Token Classification
Transformers
Safetensors
PyTorch
Dutch
modernbert
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
dutch
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-Dutch-BioClinicalModern-Base-149M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-Dutch-BioClinicalModern-Base-149M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-Dutch-BioClinicalModern-Base-149M-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-Dutch-BioClinicalModern-Base-149M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-Dutch-BioClinicalModern-Base-149M-v1") - Notebooks
- Google Colab
- Kaggle
| Classification Report for Dutch PII Detection | |
| Model: thomas-sounack/BioClinical-ModernBERT-base | |
| ============================================================ | |
| precision recall f1-score support | |
| BANKACCOUNT 0.78 0.64 0.70 136 | |
| BUILDINGNUMBER 0.77 0.77 0.77 111 | |
| CITY 0.81 0.87 0.84 334 | |
| CREDITCARD 0.80 0.81 0.80 86 | |
| DATEOFBIRTH 0.73 0.71 0.72 138 | |
| EMAIL 0.99 0.99 0.99 347 | |
| FIRSTNAME 0.78 0.78 0.78 460 | |
| LASTNAME 0.71 0.64 0.68 354 | |
| MASKEDNUMBER 0.91 0.88 0.89 77 | |
| PASSWORD 0.95 0.96 0.95 94 | |
| PHONE 0.99 0.99 0.99 230 | |
| SSN 0.95 1.00 0.97 338 | |
| STREET 0.67 0.64 0.66 123 | |
| USERNAME 0.96 0.92 0.94 367 | |
| ZIPCODE 0.95 0.90 0.92 193 | |
| micro avg 0.86 0.85 0.85 3388 | |
| macro avg 0.85 0.83 0.84 3388 | |
| weighted avg 0.86 0.85 0.85 3388 | |