Model Description:
french-document-embedding is an embedding model for documents in the French-English language, with a context length of up to 8096 tokens. This model is a specialized text-embedding model trained specifically for the French-English language. It is built upon gte-multilingual and trained using the [SimilarityLoss], Multi-Negative Ranking Loss, Matryoshka2dLoss and GISTEmbedLoss using guide model. This model embeds and converts long texts or documents into vectors with 786 dimensions, making it useful for vector databases serving semantic search or RAG (Retrieval-Augmented Generation).
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: BilingualModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
Usage:
Using this model becomes easy when you have sentence-transformers installed:
pip install -U sentence-transformers
Then you can use the model like this:
from sentence_transformers import SentenceTransformer
sentences = ["Paris est une capitale de la France", "Paris is a capital of France"]
model = SentenceTransformer('dangvantuan/french-document-embedding', trust_remote_code=True)
embeddings = model.encode(sentences)
print(embeddings)
Evaluation
Citation
@article{reimers2019sentence,
title={Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
author={Nils Reimers, Iryna Gurevych},
journal={https://arxiv.org/abs/1908.10084},
year={2019}
}
@article{zhang2024mgte,
title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and others},
journal={arXiv preprint arXiv:2407.19669},
year={2024}
}
@article{li2023towards,
title={Towards general text embeddings with multi-stage contrastive learning},
author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
journal={arXiv preprint arXiv:2308.03281},
year={2023}
}
@article{li20242d,
title={2d matryoshka sentence embeddings},
author={Li, Xianming and Li, Zongxi and Li, Jing and Xie, Haoran and Li, Qing},
journal={arXiv preprint arXiv:2402.14776},
year={2024}
}
@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}
}
@misc{solatorio2024gistembed,
title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
author={Aivin V. Solatorio},
year={2024},
eprint={2402.16829},
archivePrefix={arXiv},
primaryClass={cs.LG}
}