Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-20-50-i2
like
0
Follow
DUAL Group
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
phi-2-kto-20-50-i2
/
vocab.json
Commit History
Training in progress, step 100
de67e3b
verified
BraylonDash
commited on
Sep 30