minimind/trainer
Walle1999 eb81692c7e
Merge f6f56f0a7d into 3f1a7cc25b
2026-06-01 17:52:32 +08:00
..
rollout_engine.py [fix] inference bug 2026-05-03 20:48:48 +08:00
train_agent.py Merge f6f56f0a7d into 3f1a7cc25b 2026-06-01 17:52:32 +08:00
train_distillation.py Merge f6f56f0a7d into 3f1a7cc25b 2026-06-01 17:52:32 +08:00
train_dpo.py Merge f6f56f0a7d into 3f1a7cc25b 2026-06-01 17:52:32 +08:00
train_full_sft.py Merge f6f56f0a7d into 3f1a7cc25b 2026-06-01 17:52:32 +08:00
train_grpo.py Merge f6f56f0a7d into 3f1a7cc25b 2026-06-01 17:52:32 +08:00
train_lora.py Merge f6f56f0a7d into 3f1a7cc25b 2026-06-01 17:52:32 +08:00
train_ppo.py Merge f6f56f0a7d into 3f1a7cc25b 2026-06-01 17:52:32 +08:00
train_pretrain.py Merge f6f56f0a7d into 3f1a7cc25b 2026-06-01 17:52:32 +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 2026-05-24 10:52:56 +08:00