Daya Guo
Daya Guo
结构一样,超参不一样
DeepSeek-Coder-V2-Lite-Instruct
We use a self-developed fine-tuning framework and code, so we cannot release it. We are currently trying to use the open-source DeepSpeed for fine-tuning. If there is any progress, we...
you can refer to the following links: https://github.com/datawhalechina/self-llm/blob/master/DeepSeek-Coder-V2/04-DeepSeek-Coder-V2-Lite-Instruct%20Lora%20%E5%BE%AE%E8%B0%83.md https://github.com/DYF-AI/custom-swift
Thank you very much for your contribution. We will guide those who need SFT to this link.