Document Image Parsing via Heterogeneous Anchor Prompting
A novel multimodal document image parsing model, following an analyze-then-parse paradigm for parallel decoding
支持格式/Support Format
支持多页PDF、单页图像
Multi-page PDF, single document image (JPEG/PNG)
Multi-page PDF, single document image (JPEG/PNG)
轻量级模型/Lightweight Model
Dolphin模型参数量322M，高效易部署
Lightweight (322M) and efficient, easy to deploy
Lightweight (322M) and efficient, easy to deploy
并行解析/Parallel Parsing
Dolphin并行解析多个文本块
Parsing several text blocks in a batch for speed up
Parsing several text blocks in a batch for speed up
公式和表格/Formula and Table
支持公式(LaTeX格式)、表格(HTML格式)输出
Support formulas (LaTeX format) and tables (HTML format)
Support formulas (LaTeX format) and tables (HTML format)
内容由 AI 生成，请仔细甄别