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:

Acknowledgement

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

Downloads last month
30
Safetensors
Model size
7.62B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ 3 Ask for provider support

Model tree for apple/DiffuCoder-7B-cpGRPO

Base model

Qwen/Qwen2.5-7B
Finetuned
(1)
this model