MODEL_CARD_TEMPLATE.md

---
license: agpl-3.0
language:
- cs
- en
library_name: ultralytics
pipeline_tag: object-detection
tags:
- cropilot
- yolo
- document-layout-analysis
- document-cropping
- digitization
---

# {{ Model Title, e.g. Newspaper Outer Crop v1 }}

`{{ model-filename, e.g. newspaper_outer_crop_v1.pt }}` is a Cropilot model for {{ short description, e.g. detecting outer page crop regions in newspaper digitization workflows }}.

It is published here as a reusable model artifact for use in the [Cropilot](https://github.com/moravianlibrary/cropilot) document-cropping ecosystem.

## Intended Use

{{ Add any model-specific notes here, what data to use it on, etc. }}

## Training Data

{{ Briefly describe the training data and its source. The training data is not included in this repository. }}

## Limitations

{{ Known limitations of the model. }}

## Example Download

```python
from huggingface_hub import hf_hub_download

path = hf_hub_download(
    repo_id="cropilot-community/{{ model-name }}",
    filename="{{ model-filename }}",
)
print(path)
```

## Recommended settings

Typical Cropilot settings for this model:

- Crop model: `{{ e.g. outer_crop }}`
- Rotation model: `{{ e.g. text }}`

## Versioning

This repository stores **{{ version, e.g. v1 }}** of this model. Newer fine-tuned models should be published as separate `v<n>` repositories so deployments remain reproducible.

## License

Released under the GNU Affero General Public License v3.0 (`AGPL-3.0`).

## Model File

- File: `{{ model-filename }}`
- Base model: {{ e.g. YOLO11s / ResNet }}
- Task: {{ e.g. object-detection (crop region) / rotation angle prediction }}