jingyaogong / minimind

「大模型」3小时完全从0训练26M的小参数GPT,个人显卡即可推理训练!
https://jingyaogong.github.io/minimind
Apache License 2.0
2.7k stars 329 forks source link

Update 5-dpo_train.py #90

Open leoz9 opened 2 days ago

leoz9 commented 2 days ago

Modify the huggingface warehouse address to facilitate direct retrieval