Token Classification
Transformers
Safetensors
PyTorch
Hindi
bert
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
hindi
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-Hindi-BioClinicalBERT-Base-110M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-Hindi-BioClinicalBERT-Base-110M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-Hindi-BioClinicalBERT-Base-110M-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-Hindi-BioClinicalBERT-Base-110M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-Hindi-BioClinicalBERT-Base-110M-v1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "test_accuracy": 0.9858790087797722, | |
| "test_f1": 0.9280410067687455, | |
| "test_loss": 0.05012573301792145, | |
| "test_macro_f1": 0.940815574304646, | |
| "test_precision": 0.9254259501965924, | |
| "test_recall": 0.9306708844075392, | |
| "test_runtime": 1.9478, | |
| "test_samples_per_second": 1387.21, | |
| "test_steps_per_second": 22.076, | |
| "test_weighted_f1": 0.9267615644813842 | |
| } |