DUAL-GPO
/

phi-2-dpo-renew1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-dpo-renew1 / README.md

Commit History

End of training

5f0ee0b
verified

BraylonDash commited on Apr 9

Model save

783733b
verified

BraylonDash commited on Apr 9