jason law
jason law
> Hi, Same problem, have you fixed?
Thanks a lot! So can the provided transformers version(git+https://github.com/huggingface/transformers.git@057e1d74733f52817dc05b673a340b4e3ebea08c ) help me reproduce the correct results?
> We have confirmed that the problem is due to transformers library version, this has been fixed in the latest commit. For example, the command `python main.py mmlu --model_name llama...
Maybe the reason is that llama doesn't support chinese well, its english-only chatting is not bad.
meet the same problem, neither pytorch 2.2.1 or 2.1.2 work
updating gcc and g++ to 11.4 solve my problem
Hi, If I launch separate jobs, will the projection matrix remain the same when I set a same number for model_id?
Same problem
same problem, have you figured out?
Thanks. I'm running on a already virualized platform(ECS), it seems that both vmware and KVM are not support. Will there be a solution for it?