Does the SFT Framework Support Fine-Tuning for DeepSeek-R1-Distill-Qwen-7B

Hi,

I am currently exploring the usage of the SFT framework for fine-tuning models. I am particularly interested in fine-tuning the DeepSeek-R1-Distill-Qwen-7B model using your framework.

Could you please confirm whether the SFT framework supports fine-tuning for this specific model? If not, what modifications would be necessary to adapt the framework for this purpose?

Looking forward to your guidance and suggestions.

Thank you!