SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper
•
2503.11576
•
Published
•
108
slm-document-ai
-
-
OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
Paper • 2412.07626 • Published • 22 -
ds4sd/docling-models
Updated • 1.19M • 144 -
ds4sd/SmolDocling-256M-preview
Image-Text-to-Text • Updated • 283k • 1.39k -
HuggingFaceTB/SmolVLM2-2.2B-Instruct
Image-Text-to-Text • Updated • 82.3k • 191