PII NER Edge Optimized (INT8 ONNX)

Overview

INT8-quantized ONNX version of the fine-tuned DistilBERT PII detection model, optimized for fast and lightweight browser and edge inference.

This model is an INT8-quantized ONNX version of Musayusuf001/pii-detection-distilbert, fine-tuned on the AI4Privacy PII dataset.

The underlying DistilBERT model was fine-tuned on the AI4Privacy PII dataset:

https://www.kaggle.com/datasets/verracodeguacas/ai4privacy-pii

Use Cases

  • Real-time PII redaction
  • Browser NLP apps

Model Type

  • Token Classification (NER)
  • ONNX INT8 optimized

Usage (JavaScript)

import { pipeline } from '@huggingface/transformers';

const pipe = await pipeline( "token-classification", "samuelolubukun/pii-ner-edge-optimized" );

Downloads last month
27
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Musayusuf001/pii-detection-onnx