mlabonne's picture
Update README.md
a9b9230 verified
|
raw
history blame
636 Bytes
metadata
library_name: transformers
license: other

Daredevil-8B-abliterated

Abliterated version of mlabonne/Daredevil-8B using failspy's notebook.

It based on the technique described in the blog post "Refusal in LLMs is mediated by a single direction".

Thanks to Andy Arditi, Oscar Balcells Obeso, Aaquib111, Wes Gurnee, Neel Nanda, and failspy.

⚡ Quantization