Mingrui Chen

@GuanhuaWang I got the same problem when finetuning "EleutherAI/gpt-j-6B" using LoRA on 8×2080ti. Exactly the same error log as above. Reproduce the error: clone this repo: https://github.com/CarperAI/trlx modify the script:...

> > @chenmingjiong Did you modify the json file? If so, please paste the changes here. No. I use the original file.

try `device_map={'':torch.cuda.current_device()}` ? https://github.com/huggingface/transformers/issues/21736