That just isn't true: If the model and it’s training process is publicly available, you can remove the censorship: https://ollama.com/huihui_ai/deepseek-r1-abliterated:70b

Reply to this note

Please Login to reply.

Discussion

does that one waste time thinking?

r1 is the reasoning one, yes.

Oh, neat, that's quite good actually

It would only be honest to admit that the implementations of stripping out some of the censorship/safeguards are still rather primitive and they don’t seem to work all that well with deepseek r1 due to the way the model works internally: https://github.com/Sumandora/remove-refusals-with-transformers/issues/3#issuecomment-2622722682

So far most of the good models were stripped of their restrictions at some point.