Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-irepo-chatml-v2-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
main
phi-2-irepo-chatml-v2-i0
/
adapter_model.safetensors
Commit History
Model save
c30e760
verified
lole25
commited on
May 19
Training in progress, step 1200
fa851b1
verified
lole25
commited on
May 19
Training in progress, step 1100
c730b08
verified
lole25
commited on
May 19
Training in progress, step 1000
c1320c8
verified
lole25
commited on
May 19
Training in progress, step 900
1280977
verified
lole25
commited on
May 19
Training in progress, step 800
a0adc30
verified
lole25
commited on
May 19
Training in progress, step 700
b5b9944
verified
lole25
commited on
May 19
Training in progress, step 600
21ff62d
verified
lole25
commited on
May 19
Training in progress, step 500
409a6a9
verified
lole25
commited on
May 19
Training in progress, step 400
390fd3a
verified
lole25
commited on
May 19
Training in progress, step 300
a2ebf0a
verified
lole25
commited on
May 19
Training in progress, step 200
18d3d0c
verified
lole25
commited on
May 19
Training in progress, step 100
03be343
verified
lole25
commited on
May 19