Bge Reranker V2 M3 En Ru

🚀 Model for English and Russian

This is a truncated version of BAAI/bge-reranker-v2-m3, optimized for English and Russian.

This model is a specialized variant of BAAI/bge-reranker-v2-m3. It retains only English and Russian tokens in its vocabulary, resulting in a model that is 1.5 times smaller than the original while still generating the same embeddings. The truncation process was carried out in this notebook.

🚀 Quick Start

Generate Scores for text

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('qilowoq/bge-reranker-v2-m3-en-ru')
model = AutoModelForSequenceClassification.from_pretrained('qilowoq/bge-reranker-v2-m3-en-ru')
model.eval()

pairs = [('How many people live in Berlin?', 'Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.'),
         ('Какая площадь Берлина?', 'Площадь Берлина составляет 891,8 квадратных километров.')]
with torch.no_grad():
    inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt')
    scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
    print(scores)

📚 Documentation

Model Information

📄 License

This project is licensed under the MIT license.

📝 Citation

If you find this repository useful, please consider giving a star and citation

@misc{li2023making,
      title={Making Large Language Models A Better Foundation For Dense Retrieval}, 
      author={Chaofan Li and Zheng Liu and Shitao Xiao and Yingxia Shao},
      year={2023},
      eprint={2312.15503},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@misc{chen2024bge,
      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
      year={2024},
      eprint={2402.03216},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}