Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-i0
like
0
Follow
DUAL Group
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
phi-2-kto-i0
/
README.md
Commit History
End of training
f8ca687
verified
BraylonDash
commited on
Sep 29
Model save
b75b9f5
verified
BraylonDash
commited on
Sep 29
End of training
ec53d03
verified
BraylonDash
commited on
Sep 28
Model save
db0f377
verified
BraylonDash
commited on
Sep 28