NexaAIDev
/

OmniVLM-968M

Image-Text-to-Text

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (0)

How to use python local visual question answering

#15 opened about 1 month ago by

Help to run the model locally

#14 opened 2 months ago by

Interview request: Thoughts on genAI evaluation & documentation

#13 opened 2 months ago by

Regarding Model Weights

#12 opened 3 months ago by

Run omnivision on Nvidia Jetson-Orin

#11 opened 3 months ago by

ravindutbandara

9x token reduction

#10 opened 3 months ago by

Error loading model

#9 opened 3 months ago by

nexa-on-colab

#8 opened 3 months ago by

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

#7 opened 3 months ago by

Video or multiple frames.

#6 opened 3 months ago by

transformers version?

#5 opened 3 months ago by

How to call it through transformer

#4 opened 3 months ago by

Text/vision parameter split

#3 opened 3 months ago by

How do you encode an image in only 81 tokens?

#2 opened 3 months ago by

about ocr

#1 opened 3 months ago by