed of which task to perform (transcription or translation) by passing the appropriate "context tokens". These context tokens
are a sequence of tokens that are given to the decoder at the start of the decoding process, and take the following order:
1. The transcription always starts with the `<|startoftranscript|>` token
2. The second token is the language token (e.g. `<|en|>` for English)
3. The third token is the "task token". It can take one of two values: `<|transcribe|>` for speech recognition or `<|translate|>` for speech translation
4. In addition, a `<|notimestamps|>` token is added if the model should not include timestamp prediction
Thus, a typical sequence of context tokens might look as follows:
```
<|startoftranscript|> <|en|> <|transcribe|> <|notimestamps|>
```
Which tells the model to decode in English, under the task of speech recognition, and not to predict timestamps.
These tokens can either be forced or un-forced. If they are forced, the model is made to predict each token at
each position. This allows one to control the output language and task for the Whisper model. If they are un-forced,
the Whisper model will automatically predict the output langauge and task itself.
The context tokens can be set accordingly:
```python
model.config.forced_decoder_ids = WhisperProcessor.get_decoder_prompt_ids(language="english", task="transcribe")
```
Which forces the model to predict in English under the task of speech recognition.
## Transcription
### English to English
In this example, the context tokens are 'unforced', meaning the model automatically predicts the output language
(English) and task (transcribe).
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium")
>>> model.config.forced_decoder_ids = None
>>> # load dummy dataset and read audio files
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> sample = ds[0]["audio"]
>>> input_features = processor(sample["array"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features
>>> # generate token ids
>>> predicted_ids = model.generate(input_features)
>>> # decode token ids to text
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
['<|startoftranscript|><|en|><|transcribe|><|notimestamps|> Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.<|endoftext|>']
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
[' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.']
```
The context tokens can be removed from the start of the transcription by setting `skip_special_tokens=True`.
### French to French
The following example demonstrates French to French transcription by setting the decoder ids appropriately.
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import Audio, load_dataset
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium")
>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language="french", task="transcribe")
>>> # load streaming dataset and read first audio sample
>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
>>> ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
>>> input_speech = next(iter(ds))["audio"]
>>> input_features = processor(input_speech["array"], sampling_rate=input_speech["sampling_rate"], return_tensors="pt").input_features
>>> # generate token ids
>>> predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)
>>> # decode token ids to text
>>> 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
Setting the task to "translate" forces the Whisper model to perform speech translation.
### French to English
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import Audio, load_dataset
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium")
>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language="french", task="translate")
>>> # load streaming dataset and read first audio sample
>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
>>> ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
>>> input_speech = next(iter(ds))["audio"]
>>> input_features = processor(input_speech["array"], sampling_rate=input_speech["sampling_rate"], return_tensors="pt").input_features
>>> # generate token ids
>>> predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)
>>> # decode token ids to text
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
[' A very interesting work, we will finally be given on this subject.']
```
## Evaluation
This code snippet shows how to evaluate Whisper Medium on [LibriSpeech test-clean](https://huggingface.co/datasets/librispeech_asr):
```python
>>> from datasets import load_dataset
>>> from transformers import WhisperForConditionalGeneration, WhisperProcessor
>>> import torch
>>> from evaluate import load
>>> librispeech_test_clean = load_dataset("librispeech_asr", "clean", split="test")
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium").to("cuda")
>>> def map_to_pred(batch):
>>> audio = batch["audio"]
>>> input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features
>>> batch["reference"] = processor.tokenizer._normalize(batch['text'])
>>>
>>> with torch.no_grad():
>>> predicted_ids = model.generate(input_features.to("cuda"))[0]
>>> transcription = processor.decode(predicted_ids)
>>> batch["prediction"] = processor.tokenizer._normalize(transcription)
>>> return batch
>>> result = librispeech_test_clean.map(map_to_pred)
>>> wer = load("wer")
>>> print(100 * wer.compute(references=result["reference"], predictions=result["prediction"]))
2.900409225488902
```
## Long-Form Transcription
The Whisper model is intrinsically designed to work on audio samples of up to 30s in duration. However, by using a chunking
algorithm, it can be used to transcribe audio samples of up to arbitrary length. This is possible through Transformers
[`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
method. Chunking is enabled by setting `chunk_length_s=30` when instantiating the pipeline. With chunking enabled, the pipeline
can be run with batched inference. It can also be extended to predict sequence level timestamps by passing `return_timestamps=True`:
```python
>>> import torch
>>> from transformers import pipeline
>>> from datasets import load_dataset
>>> device = "cuda:0" if torch.cuda.is_available() else "cpu"
>>> pipe = pipeline(
>>> "automatic-speech-recognition",
>>> model="openai/whisper-medium",
>>> chunk_length_s=30,
>>> device=device,
>>> )
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> sample = ds[0]["audio"]
>>> prediction = pipe(sample.copy(), batch_size=8)["text"]
" Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel."
>>> # we can also return timestamps for the predictions
>>> prediction = pipe(sample.copy(), batch_size=8, return_timestamps=True)["chunks"]
[{'text': ' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.',
'timestamp': (0.0, 5.44)}]
```
Refer to the blog post [ASR Chunking](https://huggingface.co/blog/asr-chunking) for more details on the chunking algorithm.
## Fine-Tuning
The pre-trained Whisper model demonstrates a strong ability to generalise to different datasets and domains. However,
its predictive capabilities can be improved further for certain languages and tasks through *fine-tuning*. The blog
post [Fine-Tune Whisper with 🤗 Transformers](https://huggingface.co/blog/fine-tune-whisper) provides a step-by-step
guide to fine-tuning the Whisper model with as little as 5 hours of labelled data.
### 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
```bibtex
@misc{radford2022whisper,
doi = {10.48550/ARXIV.2212.04356},
url = {https://arxiv.org/abs/2212.04356},
author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
title = {Robust Speech Recognition via Large-Scale Weak Supervision},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}
```
| null |
Non_BioNLP
|
# Whisper
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours
of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need
for fine-tuning.
Whisper was proposed in the paper [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)
by Alec Radford et al from OpenAI. The original code repository can be found [here](https://github.com/openai/whisper).
**Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were
copied and pasted from the original model card.
## Model details
Whisper is a Transformer based encoder-decoder model, also referred to as a _sequence-to-sequence_ model.
It was trained on 680k hours of labelled speech data annotated using large-scale weak supervision.
The models were trained on either English-only data or multilingual data. The English-only models were trained
on the task of speech recognition. The multilingual models were trained on both speech recognition and speech
translation. For speech recognition, the model predicts transcriptions in the *same* language as the audio.
For speech translation, the model predicts transcriptions to a *different* language to the audio.
Whisper checkpoints come in five configurations of varying model sizes.
The smallest four are trained on either English-only or multilingual data.
The largest checkpoints are multilingual only. All ten of the pre-trained checkpoints
are available on the [Hugging Face Hub](https://huggingface.co/models?search=openai/whisper). The
checkpoints are summarised in the following table with links to the models on the Hub:
| Size | Parameters | English-only | Multilingual |
|----------|------------|------------------------------------------------------|-----------------------------------------------------|
| tiny | 39 M | [✓](https://huggingface.co/openai/whisper-tiny.en) | [✓](https://huggingface.co/openai/whisper-tiny) |
| base | 74 M | [✓](https://huggingface.co/openai/whisper-base.en) | [✓](https://huggingface.co/openai/whisper-base) |
| small | 244 M | [✓](https://huggingface.co/openai/whisper-small.en) | [✓](https://huggingface.co/openai/whisper-small) |
| medium | 769 M | [✓](https://huggingface.co/openai/whisper-medium.en) | [✓](https://huggingface.co/openai/whisper-medium) |
| large | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large) |
| large-v2 | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large-v2) |
# Usage
To transcribe audio samples, the model has to be used alongside a [`WhisperProcessor`](https://huggingface.co/docs/transformers/model_doc/whisper#transformers.WhisperProcessor).
The `WhisperProcessor` is used to:
1. Pre-process the audio inputs (converting them to log-Mel spectrograms for the model)
2. Post-process the model outputs (converting them from tokens to text)
The model is informed of which task to perform (transcription or translation) by passing the appropriate "context tokens". These context tokens
are a sequence of tokens that are given to the decoder at the start of the decoding process, and take the following order:
1. The transcription always starts with the `<|startoftranscript|>` token
2. The second token is the language token (e.g. `<|en|>` for English)
3. The third token is the "task token". It can take one of two values: `<|transcribe|>` for speech recognition or `<|translate|>` for speech translation
4. In addition, a `<|notimestamps|>` token is added if the model should not include timestamp prediction
Thus, a typical sequence of context tokens might look as follows:
```
<|startoftranscript|> <|en|> <|transcribe|> <|notimestamps|>
```
Which tells the model to decode in English, under the task of speech recognition, and not to predict timestamps.
These tokens can either be forced or un-forced. If they are forced, the model is made to predict each token at
each position. This allows one to control the output language and task for the Whisper model. If they are un-forced,
the Whisper model will automatically predict the output langauge and task itself.
The context tokens can be set accordingly:
```python
model.config.forced_decoder_ids = WhisperProcessor.get_decoder_prompt_ids(language="english", task="transcribe")
```
Which forces the model to predict in English under the task of speech recognition.
## Transcription
### English to English
In this example, the context tokens are 'unforced', meaning the model automatically predicts the output language
(English) and task (transcribe).
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium")
>>> model.config.forced_decoder_ids = None
>>> # load dummy dataset and read audio files
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> sample = ds[0]["audio"]
>>> input_features = processor(sample["array"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features
>>> # generate token ids
>>> predicted_ids = model.generate(input_features)
>>> # decode token ids to text
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
['<|startoftranscript|><|en|><|transcribe|><|notimestamps|> Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.<|endoftext|>']
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
[' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.']
```
The context tokens can be removed from the start of the transcription by setting `skip_special_tokens=True`.
### French to French
The following example demonstrates French to French transcription by setting the decoder ids appropriately.
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import Audio, load_dataset
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium")
>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language="french", task="transcribe")
>>> # load streaming dataset and read first audio sample
>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
>>> ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
>>> input_speech = next(iter(ds))["audio"]
>>> input_features = processor(input_speech["array"], sampling_rate=input_speech["sampling_rate"], return_tensors="pt").input_features
>>> # generate token ids
>>> predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)
>>> # decode token ids to text
>>> 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
Setting the task to "translate" forces the Whisper model to perform speech translation.
### French to English
```python
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
>>> from datasets import Audio, load_dataset
>>> # load model and processor
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium")
>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language="french", task="translate")
>>> # load streaming dataset and read first audio sample
>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
>>> ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
>>> input_speech = next(iter(ds))["audio"]
>>> input_features = processor(input_speech["array"], sampling_rate=input_speech["sampling_rate"], return_tensors="pt").input_features
>>> # generate token ids
>>> predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)
>>> # decode token ids to text
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
[' A very interesting work, we will finally be given on this subject.']
```
## Evaluation
This code snippet shows how to evaluate Whisper Medium on [LibriSpeech test-clean](https://huggingface.co/datasets/librispeech_asr):
```python
>>> from datasets import load_dataset
>>> from transformers import WhisperForConditionalGeneration, WhisperProcessor
>>> import torch
>>> from evaluate import load
>>> librispeech_test_clean = load_dataset("librispeech_asr", "clean", split="test")
>>> processor = WhisperProcessor.from_pretrained("openai/whisper-medium")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium").to("cuda")
>>> def map_to_pred(batch):
>>> audio = batch["audio"]
>>> input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features
>>> batch["reference"] = processor.tokenizer._normalize(batch['text'])
>>>
>>> with torch.no_grad():
>>> predicted_ids = model.generate(input_features.to("cuda"))[0]
>>> transcription = processor.decode(predicted_ids)
>>> batch["prediction"] = processor.tokenizer._normalize(transcription)
>>> return batch
>>> result = librispeech_test_clean.map(map_to_pred)
>>> wer = load("wer")
>>> print(100 * wer.compute(references=result["reference"], predictions=result["prediction"]))
2.900409225488902
```
## Long-Form Transcription
The Whisper model is intrinsically designed to work on audio samples of up to 30s in duration. However, by using a chunking
algorithm, it can be used to transcribe audio samples of up to arbitrary length. This is possible through Transformers
[`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
method. Chunking is enabled by setting `chunk_length_s=30` when instantiating the pipeline. With chunking enabled, the pipeline
can be run with batched inference. It can also be extended to predict sequence level timestamps by passing `return_timestamps=True`:
```python
>>> import torch
>>> from transformers import pipeline
>>> from datasets import load_dataset
>>> device = "cuda:0" if torch.cuda.is_available() else "cpu"
>>> pipe = pipeline(
>>> "automatic-speech-recognition",
>>> model="openai/whisper-medium",
>>> chunk_length_s=30,
>>> device=device,
>>> )
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> sample = ds[0]["audio"]
>>> prediction = pipe(sample.copy(), batch_size=8)["text"]
" Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel."
>>> # we can also return timestamps for the predictions
>>> prediction = pipe(sample.copy(), batch_size=8, return_timestamps=True)["chunks"]
[{'text': ' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.',
'timestamp': (0.0, 5.44)}]
```
Refer to the blog post [ASR Chunking](https://huggingface.co/blog/asr-chunking) for more details on the chunking algorithm.
## Fine-Tuning
The pre-trained Whisper model demonstrates a strong ability to generalise to different datasets and domains. However,
its predictive capabilities can be improved further for certain languages and tasks through *fine-tuning*. The blog
post [Fine-Tune Whisper with 🤗 Transformers](https://huggingface.co/blog/fine-tune-whisper) provides a step-by-step
guide to fine-tuning the Whisper model with as little as 5 hours of labelled data.
### 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
```bibtex
@misc{radford2022whisper,
doi = {10.48550/ARXIV.2212.04356},
url = {https://arxiv.org/abs/2212.04356},
author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
title = {Robust Speech Recognition via Large-Scale Weak Supervision},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}
```
|
{"language": ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "tr", "pl", "ca", "nl", "ar", "sv", "it", "id", "hi", "fi", "vi", "he", "uk", "el", "ms", "cs", "ro", "da", "hu", "ta", false, "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"}], "model-index": [{"name": "whisper-medium", "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": 2.9, "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": 5.9, "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": 53.87, "name": "Test WER"}]}]}]}
|
task
|
[
"TRANSLATION"
] | 43,851 |
interneuronai/az-cerebras
|
interneuronai
| null |
[
"peft",
"safetensors",
"base_model:cerebras/Cerebras-GPT-111M",
"base_model:adapter:cerebras/Cerebras-GPT-111M",
"region:us"
] | 2024-03-09T12:56:30Z |
2024-03-09T18:11:30+00:00
| 1 | 0 |
---
base_model: cerebras/Cerebras-GPT-111M
library_name: peft
---
Model Details
Original Model: cerebras/Cerebras-GPT-111M
Fine-Tuned For: Azerbaijani language understanding and generation
Dataset Used: Azerbaijani translation of the Stanford Alpaca dataset
Fine-Tuning Method: Self-instruct method
This model, is part of the ["project/Barbarossa"](https://github.com/Alas-Development-Center/project-barbarossa) initiative, aimed at enhancing natural language processing capabilities for the Azerbaijani language. By fine-tuning this model on the Azerbaijani translation of the Stanford Alpaca dataset using the self-instruct method, we've made significant strides in improving AI's understanding and generation of Azerbaijani text.
__Our primary objective with this model is to offer insights into the feasibility and outcomes of fine-tuning large language models (LLMs) for the Azerbaijani language. The fine-tuning process was undertaken with limited resources, providing valuable learnings rather than creating a model ready for production use. Therefore, we recommend treating this model as a reference or a guide to understanding the potential and challenges involved in fine-tuning LLMs for specific languages. It serves as a foundational step towards further research and development rather than a direct solution for production environments.__
This project is a proud product of the [Alas Development Center (ADC)](https://az.linkedin.com/company/alas-development-center?trk=ppro_cprof). We are thrilled to offer these finely-tuned large language models to the public, free of charge.
How to use?
```
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, pipeline
model_path = "alasdevcenter/az-cerebras"
model = AutoModelForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
instruction = "Təbiətin qorunması "
formatted_prompt = f"""Aşağıda daha çox kontekst təmin edən təlimat var. Sorğunu adekvat şəkildə tamamlayan cavab yazın.
### Təlimat:
{instruction}
### Cavab:
"""
result = pipe(formatted_prompt)
print(result[0]['generated_text'])
```
| null |
Non_BioNLP
|
Model Details
Original Model: cerebras/Cerebras-GPT-111M
Fine-Tuned For: Azerbaijani language understanding and generation
Dataset Used: Azerbaijani translation of the Stanford Alpaca dataset
Fine-Tuning Method: Self-instruct method
This model, is part of the ["project/Barbarossa"](https://github.com/Alas-Development-Center/project-barbarossa) initiative, aimed at enhancing natural language processing capabilities for the Azerbaijani language. By fine-tuning this model on the Azerbaijani translation of the Stanford Alpaca dataset using the self-instruct method, we've made significant strides in improving AI's understanding and generation of Azerbaijani text.
__Our primary objective with this model is to offer insights into the feasibility and outcomes of fine-tuning large language models (LLMs) for the Azerbaijani language. The fine-tuning process was undertaken with limited resources, providing valuable learnings rather than creating a model ready for production use. Therefore, we recommend treating this model as a reference or a guide to understanding the potential and challenges involved in fine-tuning LLMs for specific languages. It serves as a foundational step towards further research and development rather than a direct solution for production environments.__
This project is a proud product of the [Alas Development Center (ADC)](https://az.linkedin.com/company/alas-development-center?trk=ppro_cprof). We are thrilled to offer these finely-tuned large language models to the public, free of charge.
How to use?
```
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, pipeline
model_path = "alasdevcenter/az-cerebras"
model = AutoModelForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
instruction = "Təbiətin qorunması "
formatted_prompt = f"""Aşağıda daha çox kontekst təmin edən təlimat var. Sorğunu adekvat şəkildə tamamlayan cavab yazın.
### Təlimat:
{instruction}
### Cavab:
"""
result = pipe(formatted_prompt)
print(result[0]['generated_text'])
```
|
{"base_model": "cerebras/Cerebras-GPT-111M", "library_name": "peft"}
|
task
|
[
"TRANSLATION"
] | 43,852 |
HasinMDG/multilingual-mpnet-IPTC-L1-v3
|
HasinMDG
|
text-classification
|
[
"sentence-transformers",
"pytorch",
"xlm-roberta",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 2023-05-24T12:12:57Z |
2023-05-24T12:13:25+00:00
| 8 | 0 |
---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# HasinMDG/multilingual-mpnet-IPTC-L1-v3
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("HasinMDG/multilingual-mpnet-IPTC-L1-v3")
# 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
|
# HasinMDG/multilingual-mpnet-IPTC-L1-v3
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("HasinMDG/multilingual-mpnet-IPTC-L1-v3")
# 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"
] | 43,853 |
Helsinki-NLP/opus-mt-tvl-fi
|
Helsinki-NLP
|
translation
|
[
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"tvl",
"fi",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2023-08-16T12:07:46+00:00
| 38 | 0 |
---
license: apache-2.0
tags:
- translation
---
### opus-mt-tvl-fi
* source languages: tvl
* target languages: fi
* OPUS readme: [tvl-fi](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/tvl-fi/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fi/opus-2020-01-16.zip)
* test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fi/opus-2020-01-16.test.txt)
* test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fi/opus-2020-01-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.tvl.fi | 22.0 | 0.439 |
| null |
Non_BioNLP
|
### opus-mt-tvl-fi
* source languages: tvl
* target languages: fi
* OPUS readme: [tvl-fi](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/tvl-fi/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fi/opus-2020-01-16.zip)
* test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fi/opus-2020-01-16.test.txt)
* test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fi/opus-2020-01-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.tvl.fi | 22.0 | 0.439 |
|
{"license": "apache-2.0", "tags": ["translation"]}
|
task
|
[
"TRANSLATION"
] | 43,854 |
TransferGraph/Jeevesh8_feather_berts_96-finetuned-lora-tweet_eval_irony
|
TransferGraph
|
text-classification
|
[
"peft",
"safetensors",
"parquet",
"text-classification",
"dataset:tweet_eval",
"base_model:Jeevesh8/feather_berts_96",
"base_model:adapter:Jeevesh8/feather_berts_96",
"model-index",
"region:us"
] | 2024-02-27T17:20:58Z |
2024-02-29T13:33:36+00:00
| 0 | 0 |
---
base_model: Jeevesh8/feather_berts_96
datasets:
- tweet_eval
library_name: peft
metrics:
- accuracy
tags:
- parquet
- text-classification
model-index:
- name: Jeevesh8_feather_berts_96-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: 0.6743455497382199
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. -->
# Jeevesh8_feather_berts_96-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of [Jeevesh8/feather_berts_96](https://huggingface.co/Jeevesh8/feather_berts_96) on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- accuracy: 0.6743
## 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 |
|:--------:|:----------:|:-----:|
| 0.5162 | None | 0 |
| 0.5707 | 0.6876 | 0 |
| 0.6178 | 0.6541 | 1 |
| 0.6408 | 0.6166 | 2 |
| 0.6681 | 0.5880 | 3 |
| 0.6670 | 0.5604 | 4 |
| 0.6660 | 0.5459 | 5 |
| 0.6691 | 0.5308 | 6 |
| 0.6743 | 0.5190 | 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. -->
# Jeevesh8_feather_berts_96-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of [Jeevesh8/feather_berts_96](https://huggingface.co/Jeevesh8/feather_berts_96) on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- accuracy: 0.6743
## 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 |
|:--------:|:----------:|:-----:|
| 0.5162 | None | 0 |
| 0.5707 | 0.6876 | 0 |
| 0.6178 | 0.6541 | 1 |
| 0.6408 | 0.6166 | 2 |
| 0.6681 | 0.5880 | 3 |
| 0.6670 | 0.5604 | 4 |
| 0.6660 | 0.5459 | 5 |
| 0.6691 | 0.5308 | 6 |
| 0.6743 | 0.5190 | 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": "Jeevesh8/feather_berts_96", "datasets": ["tweet_eval"], "library_name": "peft", "metrics": ["accuracy"], "tags": ["parquet", "text-classification"], "model-index": [{"name": "Jeevesh8_feather_berts_96-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": 0.6743455497382199, "name": "accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,855 |
aks1s/01volt-1
|
aks1s
|
text-generation
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"merges",
"conversational",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Hermes-2-Pro-Llama-3-8B",
"base_model:finetune:NousResearch/Hermes-2-Pro-Llama-3-8B",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2024-07-15T08:54:47Z |
2024-07-15T08:58:03+00:00
| 6 | 0 |
---
base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
datasets:
- teknium/OpenHermes-2.5
language:
- en
license: apache-2.0
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
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
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"], "license": "apache-2.0", "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"
] | 43,856 |
martimfasantos/dpo-sum-10p-shuff-5e-8-full-from-sft-tiny
|
martimfasantos
|
summarization
|
[
"safetensors",
"llama",
"summarization",
"generated_from_trainer",
"base_model:martimfasantos/TinyLlama-1.1B-Sum-SFT",
"base_model:finetune:martimfasantos/TinyLlama-1.1B-Sum-SFT",
"license:apache-2.0",
"region:us"
] | 2024-08-14T00:42:48Z |
2024-08-14T00:44:07+00:00
| 12 | 0 |
---
base_model: martimfasantos/sft-sum-chosen-10lp-shuff-full-tiny_same_params
license: apache-2.0
tags:
- summarization
- generated_from_trainer
model-index:
- name: dpo-sum-10p-shuff-5e-8-full-from-sft-tiny
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. -->
# dpo-sum-10p-shuff-5e-8-full-from-sft-tiny
This model is a fine-tuned version of [martimfasantos/sft-sum-chosen-10lp-shuff-full-tiny_same_params](https://huggingface.co/martimfasantos/sft-sum-chosen-10lp-shuff-full-tiny_same_params) on the openai/summarize_from_feedback 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-08
- train_batch_size: 1
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+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. -->
# dpo-sum-10p-shuff-5e-8-full-from-sft-tiny
This model is a fine-tuned version of [martimfasantos/sft-sum-chosen-10lp-shuff-full-tiny_same_params](https://huggingface.co/martimfasantos/sft-sum-chosen-10lp-shuff-full-tiny_same_params) on the openai/summarize_from_feedback 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-08
- train_batch_size: 1
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
{"base_model": "martimfasantos/sft-sum-chosen-10lp-shuff-full-tiny_same_params", "license": "apache-2.0", "tags": ["summarization", "generated_from_trainer"], "model-index": [{"name": "dpo-sum-10p-shuff-5e-8-full-from-sft-tiny", "results": []}]}
|
task
|
[
"SUMMARIZATION"
] | 43,857 |
mrapacz/interlinear-pl-greta-t-w-t-diacritics-bh
|
mrapacz
|
text2text-generation
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"pl",
"dataset:mrapacz/greek-interlinear-translations",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2025-02-08T12:26:03Z |
2025-02-21T21:33:13+00:00
| 11 | 0 |
---
base_model:
- GreTa
datasets:
- mrapacz/greek-interlinear-translations
language:
- pl
library_name: transformers
license: cc-by-sa-4.0
metrics:
- bleu
---
# Model Card for Ancient Greek to Polish Interlinear Translation Model
This model performs interlinear translation from Ancient Greek to Polish, 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:** MT5ForConditionalGeneration
- **Base Model:** GreTa
- **Tokenizer:** GreTa
- **Language(s):** Ancient Greek (source) → Polish (target)
- **License:** CC BY-NC-SA 4.0
- **Tag Set:** BH (Bible Hub)
- **Text Preprocessing:** Diacritics
- **Morphological Encoding:** t-w-t (tags-within-text)
### Model Performance
- **BLEU Score:** 0.49
- **SemScore:** 0.51
### Model Sources
- **Repository:** https://github.com/mrapacz/loreslm-interlinear-translation
- **Paper:** https://aclanthology.org/2025.loreslm-1.11/
## Usage Example
```python
>>> from transformers import AutoModelForSeq2SeqLM, T5TokenizerFast
>>> text_blocks = ['Λέγει', 'αὐτῷ', 'ὁ', 'Ἰησοῦς', 'Ἔγειρε', 'ἆρον', 'τὸν', 'κράβαττόν', 'σου', 'καὶ', 'περιπάτει']
>>> tag_blocks = ['V-PIA-3S', 'PPro-DM3S', 'Art-NMS', 'N-NMS', 'V-PMA-2S', 'V-AMA-2S', 'Art-AMS', 'N-AMS', 'PPro-G2S', 'Conj', 'V-PMA-2S']
>>> combined_text = []
>>> for text, tag in zip(text_blocks, tag_blocks):
... combined_text.append(f"{text} <extra_id_1>{tag}")
>>> formatted_text = " <extra_id_0> ".join(combined_text)
>>> tokenizer = T5TokenizerFast.from_pretrained("mrapacz/interlinear-pl-greta-t-w-t-diacritics-bh")
>>> inputs = tokenizer(
text=formatted_text,
return_tensors="pt"
)
>>> model = T5ForConditionalGeneration.from_pretrained("mrapacz/interlinear-pl-greta-t-w-t-diacritics-bh")
>>> outputs = model.generate(
**inputs,
max_new_tokens=100,
early_stopping=True,
)
>>> tokenizer.decode(outputs[0], skip_special_tokens=True)
'- jezus twojego twojego twojego twojego twojego twojego twojego twojego twojego twojego twojego twojego twojego '
```
## 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 |
TBD
|
# Model Card for Ancient Greek to Polish Interlinear Translation Model
This model performs interlinear translation from Ancient Greek to Polish, 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:** MT5ForConditionalGeneration
- **Base Model:** GreTa
- **Tokenizer:** GreTa
- **Language(s):** Ancient Greek (source) → Polish (target)
- **License:** CC BY-NC-SA 4.0
- **Tag Set:** BH (Bible Hub)
- **Text Preprocessing:** Diacritics
- **Morphological Encoding:** t-w-t (tags-within-text)
### Model Performance
- **BLEU Score:** 0.49
- **SemScore:** 0.51
### Model Sources
- **Repository:** https://github.com/mrapacz/loreslm-interlinear-translation
- **Paper:** https://aclanthology.org/2025.loreslm-1.11/
## Usage Example
```python
>>> from transformers import AutoModelForSeq2SeqLM, T5TokenizerFast
>>> text_blocks = ['Λέγει', 'αὐτῷ', 'ὁ', 'Ἰησοῦς', 'Ἔγειρε', 'ἆρον', 'τὸν', 'κράβαττόν', 'σου', 'καὶ', 'περιπάτει']
>>> tag_blocks = ['V-PIA-3S', 'PPro-DM3S', 'Art-NMS', 'N-NMS', 'V-PMA-2S', 'V-AMA-2S', 'Art-AMS', 'N-AMS', 'PPro-G2S', 'Conj', 'V-PMA-2S']
>>> combined_text = []
>>> for text, tag in zip(text_blocks, tag_blocks):
... combined_text.append(f"{text} <extra_id_1>{tag}")
>>> formatted_text = " <extra_id_0> ".join(combined_text)
>>> tokenizer = T5TokenizerFast.from_pretrained("mrapacz/interlinear-pl-greta-t-w-t-diacritics-bh")
>>> inputs = tokenizer(
text=formatted_text,
return_tensors="pt"
)
>>> model = T5ForConditionalGeneration.from_pretrained("mrapacz/interlinear-pl-greta-t-w-t-diacritics-bh")
>>> outputs = model.generate(
**inputs,
max_new_tokens=100,
early_stopping=True,
)
>>> tokenizer.decode(outputs[0], skip_special_tokens=True)
'- jezus twojego twojego twojego twojego twojego twojego twojego twojego twojego twojego twojego twojego twojego '
```
## 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": ["GreTa"], "datasets": ["mrapacz/greek-interlinear-translations"], "language": ["pl"], "library_name": "transformers", "license": "cc-by-sa-4.0", "metrics": ["bleu"]}
|
task
|
[
"TRANSLATION"
] | 43,858 |
sudaheng/distilbert-base-uncased-finetuned-emotion
|
sudaheng
|
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"
] | 2024-06-12T09:10:54Z |
2024-06-12T14:48:09+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
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.933
name: Accuracy
- type: f1
value: 0.9329436383436902
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: 0.1677
- Accuracy: 0.933
- F1: 0.9329
## 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8068 | 1.0 | 250 | 0.2801 | 0.919 | 0.9186 |
| 0.2195 | 2.0 | 500 | 0.1871 | 0.9315 | 0.9321 |
| 0.148 | 3.0 | 750 | 0.1677 | 0.933 | 0.9329 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0
- 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. -->
# 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: 0.1677
- Accuracy: 0.933
- F1: 0.9329
## 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8068 | 1.0 | 250 | 0.2801 | 0.919 | 0.9186 |
| 0.2195 | 2.0 | 500 | 0.1871 | 0.9315 | 0.9321 |
| 0.148 | 3.0 | 750 | 0.1677 | 0.933 | 0.9329 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0
- Datasets 2.19.2
- 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": 0.933, "name": "Accuracy"}, {"type": "f1", "value": 0.9329436383436902, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,859 |
DmitriyVasiliev/autotrain-mbart-rua-par-and-sent-55389129134
|
DmitriyVasiliev
|
summarization
|
[
"transformers",
"pytorch",
"mbart",
"text2text-generation",
"autotrain",
"summarization",
"unk",
"dataset:DmitriyVasiliev/autotrain-data-mbart-rua-par-and-sent",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-05-04T12:22:24Z |
2023-05-04T12:35:42+00:00
| 24 | 0 |
---
datasets:
- DmitriyVasiliev/autotrain-data-mbart-rua-par-and-sent
language:
- unk
tags:
- autotrain
- summarization
widget:
- text: I love AutoTrain 🤗
co2_eq_emissions:
emissions: 5.124794195879908
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 55389129134
- CO2 Emissions (in grams): 5.1248
## Validation Metrics
- Loss: 0.777
- Rouge1: 8.583
- Rouge2: 2.417
- RougeL: 8.622
- RougeLsum: 8.558
- Gen Len: 21.878
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/DmitriyVasiliev/autotrain-mbart-rua-par-and-sent-55389129134
```
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 55389129134
- CO2 Emissions (in grams): 5.1248
## Validation Metrics
- Loss: 0.777
- Rouge1: 8.583
- Rouge2: 2.417
- RougeL: 8.622
- RougeLsum: 8.558
- Gen Len: 21.878
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/DmitriyVasiliev/autotrain-mbart-rua-par-and-sent-55389129134
```
|
{"datasets": ["DmitriyVasiliev/autotrain-data-mbart-rua-par-and-sent"], "language": ["unk"], "tags": ["autotrain", "summarization"], "widget": [{"text": "I love AutoTrain 🤗"}], "co2_eq_emissions": {"emissions": 5.124794195879908}}
|
task
|
[
"SUMMARIZATION"
] | 43,860 |
gokuls/hBERTv2_new_pretrain_48_KD_mrpc
|
gokuls
|
text-classification
|
[
"transformers",
"pytorch",
"tensorboard",
"hybridbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-06-14T17:17:02Z |
2023-06-14T17:24:01+00:00
| 8 | 0 |
---
datasets:
- glue
language:
- en
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: hBERTv2_new_pretrain_48_KD_mrpc
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE MRPC
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- type: accuracy
value: 0.696078431372549
name: Accuracy
- type: f1
value: 0.8074534161490682
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. -->
# hBERTv2_new_pretrain_48_KD_mrpc
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48_KD](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48_KD) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5941
- Accuracy: 0.6961
- F1: 0.8075
- Combined Score: 0.7518
## 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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6497 | 1.0 | 29 | 0.5941 | 0.6961 | 0.8075 | 0.7518 |
| 0.6083 | 2.0 | 58 | 0.6215 | 0.6544 | 0.7197 | 0.6870 |
| 0.5781 | 3.0 | 87 | 0.6071 | 0.6838 | 0.8122 | 0.7480 |
| 0.5073 | 4.0 | 116 | 0.6257 | 0.7132 | 0.8047 | 0.7590 |
| 0.4077 | 5.0 | 145 | 0.7379 | 0.6373 | 0.7329 | 0.6851 |
| 0.2908 | 6.0 | 174 | 0.9998 | 0.6422 | 0.7286 | 0.6854 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- 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. -->
# hBERTv2_new_pretrain_48_KD_mrpc
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48_KD](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48_KD) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5941
- Accuracy: 0.6961
- F1: 0.8075
- Combined Score: 0.7518
## 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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6497 | 1.0 | 29 | 0.5941 | 0.6961 | 0.8075 | 0.7518 |
| 0.6083 | 2.0 | 58 | 0.6215 | 0.6544 | 0.7197 | 0.6870 |
| 0.5781 | 3.0 | 87 | 0.6071 | 0.6838 | 0.8122 | 0.7480 |
| 0.5073 | 4.0 | 116 | 0.6257 | 0.7132 | 0.8047 | 0.7590 |
| 0.4077 | 5.0 | 145 | 0.7379 | 0.6373 | 0.7329 | 0.6851 |
| 0.2908 | 6.0 | 174 | 0.9998 | 0.6422 | 0.7286 | 0.6854 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
|
{"datasets": ["glue"], "language": ["en"], "metrics": ["accuracy", "f1"], "tags": ["generated_from_trainer"], "model-index": [{"name": "hBERTv2_new_pretrain_48_KD_mrpc", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE MRPC", "type": "glue", "config": "mrpc", "split": "validation", "args": "mrpc"}, "metrics": [{"type": "accuracy", "value": 0.696078431372549, "name": "Accuracy"}, {"type": "f1", "value": 0.8074534161490682, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,861 |
mrcoombes/distilbert-wikipedia-pokemon
|
mrcoombes
|
text-classification
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-06-05T15:07:20Z |
2022-06-05T15:28:03+00:00
| 12 | 0 |
---
{}
---
DistilBERT pokemon model (uncased)
This model is a distilled version of the BERT base model. It was introduced in this paper. The code for the distillation process can be found here. This model is uncased: it does not make a difference between english and English.
Model description
DistilBERT Wikipedia Pokemon model has been fine tuned for sequence classification using data from the notes field of these wikipedia tables. [such as this one](https://en.wikipedia.org/wiki/List_of_generation_III_Pok%C3%A9mon).
Given a pokedex entry as input, the model will return the most likely pokemon-type of the pokemon being described.
--
DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained with three objectives:
Distillation loss: the model was trained to return the same probabilities as the BERT base model.
Masked language modeling (MLM): this is part of the original training loss of the BERT base model. When taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence.
Cosine embedding loss: the model was also trained to generate hidden states as close as possible as the BERT base model.
This way, the model learns the same inner representation of the English language than its teacher model, while being faster for inference or downstream tasks.
Intended uses & limitations
Text Classification.
How to use
You can use this model directly with a pipeline for masked language modeling:
from transformers import pipeline
classifier = pipeline('text-classification', model='mrcoombes/distilbert-wikipedia-pokemon')
classifier("This pokemon likes to attend aquatic parties on midnight rooftops. Their best friend is a dolphin.")
Metrics:
Accuracy 47%.
Limitations, Next Steps and Feedback:
This model could be improved by using over-sampling and under-sampling to reduce class imbalances. The accuracy of a dragon-type pokemon is lower than the accuracy of more well-reprepresented classes within the data. However, works well for well-represented classes.
Happy Classifying 🤗
| null |
Non_BioNLP
|
DistilBERT pokemon model (uncased)
This model is a distilled version of the BERT base model. It was introduced in this paper. The code for the distillation process can be found here. This model is uncased: it does not make a difference between english and English.
Model description
DistilBERT Wikipedia Pokemon model has been fine tuned for sequence classification using data from the notes field of these wikipedia tables. [such as this one](https://en.wikipedia.org/wiki/List_of_generation_III_Pok%C3%A9mon).
Given a pokedex entry as input, the model will return the most likely pokemon-type of the pokemon being described.
--
DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained with three objectives:
Distillation loss: the model was trained to return the same probabilities as the BERT base model.
Masked language modeling (MLM): this is part of the original training loss of the BERT base model. When taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence.
Cosine embedding loss: the model was also trained to generate hidden states as close as possible as the BERT base model.
This way, the model learns the same inner representation of the English language than its teacher model, while being faster for inference or downstream tasks.
Intended uses & limitations
Text Classification.
How to use
You can use this model directly with a pipeline for masked language modeling:
from transformers import pipeline
classifier = pipeline('text-classification', model='mrcoombes/distilbert-wikipedia-pokemon')
classifier("This pokemon likes to attend aquatic parties on midnight rooftops. Their best friend is a dolphin.")
Metrics:
Accuracy 47%.
Limitations, Next Steps and Feedback:
This model could be improved by using over-sampling and under-sampling to reduce class imbalances. The accuracy of a dragon-type pokemon is lower than the accuracy of more well-reprepresented classes within the data. However, works well for well-represented classes.
Happy Classifying 🤗
|
{}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,862 |
sackoh/gemma-2-27b-it
|
sackoh
|
text-generation
|
[
"transformers",
"safetensors",
"gemma2",
"text-generation",
"conversational",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:2110.08193",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:1804.06876",
"arxiv:2103.03874",
"arxiv:2304.06364",
"arxiv:2206.04615",
"arxiv:2203.09509",
"base_model:google/gemma-2-27b",
"base_model:finetune:google/gemma-2-27b",
"license:gemma",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2025-03-02T09:54:47Z |
2025-03-02T10:14:58+00:00
| 353 | 0 |
---
base_model: google/gemma-2-27b
library_name: transformers
license: gemma
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: To access Gemma 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
---
# Gemma 2 model card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
**Resources and Technical Documentation**:
* [Responsible Generative AI Toolkit][rai-toolkit]
* [Gemma on Kaggle][kaggle-gemma]
* [Gemma on Vertex Model Garden][vertex-mg-gemma]
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2-27b-it)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights for both pre-trained variants and instruction-tuned variants.
Gemma models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Usage
Below we share some code snippets on how to get quickly started with running the model. First, install the Transformers library with:
```sh
pip install -U transformers
```
Then, copy the snippet from the section that is relevant for your usecase.
#### Running with the `pipeline` API
```python
import torch
from transformers import pipeline
pipe = pipeline(
"text-generation",
model="google/gemma-2-27b-it",
model_kwargs={"torch_dtype": torch.bfloat16},
device="cuda", # replace with "mps" to run on a Mac device
)
messages = [
{"role": "user", "content": "Who are you? Please, answer in pirate-speak."},
]
outputs = pipe(messages, max_new_tokens=256)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)
# Ahoy, matey! I be Gemma, a digital scallywag, a language-slingin' parrot of the digital seas. I be here to help ye with yer wordy woes, answer yer questions, and spin ye yarns of the digital world. So, what be yer pleasure, eh? 🦜
```
#### Running the model on a single / multi GPU
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-27b-it",
device_map="auto",
torch_dtype=torch.bfloat16,
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=32)
print(tokenizer.decode(outputs[0]))
```
You can ensure the correct chat template is applied by using `tokenizer.apply_chat_template` as follows:
```python
messages = [
{"role": "user", "content": "Write me a poem about Machine Learning."},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))
```
<a name="precisions"></a>
#### Running the model on a GPU using different precisions
The native weights of this model were exported in `bfloat16` precision.
You can also use `float32` if you skip the dtype, but no precision increase will occur (model weights will just be upcasted to `float32`). See examples below.
