Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-i0
like
0
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
/
runs
/
Sep29_16-42-50_gpu4-119-5
1 contributor
History:
1 commit
BraylonDash
Model save
b75b9f5
verified
2 days ago
events.out.tfevents.1727592217.gpu4-119-5.913570.0
5.87 kB
LFS
Model save
2 days ago