Hugging Face's logo

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

PEFT
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Community
phi-2-dpo-test-iter-0 / tokenizer_config.json

Commit History

Training in progress, step 300
086f5b8
verified

BraylonDash commited on