Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-test-iter-0

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
phi-2-gpo-test-iter-0 / runs
  • 1 contributor
 History: 2 commits
BraylonDash's picture
BraylonDash
Model save
23d0840 verified