[Question]: Why is the save training model so big using the peft training way?

[HaixHan]

🐛 Describe the bug

In stage 1 and stage 3, the size (about 13GB) of the training model is very big using the peft training way. I have set "lora_rank">0 when training sft or prompt method? Why do I get an error when I try to use "actor.save_pretrained(args.save_path):“ "AttributeError: 'BLOOMActor' object has no attribute 'save_pretrained "

Environment

No response

[JThh]

Hi, why not using trainer's saving utility?