Uses of Class
org.tribuo.util.tokens.impl.SplitFunctionTokenizer
Package
Description
Simple fixed rule tokenizers.
Provides an implementation of a Wordpiece tokenizer which implements
to the Tribuo
Tokenizer
API.-
Uses of SplitFunctionTokenizer in org.tribuo.util.tokens.impl
Modifier and TypeClassDescriptionclass
This implementation ofTokenizer
is instantiated with an array of characters that are considered split characters.class
A simple tokenizer that splits on whitespace. -
Uses of SplitFunctionTokenizer in org.tribuo.util.tokens.impl.wordpiece
Modifier and TypeClassDescriptionclass
This is a tokenizer that is used "upstream" ofWordpieceTokenizer
and implements much of the functionality of the 'BasicTokenizer' implementation in huggingface.