Enum TokenizerFamily 

pub enum TokenizerFamily {
    GPT4,
    Claude,
    Gemini,
    Llama,
    Generic,
}

The tokeniser family that governs counting heuristics.

Variants

GPT4

GPT-3.5 / GPT-4 (cl100k_base) — ~4 chars per token.

Claude

Claude 2 / 3 family — ~3.8 chars per token (slightly denser vocab).

Gemini

Google Gemini — ~3.9 chars per token.

Llama

Meta LLaMA / LLaMA-2 — ~3.6 chars per token (SentencePiece).

Generic

Unknown family — falls back to 4 chars per token.

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 Eq for TokenizerFamily

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 StructuralPartialEq for TokenizerFamily