Token Classification
Transformers
Safetensors
PyTorch
German
roberta
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
german
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1: direct link, hf CLI and curl.
- Browser
- Download file 406 Bytes
-
https://huggingface.co/OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1/resolve/main/eval_results.json
- Command line
-
hf download hf://OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/OpenMed/OpenMed-PII-German-SuperMedical-Large-355M-v1/resolve/main/eval_results.json
406 Bytes
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9946074714096407, | |
| "eval_f1": 0.9675178370259108, | |
| "eval_loss": 0.015116850845515728, | |
| "eval_macro_f1": 0.9574813244065927, | |
| "eval_precision": 0.9660667416572929, | |
| "eval_recall": 0.9689732982324182, | |
| "eval_runtime": 5.5376, | |
| "eval_samples_per_second": 954.754, | |
| "eval_steps_per_second": 29.977, | |
| "eval_weighted_f1": 0.9663937570168848 | |
| } |