I'm curious about the process. How such a thing (or any kind of model lobotomy) is done?
You can find the current state-of-art tool for censorship removal here: https://github.com/p-e-w/heretic
start here: https://huggingface.co/blog/mlabonne/abliteration
alt Hacker News
You can find the current state-of-art tool for censorship removal here: https://github.com/p-e-w/heretic