hiyouga 48d6d925f7 fix #1558 ...

Former-commit-id: 1740131d63d32aefc0370441baf4716ddb5ebcfe

2023-11-19 14:15:47 +08:00

..

dpo

fix #1558

2023-11-19 14:15:47 +08:00

ppo

fix rlhf callback

2023-11-16 03:26:19 +08:00

pt

fix #1558

2023-11-19 14:15:47 +08:00

rm

fix #1558

2023-11-19 14:15:47 +08:00

sft

fix #1558

2023-11-19 14:15:47 +08:00

__init__.py

disentangle model from tuner and rename modules

2023-11-15 16:29:09 +08:00

tuner.py

support full-parameter PPO

2023-11-16 02:08:04 +08:00

utils.py

fix #1558

2023-11-19 14:15:47 +08:00