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
..
2024-07-03 19:45:51 +08:00
2024-06-15 17:54:33 +08:00
2024-06-15 17:54:33 +08:00
2024-06-15 17:54:33 +08:00