ONNX Model Support

[zhipeng9802]

Feature request / 功能建议

支持ONNX Model的加载和推理

Motivation / 动机

在仅有CPU的环境下，我不得不考虑使用CPU去运行Embedding & Reranker 模型，经过测试，使用onnx拥有相较于
Sentence Transformer更快的处理速度

Your contribution / 您的贡献

https://huggingface.co/docs/optimum/v1.3.0/en/onnxruntime/modeling_ort#optimum.onnxruntime.ORTModelForSequenceClassification

https://github.com/onnx/onnx

[qinxuye]

Do you have some data to compare ONNX and sentence-transformers?

[zhipeng9802]

Do you have some data to compare ONNX and sentence-transformers?

I don't have a lot of data, just a simple test using internal industry knowledge data