Gpt2Tokenizer

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

3. final def ==(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

4. val appendForPieceId: Option[String]

   

   Attributes

   protected

   Definition Classes

   BpeTokenizer

5. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

6. def bpe(indToken: IndexedToken): Array[TokenPiece]

   

   Do the BPE algorithm.

   Do the BPE algorithm. Goal is to find the token as the largest words in the known vocabulary. If not possible, the word is split into smaller subwords, until they are known.

   returns

   Array of TokenPieces, corresponding to encoded token

   Attributes

   protected

   Definition Classes

   BpeTokenizer

7. val bpeRanks: Map[(String, String), Int]

   

   Attributes

   protected

   Definition Classes

   BpeTokenizer

8. val cache: Map[String, Array[String]]

   

   cache for already encoded tokens

   cache for already encoded tokens

   Attributes

   protected

   Definition Classes

   BpeTokenizer

9. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

10. def decodeTokens(tokens: Array[Int]): String

    

11. def encode(indTokens: Array[IndexedToken]): Array[TokenPiece]

    

    Definition Classes

    BpeTokenizer

12. def encode(indToken: IndexedToken): Array[TokenPiece]

    

    Definition Classes

    BpeTokenizer

13. final def eq(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

14. def equals(arg0: Any): Boolean

    

    Definition Classes

    AnyRef → Any

15. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

16. def getBpeRanking: ((String, String)) ⇒ Int

    

    Rankings for the byte pairs.

    Rankings for the byte pairs. Derived from merges.txt

    Attributes

    protected

    Definition Classes

    BpeTokenizer

17. def getBytePairs(word: Array[String]): Array[(String, String)]

    

    Create a sequence of byte-pairs of the word

    Create a sequence of byte-pairs of the word

    Attributes

    protected

    Definition Classes

    BpeTokenizer

18. final def getClass(): Class[_]

    

    Definition Classes

    AnyRef → Any

19. def getTokenPieces(indToken: IndexedToken, word: Array[String], processedToken: String): Array[TokenPiece]

    

    Attributes

    protected

    Definition Classes

    BpeTokenizer

20. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

21. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

22. val merges: Map[(String, String), Int]

    

    Definition Classes

    BpeTokenizer

23. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

24. final def notify(): Unit

    

    Definition Classes

    AnyRef

25. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

26. var padWithSentenceTokens: Boolean

    

    Definition Classes

    BpeTokenizer

27. def performMerges(wordChars: Array[String], charPairs: Array[(String, String)]): Array[String]

    

    Attributes

    protected

    Definition Classes

    BpeTokenizer

28. def preProcessTokenForBpe(token: String): String

    

    Definition Classes

    Gpt2Tokenizer → BpeTokenizer

29. val prependForPieceId: Option[String]

    

    Definition Classes

    Gpt2Tokenizer → BpeTokenizer

30. val sentencePadding: (String, String)

    

    Special tokens of the model for processing

    Special tokens of the model for processing

    Definition Classes

    BpeTokenizer

31. val specialTokens: SpecialTokens

    

    Definition Classes

    BpeTokenizer

32. def splitOnSpecialToken(specialToken: SpecialToken, text: String): ListBuffer[String]

    

    Split the the individual sub texts on special tokens, e.g.

    Split the the individual sub texts on special tokens, e.g. masking etc.

    Attributes

    protected

    Definition Classes

    BpeTokenizer

33. val splitPattern: Regex

    

34. final def synchronized[T0](arg0: ⇒ T0): T0

    

    Definition Classes

    AnyRef

35. def toString(): String

    

    Definition Classes

    AnyRef → Any

36. def tokenize(sentence: Sentence): Array[IndexedToken]

    

    Tokenize considering special tokens and split algorithm

    Tokenize considering special tokens and split algorithm

    Definition Classes

    BpeTokenizer

37. def tokenizeSubText(text: String, indexOffset: Int): Array[IndexedToken]

    

    Needs to be implemented

    Needs to be implemented

    Definition Classes

    Gpt2Tokenizer → BpeTokenizer

38. val vocab: Map[String, Int]

    

    Definition Classes

    BpeTokenizer

39. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

40. final def wait(arg0: Long, arg1: Int): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

41. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )