Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-i0
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
b75b9f5
phi-2-kto-i0
/
runs
/
Sep28_17-55-57_gpu4-119-5
1 contributor
History:
9 commits
BraylonDash
Training in progress, step 1220
00d8246
verified
5 months ago
events.out.tfevents.1727510204.gpu4-119-5.4042856.0
Safe
17.6 kB
LFS
Training in progress, step 1220
5 months ago