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

The base Qwen2.5-Math-7B model used by LUFFY, described in [Learning to Reason under Off-Policy Guidance](https://huggingface.co/papers/2504.14945). 
We change to rope_theta from 10000 to 40000 and extend the context window to 16k.
Also, we modify the chat_template for the system prompt and add <think>.

Github: https://github.com/ElliottYan/LUFFY

# Citation
If you find our model, data, or evaluation code useful, please kindly cite our paper:
```bib
@misc{luffy,
      title={Learning to Reason under Off-Policy Guidance}, 
      author={Jianhao Yan and Yafu Li and Zican Hu and Zhi Wang and Ganqu Cui and Xiaoye Qu and Yu Cheng and Yue Zhang},
      year={2025},
      eprint={2504.14945},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2504.14945}, 
}
```