Where can I get a sub 400 AMD card with 26 GB of VRAM?

Have you tried Matrix?

LLMs are statistical word association machines. Or tokens more accurately. So if you tell it to not make mistakes, it’ll likely weight the output towards having validation, checks, etc. It might still produce silly output saying no mistakes were made despite having bugs or logic errors. But LLMs are just a tool! So use them for what they’re good at and can actually do, not what they themselves claim they can do lol.

OpenWebUI connected tabbyUI’s OpenAI endpoint. I will try reducing temperature and seeing if that makes it more accurate.

Context was set to anywhere between 8k and 16k. It was responding in English properly, and then about halfway to 3/4s of the way through a response, it would start outputting tokens in either a foreign language (Russian/Chinese in the case of Qwen 2.5) or things that don’t make sense (random code snippets, improperly formatted text). Sometimes the text was repeating as well. But I thought that might have been a template problem, because it seemed to be answering the question twice.

Otherwise, all settings are the defaults.

I tried it with both Qwen 14b and Llama 3.1. Both were exl2 quants produced by bartowski.

Perplexica works. It can understand ollama and custom OpenAI providers.

Super useful guide. However after playing around with TabbyAPI, the responses from models quickly become jibberish, usually halfway through or towards the end. I’m using exl2 models off of HuggingFace, with Q4, Q6, and FP16 cache. Any tips? Also, how do I control context length on a per-model basis? max_seq_len in config.json?

Seems to be the only necessary thing in my case! Thanks.

Yeah I definitely have the default GTK chooser. Guess I have some config playing to do later.

Can you explain a bit more about this and how to configure it? When I use FF on gnome, the save dialogue just looks like other dialogues?

Not necessarily. While of course in many many cases, open source is a volunteer effort, there’s usually some implicit transaction going on. Whether that’s improving the software for yourself and passing that on to others, being a business and improving a library or something you use that helps your project generate revenue, or even a straight up commercial transaction.

But in all these cases, the open source project can be taken by you (or others) and you can do whatever you want with it. In the case of Winamp here, you cannot do any of that. It would be different if they were paying for contributions. But they’re not, so.

They basically want free labor.

Depends on the continuity and who’s writing it, but often yes. He was notably portrayed this way in the Justice League cartoon.

Doesn’t gnome already have this?

Cygwin ftw

Lol. Git itself can act as a server over the git protocol. Might have been easier 🤪

There’s plenty of git forges that aren’t GitHub. Git itself has nothing to do with central servers and can theoretically be used in a completely decentralized manner.

Definitely a good way to do it. Photoprism supports uploading to WebDAV for sharing. Could front a CDN upload with a web dav server 🤔

Yeah, that sounds like a good idea. I am using photoprism for photo management. It doesn’t really support S3 or any CDN. You could use a fuse filesystem or something, but it’s very slow.