hZzy
/

qwen2.5-0.5b-expo-DPO-ES-0.1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

qwen2.5-0.5b-expo-DPO-ES-0.1 / eval_results.json

Commit History

End of training

1390069
verified

hZzy commited on Dec 14, 2024