When I’m looking for something, and find it after searching, then I put it back in the first place I looked. Because that is apparently the most logical place where I expect it to be, and that is also where I would likely look for it next time.
Those are the tightest shorts I’ve ever seen. He does have amazing legs though.
They switched off image generation after these issues, so it (correctly) said that it couldn’t generate images at the time.
Fair enough. They only have to convince the self help books crowd 🙃
Yeah, if you already have it then it’s not really an extra cost. But the smaller models perform less well and less reliably.
In order to write a book that’s convincing enough to fool at least some buyers, I wouldn’t expect a Llama2 7B to do the trick, based on what I see in my work (ML engineer). But even at work, I run Llama2 70B quantized at most, not the full size one. Full size unquantized requires 320 GPU vram, and that’s just quite expensive (even more so when you have to rent it from cloud providers).
Although if you already have a GPU that size at home, then of course you can run any LLM you like :)
For free? The larger models require a lot of hardware.
Xi sells Xi shells by the sea shore
I started watching, realized that vomiting was going to be a plot device, and noped out. I mostly watch shows during meals. Who wants to watch people vomit? Disgusting .