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

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

This model was exported using Optimum. It includes the INT8 - Optimized for Mobile (ARM64) quantization settings and a pre-compiled tokenizer.json for fast loading.