heretic

As a completely one person, single sample anecdote, the 'heretic' uncensored Q8 GGUF variants several people have published of Qwen 3.5-122, 3.6-27B and 3.6-35B-A3B will very happily discuss just about any controversial topic that the CCP hates. Including lots of things that would get you thrown into prison if you published them in Mandarin on the domestic Chinese internet. https://github.com/p-e-w/heretic As a side note on this, if you see the reference in the screenshot in the link above to the harmful behaviors prompt set, these are all in English: https://huggingface.co/datasets/mlabonne/harmful_behaviors You could likely further de-censor a model by having a set of 'test' prompts in native Mandarin, Cantonese or really just about any other language. I don't speak any Chinese languages so I don't know if the published 'heretic' GGUF f

You can find the current state-of-art tool for censorship removal here: https://github.com/p-e-w/heretic

It's an open-weight model so it literally doesn't matter whether it refuses by default or not, because it's pretty trivial to uncensor[1] any open-weight model and make it not refuse. [1]: https://github.com/p-e-w/heretic

Once we've got the weights, anything is possible. https://github.com/p-e-w/heretic

What censorship? ;) https://github.com/p-e-w/heretic