Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-renew-30k-i1
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
main
phi-2-gpo-newSFT-b0.001-renew-30k-i1
/
runs
1 contributor
History:
12 commits
BraylonDash
Model save
0329836
verified
3 months ago
May14_21-50-04_gpu4-119-5
Training in progress, step 200
3 months ago
May15_00-56-30_gpu4-119-5
Model save
3 months ago