search

OpenGVLab / Ask-Anything

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
https://vchat.opengvlab.com/
MIT License
2.85k stars 230 forks source link

question about vision encoder #196

Open Nastu-Ho opened 1 week ago

Nastu-Ho commented 1 week ago
image

Is the vision encoder used here umt-l or internvideo2-1B? I saw that the mistral version in internvideo2 had similar results to the one here

Andy1621 commented 1 week ago

Hi! We released UMT-L since it runs faster.