shibing624 / MedicalGPT

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
Apache License 2.0
2.94k stars 451 forks source link

使用deepspeed 全参数sft后,inference 回答的都为空,有解决办法吗 #357

Open Yian320 opened 3 months ago

Yian320 commented 3 months ago

Describe the Question

Please provide a clear and concise description of what the question is.

shibing624 commented 3 months ago

没训练好?

Yian320 commented 3 months ago

没训练好?

30 57 730

使用zero-2全参数sft训练完成后,感觉模型权重没有保存,这是啥原因呢