hZzy
/

qwen2.5-0.5b-expo-DPO-ES-1000

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

qwen2.5-0.5b-expo-DPO-ES-1000 / eval_results.json

Commit History

End of training

2f5a5e6
verified

hZzy commited on Dec 16, 2024