Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v10-i1
like
0
Follow
DUAL Group
2
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
f890a87
phi-2-gpo-v10-i1
/
README.md
Commit History
End of training
f890a87
verified
lole25
commited on
May 12
Model save
89df2d4
verified
lole25
commited on
May 12
End of training
62b102c
verified
lole25
commited on
May 12
Model save
c35c185
verified
lole25
commited on
May 12