You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As I known, clip vit 336 would produce 576 visual tokens per image, the UHD are stack 6 of them, that is 3000+ visual tokens.
How does it able to send to LLM?
The text was updated successfully, but these errors were encountered:
We use a resampler to down-sample the feature tokes, ie, a slice 576 to 144. So that, 6 slices only need 1008 tokens to represent.
Moreover, our repository has been fully improved, and almost all bugs have been eliminated. For details, please refer to the main branch and the LLaVA-UHD v1 branch. This issue is now closed. If there are any new problems, feel free to open a new issue.
As I known, clip vit 336 would produce 576 visual tokens per image, the UHD are stack 6 of them, that is 3000+ visual tokens.
How does it able to send to LLM?
The text was updated successfully, but these errors were encountered: