Koboldcpp should allow you to run much larger models with a little bit of ram offloading. There’s a fork that supports rocm for AMD cards: https://github.com/YellowRoseCx/koboldcpp-rocm

Make sure to use quantized models for the best performace, q4k_M being the standard.

9/11 killed more in one day than mass shootings have in the last 20+ years. https://www.statista.com/statistics/811504/mass-shooting-victims-in-the-united-states-by-fatalities-and-injuries/

a thorough investigation is planned beforehand in order to find out how Huawei was able to produce an advanced smartphone so quickly without relying on global supply chains

There’s no way a country of 1 billion people which already manufactures most of the world’s electronics could have possibly produced complex electronics.

What a shitty investigator. It took the new one less than a week to figure it out. I can’t see how this could have possibly happened for any reason other than malice or gross incompetence. Either way both the original investigator and the rest of the department need to be looked into.

4x was a bit too aggressive I guess

Gamers truly are the most persecuted class.

I’ve used the tplink ones that they’re using and they’ve been pretty solid. I can’t say how they’d fare in a 24/7 setup though since they’re not really intended for that.

Not necessarily. The same images would be consumed by both groups, there’s no need for new data. This is exactly what artists are afraid of. Image generation increases supply dramatically without increasing demand. The amount of data required is also pretty negligible. Maybe a few thousand images.

And what does that have to do with the production of csam? In the example given the data already existed, they’ve just been more aggressive about collecting it.

Real material is being used to train some models, but sugesting that it will encourage the creation of more “data” is silly. The amount required to finetune a model is tiny compared to the amount that is already known to exist. Just like how regular models haven’t driven people to create even more data to train on.

It could be used to create a reward model like what is done right now with RLHF.

Section 5 of their privacy policy explicitly states that they don’t.