Yuliang-Liu / Monkey

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models
MIT License
1.77k stars 122 forks source link

Get the embeddings of the image. #92

Closed xinyanghuang7 closed 4 months ago

xinyanghuang7 commented 4 months ago

Thank you very much for contributing such an excellent model!

If I want to input a picture and obtain the embedding provided by Monkey-Chat, how should I do it?

Can you help me implement it with a few simple lines of code?

Looking forward to your reply!

Thanks!

echo840 commented 4 months ago

Hello, maybe you can get the embedding here: image