docling-project/docling-nlp-models

Models for docling-parse

This repository contains the models used for docling-nlp.

Contents

This model repository packages the pretrained assets used by Docling’s NLP components:

• CRF models for material classification and English part-of-speech tagging
• fastText models for language detection, metadata, semantic, topic, and person-name classification
• Regular-expression assets for geographic-location extraction and unit handling
• A default tokenizer model

Correct workflow to add new files

git lfs status
git commit -s -m "Add new models ..."

git lfs push origin main
git push origin main