Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-20-40-i1
like
0
Follow
DUAL Group
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
phi-2-kto-20-40-i1
/
runs
1 contributor
History:
26 commits
This model has 1 file scanned as suspicious.
Show
files
BraylonDash
Model save
d76bbc4
verified
30 days ago
Sep29_02-35-31_gpu4-119-5
Model save
30 days ago