Views
No views yet
1import onnxruntime as ort
2from transformers import AutoTokenizer
3
4tokenizer = AutoTokenizer.from_pretrained("thomasht86/deepset-mxbai-embed-de-large-v1-onnx-fp16")
5session = ort.InferenceSession("model.onnx", providers=["CUDAExecutionProvider", "CPUExecutionProvider"])
6
7inputs = dict(tokenizer("Your text here", return_tensors="np"))
8outputs = session.run(None, inputs)
9embeddings = outputs[0]