NexaAIDev
/

omnivision-968M

Image-Text-to-Text

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (0)

Text/vision parameter split

#3 opened about 5 hours ago by

How do you encode an image in only 81 tokens?

#2 opened about 5 hours ago by

about ocr

#1 opened about 9 hours ago by