Document Extraction SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 160
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 160
Agents Running Agents 687 First Agent Template ⚡ 687 Generate code, answer queries, and create images
Document Extraction SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 160
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 160
Agents Running Agents 687 First Agent Template ⚡ 687 Generate code, answer queries, and create images