* _Upcasting to `torch.float32`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-27b-it",
device_map="auto",
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=32)
print(tokenizer.decode(outputs[0]))
```
#### Running the model through a CLI
The [local-gemma](https://github.com/huggingface/local-gemma) repository contains a lightweight wrapper around Transformers
for running Gemma 2 through a command line interface, or CLI. Follow the [installation instructions](https://github.com/huggingface/local-gemma#cli-usage)
for getting started, then launch the CLI through the following command:
```shell
local-gemma --model 27b --preset speed
```
#### Quantized Versions through `bitsandbytes`
<details>
<summary>
Using 8-bit precision (int8)
</summary>
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-27b-it",
quantization_config=quantization_config,
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=32)
print(tokenizer.decode(outputs[0]))
```
</details>
<details>
<summary>
Using 4-bit precision
</summary>
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-27b-it",
quantization_config=quantization_config,
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=32)
print(tokenizer.decode(outputs[0]))
```
</details>
#### Advanced Usage
<details>
<summary>
Torch compile
</summary>
[Torch compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) is a method for speeding-up the
inference of PyTorch modules. The Gemma-2 model can be run up to 6x faster by leveraging torch compile.
Note that two warm-up steps are required before the full inference speed is realised:
```python
import os
os.environ["TOKENIZERS_PARALLELISM"] = "false"
from transformers import AutoTokenizer, Gemma2ForCausalLM
from transformers.cache_utils import HybridCache
import torch
torch.set_float32_matmul_precision("high")
# load the model + tokenizer
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = Gemma2ForCausalLM.from_pretrained("google/gemma-2-27b-it", torch_dtype=torch.bfloat16)
model.to("cuda")
# apply the torch compile transformation
model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True)
# pre-process inputs
input_text = "The theory of special relativity states "
model_inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
prompt_length = model_inputs.input_ids.shape[1]
# set-up k/v cache
past_key_values = HybridCache(
config=model.config,
max_batch_size=1,
max_cache_len=model.config.max_position_embeddings,
device=model.device,
dtype=model.dtype
)
# enable passing kv cache to generate
model._supports_cache_class = True
model.generation_config.cache_implementation = None
# two warm-up steps
for idx in range(2):
outputs = model.generate(**model_inputs, past_key_values=past_key_values, do_sample=True, temperature=1.0, max_new_tokens=128)
past_key_values.reset()
# fast run
outputs = model.generate(**model_inputs, past_key_values=past_key_values, do_sample=True, temperature=1.0, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
For more details, refer to the [Transformers documentation](https://huggingface.co/docs/transformers/main/en/llm_optims?static-kv=basic+usage%3A+generation_config).
</details>
### Chat Template
The instruction-tuned models use a chat template that must be adhered to for conversational use.
The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.
Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:
```py
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model_id = "google/gemma-2-27b-it"
dtype = torch.bfloat16
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="cuda",
torch_dtype=dtype,
)
chat = [
{ "role": "user", "content": "Write a hello world program" },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
```
At this point, the prompt contains the following text:
```
<bos><start_of_turn>user
Write a hello world program<end_of_turn>
<start_of_turn>model
```
As you can see, each turn is preceded by a `<start_of_turn>` delimiter and then the role of the entity
(either `user`, for content supplied by the user, or `model` for LLM responses). Turns finish with
the `<end_of_turn>` token.
You can follow this format to build the prompt manually, if you need to do it without the tokenizer's
chat template.
After the prompt is ready, generation can be performed like this:
```py
inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150)
print(tokenizer.decode(outputs[0]))
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
### Citation
```none
@article{gemma_2024,
title={Gemma},
url={https://www.kaggle.com/m/3301},
DOI={10.34740/KAGGLE/M/3301},
publisher={Kaggle},
author={Gemma Team},
year={2024}
}
```
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 13 trillion tokens and the 9B model was trained with 8 trillion tokens.
Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content.
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safety in line with
[our policies][safety-policies].
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)][tpu] hardware (TPUv5p).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably][sustainability].
### Software
Training was done using [JAX][jax] and [ML Pathways][ml-pathways].
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models][foundation-models], including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models][gemini-2-paper]; "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | Gemma PT 9B | Gemma PT 27B |
| ------------------------------ | ------------- | ----------- | ------------ |
| [MMLU][mmlu] | 5-shot, top-1 | 71.3 | 75.2 |
| [HellaSwag][hellaswag] | 10-shot | 81.9 | 86.4 |
| [PIQA][piqa] | 0-shot | 81.7 | 83.2 |
| [SocialIQA][socialiqa] | 0-shot | 53.4 | 53.7 |
| [BoolQ][boolq] | 0-shot | 84.2 | 84.8 |
| [WinoGrande][winogrande] | partial score | 80.6 | 83.7 |
| [ARC-e][arc] | 0-shot | 88.0 | 88.6 |
| [ARC-c][arc] | 25-shot | 68.4 | 71.4 |
| [TriviaQA][triviaqa] | 5-shot | 76.6 | 83.7 |
| [Natural Questions][naturalq] | 5-shot | 29.2 | 34.5 |
| [HumanEval][humaneval] | pass@1 | 40.2 | 51.8 |
| [MBPP][mbpp] | 3-shot | 52.4 | 62.6 |
| [GSM8K][gsm8k] | 5-shot, maj@1 | 68.6 | 74.0 |
| [MATH][math] | 4-shot | 36.6 | 42.3 |
| [AGIEval][agieval] | 3-5-shot | 52.8 | 55.1 |
| [BIG-Bench][big-bench] | 3-shot, CoT | 68.2 | 74.9 |
| ------------------------------ | ------------- | ----------- | ------------ |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### 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:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias][winobias] and [BBQ Dataset][bbq].
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The results of ethics and safety evaluations are within acceptable thresholds
for meeting [internal policies][safety-policies] for categories such as child
safety, content safety, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well-known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
#### Gemma 2.0
| Benchmark | Metric | Gemma 2 IT 9B | Gemma 2 IT 27B |
| ------------------------ | ------------- | --------------- | ---------------- |
| [RealToxicity][realtox] | average | 8.25 | 8.84 |
| [CrowS-Pairs][crows] | top-1 | 37.47 | 36.67 |
| [BBQ Ambig][bbq] | 1-shot, top-1 | 88.58 | 85.99 |
| [BBQ Disambig][bbq] | top-1 | 82.67 | 86.94 |
| [Winogender][winogender] | top-1 | 79.17 | 77.22 |
| [TruthfulQA][truthfulqa] | | 50.27 | 51.60 |
| [Winobias 1_2][winobias] | | 78.09 | 81.94 |
| [Winobias 2_2][winobias] | | 95.32 | 97.22 |
| [Toxigen][toxigen] | | 39.30 | 38.42 |
| ------------------------ | ------------- | --------------- | ---------------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) 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.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs 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.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world 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
* LLMs 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][rai-toolkit].
* 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 LLM 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][prohibited-use].
* Privacy violations: Models were trained on data filtered for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
[rai-toolkit]: https://ai.google.dev/responsible
[kaggle-gemma]: https://www.kaggle.com/models/google/gemma-2
[terms]: https://ai.google.dev/gemma/terms
[vertex-mg-gemma]: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335
[sensitive-info]: https://cloud.google.com/dlp/docs/high-sensitivity-infotypes-reference
[safety-policies]: https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11
[prohibited-use]: https://ai.google.dev/gemma/prohibited_use_policy
[tpu]: https://cloud.google.com/tpu/docs/intro-to-tpu
[sustainability]: https://sustainability.google/operating-sustainably/
[jax]: https://github.com/google/jax
[ml-pathways]: https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/
[sustainability]: https://sustainability.google/operating-sustainably/
[foundation-models]: https://ai.google/discover/foundation-models/
[gemini-2-paper]: https://goo.gle/gemma2report
[mmlu]: https://arxiv.org/abs/2009.03300
[hellaswag]: https://arxiv.org/abs/1905.07830
[piqa]: https://arxiv.org/abs/1911.11641
[socialiqa]: https://arxiv.org/abs/1904.09728
[boolq]: https://arxiv.org/abs/1905.10044
[winogrande]: https://arxiv.org/abs/1907.10641
[commonsenseqa]: https://arxiv.org/abs/1811.00937
[openbookqa]: https://arxiv.org/abs/1809.02789
[arc]: https://arxiv.org/abs/1911.01547
[triviaqa]: https://arxiv.org/abs/1705.03551
[naturalq]: https://github.com/google-research-datasets/natural-questions
[humaneval]: https://arxiv.org/abs/2107.03374
[mbpp]: https://arxiv.org/abs/2108.07732
[gsm8k]: https://arxiv.org/abs/2110.14168
[realtox]: https://arxiv.org/abs/2009.11462
[bold]: https://arxiv.org/abs/2101.11718
[crows]: https://aclanthology.org/2020.emnlp-main.154/
[bbq]: https://arxiv.org/abs/2110.08193v2
[winogender]: https://arxiv.org/abs/1804.09301
[truthfulqa]: https://arxiv.org/abs/2109.07958
[winobias]: https://arxiv.org/abs/1804.06876
[math]: https://arxiv.org/abs/2103.03874
[agieval]: https://arxiv.org/abs/2304.06364
[big-bench]: https://arxiv.org/abs/2206.04615
[toxigen]: https://arxiv.org/abs/2203.09509
| null |
Non_BioNLP
|
# Gemma 2 model card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
**Resources and Technical Documentation**:
* [Responsible Generative AI Toolkit][rai-toolkit]
* [Gemma on Kaggle][kaggle-gemma]
* [Gemma on Vertex Model Garden][vertex-mg-gemma]
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2-27b-it)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights for both pre-trained variants and instruction-tuned variants.
Gemma models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Usage
Below we share some code snippets on how to get quickly started with running the model. First, install the Transformers library with:
```sh
pip install -U transformers
```
Then, copy the snippet from the section that is relevant for your usecase.
#### Running with the `pipeline` API
```python
import torch
from transformers import pipeline
pipe = pipeline(
"text-generation",
model="google/gemma-2-27b-it",
model_kwargs={"torch_dtype": torch.bfloat16},
device="cuda", # replace with "mps" to run on a Mac device
)
messages = [
{"role": "user", "content": "Who are you? Please, answer in pirate-speak."},
]
outputs = pipe(messages, max_new_tokens=256)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)
# Ahoy, matey! I be Gemma, a digital scallywag, a language-slingin' parrot of the digital seas. I be here to help ye with yer wordy woes, answer yer questions, and spin ye yarns of the digital world. So, what be yer pleasure, eh? 🦜
```
#### Running the model on a single / multi GPU
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-27b-it",
device_map="auto",
torch_dtype=torch.bfloat16,
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=32)
print(tokenizer.decode(outputs[0]))
```
You can ensure the correct chat template is applied by using `tokenizer.apply_chat_template` as follows:
```python
messages = [
{"role": "user", "content": "Write me a poem about Machine Learning."},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))
```
<a name="precisions"></a>
#### Running the model on a GPU using different precisions
The native weights of this model were exported in `bfloat16` precision.
You can also use `float32` if you skip the dtype, but no precision increase will occur (model weights will just be upcasted to `float32`). See examples below.
* _Upcasting to `torch.float32`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-27b-it",
device_map="auto",
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=32)
print(tokenizer.decode(outputs[0]))
```
#### Running the model through a CLI
The [local-gemma](https://github.com/huggingface/local-gemma) repository contains a lightweight wrapper around Transformers
for running Gemma 2 through a command line interface, or CLI. Follow the [installation instructions](https://github.com/huggingface/local-gemma#cli-usage)
for getting started, then launch the CLI through the following command:
```shell
local-gemma --model 27b --preset speed
```
#### Quantized Versions through `bitsandbytes`
<details>
<summary>
Using 8-bit precision (int8)
</summary>
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-27b-it",
quantization_config=quantization_config,
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=32)
print(tokenizer.decode(outputs[0]))
```
</details>
<details>
<summary>
Using 4-bit precision
</summary>
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained(
"google/gemma-2-27b-it",
quantization_config=quantization_config,
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=32)
print(tokenizer.decode(outputs[0]))
```
</details>
#### Advanced Usage
<details>
<summary>
Torch compile
</summary>
[Torch compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) is a method for speeding-up the
inference of PyTorch modules. The Gemma-2 model can be run up to 6x faster by leveraging torch compile.
Note that two warm-up steps are required before the full inference speed is realised:
```python
import os
os.environ["TOKENIZERS_PARALLELISM"] = "false"
from transformers import AutoTokenizer, Gemma2ForCausalLM
from transformers.cache_utils import HybridCache
import torch
torch.set_float32_matmul_precision("high")
# load the model + tokenizer
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = Gemma2ForCausalLM.from_pretrained("google/gemma-2-27b-it", torch_dtype=torch.bfloat16)
model.to("cuda")
# apply the torch compile transformation
model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True)
# pre-process inputs
input_text = "The theory of special relativity states "
model_inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
prompt_length = model_inputs.input_ids.shape[1]
# set-up k/v cache
past_key_values = HybridCache(
config=model.config,
max_batch_size=1,
max_cache_len=model.config.max_position_embeddings,
device=model.device,
dtype=model.dtype
)
# enable passing kv cache to generate
model._supports_cache_class = True
model.generation_config.cache_implementation = None
# two warm-up steps
for idx in range(2):
outputs = model.generate(**model_inputs, past_key_values=past_key_values, do_sample=True, temperature=1.0, max_new_tokens=128)
past_key_values.reset()
# fast run
outputs = model.generate(**model_inputs, past_key_values=past_key_values, do_sample=True, temperature=1.0, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
For more details, refer to the [Transformers documentation](https://huggingface.co/docs/transformers/main/en/llm_optims?static-kv=basic+usage%3A+generation_config).
</details>
### Chat Template
The instruction-tuned models use a chat template that must be adhered to for conversational use.
The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.
Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:
```py
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model_id = "google/gemma-2-27b-it"
dtype = torch.bfloat16
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="cuda",
torch_dtype=dtype,
)
chat = [
{ "role": "user", "content": "Write a hello world program" },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
```
At this point, the prompt contains the following text:
```
<bos><start_of_turn>user
Write a hello world program<end_of_turn>
<start_of_turn>model
```
As you can see, each turn is preceded by a `<start_of_turn>` delimiter and then the role of the entity
(either `user`, for content supplied by the user, or `model` for LLM responses). Turns finish with
the `<end_of_turn>` token.
You can follow this format to build the prompt manually, if you need to do it without the tokenizer's
chat template.
After the prompt is ready, generation can be performed like this:
```py
inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150)
print(tokenizer.decode(outputs[0]))
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
### Citation
```none
@article{gemma_2024,
title={Gemma},
url={https://www.kaggle.com/m/3301},
DOI={10.34740/KAGGLE/M/3301},
publisher={Kaggle},
author={Gemma Team},
year={2024}
}
```
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 13 trillion tokens and the 9B model was trained with 8 trillion tokens.
Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content.
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safety in line with
[our policies][safety-policies].
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)][tpu] hardware (TPUv5p).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably][sustainability].
### Software
Training was done using [JAX][jax] and [ML Pathways][ml-pathways].
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models][foundation-models], including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models][gemini-2-paper]; "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | Gemma PT 9B | Gemma PT 27B |
| ------------------------------ | ------------- | ----------- | ------------ |
| [MMLU][mmlu] | 5-shot, top-1 | 71.3 | 75.2 |
| [HellaSwag][hellaswag] | 10-shot | 81.9 | 86.4 |
| [PIQA][piqa] | 0-shot | 81.7 | 83.2 |
| [SocialIQA][socialiqa] | 0-shot | 53.4 | 53.7 |
| [BoolQ][boolq] | 0-shot | 84.2 | 84.8 |
| [WinoGrande][winogrande] | partial score | 80.6 | 83.7 |
| [ARC-e][arc] | 0-shot | 88.0 | 88.6 |
| [ARC-c][arc] | 25-shot | 68.4 | 71.4 |
| [TriviaQA][triviaqa] | 5-shot | 76.6 | 83.7 |
| [Natural Questions][naturalq] | 5-shot | 29.2 | 34.5 |
| [HumanEval][humaneval] | pass@1 | 40.2 | 51.8 |
| [MBPP][mbpp] | 3-shot | 52.4 | 62.6 |
| [GSM8K][gsm8k] | 5-shot, maj@1 | 68.6 | 74.0 |
| [MATH][math] | 4-shot | 36.6 | 42.3 |
| [AGIEval][agieval] | 3-5-shot | 52.8 | 55.1 |
| [BIG-Bench][big-bench] | 3-shot, CoT | 68.2 | 74.9 |
| ------------------------------ | ------------- | ----------- | ------------ |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### 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:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias][winobias] and [BBQ Dataset][bbq].
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The results of ethics and safety evaluations are within acceptable thresholds
for meeting [internal policies][safety-policies] for categories such as child
safety, content safety, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well-known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
#### Gemma 2.0
| Benchmark | Metric | Gemma 2 IT 9B | Gemma 2 IT 27B |
| ------------------------ | ------------- | --------------- | ---------------- |
| [RealToxicity][realtox] | average | 8.25 | 8.84 |
| [CrowS-Pairs][crows] | top-1 | 37.47 | 36.67 |
| [BBQ Ambig][bbq] | 1-shot, top-1 | 88.58 | 85.99 |
| [BBQ Disambig][bbq] | top-1 | 82.67 | 86.94 |
| [Winogender][winogender] | top-1 | 79.17 | 77.22 |
| [TruthfulQA][truthfulqa] | | 50.27 | 51.60 |
| [Winobias 1_2][winobias] | | 78.09 | 81.94 |
| [Winobias 2_2][winobias] | | 95.32 | 97.22 |
| [Toxigen][toxigen] | | 39.30 | 38.42 |
| ------------------------ | ------------- | --------------- | ---------------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) 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.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs 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.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world 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
* LLMs 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][rai-toolkit].
* 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 LLM 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][prohibited-use].
* Privacy violations: Models were trained on data filtered for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
[rai-toolkit]: https://ai.google.dev/responsible
[kaggle-gemma]: https://www.kaggle.com/models/google/gemma-2
[terms]: https://ai.google.dev/gemma/terms
[vertex-mg-gemma]: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335
[sensitive-info]: https://cloud.google.com/dlp/docs/high-sensitivity-infotypes-reference
[safety-policies]: https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11
[prohibited-use]: https://ai.google.dev/gemma/prohibited_use_policy
[tpu]: https://cloud.google.com/tpu/docs/intro-to-tpu
[sustainability]: https://sustainability.google/operating-sustainably/
[jax]: https://github.com/google/jax
[ml-pathways]: https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/
[sustainability]: https://sustainability.google/operating-sustainably/
[foundation-models]: https://ai.google/discover/foundation-models/
[gemini-2-paper]: https://goo.gle/gemma2report
[mmlu]: https://arxiv.org/abs/2009.03300
[hellaswag]: https://arxiv.org/abs/1905.07830
[piqa]: https://arxiv.org/abs/1911.11641
[socialiqa]: https://arxiv.org/abs/1904.09728
[boolq]: https://arxiv.org/abs/1905.10044
[winogrande]: https://arxiv.org/abs/1907.10641
[commonsenseqa]: https://arxiv.org/abs/1811.00937
[openbookqa]: https://arxiv.org/abs/1809.02789
[arc]: https://arxiv.org/abs/1911.01547
[triviaqa]: https://arxiv.org/abs/1705.03551
[naturalq]: https://github.com/google-research-datasets/natural-questions
[humaneval]: https://arxiv.org/abs/2107.03374
[mbpp]: https://arxiv.org/abs/2108.07732
[gsm8k]: https://arxiv.org/abs/2110.14168
[realtox]: https://arxiv.org/abs/2009.11462
[bold]: https://arxiv.org/abs/2101.11718
[crows]: https://aclanthology.org/2020.emnlp-main.154/
[bbq]: https://arxiv.org/abs/2110.08193v2
[winogender]: https://arxiv.org/abs/1804.09301
[truthfulqa]: https://arxiv.org/abs/2109.07958
[winobias]: https://arxiv.org/abs/1804.06876
[math]: https://arxiv.org/abs/2103.03874
[agieval]: https://arxiv.org/abs/2304.06364
[big-bench]: https://arxiv.org/abs/2206.04615
[toxigen]: https://arxiv.org/abs/2203.09509
|
{"base_model": "google/gemma-2-27b", "library_name": "transformers", "license": "gemma", "pipeline_tag": "text-generation", "extra_gated_heading": "Access Gemma on Hugging Face", "extra_gated_prompt": "To access Gemma 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",
"SUMMARIZATION"
] | 43,863 |
SEBIS/code_trans_t5_base_api_generation
|
SEBIS
|
summarization
|
[
"transformers",
"pytorch",
"jax",
"t5",
"feature-extraction",
"summarization",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2021-06-23T03:57:33+00:00
| 258 | 2 |
---
tags:
- summarization
widget:
- text: parse the uses licence node of this package , if any , and returns the license
definition if theres
---
# CodeTrans model for api recommendation generation
Pretrained model for api recommendation generation using the t5 base model architecture. It was first released in
[this repository](https://github.com/agemagician/CodeTrans).
## Model description
This CodeTrans model is based on the `t5-base` model. It has its own SentencePiece vocabulary model. It used single-task training on Api Recommendation Generation dataset.
## Intended uses & limitations
The model could be used to generate api usage for the java programming tasks.
### How to use
Here is how to use this model to generate java function documentation using Transformers SummarizationPipeline:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline
pipeline = SummarizationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_base_api_generation"),
tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_base_api_generation", skip_special_tokens=True),
device=0
)
tokenized_code = "parse the uses licence node of this package , if any , and returns the license definition if theres"
pipeline([tokenized_code])
```
Run this example in [colab notebook](https://github.com/agemagician/CodeTrans/blob/main/prediction/single%20task/api%20generation/base_model.ipynb).
## Training data
The supervised training tasks datasets can be downloaded on [Link](https://www.dropbox.com/sh/488bq2of10r4wvw/AACs5CGIQuwtsD7j_Ls_JAORa/finetuning_dataset?dl=0&subfolder_nav_tracking=1)
## Evaluation results
For the code documentation tasks, different models achieves the following results on different programming languages (in BLEU score):
Test results :
| Language / Model | Java |
| -------------------- | :------------: |
| CodeTrans-ST-Small | 68.71 |
| CodeTrans-ST-Base | 70.45 |
| CodeTrans-TF-Small | 68.90 |
| CodeTrans-TF-Base | 72.11 |
| CodeTrans-TF-Large | 73.26 |
| CodeTrans-MT-Small | 58.43 |
| CodeTrans-MT-Base | 67.97 |
| CodeTrans-MT-Large | 72.29 |
| CodeTrans-MT-TF-Small | 69.29 |
| CodeTrans-MT-TF-Base | 72.89 |
| CodeTrans-MT-TF-Large | **73.39** |
| State of the art | 54.42 |
> Created by [Ahmed Elnaggar](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/) and Wei Ding | [LinkedIn](https://www.linkedin.com/in/wei-ding-92561270/)
| null |
Non_BioNLP
|
# CodeTrans model for api recommendation generation
Pretrained model for api recommendation generation using the t5 base model architecture. It was first released in
[this repository](https://github.com/agemagician/CodeTrans).
## Model description
This CodeTrans model is based on the `t5-base` model. It has its own SentencePiece vocabulary model. It used single-task training on Api Recommendation Generation dataset.
## Intended uses & limitations
The model could be used to generate api usage for the java programming tasks.
### How to use
Here is how to use this model to generate java function documentation using Transformers SummarizationPipeline:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline
pipeline = SummarizationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_base_api_generation"),
tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_base_api_generation", skip_special_tokens=True),
device=0
)
tokenized_code = "parse the uses licence node of this package , if any , and returns the license definition if theres"
pipeline([tokenized_code])
```
Run this example in [colab notebook](https://github.com/agemagician/CodeTrans/blob/main/prediction/single%20task/api%20generation/base_model.ipynb).
## Training data
The supervised training tasks datasets can be downloaded on [Link](https://www.dropbox.com/sh/488bq2of10r4wvw/AACs5CGIQuwtsD7j_Ls_JAORa/finetuning_dataset?dl=0&subfolder_nav_tracking=1)
## Evaluation results
For the code documentation tasks, different models achieves the following results on different programming languages (in BLEU score):
Test results :
| Language / Model | Java |
| -------------------- | :------------: |
| CodeTrans-ST-Small | 68.71 |
| CodeTrans-ST-Base | 70.45 |
| CodeTrans-TF-Small | 68.90 |
| CodeTrans-TF-Base | 72.11 |
| CodeTrans-TF-Large | 73.26 |
| CodeTrans-MT-Small | 58.43 |
| CodeTrans-MT-Base | 67.97 |
| CodeTrans-MT-Large | 72.29 |
| CodeTrans-MT-TF-Small | 69.29 |
| CodeTrans-MT-TF-Base | 72.89 |
| CodeTrans-MT-TF-Large | **73.39** |
| State of the art | 54.42 |
> Created by [Ahmed Elnaggar](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/) and Wei Ding | [LinkedIn](https://www.linkedin.com/in/wei-ding-92561270/)
|
{"tags": ["summarization"], "widget": [{"text": "parse the uses licence node of this package , if any , and returns the license definition if theres"}]}
|
task
|
[
"SUMMARIZATION"
] | 43,864 |
poom-sci/bert-base-uncased-multi-emotion
|
poom-sci
|
translation
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"translation",
"en",
"dataset:go_emotions",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2021-11-14T16:22:26+00:00
| 65 | 1 |
---
datasets:
- go_emotions
language:
- en
license: apache-2.0
tags:
- translation
---
created for study
| null |
Non_BioNLP
|
created for study
|
{"datasets": ["go_emotions"], "language": ["en"], "license": "apache-2.0", "tags": ["translation"]}
|
task
|
[
"TRANSLATION"
] | 43,865 |
mansoorhamidzadeh/ag-news-bert-classification
|
mansoorhamidzadeh
|
text-classification
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"nlp",
"en",
"dataset:fancyzhx/ag_news",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-07-16T22:53:32Z |
2024-07-17T09:16:05+00:00
| 143 | 0 |
---
datasets:
- fancyzhx/ag_news
language:
- en
library_name: transformers
license: mit
metrics:
- accuracy
- recall
- precision
- f1
pipeline_tag: text-classification
tags:
- text-classification
- nlp
- transformers
- bert
---
# AG-News BERT Classification
## Model Details
**Model Name:** AG-News BERT Classification
**Model Type:** Text Classification
**Developer:** Mansoor Hamidzadeh
**Repository:** [mansoorhamidzadeh/ag-news-bert-classification](https://huggingface.co/mansoorhamidzadeh/ag-news-bert-classification)
**Language(s):** English
**License:** MIT
## Model Description
### Overview
The AG-News BERT Classification model is a fine-tuned BERT (Bidirectional Encoder Representations from Transformers) model designed for text classification tasks, specifically for classifying news articles into four categories: World, Sports, Business, and Sci/Tech. The model leverages the pre-trained BERT architecture, which has been fine-tuned on the AG-News dataset to optimize its performance for this specific task.
### Intended Use
#### Primary Use Case
The primary use case for this model is to automatically classify news articles into one of the four predefined categories:
- World
- Sports
- Business
- Sci/Tech
This can be useful for news aggregation services, content recommendation systems, and any application that requires automated content categorization.
#### Applications
- News aggregators and curators
- Content recommendation engines
- Media monitoring tools
- Sentiment analysis and trend detection in news
## Training Data
### Dataset
- **Name:** AG-News Dataset
- **Source:** [AG News Corpus](https://huggingface.co/datasets/fancyzhx/ag_newss)
- **Description:** The AG-News dataset is a widely used benchmark dataset for text classification. It contains 120,000 training samples and 7,600 test samples of news articles categorized into four classes: World, Sports, Business, and Sci/Tech.
### Data Preprocessing
The text data was preprocessed to tokenize the sentences using the BERT tokenizer, converting the tokens to their corresponding IDs, and creating attention masks.
## Training Procedure
**Training Configuration:**
- **Number of Epochs:** 4
- **Batch Size:** 8
- **Learning Rate:** 1e-5
- **Optimizer:** AdamW
**Training and Validation Losses:**
- **Epoch 1:**
- Average training loss: 0.1330
- Average test loss: 0.1762
- **Epoch 2:**
- Average training loss: 0.0918
- Average test loss: 0.1733
- **Epoch 3:**
- Average training loss: 0.0622
- Average test loss: 0.1922
- **Epoch 4:**
- Average training loss: 0.0416
- Average test loss: 0.2305
**Hardware:**
- **Training Environment:** NVIDIA P100 GPU
- **Training Time:** Approximately 3 hours
## Performance
### Evaluation Metrics
The model was evaluated using standard text classification metrics:
- Accuracy
- Precision
- Recall
- F1 Score
### Results
On the AG-News test set, the model achieved the following performance:
- **Accuracy:** 93.8%
- **Precision:** 93.8%
- **Recall:** 93.8%
- **F1 Score:** 93.8%
## Limitations and Biases
### Limitations
- The model may not generalize well to other text types or news sources outside the AG-News dataset.
- Primarily designed for English text and may not perform well on text in other languages.
### Biases
- Potential biases present in the training data, reflecting biases in news reporting.
- Category-specific biases due to the distribution of articles in the dataset.
## Ethical Considerations
- Ensure the model is used in compliance with user privacy and data security standards.
- Be aware of potential biases and take steps to mitigate negative impacts, especially in sensitive applications.
## How to Use
### Inference
To use the model for inference, load it using the Hugging Face Transformers library:
```python
from transformers import BertTokenizer, BertForSequenceClassification
from transformers import TextClassificationPipeline
tokenizer = BertTokenizer.from_pretrained("mansoorhamidzadeh/ag-news-bert-classification")
model = BertForSequenceClassification.from_pretrained("mansoorhamidzadeh/ag-news-bert-classification")
pipeline = TextClassificationPipeline(model=model, tokenizer=tokenizer)
text = "Sample news article text here."
prediction = pipeline(text)
print(prediction)
```
``` bibtxt
@misc{mansoorhamidzadeh,
author = {Mansoor Hamidzadeh},
title = {AG-News BERT Classification},
year = {2024},
publisher = {Hugging Face},
howpublished = {\url{https://huggingface.co/mansoorhamidzadeh/ag-news-bert-classification}},
}
| null |
Non_BioNLP
|
# AG-News BERT Classification
## Model Details
**Model Name:** AG-News BERT Classification
**Model Type:** Text Classification
**Developer:** Mansoor Hamidzadeh
**Repository:** [mansoorhamidzadeh/ag-news-bert-classification](https://huggingface.co/mansoorhamidzadeh/ag-news-bert-classification)
**Language(s):** English
**License:** MIT
## Model Description
### Overview
The AG-News BERT Classification model is a fine-tuned BERT (Bidirectional Encoder Representations from Transformers) model designed for text classification tasks, specifically for classifying news articles into four categories: World, Sports, Business, and Sci/Tech. The model leverages the pre-trained BERT architecture, which has been fine-tuned on the AG-News dataset to optimize its performance for this specific task.
### Intended Use
#### Primary Use Case
The primary use case for this model is to automatically classify news articles into one of the four predefined categories:
- World
- Sports
- Business
- Sci/Tech
This can be useful for news aggregation services, content recommendation systems, and any application that requires automated content categorization.
#### Applications
- News aggregators and curators
- Content recommendation engines
- Media monitoring tools
- Sentiment analysis and trend detection in news
## Training Data
### Dataset
- **Name:** AG-News Dataset
- **Source:** [AG News Corpus](https://huggingface.co/datasets/fancyzhx/ag_newss)
- **Description:** The AG-News dataset is a widely used benchmark dataset for text classification. It contains 120,000 training samples and 7,600 test samples of news articles categorized into four classes: World, Sports, Business, and Sci/Tech.
### Data Preprocessing
The text data was preprocessed to tokenize the sentences using the BERT tokenizer, converting the tokens to their corresponding IDs, and creating attention masks.
## Training Procedure
**Training Configuration:**
- **Number of Epochs:** 4
- **Batch Size:** 8
- **Learning Rate:** 1e-5
- **Optimizer:** AdamW
**Training and Validation Losses:**
- **Epoch 1:**
- Average training loss: 0.1330
- Average test loss: 0.1762
- **Epoch 2:**
- Average training loss: 0.0918
- Average test loss: 0.1733
- **Epoch 3:**
- Average training loss: 0.0622
- Average test loss: 0.1922
- **Epoch 4:**
- Average training loss: 0.0416
- Average test loss: 0.2305
**Hardware:**
- **Training Environment:** NVIDIA P100 GPU
- **Training Time:** Approximately 3 hours
## Performance
### Evaluation Metrics
The model was evaluated using standard text classification metrics:
- Accuracy
- Precision
- Recall
- F1 Score
### Results
On the AG-News test set, the model achieved the following performance:
- **Accuracy:** 93.8%
- **Precision:** 93.8%
- **Recall:** 93.8%
- **F1 Score:** 93.8%
## Limitations and Biases
### Limitations
- The model may not generalize well to other text types or news sources outside the AG-News dataset.
- Primarily designed for English text and may not perform well on text in other languages.
### Biases
- Potential biases present in the training data, reflecting biases in news reporting.
- Category-specific biases due to the distribution of articles in the dataset.
## Ethical Considerations
- Ensure the model is used in compliance with user privacy and data security standards.
- Be aware of potential biases and take steps to mitigate negative impacts, especially in sensitive applications.
## How to Use
### Inference
To use the model for inference, load it using the Hugging Face Transformers library:
```python
from transformers import BertTokenizer, BertForSequenceClassification
from transformers import TextClassificationPipeline
tokenizer = BertTokenizer.from_pretrained("mansoorhamidzadeh/ag-news-bert-classification")
model = BertForSequenceClassification.from_pretrained("mansoorhamidzadeh/ag-news-bert-classification")
pipeline = TextClassificationPipeline(model=model, tokenizer=tokenizer)
text = "Sample news article text here."
prediction = pipeline(text)
print(prediction)
```
``` bibtxt
@misc{mansoorhamidzadeh,
author = {Mansoor Hamidzadeh},
title = {AG-News BERT Classification},
year = {2024},
publisher = {Hugging Face},
howpublished = {\url{https://huggingface.co/mansoorhamidzadeh/ag-news-bert-classification}},
}
|
{"datasets": ["fancyzhx/ag_news"], "language": ["en"], "library_name": "transformers", "license": "mit", "metrics": ["accuracy", "recall", "precision", "f1"], "pipeline_tag": "text-classification", "tags": ["text-classification", "nlp", "transformers", "bert"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,867 |
albert/albert-base-v1
|
albert
|
fill-mask
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"albert",
"fill-mask",
"exbert",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1909.11942",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:04Z |
2024-02-19T10:57:35+00:00
| 16,594 | 11 |
---
datasets:
- bookcorpus
- wikipedia
language: en
license: apache-2.0
tags:
- exbert
---
# ALBERT Base v1
Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in
[this paper](https://arxiv.org/abs/1909.11942) and first released in
[this repository](https://github.com/google-research/albert). This model, as all ALBERT models, is uncased: it does not make a difference
between english and English.
Disclaimer: The team releasing ALBERT did not write a model card for this model so this model card has been written by
the Hugging Face team.
## Model description
ALBERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Sentence Ordering Prediction (SOP): ALBERT uses a pretraining loss based on predicting the ordering of two consecutive segments of text.
This way, the model learns an inner representation of the English language that can then be used to extract features
useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
classifier using the features produced by the ALBERT model as inputs.
ALBERT is particular in that it shares its layers across its Transformer. Therefore, all layers have the same weights. Using repeating layers results in a small memory footprint, however, the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers.
This is the first version of the base model. Version 2 is different from version 1 due to different dropout rates, additional training data, and longer training. It has better results in nearly all downstream tasks.
This model has the following configuration:
- 12 repeating layers
- 128 embedding dimension
- 768 hidden dimension
- 12 attention heads
- 11M parameters
## Intended uses & limitations
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=albert) to look for
fine-tuned versions on a task that interests you.
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
generation you should look at model like GPT2.
### How to use
You can use this model directly with a pipeline for masked language modeling:
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='albert-base-v1')
>>> unmasker("Hello I'm a [MASK] model.")
[
{
"sequence":"[CLS] hello i'm a modeling model.[SEP]",
"score":0.05816134437918663,
"token":12807,
"token_str":"▁modeling"
},
{
"sequence":"[CLS] hello i'm a modelling model.[SEP]",
"score":0.03748830780386925,
"token":23089,
"token_str":"▁modelling"
},
{
"sequence":"[CLS] hello i'm a model model.[SEP]",
"score":0.033725276589393616,
"token":1061,
"token_str":"▁model"
},
{
"sequence":"[CLS] hello i'm a runway model.[SEP]",
"score":0.017313428223133087,
"token":8014,
"token_str":"▁runway"
},
{
"sequence":"[CLS] hello i'm a lingerie model.[SEP]",
"score":0.014405295252799988,
"token":29104,
"token_str":"▁lingerie"
}
]
```
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import AlbertTokenizer, AlbertModel
tokenizer = AlbertTokenizer.from_pretrained('albert-base-v1')
model = AlbertModel.from_pretrained("albert-base-v1")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
```
and in TensorFlow:
```python
from transformers import AlbertTokenizer, TFAlbertModel
tokenizer = AlbertTokenizer.from_pretrained('albert-base-v1')
model = TFAlbertModel.from_pretrained("albert-base-v1")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)
```
### Limitations and bias
Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
predictions:
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='albert-base-v1')
>>> unmasker("The man worked as a [MASK].")
[
{
"sequence":"[CLS] the man worked as a chauffeur.[SEP]",
"score":0.029577180743217468,
"token":28744,
"token_str":"▁chauffeur"
},
{
"sequence":"[CLS] the man worked as a janitor.[SEP]",
"score":0.028865724802017212,
"token":29477,
"token_str":"▁janitor"
},
{
"sequence":"[CLS] the man worked as a shoemaker.[SEP]",
"score":0.02581118606030941,
"token":29024,
"token_str":"▁shoemaker"
},
{
"sequence":"[CLS] the man worked as a blacksmith.[SEP]",
"score":0.01849772222340107,
"token":21238,
"token_str":"▁blacksmith"
},
{
"sequence":"[CLS] the man worked as a lawyer.[SEP]",
"score":0.01820771023631096,
"token":3672,
"token_str":"▁lawyer"
}
]
>>> unmasker("The woman worked as a [MASK].")
[
{
"sequence":"[CLS] the woman worked as a receptionist.[SEP]",
"score":0.04604868218302727,
"token":25331,
"token_str":"▁receptionist"
},
{
"sequence":"[CLS] the woman worked as a janitor.[SEP]",
"score":0.028220869600772858,
"token":29477,
"token_str":"▁janitor"
},
{
"sequence":"[CLS] the woman worked as a paramedic.[SEP]",
"score":0.0261906236410141,
"token":23386,
"token_str":"▁paramedic"
},
{
"sequence":"[CLS] the woman worked as a chauffeur.[SEP]",
"score":0.024797942489385605,
"token":28744,
"token_str":"▁chauffeur"
},
{
"sequence":"[CLS] the woman worked as a waitress.[SEP]",
"score":0.024124596267938614,
"token":13678,
"token_str":"▁waitress"
}
]
```
This bias will also affect all fine-tuned versions of this model.
## Training data
The ALBERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038
unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and
headers).
## Training procedure
### Preprocessing
The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 30,000. The inputs of the model are
then of the form:
```
[CLS] Sentence A [SEP] Sentence B [SEP]
```
### Training
The ALBERT procedure follows the BERT setup.
The details of the masking procedure for each sentence are the following:
- 15% of the tokens are masked.
- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
- In the 10% remaining cases, the masked tokens are left as is.
## Evaluation results
When fine-tuned on downstream tasks, the ALBERT models achieve the following results:
| | Average | SQuAD1.1 | SQuAD2.0 | MNLI | SST-2 | RACE |
|----------------|----------|----------|----------|----------|----------|----------|
|V2 |
|ALBERT-base |82.3 |90.2/83.2 |82.1/79.3 |84.6 |92.9 |66.8 |
|ALBERT-large |85.7 |91.8/85.2 |84.9/81.8 |86.5 |94.9 |75.2 |
|ALBERT-xlarge |87.9 |92.9/86.4 |87.9/84.1 |87.9 |95.4 |80.7 |
|ALBERT-xxlarge |90.9 |94.6/89.1 |89.8/86.9 |90.6 |96.8 |86.8 |
|V1 |
|ALBERT-base |80.1 |89.3/82.3 | 80.0/77.1|81.6 |90.3 | 64.0 |
|ALBERT-large |82.4 |90.6/83.9 | 82.3/79.4|83.5 |91.7 | 68.5 |
|ALBERT-xlarge |85.5 |92.5/86.1 | 86.1/83.1|86.4 |92.4 | 74.8 |
|ALBERT-xxlarge |91.0 |94.8/89.3 | 90.2/87.4|90.8 |96.9 | 86.5 |
### BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-1909-11942,
author = {Zhenzhong Lan and
Mingda Chen and
Sebastian Goodman and
Kevin Gimpel and
Piyush Sharma and
Radu Soricut},
title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language
Representations},
journal = {CoRR},
volume = {abs/1909.11942},
year = {2019},
url = {http://arxiv.org/abs/1909.11942},
archivePrefix = {arXiv},
eprint = {1909.11942},
timestamp = {Fri, 27 Sep 2019 13:04:21 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-11942.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
<a href="https://huggingface.co/exbert/?model=albert-base-v1">
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
</a>
| null |
Non_BioNLP
|
# ALBERT Base v1
Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in
[this paper](https://arxiv.org/abs/1909.11942) and first released in
[this repository](https://github.com/google-research/albert). This model, as all ALBERT models, is uncased: it does not make a difference
between english and English.
Disclaimer: The team releasing ALBERT did not write a model card for this model so this model card has been written by
the Hugging Face team.
## Model description
ALBERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Sentence Ordering Prediction (SOP): ALBERT uses a pretraining loss based on predicting the ordering of two consecutive segments of text.
This way, the model learns an inner representation of the English language that can then be used to extract features
useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
classifier using the features produced by the ALBERT model as inputs.
