Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-i0-v2
like
0
Follow
DUAL Group
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
7311b52
phi-2-kto-i0-v2
/
runs
/
Oct01_01-14-23_gpu4-119-5
Commit History
Training in progress, step 120
cb6c7f2
verified
BraylonDash
commited on
Sep 30
Training in progress, step 100
012d24e
verified
BraylonDash
commited on
Sep 30
Training in progress, step 80
50f3b21
verified
BraylonDash
commited on
Sep 30
Training in progress, step 60
cdeaecb
verified
BraylonDash
commited on
Sep 30