Struct ModelData 

pub struct ModelData {
    pub vocab: Vec<TokenInfo>,
    pub special_tokens: Option<Vec<SpecialTokenInfo>>,
    pub config: TekkenConfig,
    pub audio: Option<AudioConfig>,
}

Complete model data loaded from a tokenizer configuration file.

This struct represents the entire configuration and data needed to initialize a Tekken tokenizer, typically loaded from a JSON file like tekken.json.

Fields

• vocab - All vocabulary tokens with their metadata
• special_tokens - Optional special token definitions
• config - Core tokenizer configuration
• audio - Optional audio processing configuration

Fields

vocab: Vec<TokenInfo>

All vocabulary tokens with their metadata.

special_tokens: Option<Vec<SpecialTokenInfo>>

Optional special token definitions (uses defaults if None).

config: TekkenConfig

Core tokenizer configuration parameters.

audio: Option<AudioConfig>

Optional audio processing configuration for multimodal support.

Trait Implementations

impl Clone for ModelData

fn clone(&self) -> ModelData

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelData

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelData

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ModelData

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

where __S: Serializer,

Serialize this value into the given Serde serializer.