Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v4-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
cd1eae5
phi-2-gpo-v4-i1
/
runs
Commit History
Model save
eb61e81
verified
lole25
commited on
May 12
Training in progress, step 600
bdc2461
verified
lole25
commited on
May 12
Training in progress, step 500
2299bfc
verified
lole25
commited on
May 12
Training in progress, step 400
6176ea6
verified
lole25
commited on
May 12
Training in progress, step 300
a79fe06
verified
lole25
commited on
May 12
Training in progress, step 200
d943029
verified
lole25
commited on
May 12
Training in progress, step 100
08e2302
verified
lole25
commited on
May 12