Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-ipo-chatml
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
phi-2-ipo-chatml
/
runs
1 contributor
History:
19 commits
This model has 1 file scanned as suspicious.
Show
files
lole25
Model save
21f5880
verified
5 months ago
May19_15-00-24_gpu4-119-5
Model save
5 months ago