Futurology

1670 readers

75 users here now

founded 1 year ago

MODERATORS

Researchers say their open-source AI model LLaVA, is as powerful as GPT-4 Vision, which was released only weeks ago. (llava-vl.github.io)

submitted 11 months ago by [email protected] to c/[email protected]

15 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 2 points 11 months ago (1 children)

Holy shit a terabyte?

[–] [email protected] 4 points 11 months ago (1 children)

This specific one says it'll run on 24GB actually. But some are just crazy big.

[–] [email protected] 2 points 11 months ago* (last edited 11 months ago) (1 children)

There are smaller models that can run on most laptops.

https://www.maginative.com/article/stability-ai-releases-stable-lm-3b-a-small-high-performance-language-model-for-smart-devices/

In benchmarks this looks like it is not far off Chat-GPT 3.5.

[–] [email protected] 1 points 11 months ago

It's not even close, less than half of 3.5's 85.5% in ARC. Some larger Open models are competitive in Hellaswag, TruthfulQA and MMLU but ARC is still a major struggle for small models.

3Bs are kind of pointless right now because the machines with processors capable of running them at a usable speed probably have enough memory to run a 7B anyway.