Files
LlamaFactory/src/llamafactory/train/ppo/trainer.py
hiyouga 0b0e27c2f1 fix #4609
unwrap_model_for_generation(reward_model) is necessary for zero3 training


Former-commit-id: c8d5b21700577cae8d6ca03359bcf1762c8b7cb8
2024-07-03 19:45:51 +08:00

22 KiB