Wai Tak Wong
Wai Tak Wong
I hit the same issue on python3.10. 
For zzcgithub, do you mention the step 4. # 修改/modules/LoRA.py文件,大约在第28行 shared.model.resize_token_embeddings(len(shared.tokenizer)) shared.model = PeftModel.from_pretrained(shared.model, Path(f"{shared.args.lora_dir}/{lora_name}"), **params) No change for the second line, otherwise it fails. I only add the first...
> I hit the same issue on python3.10.  I discover that if I run with --cpu, then there is no issue. However, the performance (the response) is really slow,...