hiyouga af6c011fcb fix ChatGLM RLHF

2023-08-15 11:19:20 +08:00

..

core

alert pad_token source

2023-08-15 00:07:56 +08:00

dpo

fix ChatGLM lm_head #494

2023-08-14 14:14:48 +08:00

ppo

fix ChatGLM RLHF

2023-08-15 11:19:20 +08:00

pt

support DPO training (2305.18290)

2023-08-11 03:02:53 +08:00

rm

fix ChatGLM RLHF

2023-08-15 11:19:20 +08:00

sft

support DPO training (2305.18290)

2023-08-11 03:02:53 +08:00

__init__.py

modify code structure

2023-08-02 23:17:36 +08:00

tune.py

support rope scaling, fix #475 #476 #478

2023-08-12 20:46:27 +08:00