DUAL-GPO
/

phi-2-dpo-chatml-lora-0k-20k-i2

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-dpo-chatml-lora-0k-20k-i2 / trainer_state.json

Commit History

Model save

a0c1f08
verified

BraylonDash commited on Sep 13, 2024