Token Classification
Transformers
Safetensors
PyTorch
French
roberta
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
french
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-French-FastClinical-Small-82M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-French-FastClinical-Small-82M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-French-FastClinical-Small-82M-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-French-FastClinical-Small-82M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-French-FastClinical-Small-82M-v1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9928861964517525, | |
| "eval_f1": 0.9496173296914299, | |
| "eval_loss": 0.020175855606794357, | |
| "eval_macro_f1": 0.9328723933774744, | |
| "eval_precision": 0.9473883013166415, | |
| "eval_recall": 0.9518568717809704, | |
| "eval_runtime": 4.2559, | |
| "eval_samples_per_second": 1458.431, | |
| "eval_steps_per_second": 11.513, | |
| "eval_weighted_f1": 0.9451462202634883, | |
| "test_accuracy": 0.9929346909581489, | |
| "test_f1": 0.9488515209587304, | |
| "test_loss": 0.019844746217131615, | |
| "test_macro_f1": 0.9335348063261684, | |
| "test_precision": 0.9468325791855203, | |
| "test_recall": 0.9508790911549906, | |
| "test_runtime": 3.295, | |
| "test_samples_per_second": 1872.839, | |
| "test_steps_per_second": 14.871, | |
| "test_weighted_f1": 0.9445961246771372, | |
| "total_flos": 3006229263679488.0, | |
| "train_loss": 0.1773753967080065, | |
| "train_runtime": 145.8072, | |
| "train_samples_per_second": 1020.114, | |
| "train_steps_per_second": 15.946 | |
| } |