| For example, we can load and run the model with ONNX | |
| Runtime as follows: | |
| thon | |
| from transformers import AutoTokenizer | |
| from optimum.onnxruntime import ORTModelForQuestionAnswering | |
| tokenizer = AutoTokenizer.from_pretrained("distilbert_base_uncased_squad_onnx") | |
| model = ORTModelForQuestionAnswering.from_pretrained("distilbert_base_uncased_squad_onnx") | |
| inputs = tokenizer("What am I using? |