microsoft/onnxruntime-extensions
Publicmirrored fromhttps://github.com/microsoft/onnxruntime-extensionsAvailable
tokenizer/sentencepiece_tokenizer.hpp
25lines · modecode
| 1 | // Copyright (c) Microsoft Corporation. All rights reserved. |
| 2 | // Licensed under the MIT License. |
| 3 | |
| 4 | #pragma once |
| 5 | |
| 6 | #include "kernels/kernels.h" |
| 7 | #include "utils.h" |
| 8 | #include "sentencepiece_processor.h" |
| 9 | |
| 10 | struct KernelSentencepieceTokenizer : BaseKernel { |
| 11 | KernelSentencepieceTokenizer(OrtApi api, const OrtKernelInfo* info); |
| 12 | void Compute(OrtKernelContext* context); |
| 13 | |
| 14 | private: |
| 15 | sentencepiece::SentencePieceProcessor tokenizer_; |
| 16 | }; |
| 17 | |
| 18 | struct CustomOpSentencepieceTokenizer : Ort::CustomOpBase<CustomOpSentencepieceTokenizer, KernelSentencepieceTokenizer> { |
| 19 | void* CreateKernel(OrtApi api, const OrtKernelInfo* info) const; |
| 20 | const char* GetName() const; |
| 21 | size_t GetInputTypeCount() const; |
| 22 | ONNXTensorElementDataType GetInputType(size_t index) const; |
| 23 | size_t GetOutputTypeCount() const; |
| 24 | ONNXTensorElementDataType GetOutputType(size_t index) const; |
| 25 | }; |
| 26 | |