hiyouga 44fe93e9b0 fix #1438 #1439 ...

Former-commit-id: 84260d58dda22adc32c26bc943ed2a36fd01341d

2023-11-09 13:45:10 +08:00

..

core

fix #1438 #1439

2023-11-09 13:45:10 +08:00

dpo

fix ppo train and dpo eval

2023-11-07 22:48:51 +08:00

ppo

fix #1422

2023-11-07 19:42:01 +08:00

pt

fix reward model loading

2023-11-07 17:20:51 +08:00

rm

fix #1422

2023-11-07 19:42:01 +08:00

sft

fix reward model loading

2023-11-07 17:20:51 +08:00

__init__.py

modify code structure

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

tune.py

support pagination in webui preview

2023-11-02 21:21:45 +08:00