florence - Vermont-Complex-Systems/pdf-zoo GitHub Wiki
florence
tags: #llm
inst: Microsoft
paper: 2311.06242
date: Feb 2025
Microsoft's multimodal LLM capable of OCR along with other vision-language tasks.
tags: #llm
inst: Microsoft
paper: 2311.06242
date: Feb 2025
Microsoft's multimodal LLM capable of OCR along with other vision-language tasks.