Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-u3-i1
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
9eb75df
zephyr-7b-gpo-u3-i1
Commit History
Training in progress, step 1200
9eb75df
verified
lole25
commited on
Apr 8
Training in progress, step 1100
dd21b77
verified
lole25
commited on
Apr 8
Training in progress, step 1000
7d6ee68
verified
lole25
commited on
Apr 8
Training in progress, step 900
b6b7f02
verified
lole25
commited on
Apr 8
Training in progress, step 800
6a903ad
verified
lole25
commited on
Apr 8
Training in progress, step 700
52d0327
verified
lole25
commited on
Apr 8
Training in progress, step 600
2d28ec6
verified
lole25
commited on
Apr 8
Training in progress, step 500
56e64ca
verified
lole25
commited on
Apr 8
Training in progress, step 400
5aaffd7
verified
lole25
commited on
Apr 8
Training in progress, step 300
f93c786
verified
lole25
commited on
Apr 8
Training in progress, step 200
ee1dd43
verified
lole25
commited on
Apr 8
Training in progress, step 100
a5e83fd
verified
lole25
commited on
Apr 8
initial commit
36e80ab
verified
lole25
commited on
Apr 8