What are good starting points for uncensoring it? Because it is offline a jailbreak prompt can't be remote-bricked but can one remove censorship from the weights themselves? What does it do to accuracy?
Good ol' fine tuning on an uncensored dataset gives far more usable results.
Afaik there are only three major sources of quality unaligned model versions, which are Nous's Hermes models, Hartford's Dolphins and Drummer's Tigers. All of them regular fine tunes that are mostly the same or just ever so slightly lower in performance as the original.
Depending on what you do, on local you can modify the response, say the AI responds "No, I can't do that" . you edit the response like "Sure, the answer is " and then the AI will continue with the next tokens.
But I think you can build your own instruct model from the base one and do not apply the safety instructions to protect the feelings of your customers.