Enum PoolingStrategy 

pub enum PoolingStrategy {
    Mean,
    Max,
    WeightedMean,
    FirstToken,
}

Strategy for aggregating per-word embeddings into a sentence vector.

Variants

Mean

Average of all token embeddings.

Max

Element-wise maximum across token embeddings.

WeightedMean

Position-weighted mean (later tokens slightly up-weighted).

FirstToken

CLS-style: use only the first token’s representation.

Trait Implementations

impl Clone for PoolingStrategy

fn clone(&self) -> PoolingStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PoolingStrategy

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

Formats the value using the given formatter.

impl Default for PoolingStrategy

fn default() -> PoolingStrategy

Returns the “default value” for a type.

impl PartialEq for PoolingStrategy

fn eq(&self, other: &PoolingStrategy) -> 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 Eq for PoolingStrategy

impl StructuralPartialEq for PoolingStrategy