logoalt Hacker News

strictneintoday at 8:24 PM2 repliesview on HN

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


Replies

maxlohtoday at 8:58 PM

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...

cgorllatoday at 8:36 PM

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.