minimind/trainer
2025-10-30 10:05:12 +08:00
..
train_distill_reason.py [feat] add args 2025-10-30 10:05:12 +08:00
train_distillation.py [feat] add args 2025-10-30 10:05:12 +08:00
train_dpo.py [feat] add args 2025-10-30 10:05:12 +08:00
train_full_sft.py [feat] add args 2025-10-30 10:05:12 +08:00
train_grpo.py [feat] add args 2025-10-30 10:05:12 +08:00
train_lora.py [feat] add args 2025-10-30 10:05:12 +08:00
train_ppo.py [feat] add args 2025-10-30 10:05:12 +08:00
train_pretrain.py [feat] add args 2025-10-30 10:05:12 +08:00
train_spo.py [feat] add args 2025-10-30 10:05:12 +08:00
trainer_utils.py [feat] pause-training 2025-10-26 18:49:52 +08:00