vscode-ai-toolkit icon indicating copy to clipboard operation
vscode-ai-toolkit copied to clipboard

Llama Vision Models fail

Open shaneholloman opened this issue 1 year ago • 4 comments

Llama Vision models either refuse or fail to describe any image regardless of size or content.

Image

or same with larger model

Image

shaneholloman avatar Dec 09 '24 22:12 shaneholloman

Hi @shaneholloman, thanks for using AI Toolkit. As the error message suggests, your image file size exceeds limit (10M) for that model. Could you try with smaller image files?

Image

a1exwang avatar Dec 10 '24 03:12 a1exwang

The image is 300kb

shaneholloman avatar Dec 10 '24 14:12 shaneholloman

Something else is going on here

shaneholloman avatar Dec 10 '24 14:12 shaneholloman

Perhaps the image is being base64 encoded on the way to the model? That would bloat the size by quite a bit.

jflam avatar Dec 13 '24 00:12 jflam