minimind/trainer
guosj ae2805a6bf
Merge 01c04f519b into da865af63d
2026-04-29 18:01:22 +02:00
..
muon.py add muon optimizer 2026-01-29 10:40:23 +08:00
rollout_engine.py [fix] bugs 2026-04-27 19:16:08 +08:00
train_agent.py [fix] rollout bugs 2026-04-27 17:54:09 +08:00
train_distillation.py [fix] bugs 2026-04-21 13:03:34 +08:00
train_dpo.py [fix] bugs 2026-04-21 13:03:34 +08:00
train_full_sft.py Merge 01c04f519b into da865af63d 2026-04-29 18:01:22 +02:00
train_grpo.py [fix] bugs 2026-04-27 19:16:08 +08:00
train_lora.py [fix] bugs 2026-04-21 13:03:34 +08:00
train_ppo.py [fix] bugs 2026-04-27 19:16:08 +08:00
train_pretrain.py Merge 01c04f519b into da865af63d 2026-04-29 18:01:22 +02:00
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