Token Classification
Transformers
Safetensors
PyTorch
Portuguese
distilbert
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
portuguese
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-Portuguese-LiteClinicalU-Small-66M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-Portuguese-LiteClinicalU-Small-66M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-Portuguese-LiteClinicalU-Small-66M-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-Portuguese-LiteClinicalU-Small-66M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-Portuguese-LiteClinicalU-Small-66M-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload Portuguese PII detection model OpenMed-PII-Portuguese-LiteClinicalU-Small-66M-v1
f6b3999 verified | Classification Report for Portuguese PII Detection | |
| Model: distilbert/distilbert-base-uncased | |
| ============================================================ | |
| precision recall f1-score support | |
| ACCOUNTNAME 0.55 0.49 0.52 83 | |
| AGE 0.88 0.60 0.71 151 | |
| AMOUNT 0.61 0.40 0.48 584 | |
| BANKACCOUNT 0.60 0.77 0.68 53 | |
| BIC 0.00 0.00 0.00 6 | |
| BUILDINGNUMBER 0.67 0.82 0.73 197 | |
| CITY 0.90 0.93 0.91 215 | |
| COUNTY 0.00 0.00 0.00 7 | |
| CREDITCARD 0.94 0.85 0.89 187 | |
| CREDITCARDISSUER 0.43 0.43 0.43 14 | |
| CURRENCY 0.46 0.88 0.61 349 | |
| CURRENCYCODE 0.40 0.27 0.32 15 | |
| CURRENCYNAME 0.00 0.00 0.00 2 | |
| CURRENCYSYMBOL 1.00 0.01 0.01 163 | |
| CVV 0.88 0.67 0.76 21 | |
| DATE 0.97 0.95 0.96 1039 | |
| DATEOFBIRTH 0.84 0.90 0.87 110 | |
| EMAIL 0.96 0.96 0.96 200 | |
| ETHEREUMADDRESS 0.00 0.00 0.00 1 | |
| FIRSTNAME 0.97 0.99 0.98 2411 | |
| GENDER 0.00 0.00 0.00 2 | |
| IBAN 0.97 0.99 0.98 666 | |
| IMEI 0.00 0.00 0.00 2 | |
| IPADDRESS 0.98 0.92 0.95 53 | |
| JOBDEPARTMENT 0.69 0.51 0.59 43 | |
| JOBTITLE 0.62 0.57 0.59 53 | |
| LASTNAME 0.97 0.98 0.97 2420 | |
| MACADDRESS 0.00 0.00 0.00 4 | |
| MASKEDNUMBER 0.19 0.15 0.17 33 | |
| MIDDLENAME 0.00 0.00 0.00 3 | |
| OCCUPATION 0.00 0.00 0.00 28 | |
| ORDINALDIRECTION 0.00 0.00 0.00 21 | |
| ORGANIZATION 0.66 0.65 0.65 502 | |
| PASSWORD 0.71 0.52 0.60 23 | |
| PHONE 1.00 0.99 0.99 363 | |
| PIN 0.75 0.25 0.38 12 | |
| PREFIX 0.95 0.97 0.96 1367 | |
| SECONDARYADDRESS 0.00 0.00 0.00 13 | |
| SSN 0.89 0.95 0.92 671 | |
| STATE 0.89 0.89 0.89 57 | |
| STREET 0.72 0.71 0.71 274 | |
| TIME 0.66 0.79 0.72 362 | |
| URL 0.90 0.79 0.84 34 | |
| USERNAME 0.00 0.00 0.00 36 | |
| VIN 0.00 0.00 0.00 1 | |
| VRM 0.00 0.00 0.00 2 | |
| ZIPCODE 0.95 0.95 0.95 80 | |
| micro avg 0.88 0.88 0.88 12933 | |
| macro avg 0.54 0.50 0.50 12933 | |
| weighted avg 0.88 0.88 0.87 12933 | |