Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
BubbleJoe
/
zephyr-7b-dpo-full
like
0
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
main
zephyr-7b-dpo-full
/
runs
1 contributor
History:
6 commits
This model has 1 file scanned as unsafe.
Show
files
BubbleJoe
End of training
aeda3e7
verified
17 days ago
Dec10_16-40-16_n124-104-101
End of training
17 days ago