minimind/trainer
Zhenyu Wang d8c848de7f
Merge fd6448ce61 into 6efba3249a
2025-10-24 01:19:19 +08:00
..
train_distill_reason.py [feat] shuffle data 2025-10-23 20:13:28 +08:00
train_distillation.py [feat] shuffle data 2025-10-23 20:13:28 +08:00
train_dpo.py [feat] shuffle data 2025-10-23 20:13:28 +08:00
train_full_sft.py [feat] shuffle data 2025-10-23 20:13:28 +08:00
train_grpo.py [feat] shuffle data 2025-10-23 20:13:28 +08:00
train_lora.py [feat] shuffle data 2025-10-23 20:13:28 +08:00
train_ppo.py [feat] shuffle data 2025-10-23 20:13:28 +08:00
train_pretrain.py Merge fd6448ce61 into 6efba3249a 2025-10-24 01:19:19 +08:00
train_spo.py [feat] shuffle data 2025-10-23 20:13:28 +08:00