minimind/trainer
jingyaogong c090b69c4d [update] align loss 2026-01-15 00:56:32 +08:00
..
train_distillation.py [update] align loss 2026-01-15 00:56:32 +08:00
train_dpo.py [update] align loss 2026-01-15 00:56:32 +08:00
train_full_sft.py [update] align loss 2026-01-15 00:56:32 +08:00
train_grpo.py [fix] compile unpack 2026-01-14 20:13:32 +08:00
train_lora.py [update] align loss 2026-01-15 00:56:32 +08:00
train_ppo.py [fix] compile unpack 2026-01-14 20:13:32 +08:00
train_pretrain.py [update] align loss 2026-01-15 00:56:32 +08:00
train_reason.py [update] align loss 2026-01-15 00:56:32 +08:00
train_spo.py [fix] compile unpack 2026-01-14 20:13:32 +08:00
train_tokenizer.py [update] rename train tokenizer 2026-01-06 01:17:33 +08:00
trainer_utils.py [fix] compile unpack 2026-01-14 20:13:32 +08:00