projectmoon

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

Have you tried Matrix?

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?

Doesn’t gnome already have this?

Cygwin ftw

I use a Misskey fork for micro blogging and I can’t even get Lemmy posts to load. The profiles of communities do, but that’s it.

Ah right. What I really meant to ask was if it can do protocols other than http.

Which I don’t think it can…

Are you able to tunnel ports other than 80 and 443 through Cloudflare?

The fork was originally created because upstream NewPipe elected not to include sponsor block functionality.

Don’t think the snap is an official Mozilla package.

There’s a lava flow on the other side of the barrier that was built. It’s inching into the new construction at the edge of the town and has already consumed one house. Probably it will keep going, possibly to the harbor.

Will existing projects have to adapt their codebases to work with ActivityPods? I assume yes.

So is there a way to follow someone on Threads now? Or at least get one’s instance to load a post? Where are the details of this beyond Zuckerberg’s post?