granite-docling-258M demo
📝
262
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 • 214k • 1.08k -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 3.37M • 3.04k -
DeepSeek OCR Demo
🚀325Try out DeepSeek-OCR on your PDFs or images
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 13.3k • 1.46k -
MinerU OCR
📚515A data extraction tool to convert PDF to Markdown and JSON
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 57.2k • 172