[Question] Support for DeepSeek V4?

Your Question

Hi slime team,

Thank you for the great work on slime.

I would like to ask whether slime currently supports training or fine-tuning DeepSeek V4 models, or whether there are any known plans / recommended modifications to support it.

If it is not officially supported yet, I would appreciate any guidance on which parts of slime would need to be modified to make it work.

Thanks!

What I've Tried

i read all the guide.

Environment (if relevant)

• slime version:
• Python version:
• PyTorch version:
• CUDA/ROCm version:
• GPU type and count:
• OS:

Additional Context

No response

Pre-submission Checklist

• I have read the CONTRIBUTING.md and understand the collaboration scope.
• I have read the documentation and FAQ and my question is not answered there.
• I have searched for existing issues and my question has not been asked before.

Start by reviewing the slime documentation, FAQ, and CONTRIBUTING.md, then identify whether they describe DeepSeek V4 support or model-integration guidance. Done would require a confirmed support path or a clearly scoped list of modifications needed to train or fine-tune DeepSeek V4.