Enum Encoding 

pub enum Encoding {
    Cl100kBase,
    O200kBase,
    LlamaBpe,
    Heuristic,
}

Tokenizer encoding type

Different models use different tokenizers. The encoding type determines which tokenizer to use for accurate token counting.

Variants

Cl100kBase

OpenAI cl100k_base encoding (GPT-3.5, GPT-4) - via tiktoken

O200kBase

OpenAI o200k_base encoding (GPT-4o, o1, o3) - via tiktoken

LlamaBpe

Llama-style BPE tokenizer (Llama, Mistral, and derivatives)

Heuristic

Heuristic fallback (~4 characters per token)

Implementations

impl Encoding

pub fn infer_from_id(id: &str) -> Self

Infer encoding from model ID

Examples

use m2m::models::Encoding;

assert_eq!(Encoding::infer_from_id("openai/gpt-4o"), Encoding::O200kBase);
assert_eq!(Encoding::infer_from_id("openai/gpt-4"), Encoding::Cl100kBase);
assert_eq!(Encoding::infer_from_id("meta-llama/llama-3.1-70b"), Encoding::LlamaBpe);

pub fn name(&self) -> &'static str

Get encoding name as string

Trait Implementations

impl Clone for Encoding

fn clone(&self) -> Encoding

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Encoding

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

Formats the value using the given formatter.

impl Default for Encoding

fn default() -> Encoding

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Encoding

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Hash for Encoding

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 Encoding

fn eq(&self, other: &Encoding) -> 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 Serialize for Encoding

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for Encoding

impl Eq for Encoding

impl StructuralPartialEq for Encoding