Struct TextEncoderConfig 

pub struct TextEncoderConfig {
    pub vocab_size: usize,
    pub max_seq_len: usize,
    pub d_model: usize,
    pub depth: usize,
    pub num_heads: usize,
    pub mlp_dim: usize,
    pub dropout: f64,
    pub out_dim: Option<usize>,
}

Configuration for the text transformer encoder.

Fields

vocab_size: usize

Vocabulary size (default: 32 000, c4_en SentencePiece vocabulary).

max_seq_len: usize

Maximum token sequence length.

d_model: usize

Transformer hidden dimension (ViT-B = 768).

depth: usize

Number of transformer layers (ViT-B = 12).

num_heads: usize

Number of attention heads per layer.

mlp_dim: usize

Feed-forward MLP hidden dimension.

dropout: f64

Dropout probability.

out_dim: Option<usize>

Output projection dimension. None means no projection (identity).

Trait Implementations

impl Clone for TextEncoderConfig

fn clone(&self) -> TextEncoderConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TextEncoderConfig

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

Formats the value using the given formatter.

impl Default for TextEncoderConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for TextEncoderConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TextEncoderConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.