Struct TokenizerConfig 

pub struct TokenizerConfig {
    pub vocab_size: usize,
    pub min_frequency: usize,
    pub special_tokens: SpecialTokens,
    pub lowercase: bool,
    pub tokenizer_type: TokenizerType,
    pub normalization: Normalization,
}

Tokenizer configuration

Fields

vocab_size: usize

Target vocabulary size

min_frequency: usize

Minimum token frequency for training

special_tokens: SpecialTokens

Special tokens

lowercase: bool

Whether to lowercase input

tokenizer_type: TokenizerType

Tokenizer type

normalization: Normalization

Unicode normalization mode

Implementations

impl TokenizerConfig

pub fn bpe() -> Self

Create a BPE tokenizer config

pub fn wordpiece() -> Self

Create a WordPiece tokenizer config

pub fn char() -> Self

Create a character-level tokenizer config

pub fn with_vocab_size(self, size: usize) -> Self

Set vocabulary size

pub fn with_min_frequency(self, freq: usize) -> Self

Set minimum frequency

pub fn with_lowercase(self, lowercase: bool) -> Self

Enable lowercase preprocessing

pub fn with_normalization(self, normalization: Normalization) -> Self

Set the Unicode normalization mode.

Trait Implementations

impl Clone for TokenizerConfig

fn clone(&self) -> TokenizerConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TokenizerConfig

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

Formats the value using the given formatter.

impl Default for TokenizerConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for TokenizerConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TokenizerConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.