| --- |
| license: unknown |
| base_model: |
| - Qwen/Qwen2.5-Coder-7B |
| tags: |
| - code |
| - text-diffusion-model |
| - diffusion large language model |
| --- |
| |
| ### DiffuCoder-7B-Base |
|
|
| The DiffuCoder-7B-Base model is our foundational masked diffusion LLM for code generation. |
|
|
| - Training recipe: Using [DiffuLLaMA](https://github.com/HKUNLP/DiffuLLaMA)'s adaptation approach, trained on a large corpus of code: with Stage 1 65B tokens and Stage 2 65B tokens. |
|
|
| - Benchmarks: Strong baseline performance on HumanEval, MBPP and BigCodeBench. |
|
|
|
|
| #### More details and usage examples: |
|
|
| - Paper: [DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation](https://arxiv.org/abs/2506.20639) |
|
|
| - GitHub: https://github.com/apple/ml-diffucoder |
|
|
| #### Acknowledgement |
| To power this HuggingFace model release, we reuse [Dream](https://huggingface.co/Dream-org/Dream-v0-Base-7B)'s modeling architecture and generation utils. |
