SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Related Cards

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning

Retrieval-Augmented Reasoning with Lean Language Models

Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion