Enum AttentionAggregation

pub enum AttentionAggregation {
    Average,
    Maximum,
    Head(usize),
    Weighted(Vec<f64>),
}

Attention aggregation strategy

Variants

Average

Average across all heads

Maximum

Maximum across all heads

Head(usize)

Specific head only

Weighted(Vec<f64>)

Weighted combination of heads

Trait Implementations

impl Clone for AttentionAggregation

fn clone(&self) -> AttentionAggregation

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AttentionAggregation

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

Formats the value using the given formatter.

impl PartialEq for AttentionAggregation

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

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

const 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 StructuralPartialEq for AttentionAggregation