Can I read SmolDocling: Compact Vision-Language Model on EtoBox?
SmolDocling: Compact Vision-Language Model by mikjastytan is a document available to read on EtoBox.
What is SmolDocling: Compact Vision-Language Model about?
SmolDocling is an ultra-compact vision-language model designed for end-to-end document conversion, utilizing a new markup format called DocTags to capture the content, structure, and spatial location of document elements. The model, with 256 million parameters, demonstrates competitive performance compared to larger models while significantly reducing computational requirements. It includes novel datasets for various document features and aims to address challenges in document understanding across diverse f
- Author
- mikjastytan
- Language
- EN