Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-irepo-chatml-i0
like
0
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
main
phi-2-irepo-chatml-i0
/
runs
1 contributor
History:
24 commits
lole25
Model save
7825290
verified
about 2 months ago
May19_01-58-09_gpu4-119-5
Training in progress, step 100
about 2 months ago
May19_02-03-02_gpu4-119-5
Model save
about 2 months ago