this post was submitted on 26 Jul 2023
19 points (100.0% liked)

LocalLLaMA

3427 readers
3 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.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

founded 2 years ago
MODERATORS
 

For example, does a 13B parameter model at 2_K quantiation perform worse than a 7B parameter model at 8bit or 16bit?

top 7 comments
sorted by: hot top controversial new old
[–] [email protected] 9 points 2 years ago* (last edited 2 years ago) (2 children)

https://github.com/ggerganov/llama.cpp#quantization

https://github.com/ggerganov/llama.cpp/pull/1684

Regarding your question: 13B 2_K seems to be on par with 7B 16bit and 8bit. Not much of a difference between all those. (Look at the perplexity values. Lower is better.) The second link has a nice graph.

Most people don't go as low as 2bit though. It's considerably worse than 4bit.

[–] [email protected] 5 points 2 years ago

That graph is great. Very easy to understand. Thank you!

[–] [email protected] 2 points 2 years ago

These are good sources, to add one more, the GPTQ paper talks a lot about perplexity at several quantization and model sizes:

https://arxiv.org/abs/2210.17323

[–] [email protected] 2 points 2 years ago (1 children)

Anyone else see 11 comments on the post count but only 2 comments..?

[–] [email protected] 2 points 2 years ago (1 children)
[–] [email protected] 5 points 2 years ago (1 children)

Well, a few of those extra numbers are my fault. I edited my answer a few times. And lemmy reportedly counts every edit as an additional comment. (When user and community are on different instances.) I hope they fix that soon.

[–] [email protected] 2 points 2 years ago

ahh makes sense, i just made a post and deleted the comment i made on it but it glitched and deleted twice so now my post has -1 comments lmao

load more comments
view more: next ›