This model is released as part of the ReasonEmbed resources. ReasonEmbed studies enhanced text embeddings for reasoning-intensive document retrieval; for more details, please refer to our paper.

Training Data

The model was fine-tuned on the MSMARCO data from hanhainebula/bge-multilingual-gemma2-data.

Training Procedure

Base model: Qwen/Qwen3-8B
Training framework: FlagEmbedding
Training data: MSMARCO
Number of epochs: 1

Tokenizer Note

Following the tokenizer modification discussed in Qwen3-Embedding-0.6B discussion #2, we modified the tokenizer so that it can automatically add the EOS token during tokenization.

License

This model is released under the Apache 2.0 license.

Citation

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

@article{chen2025reasonembed,
  title={ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval},
  author={Chen, Jianlyu and Lan, Junwei and Li, Chaofan and Lian, Defu and Liu, Zheng},
  journal={arXiv preprint arXiv:2510.08252},
  year={2025}
}

hanhainebula/qwen3-8b-ft-msmarco

qwen3-8b-ft-msmarco

Training Data

Training Procedure

Tokenizer Note

License

Citation

hanhainebula/
qwen3-8b-ft-msmarco