---
license: mit
pipeline_tag: text-generation
library_name: transformers
---

# TMLR-Group-HF/GT-Qwen3-8B-Base

This is the Qwen3-8B-Base model trained by GRPO Ground Truth method using MATH training set, as described in the paper [Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models](https://huggingface.co/papers/2508.00410).

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

## Citation

```bibtex
@article{zhang2025coreward,
  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}
}
```