Spaces:

mucai
/

matryoshka-multimodal-models

No application file

Apply for community grant: Academic project (gpu and storage)

by mucai - opened Aug 9

Owner Aug 9

We present Matryoshka Multimodal Models (M3), which represents visual tokens in a nested manner following the coarse-to-fine order. Now users can explicitly control the visual granularity per test instance during inference! It will be great to host this model in huggingface!
@akhaliq

hysts

Aug 10

Hi @mucai , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.

mucai

Owner Aug 10

Huge thanks!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment