Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v16-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-v16-i1
Commit History
End of training
3cb14bf
verified
lole25
commited on
May 13
Model save
6fbc539
verified
lole25
commited on
May 13
Training in progress, step 200
6b8fe7a
verified
lole25
commited on
May 13
Training in progress, step 100
d08405e
verified
lole25
commited on
May 13
initial commit
b5f7f2b
verified
lole25
commited on
May 13