Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-dpo-renew1
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
783733b
phi-2-dpo-renew1
/
tokenizer.json
Commit History
Training in progress, step 100
9111d50
verified
BraylonDash
commited on
Apr 9