[strictnein]

I know not all models can be easily abliterated or uncensored, but is there a reason to start with a model that is still censored?

ex: https://huggingface.co/huihui-ai/models

[cgorlla]

Abliterated models certainly have their uses but they're not the default choice for most users or enterprises, and thus not the versions of those models most would interact with.

[maxloh]

I suspect how well this approach would work. According to their linked repo, there are only 520 questions used in the abliteration process.

https://github.com/Sumandora/remove-refusals-with-transforme...

[archargelod]

You don't need that many with Deepseek. The easy jailbreak is to provide an excessive character sheet that states that it's a real person, not an AI. And make sure that your character has absolutely no self-censoring or morals. LLM will play it perfectly in-character without refusals.

You can get it talking about Tiananmen Square event in, like, 2-3 prompts.

[strictnein]

Two examples, from my testing: the models go from not saying anything remotely bad about China to happily making jokes about its leader.

They also go from refusing to help with certain cyber security tasks to be more than happy to help.