ALBERT is particular in that it shares its layers across its Transformer. Therefore, all layers have the same weights. Using repeating layers results in a small memory footprint, however, the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers.
This is the first version of the base model. Version 2 is different from version 1 due to different dropout rates, additional training data, and longer training. It has better results in nearly all downstream tasks.
This model has the following configuration:
- 12 repeating layers
- 128 embedding dimension
- 768 hidden dimension
- 12 attention heads
- 11M parameters
## Intended uses & limitations
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=albert) to look for
fine-tuned versions on a task that interests you.
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
generation you should look at model like GPT2.
### How to use
You can use this model directly with a pipeline for masked language modeling:
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='albert-base-v1')
>>> unmasker("Hello I'm a [MASK] model.")
[
{
"sequence":"[CLS] hello i'm a modeling model.[SEP]",
"score":0.05816134437918663,
"token":12807,
"token_str":"▁modeling"
},
{
"sequence":"[CLS] hello i'm a modelling model.[SEP]",
"score":0.03748830780386925,
"token":23089,
"token_str":"▁modelling"
},
{
"sequence":"[CLS] hello i'm a model model.[SEP]",
"score":0.033725276589393616,
"token":1061,
"token_str":"▁model"
},
{
"sequence":"[CLS] hello i'm a runway model.[SEP]",
"score":0.017313428223133087,
"token":8014,
"token_str":"▁runway"
},
{
"sequence":"[CLS] hello i'm a lingerie model.[SEP]",
"score":0.014405295252799988,
"token":29104,
"token_str":"▁lingerie"
}
]
```
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import AlbertTokenizer, AlbertModel
tokenizer = AlbertTokenizer.from_pretrained('albert-base-v1')
model = AlbertModel.from_pretrained("albert-base-v1")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
```
and in TensorFlow:
```python
from transformers import AlbertTokenizer, TFAlbertModel
tokenizer = AlbertTokenizer.from_pretrained('albert-base-v1')
model = TFAlbertModel.from_pretrained("albert-base-v1")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)
```
### Limitations and bias
Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
predictions:
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='albert-base-v1')
>>> unmasker("The man worked as a [MASK].")
[
{
"sequence":"[CLS] the man worked as a chauffeur.[SEP]",
"score":0.029577180743217468,
"token":28744,
"token_str":"▁chauffeur"
},
{
"sequence":"[CLS] the man worked as a janitor.[SEP]",
"score":0.028865724802017212,
"token":29477,
"token_str":"▁janitor"
},
{
"sequence":"[CLS] the man worked as a shoemaker.[SEP]",
"score":0.02581118606030941,
"token":29024,
"token_str":"▁shoemaker"
},
{
"sequence":"[CLS] the man worked as a blacksmith.[SEP]",
"score":0.01849772222340107,
"token":21238,
"token_str":"▁blacksmith"
},
{
"sequence":"[CLS] the man worked as a lawyer.[SEP]",
"score":0.01820771023631096,
"token":3672,
"token_str":"▁lawyer"
}
]
>>> unmasker("The woman worked as a [MASK].")
[
{
"sequence":"[CLS] the woman worked as a receptionist.[SEP]",
"score":0.04604868218302727,
"token":25331,
"token_str":"▁receptionist"
},
{
"sequence":"[CLS] the woman worked as a janitor.[SEP]",
"score":0.028220869600772858,
"token":29477,
"token_str":"▁janitor"
},
{
"sequence":"[CLS] the woman worked as a paramedic.[SEP]",
"score":0.0261906236410141,
"token":23386,
"token_str":"▁paramedic"
},
{
"sequence":"[CLS] the woman worked as a chauffeur.[SEP]",
"score":0.024797942489385605,
"token":28744,
"token_str":"▁chauffeur"
},
{
"sequence":"[CLS] the woman worked as a waitress.[SEP]",
"score":0.024124596267938614,
"token":13678,
"token_str":"▁waitress"
}
]
```
This bias will also affect all fine-tuned versions of this model.
## Training data
The ALBERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038
unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and
headers).
## Training procedure
### Preprocessing
The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 30,000. The inputs of the model are
then of the form:
```
[CLS] Sentence A [SEP] Sentence B [SEP]
```
### Training
The ALBERT procedure follows the BERT setup.
The details of the masking procedure for each sentence are the following:
- 15% of the tokens are masked.
- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
- In the 10% remaining cases, the masked tokens are left as is.
## Evaluation results
When fine-tuned on downstream tasks, the ALBERT models achieve the following results:
| | Average | SQuAD1.1 | SQuAD2.0 | MNLI | SST-2 | RACE |
|----------------|----------|----------|----------|----------|----------|----------|
|V2 |
|ALBERT-base |82.3 |90.2/83.2 |82.1/79.3 |84.6 |92.9 |66.8 |
|ALBERT-large |85.7 |91.8/85.2 |84.9/81.8 |86.5 |94.9 |75.2 |
|ALBERT-xlarge |87.9 |92.9/86.4 |87.9/84.1 |87.9 |95.4 |80.7 |
|ALBERT-xxlarge |90.9 |94.6/89.1 |89.8/86.9 |90.6 |96.8 |86.8 |
|V1 |
|ALBERT-base |80.1 |89.3/82.3 | 80.0/77.1|81.6 |90.3 | 64.0 |
|ALBERT-large |82.4 |90.6/83.9 | 82.3/79.4|83.5 |91.7 | 68.5 |
|ALBERT-xlarge |85.5 |92.5/86.1 | 86.1/83.1|86.4 |92.4 | 74.8 |
|ALBERT-xxlarge |91.0 |94.8/89.3 | 90.2/87.4|90.8 |96.9 | 86.5 |
### BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-1909-11942,
author = {Zhenzhong Lan and
Mingda Chen and
Sebastian Goodman and
Kevin Gimpel and
Piyush Sharma and
Radu Soricut},
title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language
Representations},
journal = {CoRR},
volume = {abs/1909.11942},
year = {2019},
url = {http://arxiv.org/abs/1909.11942},
archivePrefix = {arXiv},
eprint = {1909.11942},
timestamp = {Fri, 27 Sep 2019 13:04:21 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-11942.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
<a href="https://huggingface.co/exbert/?model=albert-base-v1">
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
</a>
|
{"datasets": ["bookcorpus", "wikipedia"], "language": "en", "license": "apache-2.0", "tags": ["exbert"]}
|
task
|
[
"QUESTION_ANSWERING"
] | 43,868 |
Davit6174/georgian-distilbert-mlm
|
Davit6174
|
fill-mask
|
[
"transformers",
"tf",
"distilbert",
"fill-mask",
"general",
"ka",
"dataset:mc4",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-06-23T21:19:11Z |
2023-06-24T14:39:56+00:00
| 22 | 0 |
---
datasets:
- mc4
language:
- ka
library_name: transformers
tags:
- general
widget:
- text: ქართული [MASK] სწავლა საკმაოდ რთულია
example_title: Georgian Language
- text: საქართველოს [MASK] ნაკრები ერთა ლიგაზე კარგად ასპარეზობს
example_title: Football
- text: ქართული ღვინო განთქმულია [MASK] მსოფლიოში
example_title: Wine
---
# General Georgian Language Model
This language model is a pretrained model specifically designed to understand and generate text in the Georgian language. It is based on the DistilBERT-base-uncased architecture and has been trained on the MC4 dataset, which contains a large collection of Georgian web documents.
## Model Details
- **Architecture**: DistilBERT-base-uncased
- **Pretraining Corpus**: MC4 (Multilingual Crawl Corpus)
- **Language**: Georgian
## Pretraining
The model has undergone a pretraining phase using the DistilBERT architecture, which is a distilled version of the original BERT model. DistilBERT is known for its smaller size and faster inference speed while still maintaining a high level of performance.
During pretraining, the model was exposed to a vast amount of preprocessed Georgian text data from the MC4 dataset.
## Usage
To use the General Georgian Language Model, you can utilize the model through various natural language processing (NLP) tasks, such as:
- Text classification
- Named entity recognition
- Sentiment analysis
- Language generation
You can fine-tune this model on specific downstream tasks using task-specific datasets or use it as a feature extractor for transfer learning.
## Example Code
Here is an example of how to use the General Georgian Language Model using the Hugging Face `transformers` library in Python:
```python
from transformers import AutoTokenizer, TFAutoModel
from transformers import pipeline
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("Davit6174/georgian-distilbert-mlm")
model = TFAutoModel.from_pretrained("Davit6174/georgian-distilbert-mlm")
# Build pipeline
mask_filler = pipeline(
"fill-mask", model=model, tokenizer=tokenizer
)
text = 'ქართული [MASK] სწავლა საკმაოდ რთულია'
# Generate model output
preds = mask_filler(text)
# Print top 5 predictions
for pred in preds:
print(f">>> {pred['sequence']}")
```
## Limitations and Considerations
- The model's performance may vary across different downstream tasks and domains.
- The model's understanding of context and nuanced meanings may not always be accurate.
- The model may generate plausible-sounding but incorrect or nonsensical Georgian text.
- Therefore, it is recommended to evaluate the model's performance and fine-tune it on task-specific datasets when necessary.
## Acknowledgments
The Georgian Language Model was pretrained using the Hugging Face transformers library and trained on the MC4 dataset, which is maintained by the community. I would like to express my gratitude to the contributors and maintainers of these valuable resources.
| null |
Non_BioNLP
|
# General Georgian Language Model
This language model is a pretrained model specifically designed to understand and generate text in the Georgian language. It is based on the DistilBERT-base-uncased architecture and has been trained on the MC4 dataset, which contains a large collection of Georgian web documents.
## Model Details
- **Architecture**: DistilBERT-base-uncased
- **Pretraining Corpus**: MC4 (Multilingual Crawl Corpus)
- **Language**: Georgian
## Pretraining
The model has undergone a pretraining phase using the DistilBERT architecture, which is a distilled version of the original BERT model. DistilBERT is known for its smaller size and faster inference speed while still maintaining a high level of performance.
During pretraining, the model was exposed to a vast amount of preprocessed Georgian text data from the MC4 dataset.
## Usage
To use the General Georgian Language Model, you can utilize the model through various natural language processing (NLP) tasks, such as:
- Text classification
- Named entity recognition
- Sentiment analysis
- Language generation
You can fine-tune this model on specific downstream tasks using task-specific datasets or use it as a feature extractor for transfer learning.
## Example Code
Here is an example of how to use the General Georgian Language Model using the Hugging Face `transformers` library in Python:
```python
from transformers import AutoTokenizer, TFAutoModel
from transformers import pipeline
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("Davit6174/georgian-distilbert-mlm")
model = TFAutoModel.from_pretrained("Davit6174/georgian-distilbert-mlm")
# Build pipeline
mask_filler = pipeline(
"fill-mask", model=model, tokenizer=tokenizer
)
text = 'ქართული [MASK] სწავლა საკმაოდ რთულია'
# Generate model output
preds = mask_filler(text)
# Print top 5 predictions
for pred in preds:
print(f">>> {pred['sequence']}")
```
## Limitations and Considerations
- The model's performance may vary across different downstream tasks and domains.
- The model's understanding of context and nuanced meanings may not always be accurate.
- The model may generate plausible-sounding but incorrect or nonsensical Georgian text.
- Therefore, it is recommended to evaluate the model's performance and fine-tune it on task-specific datasets when necessary.
## Acknowledgments
The Georgian Language Model was pretrained using the Hugging Face transformers library and trained on the MC4 dataset, which is maintained by the community. I would like to express my gratitude to the contributors and maintainers of these valuable resources.
|
{"datasets": ["mc4"], "language": ["ka"], "library_name": "transformers", "tags": ["general"], "widget": [{"text": "ქართული [MASK] სწავლა საკმაოდ რთულია", "example_title": "Georgian Language"}, {"text": "საქართველოს [MASK] ნაკრები ერთა ლიგაზე კარგად ასპარეზობს", "example_title": "Football"}, {"text": "ქართული ღვინო განთქმულია [MASK] მსოფლიოში", "example_title": "Wine"}]}
|
task
|
[
"NAMED_ENTITY_RECOGNITION",
"TEXT_CLASSIFICATION"
] | 43,869 |
mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF
|
mradermacher
| null |
[
"transformers",
"gguf",
"en",
"base_model:mtc/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged",
"base_model:quantized:mtc/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged",
"endpoints_compatible",
"region:us"
] | 2024-11-01T09:15:24Z |
2024-11-01T09:43:13+00:00
| 37 | 0 |
---
base_model: mtc/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged
language:
- en
library_name: transformers
tags: []
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/mtc/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q2_K.gguf) | Q2_K | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| null |
Non_BioNLP
|
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/mtc/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q2_K.gguf) | Q2_K | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged-GGUF/resolve/main/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
{"base_model": "mtc/meta-llama-Llama-2-7b-hf-arxiv-summarization-10k-last_merged", "language": ["en"], "library_name": "transformers", "tags": [], "quantized_by": "mradermacher"}
|
task
|
[
"SUMMARIZATION"
] | 43,870 |
cho8389/distilbert-base-uncased-finetuned-emotion
|
cho8389
|
text-classification
|
[
"transformers",
"pytorch",
"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"
] | 2023-12-03T06:29:44Z |
2023-12-03T06:32:46+00:00
| 0 | 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: 0.9395
name: Accuracy
- type: f1
value: 0.9395589832847959
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: 0.2411
- Accuracy: 0.9395
- F1: 0.9396
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.0236 | 1.0 | 250 | 0.2320 | 0.9445 | 0.9447 |
| 0.0366 | 2.0 | 500 | 0.2411 | 0.9395 | 0.9396 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu118
- 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: 0.2411
- Accuracy: 0.9395
- F1: 0.9396
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.0236 | 1.0 | 250 | 0.2320 | 0.9445 | 0.9447 |
| 0.0366 | 2.0 | 500 | 0.2411 | 0.9395 | 0.9396 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.2
|
{"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", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.9395, "name": "Accuracy"}, {"type": "f1", "value": 0.9395589832847959, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,871 |
figurative-nlp/se4fig-roberta-base
|
figurative-nlp
| null |
[
"transformers",
"pytorch",
"roberta",
"endpoints_compatible",
"region:us"
] | 2022-03-02T23:29:05Z |
2022-02-17T15:54:01+00:00
| 48 | 0 |
---
{}
---
This model can measure semantic similarity between pairs of texts containing figurative language. As far as we know,
this model works slightly better than sup-simCSE-roberta-base. For example :
**sentence 1**: I have been in seventh heaven since Harry entered my life .
**sentence 2**: I have been in very happy since Harry entered my life.
the cosin score of simcse: 0.897
the cosin score of us: 0.897
-------------------------------------------------------------------
**sentence 1**: I have been in seventh heaven since Harry entered my life .
**sentence 2**: I have been in pain since Harry entered my life .
the cosin score of simcse: 0.846
the cosin score of us: 0.753
--------------------------------------------------
It's still a big challenge for us to measure semantic similarity of figurative language from the sentence embedding perspective.
unsupvised models may useless as the key is to infer the literal meaning of the figurative expression, since the annotated is rare.
| null |
Non_BioNLP
|
This model can measure semantic similarity between pairs of texts containing figurative language. As far as we know,
this model works slightly better than sup-simCSE-roberta-base. For example :
**sentence 1**: I have been in seventh heaven since Harry entered my life .
**sentence 2**: I have been in very happy since Harry entered my life.
the cosin score of simcse: 0.897
the cosin score of us: 0.897
-------------------------------------------------------------------
**sentence 1**: I have been in seventh heaven since Harry entered my life .
**sentence 2**: I have been in pain since Harry entered my life .
the cosin score of simcse: 0.846
the cosin score of us: 0.753
--------------------------------------------------
It's still a big challenge for us to measure semantic similarity of figurative language from the sentence embedding perspective.
unsupvised models may useless as the key is to infer the literal meaning of the figurative expression, since the annotated is rare.
|
{}
|
task
|
[
"SEMANTIC_SIMILARITY"
] | 43,872 |
tmnam20/bert-base-multilingual-cased-rte-1
|
tmnam20
|
text-classification
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:tmnam20/VieGLUE",
"base_model:google-bert/bert-base-multilingual-cased",
"base_model:finetune:google-bert/bert-base-multilingual-cased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-01-16T06:42:08Z |
2024-01-16T06:43:23+00:00
| 5 | 0 |
---
base_model: bert-base-multilingual-cased
datasets:
- tmnam20/VieGLUE
language:
- en
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: bert-base-multilingual-cased-rte-1
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: tmnam20/VieGLUE/RTE
type: tmnam20/VieGLUE
config: rte
split: validation
args: rte
metrics:
- type: accuracy
value: 0.6570397111913358
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-multilingual-cased-rte-1
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the tmnam20/VieGLUE/RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6715
- Accuracy: 0.6570
## 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: 16
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.2.0.dev20231203+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
| 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. -->
# bert-base-multilingual-cased-rte-1
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the tmnam20/VieGLUE/RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6715
- Accuracy: 0.6570
## 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: 16
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.2.0.dev20231203+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
{"base_model": "bert-base-multilingual-cased", "datasets": ["tmnam20/VieGLUE"], "language": ["en"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "bert-base-multilingual-cased-rte-1", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "tmnam20/VieGLUE/RTE", "type": "tmnam20/VieGLUE", "config": "rte", "split": "validation", "args": "rte"}, "metrics": [{"type": "accuracy", "value": 0.6570397111913358, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,873 |
psy03/scribuddies
|
psy03
| null |
[
"region:us"
] | 2024-12-12T15:34:43Z |
2024-12-12T15:35:57+00:00
| 0 | 0 |
---
{}
---
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyMw5Z1eibIWaXObvpLKkH4A",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/psy03/G6-finalproject/blob/main/Presentation.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "uCLV4w06R0Hp",
"outputId": "7ec2aa3c-d3b4-4347-c77b-a23140f57069"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting gradio\n",
" Downloading gradio-4.36.1-py3-none-any.whl (12.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.3/12.3 MB\u001b[0m \u001b[31m18.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting aiofiles<24.0,>=22.0 (from gradio)\n",
" Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
"Requirement already satisfied: altair<6.0,>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.2.2)\n",
"Collecting fastapi (from gradio)\n",
" Downloading fastapi-0.111.0-py3-none-any.whl (91 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.0/92.0 kB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting ffmpy (from gradio)\n",
" Downloading ffmpy-0.3.2.tar.gz (5.5 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting gradio-client==1.0.1 (from gradio)\n",
" Downloading gradio_client-1.0.1-py3-none-any.whl (318 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m318.1/318.1 kB\u001b[0m \u001b[31m17.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting httpx>=0.24.1 (from gradio)\n",
" Downloading httpx-0.27.0-py3-none-any.whl (75 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: huggingface-hub>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.23.3)\n",
"Requirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.4.0)\n",
"Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.1.4)\n",
"Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.1.5)\n",
"Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.7.1)\n",
"Requirement already satisfied: numpy<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.25.2)\n",
"Collecting orjson~=3.0 (from gradio)\n",
" Downloading orjson-3.10.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (144 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m145.0/145.0 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio) (24.1)\n",
"Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.0.3)\n",
"Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (9.4.0)\n",
"Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.7.3)\n",
"Collecting pydub (from gradio)\n",
" Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
"Collecting python-multipart>=0.0.9 (from gradio)\n",
" Downloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n",
"Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.0.1)\n",
"Collecting ruff>=0.2.2 (from gradio)\n",
" Downloading ruff-0.4.9-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.8/8.8 MB\u001b[0m \u001b[31m27.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting semantic-version~=2.0 (from gradio)\n",
" Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
"Collecting tomlkit==0.12.0 (from gradio)\n",
" Downloading tomlkit-0.12.0-py3-none-any.whl (37 kB)\n",
"Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.12.3)\n",
"Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.12.2)\n",
"Requirement already satisfied: urllib3~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.0.7)\n",
"Collecting uvicorn>=0.14.0 (from gradio)\n",
" Downloading uvicorn-0.30.1-py3-none-any.whl (62 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.4/62.4 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==1.0.1->gradio) (2023.6.0)\n",
"Collecting websockets<12.0,>=10.0 (from gradio-client==1.0.1->gradio)\n",
" Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (0.4)\n",
"Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (4.19.2)\n",
"Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (0.12.1)\n",
"Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (3.7.1)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (2024.6.2)\n",
"Collecting httpcore==1.* (from httpx>=0.24.1->gradio)\n",
" Downloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (3.7)\n",
"Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (1.3.1)\n",
"Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx>=0.24.1->gradio)\n",
" Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (3.14.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (4.66.4)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (1.2.1)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (4.53.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (1.4.5)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (3.1.2)\n",
"Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2023.4)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.1)\n",
"Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (0.7.0)\n",
"Requirement already satisfied: pydantic-core==2.18.4 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (2.18.4)\n",
"Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (8.1.7)\n",
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
"Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (13.7.1)\n",
"Collecting starlette<0.38.0,>=0.37.2 (from fastapi->gradio)\n",
" Downloading starlette-0.37.2-py3-none-any.whl (71 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting fastapi-cli>=0.0.2 (from fastapi->gradio)\n",
" Downloading fastapi_cli-0.0.4-py3-none-any.whl (9.5 kB)\n",
"Collecting ujson!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,>=4.0.1 (from fastapi->gradio)\n",
" Downloading ujson-5.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (53 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.6/53.6 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting email_validator>=2.0.0 (from fastapi->gradio)\n",
" Downloading email_validator-2.1.1-py3-none-any.whl (30 kB)\n",
"Collecting dnspython>=2.0.0 (from email_validator>=2.0.0->fastapi->gradio)\n",
" Downloading dnspython-2.6.1-py3-none-any.whl (307 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m307.7/307.7 kB\u001b[0m \u001b[31m19.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (23.2.0)\n",
"Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (2023.12.1)\n",
"Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.35.1)\n",
"Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.18.1)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio) (1.16.0)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.16.1)\n",
"Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx>=0.24.1->gradio) (1.2.1)\n",
"Collecting httptools>=0.5.0 (from uvicorn>=0.14.0->gradio)\n",
" Downloading httptools-0.6.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (341 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m22.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting python-dotenv>=0.13 (from uvicorn>=0.14.0->gradio)\n",
" Downloading python_dotenv-1.0.1-py3-none-any.whl (19 kB)\n",
"Collecting uvloop!=0.15.0,!=0.15.1,>=0.14.0 (from uvicorn>=0.14.0->gradio)\n",
" Downloading uvloop-0.19.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m48.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting watchfiles>=0.13 (from uvicorn>=0.14.0->gradio)\n",
" Downloading watchfiles-0.22.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m39.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.19.3->gradio) (3.3.2)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
"Building wheels for collected packages: ffmpy\n",
" Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for ffmpy: filename=ffmpy-0.3.2-py3-none-any.whl size=5584 sha256=731da06812274ce336835ac43c79d9ba64a9c9ccb0061d7629d4a175a0377a49\n",
" Stored in directory: /root/.cache/pip/wheels/bd/65/9a/671fc6dcde07d4418df0c592f8df512b26d7a0029c2a23dd81\n",
"Successfully built ffmpy\n",
"Installing collected packages: pydub, ffmpy, websockets, uvloop, ujson, tomlkit, semantic-version, ruff, python-multipart, python-dotenv, orjson, httptools, h11, dnspython, aiofiles, watchfiles, uvicorn, starlette, httpcore, email_validator, httpx, gradio-client, fastapi-cli, fastapi, gradio\n",
"Successfully installed aiofiles-23.2.1 dnspython-2.6.1 email_validator-2.1.1 fastapi-0.111.0 fastapi-cli-0.0.4 ffmpy-0.3.2 gradio-4.36.1 gradio-client-1.0.1 h11-0.14.0 httpcore-1.0.5 httptools-0.6.1 httpx-0.27.0 orjson-3.10.5 pydub-0.25.1 python-dotenv-1.0.1 python-multipart-0.0.9 ruff-0.4.9 semantic-version-2.10.0 starlette-0.37.2 tomlkit-0.12.0 ujson-5.10.0 uvicorn-0.30.1 uvloop-0.19.0 watchfiles-0.22.0 websockets-11.0.3\n",
"Setting queue=True in a Colab notebook requires sharing enabled. Setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
"\n",
"Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
"Running on public URL: https://605f087533ac265410.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<div><iframe src=\"https://605f087533ac265410.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": []
},
"metadata": {},
"execution_count": 1
}
],
"source": [
"#Scribbudies\n",
"!pip install gradio\n",
"import gradio as gr\n",
"\n",
"# 게임 상태를 저장할 변수들\n",
"prompts = []\n",
"drawings = []\n",
"texts = []\n",
"\n",
"# 주제 입력 및 그림 그리기\n",
"def input_prompt_and_draw(prompt, image):\n",
" global prompts, drawings\n",
" prompts.append(prompt)\n",
" drawings.append(image)\n",
" return (\"두 번째 플레이어가 그림을 보고 설명하는 문장을 입력하세요.\",\n",
" gr.update(visible=False), # 주제를 입력하는 부분 숨김\n",
" gr.update(visible=True, value=image), # 그림은 그대로 유지\n",
" gr.update(visible=True), # 문장 입력란 보임\n",
" gr.update(visible=True)) # 문장 제출 버튼 보임\n",
"\n",
"# 문장 입력\n",
"def input_text(text):\n",
" global texts, prompts\n",
" texts.append(text)\n",
" return (f\"모든 라운드가 끝났습니다.\\n주제: {prompts[-1]}\",\n",
" gr.update(visible=True, value=drawings[-1]), # 마지막 그림 유지\n",
" gr.update(visible=False), # 문장 입력란 숨김\n",
" gr.update(visible=True), # 결과 확인 버튼 보임\n",
" gr.update(visible=False)) # 문장 제출 버튼 숨김\n",
"\n",
"# 결과 확인\n",
"def end_game():\n",
" global prompts, texts\n",
" results = []\n",
" for i in range(len(prompts)):\n",
" result = f\"주제: {prompts[i]}\\n\"\n",
" if i < len(texts):\n",
" result += f\"문장: {texts[i]}\\n\"\n",
" results.append(result)\n",
"\n",
" # 현재 게임의 결과를 보여준 후, 리스트 초기화\n",
" final_result = \"모든 라운드가 끝났습니다.\\n\" + \"\\n\".join(results)\n",
" prompts.clear()\n",
" drawings.clear()\n",
" texts.clear()\n",
"\n",
" return final_result\n",
"\n",
"# Gradio 인터페이스 설정\n",
"with gr.Blocks() as demo:\n",
" prompt_input = gr.Textbox(label=\"주제를 입력하세요\")\n",
" draw_canvas = gr.Sketchpad(label=\"그림을 그리세요\", interactive=True)\n",
" draw_button = gr.Button(\"그림 제출\")\n",
" text_input = gr.Textbox(label=\"문장을 입력하세요\")\n",
" text_button = gr.Button(\"문장 제출\")\n",
" end_button = gr.Button(\"결과 확인\")\n",
" output = gr.Textbox(label=\"게임 결과\", interactive=False)\n",
"\n",
" # 처음 상태에서는 주제 입력란과 그림 그리기만 보임\n",
" prompt_input.submit(input_prompt_and_draw, inputs=[prompt_input, draw_canvas], outputs=[output, prompt_input, draw_canvas, text_input, text_button])\n",
" draw_button.click(input_prompt_and_draw, inputs=[prompt_input, draw_canvas], outputs=[output, prompt_input, draw_canvas, text_input, text_button])\n",
" text_button.click(input_text, inputs=text_input, outputs=[output, draw_canvas, text_input, end_button])\n",
" end_button.click(end_game, inputs=None, outputs=output)\n",
"\n",
"# Gradio 인터페이스 실행\n",
"demo.launch()"
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "Y-ZRnj84FddJ"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#Grammar Quiz\n",
"import gradio as gr\n",
"\n",
"# The story \"The Circle of Discovery\" with blanks for cloze questions\n",
"story = \"https://raw.githubusercontent.com/MK316/Spring2024/main/DLEE/Project/story06.txt\"\n",
"\n",
"# Cloze questions\n",
"cloze_questions = [\n",
" {\"question\": \"An enigmatic symbol known as 'śūnya' ________ (discover) by Idris in a text from India.\", \"answer\": \"was discovered\"},\n",
" {\"question\": \"Idris,_____ found solace amidst the dusty scrolls and ancient manuscripts, embarked on a journey that would forever alter the course of mathematical history.\", \"answer\": \"who\"},\n",
" {\"question\": \"This book _______ (borrow) from the library yesterday.\", \"answer\": \"was borrowed\"},\n",
" {\"question\": \"The new smartphone,_______ was released last week, has received rave reviews from tech enthusiasts.\", \"answer\": \"which\"},\n",
"\n",
"]\n",
"\n",
"# Function to handle the cloze quiz\n",
"def cloze_quiz(name, *answers):\n",
" score = 0\n",
" results = []\n",
" for i, question in enumerate(cloze_questions):\n",
" if answers[i].strip().lower() == question[\"answer\"].lower():\n",
" score += 1\n",
" results.append(f\"Question {i+1}: Correct\\n\")\n",
" else:\n",
" results.append(f\"Question {i+1}: Incorrect, the correct answer is: {question['answer']}\\n\")\n",
" result_text = f\"* Name: {name}\\n* Score: {score} out of {len(cloze_questions)}\\n\" + \"\\n\".join(results)\n",
"\n",
" return result_text\n",
"\n",
"# Add the input for the name\n",
"inputs = [gr.Textbox(label=\"Enter your name\")] + [gr.Textbox(label=q[\"question\"]) for q in cloze_questions]\n",
"outputs = [gr.Textbox(label=\"Results\")]\n",
"\n",
"iface = gr.Interface(fn=cloze_quiz, inputs=inputs, outputs=outputs, description=\"Cloze Quiz for 'The Circle of Discovery'\")\n",
"iface.launch(share=True)\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 609
},
"id": "0FTdQ-jw30VJ",
"outputId": "e74927b4-c9da-4b9b-877f-0622cd352612"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
"Running on public URL: https://83a37d35ae65a0d603.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<div><iframe src=\"https://83a37d35ae65a0d603.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": []
},
"metadata": {},
"execution_count": 3
}
]
},
{
"cell_type": "code",
"source": [
"#Content Quiz\n",
"import gradio as gr\n",
"\n",
"story = \"https://raw.githubusercontent.com/MK316/Spring2024/main/DLEE/Project/story06.txt\"\n",
"\n",
"# Define the comprehension questions\n",
"questions = [\n",
" {\"question\": \"1. In which ancient city was the fabled House of Wisdom located?\", \"options\": [\"Cairo\", \"Baghdad\", \"Damascus\",\"Isfahan\"], \"answer\": \"Baghdad\"},\n",
" {\"question\": \"2. What does the term 'śūnya' mean?\", \"options\": [\"Infinity\", \"Empty or Zero\", \"One\",\"Whole\"], \"answer\": \"Empty or Zero\"},\n",
" {\"question\": \"3. From which land did Idris discover the significance of 'zero'?\", \"options\": [\"Greece\", \"China\", \"India\",\"Persia\"], \"answer\": \"India\"},\n",
" {\"question\": \"4. In which fields did Idris's research on zero play a pivotal role?\", \"options\": [\"Biology\", \"Physics\", \"Mathematics and Astronomy\",\"Literature\"], \"answer\": \"Mathematics and Astronomy\"},\n",
" {\"question\": \"5. What was the name of the fabled place of knowledge and scholarship in ancient Baghdad where Idris studied?\", \"options\": [\"The Library of Alexandria\", \"The Academy of Athens\", \"The House of Wisdom\",\"The University of Constantinople\"], \"answer\": \"The House of Wisdom\"},]\n",
"\n",
"\n",
"# Function to display the story and ask questions\n",
"def quiz(*answers):\n",
" score = 0\n",
" incorrect = []\n",
" for i, question in enumerate(questions):\n",
" if answers[i] == question[\"answer\"]:\n",
" score += 1\n",
" else:\n",
" incorrect.append(f\"Question {i+1}: Correct answer is {question['answer']}\")\n",
" results = \"\\n\".join(incorrect)\n",
" return score, results\n",
"\n",
"story_display = gr.Markdown(story)\n",
"inputs = [gr.Radio(label=q[\"question\"], choices=q[\"options\"]) for q in questions]\n",
"outputs = [gr.Textbox(label=\"Score\"), gr.Textbox(label=\"Incorrect Answers\")]\n",
"\n",
"iface = gr.Interface(fn=quiz, inputs=inputs, outputs=outputs, description=\"Comprehension Quiz for 'The Circle of Discovery'\")\n",
"iface.launch(share=True)\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 609
},
"id": "_Gz_iywn9mvv",
"outputId": "a0f0d727-f373-4ffa-8fd3-6bc02f7a38bf"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
"Running on public URL: https://675a8f05fb8f58d8fa.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<div><iframe src=\"https://675a8f05fb8f58d8fa.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": []
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "code",
"source": [
"#Word List\n",
"!pip install gradio\n",
"!pip install gtts\n",
"\n",
"import gradio as gr\n",
"from gtts import gTTS\n",
"\n",
"# List of terms and translations\n",
"terms = [\n",
" (\"Baghdad\", \"바그다드\"),\n",
" (\"House of Wisdom\", \"지혜의 집\"),\n",
" (\"scholar\", \"학자\"),\n",
" (\"manuscripts\", \"원고, 사본\"),\n",
" (\"cosmos\", \"우주\"),\n",
" (\"numbers\", \"숫자\"),\n",
" (\"India\", \"인도\"),\n",
" (\"śūnya, zero\", \"슈냐 (제로)\"),\n",
" (\"calculation\", \"계산\"),\n",
" (\"origins\", \"기원\"),\n",
" (\"implications\", \"함의, 영향\"),\n",
" (\"astronomy\", \"천문학\"),\n",
" (\"placeholder\", \"자리 표시자\"),\n",
" (\"possibility\", \"가능성\"),\n",
" (\"treatises\", \"논문\"),\n",
" (\"algorithms\", \"알고리즘\"),\n",
" (\"algebra\", \"대수학\"),\n",
" (\"numerical understanding\", \"숫자 이해\"),\n",
" (\"legacy\", \"유산\")\n",
"]\n",
"\n",
"# Text-to-Speech function\n",
"def text_to_speech(text):\n",
" tts = gTTS(text=text, lang='en')\n",
" filename = f\"{text}.mp3\"\n",
" tts.save(filename)\n",
" return filename\n",
"\n",
"# Function to play text\n",
"def play_text(text):\n",
" audio_file = text_to_speech(text)\n",
" return audio_file\n",
"\n",
"# Generate the Gradio interface\n",
"with gr.Blocks() as demo:\n",
" audio = gr.Audio(label=\"Pronunciation\", autoplay=True)\n",
"\n",
" for eng, kor in terms:\n",
" with gr.Row():\n",
" with gr.Column():\n",
" button = gr.Button(eng)\n",
" button.click(fn=play_text, inputs=gr.State(eng), outputs=audio)\n",
" gr.Markdown(f\"**{kor}**\")\n",
"\n",
" demo.launch()\n",
"\n"
],
"metadata": {
"id": "4TsjQFW1F1Ew"
},
"execution_count": null,
"outputs": []
}
]
}
| null |
Non_BioNLP
