minimind/trainer
Walle1999 f5b6d18c3d
Merge 450885c0d5 into c367572702
2026-09-14 22:28:08 +08:00
..
rollout_engine.py [fix] keep agent rollout token-aligned #850 2026-09-10 11:44:05 +08:00
train_agent.py Merge 450885c0d5 into c367572702 2026-09-14 22:28:08 +08:00
train_distillation.py feat: 添加 macOS Metal (MPS) 设备支持 2026-07-06 10:54:20 +08:00
train_dpo.py feat: 添加 macOS Metal (MPS) 设备支持 2026-07-06 10:54:20 +08:00
train_full_sft.py Merge 450885c0d5 into c367572702 2026-09-14 22:28:08 +08:00
train_grpo.py Merge 450885c0d5 into c367572702 2026-09-14 22:28:08 +08:00
train_lora.py feat: 添加 macOS Metal (MPS) 设备支持 2026-07-06 10:54:20 +08:00
train_ppo.py Merge 450885c0d5 into c367572702 2026-09-14 22:28:08 +08:00
train_pretrain.py Merge 450885c0d5 into c367572702 2026-09-14 22:28:08 +08:00
train_tokenizer.py [update] minimind-3 2026-03-25 23:57:45 +08:00
trainer_utils.py feat: 添加 macOS Metal (MPS) 设备支持 2026-07-06 10:54:20 +08:00