Struct HyperConnections 

pub struct HyperConnections {
    pub lanes: usize,
    pub rank: usize,
}

Hyper-connections: the residual is lanes copies of the hidden state. Before each sublayer the lanes are normed each on its own (one weight across all of them), weighted by σ(up·silu(down·x̂ / lanes)) through a bottleneck of rank and averaged into the sublayer’s input; the sublayer’s output joins every lane scaled by 2σ(inject·x̂ / lanes). A last mix with no injection feeds the head in place of an output norm.

Fields

lanes: usize

rank: usize

Trait Implementations

impl Clone for HyperConnections

fn clone(&self) -> HyperConnections

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for HyperConnections

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

Formats the value using the given formatter.

impl PartialEq for HyperConnections

fn eq(&self, other: &HyperConnections) -> 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 Copy for HyperConnections

impl Eq for HyperConnections

impl StructuralPartialEq for HyperConnections