Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v5-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
xet
Metrics
Training metrics
Community
Use this model
main
phi-2-gpo-v5-i1
/
runs
57.4 kB
1 contributor
History:
6 commits
lole25
Model save
9b945ab
verified
over 1 year ago
May12_15-56-52_gpu4-119-5
Training in progress, step 300
over 1 year ago
May12_19-04-40_gpu4-119-5
Model save
over 1 year ago