Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-lightning-v2-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
main
phi-2-gpo-lightning-v2-i1
Commit History
End of training
2a21ecd
verified
lole25
commited on
May 12
Model save
9f96a1e
verified
lole25
commited on
May 12
Training in progress, step 100
2295211
verified
lole25
commited on
May 12
initial commit
9227e77
verified
lole25
commited on
May 12