Corey52HZ 4dbeebecbc Merge 655d4705eb into 1e6e909f88		2026-09-21 13:55:27 +08:00
..
rollout_engine.py	[fix] keep agent rollout token-aligned #850	2026-09-10 11:44:05 +08:00
train_agent.py	Merge 655d4705eb into 1e6e909f88	2026-09-21 13:55:27 +08:00
train_distillation.py	feat: support Apple Silicon (MPS) for training and web demo	2026-09-09 21:42:03 +08:00
train_dpo.py	feat: support Apple Silicon (MPS) for training and web demo	2026-09-09 21:42:03 +08:00
train_full_sft.py	feat: support Apple Silicon (MPS) for training and web demo	2026-09-09 21:42:03 +08:00
train_grpo.py	Merge 655d4705eb into 1e6e909f88	2026-09-21 13:55:27 +08:00
train_lora.py	feat: support Apple Silicon (MPS) for training and web demo	2026-09-09 21:42:03 +08:00
train_ppo.py	Merge 655d4705eb into 1e6e909f88	2026-09-21 13:55:27 +08:00
train_pretrain.py	feat: support Apple Silicon (MPS) for training and web demo	2026-09-09 21:42:03 +08:00
train_tokenizer.py	[fix] train_tokenizer 读预训练语料时产出 0 条文本，静默训出空词表	2026-09-20 10:33:51 +08:00
trainer_utils.py	[update] simplify safe math eval	2026-09-14 23:55:32 +08:00