minimind/trainer
Corey52HZ 00da95959f
Merge 655d4705eb into f659b55761
2026-09-24 23:33:15 +08:00
..
rollout_engine.py [fix] keep agent rollout token-aligned #850 2026-09-10 11:44:05 +08:00
train_agent.py Merge 655d4705eb into f659b55761 2026-09-24 23:33:15 +08:00
train_distillation.py Merge 655d4705eb into f659b55761 2026-09-24 23:33:15 +08:00
train_dpo.py Merge 655d4705eb into f659b55761 2026-09-24 23:33:15 +08:00
train_full_sft.py Merge 655d4705eb into f659b55761 2026-09-24 23:33:15 +08:00
train_grpo.py Merge 655d4705eb into f659b55761 2026-09-24 23:33:15 +08:00
train_lora.py Merge 655d4705eb into f659b55761 2026-09-24 23:33:15 +08:00
train_ppo.py Merge 655d4705eb into f659b55761 2026-09-24 23:33:15 +08:00
train_pretrain.py Merge 655d4705eb into f659b55761 2026-09-24 23:33:15 +08:00
train_tokenizer.py [fix] train_tokenizer 读预训练语料时产出 0 条文本,静默训出空词表 2026-09-20 10:33:51 +08:00
trainer_utils.py [update] simplify safe math eval 2026-09-14 23:55:32 +08:00