minimind/trainer
Jiyang be0b8b4475
Merge 437eae89d6 into 7a9137d2e9
2026-09-15 19:34:48 +08:00
..
rollout_engine.py [fix] keep agent rollout token-aligned #850 2026-09-10 11:44:05 +08:00
train_agent.py Merge 437eae89d6 into 7a9137d2e9 2026-09-15 19:34:48 +08:00
train_distillation.py [feat] add MPS support for Apple Silicon 2026-08-14 01:26:49 +08:00
train_dpo.py [feat] add MPS support for Apple Silicon 2026-08-14 01:26:49 +08:00
train_full_sft.py Merge 437eae89d6 into 7a9137d2e9 2026-09-15 19:34:48 +08:00
train_grpo.py Merge 437eae89d6 into 7a9137d2e9 2026-09-15 19:34:48 +08:00
train_lora.py [feat] add MPS support for Apple Silicon 2026-08-14 01:26:49 +08:00
train_ppo.py Merge 437eae89d6 into 7a9137d2e9 2026-09-15 19:34:48 +08:00
train_pretrain.py Merge 437eae89d6 into 7a9137d2e9 2026-09-15 19:34:48 +08:00
train_tokenizer.py [update] minimind-3 2026-03-25 23:57:45 +08:00
trainer_utils.py [update] simplify safe math eval 2026-09-14 23:55:32 +08:00