alt Hacker NewsI didn't use this tool, but I did try out abliterated versions of Gemma and yes, it lost about 100% of it's ability to produce a useful response once I did it
I didn't use this tool, but I did try out abliterated versions of Gemma and yes, it lost about 100% of it's ability to produce a useful response once I did it
the default heretic with only 100 samples isn't very good, you really need your own, larger dataset to do a proper abliteration. the best abliteration roughly matches a very careful decensor SFT