Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- token-classification
|
| 5 |
+
- pii-detection
|
| 6 |
+
- privacy
|
| 7 |
+
- named-entity-recognition
|
| 8 |
+
language:
|
| 9 |
+
- en
|
| 10 |
+
pipeline_tag: token-classification
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# PII Detection Model
|
| 14 |
+
|
| 15 |
+
This model is fine-tuned for detecting Personally Identifiable Information (PII) in text.
|
| 16 |
+
|
| 17 |
+
## Detected PII Types
|
| 18 |
+
- Names
|
| 19 |
+
- Email addresses
|
| 20 |
+
- Phone numbers
|
| 21 |
+
- Aadhaar numbers
|
| 22 |
+
- PAN cards
|
| 23 |
+
- Credit card numbers
|
| 24 |
+
|
| 25 |
+
## Usage
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
from transformers import pipeline
|
| 29 |
+
|
| 30 |
+
# Load the model
|
| 31 |
+
pii_pipe = pipeline(
|
| 32 |
+
"token-classification",
|
| 33 |
+
model="Dombara/pii-detection-model",
|
| 34 |
+
aggregation_strategy="simple"
|
| 35 |
+
)
|
| 36 |
+
|
| 37 |
+
# Detect PII
|
| 38 |
+
text = "Contact John Doe at [email protected] or 9876543210"
|
| 39 |
+
results = pii_pipe(text)
|
| 40 |
+
print(results)
|
| 41 |
+
```
|
| 42 |
+
|
| 43 |
+
## Model Details
|
| 44 |
+
- Base model: DeBERTa
|
| 45 |
+
- Fine-tuned for PII detection
|
| 46 |
+
- Supports English text
|