Comment by strictnein
2 hours ago
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?
2 hours ago
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?
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.
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...