Hyesung Jeon comments

Repositories
Issues
Comments

Results 2 comments of


                                            Hyesung Jeon

Is it possible to run Llama 2 70B with 80Gb?

I'm also having a similar problem with LLaMA 33B using an NVIDIA A100 80G * 2, even with a single micro-batch size. It is really confusing because when I execute...

Will the evaluation code release?

It seems lm-eval-harness can reproduce the Llama (paper ver.1) performance on Hellaswag, but some issues remain in other tasks. Llama-30b model gives 82.65 % acc_norm while paper shows 82.9%.