Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v18-i1
like
0
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
4ff24db
phi-2-gpo-v18-i1
/
runs
1 contributor
History:
1 commit
lole25
Training in progress, step 100
4ff24db
verified
5 months ago
May14_04-41-15_gpu4-119-5
Training in progress, step 100
5 months ago