LocalLLaMA

2878 readers

34 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

founded 2 years ago

MODERATORS

[email protected]

Microsoft researchers build 1-bit AI LLM with 2B parameters — model small enough to run on some CPUs (www.tomshardware.com)

submitted 4 days ago by [email protected] to c/[email protected]

10 comments fedilink hide all child comments

top 10 comments

sorted by: hot top controversial new old

[–] [email protected] 5 points 3 days ago (1 children)

It's trinary, and I understand why they instead say "1-bit," but it still bugs me that they call it "1-bit."

I'd love to see how low they can push this and still get spooky results. Something with ten million parameters could fit on a Macintosh Classic II - and if it ran at any speed worth calling interactive, it'd undercut a lot of loud complaints about energy use. Training takes a zillion watts. Using the model is like running a video game.

[–] [email protected] 1 points 1 day ago (1 children)

Can someone tell me what's meant by,

The repository describes bitnet.cpp as offering “a suite of optimized kernels that support fast and lossless inference of 1.58-bit models on CPU

Does it mean you need to run your OS with a specific kernel from bitnet.cpp? Or is it a different kind of 'kernel'?

[–] [email protected] 2 points 21 hours ago* (last edited 21 hours ago)

I think they mean whatever's handling the model. A program into which you feed this inherently restricted format, so it takes advantage of those limitations, in order to run more efficiently.

Like if every number's magnitude is 1 or 0, you don't need to do floating-point multiplication.

[–] [email protected] 1 points 4 days ago

https://lemm.ee/post/61408911

[–] [email protected] 6 points 4 days ago (1 children)

Rather than CPUs I think these are a much bigger deal for GPUs where memory is much more expensive. I can get 128GB of ram for 300CAD, the same amount in vram would be several grand.

[–] [email protected] 2 points 3 days ago

For a second, I was thinking about why you need 300 instances of CAD software and if 128GB isn't a bit too small for that ludicrous amount of computer aided design.

[–] [email protected] 13 points 4 days ago (3 children)

But what makes this AI model unique is that it’s lightweight enough to work efficiently on a CPU, with TechCrunch saying an Apple M2 chip can run it.

An Apple M2 can run bigger, higher-precision models than this FWIW. More important than this is perhaps whether older CPUs can run it with acceptable performance.

AI models are often criticized for taking too much energy to train and operate. But lightweight LLMs, such as BitNet b1.58 2B4T, could help us run AI models locally on less powerful hardware. This could reduce our dependence on massive data centers and even give people without access to the latest processors with built-in NPUs and the most powerful GPUs to use artificial intelligence.

This is definitely relevant to my interests especially with NPU support for such models coming. Dirt cheap ARM-based PCs based on e.g. the RK3588 are shipping with small NPUs

[–] [email protected] 1 points 7 hours ago

The NPUs will have to be rearchitected to optimize themselves for bitnet.

[–] [email protected] 4 points 4 days ago

Apple RAM about as expensive as GPU RAM.

[–] [email protected] 2 points 4 days ago

Very interesting stuff! Thanks for sharing.