Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
BraylonDash
/
phi-2-gpo-test-iter-0
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
05536a6
phi-2-gpo-test-iter-0
/
runs
/
Mar19_14-44-38_Braylon
1 contributor
History:
1 commit
BraylonDash
Model save
d232254
verified
8 months ago
events.out.tfevents.1710820019.Braylon.30099.0
Safe
5.79 kB
LFS
Model save
8 months ago