It’s enough to run quantized versions of the distilled r1 model based on Qwen and Llama 3. Don’t know how fast it’ll run though.

For stuff like that, it’s best to have an auto formatter like checkstyle or something.

Had a team lead that kept requesting nitpicky changes, going in a FULL CIRCLE about what we should change or not, to the point that changes would take weeks to get merged. Then he had the gall to say that changes were taking too long to be merged and that we couldn’t just leave code lying around in PRs.

Jesus fucking Christ.

There’s a reason that team imploded…

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?

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.

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.

Depends on the language. There is no explicit typing in JavaScript, for example. That’s why Typescript was invented.

Didn’t they contribute networking stuff?

It used to be open source, then it went completely closed. As mentioned, Organic Maps is the fork that is the continuation of the GPL app.

Tasks.org syncs with various services. Those services may or may not have a web UI. I use it with Nextcloud tasks, which has a serviceable web UI.

If you download it from Fdroid, it doesn’t have a subscription. And it has all the features unlocked.