Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-v7-lightai-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-v7-lightai-i1
/
runs
1 contributor
History:
4 commits
BraylonDash
Model save
74f0d63
verified
3 months ago
May15_02-04-22_ip-10-192-12-69
Training in progress, step 200
3 months ago
May15_04-09-53_ip-10-192-15-18
Model save
3 months ago