Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v13-i1
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
19322b0
phi-2-gpo-v13-i1
/
runs
1 contributor
History:
18 commits
lole25
Model save
19322b0
verified
6 months ago
May13_12-47-35_gpu4-119-5
Model save
6 months ago