Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v9-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-v9-i1
/
runs
1 contributor
History:
10 commits
lole25
Model save
cd72168
verified
10 months ago
May13_01-13-05_gpu4-119-5
Model save
10 months ago
May13_09-10-25_gpu4-119-5
Model save
10 months ago