README.md

---
base_model: broadfield-dev/bert-small-ner-pii-tuned-12261022
library_name: transformers
tags:
- onnx
- transformers
- optimum
- onnxruntime
- token-classification
- int8
- quantized
- mobile
language: en
pipeline_tag: token-classification
---

# ONNX Export: broadfield-dev/bert-small-ner-pii-tuned-12261022

This is a version of [broadfield-dev/bert-small-ner-pii-tuned-12261022](https://huggingface.co/broadfield-dev/bert-small-ner-pii-tuned-12261022) that has been converted to ONNX and optimized.

## Model Details
- **Base Model:** `broadfield-dev/bert-small-ner-pii-tuned-12261022`
- **Task:** `token-classification`
- **Opset Version:** `17`
- **Optimization:** `INT8 - Optimized for Mobile (ARM64)`

## Usage

### Installation
```bash
pip install onnxruntime transformers
```

### Python Example
```python
from tokenizers import Tokenizer
import onnxruntime as ort
import numpy as np

# 1. Load the lightweight tokenizer (No Transformers dependency needed)
tokenizer = Tokenizer.from_pretrained("broadfield-dev/bert-small-ner-pii-tuned-12261022-onnx")

# 2. Load the ONNX model
session = ort.InferenceSession("model.onnx")

# 3. Preprocess (Simple text encoding)
text = "Run inference on mobile!"
encoding = tokenizer.encode(text)

# Prepare inputs (Exact names vary by model, usually input_ids + attention_mask)
inputs = {{
    "input_ids": np.array([encoding.ids], dtype=np.int64),
    "attention_mask": np.array([encoding.attention_mask], dtype=np.int64)
}}

# 4. Run Inference
outputs = session.run(None, inputs)
print("Output logits shape:", outputs[0].shape)

```

## About this Export
This model was exported using [Optimum](https://huggingface.co/docs/optimum/index) and `onnxruntime`. 
It includes the `INT8 - Optimized for Mobile (ARM64)` quantization settings.