Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-iter-0
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
mit
Model card
Files
Files and versions
Community
Use this model
b047f45
phi-2-gpo-iter-0
Commit History
Model save
b047f45
verified
lole25
commited on
Mar 20
End of training
514b203
verified
lole25
commited on
Mar 20
Model save
cbca9fa
verified
lole25
commited on
Mar 20
Training in progress, step 100
b3fdd14
verified
lole25
commited on
Mar 20
End of training
b7f9dd9
verified
lole25
commited on
Mar 20
Model save
68b05e6
verified
lole25
commited on
Mar 20
initial commit
e9f031c
verified
lole25
commited on
Mar 20