Struct TokenizerConfig 

pub struct TokenizerConfig {
    pub tokenizer_type: TokenizerType,
    pub path: String,
    pub add_special_tokens: bool,
    pub use_fast: bool,
    pub truncation: Option<TruncationConfig>,
    pub padding: Option<PaddingConfig>,
    pub chat_template: Option<String>,
    pub extra_options: HashMap<String, Value>,
}

Tokenizer configuration

Fields

tokenizer_type: TokenizerType

Tokenizer type

path: String

Path to tokenizer files

add_special_tokens: bool

Whether to add special tokens during encoding

use_fast: bool

Whether to use fast tokenization (if available)

truncation: Option<TruncationConfig>

Truncation configuration

padding: Option<PaddingConfig>

Padding configuration

chat_template: Option<String>

Chat template (if any)

extra_options: HashMap<String, Value>

Additional tokenizer-specific options

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<'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.