Justin Guese c3199c7240 [update] 把 num_experts / num_experts_per_tok 暴露到命令行 ... 此前要改专家数只能去编辑 model_minimind.py。三个入口 （train_pretrain / train_full_sft / eval_llm）的默认值与 MiniMindConfig 一致（4 / 1），默认行为不变；RL 与 agent 相关的 trainer 不动。		2026-09-03 15:13:29 +07:00
..
rollout_engine.py	[fix] inference bug	2026-05-03 20:48:48 +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	[update] 把 num_experts / num_experts_per_tok 暴露到命令行	2026-09-03 15:13:29 +07:00
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_ppo.py	[refactor] PPO cleanup	2026-07-23 11:11:05 +08:00
train_pretrain.py	[update] 把 num_experts / num_experts_per_tok 暴露到命令行	2026-09-03 15:13:29 +07:00
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