Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v16-i1
like
0
Follow
DUAL Group
2
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-gpo-v16-i1
/
runs
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
lole25
Model save
6fbc539
verified
over 1 year ago
May13_12-49-19_ip-10-192-12-104
Model save
over 1 year ago
