minimind/trainer
yanghw116 efd8073450 adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
..
rollout_engine.py [fix] inference bug 2026-05-03 20:48:48 +08:00
train_agent.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
train_distillation.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
train_dpo.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
train_full_sft.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
train_grpo.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
train_lora.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
train_ppo.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
train_pretrain.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00
train_tokenizer.py [update] minimind-3 2026-03-25 23:57:45 +08:00
trainer_utils.py adapt to Ascend NPU 2026-05-18 18:36:14 +08:00