|
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyMw5Z1eibIWaXObvpLKkH4A",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/psy03/G6-finalproject/blob/main/Presentation.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "uCLV4w06R0Hp",
"outputId": "7ec2aa3c-d3b4-4347-c77b-a23140f57069"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting gradio\n",
" Downloading gradio-4.36.1-py3-none-any.whl (12.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.3/12.3 MB\u001b[0m \u001b[31m18.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting aiofiles<24.0,>=22.0 (from gradio)\n",
" Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
"Requirement already satisfied: altair<6.0,>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.2.2)\n",
"Collecting fastapi (from gradio)\n",
" Downloading fastapi-0.111.0-py3-none-any.whl (91 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.0/92.0 kB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting ffmpy (from gradio)\n",
" Downloading ffmpy-0.3.2.tar.gz (5.5 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting gradio-client==1.0.1 (from gradio)\n",
" Downloading gradio_client-1.0.1-py3-none-any.whl (318 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m318.1/318.1 kB\u001b[0m \u001b[31m17.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting httpx>=0.24.1 (from gradio)\n",
" Downloading httpx-0.27.0-py3-none-any.whl (75 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: huggingface-hub>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.23.3)\n",
"Requirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.4.0)\n",
"Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.1.4)\n",
"Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.1.5)\n",
"Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.7.1)\n",
"Requirement already satisfied: numpy<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.25.2)\n",
"Collecting orjson~=3.0 (from gradio)\n",
" Downloading orjson-3.10.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (144 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m145.0/145.0 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio) (24.1)\n",
"Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.0.3)\n",
"Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (9.4.0)\n",
"Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.7.3)\n",
"Collecting pydub (from gradio)\n",
" Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
"Collecting python-multipart>=0.0.9 (from gradio)\n",
" Downloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n",
"Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.0.1)\n",
"Collecting ruff>=0.2.2 (from gradio)\n",
" Downloading ruff-0.4.9-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.8/8.8 MB\u001b[0m \u001b[31m27.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting semantic-version~=2.0 (from gradio)\n",
" Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
"Collecting tomlkit==0.12.0 (from gradio)\n",
" Downloading tomlkit-0.12.0-py3-none-any.whl (37 kB)\n",
"Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.12.3)\n",
"Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.12.2)\n",
"Requirement already satisfied: urllib3~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.0.7)\n",
"Collecting uvicorn>=0.14.0 (from gradio)\n",
" Downloading uvicorn-0.30.1-py3-none-any.whl (62 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.4/62.4 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==1.0.1->gradio) (2023.6.0)\n",
"Collecting websockets<12.0,>=10.0 (from gradio-client==1.0.1->gradio)\n",
" Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (0.4)\n",
"Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (4.19.2)\n",
"Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (0.12.1)\n",
"Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (3.7.1)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (2024.6.2)\n",
"Collecting httpcore==1.* (from httpx>=0.24.1->gradio)\n",
" Downloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (3.7)\n",
"Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (1.3.1)\n",
"Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx>=0.24.1->gradio)\n",
" Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (3.14.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (4.66.4)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (1.2.1)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (4.53.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (1.4.5)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (3.1.2)\n",
"Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2023.4)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.1)\n",
"Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (0.7.0)\n",
"Requirement already satisfied: pydantic-core==2.18.4 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (2.18.4)\n",
"Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (8.1.7)\n",
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
"Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (13.7.1)\n",
"Collecting starlette<0.38.0,>=0.37.2 (from fastapi->gradio)\n",
" Downloading starlette-0.37.2-py3-none-any.whl (71 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting fastapi-cli>=0.0.2 (from fastapi->gradio)\n",
" Downloading fastapi_cli-0.0.4-py3-none-any.whl (9.5 kB)\n",
"Collecting ujson!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,>=4.0.1 (from fastapi->gradio)\n",
" Downloading ujson-5.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (53 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.6/53.6 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting email_validator>=2.0.0 (from fastapi->gradio)\n",
" Downloading email_validator-2.1.1-py3-none-any.whl (30 kB)\n",
"Collecting dnspython>=2.0.0 (from email_validator>=2.0.0->fastapi->gradio)\n",
" Downloading dnspython-2.6.1-py3-none-any.whl (307 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m307.7/307.7 kB\u001b[0m \u001b[31m19.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (23.2.0)\n",
"Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (2023.12.1)\n",
"Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.35.1)\n",
"Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.18.1)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio) (1.16.0)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.16.1)\n",
"Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx>=0.24.1->gradio) (1.2.1)\n",
"Collecting httptools>=0.5.0 (from uvicorn>=0.14.0->gradio)\n",
" Downloading httptools-0.6.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (341 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m22.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting python-dotenv>=0.13 (from uvicorn>=0.14.0->gradio)\n",
" Downloading python_dotenv-1.0.1-py3-none-any.whl (19 kB)\n",
"Collecting uvloop!=0.15.0,!=0.15.1,>=0.14.0 (from uvicorn>=0.14.0->gradio)\n",
" Downloading uvloop-0.19.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m48.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting watchfiles>=0.13 (from uvicorn>=0.14.0->gradio)\n",
" Downloading watchfiles-0.22.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m39.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.19.3->gradio) (3.3.2)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
"Building wheels for collected packages: ffmpy\n",
" Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for ffmpy: filename=ffmpy-0.3.2-py3-none-any.whl size=5584 sha256=731da06812274ce336835ac43c79d9ba64a9c9ccb0061d7629d4a175a0377a49\n",
" Stored in directory: /root/.cache/pip/wheels/bd/65/9a/671fc6dcde07d4418df0c592f8df512b26d7a0029c2a23dd81\n",
"Successfully built ffmpy\n",
"Installing collected packages: pydub, ffmpy, websockets, uvloop, ujson, tomlkit, semantic-version, ruff, python-multipart, python-dotenv, orjson, httptools, h11, dnspython, aiofiles, watchfiles, uvicorn, starlette, httpcore, email_validator, httpx, gradio-client, fastapi-cli, fastapi, gradio\n",
"Successfully installed aiofiles-23.2.1 dnspython-2.6.1 email_validator-2.1.1 fastapi-0.111.0 fastapi-cli-0.0.4 ffmpy-0.3.2 gradio-4.36.1 gradio-client-1.0.1 h11-0.14.0 httpcore-1.0.5 httptools-0.6.1 httpx-0.27.0 orjson-3.10.5 pydub-0.25.1 python-dotenv-1.0.1 python-multipart-0.0.9 ruff-0.4.9 semantic-version-2.10.0 starlette-0.37.2 tomlkit-0.12.0 ujson-5.10.0 uvicorn-0.30.1 uvloop-0.19.0 watchfiles-0.22.0 websockets-11.0.3\n",
"Setting queue=True in a Colab notebook requires sharing enabled. Setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
"\n",
"Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
"Running on public URL: https://605f087533ac265410.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<div><iframe src=\"https://605f087533ac265410.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": []
},
"metadata": {},
"execution_count": 1
}
],
"source": [
"#Scribbudies\n",
"!pip install gradio\n",
"import gradio as gr\n",
"\n",
"# 게임 상태를 저장할 변수들\n",
"prompts = []\n",
"drawings = []\n",
"texts = []\n",
"\n",
"# 주제 입력 및 그림 그리기\n",
"def input_prompt_and_draw(prompt, image):\n",
" global prompts, drawings\n",
" prompts.append(prompt)\n",
" drawings.append(image)\n",
" return (\"두 번째 플레이어가 그림을 보고 설명하는 문장을 입력하세요.\",\n",
" gr.update(visible=False), # 주제를 입력하는 부분 숨김\n",
" gr.update(visible=True, value=image), # 그림은 그대로 유지\n",
" gr.update(visible=True), # 문장 입력란 보임\n",
" gr.update(visible=True)) # 문장 제출 버튼 보임\n",
"\n",
"# 문장 입력\n",
"def input_text(text):\n",
" global texts, prompts\n",
" texts.append(text)\n",
" return (f\"모든 라운드가 끝났습니다.\\n주제: {prompts[-1]}\",\n",
" gr.update(visible=True, value=drawings[-1]), # 마지막 그림 유지\n",
" gr.update(visible=False), # 문장 입력란 숨김\n",
" gr.update(visible=True), # 결과 확인 버튼 보임\n",
" gr.update(visible=False)) # 문장 제출 버튼 숨김\n",
"\n",
"# 결과 확인\n",
"def end_game():\n",
" global prompts, texts\n",
" results = []\n",
" for i in range(len(prompts)):\n",
" result = f\"주제: {prompts[i]}\\n\"\n",
" if i < len(texts):\n",
" result += f\"문장: {texts[i]}\\n\"\n",
" results.append(result)\n",
"\n",
" # 현재 게임의 결과를 보여준 후, 리스트 초기화\n",
" final_result = \"모든 라운드가 끝났습니다.\\n\" + \"\\n\".join(results)\n",
" prompts.clear()\n",
" drawings.clear()\n",
" texts.clear()\n",
"\n",
" return final_result\n",
"\n",
"# Gradio 인터페이스 설정\n",
"with gr.Blocks() as demo:\n",
" prompt_input = gr.Textbox(label=\"주제를 입력하세요\")\n",
" draw_canvas = gr.Sketchpad(label=\"그림을 그리세요\", interactive=True)\n",
" draw_button = gr.Button(\"그림 제출\")\n",
" text_input = gr.Textbox(label=\"문장을 입력하세요\")\n",
" text_button = gr.Button(\"문장 제출\")\n",
" end_button = gr.Button(\"결과 확인\")\n",
" output = gr.Textbox(label=\"게임 결과\", interactive=False)\n",
"\n",
" # 처음 상태에서는 주제 입력란과 그림 그리기만 보임\n",
" prompt_input.submit(input_prompt_and_draw, inputs=[prompt_input, draw_canvas], outputs=[output, prompt_input, draw_canvas, text_input, text_button])\n",
" draw_button.click(input_prompt_and_draw, inputs=[prompt_input, draw_canvas], outputs=[output, prompt_input, draw_canvas, text_input, text_button])\n",
" text_button.click(input_text, inputs=text_input, outputs=[output, draw_canvas, text_input, end_button])\n",
" end_button.click(end_game, inputs=None, outputs=output)\n",
"\n",
"# Gradio 인터페이스 실행\n",
"demo.launch()"
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "Y-ZRnj84FddJ"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#Grammar Quiz\n",
"import gradio as gr\n",
"\n",
"# The story \"The Circle of Discovery\" with blanks for cloze questions\n",
"story = \"https://raw.githubusercontent.com/MK316/Spring2024/main/DLEE/Project/story06.txt\"\n",
"\n",
"# Cloze questions\n",
"cloze_questions = [\n",
" {\"question\": \"An enigmatic symbol known as 'śūnya' ________ (discover) by Idris in a text from India.\", \"answer\": \"was discovered\"},\n",
" {\"question\": \"Idris,_____ found solace amidst the dusty scrolls and ancient manuscripts, embarked on a journey that would forever alter the course of mathematical history.\", \"answer\": \"who\"},\n",
" {\"question\": \"This book _______ (borrow) from the library yesterday.\", \"answer\": \"was borrowed\"},\n",
" {\"question\": \"The new smartphone,_______ was released last week, has received rave reviews from tech enthusiasts.\", \"answer\": \"which\"},\n",
"\n",
"]\n",
"\n",
"# Function to handle the cloze quiz\n",
"def cloze_quiz(name, *answers):\n",
" score = 0\n",
" results = []\n",
" for i, question in enumerate(cloze_questions):\n",
" if answers[i].strip().lower() == question[\"answer\"].lower():\n",
" score += 1\n",
" results.append(f\"Question {i+1}: Correct\\n\")\n",
" else:\n",
" results.append(f\"Question {i+1}: Incorrect, the correct answer is: {question['answer']}\\n\")\n",
" result_text = f\"* Name: {name}\\n* Score: {score} out of {len(cloze_questions)}\\n\" + \"\\n\".join(results)\n",
"\n",
" return result_text\n",
"\n",
"# Add the input for the name\n",
"inputs = [gr.Textbox(label=\"Enter your name\")] + [gr.Textbox(label=q[\"question\"]) for q in cloze_questions]\n",
"outputs = [gr.Textbox(label=\"Results\")]\n",
"\n",
"iface = gr.Interface(fn=cloze_quiz, inputs=inputs, outputs=outputs, description=\"Cloze Quiz for 'The Circle of Discovery'\")\n",
"iface.launch(share=True)\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 609
},
"id": "0FTdQ-jw30VJ",
"outputId": "e74927b4-c9da-4b9b-877f-0622cd352612"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
"Running on public URL: https://83a37d35ae65a0d603.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<div><iframe src=\"https://83a37d35ae65a0d603.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": []
},
"metadata": {},
"execution_count": 3
}
]
},
{
"cell_type": "code",
"source": [
"#Content Quiz\n",
"import gradio as gr\n",
"\n",
"story = \"https://raw.githubusercontent.com/MK316/Spring2024/main/DLEE/Project/story06.txt\"\n",
"\n",
"# Define the comprehension questions\n",
"questions = [\n",
" {\"question\": \"1. In which ancient city was the fabled House of Wisdom located?\", \"options\": [\"Cairo\", \"Baghdad\", \"Damascus\",\"Isfahan\"], \"answer\": \"Baghdad\"},\n",
" {\"question\": \"2. What does the term 'śūnya' mean?\", \"options\": [\"Infinity\", \"Empty or Zero\", \"One\",\"Whole\"], \"answer\": \"Empty or Zero\"},\n",
" {\"question\": \"3. From which land did Idris discover the significance of 'zero'?\", \"options\": [\"Greece\", \"China\", \"India\",\"Persia\"], \"answer\": \"India\"},\n",
" {\"question\": \"4. In which fields did Idris's research on zero play a pivotal role?\", \"options\": [\"Biology\", \"Physics\", \"Mathematics and Astronomy\",\"Literature\"], \"answer\": \"Mathematics and Astronomy\"},\n",
" {\"question\": \"5. What was the name of the fabled place of knowledge and scholarship in ancient Baghdad where Idris studied?\", \"options\": [\"The Library of Alexandria\", \"The Academy of Athens\", \"The House of Wisdom\",\"The University of Constantinople\"], \"answer\": \"The House of Wisdom\"},]\n",
"\n",
"\n",
"# Function to display the story and ask questions\n",
"def quiz(*answers):\n",
" score = 0\n",
" incorrect = []\n",
" for i, question in enumerate(questions):\n",
" if answers[i] == question[\"answer\"]:\n",
" score += 1\n",
" else:\n",
" incorrect.append(f\"Question {i+1}: Correct answer is {question['answer']}\")\n",
" results = \"\\n\".join(incorrect)\n",
" return score, results\n",
"\n",
"story_display = gr.Markdown(story)\n",
"inputs = [gr.Radio(label=q[\"question\"], choices=q[\"options\"]) for q in questions]\n",
"outputs = [gr.Textbox(label=\"Score\"), gr.Textbox(label=\"Incorrect Answers\")]\n",
"\n",
"iface = gr.Interface(fn=quiz, inputs=inputs, outputs=outputs, description=\"Comprehension Quiz for 'The Circle of Discovery'\")\n",
"iface.launch(share=True)\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 609
},
"id": "_Gz_iywn9mvv",
"outputId": "a0f0d727-f373-4ffa-8fd3-6bc02f7a38bf"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
"Running on public URL: https://675a8f05fb8f58d8fa.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<div><iframe src=\"https://675a8f05fb8f58d8fa.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": []
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "code",
"source": [
"#Word List\n",
"!pip install gradio\n",
"!pip install gtts\n",
"\n",
"import gradio as gr\n",
"from gtts import gTTS\n",
"\n",
"# List of terms and translations\n",
"terms = [\n",
" (\"Baghdad\", \"바그다드\"),\n",
" (\"House of Wisdom\", \"지혜의 집\"),\n",
" (\"scholar\", \"학자\"),\n",
" (\"manuscripts\", \"원고, 사본\"),\n",
" (\"cosmos\", \"우주\"),\n",
" (\"numbers\", \"숫자\"),\n",
" (\"India\", \"인도\"),\n",
" (\"śūnya, zero\", \"슈냐 (제로)\"),\n",
" (\"calculation\", \"계산\"),\n",
" (\"origins\", \"기원\"),\n",
" (\"implications\", \"함의, 영향\"),\n",
" (\"astronomy\", \"천문학\"),\n",
" (\"placeholder\", \"자리 표시자\"),\n",
" (\"possibility\", \"가능성\"),\n",
" (\"treatises\", \"논문\"),\n",
" (\"algorithms\", \"알고리즘\"),\n",
" (\"algebra\", \"대수학\"),\n",
" (\"numerical understanding\", \"숫자 이해\"),\n",
" (\"legacy\", \"유산\")\n",
"]\n",
"\n",
"# Text-to-Speech function\n",
"def text_to_speech(text):\n",
" tts = gTTS(text=text, lang='en')\n",
" filename = f\"{text}.mp3\"\n",
" tts.save(filename)\n",
" return filename\n",
"\n",
"# Function to play text\n",
"def play_text(text):\n",
" audio_file = text_to_speech(text)\n",
" return audio_file\n",
"\n",
"# Generate the Gradio interface\n",
"with gr.Blocks() as demo:\n",
" audio = gr.Audio(label=\"Pronunciation\", autoplay=True)\n",
"\n",
" for eng, kor in terms:\n",
" with gr.Row():\n",
" with gr.Column():\n",
" button = gr.Button(eng)\n",
" button.click(fn=play_text, inputs=gr.State(eng), outputs=audio)\n",
" gr.Markdown(f\"**{kor}**\")\n",
"\n",
" demo.launch()\n",
"\n"
],
"metadata": {
"id": "4TsjQFW1F1Ew"
},
"execution_count": null,
"outputs": []
}
]
}
|
{}
|
task
|
[
"TRANSLATION"
] | 43,874 |
mini1013/master_cate_fi1
|
mini1013
|
text-classification
|
[
"setfit",
"safetensors",
"roberta",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:mini1013/master_domain",
"base_model:finetune:mini1013/master_domain",
"model-index",
"region:us"
] | 2025-01-21T19:03:53Z |
2025-01-21T19:04:19+00:00
| 220 | 0 |
---
base_model: mini1013/master_domain
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 모던탑21 모던 클래식 800 3단 장식장 가구/인테리어>거실가구>장식장
- text: 스코나 마넌트 아쿠아텍스 패브릭 1인 리클라이너 소파 가구/인테리어>거실가구>소파>리클라이너소파
- text: 가구느낌 베스트책상 1000x400 접이식 간이 테이블 가구/인테리어>거실가구>테이블>접이식테이블
- text: 자코모 러버블 컴팩트 4인 스위브 소파 + 스툴 가구/인테리어>거실가구>소파>패브릭소파
- text: 미드센추리테이블 유리좌탁 거실소파테이블 1000 가구/인테리어>거실가구>테이블>거실테이블
inference: true
model-index:
- name: SetFit with mini1013/master_domain
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 1.0
name: Accuracy
---
# SetFit with mini1013/master_domain
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [mini1013/master_domain](https://huggingface.co/mini1013/master_domain) 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:** [mini1013/master_domain](https://huggingface.co/mini1013/master_domain)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 4 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 |
|:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 1.0 | <ul><li>'에싸 라보엠Ⅲ 4인 오픈코너형 기능성 카시미라 패브릭 소파 가구/인테리어>거실가구>소파>패브릭소파'</li><li>'보루네오 플레타 3인용 천연소가죽 소파 가구/인테리어>거실가구>소파>가죽소파'</li><li>'동서가구 프라임 소나무원목 내추럴 황토 카우치 흙소파 DF638379 가구/인테리어>거실가구>소파>흙/돌소파'</li></ul> |
| 2.0 | <ul><li>'체스 유리 진열장 가구/인테리어>거실가구>장식장'</li><li>'디자인벤처스 로맨틱 1800 유리장 가구/인테리어>거실가구>장식장'</li><li>'퍼니처스마트 로랜드 유리 장식장 가구/인테리어>거실가구>장식장'</li></ul> |
| 0.0 | <ul><li>'나무뜰 켄트 서랍형 거실장 1200 티비다이 MRF013 가구/인테리어>거실가구>TV거실장'</li><li>'리바트 셀리나 1800 거실장 가구/인테리어>거실가구>TV거실장'</li><li>'슈퍼홈 리처 티비다이 낮은 거실장 2000 가구/인테리어>거실가구>TV거실장'</li></ul> |
| 3.0 | <ul><li>'테이블 거실 커피 탁자 북유럽 좌식 인테리어 티 모던 카페 라운드 가구/인테리어>거실가구>테이블>거실테이블'</li><li>'미드센추리 테라조 협탁 사이드 테이블 거실 소파 장식장 선반형 가구/인테리어>거실가구>테이블>사이드테이블'</li><li>'원목좌식테이블 방석 세트 원형 차 홈 카페 거실 가구/인테리어>거실가구>테이블>거실테이블'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 1.0 |
## 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("mini1013/master_cate_fi1")
# Run inference
preds = model("모던탑21 모던 클래식 800 3단 장식장 가구/인테리어>거실가구>장식장")
```
<!--
### 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 | 4 | 8.1714 | 18 |
| Label | Training Sample Count |
|:------|:----------------------|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 70 |
| 3.0 | 70 |
### Training Hyperparameters
- batch_size: (256, 256)
- num_epochs: (30, 30)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 50
- 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 |
|:-------:|:----:|:-------------:|:---------------:|
| 0.0182 | 1 | 0.4862 | - |
| 0.9091 | 50 | 0.4961 | - |
| 1.8182 | 100 | 0.4367 | - |
| 2.7273 | 150 | 0.0317 | - |
| 3.6364 | 200 | 0.0 | - |
| 4.5455 | 250 | 0.0 | - |
| 5.4545 | 300 | 0.0 | - |
| 6.3636 | 350 | 0.0 | - |
| 7.2727 | 400 | 0.0 | - |
| 8.1818 | 450 | 0.0 | - |
| 9.0909 | 500 | 0.0 | - |
| 10.0 | 550 | 0.0 | - |
| 10.9091 | 600 | 0.0 | - |
| 11.8182 | 650 | 0.0 | - |
| 12.7273 | 700 | 0.0 | - |
| 13.6364 | 750 | 0.0 | - |
| 14.5455 | 800 | 0.0 | - |
| 15.4545 | 850 | 0.0 | - |
| 16.3636 | 900 | 0.0 | - |
| 17.2727 | 950 | 0.0 | - |
| 18.1818 | 1000 | 0.0 | - |
| 19.0909 | 1050 | 0.0 | - |
| 20.0 | 1100 | 0.0 | - |
| 20.9091 | 1150 | 0.0 | - |
| 21.8182 | 1200 | 0.0 | - |
| 22.7273 | 1250 | 0.0 | - |
| 23.6364 | 1300 | 0.0 | - |
| 24.5455 | 1350 | 0.0 | - |
| 25.4545 | 1400 | 0.0 | - |
| 26.3636 | 1450 | 0.0 | - |
| 27.2727 | 1500 | 0.0 | - |
| 28.1818 | 1550 | 0.0 | - |
| 29.0909 | 1600 | 0.0 | - |
| 30.0 | 1650 | 0.0 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.3.1
- Transformers: 4.44.2
- PyTorch: 2.2.0a0+81ea7a4
- Datasets: 3.2.0
- 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 mini1013/master_domain
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [mini1013/master_domain](https://huggingface.co/mini1013/master_domain) 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:** [mini1013/master_domain](https://huggingface.co/mini1013/master_domain)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 4 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 |
|:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 1.0 | <ul><li>'에싸 라보엠Ⅲ 4인 오픈코너형 기능성 카시미라 패브릭 소파 가구/인테리어>거실가구>소파>패브릭소파'</li><li>'보루네오 플레타 3인용 천연소가죽 소파 가구/인테리어>거실가구>소파>가죽소파'</li><li>'동서가구 프라임 소나무원목 내추럴 황토 카우치 흙소파 DF638379 가구/인테리어>거실가구>소파>흙/돌소파'</li></ul> |
| 2.0 | <ul><li>'체스 유리 진열장 가구/인테리어>거실가구>장식장'</li><li>'디자인벤처스 로맨틱 1800 유리장 가구/인테리어>거실가구>장식장'</li><li>'퍼니처스마트 로랜드 유리 장식장 가구/인테리어>거실가구>장식장'</li></ul> |
| 0.0 | <ul><li>'나무뜰 켄트 서랍형 거실장 1200 티비다이 MRF013 가구/인테리어>거실가구>TV거실장'</li><li>'리바트 셀리나 1800 거실장 가구/인테리어>거실가구>TV거실장'</li><li>'슈퍼홈 리처 티비다이 낮은 거실장 2000 가구/인테리어>거실가구>TV거실장'</li></ul> |
| 3.0 | <ul><li>'테이블 거실 커피 탁자 북유럽 좌식 인테리어 티 모던 카페 라운드 가구/인테리어>거실가구>테이블>거실테이블'</li><li>'미드센추리 테라조 협탁 사이드 테이블 거실 소파 장식장 선반형 가구/인테리어>거실가구>테이블>사이드테이블'</li><li>'원목좌식테이블 방석 세트 원형 차 홈 카페 거실 가구/인테리어>거실가구>테이블>거실테이블'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 1.0 |
## 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("mini1013/master_cate_fi1")
# Run inference
preds = model("모던탑21 모던 클래식 800 3단 장식장 가구/인테리어>거실가구>장식장")
```
<!--
### 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 | 4 | 8.1714 | 18 |
| Label | Training Sample Count |
|:------|:----------------------|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 70 |
| 3.0 | 70 |
### Training Hyperparameters
- batch_size: (256, 256)
- num_epochs: (30, 30)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 50
- 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 |
|:-------:|:----:|:-------------:|:---------------:|
| 0.0182 | 1 | 0.4862 | - |
| 0.9091 | 50 | 0.4961 | - |
| 1.8182 | 100 | 0.4367 | - |
| 2.7273 | 150 | 0.0317 | - |
| 3.6364 | 200 | 0.0 | - |
| 4.5455 | 250 | 0.0 | - |
| 5.4545 | 300 | 0.0 | - |
| 6.3636 | 350 | 0.0 | - |
| 7.2727 | 400 | 0.0 | - |
| 8.1818 | 450 | 0.0 | - |
| 9.0909 | 500 | 0.0 | - |
| 10.0 | 550 | 0.0 | - |
| 10.9091 | 600 | 0.0 | - |
| 11.8182 | 650 | 0.0 | - |
| 12.7273 | 700 | 0.0 | - |
| 13.6364 | 750 | 0.0 | - |
| 14.5455 | 800 | 0.0 | - |
| 15.4545 | 850 | 0.0 | - |
| 16.3636 | 900 | 0.0 | - |
| 17.2727 | 950 | 0.0 | - |
| 18.1818 | 1000 | 0.0 | - |
| 19.0909 | 1050 | 0.0 | - |
| 20.0 | 1100 | 0.0 | - |
| 20.9091 | 1150 | 0.0 | - |
| 21.8182 | 1200 | 0.0 | - |
| 22.7273 | 1250 | 0.0 | - |
| 23.6364 | 1300 | 0.0 | - |
| 24.5455 | 1350 | 0.0 | - |
| 25.4545 | 1400 | 0.0 | - |
| 26.3636 | 1450 | 0.0 | - |
| 27.2727 | 1500 | 0.0 | - |
| 28.1818 | 1550 | 0.0 | - |
| 29.0909 | 1600 | 0.0 | - |
| 30.0 | 1650 | 0.0 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.3.1
- Transformers: 4.44.2
- PyTorch: 2.2.0a0+81ea7a4
- Datasets: 3.2.0
- 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": "mini1013/master_domain", "library_name": "setfit", "metrics": ["accuracy"], "pipeline_tag": "text-classification", "tags": ["setfit", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "widget": [{"text": "모던탑21 모던 클래식 800 3단 장식장 가구/인테리어>거실가구>장식장"}, {"text": "스코나 마넌트 아쿠아텍스 패브릭 1인 리클라이너 소파 가구/인테리어>거실가구>소파>리클라이너소파"}, {"text": "가구느낌 베스트책상 1000x400 접이식 간이 테이블 가구/인테리어>거실가구>테이블>접이식테이블"}, {"text": "자코모 러버블 컴팩트 4인 스위브 소파 + 스툴 가구/인테리어>거실가구>소파>패브릭소파"}, {"text": "미드센추리테이블 유리좌탁 거실소파테이블 1000 가구/인테리어>거실가구>테이블>거실테이블"}], "inference": true, "model-index": [{"name": "SetFit with mini1013/master_domain", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "Unknown", "type": "unknown", "split": "test"}, "metrics": [{"type": "accuracy", "value": 1.0, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,875 |
gokuls/hbertv1-emotion-logit_KD-tiny_ffn_0.5
|
gokuls
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"hybridbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5",
"base_model:finetune:gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2023-11-26T00:48:07Z |
2023-11-26T00:50:21+00:00
| 4 | 0 |
---
base_model: gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5
datasets:
- emotion
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: hbertv1-emotion-logit_KD-tiny_ffn_0.5
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.8945
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. -->
# hbertv1-emotion-logit_KD-tiny_ffn_0.5
This model is a fine-tuned version of [gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5](https://huggingface.co/gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5131
- Accuracy: 0.8945
## 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: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 3.1241 | 1.0 | 250 | 2.5267 | 0.5775 |
| 2.0224 | 2.0 | 500 | 1.4869 | 0.748 |
| 1.2988 | 3.0 | 750 | 0.9838 | 0.836 |
| 0.9355 | 4.0 | 1000 | 0.7613 | 0.8535 |
| 0.7507 | 5.0 | 1250 | 0.6392 | 0.8805 |
| 0.6071 | 6.0 | 1500 | 0.5669 | 0.888 |
| 0.5377 | 7.0 | 1750 | 0.5131 | 0.8945 |
| 0.4707 | 8.0 | 2000 | 0.5133 | 0.8935 |
| 0.4223 | 9.0 | 2250 | 0.5078 | 0.8905 |
| 0.3933 | 10.0 | 2500 | 0.5156 | 0.8855 |
| 0.3612 | 11.0 | 2750 | 0.4883 | 0.894 |
| 0.3409 | 12.0 | 3000 | 0.4883 | 0.894 |
### Framework versions
- Transformers 4.35.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.15.0
- Tokenizers 0.15.0
| 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. -->
# hbertv1-emotion-logit_KD-tiny_ffn_0.5
This model is a fine-tuned version of [gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5](https://huggingface.co/gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5131
- Accuracy: 0.8945
## 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: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 3.1241 | 1.0 | 250 | 2.5267 | 0.5775 |
| 2.0224 | 2.0 | 500 | 1.4869 | 0.748 |
| 1.2988 | 3.0 | 750 | 0.9838 | 0.836 |
| 0.9355 | 4.0 | 1000 | 0.7613 | 0.8535 |
| 0.7507 | 5.0 | 1250 | 0.6392 | 0.8805 |
| 0.6071 | 6.0 | 1500 | 0.5669 | 0.888 |
| 0.5377 | 7.0 | 1750 | 0.5131 | 0.8945 |
| 0.4707 | 8.0 | 2000 | 0.5133 | 0.8935 |
| 0.4223 | 9.0 | 2250 | 0.5078 | 0.8905 |
| 0.3933 | 10.0 | 2500 | 0.5156 | 0.8855 |
| 0.3612 | 11.0 | 2750 | 0.4883 | 0.894 |
| 0.3409 | 12.0 | 3000 | 0.4883 | 0.894 |
### Framework versions
- Transformers 4.35.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.15.0
- Tokenizers 0.15.0
|
{"base_model": "gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5", "datasets": ["emotion"], "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "hbertv1-emotion-logit_KD-tiny_ffn_0.5", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.8945, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,876 |
Kaludi/autotrain-28eqp-t2e16
|
Kaludi
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"deberta-v2",
"text-classification",
"autotrain",
"dataset:autotrain-28eqp-t2e16/autotrain-data",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-05-08T09:35:21Z |
2024-05-08T10:01:35+00:00
| 9 | 0 |
---
datasets:
- autotrain-28eqp-t2e16/autotrain-data
tags:
- autotrain
- text-classification
widget:
- text: I love AutoTrain
---
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.18809613585472107
f1: 0.967032967032967
precision: 0.9617486338797814
recall: 0.9723756906077348
auc: 0.9890489344909235
accuracy: 0.9656160458452722
| null |
Non_BioNLP
|
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.18809613585472107
f1: 0.967032967032967
precision: 0.9617486338797814
recall: 0.9723756906077348
auc: 0.9890489344909235
accuracy: 0.9656160458452722
|
{"datasets": ["autotrain-28eqp-t2e16/autotrain-data"], "tags": ["autotrain", "text-classification"], "widget": [{"text": "I love AutoTrain"}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,877 |
VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Full-Precision
|
VishnuPJ
| null |
[
"safetensors",
"paligemma",
"ml",
"license:mit",
"region:us"
] | 2024-08-22T05:00:35Z |
2024-08-30T06:22:09+00:00
| 12 | 0 |
---
language:
- ml
license: mit
---
# PaliGemma-3B-MalayaLLM
<img src="https://github.com/user-attachments/assets/8e8937a7-fd47-482c-acaf-48efc3c04597" alt="Baby MalayaLLM" width="300" height="auto">
# Introducing the Developer:
Discover the mind behind this model and stay updated on their contributions to the field
https://www.linkedin.com/in/vishnu-prasad-j/
# Model description
This is a PaliGemma-3B based model for Malayalam captioning and Visual Question Answering.
- **Model type:** A 3B PaliGemma-2 finetuned model on Malayalam captions and queries.
- **Language(s):** Malayalam and English
- **Datasets:**
* [VishnuPJ/SAM-LLAVA-20k-Malayalam-Caption-Pretrain](https://huggingface.co/datasets/VishnuPJ/SAM-LLAVA-20k-Malayalam-Caption-Pretrain)
* [VishnuPJ/laion-14k-GPT4V-LIVIS-Captions_Malayalam](https://huggingface.co/datasets/VishnuPJ/laion-14k-GPT4V-LIVIS-Captions_Malayalam)
* [VishnuPJ/Malayalam-VQA](https://huggingface.co/datasets/VishnuPJ/Malayalam-VQA)
- **Caption Model-Full Precisoin:** [VishnuPJ/MalayaLLM-Paligemma-Caption-3B-Full-Precision](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-Caption-3B-Full-Precision)
- **Caption 4bit Quant:** [VishnuPJ/MalayaLLM-Paligemma-Caption-3B-4bitQuant](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-Caption-3B-4bitQuant)
- **VQA Model-Full Precison:** [VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Full-Precision](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Full-Precision)
- **VQA 4bit Quant:** [VishnuPJ/MalayaLLM-Paligemma-VQA-3B-4bitQuant](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-VQA-3B-4bitQuant)
- **VQA LORA Adapters:** [VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Adapters](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Adapters)
- **Training Precision:** `float16`,`4bit`
# Dataset Creation
I have used [indictrans2](https://huggingface.co/ai4bharat/indictrans2-en-indic-1B) for translating English datasets to Malayalam.
# 🌟Happy coding💻🌟
| null |
Non_BioNLP
|
# PaliGemma-3B-MalayaLLM
<img src="https://github.com/user-attachments/assets/8e8937a7-fd47-482c-acaf-48efc3c04597" alt="Baby MalayaLLM" width="300" height="auto">
# Introducing the Developer:
Discover the mind behind this model and stay updated on their contributions to the field
https://www.linkedin.com/in/vishnu-prasad-j/
# Model description
This is a PaliGemma-3B based model for Malayalam captioning and Visual Question Answering.
- **Model type:** A 3B PaliGemma-2 finetuned model on Malayalam captions and queries.
- **Language(s):** Malayalam and English
- **Datasets:**
* [VishnuPJ/SAM-LLAVA-20k-Malayalam-Caption-Pretrain](https://huggingface.co/datasets/VishnuPJ/SAM-LLAVA-20k-Malayalam-Caption-Pretrain)
* [VishnuPJ/laion-14k-GPT4V-LIVIS-Captions_Malayalam](https://huggingface.co/datasets/VishnuPJ/laion-14k-GPT4V-LIVIS-Captions_Malayalam)
* [VishnuPJ/Malayalam-VQA](https://huggingface.co/datasets/VishnuPJ/Malayalam-VQA)
- **Caption Model-Full Precisoin:** [VishnuPJ/MalayaLLM-Paligemma-Caption-3B-Full-Precision](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-Caption-3B-Full-Precision)
- **Caption 4bit Quant:** [VishnuPJ/MalayaLLM-Paligemma-Caption-3B-4bitQuant](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-Caption-3B-4bitQuant)
- **VQA Model-Full Precison:** [VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Full-Precision](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Full-Precision)
- **VQA 4bit Quant:** [VishnuPJ/MalayaLLM-Paligemma-VQA-3B-4bitQuant](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-VQA-3B-4bitQuant)
- **VQA LORA Adapters:** [VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Adapters](https://huggingface.co/VishnuPJ/MalayaLLM-Paligemma-VQA-3B-Adapters)
- **Training Precision:** `float16`,`4bit`
# Dataset Creation
I have used [indictrans2](https://huggingface.co/ai4bharat/indictrans2-en-indic-1B) for translating English datasets to Malayalam.
# 🌟Happy coding💻🌟
|
{"language": ["ml"], "license": "mit"}
|
task
|
[
"QUESTION_ANSWERING"
] | 43,878 |
russfischer/setfit-ethos-multilabel-example
|
russfischer
|
text-classification
|
[
"setfit",
"safetensors",
"mpnet",
"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"
] | 2024-06-27T10:44:34Z |
2024-07-02T11:44:02+00:00
| 50 | 0 |
---
base_model: sentence-transformers/paraphrase-mpnet-base-v2
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: customers house is all concrete as well as neighbors house where the flowerpot
feeds both houses and theres no other flowerpot near by to feed the houses
- text: customer have new remodel elation at the front yard, including fake grass
and pavers and they dont want any damage on their front yard or move the pavers
- text: neighbor said no digging at all please stop asking. are we able to add a second
stub out to get customer in service
- text: Edward.R spoke with customer They requested a change of appointment via phonecause
no one is it home. Advised them to call AT&T. To reschedule.
- text: 'NO ACCESS: Waiting on customer to get access to neighbors yard.'
inference: false
model-index:
- name: SetFit 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: 0.6666666666666666
name: Accuracy
---
# SetFit with sentence-transformers/paraphrase-mpnet-base-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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A OneVsRestClassifier 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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
- **Classification head:** a OneVsRestClassifier instance
- **Maximum Sequence Length:** 512 tokens
<!-- - **Number of Classes:** Unknown -->
<!-- - **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)
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.6667 |
## 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("russfischer/setfit-ethos-multilabel-example")
# Run inference
preds = model("NO ACCESS: Waiting on customer to get access to neighbors yard.")
```
<!--
### 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 | 4 | 23.4886 | 65 |
### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- 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 |
|:------:|:----:|:-------------:|:---------------:|
| 0.0045 | 1 | 0.1219 | - |
| 0.2273 | 50 | 0.139 | - |
| 0.4545 | 100 | 0.0344 | - |
| 0.6818 | 150 | 0.0519 | - |
| 0.9091 | 200 | 0.027 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 3.0.1
- Transformers: 4.39.0
- PyTorch: 2.3.0+cu121
- Datasets: 2.20.0
- Tokenizers: 0.15.2
## 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-mpnet-base-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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A OneVsRestClassifier 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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
- **Classification head:** a OneVsRestClassifier instance
- **Maximum Sequence Length:** 512 tokens
<!-- - **Number of Classes:** Unknown -->
<!-- - **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)
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.6667 |
## 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("russfischer/setfit-ethos-multilabel-example")
# Run inference
preds = model("NO ACCESS: Waiting on customer to get access to neighbors yard.")
