Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Posts
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

NexaAIDev
/
OmniVLM-968M

GGUF
multimodal
conversational
GGUF
Image-Text-to-Text
Model card Files Files and versions Community
16
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Report

#16 opened 11 days ago by
jonyyolk

How to use python local visual question answering

#15 opened 4 months ago by
mint20262026

Help to run the model locally

1
#14 opened 5 months ago by
Salzani

Interview request: Thoughts on genAI evaluation & documentation

#13 opened 5 months ago by
evatang

Regarding Model Weights

1
#12 opened 5 months ago by
BimsaraRad

Run omnivision on Nvidia Jetson-Orin

1
#11 opened 5 months ago by
ravindutbandara

9x token reduction

1
#10 opened 5 months ago by
Sijuade

Error loading model

2
#9 opened 6 months ago by
iojvsuynv

nexa-on-colab

2
1
#8 opened 6 months ago by
sdyy

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

3
#7 opened 6 months ago by
nemonameless

Video or multiple frames.

2
1
#6 opened 6 months ago by
monamie

transformers version?

1
#5 opened 6 months ago by
CHNtentes

How to call it through transformer

2
2
#4 opened 6 months ago by
awelker

Text/vision parameter split

1
#3 opened 6 months ago by
AlexThompson

How do you encode an image in only 81 tokens?

5
#2 opened 6 months ago by
ChristineLai

about ocr

1
#1 opened 6 months ago by
MiaHawthorne
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs