granite-docling-258M demo
📝
259
Convert images to structured text and answer questions
OCR
-
-
Multimodal RAG with Granite Vision
🚀36RAG example using Granite [vision, embedding, instruct]
-
ibm-granite/granite-docling-258M
Image-Text-to-Text • 0.3B • Updated • 197k • 1.07k -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 4.02M • 3.01k -
DeepSeek OCR Demo
🚀312Try out DeepSeek-OCR on your PDFs or images
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 17k • 1.43k -
MinerU OCR
📚511A data extraction tool to convert PDF to Markdown and JSON
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 87.5k • 168