王翛玄 207db58dbc Merge 0761ffa7cd into cc312c1cc6		2026-09-19 09:03:44 +08:00
..
rollout_engine.py	[fix] keep agent rollout token-aligned #850	2026-09-10 11:44:05 +08:00
train_agent.py	[update] trim verbose ddp comments	2026-09-15 14:53:11 +08:00
train_agentic_rl_async.py	feat(trainer): add new train_agentic_rl_async.py	2026-05-28 17:01:00 +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	[update] remove expert args	2026-09-04 22:16:38 +08:00
train_grpo.py	[update] trim verbose ddp comments	2026-09-15 14:53:11 +08:00
train_lora.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_ppo.py	[update] trim verbose ddp comments	2026-09-15 14:53:11 +08:00
train_pretrain.py	[update] remove expert args	2026-09-04 22:16:38 +08:00
train_tokenizer.py	[update] minimind-3	2026-03-25 23:57:45 +08:00
trainer_utils.py	[update] simplify safe math eval	2026-09-14 23:55:32 +08:00