DUAL-GPO
/

phi-2-kto-i0

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-kto-i0 / runs /Sep29_16-42-50_gpu4-119-5 /events.out.tfevents.1727592217.gpu4-119-5.913570.0

Commit History

Model save

b75b9f5
verified

BraylonDash commited on 2 days ago