hZzy
/

qwen2.5-0.5b-expo-DPO-ES2-0.1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

qwen2.5-0.5b-expo-DPO-ES2-0.1 / eval_results.json

Commit History

End of training

f4966a5
verified

hZzy commited on 20 days ago