Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-dpo-chatml-lora-10k-30k-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
18011e1
phi-2-dpo-chatml-lora-10k-30k-i1
/
runs
/
Sep10_19-37-45_gpu4-119-5
Commit History
Model save
18011e1
verified
BraylonDash
commited on
Sep 10
Training in progress, step 600
2066bc3
verified
BraylonDash
commited on
Sep 10
Training in progress, step 500
7e35958
verified
BraylonDash
commited on
Sep 10