Luning Wang

Change the data_loader definition sentence(approximately at line 145) to the following sentence : data_loader = data.DataLoader(dataset, args.batch_size, num_workers=args.num_workers, shuffle=True, collate_fn=detection_collate, pin_memory=True, generator = torch.Generator(device='cuda'))

I also encounted this issue and found the problem as incompatibility of different versions of transformers. You may choose to use older versions to get around the problem: ```sh pip...

Update: I discussed the dependency problem with the authors and they recommend to use transformers==4.33, I've tried it on llama-2-7b-chat and got correct responses.

> Thanks for the reply and reaching out to the authors. That worked for me using transformers==4.33, after applying the small changes in this PR #41. > > Is there...