```
<!--
### 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 | 4 | 23.4886 | 65 |
### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- 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 |
|:------:|:----:|:-------------:|:---------------:|
| 0.0045 | 1 | 0.1219 | - |
| 0.2273 | 50 | 0.139 | - |
| 0.4545 | 100 | 0.0344 | - |
| 0.6818 | 150 | 0.0519 | - |
| 0.9091 | 200 | 0.027 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 3.0.1
- Transformers: 4.39.0
- PyTorch: 2.3.0+cu121
- Datasets: 2.20.0
- Tokenizers: 0.15.2
## 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", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "widget": [{"text": "customers house is all concrete as well as neighbors house where the flowerpot feeds both houses and theres no other flowerpot near by to feed the houses"}, {"text": "customer have new remodel elation at the front yard, including fake grass and pavers and they dont want any damage on their front yard or move the pavers"}, {"text": "neighbor said no digging at all please stop asking. are we able to add a second stub out to get customer in service"}, {"text": "Edward.R spoke with customer They requested a change of appointment via phonecause no one is it home. Advised them to call AT&T. To reschedule."}, {"text": "NO ACCESS: Waiting on customer to get access to neighbors yard."}], "inference": false, "model-index": [{"name": "SetFit 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": 0.6666666666666666, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,879 |
FareedKhan/mx_bai_test_full_cuda
|
FareedKhan
|
sentence-similarity
|
[
"sentence-transformers",
"safetensors",
"xlm-roberta",
"sentence-similarity",
"feature-extraction",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 2024-10-21T12:18:38Z |
2024-10-21T12:21:17+00:00
| 8 | 0 |
---
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
---
# SentenceTransformer
This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 1024-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:** [Unknown](https://huggingface.co/unknown) -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 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': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, '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("FareedKhan/mx_bai_test_full_cuda")
# Run inference
sentences = [
'The weather is lovely today.',
"It's so sunny outside!",
'He drove to the stadium.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 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
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.2.0
- Transformers: 4.44.2
- PyTorch: 2.4.1+cu121
- Accelerate: 0.34.2
- Datasets:
- Tokenizers: 0.19.1
## Citation
### BibTeX
<!--
## 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
This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 1024-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:** [Unknown](https://huggingface.co/unknown) -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 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': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, '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("FareedKhan/mx_bai_test_full_cuda")
# Run inference
sentences = [
'The weather is lovely today.',
"It's so sunny outside!",
'He drove to the stadium.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 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
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.2.0
- Transformers: 4.44.2
- PyTorch: 2.4.1+cu121
- Accelerate: 0.34.2
- Datasets:
- Tokenizers: 0.19.1
## Citation
### BibTeX
<!--
## 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.*
-->
|
{"library_name": "sentence-transformers", "pipeline_tag": "sentence-similarity", "tags": ["sentence-transformers", "sentence-similarity", "feature-extraction"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,880 |
zxcvo/phone-search-model
|
zxcvo
|
sentence-similarity
|
[
"sentence-transformers",
"safetensors",
"roberta",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:63",
"loss:MatryoshkaLoss",
"loss:MultipleNegativesRankingLoss",
"arxiv:1908.10084",
"arxiv:2205.13147",
"arxiv:1705.00652",
"base_model:keepitreal/vietnamese-sbert",
"base_model:finetune:keepitreal/vietnamese-sbert",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-12-25T09:15:20Z |
2024-12-25T09:39:34+00:00
| 8 | 0 |
---
base_model: keepitreal/vietnamese-sbert
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:63
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: Samsung Galaxy S22 Ultra
sentences:
- Điện thoại camera 108MP
- Điện thoại RAM 12GB
- Điện thoại có zoom quang học 10x
- source_sentence: Google Pixel 8 Pro
sentences:
- Điện thoại có jack cắm tai nghe 3.5mm
- Điện thoại có bộ nhớ trong 256GB
- Điện thoại chụp ảnh đẹp
- source_sentence: Google Pixel 8
sentences:
- Điện thoại màn hình 120Hz
- Điện thoại giá rẻ
- Điện thoại Android mới nhất
- source_sentence: JBL Reflect Flow Pro
sentences:
- iPhone mới nhất
- Điện thoại màn hình cong
- Điện thoại có loa Harman Kardon
- source_sentence: Asus ROG Phone 7
sentences:
- Điện thoại có bút
- Điện thoại chơi game
- Điện thoại có đèn flash kép
model-index:
- name: SentenceTransformer based on keepitreal/vietnamese-sbert
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 768
type: dim_768
metrics:
- type: cosine_accuracy@1
value: 0.0
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.2857142857142857
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.2857142857142857
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.5714285714285714
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.0
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.09523809523809523
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.05714285714285715
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.05714285714285715
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.0
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.2857142857142857
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.2857142857142857
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.5714285714285714
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.25679948860544627
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.1598639455782313
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.17696777071484332
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 512
type: dim_512
metrics:
- type: cosine_accuracy@1
value: 0.0
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.42857142857142855
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.5714285714285714
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.7142857142857143
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.0
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.14285714285714285
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1142857142857143
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.07142857142857142
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.0
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.42857142857142855
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.5714285714285714
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.7142857142857143
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.3358736991627618
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.21564625850340136
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.22075481533609612
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 256
type: dim_256
metrics:
- type: cosine_accuracy@1
value: 0.0
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.0
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.2857142857142857
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.5714285714285714
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.0
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.0
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.05714285714285715
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.05714285714285715
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.0
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.0
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.2857142857142857
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.5714285714285714
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.22155623379830594
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.11564625850340135
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.13073998125841443
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 128
type: dim_128
metrics:
- type: cosine_accuracy@1
value: 0.0
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.14285714285714285
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.2857142857142857
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.42857142857142855
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.0
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.047619047619047616
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.05714285714285715
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.042857142857142864
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.0
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.14285714285714285
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.2857142857142857
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.42857142857142855
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.18057284162953233
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.10374149659863945
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.11943368484517551
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 64
type: dim_64
metrics:
- type: cosine_accuracy@1
value: 0.14285714285714285
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.2857142857142857
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.2857142857142857
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.5714285714285714
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.14285714285714285
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.09523809523809523
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.05714285714285715
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.05714285714285715
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.14285714285714285
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.2857142857142857
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.2857142857142857
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.5714285714285714
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.32106066086016677
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.24801587301587302
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.2591176744402551
name: Cosine Map@100
---
# SentenceTransformer based on keepitreal/vietnamese-sbert
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [keepitreal/vietnamese-sbert](https://huggingface.co/keepitreal/vietnamese-sbert) on the json 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:** [keepitreal/vietnamese-sbert](https://huggingface.co/keepitreal/vietnamese-sbert) <!-- at revision a9467ef2ef47caa6448edeabfd8e5e5ce0fa2a23 -->
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- json
<!-- - **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: RobertaModel
(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("zxcvo/phone-search-model")
# Run inference
sentences = [
'Asus ROG Phone 7',
'Điện thoại chơi game',
'Điện thoại có đèn flash kép',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Information Retrieval
* Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 |
|:--------------------|:-----------|:-----------|:-----------|:-----------|:-----------|
| cosine_accuracy@1 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1429 |
| cosine_accuracy@3 | 0.2857 | 0.4286 | 0.0 | 0.1429 | 0.2857 |
| cosine_accuracy@5 | 0.2857 | 0.5714 | 0.2857 | 0.2857 | 0.2857 |
| cosine_accuracy@10 | 0.5714 | 0.7143 | 0.5714 | 0.4286 | 0.5714 |
| cosine_precision@1 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1429 |
| cosine_precision@3 | 0.0952 | 0.1429 | 0.0 | 0.0476 | 0.0952 |
| cosine_precision@5 | 0.0571 | 0.1143 | 0.0571 | 0.0571 | 0.0571 |
| cosine_precision@10 | 0.0571 | 0.0714 | 0.0571 | 0.0429 | 0.0571 |
| cosine_recall@1 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1429 |
| cosine_recall@3 | 0.2857 | 0.4286 | 0.0 | 0.1429 | 0.2857 |
| cosine_recall@5 | 0.2857 | 0.5714 | 0.2857 | 0.2857 | 0.2857 |
| cosine_recall@10 | 0.5714 | 0.7143 | 0.5714 | 0.4286 | 0.5714 |
| **cosine_ndcg@10** | **0.2568** | **0.3359** | **0.2216** | **0.1806** | **0.3211** |
| cosine_mrr@10 | 0.1599 | 0.2156 | 0.1156 | 0.1037 | 0.248 |
| cosine_map@100 | 0.177 | 0.2208 | 0.1307 | 0.1194 | 0.2591 |
<!--
## 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
#### json
* Dataset: json
* Size: 63 training samples
* Columns: <code>positive</code> and <code>anchor</code>
* Approximate statistics based on the first 63 samples:
| | positive | anchor |
|:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 6.9 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.86 tokens</li><li>max: 12 tokens</li></ul> |
* Samples:
| positive | anchor |
|:-----------------------------------------------------------|:-----------------------------------------|
| <code>Google Pixel 8</code> | <code>Điện thoại Android mới nhất</code> |
| <code>Samsung Galaxy S22 Ultra</code> | <code>Điện thoại có sạc không dây</code> |
| <code>Samsung Galaxy Note 20 Ultra đi kèm bút S Pen</code> | <code>Điện thoại có bút</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
1,
1,
1,
1
],
"n_dims_per_step": -1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 32
- `gradient_accumulation_steps`: 16
- `learning_rate`: 2e-05
- `num_train_epochs`: 4
- `bf16`: True
- `load_best_model_at_end`: True
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: epoch
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 8
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 16
- `eval_accumulation_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 4
- `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`: True
- `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`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `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
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
|:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
| **1.0** | **1** | **0.3188** | **0.3971** | **0.3073** | **0.1945** | **0.2442** |
| 2.0 | 2 | 0.3209 | 0.3886 | 0.2545 | 0.1838 | 0.3194 |
| 3.0 | 3 | 0.2542 | 0.3359 | 0.2391 | 0.1838 | 0.3211 |
| 4.0 | 4 | 0.2568 | 0.3359 | 0.2216 | 0.1806 | 0.3211 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.11.0
- Sentence Transformers: 3.3.1
- Transformers: 4.41.2
- PyTorch: 2.5.1+cu124
- Accelerate: 1.2.1
- Datasets: 2.19.1
- 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",
}
```
#### MatryoshkaLoss
```bibtex
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
| null |
Non_BioNLP
|
# SentenceTransformer based on keepitreal/vietnamese-sbert
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [keepitreal/vietnamese-sbert](https://huggingface.co/keepitreal/vietnamese-sbert) on the json 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:** [keepitreal/vietnamese-sbert](https://huggingface.co/keepitreal/vietnamese-sbert) <!-- at revision a9467ef2ef47caa6448edeabfd8e5e5ce0fa2a23 -->
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- json
<!-- - **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: RobertaModel
(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("zxcvo/phone-search-model")
# Run inference
sentences = [
'Asus ROG Phone 7',
'Điện thoại chơi game',
'Điện thoại có đèn flash kép',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Information Retrieval
* Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 |
|:--------------------|:-----------|:-----------|:-----------|:-----------|:-----------|
| cosine_accuracy@1 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1429 |
| cosine_accuracy@3 | 0.2857 | 0.4286 | 0.0 | 0.1429 | 0.2857 |
| cosine_accuracy@5 | 0.2857 | 0.5714 | 0.2857 | 0.2857 | 0.2857 |
| cosine_accuracy@10 | 0.5714 | 0.7143 | 0.5714 | 0.4286 | 0.5714 |
| cosine_precision@1 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1429 |
| cosine_precision@3 | 0.0952 | 0.1429 | 0.0 | 0.0476 | 0.0952 |
| cosine_precision@5 | 0.0571 | 0.1143 | 0.0571 | 0.0571 | 0.0571 |
| cosine_precision@10 | 0.0571 | 0.0714 | 0.0571 | 0.0429 | 0.0571 |
| cosine_recall@1 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1429 |
| cosine_recall@3 | 0.2857 | 0.4286 | 0.0 | 0.1429 | 0.2857 |
| cosine_recall@5 | 0.2857 | 0.5714 | 0.2857 | 0.2857 | 0.2857 |
| cosine_recall@10 | 0.5714 | 0.7143 | 0.5714 | 0.4286 | 0.5714 |
| **cosine_ndcg@10** | **0.2568** | **0.3359** | **0.2216** | **0.1806** | **0.3211** |
| cosine_mrr@10 | 0.1599 | 0.2156 | 0.1156 | 0.1037 | 0.248 |
| cosine_map@100 | 0.177 | 0.2208 | 0.1307 | 0.1194 | 0.2591 |
<!--
## 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
#### json
* Dataset: json
* Size: 63 training samples
* Columns: <code>positive</code> and <code>anchor</code>
* Approximate statistics based on the first 63 samples:
| | positive | anchor |
|:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 6.9 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.86 tokens</li><li>max: 12 tokens</li></ul> |
* Samples:
| positive | anchor |
|:-----------------------------------------------------------|:-----------------------------------------|
| <code>Google Pixel 8</code> | <code>Điện thoại Android mới nhất</code> |
| <code>Samsung Galaxy S22 Ultra</code> | <code>Điện thoại có sạc không dây</code> |
| <code>Samsung Galaxy Note 20 Ultra đi kèm bút S Pen</code> | <code>Điện thoại có bút</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
1,
1,
1,
1
],
"n_dims_per_step": -1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 32
- `gradient_accumulation_steps`: 16
- `learning_rate`: 2e-05
- `num_train_epochs`: 4
- `bf16`: True
- `load_best_model_at_end`: True
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: epoch
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 8
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 16
- `eval_accumulation_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 4
- `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`: True
- `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`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `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
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
|:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
| **1.0** | **1** | **0.3188** | **0.3971** | **0.3073** | **0.1945** | **0.2442** |
| 2.0 | 2 | 0.3209 | 0.3886 | 0.2545 | 0.1838 | 0.3194 |
| 3.0 | 3 | 0.2542 | 0.3359 | 0.2391 | 0.1838 | 0.3211 |
| 4.0 | 4 | 0.2568 | 0.3359 | 0.2216 | 0.1806 | 0.3211 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.11.0
- Sentence Transformers: 3.3.1
- Transformers: 4.41.2
- PyTorch: 2.5.1+cu124
- Accelerate: 1.2.1
- Datasets: 2.19.1
- 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",
}
```
#### MatryoshkaLoss
```bibtex
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
|
{"base_model": "keepitreal/vietnamese-sbert", "library_name": "sentence-transformers", "metrics": ["cosine_accuracy@1", "cosine_accuracy@3", "cosine_accuracy@5", "cosine_accuracy@10", "cosine_precision@1", "cosine_precision@3", "cosine_precision@5", "cosine_precision@10", "cosine_recall@1", "cosine_recall@3", "cosine_recall@5", "cosine_recall@10", "cosine_ndcg@10", "cosine_mrr@10", "cosine_map@100"], "pipeline_tag": "sentence-similarity", "tags": ["sentence-transformers", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:63", "loss:MatryoshkaLoss", "loss:MultipleNegativesRankingLoss"], "widget": [{"source_sentence": "Samsung Galaxy S22 Ultra", "sentences": ["Điện thoại camera 108MP", "Điện thoại RAM 12GB", "Điện thoại có zoom quang học 10x"]}, {"source_sentence": "Google Pixel 8 Pro", "sentences": ["Điện thoại có jack cắm tai nghe 3.5mm", "Điện thoại có bộ nhớ trong 256GB", "Điện thoại chụp ảnh đẹp"]}, {"source_sentence": "Google Pixel 8", "sentences": ["Điện thoại màn hình 120Hz", "Điện thoại giá rẻ", "Điện thoại Android mới nhất"]}, {"source_sentence": "JBL Reflect Flow Pro", "sentences": ["iPhone mới nhất", "Điện thoại màn hình cong", "Điện thoại có loa Harman Kardon"]}, {"source_sentence": "Asus ROG Phone 7", "sentences": ["Điện thoại có bút", "Điện thoại chơi game", "Điện thoại có đèn flash kép"]}], "model-index": [{"name": "SentenceTransformer based on keepitreal/vietnamese-sbert", "results": [{"task": {"type": "information-retrieval", "name": "Information Retrieval"}, "dataset": {"name": "dim 768", "type": "dim_768"}, "metrics": [{"type": "cosine_accuracy@1", "value": 0.0, "name": "Cosine Accuracy@1"}, {"type": "cosine_accuracy@3", "value": 0.2857142857142857, "name": "Cosine Accuracy@3"}, {"type": "cosine_accuracy@5", "value": 0.2857142857142857, "name": "Cosine Accuracy@5"}, {"type": "cosine_accuracy@10", "value": 0.5714285714285714, "name": "Cosine Accuracy@10"}, {"type": "cosine_precision@1", "value": 0.0, "name": "Cosine Precision@1"}, {"type": "cosine_precision@3", "value": 0.09523809523809523, "name": "Cosine Precision@3"}, {"type": "cosine_precision@5", "value": 0.05714285714285715, "name": "Cosine Precision@5"}, {"type": "cosine_precision@10", "value": 0.05714285714285715, "name": "Cosine Precision@10"}, {"type": "cosine_recall@1", "value": 0.0, "name": "Cosine Recall@1"}, {"type": "cosine_recall@3", "value": 0.2857142857142857, "name": "Cosine Recall@3"}, {"type": "cosine_recall@5", "value": 0.2857142857142857, "name": "Cosine Recall@5"}, {"type": "cosine_recall@10", "value": 0.5714285714285714, "name": "Cosine Recall@10"}, {"type": "cosine_ndcg@10", "value": 0.25679948860544627, "name": "Cosine Ndcg@10"}, {"type": "cosine_mrr@10", "value": 0.1598639455782313, "name": "Cosine Mrr@10"}, {"type": "cosine_map@100", "value": 0.17696777071484332, "name": "Cosine Map@100"}]}, {"task": {"type": "information-retrieval", "name": "Information Retrieval"}, "dataset": {"name": "dim 512", "type": "dim_512"}, "metrics": [{"type": "cosine_accuracy@1", "value": 0.0, "name": "Cosine Accuracy@1"}, {"type": "cosine_accuracy@3", "value": 0.42857142857142855, "name": "Cosine Accuracy@3"}, {"type": "cosine_accuracy@5", "value": 0.5714285714285714, "name": "Cosine Accuracy@5"}, {"type": "cosine_accuracy@10", "value": 0.7142857142857143, "name": "Cosine Accuracy@10"}, {"type": "cosine_precision@1", "value": 0.0, "name": "Cosine Precision@1"}, {"type": "cosine_precision@3", "value": 0.14285714285714285, "name": "Cosine Precision@3"}, {"type": "cosine_precision@5", "value": 0.1142857142857143, "name": "Cosine Precision@5"}, {"type": "cosine_precision@10", "value": 0.07142857142857142, "name": "Cosine Precision@10"}, {"type": "cosine_recall@1", "value": 0.0, "name": "Cosine Recall@1"}, {"type": "cosine_recall@3", "value": 0.42857142857142855, "name": "Cosine Recall@3"}, {"type": "cosine_recall@5", "value": 0.5714285714285714, "name": "Cosine Recall@5"}, {"type": "cosine_recall@10", "value": 0.7142857142857143, "name": "Cosine Recall@10"}, {"type": "cosine_ndcg@10", "value": 0.3358736991627618, "name": "Cosine Ndcg@10"}, {"type": "cosine_mrr@10", "value": 0.21564625850340136, "name": "Cosine Mrr@10"}, {"type": "cosine_map@100", "value": 0.22075481533609612, "name": "Cosine Map@100"}]}, {"task": {"type": "information-retrieval", "name": "Information Retrieval"}, "dataset": {"name": "dim 256", "type": "dim_256"}, "metrics": [{"type": "cosine_accuracy@1", "value": 0.0, "name": "Cosine Accuracy@1"}, {"type": "cosine_accuracy@3", "value": 0.0, "name": "Cosine Accuracy@3"}, {"type": "cosine_accuracy@5", "value": 0.2857142857142857, "name": "Cosine Accuracy@5"}, {"type": "cosine_accuracy@10", "value": 0.5714285714285714, "name": "Cosine Accuracy@10"}, {"type": "cosine_precision@1", "value": 0.0, "name": "Cosine Precision@1"}, {"type": "cosine_precision@3", "value": 0.0, "name": "Cosine Precision@3"}, {"type": "cosine_precision@5", "value": 0.05714285714285715, "name": "Cosine Precision@5"}, {"type": "cosine_precision@10", "value": 0.05714285714285715, "name": "Cosine Precision@10"}, {"type": "cosine_recall@1", "value": 0.0, "name": "Cosine Recall@1"}, {"type": "cosine_recall@3", "value": 0.0, "name": "Cosine Recall@3"}, {"type": "cosine_recall@5", "value": 0.2857142857142857, "name": "Cosine Recall@5"}, {"type": "cosine_recall@10", "value": 0.5714285714285714, "name": "Cosine Recall@10"}, {"type": "cosine_ndcg@10", "value": 0.22155623379830594, "name": "Cosine Ndcg@10"}, {"type": "cosine_mrr@10", "value": 0.11564625850340135, "name": "Cosine Mrr@10"}, {"type": "cosine_map@100", "value": 0.13073998125841443, "name": "Cosine Map@100"}]}, {"task": {"type": "information-retrieval", "name": "Information Retrieval"}, "dataset": {"name": "dim 128", "type": "dim_128"}, "metrics": [{"type": "cosine_accuracy@1", "value": 0.0, "name": "Cosine Accuracy@1"}, {"type": "cosine_accuracy@3", "value": 0.14285714285714285, "name": "Cosine Accuracy@3"}, {"type": "cosine_accuracy@5", "value": 0.2857142857142857, "name": "Cosine Accuracy@5"}, {"type": "cosine_accuracy@10", "value": 0.42857142857142855, "name": "Cosine Accuracy@10"}, {"type": "cosine_precision@1", "value": 0.0, "name": "Cosine Precision@1"}, {"type": "cosine_precision@3", "value": 0.047619047619047616, "name": "Cosine Precision@3"}, {"type": "cosine_precision@5", "value": 0.05714285714285715, "name": "Cosine Precision@5"}, {"type": "cosine_precision@10", "value": 0.042857142857142864, "name": "Cosine Precision@10"}, {"type": "cosine_recall@1", "value": 0.0, "name": "Cosine Recall@1"}, {"type": "cosine_recall@3", "value": 0.14285714285714285, "name": "Cosine Recall@3"}, {"type": "cosine_recall@5", "value": 0.2857142857142857, "name": "Cosine Recall@5"}, {"type": "cosine_recall@10", "value": 0.42857142857142855, "name": "Cosine Recall@10"}, {"type": "cosine_ndcg@10", "value": 0.18057284162953233, "name": "Cosine Ndcg@10"}, {"type": "cosine_mrr@10", "value": 0.10374149659863945, "name": "Cosine Mrr@10"}, {"type": "cosine_map@100", "value": 0.11943368484517551, "name": "Cosine Map@100"}]}, {"task": {"type": "information-retrieval", "name": "Information Retrieval"}, "dataset": {"name": "dim 64", "type": "dim_64"}, "metrics": [{"type": "cosine_accuracy@1", "value": 0.14285714285714285, "name": "Cosine Accuracy@1"}, {"type": "cosine_accuracy@3", "value": 0.2857142857142857, "name": "Cosine Accuracy@3"}, {"type": "cosine_accuracy@5", "value": 0.2857142857142857, "name": "Cosine Accuracy@5"}, {"type": "cosine_accuracy@10", "value": 0.5714285714285714, "name": "Cosine Accuracy@10"}, {"type": "cosine_precision@1", "value": 0.14285714285714285, "name": "Cosine Precision@1"}, {"type": "cosine_precision@3", "value": 0.09523809523809523, "name": "Cosine Precision@3"}, {"type": "cosine_precision@5", "value": 0.05714285714285715, "name": "Cosine Precision@5"}, {"type": "cosine_precision@10", "value": 0.05714285714285715, "name": "Cosine Precision@10"}, {"type": "cosine_recall@1", "value": 0.14285714285714285, "name": "Cosine Recall@1"}, {"type": "cosine_recall@3", "value": 0.2857142857142857, "name": "Cosine Recall@3"}, {"type": "cosine_recall@5", "value": 0.2857142857142857, "name": "Cosine Recall@5"}, {"type": "cosine_recall@10", "value": 0.5714285714285714, "name": "Cosine Recall@10"}, {"type": "cosine_ndcg@10", "value": 0.32106066086016677, "name": "Cosine Ndcg@10"}, {"type": "cosine_mrr@10", "value": 0.24801587301587302, "name": "Cosine Mrr@10"}, {"type": "cosine_map@100", "value": 0.2591176744402551, "name": "Cosine Map@100"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,881 |
facebook/fasttext-hi-vectors
|
facebook
|
feature-extraction
|
[
"fasttext",
"feature-extraction",
"hi",
"arxiv:1607.04606",
"arxiv:1802.06893",
"arxiv:1607.01759",
"arxiv:1612.03651",
"license:cc-by-sa-3.0",
"region:us"
] | 2023-03-19T05:56:15Z |
2023-06-03T22:11:54+00:00
| 3 | 1 |
---
language: hi
library_name: fasttext
license: cc-by-sa-3.0
tags:
- feature-extraction
widget:
- text: apple
example_title: apple
---
# fastText (Hindi)
fastText is an open-source, free, lightweight library that allows users to learn text representations and text classifiers. It works on standard, generic hardware. Models can later be reduced in size to even fit on mobile devices. It was introduced in [this paper](https://arxiv.org/abs/1607.04606). The official website can be found [here](https://fasttext.cc/).
## Model description
fastText is a library for efficient learning of word representations and sentence classification. fastText is designed to be simple to use for developers, domain experts, and students. It's dedicated to text classification and learning word representations, and was designed to allow for quick model iteration and refinement without specialized hardware. fastText models can be trained on more than a billion words on any multicore CPU in less than a few minutes.
It includes pre-trained models learned on Wikipedia and in over 157 different languages. fastText can be used as a command line, linked to a C++ application, or used as a library for use cases from experimentation and prototyping to production.
## Intended uses & limitations
You can use pre-trained word vectors for text classification or language identification. See the [tutorials](https://fasttext.cc/docs/en/supervised-tutorial.html) and [resources](https://fasttext.cc/docs/en/english-vectors.html) on its official website to look for tasks that interest you.
### How to use
Here is how to load and use a pre-trained vectors
```python
>>> import fasttext
>>> from huggingface_hub import hf_hub_download
>>> model_path = hf_hub_download(repo_id="facebook/fasttext-hi-vectors", filename="model.bin")
>>> model = fasttext.load_model(model_path)
>>> model.words
['the', 'of', 'and', 'to', 'in', 'a', 'that', 'is', ...]
>>> len(model.words)
145940
>>> model['bread']
array([ 4.89417791e-01, 1.60882145e-01, -2.25947708e-01, -2.94273376e-01,
-1.04577184e-01, 1.17962055e-01, 1.34821936e-01, -2.41778508e-01, ...])
```
Here is how to use this model to query nearest neighbors of an English word vector:
```python
>>> import fasttext
>>> from huggingface_hub import hf_hub_download
>>> model_path = hf_hub_download(repo_id="facebook/fasttext-en-nearest-neighbors", filename="model.bin")
>>> model = fasttext.load_model(model_path)
>>> model.get_nearest_neighbors("bread", k=5)
[(0.5641006231307983, 'butter'),
(0.48875734210014343, 'loaf'),
(0.4491206705570221, 'eat'),
(0.42444291710853577, 'food'),
(0.4229326844215393, 'cheese')]
```
Here is how to use this model to detect the language of a given text:
```python
>>> import fasttext
>>> from huggingface_hub import hf_hub_download
>>> model_path = hf_hub_download(repo_id="facebook/fasttext-language-identification", filename="model.bin")
>>> model = fasttext.load_model(model_path)
>>> model.predict("Hello, world!")
(('__label__eng_Latn',), array([0.81148803]))
>>> model.predict("Hello, world!", k=5)
(('__label__eng_Latn', '__label__vie_Latn', '__label__nld_Latn', '__label__pol_Latn', '__label__deu_Latn'),
array([0.61224753, 0.21323682, 0.09696738, 0.01359863, 0.01319415]))
```
### Limitations and bias
Even if the training data used for this model could be characterized as fairly neutral, this model can have biased predictions.
Cosine similarity can be used to measure the similarity between two different word vectors. If two two vectors are identical, the cosine similarity will be 1. For two completely unrelated vectors, the value will be 0. If two vectors have an opposite relationship, the value will be -1.
```python
>>> import numpy as np
>>> def cosine_similarity(word1, word2):
>>> return np.dot(model[word1], model[word2]) / (np.linalg.norm(model[word1]) * np.linalg.norm(model[word2]))
>>> cosine_similarity("man", "boy")
0.061653383
>>> cosine_similarity("man", "ceo")
0.11989131
>>> cosine_similarity("woman", "ceo")
-0.08834904
```
## Training data
Pre-trained word vectors for 157 languages were trained on [Common Crawl](http://commoncrawl.org/) and [Wikipedia](https://www.wikipedia.org/) using fastText. These models were trained using CBOW with position-weights, in dimension 300, with character n-grams of length 5, a window of size 5 and 10 negatives. We also distribute three new word analogy datasets, for French, Hindi and Polish.
## Training procedure
### Tokenization
We used the [Stanford word segmenter](https://nlp.stanford.edu/software/segmenter.html) for Chinese, [Mecab](http://taku910.github.io/mecab/) for Japanese and [UETsegmenter](https://github.com/phongnt570/UETsegmenter) for Vietnamese. For languages using the Latin, Cyrillic, Hebrew or Greek scripts, we used the tokenizer from the [Europarl](https://www.statmt.org/europarl/) preprocessing tools. For the remaining languages, we used the ICU tokenizer.
More information about the training of these models can be found in the article [Learning Word Vectors for 157 Languages](https://arxiv.org/abs/1802.06893).
### License
The word vectors are distributed under the [*Creative Commons Attribution-Share-Alike License 3.0*](https://creativecommons.org/licenses/by-sa/3.0/).
### Evaluation datasets
The analogy evaluation datasets described in the paper are available here: [French](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-fr.txt), [Hindi](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-hi.txt), [Polish](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-pl.txt).
### BibTeX entry and citation info
Please cite [1] if using this code for learning word representations or [2] if using for text classification.
[1] P. Bojanowski\*, E. Grave\*, A. Joulin, T. Mikolov, [*Enriching Word Vectors with Subword Information*](https://arxiv.org/abs/1607.04606)
```markup
@article{bojanowski2016enriching,
title={Enriching Word Vectors with Subword Information},
author={Bojanowski, Piotr and Grave, Edouard and Joulin, Armand and Mikolov, Tomas},
journal={arXiv preprint arXiv:1607.04606},
year={2016}
}
```
[2] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, [*Bag of Tricks for Efficient Text Classification*](https://arxiv.org/abs/1607.01759)
```markup
@article{joulin2016bag,
title={Bag of Tricks for Efficient Text Classification},
author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Mikolov, Tomas},
journal={arXiv preprint arXiv:1607.01759},
year={2016}
}
```
[3] A. Joulin, E. Grave, P. Bojanowski, M. Douze, H. Jégou, T. Mikolov, [*FastText.zip: Compressing text classification models*](https://arxiv.org/abs/1612.03651)
```markup
@article{joulin2016fasttext,
title={FastText.zip: Compressing text classification models},
author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Douze, Matthijs and J{'e}gou, H{'e}rve and Mikolov, Tomas},
journal={arXiv preprint arXiv:1612.03651},
year={2016}
}
```
If you use these word vectors, please cite the following paper:
[4] E. Grave\*, P. Bojanowski\*, P. Gupta, A. Joulin, T. Mikolov, [*Learning Word Vectors for 157 Languages*](https://arxiv.org/abs/1802.06893)
```markup
@inproceedings{grave2018learning,
title={Learning Word Vectors for 157 Languages},
author={Grave, Edouard and Bojanowski, Piotr and Gupta, Prakhar and Joulin, Armand and Mikolov, Tomas},
booktitle={Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018)},
year={2018}
}
```
(\* These authors contributed equally.)
| null |
Non_BioNLP
|
# fastText (Hindi)
fastText is an open-source, free, lightweight library that allows users to learn text representations and text classifiers. It works on standard, generic hardware. Models can later be reduced in size to even fit on mobile devices. It was introduced in [this paper](https://arxiv.org/abs/1607.04606). The official website can be found [here](https://fasttext.cc/).
## Model description
fastText is a library for efficient learning of word representations and sentence classification. fastText is designed to be simple to use for developers, domain experts, and students. It's dedicated to text classification and learning word representations, and was designed to allow for quick model iteration and refinement without specialized hardware. fastText models can be trained on more than a billion words on any multicore CPU in less than a few minutes.
It includes pre-trained models learned on Wikipedia and in over 157 different languages. fastText can be used as a command line, linked to a C++ application, or used as a library for use cases from experimentation and prototyping to production.
## Intended uses & limitations
You can use pre-trained word vectors for text classification or language identification. See the [tutorials](https://fasttext.cc/docs/en/supervised-tutorial.html) and [resources](https://fasttext.cc/docs/en/english-vectors.html) on its official website to look for tasks that interest you.
### How to use
Here is how to load and use a pre-trained vectors
```python
>>> import fasttext
>>> from huggingface_hub import hf_hub_download
>>> model_path = hf_hub_download(repo_id="facebook/fasttext-hi-vectors", filename="model.bin")
>>> model = fasttext.load_model(model_path)
>>> model.words
['the', 'of', 'and', 'to', 'in', 'a', 'that', 'is', ...]
>>> len(model.words)
145940
>>> model['bread']
array([ 4.89417791e-01, 1.60882145e-01, -2.25947708e-01, -2.94273376e-01,
-1.04577184e-01, 1.17962055e-01, 1.34821936e-01, -2.41778508e-01, ...])
```
Here is how to use this model to query nearest neighbors of an English word vector:
```python
>>> import fasttext
>>> from huggingface_hub import hf_hub_download
>>> model_path = hf_hub_download(repo_id="facebook/fasttext-en-nearest-neighbors", filename="model.bin")
>>> model = fasttext.load_model(model_path)
>>> model.get_nearest_neighbors("bread", k=5)
[(0.5641006231307983, 'butter'),
(0.48875734210014343, 'loaf'),
(0.4491206705570221, 'eat'),
(0.42444291710853577, 'food'),
(0.4229326844215393, 'cheese')]
```
Here is how to use this model to detect the language of a given text:
```python
>>> import fasttext
>>> from huggingface_hub import hf_hub_download
>>> model_path = hf_hub_download(repo_id="facebook/fasttext-language-identification", filename="model.bin")
>>> model = fasttext.load_model(model_path)
>>> model.predict("Hello, world!")
(('__label__eng_Latn',), array([0.81148803]))
>>> model.predict("Hello, world!", k=5)
(('__label__eng_Latn', '__label__vie_Latn', '__label__nld_Latn', '__label__pol_Latn', '__label__deu_Latn'),
array([0.61224753, 0.21323682, 0.09696738, 0.01359863, 0.01319415]))
```
### Limitations and bias
Even if the training data used for this model could be characterized as fairly neutral, this model can have biased predictions.
Cosine similarity can be used to measure the similarity between two different word vectors. If two two vectors are identical, the cosine similarity will be 1. For two completely unrelated vectors, the value will be 0. If two vectors have an opposite relationship, the value will be -1.
```python
>>> import numpy as np
>>> def cosine_similarity(word1, word2):
>>> return np.dot(model[word1], model[word2]) / (np.linalg.norm(model[word1]) * np.linalg.norm(model[word2]))
>>> cosine_similarity("man", "boy")
0.061653383
>>> cosine_similarity("man", "ceo")
0.11989131
>>> cosine_similarity("woman", "ceo")
-0.08834904
```
## Training data
Pre-trained word vectors for 157 languages were trained on [Common Crawl](http://commoncrawl.org/) and [Wikipedia](https://www.wikipedia.org/) using fastText. These models were trained using CBOW with position-weights, in dimension 300, with character n-grams of length 5, a window of size 5 and 10 negatives. We also distribute three new word analogy datasets, for French, Hindi and Polish.
## Training procedure
### Tokenization
We used the [Stanford word segmenter](https://nlp.stanford.edu/software/segmenter.html) for Chinese, [Mecab](http://taku910.github.io/mecab/) for Japanese and [UETsegmenter](https://github.com/phongnt570/UETsegmenter) for Vietnamese. For languages using the Latin, Cyrillic, Hebrew or Greek scripts, we used the tokenizer from the [Europarl](https://www.statmt.org/europarl/) preprocessing tools. For the remaining languages, we used the ICU tokenizer.
More information about the training of these models can be found in the article [Learning Word Vectors for 157 Languages](https://arxiv.org/abs/1802.06893).
### License
The word vectors are distributed under the [*Creative Commons Attribution-Share-Alike License 3.0*](https://creativecommons.org/licenses/by-sa/3.0/).
### Evaluation datasets
The analogy evaluation datasets described in the paper are available here: [French](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-fr.txt), [Hindi](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-hi.txt), [Polish](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-pl.txt).
### BibTeX entry and citation info
Please cite [1] if using this code for learning word representations or [2] if using for text classification.
[1] P. Bojanowski\*, E. Grave\*, A. Joulin, T. Mikolov, [*Enriching Word Vectors with Subword Information*](https://arxiv.org/abs/1607.04606)
```markup
@article{bojanowski2016enriching,
title={Enriching Word Vectors with Subword Information},
author={Bojanowski, Piotr and Grave, Edouard and Joulin, Armand and Mikolov, Tomas},
journal={arXiv preprint arXiv:1607.04606},
year={2016}
}
```
[2] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, [*Bag of Tricks for Efficient Text Classification*](https://arxiv.org/abs/1607.01759)
```markup
@article{joulin2016bag,
title={Bag of Tricks for Efficient Text Classification},
author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Mikolov, Tomas},
journal={arXiv preprint arXiv:1607.01759},
year={2016}
}
```
[3] A. Joulin, E. Grave, P. Bojanowski, M. Douze, H. Jégou, T. Mikolov, [*FastText.zip: Compressing text classification models*](https://arxiv.org/abs/1612.03651)
```markup
@article{joulin2016fasttext,
title={FastText.zip: Compressing text classification models},
author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Douze, Matthijs and J{'e}gou, H{'e}rve and Mikolov, Tomas},
journal={arXiv preprint arXiv:1612.03651},
year={2016}
}
```
If you use these word vectors, please cite the following paper:
[4] E. Grave\*, P. Bojanowski\*, P. Gupta, A. Joulin, T. Mikolov, [*Learning Word Vectors for 157 Languages*](https://arxiv.org/abs/1802.06893)
```markup
@inproceedings{grave2018learning,
title={Learning Word Vectors for 157 Languages},
author={Grave, Edouard and Bojanowski, Piotr and Gupta, Prakhar and Joulin, Armand and Mikolov, Tomas},
booktitle={Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018)},
year={2018}
}
```
(\* These authors contributed equally.)
|
{"language": "hi", "library_name": "fasttext", "license": "cc-by-sa-3.0", "tags": ["feature-extraction"], "widget": [{"text": "apple", "example_title": "apple"}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,882 |
abdelmageed/distilbert-base-uncased-distilled-clinc
|
abdelmageed
|
text-classification
|
[
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:clinc_oos",
"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"
] | 2023-11-13T12:06:11Z |
2023-11-13T12:26:53+00:00
| 7 | 0 |
---
base_model: distilbert-base-uncased
datasets:
- clinc_oos
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-distilled-clinc
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: clinc_oos
type: clinc_oos
config: plus
split: validation
args: plus
metrics:
- type: accuracy
value: 0.9416129032258065
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-distilled-clinc
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1005
- Accuracy: 0.9416
## 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: 48
- eval_batch_size: 48
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9034 | 1.0 | 318 | 0.5760 | 0.7342 |
| 0.45 | 2.0 | 636 | 0.2855 | 0.8784 |
| 0.2544 | 3.0 | 954 | 0.1801 | 0.9223 |
| 0.1773 | 4.0 | 1272 | 0.1399 | 0.93 |
| 0.1427 | 5.0 | 1590 | 0.1212 | 0.9329 |
| 0.1247 | 6.0 | 1908 | 0.1119 | 0.9384 |
| 0.1145 | 7.0 | 2226 | 0.1063 | 0.9419 |
| 0.1078 | 8.0 | 2544 | 0.1031 | 0.9419 |
| 0.1042 | 9.0 | 2862 | 0.1013 | 0.9410 |
| 0.102 | 10.0 | 3180 | 0.1005 | 0.9416 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- 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. -->
# distilbert-base-uncased-distilled-clinc
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1005
- Accuracy: 0.9416
## 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: 48
- eval_batch_size: 48
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9034 | 1.0 | 318 | 0.5760 | 0.7342 |
| 0.45 | 2.0 | 636 | 0.2855 | 0.8784 |
| 0.2544 | 3.0 | 954 | 0.1801 | 0.9223 |
| 0.1773 | 4.0 | 1272 | 0.1399 | 0.93 |
| 0.1427 | 5.0 | 1590 | 0.1212 | 0.9329 |
| 0.1247 | 6.0 | 1908 | 0.1119 | 0.9384 |
| 0.1145 | 7.0 | 2226 | 0.1063 | 0.9419 |
| 0.1078 | 8.0 | 2544 | 0.1031 | 0.9419 |
| 0.1042 | 9.0 | 2862 | 0.1013 | 0.9410 |
| 0.102 | 10.0 | 3180 | 0.1005 | 0.9416 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
|
{"base_model": "distilbert-base-uncased", "datasets": ["clinc_oos"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert-base-uncased-distilled-clinc", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "clinc_oos", "type": "clinc_oos", "config": "plus", "split": "validation", "args": "plus"}, "metrics": [{"type": "accuracy", "value": 0.9416129032258065, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,883 |
fine-tuned/ArguAna-512-192-gpt-4o-2024-05-13-53785794
|
fine-tuned
|
feature-extraction
|
[
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"en",
"dataset:fine-tuned/ArguAna-512-192-gpt-4o-2024-05-13-53785794",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 2024-05-28T23:19:21Z |
2024-05-28T23:19:59+00:00
| 6 | 0 |
---
datasets:
- fine-tuned/ArguAna-512-192-gpt-4o-2024-05-13-53785794
- 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-large-en-v1.5**](https://huggingface.co/BAAI/bge-large-en-v1.5) 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/ArguAna-512-192-gpt-4o-2024-05-13-53785794',
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-large-en-v1.5**](https://huggingface.co/BAAI/bge-large-en-v1.5) 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/ArguAna-512-192-gpt-4o-2024-05-13-53785794',
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/ArguAna-512-192-gpt-4o-2024-05-13-53785794", "allenai/c4"], "language": ["en", "en"], "license": "apache-2.0", "pipeline_tag": "feature-extraction", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity", "mteb"]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,884 |
prithivMLmods/Sombrero-QwQ-32B-Elite10-Fixed
|
prithivMLmods
|
text-generation
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"text-generation-inference",
"StreamlinedMemory",
"Reasoning",
"Fixed",
"conversational",
"en",
"base_model:Qwen/QwQ-32B",
"base_model:finetune:Qwen/QwQ-32B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2025-03-09T18:34:15Z |
2025-03-12T13:59:37+00:00
| 259 | 9 |
---
base_model:
- Qwen/QwQ-32B
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
- text-generation-inference
- StreamlinedMemory
- Reasoning
- Fixed
---
# **Sombrero-QwQ-32B-Elite10-Fixed**
> Sombrero-QwQ-32B-Elite10 is based on the QwQ 32B modality architecture, optimized for **Streamlined Memory Optimization** while avoiding unwanted textual token mathematical problem-solving and reasoning. This model is tailored for enhanced contextual comprehension, structured text generation, and efficiency in long-context applications.
## **Key Improvements**
1. **Optimized Memory Utilization**: Designed to reduce memory overhead while maintaining high-performance inference, making it ideal for complex workflows.
2. **Precision in Textual Outputs**: Prioritizes structured content generation and avoids unnecessary mathematical computations in responses.
3. **Versatile Adaptability**: Handles diverse queries efficiently, providing coherent and relevant answers across multiple domains.
4. **Long-Context Support**: Supports up to 256K tokens for input context and generates up to 16K tokens in a single output, ensuring detailed and structured responses.
## **Quickstart with transformers**
Here is a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and generate content:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "prithivMLmods/Sombrero-QwQ-32B-Elite10-Fixed"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "How does streamlined memory optimization improve AI model efficiency?"
messages = [
{"role": "system", "content": "You are an AI specialized in memory-efficient text generation and structured reasoning."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## **Intended Use**
1. **Contextual Understanding & Content Generation**:
Designed to generate structured, coherent, and contextually relevant text while minimizing unnecessary computational overhead.
2. **Enterprise and Research Applications**:
Suitable for large-scale knowledge retrieval, document summarization, and structured data processing.
3. **Conversational AI & Virtual Assistants**:
Provides human-like conversational experiences while maintaining response clarity and efficiency.
4. **Multilingual AI Systems**:
Enhances cross-language communication and supports multilingual deployments.
5. **Long-Form Content Generation**:
Capable of producing extended articles, reports, and structured documents with high coherence.
## **Limitations**
1. **Hardware Requirements**:
Due to its 32B parameter size, high-memory GPUs or TPUs are recommended for optimal performance.
2. **Avoidance of Mathematical Problem-Solving**:
Unlike traditional AI models, this model is optimized to reduce mathematical computation, which may limit its effectiveness in solving complex numerical problems.
3. **Potential Bias in Responses**:
While fine-tuned for neutrality, responses may still carry biases from training data.
4. **Prompt Sensitivity**:
The model’s output quality depends on the structure and clarity of the input prompt.
5. **Real-Time Awareness Limitations**:
Does not have access to real-world events beyond its training data.
| null |
Non_BioNLP
|
# **Sombrero-QwQ-32B-Elite10-Fixed**
> Sombrero-QwQ-32B-Elite10 is based on the QwQ 32B modality architecture, optimized for **Streamlined Memory Optimization** while avoiding unwanted textual token mathematical problem-solving and reasoning. This model is tailored for enhanced contextual comprehension, structured text generation, and efficiency in long-context applications.
## **Key Improvements**
1. **Optimized Memory Utilization**: Designed to reduce memory overhead while maintaining high-performance inference, making it ideal for complex workflows.
2. **Precision in Textual Outputs**: Prioritizes structured content generation and avoids unnecessary mathematical computations in responses.
3. **Versatile Adaptability**: Handles diverse queries efficiently, providing coherent and relevant answers across multiple domains.
4. **Long-Context Support**: Supports up to 256K tokens for input context and generates up to 16K tokens in a single output, ensuring detailed and structured responses.
## **Quickstart with transformers**
Here is a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and generate content:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "prithivMLmods/Sombrero-QwQ-32B-Elite10-Fixed"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "How does streamlined memory optimization improve AI model efficiency?"
messages = [
{"role": "system", "content": "You are an AI specialized in memory-efficient text generation and structured reasoning."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## **Intended Use**
1. **Contextual Understanding & Content Generation**:
Designed to generate structured, coherent, and contextually relevant text while minimizing unnecessary computational overhead.
2. **Enterprise and Research Applications**:
Suitable for large-scale knowledge retrieval, document summarization, and structured data processing.
3. **Conversational AI & Virtual Assistants**:
Provides human-like conversational experiences while maintaining response clarity and efficiency.
4. **Multilingual AI Systems**:
Enhances cross-language communication and supports multilingual deployments.
5. **Long-Form Content Generation**:
Capable of producing extended articles, reports, and structured documents with high coherence.
## **Limitations**
1. **Hardware Requirements**:
Due to its 32B parameter size, high-memory GPUs or TPUs are recommended for optimal performance.
2. **Avoidance of Mathematical Problem-Solving**:
Unlike traditional AI models, this model is optimized to reduce mathematical computation, which may limit its effectiveness in solving complex numerical problems.
3. **Potential Bias in Responses**:
While fine-tuned for neutrality, responses may still carry biases from training data.
4. **Prompt Sensitivity**:
The model’s output quality depends on the structure and clarity of the input prompt.
