飞羽ok
Results
2
repositories owned by
飞羽ok
LLaMA-MOSS-RLHF-LoRA
18
Stars
1
Forks
Watchers
用RLHF可选LoRA对LLaMA和MOSS进行训练|Training LLaMA or MOSS with RLHF [LoRA]
ChatGLM-RLHF
186
Stars
26
Forks
Watchers
对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF