Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-renew2-b0.001-i1
like
0
Follow
DUAL Group
2
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-renew2-b0.001-i1
/
runs
1 contributor
History:
3 commits
BraylonDash
Model save
47c7a97
verified
7 months ago
Apr17_17-08-49_gpu4-119-5
Training in progress, step 200
7 months ago
Apr22_14-25-39_gpu4-119-5
Model save
7 months ago