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.

That is exactly the plan.

You can right click the URL bar for sites that support the OpenSearch XML standard. Which I guess is what they wanted to replace it with. But I don’t really know why they removed the button to a about: config setting. Could at least be a checkbox or something to enable.

Returns the add custom search engine button. Which for some reason, has been hidden by default.

Anyone have any suggestions for bulk options in the Netherlands?

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

The only problem I really have, is context size. It’s harder to get larger than 8k context size and maintain decent generation speed with 16 GB of VRAM and 16 GB of RAM. Gonna get more RAM at some point though, and hope ollama/llamacpp gets better at memory management. Hopefully the distributed running from llamaccp ends up in ollama.

I do have a local setup. Not powerful enough to run Mixtral 8x22b, but can run 8x7b (albeit quite slowly). Use it a lot.

No trying to get around anything. No funny instructions like my grandma singing a lullaby about illegal activities. Just using instructions to tell a story. Even things like having a superhero in a fight is enough to trigger this. Also doesn’t explain why regen makes it continue.

https://sh.itjust.works/c/localllama