Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Katayoon
/
CDPO-Zephyr-7B-iter-3
like
0
Safetensors
updated
original
mistral
alignment-handbook
trl
dpo
Generated from Trainer
License:
mit
Model card
Files
Files and versions
Community
main
CDPO-Zephyr-7B-iter-3
Commit History
End of training
073afd5
verified
Katayoon
commited on
Sep 27, 2024
Model save
ad91a1b
verified
Katayoon
commited on
Sep 27, 2024
initial commit
11451aa
verified
Katayoon
commited on
Sep 27, 2024