Loading...
Searching...
No Matches
tokenizer_operator.h File Reference
#include <array>
#include <memory>
#include <unordered_set>
#include "opennn/network/operators/operator.h"
#include "opennn/core/string_utilities.h"

Go to the source code of this file.

Classes

class  opennn::TokenizerOperator
 
class  opennn::WordLevelTokenizer
 
class  opennn::WordPieceTokenizer
 
class  opennn::BytePairTokenizer
 
class  opennn::Qwen3Tokenizer
 

Namespaces

namespace  opennn
 

Functions

vector< string > opennn::make_vocabulary (const unordered_map< string_view, size_t > &, span< const string > reserved_tokens, Index maximum_size, Index minimum_frequency)
 
constexpr size_t opennn::utf8_sequence_length (unsigned char lead) noexcept
 
constexpr bool opennn::is_utf8_continuation (unsigned char byte) noexcept
 
unique_ptr< TokenizerOperator > opennn::make_tokenizer_operator (string_view kind)