5. **Real-Time Awareness Limitations**:
Does not have access to real-world events beyond its training data.
|
{"base_model": ["Qwen/QwQ-32B"], "language": ["en"], "library_name": "transformers", "license": "apache-2.0", "pipeline_tag": "text-generation", "tags": ["text-generation-inference", "StreamlinedMemory", "Reasoning", "Fixed"]}
|
task
|
[
"SUMMARIZATION"
] | 43,885 |
Vangmayy/emotion
|
Vangmayy
|
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"
] | 2024-06-08T09:12:38Z |
2024-06-08T09:12:48+00:00
| 7 | 0 |
---
base_model: distilbert-base-uncased
datasets:
- emotion
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: emotion
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.9435
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. -->
# 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: 0.1248
- Accuracy: 0.9435
## 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: 8e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7944 | 1.0 | 125 | 0.1987 | 0.9335 |
| 0.1562 | 2.0 | 250 | 0.1426 | 0.941 |
| 0.0964 | 3.0 | 375 | 0.1233 | 0.941 |
| 0.0679 | 4.0 | 500 | 0.1248 | 0.9435 |
### 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. -->
# 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: 0.1248
- Accuracy: 0.9435
## 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: 8e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7944 | 1.0 | 125 | 0.1987 | 0.9335 |
| 0.1562 | 2.0 | 250 | 0.1426 | 0.941 |
| 0.0964 | 3.0 | 375 | 0.1233 | 0.941 |
| 0.0679 | 4.0 | 500 | 0.1248 | 0.9435 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
|
{"base_model": "distilbert-base-uncased", "datasets": ["emotion"], "license": "apache-2.0", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "emotion", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.9435, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,886 |
vroomhf/distilbert-base-uncased-finetuned-emotion
|
vroomhf
|
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"
] | 2024-01-12T22:41:20Z |
2024-05-20T13:40:43+00:00
| 6 | 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: 0.9255
name: Accuracy
- type: f1
value: 0.9255597966891186
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: 0.2188
- Accuracy: 0.9255
- F1: 0.9256
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8257 | 1.0 | 250 | 0.3229 | 0.9065 | 0.9057 |
| 0.2559 | 2.0 | 500 | 0.2188 | 0.9255 | 0.9256 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
| 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. -->
# 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: 0.2188
- Accuracy: 0.9255
- F1: 0.9256
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8257 | 1.0 | 250 | 0.3229 | 0.9065 | 0.9057 |
| 0.2559 | 2.0 | 500 | 0.2188 | 0.9255 | 0.9256 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
{"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": 0.9255, "name": "Accuracy"}, {"type": "f1", "value": 0.9255597966891186, "name": "F1"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,887 |
RinaChen/Guwen-nomic-embed-text-v1.5
|
RinaChen
|
sentence-similarity
|
[
"sentence-transformers",
"safetensors",
"nomic_bert",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:756057",
"loss:MultipleNegativesRankingLoss",
"custom_code",
"arxiv:1908.10084",
"arxiv:1705.00652",
"base_model:nomic-ai/nomic-embed-text-v1.5",
"base_model:finetune:nomic-ai/nomic-embed-text-v1.5",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 2024-08-08T01:05:19Z |
2024-08-08T01:06:09+00:00
| 37 | 0 |
---
base_model: nomic-ai/nomic-embed-text-v1.5
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:756057
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: 府君奈何以蓋世之才欲立忠於垂亡之國
sentences:
- 將遠方進貢來的奇獸飛禽以及白山雞等物縱還山林比起雍畤的祭祀禮數頗有增加
- 您為什麼以蓋絕當世的奇才卻打算向這個面臨滅亡的國家盡效忠心呢
- 大統年間他出任岐州刺史在任不久就因為能力強而聞名
- source_sentence: 將率既至授單于印紱詔令上故印紱
sentences:
- 已經到達的五威將到達後授給單于新印信宣讀詔書要求交回漢朝舊印信
- 於是拜陶隗為西南面招討使
- 司馬錯建議秦惠王攻打蜀國張儀說 還不如進攻韓國
- source_sentence: 行醮禮皇太子詣醴席樂作
sentences:
- 閏七月十七日上宣宗廢除皇后胡氏尊諡
- 等到看見西羌鼠竊狗盜父不父子不子君臣沒有分別四夷之人西羌最為低下
- 行醮禮皇太子來到酒醴席奏樂
- source_sentence: 領軍臧盾太府卿沈僧果等並被時遇孝綽尤輕之
sentences:
- 過了幾天太宰官又來要國書並且說 我國自太宰府以東上國使臣沒有到過今大朝派使臣來若不見國書何以相信
- 所以丹陽葛洪解釋說渾天儀注說 天體像雞蛋地就像是雞蛋中的蛋黃獨處於天體之內天是大的而地是小的
- 領軍臧盾太府卿沈僧果等都是因趕上時機而得到官職的孝綽尤其輕蔑他們每次在朝中集合會面雖然一起做官但從不與他們說話
- source_sentence: 九月辛未太祖曾孫舒國公從式進封安定郡王
sentences:
- 九月初二太祖曾孫舒國公從式進封安定郡王
- 楊難當在漢中大肆燒殺搶劫然後率眾離開了漢中向西返回仇池留下趙溫據守梁州又派他的魏興太守薛健屯駐黃金山
- 正統元年普定蠻夷阿遲等反叛非法稱王四處出擊攻打掠奪
---
# SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) <!-- at revision c4f06e01594879a8ccc5c40b0b0a0e2ad46e3a62 -->
- **Maximum Sequence Length:** 8192 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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel
(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("sentence_transformers_model_id")
# Run inference
sentences = [
'九月辛未太祖曾孫舒國公從式進封安定郡王',
'九月初二太祖曾孫舒國公從式進封安定郡王',
'楊難當在漢中大肆燒殺搶劫然後率眾離開了漢中向西返回仇池留下趙溫據守梁州又派他的魏興太守薛健屯駐黃金山',
]
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: 756,057 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 20.76 tokens</li><li>max: 199 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 31.48 tokens</li><li>max: 602 tokens</li></ul> |
* Samples:
| anchor | positive |
|:------------------------------------------|:------------------------------------------------------------|
| <code>虜懷兼弱之威挾廣地之計強兵大眾親自凌殄旍鼓彌年矢石不息</code> | <code>魏人懷有兼併弱小的威嚴胸藏拓展土地的計謀強人的軍隊親自出徵侵逼消滅旌旗戰鼓連年出動戰事不停息</code> |
| <code>孟子曰 以善服人者未有能服人者也以善養人然後能服天下</code> | <code>孟子說 用自己的善良使人們服從的人沒有能使人服從的用善良影響教導人們才能使天下的人們都信服</code> |
| <code>開慶初大元兵渡江理宗議遷都平江慶元后諫不可恐搖動民心乃止</code> | <code>開慶初年大元朝部隊渡過長江理宗打算遷都到平江慶元皇后勸諫不可遷都深恐動搖民心理宗才作罷</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"
}
```
### Evaluation Dataset
#### Unnamed Dataset
* Size: 84,007 evaluation samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 20.23 tokens</li><li>max: 138 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 31.45 tokens</li><li>max: 415 tokens</li></ul> |
* Samples:
| anchor | positive |
|:--------------------------------------------------|:------------------------------------------------------------------|
| <code>雒陽戶五萬二千八百三十九</code> | <code>雒陽有五萬二千八百三十九戶</code> |
| <code>拜南青州刺史在任有政績</code> | <code>任南青州刺史很有政績</code> |
| <code>第六品以下加不得服金釒奠綾錦錦繡七緣綺貂豽裘金叉環鉺及以金校飾器物張絳帳</code> | <code>官位在第六品以下的官員再增加不得穿用金鈿綾錦錦繡七緣綺貂鈉皮衣金叉繯餌以及用金裝飾的器物張絳帳等衣服物品</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
- `eval_strategy`: steps
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `fp16`: True
- `load_best_model_at_end`: True
- `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`: 16
- `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-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `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
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | loss |
|:----------:|:---------:|:-------------:|:----------:|
| 0.0021 | 100 | 0.4574 | - |
| 0.0042 | 200 | 0.4089 | - |
| 0.0063 | 300 | 0.2872 | - |
| 0.0085 | 400 | 0.2909 | - |
| 0.0106 | 500 | 0.3076 | - |
| 0.0127 | 600 | 0.2958 | - |
| 0.0148 | 700 | 0.2953 | - |
| 0.0169 | 800 | 0.31 | - |
| 0.0190 | 900 | 0.3031 | - |
| 0.0212 | 1000 | 0.263 | - |
| 0.0233 | 1100 | 0.27 | - |
| 0.0254 | 1200 | 0.3107 | - |
| 0.0275 | 1300 | 0.2453 | - |
| 0.0296 | 1400 | 0.2487 | - |
| 0.0317 | 1500 | 0.2332 | - |
| 0.0339 | 1600 | 0.2708 | - |
| 0.0360 | 1700 | 0.2731 | - |
| 0.0381 | 1800 | 0.3102 | - |
| 0.0402 | 1900 | 0.3385 | - |
| 0.0423 | 2000 | 0.2802 | - |
| 0.0444 | 2100 | 0.3348 | - |
| 0.0466 | 2200 | 0.2527 | - |
| 0.0487 | 2300 | 0.2916 | - |
| 0.0508 | 2400 | 0.2671 | - |
| 0.0529 | 2500 | 0.2187 | - |
| 0.0550 | 2600 | 0.2624 | - |
| 0.0571 | 2700 | 0.3061 | - |
| 0.0593 | 2800 | 0.2439 | - |
| 0.0614 | 2900 | 0.2831 | - |
| 0.0635 | 3000 | 0.2948 | - |
| 0.0656 | 3100 | 0.2828 | - |
| 0.0677 | 3200 | 0.3079 | - |
| 0.0698 | 3300 | 0.3194 | - |
| 0.0720 | 3400 | 0.2768 | - |
| 0.0741 | 3500 | 0.304 | - |
| 0.0762 | 3600 | 0.3056 | - |
| 0.0783 | 3700 | 0.2562 | - |
| 0.0804 | 3800 | 0.3138 | - |
| 0.0825 | 3900 | 0.3081 | - |
| 0.0846 | 4000 | 0.2733 | - |
| 0.0868 | 4100 | 0.3065 | - |
| 0.0889 | 4200 | 0.25 | - |
| 0.0910 | 4300 | 0.3076 | - |
| 0.0931 | 4400 | 0.2935 | - |
| 0.0952 | 4500 | 0.2644 | - |
| 0.0973 | 4600 | 0.2943 | - |
| 0.0995 | 4700 | 0.316 | - |
| 0.1016 | 4800 | 0.2616 | - |
| 0.1037 | 4900 | 0.2985 | - |
| 0.1058 | 5000 | 0.2962 | 0.2798 |
| 0.1079 | 5100 | 0.2872 | - |
| 0.1100 | 5200 | 0.2963 | - |
| 0.1122 | 5300 | 0.2968 | - |
| 0.1143 | 5400 | 0.2738 | - |
| 0.1164 | 5500 | 0.3198 | - |
| 0.1185 | 5600 | 0.294 | - |
| 0.1206 | 5700 | 0.3296 | - |
| 0.1227 | 5800 | 0.2605 | - |
| 0.1249 | 5900 | 0.3187 | - |
| 0.1270 | 6000 | 0.2657 | - |
| 0.1291 | 6100 | 0.3267 | - |
| 0.1312 | 6200 | 0.3839 | - |
| 0.1333 | 6300 | 0.3077 | - |
| 0.1354 | 6400 | 0.205 | - |
| 0.1376 | 6500 | 0.2839 | - |
| 0.1397 | 6600 | 0.3037 | - |
| 0.1418 | 6700 | 0.2694 | - |
| 0.1439 | 6800 | 0.2956 | - |
| 0.1460 | 6900 | 0.261 | - |
| 0.1481 | 7000 | 0.3173 | - |
| 0.1503 | 7100 | 0.2492 | - |
| 0.1524 | 7200 | 0.2885 | - |
| 0.1545 | 7300 | 0.3059 | - |
| 0.1566 | 7400 | 0.2883 | - |
| 0.1587 | 7500 | 0.2465 | - |
| 0.1608 | 7600 | 0.2926 | - |
| 0.1629 | 7700 | 0.2776 | - |
| 0.1651 | 7800 | 0.2769 | - |
| 0.1672 | 7900 | 0.2644 | - |
| 0.1693 | 8000 | 0.2416 | - |
| 0.1714 | 8100 | 0.254 | - |
| 0.1735 | 8200 | 0.2485 | - |
| 0.1756 | 8300 | 0.3029 | - |
| 0.1778 | 8400 | 0.2938 | - |
| 0.1799 | 8500 | 0.2936 | - |
| 0.1820 | 8600 | 0.2804 | - |
| 0.1841 | 8700 | 0.2408 | - |
| 0.1862 | 8800 | 0.2849 | - |
| 0.1883 | 8900 | 0.2954 | - |
| 0.1905 | 9000 | 0.2902 | - |
| 0.1926 | 9100 | 0.2845 | - |
| 0.1947 | 9200 | 0.3143 | - |
| 0.1968 | 9300 | 0.2514 | - |
| 0.1989 | 9400 | 0.2508 | - |
| 0.2010 | 9500 | 0.2782 | - |
| 0.2032 | 9600 | 0.291 | - |
| 0.2053 | 9700 | 0.2464 | - |
| 0.2074 | 9800 | 0.323 | - |
| 0.2095 | 9900 | 0.2332 | - |
| 0.2116 | 10000 | 0.2231 | 0.2521 |
| 0.2137 | 10100 | 0.245 | - |
| 0.2159 | 10200 | 0.2883 | - |
| 0.2180 | 10300 | 0.3097 | - |
| 0.2201 | 10400 | 0.2303 | - |
| 0.2222 | 10500 | 0.3194 | - |
| 0.2243 | 10600 | 0.2836 | - |
| 0.2264 | 10700 | 0.2727 | - |
| 0.2286 | 10800 | 0.2542 | - |
| 0.2307 | 10900 | 0.2708 | - |
| 0.2328 | 11000 | 0.263 | - |
| 0.2349 | 11100 | 0.3063 | - |
| 0.2370 | 11200 | 0.2667 | - |
| 0.2391 | 11300 | 0.2575 | - |
| 0.2412 | 11400 | 0.2487 | - |
| 0.2434 | 11500 | 0.2552 | - |
| 0.2455 | 11600 | 0.2669 | - |
| 0.2476 | 11700 | 0.2241 | - |
| 0.2497 | 11800 | 0.3029 | - |
| 0.2518 | 11900 | 0.2443 | - |
| 0.2539 | 12000 | 0.2961 | - |
| 0.2561 | 12100 | 0.2561 | - |
| 0.2582 | 12200 | 0.2436 | - |
| 0.2603 | 12300 | 0.2601 | - |
| 0.2624 | 12400 | 0.2553 | - |
| 0.2645 | 12500 | 0.2617 | - |
| 0.2666 | 12600 | 0.2581 | - |
| 0.2688 | 12700 | 0.2452 | - |
| 0.2709 | 12800 | 0.2227 | - |
| 0.2730 | 12900 | 0.2455 | - |
| 0.2751 | 13000 | 0.2469 | - |
| 0.2772 | 13100 | 0.2197 | - |
| 0.2793 | 13200 | 0.3086 | - |
| 0.2815 | 13300 | 0.2379 | - |
| 0.2836 | 13400 | 0.2441 | - |
| 0.2857 | 13500 | 0.2854 | - |
| 0.2878 | 13600 | 0.2405 | - |
| 0.2899 | 13700 | 0.2681 | - |
| 0.2920 | 13800 | 0.2405 | - |
| 0.2942 | 13900 | 0.251 | - |
| 0.2963 | 14000 | 0.2477 | - |
| 0.2984 | 14100 | 0.231 | - |
| 0.3005 | 14200 | 0.26 | - |
| 0.3026 | 14300 | 0.2395 | - |
| 0.3047 | 14400 | 0.2296 | - |
| 0.3069 | 14500 | 0.2554 | - |
| 0.3090 | 14600 | 0.2434 | - |
| 0.3111 | 14700 | 0.2247 | - |
| 0.3132 | 14800 | 0.267 | - |
| 0.3153 | 14900 | 0.2212 | - |
| 0.3174 | 15000 | 0.2744 | 0.2352 |
| 0.3195 | 15100 | 0.2168 | - |
| 0.3217 | 15200 | 0.2042 | - |
| 0.3238 | 15300 | 0.2187 | - |
| 0.3259 | 15400 | 0.2368 | - |
| 0.3280 | 15500 | 0.2693 | - |
| 0.3301 | 15600 | 0.255 | - |
| 0.3322 | 15700 | 0.2398 | - |
| 0.3344 | 15800 | 0.247 | - |
| 0.3365 | 15900 | 0.2431 | - |
| 0.3386 | 16000 | 0.2349 | - |
| 0.3407 | 16100 | 0.212 | - |
| 0.3428 | 16200 | 0.2875 | - |
| 0.3449 | 16300 | 0.2571 | - |
| 0.3471 | 16400 | 0.2513 | - |
| 0.3492 | 16500 | 0.2729 | - |
| 0.3513 | 16600 | 0.2755 | - |
| 0.3534 | 16700 | 0.2079 | - |
| 0.3555 | 16800 | 0.1997 | - |
| 0.3576 | 16900 | 0.2217 | - |
| 0.3598 | 17000 | 0.1887 | - |
| 0.3619 | 17100 | 0.2623 | - |
| 0.3640 | 17200 | 0.2049 | - |
| 0.3661 | 17300 | 0.2 | - |
| 0.3682 | 17400 | 0.2367 | - |
| 0.3703 | 17500 | 0.2368 | - |
| 0.3725 | 17600 | 0.2311 | - |
| 0.3746 | 17700 | 0.2359 | - |
| 0.3767 | 17800 | 0.2586 | - |
| 0.3788 | 17900 | 0.2222 | - |
| 0.3809 | 18000 | 0.2561 | - |
| 0.3830 | 18100 | 0.2246 | - |
| 0.3852 | 18200 | 0.1871 | - |
| 0.3873 | 18300 | 0.2147 | - |
| 0.3894 | 18400 | 0.2741 | - |
| 0.3915 | 18500 | 0.2079 | - |
| 0.3936 | 18600 | 0.2399 | - |
| 0.3957 | 18700 | 0.2375 | - |
| 0.3978 | 18800 | 0.2502 | - |
| 0.4000 | 18900 | 0.2385 | - |
| 0.4021 | 19000 | 0.2647 | - |
| 0.4042 | 19100 | 0.1847 | - |
| 0.4063 | 19200 | 0.2367 | - |
| 0.4084 | 19300 | 0.2148 | - |
| 0.4105 | 19400 | 0.1826 | - |
| 0.4127 | 19500 | 0.225 | - |
| 0.4148 | 19600 | 0.2415 | - |
| 0.4169 | 19700 | 0.2998 | - |
| 0.4190 | 19800 | 0.2435 | - |
| 0.4211 | 19900 | 0.2283 | - |
| 0.4232 | 20000 | 0.2782 | 0.2263 |
| 0.4254 | 20100 | 0.2786 | - |
| 0.4275 | 20200 | 0.2695 | - |
| 0.4296 | 20300 | 0.2112 | - |
| 0.4317 | 20400 | 0.2006 | - |
| 0.4338 | 20500 | 0.2031 | - |
| 0.4359 | 20600 | 0.2335 | - |
| 0.4381 | 20700 | 0.2154 | - |
| 0.4402 | 20800 | 0.2225 | - |
| 0.4423 | 20900 | 0.2234 | - |
| 0.4444 | 21000 | 0.2233 | - |
| 0.4465 | 21100 | 0.1851 | - |
| 0.4486 | 21200 | 0.2009 | - |
| 0.4508 | 21300 | 0.2337 | - |
| 0.4529 | 21400 | 0.2175 | - |
| 0.4550 | 21500 | 0.2564 | - |
| 0.4571 | 21600 | 0.205 | - |
| 0.4592 | 21700 | 0.233 | - |
| 0.4613 | 21800 | 0.2027 | - |
| 0.4635 | 21900 | 0.209 | - |
| 0.4656 | 22000 | 0.261 | - |
| 0.4677 | 22100 | 0.1755 | - |
| 0.4698 | 22200 | 0.2219 | - |
| 0.4719 | 22300 | 0.2108 | - |
| 0.4740 | 22400 | 0.212 | - |
| 0.4762 | 22500 | 0.2676 | - |
| 0.4783 | 22600 | 0.2314 | - |
| 0.4804 | 22700 | 0.1838 | - |
| 0.4825 | 22800 | 0.1967 | - |
| 0.4846 | 22900 | 0.2412 | - |
| 0.4867 | 23000 | 0.2203 | - |
| 0.4888 | 23100 | 0.2183 | - |
| 0.4910 | 23200 | 0.239 | - |
| 0.4931 | 23300 | 0.2273 | - |
| 0.4952 | 23400 | 0.2335 | - |
| 0.4973 | 23500 | 0.202 | - |
| 0.4994 | 23600 | 0.2176 | - |
| 0.5015 | 23700 | 0.2331 | - |
| 0.5037 | 23800 | 0.1949 | - |
| 0.5058 | 23900 | 0.2321 | - |
| 0.5079 | 24000 | 0.2046 | - |
| 0.5100 | 24100 | 0.2092 | - |
| 0.5121 | 24200 | 0.2195 | - |
| 0.5142 | 24300 | 0.2069 | - |
| 0.5164 | 24400 | 0.2049 | - |
| 0.5185 | 24500 | 0.2955 | - |
| 0.5206 | 24600 | 0.2101 | - |
| 0.5227 | 24700 | 0.2036 | - |
| 0.5248 | 24800 | 0.2507 | - |
| 0.5269 | 24900 | 0.2343 | - |
| 0.5291 | 25000 | 0.2026 | 0.2072 |
| 0.5312 | 25100 | 0.2288 | - |
| 0.5333 | 25200 | 0.2208 | - |
| 0.5354 | 25300 | 0.1914 | - |
| 0.5375 | 25400 | 0.1903 | - |
| 0.5396 | 25500 | 0.2156 | - |
| 0.5418 | 25600 | 0.216 | - |
| 0.5439 | 25700 | 0.1909 | - |
| 0.5460 | 25800 | 0.2265 | - |
| 0.5481 | 25900 | 0.2447 | - |
| 0.5502 | 26000 | 0.1879 | - |
| 0.5523 | 26100 | 0.204 | - |
| 0.5545 | 26200 | 0.2262 | - |
| 0.5566 | 26300 | 0.2448 | - |
| 0.5587 | 26400 | 0.1758 | - |
| 0.5608 | 26500 | 0.2102 | - |
| 0.5629 | 26600 | 0.2175 | - |
| 0.5650 | 26700 | 0.2109 | - |
| 0.5671 | 26800 | 0.202 | - |
| 0.5693 | 26900 | 0.2075 | - |
| 0.5714 | 27000 | 0.2021 | - |
| 0.5735 | 27100 | 0.1799 | - |
| 0.5756 | 27200 | 0.2084 | - |
| 0.5777 | 27300 | 0.2114 | - |
| 0.5798 | 27400 | 0.1851 | - |
| 0.5820 | 27500 | 0.22 | - |
| 0.5841 | 27600 | 0.181 | - |
| 0.5862 | 27700 | 0.2276 | - |
| 0.5883 | 27800 | 0.1944 | - |
| 0.5904 | 27900 | 0.1907 | - |
| 0.5925 | 28000 | 0.2176 | - |
| 0.5947 | 28100 | 0.2243 | - |
| 0.5968 | 28200 | 0.2191 | - |
| 0.5989 | 28300 | 0.2215 | - |
| 0.6010 | 28400 | 0.1769 | - |
| 0.6031 | 28500 | 0.1971 | - |
| 0.6052 | 28600 | 0.179 | - |
| 0.6074 | 28700 | 0.2308 | - |
| 0.6095 | 28800 | 0.2453 | - |
| 0.6116 | 28900 | 0.2293 | - |
| 0.6137 | 29000 | 0.2191 | - |
| 0.6158 | 29100 | 0.1988 | - |
| 0.6179 | 29200 | 0.1878 | - |
| 0.6201 | 29300 | 0.2215 | - |
| 0.6222 | 29400 | 0.2188 | - |
| 0.6243 | 29500 | 0.1821 | - |
| 0.6264 | 29600 | 0.1856 | - |
| 0.6285 | 29700 | 0.1907 | - |
| 0.6306 | 29800 | 0.1999 | - |
| 0.6328 | 29900 | 0.1803 | - |
| 0.6349 | 30000 | 0.201 | 0.1948 |
| 0.6370 | 30100 | 0.179 | - |
| 0.6391 | 30200 | 0.2073 | - |
| 0.6412 | 30300 | 0.2676 | - |
| 0.6433 | 30400 | 0.1824 | - |
| 0.6454 | 30500 | 0.1995 | - |
| 0.6476 | 30600 | 0.2097 | - |
| 0.6497 | 30700 | 0.2421 | - |
| 0.6518 | 30800 | 0.1745 | - |
| 0.6539 | 30900 | 0.2682 | - |
| 0.6560 | 31000 | 0.1892 | - |
| 0.6581 | 31100 | 0.2054 | - |
| 0.6603 | 31200 | 0.23 | - |
| 0.6624 | 31300 | 0.1711 | - |
| 0.6645 | 31400 | 0.2163 | - |
| 0.6666 | 31500 | 0.196 | - |
| 0.6687 | 31600 | 0.1746 | - |
| 0.6708 | 31700 | 0.2402 | - |
| 0.6730 | 31800 | 0.2096 | - |
| 0.6751 | 31900 | 0.1934 | - |
| 0.6772 | 32000 | 0.2021 | - |
| 0.6793 | 32100 | 0.1942 | - |
| 0.6814 | 32200 | 0.2076 | - |
| 0.6835 | 32300 | 0.1662 | - |
| 0.6857 | 32400 | 0.1777 | - |
| 0.6878 | 32500 | 0.1899 | - |
| 0.6899 | 32600 | 0.2253 | - |
| 0.6920 | 32700 | 0.221 | - |
| 0.6941 | 32800 | 0.1797 | - |
| 0.6962 | 32900 | 0.1884 | - |
| 0.6984 | 33000 | 0.2185 | - |
| 0.7005 | 33100 | 0.193 | - |
| 0.7026 | 33200 | 0.1975 | - |
| 0.7047 | 33300 | 0.1774 | - |
| 0.7068 | 33400 | 0.1709 | - |
| 0.7089 | 33500 | 0.1753 | - |
| 0.7111 | 33600 | 0.1834 | - |
| 0.7132 | 33700 | 0.1853 | - |
| 0.7153 | 33800 | 0.2155 | - |
| 0.7174 | 33900 | 0.1837 | - |
| 0.7195 | 34000 | 0.1655 | - |
| 0.7216 | 34100 | 0.212 | - |
| 0.7237 | 34200 | 0.2203 | - |
| 0.7259 | 34300 | 0.2267 | - |
| 0.7280 | 34400 | 0.208 | - |
| 0.7301 | 34500 | 0.1545 | - |
| 0.7322 | 34600 | 0.2003 | - |
| 0.7343 | 34700 | 0.2058 | - |
| 0.7364 | 34800 | 0.1837 | - |
| 0.7386 | 34900 | 0.2199 | - |
| 0.7407 | 35000 | 0.1931 | 0.1848 |
| 0.7428 | 35100 | 0.2456 | - |
| 0.7449 | 35200 | 0.1996 | - |
| 0.7470 | 35300 | 0.2145 | - |
| 0.7491 | 35400 | 0.1915 | - |
| 0.7513 | 35500 | 0.1734 | - |
| 0.7534 | 35600 | 0.19 | - |
| 0.7555 | 35700 | 0.182 | - |
| 0.7576 | 35800 | 0.1808 | - |
| 0.7597 | 35900 | 0.1625 | - |
| 0.7618 | 36000 | 0.1813 | - |
| 0.7640 | 36100 | 0.1412 | - |
| 0.7661 | 36200 | 0.2279 | - |
| 0.7682 | 36300 | 0.2444 | - |
| 0.7703 | 36400 | 0.1882 | - |
| 0.7724 | 36500 | 0.1731 | - |
| 0.7745 | 36600 | 0.1794 | - |
| 0.7767 | 36700 | 0.2577 | - |
| 0.7788 | 36800 | 0.169 | - |
| 0.7809 | 36900 | 0.1725 | - |
| 0.7830 | 37000 | 0.1788 | - |
| 0.7851 | 37100 | 0.1783 | - |
| 0.7872 | 37200 | 0.1764 | - |
| 0.7894 | 37300 | 0.1616 | - |
| 0.7915 | 37400 | 0.21 | - |
| 0.7936 | 37500 | 0.2091 | - |
| 0.7957 | 37600 | 0.1107 | - |
| 0.7978 | 37700 | 0.1773 | - |
| 0.7999 | 37800 | 0.1801 | - |
| 0.8020 | 37900 | 0.1621 | - |
| 0.8042 | 38000 | 0.189 | - |
| 0.8063 | 38100 | 0.182 | - |
| 0.8084 | 38200 | 0.1912 | - |
| 0.8105 | 38300 | 0.1731 | - |
| 0.8126 | 38400 | 0.1646 | - |
| 0.8147 | 38500 | 0.2037 | - |
| 0.8169 | 38600 | 0.1418 | - |
| 0.8190 | 38700 | 0.1485 | - |
| 0.8211 | 38800 | 0.2221 | - |
| 0.8232 | 38900 | 0.1886 | - |
| 0.8253 | 39000 | 0.2082 | - |
| 0.8274 | 39100 | 0.1742 | - |
| 0.8296 | 39200 | 0.1589 | - |
| 0.8317 | 39300 | 0.1959 | - |
| 0.8338 | 39400 | 0.1517 | - |
| 0.8359 | 39500 | 0.2049 | - |
| 0.8380 | 39600 | 0.2187 | - |
| 0.8401 | 39700 | 0.1801 | - |
| 0.8423 | 39800 | 0.1735 | - |
| 0.8444 | 39900 | 0.1881 | - |
| 0.8465 | 40000 | 0.1778 | 0.1787 |
| 0.8486 | 40100 | 0.1898 | - |
| 0.8507 | 40200 | 0.2021 | - |
| 0.8528 | 40300 | 0.1972 | - |
| 0.8550 | 40400 | 0.156 | - |
| 0.8571 | 40500 | 0.1791 | - |
| 0.8592 | 40600 | 0.188 | - |
| 0.8613 | 40700 | 0.2177 | - |
| 0.8634 | 40800 | 0.1287 | - |
| 0.8655 | 40900 | 0.1797 | - |
| 0.8677 | 41000 | 0.1533 | - |
| 0.8698 | 41100 | 0.1668 | - |
| 0.8719 | 41200 | 0.2047 | - |
| 0.8740 | 41300 | 0.1619 | - |
| 0.8761 | 41400 | 0.165 | - |
| 0.8782 | 41500 | 0.1781 | - |
| 0.8803 | 41600 | 0.2221 | - |
| 0.8825 | 41700 | 0.2031 | - |
| 0.8846 | 41800 | 0.1732 | - |
| 0.8867 | 41900 | 0.1599 | - |
| 0.8888 | 42000 | 0.1865 | - |
| 0.8909 | 42100 | 0.1367 | - |
| 0.8930 | 42200 | 0.1469 | - |
| 0.8952 | 42300 | 0.1777 | - |
| 0.8973 | 42400 | 0.1833 | - |
| 0.8994 | 42500 | 0.2102 | - |
| 0.9015 | 42600 | 0.164 | - |
| 0.9036 | 42700 | 0.1752 | - |
| 0.9057 | 42800 | 0.2186 | - |
| 0.9079 | 42900 | 0.1824 | - |
| 0.9100 | 43000 | 0.1796 | - |
| 0.9121 | 43100 | 0.1626 | - |
| 0.9142 | 43200 | 0.1623 | - |
| 0.9163 | 43300 | 0.2036 | - |
| 0.9184 | 43400 | 0.1365 | - |
| 0.9206 | 43500 | 0.1792 | - |
| 0.9227 | 43600 | 0.1583 | - |
| 0.9248 | 43700 | 0.1943 | - |
| 0.9269 | 43800 | 0.1931 | - |
| 0.9290 | 43900 | 0.1777 | - |
| 0.9311 | 44000 | 0.1633 | - |
| 0.9333 | 44100 | 0.1841 | - |
| 0.9354 | 44200 | 0.1674 | - |
| 0.9375 | 44300 | 0.1958 | - |
| 0.9396 | 44400 | 0.1831 | - |
| 0.9417 | 44500 | 0.1899 | - |
| 0.9438 | 44600 | 0.177 | - |
| 0.9460 | 44700 | 0.1881 | - |
| 0.9481 | 44800 | 0.1643 | - |
| 0.9502 | 44900 | 0.1462 | - |
| **0.9523** | **45000** | **0.2118** | **0.1719** |
| 0.9544 | 45100 | 0.1655 | - |
| 0.9565 | 45200 | 0.1567 | - |
| 0.9586 | 45300 | 0.1429 | - |
| 0.9608 | 45400 | 0.1718 | - |
| 0.9629 | 45500 | 0.1549 | - |
| 0.9650 | 45600 | 0.1556 | - |
| 0.9671 | 45700 | 0.1323 | - |
| 0.9692 | 45800 | 0.1988 | - |
| 0.9713 | 45900 | 0.15 | - |
| 0.9735 | 46000 | 0.1546 | - |
| 0.9756 | 46100 | 0.1472 | - |
| 0.9777 | 46200 | 0.196 | - |
| 0.9798 | 46300 | 0.1913 | - |
| 0.9819 | 46400 | 0.2261 | - |
| 0.9840 | 46500 | 0.1842 | - |
| 0.9862 | 46600 | 0.172 | - |
| 0.9883 | 46700 | 0.1925 | - |
| 0.9904 | 46800 | 0.1928 | - |
| 0.9925 | 46900 | 0.1698 | - |
| 0.9946 | 47000 | 0.1778 | - |
| 0.9967 | 47100 | 0.1497 | - |
| 0.9989 | 47200 | 0.1506 | - |
* The bold row denotes the saved checkpoint.
