The HF Entity Recognition deep learning package seamlessly integrates pretrained Entity Recognition models from the Hugging Face Hub with ArcGIS, allowing you to use a variety of models directly within ArcGIS. With this package, you can extract entities belonging to predefined categories from text using the capabilities of the selected pretrained Hugging Face model.
The deep learning package is compatible with a wide range of Hugging Face models for Named Entity Recognition (NER) tasks. Before running a model, ensure compliance with its licensing terms, which are listed on the Hugging Face model page. Use only trusted models, as they include weights and code that could impact system security. Since model sizes vary, confirm that adequate CPU/GPU memory is available for inference.
Model details
This model has the following characteristics:
- Input—A feature class or table containing text on which entity extraction will be performed.
- Output—The extracted entities from the input data are added to the corresponding category columns.
- Compute—This workflow is compute intensive, and a GPU with a minimum CUDA compute capability of 6.0 is recommended.
- Architecture—Uses a Hugging Face pretrained model tagged with Token Classification, identified by its model ID.
Access and download the model
Download the HF Entity Recognition pretrained model from ArcGIS Living Atlas of the World.
- Browse to ArcGIS Living Atlas of the World.
- Sign in with your ArcGIS Online credentials.
- Search for HF Entity Recognition and open the item page from the search results.
- Click the Download button to download the model.
You can use the downloaded .dlpk file directly in ArcGIS Pro, or upload and use it in ArcGIS Enterprise.
Release notes
The following are the release notes:
| Date | Description |
|---|---|
| September 2025 | First release of HF Entity Recognition model |