this post was submitted on 22 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
ShareGPT4V - New multi-modal model, improves on LLaVA (sharegpt4v.github.io)
submitted 11 months ago by Cradawx@alien.top to c/localllama@poweruser.forum
17 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] M0ULINIER@alien.top 1 points 11 months ago (2 children)

https://preview.redd.it/vnony8f0ax1c1.png?width=1080&format=pjpg&auto=webp&s=dc261252751a0a1e209d9049854895688de25fa4

Benchmark in their GitHub, even if it's hard to be sure in current times

[–] justletmefuckinggo@alien.top 1 points 11 months ago

im new here. but is this true multimodality, or is it the llm communicating with a vision model?

and what are those 4 models being benchmark tested here for exactly?

[–] lakolda@alien.top 1 points 11 months ago

This isn’t comparing with the 13B version of LLAVA. I’d be curious to see that.