CharlesCheung996 32d15a9932 Merge 744f16d802 into a3c7b01cc0		2026-09-10 15:51:58 +08:00
..
rollout_engine.py	[fix] keep agent rollout token-aligned #850	2026-09-10 11:44:05 +08:00
train_agent.py	Merge 744f16d802 into a3c7b01cc0	2026-09-10 15:51:58 +08:00
train_distillation.py	feat: enable MPS across training entrypoints	2026-09-06 03:14:06 +08:00
train_dpo.py	feat: enable MPS across training entrypoints	2026-09-06 03:14:06 +08:00
train_full_sft.py	feat: enable MPS across training entrypoints	2026-09-06 03:14:06 +08:00
train_grpo.py	Merge 744f16d802 into a3c7b01cc0	2026-09-10 15:51:58 +08:00
train_lora.py	feat: enable MPS across training entrypoints	2026-09-06 03:14:06 +08:00
train_ppo.py	Merge 744f16d802 into a3c7b01cc0	2026-09-10 15:51:58 +08:00
train_pretrain.py	feat: enable MPS across training entrypoints	2026-09-06 03:14:06 +08:00
train_tokenizer.py	[update] minimind-3	2026-03-25 23:57:45 +08:00
trainer_utils.py	feat: add device-agnostic training utilities	2026-09-06 03:14:06 +08:00