Enum TokenizerFamily 

pub enum TokenizerFamily {
    O200kBase,
    Cl100k,
    Gemini,
    Llama,
}

Tokenizer families for different LLM providers.

Different LLM families use different tokenizers, leading to 5–15% variance in token counts. This enum lets callers select the appropriate tokenizer.

Variants

O200kBase

GPT-4o, GPT-4-turbo (tiktoken o200k_base, exact)

Cl100k

Claude / Anthropic (approximated via tiktoken cl100k_base)

Gemini

Gemini / Google (o200k_base with 1.1× correction factor)

Llama

Llama 3+ (approximated via cl100k_base)

Trait Implementations

impl Clone for TokenizerFamily

fn clone(&self) -> TokenizerFamily

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for TokenizerFamily

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for TokenizerFamily

fn default() -> TokenizerFamily

Returns the “default value” for a type.

impl Display for TokenizerFamily

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Hash for TokenizerFamily

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for TokenizerFamily

fn eq(&self, other: &TokenizerFamily) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for TokenizerFamily

impl Eq for TokenizerFamily

impl StructuralPartialEq for TokenizerFamily