hpd-parsing / README.md
multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
559419c verified
|
Raw
History Blame Contribute Delete
779 Bytes
---
title: HPD-Parsing
emoji: ๐Ÿ“„
colorFrom: indigo
colorTo: pink
sdk: gradio
sdk_version: 6.20.0
app_file: app.py
short_description: Hierarchical parallel document parsing with a 1B VLM
python_version: "3.10"
startup_duration_timeout: 30m
---
## HPD-Parsing: Hierarchical Parallel Document Parsing
This Space demos [PaddlePaddle/HPD-Parsing](https://huggingface.co/PaddlePaddle/HPD-Parsing),
a lightweight 1B-parameter document parsing model that uses a Hierarchical Parallel
Decoding (HPD) paradigm to overcome the sequential bottleneck of traditional VLM-based
parsers. It achieves a state-of-the-art score of 94.91% on OmniDocBench v1.6.
Upload a document image and the model will parse it into structured text (markdown),
capturing layout, tables, and content hierarchy.