NexaAIDev
/

omnivision-968M

Image-Text-to-Text

Model card Files Files and versions Community

Resources

View closed (0)

nexa-on-colab

#8 opened 1 day ago by

Compare with llava-onevision-894M and internvl2-938M?

#7 opened 2 days ago by

Video or multiple frames.

#6 opened 3 days ago by

transformers version?

#5 opened 3 days ago by

How to call it through transformer

#4 opened 4 days ago by

Text/vision parameter split

#3 opened 6 days ago by

How do you encode an image in only 81 tokens?

#2 opened 6 days ago by

about ocr

#1 opened 7 days ago by