Token Classification
Transformers
Safetensors
PyTorch
French
xlm-roberta
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
french
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download classification_report.txt from OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1: direct link, hf CLI and curl.
- Browser
- Download file 3.51 kB
-
https://huggingface.co/OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1/resolve/main/classification_report.txt
- Command line
-
hf download hf://OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1/classification_report.txt
-
curl -L -o classification_report.txt https://huggingface.co/OpenMed/OpenMed-PII-French-BigMed-Large-560M-v1/resolve/main/classification_report.txt
3.51 kB
| Classification Report for French PII Detection | |
| Model: FacebookAI/xlm-roberta-large | |
| ============================================================ | |
| precision recall f1-score support | |
| ACCOUNTNAME 1.00 1.00 1.00 360 | |
| AGE 0.98 0.99 0.99 389 | |
| AMOUNT 0.99 1.00 1.00 104 | |
| BANKACCOUNT 1.00 1.00 1.00 312 | |
| BIC 0.98 1.00 0.99 98 | |
| BITCOINADDRESS 0.98 0.99 0.98 318 | |
| BUILDINGNUMBER 0.98 0.95 0.97 396 | |
| CITY 0.99 0.99 0.99 329 | |
| COUNTY 0.99 0.99 0.99 382 | |
| CREDITCARD 0.91 0.97 0.94 382 | |
| CREDITCARDISSUER 1.00 1.00 1.00 210 | |
| CURRENCY 0.67 0.76 0.71 210 | |
| CURRENCYCODE 0.98 0.99 0.99 106 | |
| CURRENCYNAME 0.43 0.44 0.43 109 | |
| CURRENCYSYMBOL 0.99 0.99 0.99 355 | |
| CVV 0.99 1.00 0.99 83 | |
| DATE 0.79 0.92 0.85 598 | |
| DATEOFBIRTH 0.83 0.64 0.72 404 | |
| EMAIL 1.00 1.00 1.00 495 | |
| ETHEREUMADDRESS 1.00 1.00 1.00 236 | |
| EYECOLOR 0.99 1.00 1.00 162 | |
| FIRSTNAME 0.99 0.99 0.99 1927 | |
| GENDER 1.00 1.00 1.00 412 | |
| GPSCOORDINATES 1.00 1.00 1.00 300 | |
| HEIGHT 0.99 0.99 0.99 155 | |
| IBAN 1.00 1.00 1.00 273 | |
| IMEI 1.00 1.00 1.00 304 | |
| IPADDRESS 1.00 1.00 1.00 992 | |
| JOBDEPARTMENT 0.99 1.00 0.99 336 | |
| JOBTITLE 1.00 1.00 1.00 329 | |
| LASTNAME 0.99 0.98 0.99 585 | |
| LITECOINADDRESS 0.96 0.93 0.94 110 | |
| MACADDRESS 1.00 1.00 1.00 145 | |
| MASKEDNUMBER 0.96 0.88 0.92 302 | |
| MIDDLENAME 0.94 0.99 0.96 374 | |
| OCCUPATION 1.00 0.99 1.00 382 | |
| ORDINALDIRECTION 1.00 1.00 1.00 185 | |
| ORGANIZATION 1.00 1.00 1.00 322 | |
| PASSWORD 1.00 1.00 1.00 393 | |
| PHONE 1.00 1.00 1.00 341 | |
| PIN 0.99 1.00 0.99 83 | |
| PREFIX 1.00 0.98 0.99 391 | |
| SECONDARYADDRESS 1.00 1.00 1.00 357 | |
| SEX 1.00 1.00 1.00 422 | |
| SSN 1.00 1.00 1.00 331 | |
| STATE 0.99 1.00 0.99 348 | |
| STREET 0.99 1.00 0.99 409 | |
| TIME 1.00 1.00 1.00 348 | |
| URL 1.00 1.00 1.00 364 | |
| USERAGENT 0.99 1.00 0.99 295 | |
| USERNAME 1.00 1.00 1.00 348 | |
| VIN 1.00 0.98 0.99 113 | |
| VRM 1.00 1.00 1.00 125 | |
| ZIPCODE 0.95 0.98 0.97 346 | |
| micro avg 0.97 0.97 0.97 18485 | |
| macro avg 0.97 0.97 0.97 18485 | |
| weighted avg 0.97 0.97 0.97 18485 | |