hugpadhugpad

HuggingFaceTB / SmolVLM-Instruct

Vision2.2B15.3K601Updated Apr 8, 2025
Hugging Face

Downloads

15.3K

Likes

601

Last updated

Apr 8, 2025

License

apache-2.0

SmolVLM is a compact open multimodal model that accepts arbitrary sequences of image and text inputs to produce text outputs. Designed for efficiency, SmolVLM can answer questions about images, describe visual content, create stories grounded on multiple images, or function as…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • onnx
  • idefics3
  • image-text-to-text
  • conversational
  • en

Technical specifications

Parameters2.2B
Librarytransformers
Languagesen
Base modelHuggingFaceTB/SmolLM2-1.7B-Instruct
Licenseapache-2.0