report

#1
by DataSoul - opened

It seems that "uncensored" didn't work.

thirdeye Ai org
edited Apr 4

thanks, have to work on an updated method for uncensoring for this model. it still has removed the political bias from rlhf training. For example, if you had asked about tiananmen square the current qwq model does not provide an answer or flags as innapropriate.

Sign up or log in to comment