minimind/trainer
R b92396ad0a use wandb 2026-05-28 22:09:21 -07:00
..
rollout_engine.py [fix] inference bug 2026-05-03 20:48:48 +08:00
train_agent.py use wandb 2026-05-28 22:09:21 -07:00
train_distillation.py use wandb 2026-05-28 22:09:21 -07:00
train_dpo.py use wandb 2026-05-28 22:09:21 -07:00
train_full_sft.py use wandb 2026-05-28 22:09:21 -07:00
train_grpo.py use wandb 2026-05-28 22:09:21 -07:00
train_lora.py use wandb 2026-05-28 22:09:21 -07:00
train_ppo.py use wandb 2026-05-28 22:09:21 -07:00
train_pretrain.py use wandb 2026-05-28 22:09:21 -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