Abolfazl-kr

Results 2 comments of Abolfazl-kr

pretrain.py of llama-7b model, Exception: : Current loss scale already at minimum

i think it's good to try bf16. it will work with A100 and the problem of loss scale

Code for training llama pro?

does anybody know how to continue pre-training LLaMA Pro? @yhyu13 @raghavgarg97 @yxgeee @hills-code