← Back to search

Models tagged "document-understanding"

Sort by:

Found 2 models (showing 1-2)

🤖 Model 🖼️ → 📝

ibm-granite/granite-vision-3.2-2b

Extract content and answer questions from images of documents. Takes an image plus a text prompt or question and outputs...

🖼️ → 📝 • image-to-text • ocr • 118.0K runs

🤖 Model 🖼️ → 📝

lucataco/nemotron-nano-vl-8b-v1

Answer questions about an image and generate captions and summaries. Accepts a single image and a natural-language quest...

🖼️ → 📝 • image-to-text • visual-question-answering • 9 runs