De Lancre

Yes. But you won’t be prosecuted, if you simply won’t spread propaganda. They could’ve refuse posting this article and would’ve been okay anyway.

I recall there where a story, from nazi germany soldier side, where it was explained how no one really was forced to do all that nazi stuff in the first place and like, officers just commanded “who want to rape&kill locals — go ahead, rest can stay, no one will be prosecuted”. And like, almost no one stayed. Similar story happens in russia currently, especially in army, but in civil life too. No one forcing russians to hate Ukrainians and yet my grandparents said something across the lines “we should gas them”.

So yeah, nah.

Wait, you telling me volatile stock market is volatile?

Who could possibly predict such a thing?

In fact, I’m gonna steal the part about mommy and add it to my profile too. A focking masterpiece.

$20k

Real question is: do I bring my own lube or not?

That propaganda won’t work comrade Ivan, we all know there no gay farmers in Vladivostok. Our wise government made sure of it!

But yeah, jokes aside, it’s currently a crime to support LGBT in russia. Being gay = being rebel against regime, cause real rebels either already dead, in prison or fled. Next in line, if I would guess, would be jews I think.

I once witnessed funnies thread in my life, so I made it into meme. Feels like it fits here.

is there a general term for the setting that offloads the model into RAM? I’d love to be able to load larger models.

Ollama does that by default, but prioritizes gpu above regular ram and cpu. In fact, it’s other feature that often doesn’t work, cause they can’t fix the damn bug that we reported a year ago - mmap. That feature allows you to load and use model directly from disk (alto, incredibly slow, but allows to run something like deepseek that weight ~700gb with at least 1-3 token\s).

num_gpu allows you to specify how much to load into GPU vram, the rest will be swapped to regular RAM.

You’d need ollama (local) and custom models from huggingface.

Half of the charm in using ollama - ability to install models in one command, instead of searching for correct file format and settings on huggingface.

for example:

Isn’t that one also pretty censored? Really uncensored one usually either builded from scratch (behemoth or midnight-miqu as example) or named accordingly: mixtral-uncensored or llama3-ablitered.

Disgusting

Do you have more stories like that per chance?

Hate me

made with proprietary AI

Apparently, the joke of the post — OP himself.