hy 3159159c10 Merge 864bd67437 into d65ef2c00e		2026-08-21 22:00:07 +08:00
..
opd_utils.py	feat: add generalized on-policy distillation trainer	2026-07-15 21:15:10 +08:00
rollout_engine.py	feat: add generalized on-policy distillation trainer	2026-07-15 21:15:10 +08:00
train_agent.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_distillation.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_dpo.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_full_sft.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_grpo.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_lora.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_opd.py	feat: add generalized on-policy distillation trainer	2026-07-15 21:15:10 +08:00
train_ppo.py	[refactor] PPO cleanup	2026-07-23 11:11:05 +08:00
train_pretrain.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_tokenizer.py	[update] minimind-3	2026-03-25 23:57:45 +08:00
trainer_utils.py	[update] minimind-3	2026-03-25 23:57:45 +08:00