Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-v10-lightai-i1
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-newSFT-b0.001-v10-lightai-i1
Commit History
End of training
8f2a4c2
verified
BraylonDash
commited on
May 16
Model save
4843c21
verified
BraylonDash
commited on
May 16
Training in progress, step 300
8ee7221
verified
BraylonDash
commited on
May 16
Training in progress, step 100
7e3e467
verified
BraylonDash
commited on
May 16
initial commit
84c5dc1
verified
BraylonDash
commited on
May 15