apple/DiffuCoder-7B-cpGRPO

DiffuCoder-7B-cpGRPO

The DiffuCoder-7B-cpGRPO variant further refines DiffuCoder-Instruct with reinforcement learning via Coupled-GRPO.

Training recipe:

• Initialized from DiffuCoder-7B-Instruct, post-training with coupled-GRPO on 21K code data (1 epoch).
• coupled-GRPO significantly improves DiffuCoder's performance on code generation benchmarks (+4.4% on EvalPlus) and reduces reliance on AR bias during decoding.

More details and usage examples:

• Paper: DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

• GitHub: https://github.com/apple/ml-diffucoder

Acknowledgement

To power this HuggingFace model release, we reuse Dream's modeling architecture and generation utils.