hiyouga f2e139f5cd fix #1452 ...

Former-commit-id: 4d16214467715df458e24d03bb7d303d62b8bdcd

2023-11-09 16:41:32 +08:00

..

__init__.py

support DPO training (2305.18290)

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

collator.py

fix bug in DPO data collator

2023-09-08 20:45:07 +08:00

trainer.py

fix #1452

2023-11-09 16:41:32 +08:00

workflow.py

fix ppo train and dpo eval

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