QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization

Paper HuggingFace

Citation

@misc{keprepair,
      title={QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization}, 
      author={Changxin Ke and Rui Zhang and Jiaming Guo and Yuanbo Wen and Li Ding and Shuo Wang and Xuyuan Zhu and Xiong Peng and Di Huang and Zidong Du and Xing Hu and Qi Guo and Yunji Chen},
      year={2026},
      eprint={2604.05963},
      archivePrefix={arXiv},
      primaryClass={cs.SE},
      url={https://arxiv.org/abs/2604.05963}, 
}
Downloads last month
-
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kcxain/Prepair-Python-7B-EA

Base model

Qwen/Qwen2.5-7B
Finetuned
(321)
this model

Collection including kcxain/Prepair-Python-7B-EA

Paper for kcxain/Prepair-Python-7B-EA