Modelpublic

TMLR-Group-HF/Co-rewarding-I-Qwen3-4B-Base-MATH

sourceHugging Facemitupdated 1y agoView on Hugging Face

1likes22downloads

Model Card

CoReward-Qwen3-4B-Base

This is the Qwen3-4B-Base model trained by the Co-rewarding method using MATH training set, as presented in the paper Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.

If you are interested in Co-rewarding, you can find more details on our Github Repo [https://github.com/tmlr-group/Co-rewarding].

Citation

@article{zhang2025co,
  title={Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models},
  author={Zhang, Zizhuo and Zhu, Jianing and Ge, Xinmu and Zhao, Zihua and Zhou, Zhanke and Li, Xuan and Feng, Xiao and Yao, Jiangchao and Han, Bo},
  journal={arXiv preprint arXiv:2508.00410},
  year={2025}
}