</details>
### Framework Versions
- Python: 3.12.4
- Sentence Transformers: 3.1.0.dev0
- Transformers: 4.42.4
- PyTorch: 2.3.1+cpu
- Accelerate: 0.32.1
- Datasets: 2.20.0
- 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",
}
```
#### 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 nomic-ai/nomic-embed-text-v1.5
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) <!-- at revision c4f06e01594879a8ccc5c40b0b0a0e2ad46e3a62 -->
- **Maximum Sequence Length:** 8192 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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel
(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("sentence_transformers_model_id")
# Run inference
sentences = [
'九月辛未太祖曾孫舒國公從式進封安定郡王',
'九月初二太祖曾孫舒國公從式進封安定郡王',
'楊難當在漢中大肆燒殺搶劫然後率眾離開了漢中向西返回仇池留下趙溫據守梁州又派他的魏興太守薛健屯駐黃金山',
]
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: 756,057 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 20.76 tokens</li><li>max: 199 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 31.48 tokens</li><li>max: 602 tokens</li></ul> |
* Samples:
| anchor | positive |
|:------------------------------------------|:------------------------------------------------------------|
| <code>虜懷兼弱之威挾廣地之計強兵大眾親自凌殄旍鼓彌年矢石不息</code> | <code>魏人懷有兼併弱小的威嚴胸藏拓展土地的計謀強人的軍隊親自出徵侵逼消滅旌旗戰鼓連年出動戰事不停息</code> |
| <code>孟子曰 以善服人者未有能服人者也以善養人然後能服天下</code> | <code>孟子說 用自己的善良使人們服從的人沒有能使人服從的用善良影響教導人們才能使天下的人們都信服</code> |
| <code>開慶初大元兵渡江理宗議遷都平江慶元后諫不可恐搖動民心乃止</code> | <code>開慶初年大元朝部隊渡過長江理宗打算遷都到平江慶元皇后勸諫不可遷都深恐動搖民心理宗才作罷</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"
}
```
### Evaluation Dataset
#### Unnamed Dataset
* Size: 84,007 evaluation samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 20.23 tokens</li><li>max: 138 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 31.45 tokens</li><li>max: 415 tokens</li></ul> |
* Samples:
| anchor | positive |
|:--------------------------------------------------|:------------------------------------------------------------------|
| <code>雒陽戶五萬二千八百三十九</code> | <code>雒陽有五萬二千八百三十九戶</code> |
| <code>拜南青州刺史在任有政績</code> | <code>任南青州刺史很有政績</code> |
| <code>第六品以下加不得服金釒奠綾錦錦繡七緣綺貂豽裘金叉環鉺及以金校飾器物張絳帳</code> | <code>官位在第六品以下的官員再增加不得穿用金鈿綾錦錦繡七緣綺貂鈉皮衣金叉繯餌以及用金裝飾的器物張絳帳等衣服物品</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
- `eval_strategy`: steps
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `fp16`: True
- `load_best_model_at_end`: True
- `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`: 16
- `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-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `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
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | loss |
|:----------:|:---------:|:-------------:|:----------:|
| 0.0021 | 100 | 0.4574 | - |
| 0.0042 | 200 | 0.4089 | - |
| 0.0063 | 300 | 0.2872 | - |
| 0.0085 | 400 | 0.2909 | - |
| 0.0106 | 500 | 0.3076 | - |
| 0.0127 | 600 | 0.2958 | - |
| 0.0148 | 700 | 0.2953 | - |
| 0.0169 | 800 | 0.31 | - |
| 0.0190 | 900 | 0.3031 | - |
| 0.0212 | 1000 | 0.263 | - |
| 0.0233 | 1100 | 0.27 | - |
| 0.0254 | 1200 | 0.3107 | - |
| 0.0275 | 1300 | 0.2453 | - |
| 0.0296 | 1400 | 0.2487 | - |
| 0.0317 | 1500 | 0.2332 | - |
| 0.0339 | 1600 | 0.2708 | - |
| 0.0360 | 1700 | 0.2731 | - |
| 0.0381 | 1800 | 0.3102 | - |
| 0.0402 | 1900 | 0.3385 | - |
| 0.0423 | 2000 | 0.2802 | - |
| 0.0444 | 2100 | 0.3348 | - |
| 0.0466 | 2200 | 0.2527 | - |
| 0.0487 | 2300 | 0.2916 | - |
| 0.0508 | 2400 | 0.2671 | - |
| 0.0529 | 2500 | 0.2187 | - |
| 0.0550 | 2600 | 0.2624 | - |
| 0.0571 | 2700 | 0.3061 | - |
| 0.0593 | 2800 | 0.2439 | - |
| 0.0614 | 2900 | 0.2831 | - |
| 0.0635 | 3000 | 0.2948 | - |
| 0.0656 | 3100 | 0.2828 | - |
| 0.0677 | 3200 | 0.3079 | - |
| 0.0698 | 3300 | 0.3194 | - |
| 0.0720 | 3400 | 0.2768 | - |
| 0.0741 | 3500 | 0.304 | - |
| 0.0762 | 3600 | 0.3056 | - |
| 0.0783 | 3700 | 0.2562 | - |
| 0.0804 | 3800 | 0.3138 | - |
| 0.0825 | 3900 | 0.3081 | - |
| 0.0846 | 4000 | 0.2733 | - |
| 0.0868 | 4100 | 0.3065 | - |
| 0.0889 | 4200 | 0.25 | - |
| 0.0910 | 4300 | 0.3076 | - |
| 0.0931 | 4400 | 0.2935 | - |
| 0.0952 | 4500 | 0.2644 | - |
| 0.0973 | 4600 | 0.2943 | - |
| 0.0995 | 4700 | 0.316 | - |
| 0.1016 | 4800 | 0.2616 | - |
| 0.1037 | 4900 | 0.2985 | - |
| 0.1058 | 5000 | 0.2962 | 0.2798 |
| 0.1079 | 5100 | 0.2872 | - |
| 0.1100 | 5200 | 0.2963 | - |
| 0.1122 | 5300 | 0.2968 | - |
| 0.1143 | 5400 | 0.2738 | - |
| 0.1164 | 5500 | 0.3198 | - |
| 0.1185 | 5600 | 0.294 | - |
| 0.1206 | 5700 | 0.3296 | - |
| 0.1227 | 5800 | 0.2605 | - |
| 0.1249 | 5900 | 0.3187 | - |
| 0.1270 | 6000 | 0.2657 | - |
| 0.1291 | 6100 | 0.3267 | - |
| 0.1312 | 6200 | 0.3839 | - |
| 0.1333 | 6300 | 0.3077 | - |
| 0.1354 | 6400 | 0.205 | - |
| 0.1376 | 6500 | 0.2839 | - |
| 0.1397 | 6600 | 0.3037 | - |
| 0.1418 | 6700 | 0.2694 | - |
| 0.1439 | 6800 | 0.2956 | - |
| 0.1460 | 6900 | 0.261 | - |
| 0.1481 | 7000 | 0.3173 | - |
| 0.1503 | 7100 | 0.2492 | - |
| 0.1524 | 7200 | 0.2885 | - |
| 0.1545 | 7300 | 0.3059 | - |
| 0.1566 | 7400 | 0.2883 | - |
| 0.1587 | 7500 | 0.2465 | - |
| 0.1608 | 7600 | 0.2926 | - |
| 0.1629 | 7700 | 0.2776 | - |
| 0.1651 | 7800 | 0.2769 | - |
| 0.1672 | 7900 | 0.2644 | - |
| 0.1693 | 8000 | 0.2416 | - |
| 0.1714 | 8100 | 0.254 | - |
| 0.1735 | 8200 | 0.2485 | - |
| 0.1756 | 8300 | 0.3029 | - |
| 0.1778 | 8400 | 0.2938 | - |
| 0.1799 | 8500 | 0.2936 | - |
| 0.1820 | 8600 | 0.2804 | - |
| 0.1841 | 8700 | 0.2408 | - |
| 0.1862 | 8800 | 0.2849 | - |
| 0.1883 | 8900 | 0.2954 | - |
| 0.1905 | 9000 | 0.2902 | - |
| 0.1926 | 9100 | 0.2845 | - |
| 0.1947 | 9200 | 0.3143 | - |
| 0.1968 | 9300 | 0.2514 | - |
| 0.1989 | 9400 | 0.2508 | - |
| 0.2010 | 9500 | 0.2782 | - |
| 0.2032 | 9600 | 0.291 | - |
| 0.2053 | 9700 | 0.2464 | - |
| 0.2074 | 9800 | 0.323 | - |
| 0.2095 | 9900 | 0.2332 | - |
| 0.2116 | 10000 | 0.2231 | 0.2521 |
| 0.2137 | 10100 | 0.245 | - |
| 0.2159 | 10200 | 0.2883 | - |
| 0.2180 | 10300 | 0.3097 | - |
| 0.2201 | 10400 | 0.2303 | - |
| 0.2222 | 10500 | 0.3194 | - |
| 0.2243 | 10600 | 0.2836 | - |
| 0.2264 | 10700 | 0.2727 | - |
| 0.2286 | 10800 | 0.2542 | - |
| 0.2307 | 10900 | 0.2708 | - |
| 0.2328 | 11000 | 0.263 | - |
| 0.2349 | 11100 | 0.3063 | - |
| 0.2370 | 11200 | 0.2667 | - |
| 0.2391 | 11300 | 0.2575 | - |
| 0.2412 | 11400 | 0.2487 | - |
| 0.2434 | 11500 | 0.2552 | - |
| 0.2455 | 11600 | 0.2669 | - |
| 0.2476 | 11700 | 0.2241 | - |
| 0.2497 | 11800 | 0.3029 | - |
| 0.2518 | 11900 | 0.2443 | - |
| 0.2539 | 12000 | 0.2961 | - |
| 0.2561 | 12100 | 0.2561 | - |
| 0.2582 | 12200 | 0.2436 | - |
| 0.2603 | 12300 | 0.2601 | - |
| 0.2624 | 12400 | 0.2553 | - |
| 0.2645 | 12500 | 0.2617 | - |
| 0.2666 | 12600 | 0.2581 | - |
| 0.2688 | 12700 | 0.2452 | - |
| 0.2709 | 12800 | 0.2227 | - |
| 0.2730 | 12900 | 0.2455 | - |
| 0.2751 | 13000 | 0.2469 | - |
| 0.2772 | 13100 | 0.2197 | - |
| 0.2793 | 13200 | 0.3086 | - |
| 0.2815 | 13300 | 0.2379 | - |
| 0.2836 | 13400 | 0.2441 | - |
| 0.2857 | 13500 | 0.2854 | - |
| 0.2878 | 13600 | 0.2405 | - |
| 0.2899 | 13700 | 0.2681 | - |
| 0.2920 | 13800 | 0.2405 | - |
| 0.2942 | 13900 | 0.251 | - |
| 0.2963 | 14000 | 0.2477 | - |
| 0.2984 | 14100 | 0.231 | - |
| 0.3005 | 14200 | 0.26 | - |
| 0.3026 | 14300 | 0.2395 | - |
| 0.3047 | 14400 | 0.2296 | - |
| 0.3069 | 14500 | 0.2554 | - |
| 0.3090 | 14600 | 0.2434 | - |
| 0.3111 | 14700 | 0.2247 | - |
| 0.3132 | 14800 | 0.267 | - |
| 0.3153 | 14900 | 0.2212 | - |
| 0.3174 | 15000 | 0.2744 | 0.2352 |
| 0.3195 | 15100 | 0.2168 | - |
| 0.3217 | 15200 | 0.2042 | - |
| 0.3238 | 15300 | 0.2187 | - |
| 0.3259 | 15400 | 0.2368 | - |
| 0.3280 | 15500 | 0.2693 | - |
| 0.3301 | 15600 | 0.255 | - |
| 0.3322 | 15700 | 0.2398 | - |
| 0.3344 | 15800 | 0.247 | - |
| 0.3365 | 15900 | 0.2431 | - |
| 0.3386 | 16000 | 0.2349 | - |
| 0.3407 | 16100 | 0.212 | - |
| 0.3428 | 16200 | 0.2875 | - |
| 0.3449 | 16300 | 0.2571 | - |
| 0.3471 | 16400 | 0.2513 | - |
| 0.3492 | 16500 | 0.2729 | - |
| 0.3513 | 16600 | 0.2755 | - |
| 0.3534 | 16700 | 0.2079 | - |
| 0.3555 | 16800 | 0.1997 | - |
| 0.3576 | 16900 | 0.2217 | - |
| 0.3598 | 17000 | 0.1887 | - |
| 0.3619 | 17100 | 0.2623 | - |
| 0.3640 | 17200 | 0.2049 | - |
| 0.3661 | 17300 | 0.2 | - |
| 0.3682 | 17400 | 0.2367 | - |
| 0.3703 | 17500 | 0.2368 | - |
| 0.3725 | 17600 | 0.2311 | - |
| 0.3746 | 17700 | 0.2359 | - |
| 0.3767 | 17800 | 0.2586 | - |
| 0.3788 | 17900 | 0.2222 | - |
| 0.3809 | 18000 | 0.2561 | - |
| 0.3830 | 18100 | 0.2246 | - |
| 0.3852 | 18200 | 0.1871 | - |
| 0.3873 | 18300 | 0.2147 | - |
| 0.3894 | 18400 | 0.2741 | - |
| 0.3915 | 18500 | 0.2079 | - |
| 0.3936 | 18600 | 0.2399 | - |
| 0.3957 | 18700 | 0.2375 | - |
| 0.3978 | 18800 | 0.2502 | - |
| 0.4000 | 18900 | 0.2385 | - |
| 0.4021 | 19000 | 0.2647 | - |
| 0.4042 | 19100 | 0.1847 | - |
| 0.4063 | 19200 | 0.2367 | - |
| 0.4084 | 19300 | 0.2148 | - |
| 0.4105 | 19400 | 0.1826 | - |
| 0.4127 | 19500 | 0.225 | - |
| 0.4148 | 19600 | 0.2415 | - |
| 0.4169 | 19700 | 0.2998 | - |
| 0.4190 | 19800 | 0.2435 | - |
| 0.4211 | 19900 | 0.2283 | - |
| 0.4232 | 20000 | 0.2782 | 0.2263 |
| 0.4254 | 20100 | 0.2786 | - |
| 0.4275 | 20200 | 0.2695 | - |
| 0.4296 | 20300 | 0.2112 | - |
| 0.4317 | 20400 | 0.2006 | - |
| 0.4338 | 20500 | 0.2031 | - |
| 0.4359 | 20600 | 0.2335 | - |
| 0.4381 | 20700 | 0.2154 | - |
| 0.4402 | 20800 | 0.2225 | - |
| 0.4423 | 20900 | 0.2234 | - |
| 0.4444 | 21000 | 0.2233 | - |
| 0.4465 | 21100 | 0.1851 | - |
| 0.4486 | 21200 | 0.2009 | - |
| 0.4508 | 21300 | 0.2337 | - |
| 0.4529 | 21400 | 0.2175 | - |
| 0.4550 | 21500 | 0.2564 | - |
| 0.4571 | 21600 | 0.205 | - |
| 0.4592 | 21700 | 0.233 | - |
| 0.4613 | 21800 | 0.2027 | - |
| 0.4635 | 21900 | 0.209 | - |
| 0.4656 | 22000 | 0.261 | - |
| 0.4677 | 22100 | 0.1755 | - |
| 0.4698 | 22200 | 0.2219 | - |
| 0.4719 | 22300 | 0.2108 | - |
| 0.4740 | 22400 | 0.212 | - |
| 0.4762 | 22500 | 0.2676 | - |
| 0.4783 | 22600 | 0.2314 | - |
| 0.4804 | 22700 | 0.1838 | - |
| 0.4825 | 22800 | 0.1967 | - |
| 0.4846 | 22900 | 0.2412 | - |
| 0.4867 | 23000 | 0.2203 | - |
| 0.4888 | 23100 | 0.2183 | - |
| 0.4910 | 23200 | 0.239 | - |
| 0.4931 | 23300 | 0.2273 | - |
| 0.4952 | 23400 | 0.2335 | - |
| 0.4973 | 23500 | 0.202 | - |
| 0.4994 | 23600 | 0.2176 | - |
| 0.5015 | 23700 | 0.2331 | - |
| 0.5037 | 23800 | 0.1949 | - |
| 0.5058 | 23900 | 0.2321 | - |
| 0.5079 | 24000 | 0.2046 | - |
| 0.5100 | 24100 | 0.2092 | - |
| 0.5121 | 24200 | 0.2195 | - |
| 0.5142 | 24300 | 0.2069 | - |
| 0.5164 | 24400 | 0.2049 | - |
| 0.5185 | 24500 | 0.2955 | - |
| 0.5206 | 24600 | 0.2101 | - |
| 0.5227 | 24700 | 0.2036 | - |
| 0.5248 | 24800 | 0.2507 | - |
| 0.5269 | 24900 | 0.2343 | - |
| 0.5291 | 25000 | 0.2026 | 0.2072 |
| 0.5312 | 25100 | 0.2288 | - |
| 0.5333 | 25200 | 0.2208 | - |
| 0.5354 | 25300 | 0.1914 | - |
| 0.5375 | 25400 | 0.1903 | - |
| 0.5396 | 25500 | 0.2156 | - |
| 0.5418 | 25600 | 0.216 | - |
| 0.5439 | 25700 | 0.1909 | - |
| 0.5460 | 25800 | 0.2265 | - |
| 0.5481 | 25900 | 0.2447 | - |
| 0.5502 | 26000 | 0.1879 | - |
| 0.5523 | 26100 | 0.204 | - |
| 0.5545 | 26200 | 0.2262 | - |
| 0.5566 | 26300 | 0.2448 | - |
| 0.5587 | 26400 | 0.1758 | - |
| 0.5608 | 26500 | 0.2102 | - |
| 0.5629 | 26600 | 0.2175 | - |
| 0.5650 | 26700 | 0.2109 | - |
| 0.5671 | 26800 | 0.202 | - |
| 0.5693 | 26900 | 0.2075 | - |
| 0.5714 | 27000 | 0.2021 | - |
| 0.5735 | 27100 | 0.1799 | - |
| 0.5756 | 27200 | 0.2084 | - |
| 0.5777 | 27300 | 0.2114 | - |
| 0.5798 | 27400 | 0.1851 | - |
| 0.5820 | 27500 | 0.22 | - |
| 0.5841 | 27600 | 0.181 | - |
| 0.5862 | 27700 | 0.2276 | - |
| 0.5883 | 27800 | 0.1944 | - |
| 0.5904 | 27900 | 0.1907 | - |
| 0.5925 | 28000 | 0.2176 | - |
| 0.5947 | 28100 | 0.2243 | - |
| 0.5968 | 28200 | 0.2191 | - |
| 0.5989 | 28300 | 0.2215 | - |
| 0.6010 | 28400 | 0.1769 | - |
| 0.6031 | 28500 | 0.1971 | - |
| 0.6052 | 28600 | 0.179 | - |
| 0.6074 | 28700 | 0.2308 | - |
| 0.6095 | 28800 | 0.2453 | - |
| 0.6116 | 28900 | 0.2293 | - |
| 0.6137 | 29000 | 0.2191 | - |
| 0.6158 | 29100 | 0.1988 | - |
| 0.6179 | 29200 | 0.1878 | - |
| 0.6201 | 29300 | 0.2215 | - |
| 0.6222 | 29400 | 0.2188 | - |
| 0.6243 | 29500 | 0.1821 | - |
| 0.6264 | 29600 | 0.1856 | - |
| 0.6285 | 29700 | 0.1907 | - |
| 0.6306 | 29800 | 0.1999 | - |
| 0.6328 | 29900 | 0.1803 | - |
| 0.6349 | 30000 | 0.201 | 0.1948 |
| 0.6370 | 30100 | 0.179 | - |
| 0.6391 | 30200 | 0.2073 | - |
| 0.6412 | 30300 | 0.2676 | - |
| 0.6433 | 30400 | 0.1824 | - |
| 0.6454 | 30500 | 0.1995 | - |
| 0.6476 | 30600 | 0.2097 | - |
| 0.6497 | 30700 | 0.2421 | - |
| 0.6518 | 30800 | 0.1745 | - |
| 0.6539 | 30900 | 0.2682 | - |
| 0.6560 | 31000 | 0.1892 | - |
| 0.6581 | 31100 | 0.2054 | - |
| 0.6603 | 31200 | 0.23 | - |
| 0.6624 | 31300 | 0.1711 | - |
| 0.6645 | 31400 | 0.2163 | - |
| 0.6666 | 31500 | 0.196 | - |
| 0.6687 | 31600 | 0.1746 | - |
| 0.6708 | 31700 | 0.2402 | - |
| 0.6730 | 31800 | 0.2096 | - |
| 0.6751 | 31900 | 0.1934 | - |
| 0.6772 | 32000 | 0.2021 | - |
| 0.6793 | 32100 | 0.1942 | - |
| 0.6814 | 32200 | 0.2076 | - |
| 0.6835 | 32300 | 0.1662 | - |
| 0.6857 | 32400 | 0.1777 | - |
| 0.6878 | 32500 | 0.1899 | - |
| 0.6899 | 32600 | 0.2253 | - |
| 0.6920 | 32700 | 0.221 | - |
| 0.6941 | 32800 | 0.1797 | - |
| 0.6962 | 32900 | 0.1884 | - |
| 0.6984 | 33000 | 0.2185 | - |
| 0.7005 | 33100 | 0.193 | - |
| 0.7026 | 33200 | 0.1975 | - |
| 0.7047 | 33300 | 0.1774 | - |
| 0.7068 | 33400 | 0.1709 | - |
| 0.7089 | 33500 | 0.1753 | - |
| 0.7111 | 33600 | 0.1834 | - |
| 0.7132 | 33700 | 0.1853 | - |
| 0.7153 | 33800 | 0.2155 | - |
| 0.7174 | 33900 | 0.1837 | - |
| 0.7195 | 34000 | 0.1655 | - |
| 0.7216 | 34100 | 0.212 | - |
| 0.7237 | 34200 | 0.2203 | - |
| 0.7259 | 34300 | 0.2267 | - |
| 0.7280 | 34400 | 0.208 | - |
| 0.7301 | 34500 | 0.1545 | - |
| 0.7322 | 34600 | 0.2003 | - |
| 0.7343 | 34700 | 0.2058 | - |
| 0.7364 | 34800 | 0.1837 | - |
| 0.7386 | 34900 | 0.2199 | - |
| 0.7407 | 35000 | 0.1931 | 0.1848 |
| 0.7428 | 35100 | 0.2456 | - |
| 0.7449 | 35200 | 0.1996 | - |
| 0.7470 | 35300 | 0.2145 | - |
| 0.7491 | 35400 | 0.1915 | - |
| 0.7513 | 35500 | 0.1734 | - |
| 0.7534 | 35600 | 0.19 | - |
| 0.7555 | 35700 | 0.182 | - |
| 0.7576 | 35800 | 0.1808 | - |
| 0.7597 | 35900 | 0.1625 | - |
| 0.7618 | 36000 | 0.1813 | - |
| 0.7640 | 36100 | 0.1412 | - |
| 0.7661 | 36200 | 0.2279 | - |
| 0.7682 | 36300 | 0.2444 | - |
| 0.7703 | 36400 | 0.1882 | - |
| 0.7724 | 36500 | 0.1731 | - |
| 0.7745 | 36600 | 0.1794 | - |
| 0.7767 | 36700 | 0.2577 | - |
| 0.7788 | 36800 | 0.169 | - |
| 0.7809 | 36900 | 0.1725 | - |
| 0.7830 | 37000 | 0.1788 | - |
| 0.7851 | 37100 | 0.1783 | - |
| 0.7872 | 37200 | 0.1764 | - |
| 0.7894 | 37300 | 0.1616 | - |
| 0.7915 | 37400 | 0.21 | - |
| 0.7936 | 37500 | 0.2091 | - |
| 0.7957 | 37600 | 0.1107 | - |
| 0.7978 | 37700 | 0.1773 | - |
| 0.7999 | 37800 | 0.1801 | - |
| 0.8020 | 37900 | 0.1621 | - |
| 0.8042 | 38000 | 0.189 | - |
| 0.8063 | 38100 | 0.182 | - |
| 0.8084 | 38200 | 0.1912 | - |
| 0.8105 | 38300 | 0.1731 | - |
| 0.8126 | 38400 | 0.1646 | - |
| 0.8147 | 38500 | 0.2037 | - |
| 0.8169 | 38600 | 0.1418 | - |
| 0.8190 | 38700 | 0.1485 | - |
| 0.8211 | 38800 | 0.2221 | - |
| 0.8232 | 38900 | 0.1886 | - |
| 0.8253 | 39000 | 0.2082 | - |
| 0.8274 | 39100 | 0.1742 | - |
| 0.8296 | 39200 | 0.1589 | - |
| 0.8317 | 39300 | 0.1959 | - |
| 0.8338 | 39400 | 0.1517 | - |
| 0.8359 | 39500 | 0.2049 | - |
| 0.8380 | 39600 | 0.2187 | - |
| 0.8401 | 39700 | 0.1801 | - |
| 0.8423 | 39800 | 0.1735 | - |
| 0.8444 | 39900 | 0.1881 | - |
| 0.8465 | 40000 | 0.1778 | 0.1787 |
| 0.8486 | 40100 | 0.1898 | - |
| 0.8507 | 40200 | 0.2021 | - |
| 0.8528 | 40300 | 0.1972 | - |
| 0.8550 | 40400 | 0.156 | - |
| 0.8571 | 40500 | 0.1791 | - |
| 0.8592 | 40600 | 0.188 | - |
| 0.8613 | 40700 | 0.2177 | - |
| 0.8634 | 40800 | 0.1287 | - |
| 0.8655 | 40900 | 0.1797 | - |
| 0.8677 | 41000 | 0.1533 | - |
| 0.8698 | 41100 | 0.1668 | - |
| 0.8719 | 41200 | 0.2047 | - |
| 0.8740 | 41300 | 0.1619 | - |
| 0.8761 | 41400 | 0.165 | - |
| 0.8782 | 41500 | 0.1781 | - |
| 0.8803 | 41600 | 0.2221 | - |
| 0.8825 | 41700 | 0.2031 | - |
| 0.8846 | 41800 | 0.1732 | - |
| 0.8867 | 41900 | 0.1599 | - |
| 0.8888 | 42000 | 0.1865 | - |
| 0.8909 | 42100 | 0.1367 | - |
| 0.8930 | 42200 | 0.1469 | - |
| 0.8952 | 42300 | 0.1777 | - |
| 0.8973 | 42400 | 0.1833 | - |
| 0.8994 | 42500 | 0.2102 | - |
| 0.9015 | 42600 | 0.164 | - |
| 0.9036 | 42700 | 0.1752 | - |
| 0.9057 | 42800 | 0.2186 | - |
| 0.9079 | 42900 | 0.1824 | - |
| 0.9100 | 43000 | 0.1796 | - |
| 0.9121 | 43100 | 0.1626 | - |
| 0.9142 | 43200 | 0.1623 | - |
| 0.9163 | 43300 | 0.2036 | - |
| 0.9184 | 43400 | 0.1365 | - |
| 0.9206 | 43500 | 0.1792 | - |
| 0.9227 | 43600 | 0.1583 | - |
| 0.9248 | 43700 | 0.1943 | - |
| 0.9269 | 43800 | 0.1931 | - |
| 0.9290 | 43900 | 0.1777 | - |
| 0.9311 | 44000 | 0.1633 | - |
| 0.9333 | 44100 | 0.1841 | - |
| 0.9354 | 44200 | 0.1674 | - |
| 0.9375 | 44300 | 0.1958 | - |
| 0.9396 | 44400 | 0.1831 | - |
| 0.9417 | 44500 | 0.1899 | - |
| 0.9438 | 44600 | 0.177 | - |
| 0.9460 | 44700 | 0.1881 | - |
| 0.9481 | 44800 | 0.1643 | - |
| 0.9502 | 44900 | 0.1462 | - |
| **0.9523** | **45000** | **0.2118** | **0.1719** |
| 0.9544 | 45100 | 0.1655 | - |
| 0.9565 | 45200 | 0.1567 | - |
| 0.9586 | 45300 | 0.1429 | - |
| 0.9608 | 45400 | 0.1718 | - |
| 0.9629 | 45500 | 0.1549 | - |
| 0.9650 | 45600 | 0.1556 | - |
| 0.9671 | 45700 | 0.1323 | - |
| 0.9692 | 45800 | 0.1988 | - |
| 0.9713 | 45900 | 0.15 | - |
| 0.9735 | 46000 | 0.1546 | - |
| 0.9756 | 46100 | 0.1472 | - |
| 0.9777 | 46200 | 0.196 | - |
| 0.9798 | 46300 | 0.1913 | - |
| 0.9819 | 46400 | 0.2261 | - |
| 0.9840 | 46500 | 0.1842 | - |
| 0.9862 | 46600 | 0.172 | - |
| 0.9883 | 46700 | 0.1925 | - |
| 0.9904 | 46800 | 0.1928 | - |
| 0.9925 | 46900 | 0.1698 | - |
| 0.9946 | 47000 | 0.1778 | - |
| 0.9967 | 47100 | 0.1497 | - |
| 0.9989 | 47200 | 0.1506 | - |
* The bold row denotes the saved checkpoint.
</details>
### Framework Versions
- Python: 3.12.4
- Sentence Transformers: 3.1.0.dev0
- Transformers: 4.42.4
- PyTorch: 2.3.1+cpu
- Accelerate: 0.32.1
- Datasets: 2.20.0
- 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",
}
```
#### 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": "nomic-ai/nomic-embed-text-v1.5", "datasets": [], "language": [], "library_name": "sentence-transformers", "pipeline_tag": "sentence-similarity", "tags": ["sentence-transformers", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:756057", "loss:MultipleNegativesRankingLoss"], "widget": [{"source_sentence": "府君奈何以蓋世之才欲立忠於垂亡之國", "sentences": ["將遠方進貢來的奇獸飛禽以及白山雞等物縱還山林比起雍畤的祭祀禮數頗有增加", "您為什麼以蓋絕當世的奇才卻打算向這個面臨滅亡的國家盡效忠心呢", "大統年間他出任岐州刺史在任不久就因為能力強而聞名"]}, {"source_sentence": "將率既至授單于印紱詔令上故印紱", "sentences": ["已經到達的五威將到達後授給單于新印信宣讀詔書要求交回漢朝舊印信", "於是拜陶隗為西南面招討使", "司馬錯建議秦惠王攻打蜀國張儀說 還不如進攻韓國"]}, {"source_sentence": "行醮禮皇太子詣醴席樂作", "sentences": ["閏七月十七日上宣宗廢除皇后胡氏尊諡", "等到看見西羌鼠竊狗盜父不父子不子君臣沒有分別四夷之人西羌最為低下", "行醮禮皇太子來到酒醴席奏樂"]}, {"source_sentence": "領軍臧盾太府卿沈僧果等並被時遇孝綽尤輕之", "sentences": ["過了幾天太宰官又來要國書並且說 我國自太宰府以東上國使臣沒有到過今大朝派使臣來若不見國書何以相信", "所以丹陽葛洪解釋說渾天儀注說 天體像雞蛋地就像是雞蛋中的蛋黃獨處於天體之內天是大的而地是小的", "領軍臧盾太府卿沈僧果等都是因趕上時機而得到官職的孝綽尤其輕蔑他們每次在朝中集合會面雖然一起做官但從不與他們說話"]}, {"source_sentence": "九月辛未太祖曾孫舒國公從式進封安定郡王", "sentences": ["九月初二太祖曾孫舒國公從式進封安定郡王", "楊難當在漢中大肆燒殺搶劫然後率眾離開了漢中向西返回仇池留下趙溫據守梁州又派他的魏興太守薛健屯駐黃金山", "正統元年普定蠻夷阿遲等反叛非法稱王四處出擊攻打掠奪"]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,888 |
Oriserve/Whisper-Hindi2Hinglish-Prime
|
Oriserve
|
automatic-speech-recognition
|
[
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"audio",
"whisper-event",
"pytorch",
"hinglish",
"en",
"hi",
"base_model:openai/whisper-large-v3",
"base_model:finetune:openai/whisper-large-v3",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | 2025-01-07T10:44:58Z |
2025-02-05T06:19:45+00:00
| 1,046 | 6 |
---
base_model:
- openai/whisper-large-v3
language:
- en
- hi
library_name: transformers
license: apache-2.0
metrics:
- wer
pipeline_tag: automatic-speech-recognition
tags:
- audio
- automatic-speech-recognition
- whisper-event
- pytorch
- hinglish
inference: true
widget:
- src: audios/c0637211-7384-4abc-af69-5aacf7549824_1_2629072_2656224.wav
output:
text: Mehnat to poora karte hain.
- src: audios/c0faba11-27ba-4837-a2eb-ccd67be07f40_1_3185088_3227568.wav
output:
text: Haan vahi ek aapko bataaya na.
- src: audios/663eb653-d6b5-4fda-b5f2-9ef98adc0a61_0_1098400_1118688.wav
output:
text: Aap pandrah log hain.
- src: audios/f5e0178c-354c-40c9-b3a7-687c86240a77_1_2613728_2630112.wav
output:
text: Kitne saal ki?
- src: audios/f5e0178c-354c-40c9-b3a7-687c86240a77_1_1152496_1175488.wav
output:
text: Lander cycle chaahie.
- src: audios/c0637211-7384-4abc-af69-5aacf7549824_1_2417088_2444224.wav
output:
text: Haan haan, dekhe hain.
- src: audios/common_voice_hi_23796065.mp3
example_title: Speech Example 1
- src: audios/common_voice_hi_41666099.mp3
example_title: Speech Example 2
- src: audios/common_voice_hi_41429198.mp3
example_title: Speech Example 3
- src: audios/common_voice_hi_41429259.mp3
example_title: Speech Example 4
- src: audios/common_voice_hi_40904697.mp3
example_title: Speech Example 5
model-index:
- name: Whisper-Hindi2Hinglish-Prime
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: google/fleurs
type: google/fleurs
config: hi_in
split: test
metrics:
- type: wer
value: 28.6806
name: WER
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: mozilla-foundation/common_voice_20_0
type: mozilla-foundation/common_voice_20_0
config: hi
split: test
metrics:
- type: wer
value: 32.4314
name: WER
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Indic-Voices
type: Indic-Voices
config: hi
split: test
metrics:
- type: wer
value: 60.8224
name: WER
---
## Whisper-Hindi2Hinglish-Prime:
- GITHUB LINK: [github link](https://github.com/OriserveAI/Whisper-Hindi2Hinglish)
- SPEECH-TO-TEXT ARENA: [Speech-To-Text Arena](https://huggingface.co/spaces/Oriserve/ASR_arena)
### Table of Contents:
- [Key Features](#key-features)
- [Training](#training)
- [Data](#data)
- [Finetuning](#finetuning)
- [Usage](#usage)
- [Performance Overview](#performance-overview)
- [Qualitative Performance Overview](#qualitative-performance-overview)
- [Quantitative Performance Overview](#quantitative-performance-overview)
- [Miscellaneous](#miscellaneous)
### Key Features:
1. **Hinglish as a language**: Added ability to transcribe audio into spoken Hinglish language reducing chances of grammatical errors
2. **Whisper Architecture**: Based on the whisper architecture making it easy to use with the transformers package
3. **Better Noise handling**: The model is resistant to noise and thus does not return transcriptions for audios with just noise
4. **Hallucination Mitigation**: Minimizes transcription hallucinations to enhance accuracy.
5. **Performance Increase**: ~39% average performance increase versus pretrained model across benchmarking datasets
### Training:
#### Data:
- **Duration**: A total of ~550 Hrs of noisy Indian-accented Hindi data was used to finetune the model.
- **Collection**: Due to a lack of ASR-ready hinglish datasets available, a specially curated proprietary dataset was used.
- **Labelling**: This data was then labeled using a SOTA model and the transcriptions were improved by human intervention.
- **Quality**: Emphasis was placed on collecting noisy data for the task as the intended use case of the model is in Indian environments where background noise is abundant.
- **Processing**: It was ensured that the audios are all chunked into chunks of length <30s, and there are at max 2 speakers in a clip. No further processing steps were done so as to not change the quality of the source data.
#### Finetuning:
- **Novel Trainer Architecture**: A custom trainer was written to ensure efficient supervised finetuning, with custom callbacks to enable higher observability during the training process.
- **Custom Dynamic Layer Freezing**: Most active layers were identified in the model by running inference on a subset of the training data using the pre-trained models. These layers were then kept unfrozen during the training process while all the other layers were kept frozen. This enabled faster convergence and efficient finetuning
- **Deepspeed Integration**: Deepspeed was also utilized to speed up, and optimize the training process.
### Performance Overview
#### Qualitative Performance Overview
| Audio | Whisper Large V3 | Whisper-Hindi2Hinglish-Prime |
|-------|------------------|------------------------------|
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/c0637211-7384-4abc-af69-5aacf7549824_1_2629072_2656224.wav" type="audio/wav"></audio> | maynata pura, canta maynata | Mehnat to poora karte hain. |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/c0faba11-27ba-4837-a2eb-ccd67be07f40_1_3185088_3227568.wav" type="audio/wav"></audio> | Where did they come from? | Haan vahi ek aapko bataaya na. |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/663eb653-d6b5-4fda-b5f2-9ef98adc0a61_0_1098400_1118688.wav" type="audio/wav"></audio> | A Pantral Logan. | Aap pandrah log hain. |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/f5e0178c-354c-40c9-b3a7-687c86240a77_1_2613728_2630112.wav" type="audio/wav"></audio> | Thank you, Sanchez. | Kitne saal ki? |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/f5e0178c-354c-40c9-b3a7-687c86240a77_1_1152496_1175488.wav" type="audio/wav"></audio> | Rangers, I can tell you. | Lander cycle chaahie. |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/c0637211-7384-4abc-af69-5aacf7549824_1_2417088_2444224.wav" type="audio/wav"></audio> | Uh-huh. They can't. | Haan haan, dekhe hain. |
#### Quantitative Performance Overview
***Note***:
- *The below WER scores are for Hinglish text generated by our model and the original whisper model*
- *To check our model's real-world performance against other SOTA models please head to our [Speech-To-Text Arena](https://huggingface.co/spaces/Oriserve/ASR_arena) arena space.*
| Dataset | Whisper Large V3 | Whisper-Hindi2Hinglish-Prime |
|-------|------------------------|-------------------------|
| [Common-Voice](https://commonvoice.mozilla.org/en) | 61.9432| 32.4314 |
| [FLEURS](https://huggingface.co/datasets/google/fleurs) | 50.8425 | 28.6806 |
| [Indic-Voices](https://ai4bharat.iitm.ac.in/datasets/indicvoices)| 82.5621 | 60.8224 |
### Usage:
#### Using Transformers
- To run the model, first install the Transformers library
```pip install -U transformers```
- The model can be used with the [`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
class to transcribe audios of arbitrary length:
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
# Set device (GPU if available, otherwise CPU) and precision
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
# Specify the pre-trained model ID
model_id = "Oriserve/Whisper-Hindi2Hinglish-Prime"
# Load the speech-to-text model with specified configurations
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id,
torch_dtype=torch_dtype, # Use appropriate precision (float16 for GPU, float32 for CPU)
low_cpu_mem_usage=True, # Optimize memory usage during loading
use_safetensors=True # Use safetensors format for better security
)
model.to(device) # Move model to specified device
# Load the processor for audio preprocessing and tokenization
processor = AutoProcessor.from_pretrained(model_id)
# Create speech recognition pipeline
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
torch_dtype=torch_dtype,
device=device,
generate_kwargs={
"task": "transcribe", # Set task to transcription
"language": "en" # Specify English language
}
)
# Process audio file and print transcription
sample = "sample.wav" # Input audio file path
result = pipe(sample) # Run inference
print(result["text"]) # Print transcribed text
```
#### Using Flash Attention 2
Flash-Attention 2 can be used to make the transcription fast. If your GPU supports Flash-Attention you can use it by, first installing Flash Attention:
```pip install flash-attn --no-build-isolation```
- Once installed you can then load the model using the below code:
```python
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, attn_implementation="flash_attention_2")
```
#### Using the OpenAI Whisper module
- First, install the openai-whisper library
```pip install -U openai-whisper tqdm```
- Convert the huggingface checkpoint to a pytorch model
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq
import re
from tqdm import tqdm
from collections import OrderedDict
import json
# Load parameter name mapping from HF to OpenAI format
with open('convert_hf2openai.json', 'r') as f:
reverse_translation = json.load(f)
reverse_translation = OrderedDict(reverse_translation)
def save_model(model, save_path):
def reverse_translate(current_param):
# Convert parameter names using regex patterns
for pattern, repl in reverse_translation.items():
if re.match(pattern, current_param):
return re.sub(pattern, repl, current_param)
# Extract model dimensions from config
config = model.config
model_dims = {
"n_mels": config.num_mel_bins, # Number of mel spectrogram bins
"n_vocab": config.vocab_size, # Vocabulary size
"n_audio_ctx": config.max_source_positions, # Max audio context length
"n_audio_state": config.d_model, # Audio encoder state dimension
"n_audio_head": config.encoder_attention_heads, # Audio encoder attention heads
"n_audio_layer": config.encoder_layers, # Number of audio encoder layers
"n_text_ctx": config.max_target_positions, # Max text context length
"n_text_state": config.d_model, # Text decoder state dimension
"n_text_head": config.decoder_attention_heads, # Text decoder attention heads
"n_text_layer": config.decoder_layers, # Number of text decoder layers
}
# Convert model state dict to Whisper format
original_model_state_dict = model.state_dict()
new_state_dict = {}
for key, value in tqdm(original_model_state_dict.items()):
key = key.replace("model.", "") # Remove 'model.' prefix
new_key = reverse_translate(key) # Convert parameter names
if new_key is not None:
new_state_dict[new_key] = value
# Create final model dictionary
pytorch_model = {"dims": model_dims, "model_state_dict": new_state_dict}
# Save converted model
torch.save(pytorch_model, save_path)
# Load Hugging Face model
model_id = "Oriserve/Whisper-Hindi2Hinglish-Prime"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id,
low_cpu_mem_usage=True, # Optimize memory usage
use_safetensors=True # Use safetensors format
)
# Convert and save model
model_save_path = "Whisper-Hindi2Hinglish-Prime.pt"
save_model(model,model_save_path)
```
- Transcribe
```python
import whisper
# Load converted model with Whisper and transcribe
model = whisper.load_model("Whisper-Hindi2Hinglish-Prime.pt")
result = model.transcribe("sample.wav")
print(result["text"])
```
### Miscellaneous
This model is from a family of transformers-based ASR models trained by Oriserve. To compare this model against other models from the same family or other SOTA models please head to our [Speech-To-Text Arena](https://huggingface.co/spaces/Oriserve/ASR_arena). To learn more about our other models, and other queries regarding AI voice agents you can reach out to us at our email [[email protected]]([email protected])
| null |
Non_BioNLP
|
## Whisper-Hindi2Hinglish-Prime:
- GITHUB LINK: [github link](https://github.com/OriserveAI/Whisper-Hindi2Hinglish)
- SPEECH-TO-TEXT ARENA: [Speech-To-Text Arena](https://huggingface.co/spaces/Oriserve/ASR_arena)
### Table of Contents:
- [Key Features](#key-features)
- [Training](#training)
- [Data](#data)
- [Finetuning](#finetuning)
- [Usage](#usage)
- [Performance Overview](#performance-overview)
- [Qualitative Performance Overview](#qualitative-performance-overview)
- [Quantitative Performance Overview](#quantitative-performance-overview)
- [Miscellaneous](#miscellaneous)
### Key Features:
1. **Hinglish as a language**: Added ability to transcribe audio into spoken Hinglish language reducing chances of grammatical errors
2. **Whisper Architecture**: Based on the whisper architecture making it easy to use with the transformers package
3. **Better Noise handling**: The model is resistant to noise and thus does not return transcriptions for audios with just noise
4. **Hallucination Mitigation**: Minimizes transcription hallucinations to enhance accuracy.
5. **Performance Increase**: ~39% average performance increase versus pretrained model across benchmarking datasets
### Training:
#### Data:
- **Duration**: A total of ~550 Hrs of noisy Indian-accented Hindi data was used to finetune the model.
- **Collection**: Due to a lack of ASR-ready hinglish datasets available, a specially curated proprietary dataset was used.
- **Labelling**: This data was then labeled using a SOTA model and the transcriptions were improved by human intervention.
- **Quality**: Emphasis was placed on collecting noisy data for the task as the intended use case of the model is in Indian environments where background noise is abundant.
- **Processing**: It was ensured that the audios are all chunked into chunks of length <30s, and there are at max 2 speakers in a clip. No further processing steps were done so as to not change the quality of the source data.
#### Finetuning:
- **Novel Trainer Architecture**: A custom trainer was written to ensure efficient supervised finetuning, with custom callbacks to enable higher observability during the training process.
- **Custom Dynamic Layer Freezing**: Most active layers were identified in the model by running inference on a subset of the training data using the pre-trained models. These layers were then kept unfrozen during the training process while all the other layers were kept frozen. This enabled faster convergence and efficient finetuning
- **Deepspeed Integration**: Deepspeed was also utilized to speed up, and optimize the training process.
### Performance Overview
#### Qualitative Performance Overview
| Audio | Whisper Large V3 | Whisper-Hindi2Hinglish-Prime |
|-------|------------------|------------------------------|
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/c0637211-7384-4abc-af69-5aacf7549824_1_2629072_2656224.wav" type="audio/wav"></audio> | maynata pura, canta maynata | Mehnat to poora karte hain. |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/c0faba11-27ba-4837-a2eb-ccd67be07f40_1_3185088_3227568.wav" type="audio/wav"></audio> | Where did they come from? | Haan vahi ek aapko bataaya na. |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/663eb653-d6b5-4fda-b5f2-9ef98adc0a61_0_1098400_1118688.wav" type="audio/wav"></audio> | A Pantral Logan. | Aap pandrah log hain. |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/f5e0178c-354c-40c9-b3a7-687c86240a77_1_2613728_2630112.wav" type="audio/wav"></audio> | Thank you, Sanchez. | Kitne saal ki? |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/f5e0178c-354c-40c9-b3a7-687c86240a77_1_1152496_1175488.wav" type="audio/wav"></audio> | Rangers, I can tell you. | Lander cycle chaahie. |
| <audio controls><source src="https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime/resolve/main/audios/c0637211-7384-4abc-af69-5aacf7549824_1_2417088_2444224.wav" type="audio/wav"></audio> | Uh-huh. They can't. | Haan haan, dekhe hain. |
#### Quantitative Performance Overview
***Note***:
- *The below WER scores are for Hinglish text generated by our model and the original whisper model*
- *To check our model's real-world performance against other SOTA models please head to our [Speech-To-Text Arena](https://huggingface.co/spaces/Oriserve/ASR_arena) arena space.*
| Dataset | Whisper Large V3 | Whisper-Hindi2Hinglish-Prime |
|-------|------------------------|-------------------------|
| [Common-Voice](https://commonvoice.mozilla.org/en) | 61.9432| 32.4314 |
| [FLEURS](https://huggingface.co/datasets/google/fleurs) | 50.8425 | 28.6806 |
| [Indic-Voices](https://ai4bharat.iitm.ac.in/datasets/indicvoices)| 82.5621 | 60.8224 |
### Usage:
#### Using Transformers
- To run the model, first install the Transformers library
```pip install -U transformers```
- The model can be used with the [`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
class to transcribe audios of arbitrary length:
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
# Set device (GPU if available, otherwise CPU) and precision
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
# Specify the pre-trained model ID
model_id = "Oriserve/Whisper-Hindi2Hinglish-Prime"
# Load the speech-to-text model with specified configurations
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id,
torch_dtype=torch_dtype, # Use appropriate precision (float16 for GPU, float32 for CPU)
low_cpu_mem_usage=True, # Optimize memory usage during loading
use_safetensors=True # Use safetensors format for better security
)
model.to(device) # Move model to specified device
# Load the processor for audio preprocessing and tokenization
processor = AutoProcessor.from_pretrained(model_id)
# Create speech recognition pipeline
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
torch_dtype=torch_dtype,
device=device,
generate_kwargs={
"task": "transcribe", # Set task to transcription
"language": "en" # Specify English language
}
)
# Process audio file and print transcription
sample = "sample.wav" # Input audio file path
result = pipe(sample) # Run inference
print(result["text"]) # Print transcribed text
```
#### Using Flash Attention 2
Flash-Attention 2 can be used to make the transcription fast. If your GPU supports Flash-Attention you can use it by, first installing Flash Attention:
```pip install flash-attn --no-build-isolation```
- Once installed you can then load the model using the below code:
```python
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, attn_implementation="flash_attention_2")
```
#### Using the OpenAI Whisper module
- First, install the openai-whisper library
```pip install -U openai-whisper tqdm```
- Convert the huggingface checkpoint to a pytorch model
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq
import re
from tqdm import tqdm
from collections import OrderedDict
import json
# Load parameter name mapping from HF to OpenAI format
with open('convert_hf2openai.json', 'r') as f:
reverse_translation = json.load(f)
reverse_translation = OrderedDict(reverse_translation)
def save_model(model, save_path):
def reverse_translate(current_param):
# Convert parameter names using regex patterns
for pattern, repl in reverse_translation.items():
if re.match(pattern, current_param):
return re.sub(pattern, repl, current_param)
# Extract model dimensions from config
config = model.config
model_dims = {
"n_mels": config.num_mel_bins, # Number of mel spectrogram bins
"n_vocab": config.vocab_size, # Vocabulary size
"n_audio_ctx": config.max_source_positions, # Max audio context length
"n_audio_state": config.d_model, # Audio encoder state dimension
"n_audio_head": config.encoder_attention_heads, # Audio encoder attention heads
"n_audio_layer": config.encoder_layers, # Number of audio encoder layers
"n_text_ctx": config.max_target_positions, # Max text context length
"n_text_state": config.d_model, # Text decoder state dimension
"n_text_head": config.decoder_attention_heads, # Text decoder attention heads
"n_text_layer": config.decoder_layers, # Number of text decoder layers
}
# Convert model state dict to Whisper format
original_model_state_dict = model.state_dict()
new_state_dict = {}
for key, value in tqdm(original_model_state_dict.items()):
key = key.replace("model.", "") # Remove 'model.' prefix
new_key = reverse_translate(key) # Convert parameter names
if new_key is not None:
new_state_dict[new_key] = value
# Create final model dictionary
pytorch_model = {"dims": model_dims, "model_state_dict": new_state_dict}
# Save converted model
torch.save(pytorch_model, save_path)
# Load Hugging Face model
model_id = "Oriserve/Whisper-Hindi2Hinglish-Prime"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id,
low_cpu_mem_usage=True, # Optimize memory usage
use_safetensors=True # Use safetensors format
)
# Convert and save model
model_save_path = "Whisper-Hindi2Hinglish-Prime.pt"
save_model(model,model_save_path)
```
- Transcribe
```python
import whisper
# Load converted model with Whisper and transcribe
model = whisper.load_model("Whisper-Hindi2Hinglish-Prime.pt")
result = model.transcribe("sample.wav")
print(result["text"])
```
### Miscellaneous
This model is from a family of transformers-based ASR models trained by Oriserve. To compare this model against other models from the same family or other SOTA models please head to our [Speech-To-Text Arena](https://huggingface.co/spaces/Oriserve/ASR_arena). To learn more about our other models, and other queries regarding AI voice agents you can reach out to us at our email [[email protected]]([email protected])
|
{"base_model": ["openai/whisper-large-v3"], "language": ["en", "hi"], "library_name": "transformers", "license": "apache-2.0", "metrics": ["wer"], "pipeline_tag": "automatic-speech-recognition", "tags": ["audio", "automatic-speech-recognition", "whisper-event", "pytorch", "hinglish"], "inference": true, "widget": [{"src": "audios/c0637211-7384-4abc-af69-5aacf7549824_1_2629072_2656224.wav", "output": {"text": "Mehnat to poora karte hain."}}, {"src": "audios/c0faba11-27ba-4837-a2eb-ccd67be07f40_1_3185088_3227568.wav", "output": {"text": "Haan vahi ek aapko bataaya na."}}, {"src": "audios/663eb653-d6b5-4fda-b5f2-9ef98adc0a61_0_1098400_1118688.wav", "output": {"text": "Aap pandrah log hain."}}, {"src": "audios/f5e0178c-354c-40c9-b3a7-687c86240a77_1_2613728_2630112.wav", "output": {"text": "Kitne saal ki?"}}, {"src": "audios/f5e0178c-354c-40c9-b3a7-687c86240a77_1_1152496_1175488.wav", "output": {"text": "Lander cycle chaahie."}}, {"src": "audios/c0637211-7384-4abc-af69-5aacf7549824_1_2417088_2444224.wav", "output": {"text": "Haan haan, dekhe hain."}}, {"src": "audios/common_voice_hi_23796065.mp3", "example_title": "Speech Example 1"}, {"src": "audios/common_voice_hi_41666099.mp3", "example_title": "Speech Example 2"}, {"src": "audios/common_voice_hi_41429198.mp3", "example_title": "Speech Example 3"}, {"src": "audios/common_voice_hi_41429259.mp3", "example_title": "Speech Example 4"}, {"src": "audios/common_voice_hi_40904697.mp3", "example_title": "Speech Example 5"}], "model-index": [{"name": "Whisper-Hindi2Hinglish-Prime", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "google/fleurs", "type": "google/fleurs", "config": "hi_in", "split": "test"}, "metrics": [{"type": "wer", "value": 28.6806, "name": "WER"}]}, {"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "mozilla-foundation/common_voice_20_0", "type": "mozilla-foundation/common_voice_20_0", "config": "hi", "split": "test"}, "metrics": [{"type": "wer", "value": 32.4314, "name": "WER"}]}, {"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "Indic-Voices", "type": "Indic-Voices", "config": "hi", "split": "test"}, "metrics": [{"type": "wer", "value": 60.8224, "name": "WER"}]}]}]}
|
task
|
[
"TRANSLATION"
] | 43,889 |
Sandiago21/llama-7b-hf-prompt-answering
|
Sandiago21
|
text-generation
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"decapoda-research-7b-hf",
"prompt answering",
"peft",
"en",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"region:us"
] | 2023-06-02T20:35:24Z |
2023-06-12T09:29:54+00:00
| 49 | 3 |
---
language:
- en
library_name: transformers
license: other
pipeline_tag: text-generation
tags:
- llama
- decapoda-research-7b-hf
- prompt answering
- peft
---
## Model Card for Model ID
This repository contains a LLaMA-7B further fine-tuned model on conversations and question answering prompts.
