OpenRLHF icon indicating copy to clipboard operation
OpenRLHF copied to clipboard

Published 20 hours ago • verified publisher icon OpenLLMAI

The configuration for Llama-7b on 4 RTX4090

Open LinkyLiu opened this issue 2 months ago • 5 comments

Hello, I want to run train_ppo_llama_ray.sh on 4 RTX4090, should I modify the actor_num_gpus_per_node/critic_num_gpus_per_node in train_ppo_llama_ray.sh ? As the default script is for 8 gpus, what else should I pay attention to or should be modified?

LinkyLiu avatar Apr 15 '24 14:04 LinkyLiu