Struct TransformerEncoderConfig 

pub struct TransformerEncoderConfig {
    pub vocab_size: usize,
    pub hidden_size: usize,
    pub num_heads: usize,
    pub num_layers: usize,
    pub max_seq_len: usize,
    pub dropout: f32,
    pub seed: u64,
}

Configuration for TransformerTextEncoder.

Fields

vocab_size: usize

Vocabulary size (number of distinct token IDs).

hidden_size: usize

Dimensionality of token + position embeddings.

num_heads: usize

Number of attention heads.

num_layers: usize

Number of encoder layers.

max_seq_len: usize

Maximum sequence length supported.

dropout: f32

Dropout probability (applied during training; unused at inference).

seed: u64

PRNG seed for weight initialisation.

Trait Implementations

impl Clone for TransformerEncoderConfig

fn clone(&self) -> TransformerEncoderConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TransformerEncoderConfig

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

Formats the value using the given formatter.

impl Default for TransformerEncoderConfig

fn default() -> Self

Returns the “default value” for a type.