Mila 0.13.48
Deep Neural Network Library
Loading...
Searching...
No Matches
Mila::Data::Tokenizer Class Referenceabstractexport
Inheritance diagram for Mila::Data::Tokenizer:

Public Member Functions

virtual ~Tokenizer ()=default
virtual std::string decode (std::span< const TokenId > tokens)=0
virtual std::vector< TokenIdencode (const std::string &text)=0
virtual std::optional< TokenIdgetBosTokenId () const =0
virtual std::optional< TokenIdgetEosTokenId () const =0
virtual std::optional< TokenIdgetPadTokenId () const =0
virtual size_t getVocabSize () const =0
virtual bool isValidToken (TokenId tokenId) const =0
virtual std::string tokenToString (TokenId tokenId) const =0

Constructor & Destructor Documentation

◆ ~Tokenizer()

virtual Mila::Data::Tokenizer::~Tokenizer ( )
virtualdefault

Member Function Documentation

◆ decode()

virtual std::string Mila::Data::Tokenizer::decode ( std::span< const TokenId > tokens)
pure virtual

◆ encode()

virtual std::vector< TokenId > Mila::Data::Tokenizer::encode ( const std::string & text)
pure virtual

◆ getBosTokenId()

virtual std::optional< TokenId > Mila::Data::Tokenizer::getBosTokenId ( ) const
pure virtual

◆ getEosTokenId()

virtual std::optional< TokenId > Mila::Data::Tokenizer::getEosTokenId ( ) const
pure virtual

◆ getPadTokenId()

virtual std::optional< TokenId > Mila::Data::Tokenizer::getPadTokenId ( ) const
pure virtual

◆ getVocabSize()

virtual size_t Mila::Data::Tokenizer::getVocabSize ( ) const
pure virtual

◆ isValidToken()

virtual bool Mila::Data::Tokenizer::isValidToken ( TokenId tokenId) const
pure virtual

◆ tokenToString()

virtual std::string Mila::Data::Tokenizer::tokenToString ( TokenId tokenId) const
pure virtual

The documentation for this class was generated from the following file: