Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-test-longest-iter-v1-3
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
mit
Model card
Files
Files and versions
Community
Use this model
main
phi-2-gpo-test-longest-iter-v1-3
Commit History
End of training
40174a2
verified
BraylonDash
commited on
Mar 26
Model save
f36a8d3
verified
BraylonDash
commited on
Mar 26
Training in progress, step 200
7827738
verified
BraylonDash
commited on
Mar 26
initial commit
b499326
verified
BraylonDash
commited on
Mar 26