caibucai
caibucai
·
AI & ML interests
None yet
Organizations
None yet
-
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper • 2503.11576 • Published • 157 -
docling-project/SmolDocling-256M-preview
Image-Text-to-Text • Updated • 35.4k • 1.61k -
reducto/RolmOCR
Image-Text-to-Text • 8B • Updated • 305k • 585 -
nanonets/Nanonets-OCR-s
Image-Text-to-Text • 4B • Updated • 28.8k • 1.59k
-
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper • 2503.11576 • Published • 157 -
docling-project/SmolDocling-256M-preview
Image-Text-to-Text • Updated • 35.4k • 1.61k -
reducto/RolmOCR
Image-Text-to-Text • 8B • Updated • 305k • 585 -
nanonets/Nanonets-OCR-s
Image-Text-to-Text • 4B • Updated • 28.8k • 1.59k