gistfile1.txt

import onnxruntime as ort
from transformers import AutoTokenizer

session = ort.InferenceSession('./bge-small-en/model.onnx')
tokenizer = AutoTokenizer.from_pretrained("./bge-small-en")

inputs = tokenizer("hello world.", padding="longest", return_tensors="np")

inputs_onnx = {key: ort.OrtValue.ortvalue_from_numpy(value) for key, value in inputs.items()}

outputs = session.run(None, inputs_onnx)

print(f"Number of Dense Vectors: {len(outputs[0])}")
print(f"Dense Vector Length: {len(outputs[0][0])}")

gistfile2.txt

import onnxruntime as ort
import numpy as np

from transformers import AutoTokenizer

session = ort.InferenceSession('./multilingual-e5-small/model.onnx')
tokenizer = AutoTokenizer.from_pretrained("./multilingual-e5-small")

inputs = tokenizer("hello world.", padding="longest", return_tensors="np")
inputs["token_type_ids"] = np.zeros_like(inputs["input_ids"])

inputs_onnx = {key: ort.OrtValue.ortvalue_from_numpy(value) for key, value in inputs.items()}

outputs = session.run(None, inputs_onnx)

tokenizer.convert_ids_to_tokens(inputs["input_ids"][0])