Text Generation
Transformers
Safetensors
English
multimodal
text
image
image-to-text
idefics-9b / README.md
typeof's picture
Create README.md
4983e63
metadata
language: en
tags:
  - multimodal
  - text
  - image
  - image-to-text
license: other
datasets:
  - HuggingFaceM4/OBELICS
  - wikipedia
  - facebook/pmd
  - laion/laion2B-en
pipeline_tag: text-generation
inference: false