lansinuote/Simple_RLHF_tiny

RLHF,一个更轻更快更简单的实现.

原版代码:https://github.com/lansinuote/Simple_RLHF

运行环境:

torch==1.13.1+cu117

transformers==4.38.2

datasets==2.18.0

accelerate==0.28.0

peft==0.9.0

视频课程:https://www.bilibili.com/video/BV13r42177Hk