README.md

---
license: apache-2.0
base_model: OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1
pipeline_tag: token-classification
library_name: openmed
tags:
  - openmed
  - mlx
  - apple-silicon
  - token-classification
  - pii
  - de-identification
  - medical
  - clinical
  - deberta-v2
---

# OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1 for OpenMed MLX

This repository contains an MLX packaging of [`OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1`](https://huggingface.co/OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1) for Apple Silicon inference with [OpenMed](https://github.com/maziyarpanahi/openmed).

## At a Glance

- Source checkpoint: [`OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1`](https://huggingface.co/OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1)
- Model family: `deberta-v2` (`DebertaV2ForTokenClassification`)
- Primary language hint: Portuguese (`pt`)
- Artifact layout: legacy-compatible MLX (`config.json`, `id2label.json`, MLX weight files)
- Weight format: `safetensors`
- Python MLX: supported through `openmed[mlx]` on Apple Silicon Macs

## Python Quick Start

Use the standard OpenMed API if you want OpenMed to choose the right runtime automatically:

```bash
pip install "openmed[mlx]"
```

```python
from openmed import extract_pii

text = "<your clinical note here>"
result = extract_pii(
    text,
    model_name="OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1",
    use_smart_merging=True,
)

for entity in result.entities:
    print(entity.label, entity.text, round(entity.confidence, 4))
```

On Apple Silicon, OpenMed can use this preconverted MLX artifact when `openmed[mlx]` is installed. On other systems, OpenMed falls back to the Hugging Face / PyTorch backend.

## Use This Preconverted MLX Repo Directly

If you want to use this MLX snapshot explicitly, download it locally and point OpenMed at the directory:

```bash
pip install "openmed[mlx]"
hf download OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1-mlx --local-dir ./OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1-mlx
```

If this repo is private in your environment, authenticate first with `hf auth login` or set `HF_TOKEN`.

```python
from openmed import extract_pii
from openmed.core import OpenMedConfig

text = "<your clinical note here>"
result = extract_pii(
    text,
    model_name="./OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1-mlx",
    config=OpenMedConfig(backend="mlx"),
    use_smart_merging=True,
)

print(result.entities)
```

## Swift Status

This repo is based on `deberta-v2`. Python MLX supports this artifact today, but the current public OpenMedKit Swift MLX rollout is limited to `bert`, `distilbert`, `roberta`, `xlm-roberta`, and `electra`.

If you are building an Apple app today, the recommended paths for this model are:

- Python MLX for evaluation or local workflows on Apple Silicon
- CoreML in OpenMedKit if you already have a compatible bundled Apple export
- Track the current Swift support matrix in the [OpenMedKit docs](https://openmed.life/docs/swift-openmedkit/)

## Artifact Notes

This repo uses the current legacy-compatible MLX layout:

- `config.json`
- `id2label.json`
- MLX weight files (`weights.safetensors` and/or `weights.npz`)

Tokenizer assets are bundled in this repo.

## Links

- Source checkpoint: [`OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1`](https://huggingface.co/OpenMed/OpenMed-PII-Portuguese-mSuperClinical-Large-279M-v1)
- OpenMed GitHub: [https://github.com/maziyarpanahi/openmed](https://github.com/maziyarpanahi/openmed)
- MLX backend docs: [https://openmed.life/docs/mlx-backend/](https://openmed.life/docs/mlx-backend/)
- OpenMedKit docs: [https://openmed.life/docs/swift-openmedkit/](https://openmed.life/docs/swift-openmedkit/)