MarkupLM Base is Microsoft's open-weight transformer model for understanding structured HTML documents and web page layouts. Developers and researchers can download and run the model locally for document intelligence and information extraction tasks.
Markuplm Base is an Other AI project. It focuses on understanding and extracting information from structured web pages for document intelligence applications. It is built as an open-source project for machine learning developers and researchers. The project is open source (MIT). It ships for the web, API, and the command line, and it can be self-hosted.
Behind Markuplm Base is Microsoft, and it first shipped in 2020. The project is developed in the open on GitHub with 11.7k stars. Among its 6 catalogued features are HTML understanding, web page parsing, and layout awareness.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do