⚠️ **I used [LLaMA-7b-hf](https://huggingface.co/decapoda-research/llama-7b-hf) as a base model, so this model is for Research purpose only (See the [license](https://huggingface.co/decapoda-research/llama-7b-hf/blob/main/LICENSE))**
## Model Details
Anyone can use (ask prompts) and play with the model using the pre-existing Jupyter Notebook in the **noteboooks** folder. The Jupyter Notebook contains example code to load the model and ask prompts to it as well as example prompts to get you started.
### Model Description
The decapoda-research/llama-7b-hf model was finetuned on conversations and question answering prompts.
**Developed by:** [More Information Needed]
**Shared by:** [More Information Needed]
**Model type:** Causal LM
**Language(s) (NLP):** English, multilingual
**License:** Research
**Finetuned from model:** decapoda-research/llama-7b-hf
## Model Sources [optional]
**Repository:** [More Information Needed]
**Paper:** [More Information Needed]
**Demo:** [More Information Needed]
## Uses
The model can be used for prompt answering
### Direct Use
The model can be used for prompt answering
### Downstream Use
Generating text and prompt answering
## Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
# Usage
## Creating prompt
The model was trained on the following kind of prompt:
```python
def generate_prompt(instruction: str, input_ctxt: str = None) -> str:
if input_ctxt:
return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Input:
{input_ctxt}
### Response:"""
else:
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response:"""
```
## How to Get Started with the Model
Use the code below to get started with the model.
1. You can git clone the repo, which contains also the artifacts for the base model for simplicity and completeness, and run the following code snippet to load the mode:
```python
import torch
from peft import PeftConfig, PeftModel
from transformers import GenerationConfig, LlamaTokenizer, LlamaForCausalLM
MODEL_NAME = "Sandiago21/llama-7b-hf-prompt-answering"
config = PeftConfig.from_pretrained(MODEL_NAME)
# Setting the path to look at your repo directory, assuming that you are at that directory when running this script
config.base_model_name_or_path = "decapoda-research/llama-7b-hf/"
model = LlamaForCausalLM.from_pretrained(
config.base_model_name_or_path,
load_in_8bit=True,
torch_dtype=torch.float16,
device_map="auto",
)
tokenizer = LlamaTokenizer.from_pretrained(MODEL_NAME)
model = PeftModel.from_pretrained(model, MODEL_NAME)
generation_config = GenerationConfig(
temperature=0.2,
top_p=0.75,
top_k=40,
num_beams=4,
max_new_tokens=32,
)
model.eval()
if torch.__version__ >= "2":
model = torch.compile(model)
```
### Example of Usage
```python
instruction = "What is the capital city of Greece and with which countries does Greece border?"
input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.
prompt = generate_prompt(instruction, input_ctxt)
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
input_ids = input_ids.to(model.device)
with torch.no_grad():
outputs = model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
)
response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
print(response)
>>> The capital city of Greece is Athens and it borders Turkey, Bulgaria, Macedonia, Albania, and the Aegean Sea.
```
2. You can directly call the model from HuggingFace using the following code snippet:
```python
import torch
from peft import PeftConfig, PeftModel
from transformers import GenerationConfig, LlamaTokenizer, LlamaForCausalLM
MODEL_NAME = "Sandiago21/llama-7b-hf-prompt-answering"
BASE_MODEL = "decapoda-research/llama-7b-hf"
config = PeftConfig.from_pretrained(MODEL_NAME)
model = LlamaForCausalLM.from_pretrained(
BASE_MODEL,
load_in_8bit=True,
torch_dtype=torch.float16,
device_map="auto",
)
tokenizer = LlamaTokenizer.from_pretrained(MODEL_NAME)
model = PeftModel.from_pretrained(model, MODEL_NAME)
generation_config = GenerationConfig(
temperature=0.2,
top_p=0.75,
top_k=40,
num_beams=4,
max_new_tokens=32,
)
model.eval()
if torch.__version__ >= "2":
model = torch.compile(model)
```
### Example of Usage
```python
instruction = "What is the capital city of Greece and with which countries does Greece border?"
input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.
prompt = generate_prompt(instruction, input_ctxt)
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
input_ids = input_ids.to(model.device)
with torch.no_grad():
outputs = model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
)
response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
print(response)
>>> The capital city of Greece is Athens and it borders Turkey, Bulgaria, Macedonia, Albania, and the Aegean Sea.
```
## Training Details
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.12.0
- Tokenizers 0.12.1
### Training Data
The decapoda-research/llama-7b-hf was finetuned on conversations and question answering data
### Training Procedure
The decapoda-research/llama-7b-hf model was further trained and finetuned on question answering and prompts data for 1 epoch (approximately 10 hours of training on a single GPU)
## Model Architecture and Objective
The model is based on decapoda-research/llama-7b-hf model and finetuned adapters on top of the main model on conversations and question answering data.
| null |
Non_BioNLP
|
## Model Card for Model ID
This repository contains a LLaMA-7B further fine-tuned model on conversations and question answering prompts.
⚠️ **I used [LLaMA-7b-hf](https://huggingface.co/decapoda-research/llama-7b-hf) as a base model, so this model is for Research purpose only (See the [license](https://huggingface.co/decapoda-research/llama-7b-hf/blob/main/LICENSE))**
## Model Details
Anyone can use (ask prompts) and play with the model using the pre-existing Jupyter Notebook in the **noteboooks** folder. The Jupyter Notebook contains example code to load the model and ask prompts to it as well as example prompts to get you started.
### Model Description
The decapoda-research/llama-7b-hf model was finetuned on conversations and question answering prompts.
**Developed by:** [More Information Needed]
**Shared by:** [More Information Needed]
**Model type:** Causal LM
**Language(s) (NLP):** English, multilingual
**License:** Research
**Finetuned from model:** decapoda-research/llama-7b-hf
## Model Sources [optional]
**Repository:** [More Information Needed]
**Paper:** [More Information Needed]
**Demo:** [More Information Needed]
## Uses
The model can be used for prompt answering
### Direct Use
The model can be used for prompt answering
### Downstream Use
Generating text and prompt answering
## Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
# Usage
## Creating prompt
The model was trained on the following kind of prompt:
```python
def generate_prompt(instruction: str, input_ctxt: str = None) -> str:
if input_ctxt:
return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Input:
{input_ctxt}
### Response:"""
else:
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response:"""
```
## How to Get Started with the Model
Use the code below to get started with the model.
1. You can git clone the repo, which contains also the artifacts for the base model for simplicity and completeness, and run the following code snippet to load the mode:
```python
import torch
from peft import PeftConfig, PeftModel
from transformers import GenerationConfig, LlamaTokenizer, LlamaForCausalLM
MODEL_NAME = "Sandiago21/llama-7b-hf-prompt-answering"
config = PeftConfig.from_pretrained(MODEL_NAME)
# Setting the path to look at your repo directory, assuming that you are at that directory when running this script
config.base_model_name_or_path = "decapoda-research/llama-7b-hf/"
model = LlamaForCausalLM.from_pretrained(
config.base_model_name_or_path,
load_in_8bit=True,
torch_dtype=torch.float16,
device_map="auto",
)
tokenizer = LlamaTokenizer.from_pretrained(MODEL_NAME)
model = PeftModel.from_pretrained(model, MODEL_NAME)
generation_config = GenerationConfig(
temperature=0.2,
top_p=0.75,
top_k=40,
num_beams=4,
max_new_tokens=32,
)
model.eval()
if torch.__version__ >= "2":
model = torch.compile(model)
```
### Example of Usage
```python
instruction = "What is the capital city of Greece and with which countries does Greece border?"
input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.
prompt = generate_prompt(instruction, input_ctxt)
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
input_ids = input_ids.to(model.device)
with torch.no_grad():
outputs = model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
)
response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
print(response)
>>> The capital city of Greece is Athens and it borders Turkey, Bulgaria, Macedonia, Albania, and the Aegean Sea.
```
2. You can directly call the model from HuggingFace using the following code snippet:
```python
import torch
from peft import PeftConfig, PeftModel
from transformers import GenerationConfig, LlamaTokenizer, LlamaForCausalLM
MODEL_NAME = "Sandiago21/llama-7b-hf-prompt-answering"
BASE_MODEL = "decapoda-research/llama-7b-hf"
config = PeftConfig.from_pretrained(MODEL_NAME)
model = LlamaForCausalLM.from_pretrained(
BASE_MODEL,
load_in_8bit=True,
torch_dtype=torch.float16,
device_map="auto",
)
tokenizer = LlamaTokenizer.from_pretrained(MODEL_NAME)
model = PeftModel.from_pretrained(model, MODEL_NAME)
generation_config = GenerationConfig(
temperature=0.2,
top_p=0.75,
top_k=40,
num_beams=4,
max_new_tokens=32,
)
model.eval()
if torch.__version__ >= "2":
model = torch.compile(model)
```
### Example of Usage
```python
instruction = "What is the capital city of Greece and with which countries does Greece border?"
input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.
prompt = generate_prompt(instruction, input_ctxt)
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
input_ids = input_ids.to(model.device)
with torch.no_grad():
outputs = model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
)
response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
print(response)
>>> The capital city of Greece is Athens and it borders Turkey, Bulgaria, Macedonia, Albania, and the Aegean Sea.
```
## Training Details
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.12.0
- Tokenizers 0.12.1
### Training Data
The decapoda-research/llama-7b-hf was finetuned on conversations and question answering data
### Training Procedure
The decapoda-research/llama-7b-hf model was further trained and finetuned on question answering and prompts data for 1 epoch (approximately 10 hours of training on a single GPU)
## Model Architecture and Objective
The model is based on decapoda-research/llama-7b-hf model and finetuned adapters on top of the main model on conversations and question answering data.
|
{"language": ["en"], "library_name": "transformers", "license": "other", "pipeline_tag": "text-generation", "tags": ["llama", "decapoda-research-7b-hf", "prompt answering", "peft"]}
|
task
|
[
"QUESTION_ANSWERING"
] | 43,890 |
Shebna/distilbert-base-uncased-finetuned-cola
|
Shebna
|
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"
] | 2022-10-12T12:10:49Z |
2022-10-13T05:25:14+00:00
| 9 | 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: 0.542244787638552
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: 0.8054
- Matthews Correlation: 0.5422
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5231 | 1.0 | 535 | 0.5317 | 0.4122 |
| 0.348 | 2.0 | 1070 | 0.5014 | 0.5166 |
| 0.2365 | 3.0 | 1605 | 0.5800 | 0.5305 |
| 0.1833 | 4.0 | 2140 | 0.7610 | 0.5288 |
| 0.1381 | 5.0 | 2675 | 0.8054 | 0.5422 |
### Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- 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. -->
# 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: 0.8054
- Matthews Correlation: 0.5422
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5231 | 1.0 | 535 | 0.5317 | 0.4122 |
| 0.348 | 2.0 | 1070 | 0.5014 | 0.5166 |
| 0.2365 | 3.0 | 1605 | 0.5800 | 0.5305 |
| 0.1833 | 4.0 | 2140 | 0.7610 | 0.5288 |
| 0.1381 | 5.0 | 2675 | 0.8054 | 0.5422 |
### Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.13.1
|
{"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": 0.542244787638552, "name": "Matthews Correlation"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,891 |
weslleylima/my-awesome-setfit-model
|
weslleylima
|
text-classification
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 2023-06-28T12:33:07Z |
2023-06-28T13:27:42+00:00
| 11 | 0 |
---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# weslleylima/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("weslleylima/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
|
# weslleylima/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("weslleylima/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"
] | 43,892 |
gaudi/opus-mt-fi-swc-ctranslate2
|
gaudi
|
translation
|
[
"transformers",
"marian",
"ctranslate2",
"translation",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 2024-07-22T15:54:40Z |
2024-10-19T03:59:40+00:00
| 6 | 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-fi-swc)
- 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-fi-swc).**
## 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-fi-swc --output_dir ./ctranslate2/opus-mt-fi-swc-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-fi-swc-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-fi-swc-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-fi-swc-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-fi-swc) 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-fi-swc)
- 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-fi-swc).**
## 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-fi-swc --output_dir ./ctranslate2/opus-mt-fi-swc-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-fi-swc-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-fi-swc-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-fi-swc-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-fi-swc) by Helsinki-NLP.
|
{"license": "apache-2.0", "tags": ["ctranslate2", "translation"]}
|
task
|
[
"TRANSLATION"
] | 43,893 |
gokulsrinivasagan/distilbert_lda_20_v1_sst2
|
gokulsrinivasagan
|
text-classification
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokulsrinivasagan/distilbert_lda_20_v1",
"base_model:finetune:gokulsrinivasagan/distilbert_lda_20_v1",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 2024-11-26T20:47:37Z |
2024-12-04T14:18:19+00:00
| 5 | 0 |
---
base_model: gokulsrinivasagan/distilbert_lda_20_v1
datasets:
- glue
language:
- en
library_name: transformers
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: distilbert_lda_20_v1_sst2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE SST2
type: glue
args: sst2
metrics:
- type: accuracy
value: 0.8451834862385321
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_lda_20_v1_sst2
This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_20_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_20_v1) on the GLUE SST2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3649
- Accuracy: 0.8452
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3686 | 1.0 | 264 | 0.3649 | 0.8452 |
| 0.2092 | 2.0 | 528 | 0.3841 | 0.8532 |
| 0.143 | 3.0 | 792 | 0.4609 | 0.8383 |
| 0.1028 | 4.0 | 1056 | 0.4837 | 0.8475 |
| 0.0783 | 5.0 | 1320 | 0.5645 | 0.8406 |
| 0.0607 | 6.0 | 1584 | 0.6181 | 0.8406 |
### 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_lda_20_v1_sst2
This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_20_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_20_v1) on the GLUE SST2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3649
- Accuracy: 0.8452
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3686 | 1.0 | 264 | 0.3649 | 0.8452 |
| 0.2092 | 2.0 | 528 | 0.3841 | 0.8532 |
| 0.143 | 3.0 | 792 | 0.4609 | 0.8383 |
| 0.1028 | 4.0 | 1056 | 0.4837 | 0.8475 |
| 0.0783 | 5.0 | 1320 | 0.5645 | 0.8406 |
| 0.0607 | 6.0 | 1584 | 0.6181 | 0.8406 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
|
{"base_model": "gokulsrinivasagan/distilbert_lda_20_v1", "datasets": ["glue"], "language": ["en"], "library_name": "transformers", "metrics": ["accuracy"], "tags": ["generated_from_trainer"], "model-index": [{"name": "distilbert_lda_20_v1_sst2", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "GLUE SST2", "type": "glue", "args": "sst2"}, "metrics": [{"type": "accuracy", "value": 0.8451834862385321, "name": "Accuracy"}]}]}]}
|
task
|
[
"TEXT_CLASSIFICATION"
] | 43,894 |
searde/model-financial-documents
|
searde
|
text2text-generation
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:searde/dataset-financial-documents-2",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2023-06-28T12:45:30Z |
2023-07-03T11:46:37+00:00
| 22 | 1 |
---
datasets:
- searde/dataset-financial-documents-2
license: apache-2.0
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: tst-summarization
results:
- task:
type: summarization
name: Summarization
dataset:
name: searde/dataset-financial-documents-2 3.0.0
type: searde/dataset-financial-documents-2
config: 3.0.0
split: validation
args: 3.0.0
metrics:
- type: rouge
value: 90.0297
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. -->
# tst-summarization
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the searde/dataset-financial-documents-2 3.0.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0730
- Rouge1: 90.0297
- Rouge2: 68.9083
- Rougel: 89.8451
- Rougelsum: 89.9838
- Gen Len: 38.9598
## 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: 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: 3.0
### Training results
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.1
- 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. -->
# tst-summarization
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the searde/dataset-financial-documents-2 3.0.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0730
- Rouge1: 90.0297
- Rouge2: 68.9083
- Rougel: 89.8451
- Rougelsum: 89.9838
- Gen Len: 38.9598
## 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: 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: 3.0
### Training results
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3
|
{"datasets": ["searde/dataset-financial-documents-2"], "license": "apache-2.0", "metrics": ["rouge"], "tags": ["generated_from_trainer"], "model-index": [{"name": "tst-summarization", "results": [{"task": {"type": "summarization", "name": "Summarization"}, "dataset": {"name": "searde/dataset-financial-documents-2 3.0.0", "type": "searde/dataset-financial-documents-2", "config": "3.0.0", "split": "validation", "args": "3.0.0"}, "metrics": [{"type": "rouge", "value": 90.0297, "name": "Rouge1"}]}]}]}
|
task
|
[
"SUMMARIZATION"
] | 43,895 |
north/t5_small_NCC_modern
|
north
|
text2text-generation
|
[
"transformers",
"pytorch",
"tf",
"jax",
"tensorboard",
"t5",
"text2text-generation",
"no",
"nn",
"sv",
"dk",
"is",
"en",
"dataset:nbailab/NCC",
"dataset:mc4",
"dataset:wikipedia",
"arxiv:2104.09617",
"arxiv:1910.10683",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 2022-05-21T11:44:53Z |
2022-10-13T14:32:03+00:00
| 59 | 0 |
---
datasets:
- nbailab/NCC
- mc4
- wikipedia
language:
- false
- nn
- sv
- dk
- is
- en
license: other
widget:
- text: <extra_id_0> hver uke samles Regjeringens medlemmer til Statsråd på <extra_id_1>.
Dette organet er øverste <extra_id_2> i Norge. For at møtet skal være <extra_id_3>,
må over halvparten av regjeringens <extra_id_4> være til stede.
- text: På <extra_id_0> kan man <extra_id_1> en bok, og man kan også <extra_id_2>
seg ned og lese den.
---
The North-T5-models are a set of Norwegian and Scandinavian sequence-to-sequence-models. It builds upon the flexible [T5](https://github.com/google-research/text-to-text-transfer-transformer) and [T5X](https://github.com/google-research/t5x) and can be used for a variety of NLP tasks ranging from classification to translation.
| |**Small** <br />_60M_|**Base** <br />_220M_|**Large** <br />_770M_|**XL** <br />_3B_|**XXL** <br />_11B_|
|:-----------|:------------:|:------------:|:------------:|:------------:|:------------:|
|North-T5‑NCC|[🤗](https://huggingface.co/north/t5_small_NCC)|[🤗](https://huggingface.co/north/t5_base_NCC)|[🤗](https://huggingface.co/north/t5_large_NCC)|[🤗](https://huggingface.co/north/t5_xl_NCC)|[🤗](https://huggingface.co/north/t5_xxl_NCC)||
|North-T5‑NCC‑lm|[🤗](https://huggingface.co/north/t5_small_NCC_lm)|[🤗](https://huggingface.co/north/t5_base_NCC_lm)|[🤗](https://huggingface.co/north/t5_large_NCC_lm)|[🤗](https://huggingface.co/north/t5_xl_NCC_lm)|[🤗](https://huggingface.co/north/t5_xxl_NCC_lm)||
|North-T5‑NCC‑modern|✔|[🤗](https://huggingface.co/north/t5_base_NCC_modern)|[🤗](https://huggingface.co/north/t5_large_NCC_modern)|[🤗](https://huggingface.co/north/t5_xl_NCC_modern)||
|North-T5‑NCC‑modern‑lm|[🤗](https://huggingface.co/north/t5_small_NCC_modern_lm)|[🤗](https://huggingface.co/north/t5_base_NCC_modern_lm)|[🤗](https://huggingface.co/north/t5_large_NCC_modern_lm)|[🤗](https://huggingface.co/north/t5_xl_NCC_modern_lm)||
|North-T5‑NCC‑scand|[🤗](https://huggingface.co/north/t5_small_NCC_scand)|[🤗](https://huggingface.co/north/t5_base_NCC_scand)|[🤗](https://huggingface.co/north/t5_large_NCC_scand)|[🤗](https://huggingface.co/north/t5_xl_NCC_scand)||
|North-T5‑scand|[🤗](https://huggingface.co/north/t5_small_scand)|[🤗](https://huggingface.co/north/t5_base_scand)|[🤗](https://huggingface.co/north/t5_large_scand)||
|North-byT5‑NCC|[🤗](https://huggingface.co/north/byt5_small_NCC)|[🤗](https://huggingface.co/north/byt5_base_NCC)|[🤗](https://huggingface.co/north/byt5_large_NCC)||
|North-T5‑scand3M|| [🤗](https://huggingface.co/north/t5_base_scand3M)|[🤗](https://huggingface.co/north/t5_large_scand3M)|[🤗](https://huggingface.co/north/t5_xl_scand3M)||
## T5X Checkpoint
The original T5X checkpoint is also available for this model in the [Google Cloud Bucket](gs://north-t5x/pretrained_models/small/norwegian_NCC_plus_English_pluss200k_balanced_bokmaal_nynorsk_t5x_small/).
## Performance
A thorough evaluation of the North-T5 models is planned, and I strongly recommend external researchers to make their own evaluation. The main advantage with the T5-models are their flexibility. Traditionally, encoder-only models (like BERT) excels in classification tasks, while seq-2-seq models are easier to train for tasks like translation and Q&A. Despite this, here are the results from using North-T5 on the political classification task explained [here](https://arxiv.org/abs/2104.09617).
|**Model:** | **F1** |
|:-----------|:------------|
|mT5-base|73.2 |
|mBERT-base|78.4 |
|NorBERT-base|78.2 |
|North-T5-small|80.5 |
|nb-bert-base|81.8 |
|North-T5-base|85.3 |
|North-T5-large|86.7 |
|North-T5-xl|88.7 |
|North-T5-xxl|91.8|
These are preliminary results. The [results](https://arxiv.org/abs/2104.09617) from the BERT-models are based on the test-results from the best model after 10 runs with early stopping and a decaying learning rate. The T5-results are the average of five runs on the evaluation set. The small-model was trained for 10.000 steps, while the rest for 5.000 steps. A fixed learning rate was used (no decay), and no early stopping. Neither was the recommended rank classification used. We use a max sequence length of 512. This method simplifies the test setup and gives results that are easy to interpret. However, the results from the T5 model might actually be a bit sub-optimal.
## Sub-versions of North-T5
The following sub-versions are available. More versions will be available shorter.
|**Model** | **Description** |
|:-----------|:-------|
|**North‑T5‑NCC** |This is the main version. It is trained an additonal 500.000 steps on from the mT5 checkpoint. The training corpus is based on [the Norwegian Colossal Corpus (NCC)](https://huggingface.co/datasets/NbAiLab/NCC). In addition there are added data from MC4 and English Wikipedia.|
|**North‑T5‑NCC‑lm**|The model is pretrained for an addtional 100k steps on the LM objective discussed in the [T5 paper](https://arxiv.org/pdf/1910.10683.pdf). In a way this turns a masked language model into an autoregressive model. It also prepares the model for some tasks. When for instance doing translation and NLI, it is well documented that there is a clear benefit to do a step of unsupervised LM-training before starting the finetuning.|
|**North‑T5‑NCC‑modern**| The model is pretrained for an additional 200k steps on a blanaced Bokmål and Nynorsk corpus. While this was originally done for doing translation between Bokmål and Nynorsk, it might also give improved results on tasks where you know that the input/output is modern "standard" text. A significant part of the training corpus is newspapers and reports.|
|**North‑T5‑NCC‑modern‑lm**| Trained as above but with an additional 100k "language model"-pretraining.|
|**North‑T5‑NCC‑scand**|The model is pretrained for an additional 200k steps on a Scandinavian corpus (Bokmål, Nynorsk, Danish, Swedish and Icelandic (+ a tiny bit Faeroyish)). The model was trained for increasing the understanding of what effect such training has on various languages.|
|**North‑T5‑scand**|Pretrained for 1,700,000 steps starting with the mT5 checkpoing. The purpose of the mode is studying the difference of different training regimes for Scandinavian language model.|
|**North‑byT5‑base**| This is a vocabulary free version of T5. It is trained exactly like North-T5, but instead of the 250,112 vocabulary, this model operates directly on the raw text. The model architecture might be of particulary interest for tasks involving for instance spelling correction, OCR-cleaning, handwriting recognition etc. However, it will - by design - have amuch shorter maximum sequence length.|
## Fine-tuned versions
As explained below, the model really needs to be fine-tuned for specific tasks. This procedure is relatively simple, and the models are not very sensitive to the hyper-parameters used. Usually a decent result can be obtained by using a fixed learning rate of 1e-3. Smaller versions of the model typically needs to be trained for a longer time. It is easy to train the base-models in a Google Colab.
Since some people really want to see what the models are capable of, without going through the training procedure, I provide a couple of test models. These models are by no means optimised, and are just for demonstrating how the North-T5 models can be used.
* Nynorsk Translator. Translates any text from Norwegian Bokmål to Norwegian Nynorsk. Please test the [Streamlit-demo](https://huggingface.co/spaces/north/Nynorsk) and the [HuggingFace repo](https://huggingface.co/north/demo-nynorsk-base)
* DeUnCaser. The model adds punctation, spaces and capitalisation back into the text. The input needs to be in Norwegian but does not have to be divided into sentences or have proper capitalisation of words. You can even remove the spaces from the text, and make the model reconstruct it. It can be tested with the [Streamlit-demo](https://huggingface.co/spaces/north/DeUnCaser) and directly on the [HuggingFace repo](https://huggingface.co/north/demo-deuncaser-base)
## Training details
All models are built using the Flax-based T5X codebase, and all models are initiated with the mT5 pretrained weights. The models are trained using the T5.1.1 training regime, where they are only trained on an unsupervised masking-task. This also means that the models (contrary to the original T5) needs to be finetuned to solve specific tasks. This finetuning is however usually not very compute intensive, and in most cases it can be performed even with free online training resources.
All the main model model versions are trained for 500.000 steps after the mT5 checkpoint (1.000.000 steps). They are trained mainly on a 75GB corpus, consisting of NCC, Common Crawl and some additional high quality English text (Wikipedia). The corpus is roughly 80% Norwegian text. Additional languages are added to retain some of the multilingual capabilities, making the model both more robust to new words/concepts and also more suited as a basis for translation tasks.
While the huge models almost always will give the best results, they are also both more difficult and more expensive to finetune. I will strongly recommended to start with finetuning a base-models. The base-models can easily be finetuned on a standard graphic card or a free TPU through Google Colab.
All models were trained on TPUs. The largest XXL model was trained on a TPU v4-64, the XL model on a TPU v4-32, the Large model on a TPU v4-16 and the rest on TPU v4-8. Since it is possible to reduce the batch size during fine-tuning, it is also possible to finetune on slightly smaller hardware. The rule of thumb is that you can go "one step down" when finetuning. The large models still rewuire access to significant hardware, even for finetuning.
## Formats
All models are trained using the Flax-based T5X library. The original checkpoints are available in T5X format and can be used for both finetuning or interference. All models, except the XXL-model, are also converted to Transformers/HuggingFace. In this framework, the models can be loaded for finetuning or inference both in Flax, PyTorch and TensorFlow format.
## Future
I will continue to train and release additional models to this set. What models that are added is dependent upon the feedbacki from the users
## Thanks
This release would not have been possible without getting support and hardware from the [TPU Research Cloud](https://sites.research.google/trc/about/) at Google Research. Both the TPU Research Cloud Team and the T5X Team has provided extremely useful support for getting this running.
Freddy Wetjen at the National Library of Norway has been of tremendous help in generating the original NCC corpus, and has also contributed to generate the collated coprus used for this training. In addition he has been a dicussion partner in the creation of these models.
Also thanks to Stefan Schweter for writing the [script](https://github.com/huggingface/transformers/blob/main/src/transformers/models/t5/convert_t5x_checkpoint_to_flax.py) for converting these models from T5X to HuggingFace and to Javier de la Rosa for writing the dataloader for reading the HuggingFace Datasets in T5X.
## Warranty
Use at your own risk. The models have not yet been thougroughly tested, and may contain both errors and biases.
## Contact/About
These models were trained by Per E Kummervold. Please contact me on [email protected].
| null |
Non_BioNLP
|
The North-T5-models are a set of Norwegian and Scandinavian sequence-to-sequence-models. It builds upon the flexible [T5](https://github.com/google-research/text-to-text-transfer-transformer) and [T5X](https://github.com/google-research/t5x) and can be used for a variety of NLP tasks ranging from classification to translation.
| |**Small** <br />_60M_|**Base** <br />_220M_|**Large** <br />_770M_|**XL** <br />_3B_|**XXL** <br />_11B_|
|:-----------|:------------:|:------------:|:------------:|:------------:|:------------:|
|North-T5‑NCC|[🤗](https://huggingface.co/north/t5_small_NCC)|[🤗](https://huggingface.co/north/t5_base_NCC)|[🤗](https://huggingface.co/north/t5_large_NCC)|[🤗](https://huggingface.co/north/t5_xl_NCC)|[🤗](https://huggingface.co/north/t5_xxl_NCC)||
|North-T5‑NCC‑lm|[🤗](https://huggingface.co/north/t5_small_NCC_lm)|[🤗](https://huggingface.co/north/t5_base_NCC_lm)|[🤗](https://huggingface.co/north/t5_large_NCC_lm)|[🤗](https://huggingface.co/north/t5_xl_NCC_lm)|[🤗](https://huggingface.co/north/t5_xxl_NCC_lm)||
|North-T5‑NCC‑modern|✔|[🤗](https://huggingface.co/north/t5_base_NCC_modern)|[🤗](https://huggingface.co/north/t5_large_NCC_modern)|[🤗](https://huggingface.co/north/t5_xl_NCC_modern)||
|North-T5‑NCC‑modern‑lm|[🤗](https://huggingface.co/north/t5_small_NCC_modern_lm)|[🤗](https://huggingface.co/north/t5_base_NCC_modern_lm)|[🤗](https://huggingface.co/north/t5_large_NCC_modern_lm)|[🤗](https://huggingface.co/north/t5_xl_NCC_modern_lm)||
|North-T5‑NCC‑scand|[🤗](https://huggingface.co/north/t5_small_NCC_scand)|[🤗](https://huggingface.co/north/t5_base_NCC_scand)|[🤗](https://huggingface.co/north/t5_large_NCC_scand)|[🤗](https://huggingface.co/north/t5_xl_NCC_scand)||
|North-T5‑scand|[🤗](https://huggingface.co/north/t5_small_scand)|[🤗](https://huggingface.co/north/t5_base_scand)|[🤗](https://huggingface.co/north/t5_large_scand)||
|North-byT5‑NCC|[🤗](https://huggingface.co/north/byt5_small_NCC)|[🤗](https://huggingface.co/north/byt5_base_NCC)|[🤗](https://huggingface.co/north/byt5_large_NCC)||
|North-T5‑scand3M|| [🤗](https://huggingface.co/north/t5_base_scand3M)|[🤗](https://huggingface.co/north/t5_large_scand3M)|[🤗](https://huggingface.co/north/t5_xl_scand3M)||
## T5X Checkpoint
The original T5X checkpoint is also available for this model in the [Google Cloud Bucket](gs://north-t5x/pretrained_models/small/norwegian_NCC_plus_English_pluss200k_balanced_bokmaal_nynorsk_t5x_small/).
## Performance
A thorough evaluation of the North-T5 models is planned, and I strongly recommend external researchers to make their own evaluation. The main advantage with the T5-models are their flexibility. Traditionally, encoder-only models (like BERT) excels in classification tasks, while seq-2-seq models are easier to train for tasks like translation and Q&A. Despite this, here are the results from using North-T5 on the political classification task explained [here](https://arxiv.org/abs/2104.09617).
|**Model:** | **F1** |
|:-----------|:------------|
|mT5-base|73.2 |
|mBERT-base|78.4 |
|NorBERT-base|78.2 |
|North-T5-small|80.5 |
|nb-bert-base|81.8 |
|North-T5-base|85.3 |
|North-T5-large|86.7 |
|North-T5-xl|88.7 |
|North-T5-xxl|91.8|
These are preliminary results. The [results](https://arxiv.org/abs/2104.09617) from the BERT-models are based on the test-results from the best model after 10 runs with early stopping and a decaying learning rate. The T5-results are the average of five runs on the evaluation set. The small-model was trained for 10.000 steps, while the rest for 5.000 steps. A fixed learning rate was used (no decay), and no early stopping. Neither was the recommended rank classification used. We use a max sequence length of 512. This method simplifies the test setup and gives results that are easy to interpret. However, the results from the T5 model might actually be a bit sub-optimal.
## Sub-versions of North-T5
The following sub-versions are available. More versions will be available shorter.
|**Model** | **Description** |
|:-----------|:-------|
|**North‑T5‑NCC** |This is the main version. It is trained an additonal 500.000 steps on from the mT5 checkpoint. The training corpus is based on [the Norwegian Colossal Corpus (NCC)](https://huggingface.co/datasets/NbAiLab/NCC). In addition there are added data from MC4 and English Wikipedia.|
|**North‑T5‑NCC‑lm**|The model is pretrained for an addtional 100k steps on the LM objective discussed in the [T5 paper](https://arxiv.org/pdf/1910.10683.pdf). In a way this turns a masked language model into an autoregressive model. It also prepares the model for some tasks. When for instance doing translation and NLI, it is well documented that there is a clear benefit to do a step of unsupervised LM-training before starting the finetuning.|
|**North‑T5‑NCC‑modern**| The model is pretrained for an additional 200k steps on a blanaced Bokmål and Nynorsk corpus. While this was originally done for doing translation between Bokmål and Nynorsk, it might also give improved results on tasks where you know that the input/output is modern "standard" text. A significant part of the training corpus is newspapers and reports.|
|**North‑T5‑NCC‑modern‑lm**| Trained as above but with an additional 100k "language model"-pretraining.|
|**North‑T5‑NCC‑scand**|The model is pretrained for an additional 200k steps on a Scandinavian corpus (Bokmål, Nynorsk, Danish, Swedish and Icelandic (+ a tiny bit Faeroyish)). The model was trained for increasing the understanding of what effect such training has on various languages.|
|**North‑T5‑scand**|Pretrained for 1,700,000 steps starting with the mT5 checkpoing. The purpose of the mode is studying the difference of different training regimes for Scandinavian language model.|
|**North‑byT5‑base**| This is a vocabulary free version of T5. It is trained exactly like North-T5, but instead of the 250,112 vocabulary, this model operates directly on the raw text. The model architecture might be of particulary interest for tasks involving for instance spelling correction, OCR-cleaning, handwriting recognition etc. However, it will - by design - have amuch shorter maximum sequence length.|
## Fine-tuned versions
As explained below, the model really needs to be fine-tuned for specific tasks. This procedure is relatively simple, and the models are not very sensitive to the hyper-parameters used. Usually a decent result can be obtained by using a fixed learning rate of 1e-3. Smaller versions of the model typically needs to be trained for a longer time. It is easy to train the base-models in a Google Colab.
Since some people really want to see what the models are capable of, without going through the training procedure, I provide a couple of test models. These models are by no means optimised, and are just for demonstrating how the North-T5 models can be used.
* Nynorsk Translator. Translates any text from Norwegian Bokmål to Norwegian Nynorsk. Please test the [Streamlit-demo](https://huggingface.co/spaces/north/Nynorsk) and the [HuggingFace repo](https://huggingface.co/north/demo-nynorsk-base)
* DeUnCaser. The model adds punctation, spaces and capitalisation back into the text. The input needs to be in Norwegian but does not have to be divided into sentences or have proper capitalisation of words. You can even remove the spaces from the text, and make the model reconstruct it. It can be tested with the [Streamlit-demo](https://huggingface.co/spaces/north/DeUnCaser) and directly on the [HuggingFace repo](https://huggingface.co/north/demo-deuncaser-base)
## Training details
All models are built using the Flax-based T5X codebase, and all models are initiated with the mT5 pretrained weights. The models are trained using the T5.1.1 training regime, where they are only trained on an unsupervised masking-task. This also means that the models (contrary to the original T5) needs to be finetuned to solve specific tasks. This finetuning is however usually not very compute intensive, and in most cases it can be performed even with free online training resources.
All the main model model versions are trained for 500.000 steps after the mT5 checkpoint (1.000.000 steps). They are trained mainly on a 75GB corpus, consisting of NCC, Common Crawl and some additional high quality English text (Wikipedia). The corpus is roughly 80% Norwegian text. Additional languages are added to retain some of the multilingual capabilities, making the model both more robust to new words/concepts and also more suited as a basis for translation tasks.
While the huge models almost always will give the best results, they are also both more difficult and more expensive to finetune. I will strongly recommended to start with finetuning a base-models. The base-models can easily be finetuned on a standard graphic card or a free TPU through Google Colab.
All models were trained on TPUs. The largest XXL model was trained on a TPU v4-64, the XL model on a TPU v4-32, the Large model on a TPU v4-16 and the rest on TPU v4-8. Since it is possible to reduce the batch size during fine-tuning, it is also possible to finetune on slightly smaller hardware. The rule of thumb is that you can go "one step down" when finetuning. The large models still rewuire access to significant hardware, even for finetuning.
## Formats
All models are trained using the Flax-based T5X library. The original checkpoints are available in T5X format and can be used for both finetuning or interference. All models, except the XXL-model, are also converted to Transformers/HuggingFace. In this framework, the models can be loaded for finetuning or inference both in Flax, PyTorch and TensorFlow format.
## Future
I will continue to train and release additional models to this set. What models that are added is dependent upon the feedbacki from the users
## Thanks
This release would not have been possible without getting support and hardware from the [TPU Research Cloud](https://sites.research.google/trc/about/) at Google Research. Both the TPU Research Cloud Team and the T5X Team has provided extremely useful support for getting this running.
Freddy Wetjen at the National Library of Norway has been of tremendous help in generating the original NCC corpus, and has also contributed to generate the collated coprus used for this training. In addition he has been a dicussion partner in the creation of these models.
Also thanks to Stefan Schweter for writing the [script](https://github.com/huggingface/transformers/blob/main/src/transformers/models/t5/convert_t5x_checkpoint_to_flax.py) for converting these models from T5X to HuggingFace and to Javier de la Rosa for writing the dataloader for reading the HuggingFace Datasets in T5X.
## Warranty
Use at your own risk. The models have not yet been thougroughly tested, and may contain both errors and biases.
## Contact/About
These models were trained by Per E Kummervold. Please contact me on [email protected].
|
{"datasets": ["nbailab/NCC", "mc4", "wikipedia"], "language": [false, "nn", "sv", "dk", "is", "en"], "license": "other", "widget": [{"text": "<extra_id_0> hver uke samles Regjeringens medlemmer til Statsråd på <extra_id_1>. Dette organet er øverste <extra_id_2> i Norge. For at møtet skal være <extra_id_3>, må over halvparten av regjeringens <extra_id_4> være til stede."}, {"text": "På <extra_id_0> kan man <extra_id_1> en bok, og man kan også <extra_id_2> seg ned og lese den."}]}
|
task
|
[
"TRANSLATION"
] | 43,896 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.