minimind/trainer
readlnh 9fe4343b7b [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
..
train_distillation.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
train_dpo.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
train_full_sft.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
train_grpo.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
train_lora.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
train_ppo.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
train_pretrain.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
train_reason.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
train_spo.py [fix] gradient accumulation step alignment 2026-03-24 01:45:04 +01:00
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