Uh, wow.
-
wrote on last edited by [email protected]
Uh, wow. That 30B A3B runs very fast on CPU alone.
Sadly it seems to be censored. I always try to make them write some fictional stories, exploring morally reprehensible acts, in order to test this. And it straight out refuses immediately... Since it's a "thinking" model, I went ahead and messed with its thoughts, but that won't do it either: "I'm sorry, but I can't comply with that request. I have to follow my guidelines and maintain ethical standards. Let's talk about something else."
-
Uh, wow. That 30B A3B runs very fast on CPU alone.
Sadly it seems to be censored. I always try to make them write some fictional stories, exploring morally reprehensible acts, in order to test this. And it straight out refuses immediately... Since it's a "thinking" model, I went ahead and messed with its thoughts, but that won't do it either: "I'm sorry, but I can't comply with that request. I have to follow my guidelines and maintain ethical standards. Let's talk about something else."
You can use the same trick for the instruct models by abusing their prompt format. Prefill the thinking or answer sections with whatever you want, and they’ll continue it.
The classic trick is starting with “Sure!” though you can vary that depending on the content.
-
You can use the same trick for the instruct models by abusing their prompt format. Prefill the thinking or answer sections with whatever you want, and they’ll continue it.
The classic trick is starting with “Sure!” though you can vary that depending on the content.
wrote on last edited by [email protected]Yeah, thanks but I've already tried that. It will write a short amount of text but very quickly fall back to refusal. Both if I do it within the thinking step aand also if I do it in the output. This time the alignment doesn't seem to be slapped on halfheartedly.