(Copied from Slack DM) If finetuning to remove censorship causes a shift in parameters that is small relative to the quantization step size, then an additional quantization step will simply undo finetuning (reverting to censorship).
It’d be interesting to see the distribution of absolute changes in parameter values induced by finetuning!
(Copied from Slack DM) If finetuning to remove censorship causes a shift in parameters that is small relative to the quantization step size, then an additional quantization step will simply undo finetuning (reverting to censorship).
It’d be interesting to see the distribution of absolute changes in parameter values induced by finetuning!