peft训练完成,参考的是04-Qwen-7B-Chat Lora 微调.ipynb,但是重新载入模型时,提示peft版本问题,用的是model = AutoModelForCausalLM.from_pretrained("../output/Qwen/checkpoint-1300/", trust_remote_code=True).eval(),提示的错误时ValueError: The version of PEFT you are using is not compatible, please use a version that is greater than 0.5.0 #95
补充,我训练时安装的时推荐版本依赖,即 pip install transformers==4.35.2 pip install peft==0.4.0 pip install datasets==2.10.1 pip install accelerate==0.20.3 pip install tiktoken pip install transformers_stream_generator