projectmoon

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?

That is exactly the plan.

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

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?

Word can in fact open odt files. It was added quite a long time ago. Don’t know how good the compatibility is, though

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

I use Simple Login a lot too. But be careful, as some sites reject these email addresses. Or in the case of Shell Recharge, change their business logic to reject the email addresses without letting me change to another email … Haven’t been able to log in for months 🙃

Didn’t they contribute networking stuff?

It’s because OsmAnd has some serious issues searching for certain addresses. It’s not an OpenStreetMaps problem, but an issue with the app. Organic Maps is better. Magic Earth is even better. Note: only talking about address searching. OsmAnd still has a ton of other useful features.

If I need to use OsmAnd, sometimes I’ll copy the plus code from Google Maps, as that translates to GPS coordinates.

Unfortunately, it doesn’t look like that BBC experiment is going well. They’ve barely posted anything, relative to what they could post. They should set up their systems to auto-post to Mastodon when they post to Twitter or where ever else.