minimind/trainer
jingyaogong 9d898576ac [update] aux loss 2026-01-01 22:41:46 +08:00
..
train_distill_reason.py [update] aux loss 2026-01-01 22:41:46 +08:00
train_distillation.py [update] aux loss 2026-01-01 22:41:46 +08:00
train_dpo.py [update] aux loss 2026-01-01 22:41:46 +08:00
train_full_sft.py [update] aux loss 2026-01-01 22:41:46 +08:00
train_grpo.py [update] aux loss 2026-01-01 22:41:46 +08:00
train_lora.py [update] aux loss 2026-01-01 22:41:46 +08:00
train_ppo.py [update] aux loss 2026-01-01 22:41:46 +08:00
train_pretrain.py [update] aux loss 2026-01-01 22:41:46 +08:00
train_spo.py [update] aux loss 2026-01-01 22:41:46 +08:00
trainer_utils.py [feat] get params 2025-12-31 20:46:59 +08:00