Add form-field-v1 detector family (split form-field into detection + understanding rows)

README.md

@@ -35,7 +35,8 @@ We publish narrow models for those tasks and the benchmarks that show where each
 | **Document splitting** (page-stream segmentation): where does one document end and the next begin? | [doc-split-v1](https://huggingface.co/nutrientdocs/doc-split-v1) (Apache-2.0, ONNX) | [doc-split-v2](https://huggingface.co/nutrientdocs/doc-split-v2) | [doc-split-benchmark](https://huggingface.co/datasets/nutrientdocs/doc-split-benchmark) (CC-BY-SA-4.0) | [doc-split-leaderboard](https://huggingface.co/spaces/nutrientdocs/doc-split-leaderboard) | [doc-split-demo](https://huggingface.co/spaces/nutrientdocs/doc-split-demo) |
 | **Document classification** (open-vocabulary, zero-shot): classify a page against labels you choose at runtime | [document-classification-v1](https://huggingface.co/nutrientdocs/document-classification-v1) (Apache-2.0, ONNX) | [document-classification-v2](https://huggingface.co/nutrientdocs/document-classification-v2) | [document-classification-benchmark](https://huggingface.co/datasets/nutrientdocs/document-classification-benchmark) | [document-classification-leaderboard](https://huggingface.co/spaces/nutrientdocs/document-classification-leaderboard) | [document-classification-demo](https://huggingface.co/spaces/nutrientdocs/document-classification-demo) |
 | **Document and figure image classification** (open-vocabulary): documents, charts, signatures, screenshots | | [doc-img-classification](https://huggingface.co/nutrientdocs/doc-img-classification) | [doc-openvocab-benchmark](https://huggingface.co/datasets/nutrientdocs/doc-openvocab-benchmark) (CC-BY-SA-4.0) | [doc-openvocab-leaderboard](https://huggingface.co/spaces/nutrientdocs/doc-openvocab-leaderboard) | [doc-openvocab-demo](https://huggingface.co/spaces/nutrientdocs/doc-openvocab-demo) |
-| **Form field detection**: bounding box, type, label, and radio-group identity for every field on a page image | | [form-field-vlm](https://huggingface.co/nutrientdocs/form-field-vlm) | [form-field-vlm-benchmark](https://huggingface.co/datasets/nutrientdocs/form-field-vlm-benchmark) (CC-BY-4.0) | [form-field-vlm-leaderboard](https://huggingface.co/spaces/nutrientdocs/form-field-vlm-leaderboard) | [form-field-vlm-demo](https://huggingface.co/spaces/nutrientdocs/form-field-vlm-demo) |
+| **Form field detection**: locate every field on a page image with its bounding box, type (text / choice / signature), and filled-vs-empty state — on empty, filled, and handwritten forms | [form-field-v1-nano](https://huggingface.co/nutrientdocs/form-field-v1-nano) (Apache-2.0, ONNX) | [form-field-v1-small](https://huggingface.co/nutrientdocs/form-field-v1-small) · [form-field-v1-medium](https://huggingface.co/nutrientdocs/form-field-v1-medium) | [form-field-v1-benchmark](https://huggingface.co/datasets/nutrientdocs/form-field-v1-benchmark) (CC-BY-4.0) | [form-field-v1-leaderboard](https://huggingface.co/spaces/nutrientdocs/form-field-v1-leaderboard) | [form-field-v1-demo](https://huggingface.co/spaces/nutrientdocs/form-field-v1-demo) |
+| **Form field understanding**: add the text label and radio-group identity for each detected field | | [form-field-vlm](https://huggingface.co/nutrientdocs/form-field-vlm) | [form-field-vlm-benchmark](https://huggingface.co/datasets/nutrientdocs/form-field-vlm-benchmark) (CC-BY-4.0) | [form-field-vlm-leaderboard](https://huggingface.co/spaces/nutrientdocs/form-field-vlm-leaderboard) | [form-field-vlm-demo](https://huggingface.co/spaces/nutrientdocs/form-field-vlm-demo) |
 | **PII detection and redaction**: context-aware redaction on full documents | | | [DocPII-redaction-benchmark](https://huggingface.co/datasets/nutrientdocs/DocPII-redaction-benchmark) (MIT) | [LLM-PII-Detection-Leaderboard](https://huggingface.co/spaces/nutrientdocs/LLM-PII-Detection-Leaderboard) | |
 
 Every leaderboard is scored by the same open scorer we use ourselves. Current numbers, including the cases where a cloud model beats us, live on the leaderboards, not in this README. To add a model, run the scorer and open a pull request on the leaderboard space.