this post was submitted on 22 Nov 2024
21 points (100.0% liked)

Technology

998 readers
111 users here now

A tech news sub for communists

founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] yogthos@lemmygrad.ml 12 points 1 month ago (2 children)

It's a way to run models on your local machine and provide an API that's compatible with OpenAI that can be used by apps that normally rely on that.

[–] Kultronx@lemmygrad.ml 2 points 1 month ago (1 children)

what is the advantage of doing something like this? i am a layperson

[–] yogthos@lemmygrad.ml 6 points 1 month ago (1 children)

Privacy and ability to generate content you want. Using commercial services like OpenAI means your data is sent to their servers, so anything you query is known to the company, and their models are often restricted in terms of content they will allow you to generate. For example, Google's Gemini will refuse to deal with many political subjects.

[–] Kultronx@lemmygrad.ml 2 points 1 month ago (1 children)

is there a guide how to use this? i downloaded the zip file but i have no idea what to do with it

[–] yogthos@lemmygrad.ml 2 points 1 month ago (1 children)

Oh haha it's a bit tricky if you're not technical, the easiest way is to use docker, but that's a whole thing of itself. If you want just an app you can run, one of these is easier to get going with

[–] Kultronx@lemmygrad.ml 2 points 1 month ago

Thanks for the tips, I will check those out

[–] JucheStalin@lemmygrad.ml 2 points 1 month ago (1 children)

Hm so it downloads fixed models and works without an internet connection? Interesting.

[–] yogthos@lemmygrad.ml 2 points 1 month ago (1 children)

Right, you can download any publicly available model and run it without using the internet. Caveat is that you do need a relatively fast machine to make it performant.

[–] FuckBigTech347@lemmygrad.ml 3 points 1 month ago (1 children)

For reference the oldest card I have that Vulkan supports is an RX 560 that I bought in 2017 (I'm on GNU/Linux w/ amdgpu and the RADV mesa driver aka. "The Default"). Most medium models on it run at around 6 - 10 Tokens/s. Some crawl to below 6 Tokens/s though and become slower the longer the answer they output is, probably because parts of the model is in RAM since that card has "only" 4GB of VRAM. Models that fully fit in VRAM are a lot faster.

[–] KrasnaiaZvezda@lemmygrad.ml 1 points 1 month ago

I can run Qwen 2.5 Coder 14B Q4_k_m on CPU at only a little above 1 t/s but it's worth it when I just want to have it look at whatever code I have without disclosing it with corporations that don't have my best interests in mind.