from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import pipeline, AutoTokenizer
 
model = ORTModelForSequenceClassification.from_pretrained(onnx_path,file_name="model_optimized_quantized.onnx")
tokenizer = AutoTokenizer.from_pretrained(onnx_path)
 
q8_clf = pipeline("text-classification",model=model, tokenizer=tokenizer)
 
q8_clf("What is the exchange rate like on this app?")