RekaAI / reka-edge-2603

Vision7.1B1.1K134Updated Apr 24, 2026

Downloads

1.1K

Likes

134

Last updated

Apr 24, 2026

License

reka-edge-2603-license

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding, video analysis, object detection, and a…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • yasa2
  • image-text-to-text
  • conversational
  • custom_code

Technical specifications

Parameters7.1B
Librarytransformers
LanguagesNot available
Licensereka-edge-2603-license