Struct TransformerLayerConfig 

pub struct TransformerLayerConfig {
    pub attention: AttentionConfig,
    pub feed_forward: FeedForwardConfig,
    pub pre_norm: bool,
}

Configuration for a complete transformer layer

Fields

attention: AttentionConfig

Attention configuration

feed_forward: FeedForwardConfig

Feed-forward configuration

pre_norm: bool

Whether to use pre-layer normalization (vs post)

Implementations

impl TransformerLayerConfig

pub fn new(d_model: usize, n_heads: usize, d_ff: usize) -> Result<Self>

Create a new transformer layer configuration

pub fn with_pre_norm(self, pre_norm: bool) -> Self

Set pre-normalization vs post-normalization

pub fn validate(&self) -> Result<()>

Validate configuration

Trait Implementations

impl Clone for TransformerLayerConfig

fn clone(&self) -> TransformerLayerConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TransformerLayerConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for TransformerLayerConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for TransformerLayerConfig

fn eq(&self, other: &TransformerLayerConfig) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for TransformerLayerConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for TransformerLayerConfig