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
25 lines
476 B
C++
25 lines
476 B
C++
#pragma once
|
|
|
|
#include <cstdint>
|
|
#include <memory>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
namespace engine::tokenizers {
|
|
|
|
struct TokenizedText {
|
|
std::string text;
|
|
std::vector<int32_t> token_ids;
|
|
};
|
|
|
|
class ITokenizer {
|
|
public:
|
|
virtual ~ITokenizer() = default;
|
|
|
|
virtual std::string family() const = 0;
|
|
virtual TokenizedText tokenize(const std::string & text) const = 0;
|
|
};
|
|
|
|
using TokenizerPtr = std::shared_ptr<ITokenizer>;
|
|
|
|
} // namespace engine::tokenizers
|