NerGuard-0.3B-onnx-int8

import numpy as np
from optimum.onnxruntime import ORTModelForTokenClassification
from transformers import AutoTokenizer, pipeline
from pprint import pprint

# Load Quantized ONNX Model & Tokenizer from Hugging Face
model_name = "exdsgift/NerGuard-0.3B-onnx-int8"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = ORTModelForTokenClassification.from_pretrained(
    model_name,
    file_name="model_quantized.onnx"
)

# Initialize Pipeline
nlp = pipeline(
    "token-classification",
    model=model,
    tokenizer=tokenizer,
    aggregation_strategy="simple"
)

# Inference on multilingual samples
multilingual_cases = [
    "Please send the report to Mr. John Smith at [email protected] immediately.",
    "J'habite au 15 Rue de la Paix, Paris. Mon nom est Pierre Martin.",
    "Mein Name ist Thomas Müller und ich lebe in der Berliner Straße 5, München.",
    "La doctora Ana María González López trabaja en el Hospital Central de Madrid.",
    "Il codice fiscale di Mario Rossi è RSSMRA80A01H501U.",
    "Ik ben Sven van der Berg en mijn e-mailadres is [email protected]."
]

for text in multilingual_cases:
    results = nlp(text)
    print(f"\n--- Sample: {text} ---")
    pprint(results)