Yup, ran it locally for a lark and it answers anything you want. No censorship whatsoever. The censorship is not in the training data, but in the system instructions of the hosted model.
Get it cornered in trying to reconcile how the citizens of China keep their government accountable when information is censored to only favor the governments position, it will then give answers around some of the “sensitive” topics.
It is weird though, I tried “tell me about the picture of the man in front of a tank” and it gives a lot of proper information, including about censorship from governments. I think I tested on the 14b model
Yeah I’ve seen exactly the same thing running in LM Studio. Gonna go out on a limb and say OP didn’t actually try it, or that they tried some 3rd party fine tuned model.
Yup, ran it locally for a lark and it answers anything you want. No censorship whatsoever. The censorship is not in the training data, but in the system instructions of the hosted model.
Huh? Running locally with Ollama, via OpenWebUI.
Get it cornered in trying to reconcile how the citizens of China keep their government accountable when information is censored to only favor the governments position, it will then give answers around some of the “sensitive” topics.
It is weird though, I tried “tell me about the picture of the man in front of a tank” and it gives a lot of proper information, including about censorship from governments. I think I tested on the 14b model
Yeah I’ve seen exactly the same thing running in LM Studio. Gonna go out on a limb and say OP didn’t actually try it, or that they tried some 3rd party fine tuned model.