Sts Distilcamembert Base

🚀 Sentence-Transformers

This project is a feature extraction model based on sentence-transformers, which can encode sentences or paragraphs into 768-dimensional vectors, enabling tasks such as sentence similarity calculation.

🚀 Quick Start

This model can be used through the sentence-transformers or transformers libraries. Here are the installation and usage examples for both libraries.

Installation via sentence-transformers

pip install -U sentence-transformers

Usage via sentence-transformers

from sentence_transformers import SentenceTransformer
sentences = ["Ceci est un exemple", "deuxième exemple"]

model = SentenceTransformer('h4c5/sts-distilcamembert-base')
embeddings = model.encode(sentences)
print(embeddings)

Installation via transformers

pip install -U transformers

Usage via transformers

from transformers import AutoTokenizer, AutoModel
import torch

tokenizer = AutoTokenizer.from_pretrained("h4c5/sts-distilcamembert-base")
model = AutoModel.from_pretrained("h4c5/sts-distilcamembert-base")
model.eval()


# Mean Pooling
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[
        0
    ]  # First element of model_output contains all token embeddings
    input_mask_expanded = (
        attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    )
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(
        input_mask_expanded.sum(1), min=1e-9
    )

# Tokenization et calcul des embeddings des tokens
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors="pt")
model_output = model(**encoded_input)

# Mean pooling
sentence_embeddings = mean_pooling(model_output, encoded_input["attention_mask"])

print(sentence_embeddings)

✨ Features

• This model is based on the cmarkea/distilcamembert-base model and is fine-tuned using the sentence-transformers library.
• It can encode sentences or paragraphs (up to 514 tokens) into 768-dimensional vectors.
• The underlying DistilCamemBERT model is a distilled version of CamemBERT, which reduces the number of model parameters by half and improves inference time.

📦 Installation

You can install the necessary libraries using the following commands:

• For sentence-transformers:

pip install -U sentence-transformers

• For transformers:

pip install -U transformers

💻 Usage Examples

The above quick start section already provides basic usage examples. Here is an example of evaluating the model:

Model Evaluation

The model was evaluated on the STSb fr dataset:

from datasets import load_dataset
from sentence_transformers import InputExample, evaluation


def dataset_to_input_examples(dataset):
    return [
        InputExample(
            texts=[example["sentence1"], example["sentence2"]],
            label=example["similarity_score"] / 5.0,
        )
        for example in dataset
    ]


sts_test_dataset = load_dataset("stsb_multi_mt", name="fr", split="test")
sts_test_examples = dataset_to_input_examples(sts_test_dataset)

sts_test_evaluator = evaluation.EmbeddingSimilarityEvaluator.from_input_examples(
    sts_test_examples, name="sts-test"
)

sts_test_evaluator(model, ".")

Evaluation Results

The following are the evaluation results of the model on the stsb_multi_mt dataset (French data, test split):

🔧 Technical Details

Training Parameters

The model was trained with the following parameters:

• DataLoader: torch.utils.data.dataloader.DataLoader of length 180 with parameters:

{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

• Loss: sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss
• Parameters of the fit() method:

{
    "epochs": 10,
    "evaluation_steps": 1000,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 500,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: CamembertModel 
  (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})
)

📄 License

This project is licensed under the MIT license.

📚 Documentation

Citing

If you use this model, please cite the following papers:

@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",
    journal={"https://arxiv.org/abs/1908.10084"},
}

@inproceedings{sanh2019distilbert,
    title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
    author={Sanh, Victor and Debut, Lysandre and Chaumond, Julien and Wolf, Thomas},
    booktitle={NeurIPS EMC^2 Workshop},
    journal={https://arxiv.org/abs/1910.01108},
    year={2019}
}

@inproceedings{martin2020camembert,
    title={CamemBERT: a Tasty French Language Model},
    author={Martin, Louis and Muller, Benjamin and Su{\'a}rez, Pedro Javier Ortiz and Dupont, Yoann and Romary, Laurent and de la Clergerie, {\'E}ric Villemonte and Seddah, Djam{\'e} and Sagot, Beno{\^\i}t},
    booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
    journal={https://arxiv.org/abs/1911.03894},
    year={2020}
}

@inproceedings{delestre:hal-03674695,
    TITLE = {{DistilCamemBERT : une distillation du mod{\`e}le fran{\c c}ais CamemBERT}},
    AUTHOR = {Delestre, Cyrile and Amar, Abibatou},
    URL = {https://hal.archives-ouvertes.fr/hal-03674695},
    BOOKTITLE = {{CAp (Conf{\'e}rence sur l'Apprentissage automatique)}},
    ADDRESS = {Vannes, France},
    YEAR = {2022},
    MONTH = Jul,
    KEYWORDS = {NLP ; Transformers ; CamemBERT ; Distillation},
    PDF = {https://hal.archives-ouvertes.fr/hal-03674695/file/cap2022.pdf},
    HAL_ID = {hal-03674695},
    HAL_VERSION = {v1},
    journal={https://arxiv.org/abs/2205.11111},
}