Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-dpo-test-iter-0
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-dpo-test-iter-0
Commit History
End of training
704bb29
verified
BraylonDash
commited on
Mar 28
Model save
9237faa
verified
BraylonDash
commited on
Mar 28
Training in progress, step 300
086f5b8
verified
BraylonDash
commited on
Mar 28
initial commit
bccd77f
verified
BraylonDash
commited on
Mar 28