minimind/trainer
2025-10-23 15:03:19 +08:00
..
train_distill_reason.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
train_distillation.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
train_dpo.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
train_full_sft.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
train_grpo.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
train_lora.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
train_ppo.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
train_pretrain.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00
train_spo.py [fix] sampler-ddp 2025-10-23 15:03:19 +08:00