issues
search
mymusise
/
ChatGLM-Tuning
基于ChatGLM-6B + LoRA的Fintune方案
MIT License
3.71k
stars
444
forks
source link
add RLHF
#189
Open
mymusise
opened
1 year ago
mymusise
commented
1 year ago
add reward model
add ppo trainer