| For example, if you're running inference on a question answering task, load the optimum/roberta-base-squad2 checkpoint which contains a model.onnx file: | |
| from transformers import AutoTokenizer, pipeline | |
| from optimum.onnxruntime import ORTModelForQuestionAnswering | |
| model = ORTModelForQuestionAnswering.from_pretrained("optimum/roberta-base-squad2") | |
| tokenizer = AutoTokenizer.from_pretrained("deepset/roberta-base-squad2") | |
| onnx_qa = pipeline("question-answering", model=model, tokenizer=tokenizer) | |
| question = "What's my name?" |