Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-irepo-chatml-v2-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-v2-i0
/
runs
1 contributor
History:
13 commits
lole25
Model save
c30e760
verified
4 months ago
May19_10-48-24_gpu4-119-5
Training in progress, step 100
4 months ago
May19_10-51-36_gpu4-119-5
Training in progress, step 100
4 months ago
May19_10-53-15_gpu4-119-5
Model save
4 months ago