TokenizerAccuracy

org.llm4s.context.tokens.TokenizerAccuracy
See theTokenizerAccuracy companion object
sealed trait TokenizerAccuracy

Represents the accuracy of tokenizer mapping for a model.

This sealed trait hierarchy captures three levels of accuracy:

  • '''Exact''': Native tokenizer available, counts are precise
  • '''Approximate''': Using a similar tokenizer, counts may differ
  • '''Unknown''': Unknown model, using fallback tokenizer

Attributes

See also
Companion
object
Graph
Supertypes
class Object
trait Matchable
class Any
Known subtypes
class Approximate
class Exact
class Unknown

Members list

Value members

Abstract methods

def description: String

Human-readable description of the accuracy level.

Human-readable description of the accuracy level.

Attributes

def isExact: Boolean

True if token counts will match actual API usage.

True if token counts will match actual API usage.

Attributes