OpenMed-PII-SuperClinical-Base-184M-v1 for OpenMed MLX

This repository contains an MLX packaging of OpenMed/OpenMed-PII-SuperClinical-Base-184M-v1 for Apple Silicon inference with OpenMed.

At a Glance

Source checkpoint: OpenMed/OpenMed-PII-SuperClinical-Base-184M-v1
Model family: deberta-v2 (DebertaV2ForTokenClassification)
Primary language hint: English (en)
Artifact layout: legacy-compatible MLX (config.json, id2label.json, MLX weight files)
Python MLX: supported through openmed[mlx] on Apple Silicon Macs
Swift MLX: not yet in the current OpenMedKit Swift MLX v1 rollout for deberta-v2 models

Python Quick Start

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

pip install "openmed[mlx]"

from openmed import extract_pii

text = "<your clinical note here>"
result = extract_pii(
    text,
    model_name="OpenMed/OpenMed-PII-SuperClinical-Base-184M-v1",
    use_smart_merging=True,
)

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

On Apple Silicon, OpenMed auto-selects MLX when openmed[mlx] is installed. On other systems it 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:

pip install "openmed[mlx]"
hf download OpenMed/OpenMed-PII-SuperClinical-Base-184M-v1-mlx --local-dir ./OpenMed-PII-SuperClinical-Base-184M-v1-mlx

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

from openmed import extract_pii
from openmed.core import OpenMedConfig

text = "<your clinical note here>"
result = extract_pii(
    text,
    model_name="./OpenMed-PII-SuperClinical-Base-184M-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 family today, but the current public Swift MLX rollout in OpenMedKit is intentionally 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

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 not bundled in this repo layout. OpenMed and OpenMedKit keep backward compatibility by falling back to the source tokenizer reference in config.json when needed.