Some checks failed
Linux Build / Linux cpu (push) Has been cancelled
Linux Build / Linux cpu-clang (push) Has been cancelled
Linux Build / Linux vulkan (push) Has been cancelled
mac-build / macOS CPU (push) Has been cancelled
Nix Build / Nix (cpu) (push) Has been cancelled
Nix Build / Nix (vulkan) (push) Has been cancelled
windows-build / Windows CPU (push) Has been cancelled
26 lines
603 B
C++
26 lines
603 B
C++
#pragma once
|
|
|
|
#include <cstdint>
|
|
#include <filesystem>
|
|
#include <memory>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
namespace llama_tokenizer_vendor {
|
|
struct BpeVocabulary;
|
|
} // namespace llama_tokenizer_vendor
|
|
|
|
namespace engine::models::yue2 {
|
|
|
|
class Yue2TextTokenizer {
|
|
public:
|
|
explicit Yue2TextTokenizer(const std::filesystem::path & vocab_path);
|
|
|
|
std::vector<int32_t> encode(const std::string & text) const;
|
|
std::string decode(const std::vector<int32_t> & token_ids) const;
|
|
|
|
private:
|
|
std::shared_ptr<llama_tokenizer_vendor::BpeVocabulary> vocab_;
|
|
};
|
|
|
|
} // namespace engine::models::yue2
|