Token Classification
Transformers
Safetensors
PyTorch
German
distilbert
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
german
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download test_results.json from OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1: direct link, hf CLI and curl.
- Browser
- Download file 389 Bytes
-
https://huggingface.co/OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1/resolve/main/test_results.json
- Command line
-
hf download hf://OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1/test_results.json
-
curl -L -o test_results.json https://huggingface.co/OpenMed/OpenMed-PII-German-mLiteClinical-Base-135M-v1/resolve/main/test_results.json
389 Bytes
| { | |
| "test_accuracy": 0.9930476960388036, | |
| "test_f1": 0.9566419504838506, | |
| "test_loss": 0.021570058539509773, | |
| "test_macro_f1": 0.9385049867502346, | |
| "test_precision": 0.9547820633427406, | |
| "test_recall": 0.9585090977774979, | |
| "test_runtime": 2.6019, | |
| "test_samples_per_second": 2029.325, | |
| "test_steps_per_second": 16.142, | |
| "test_weighted_f1": 0.9538525607355363 | |
| } |