Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-test-longest-iter-v1-0
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
44236d0
phi-2-gpo-test-longest-iter-v1-0
/
training_args.bin
Commit History
Training in progress, step 200
44236d0
verified
BraylonDash
commited on
Mar 26