Enum AttentionType 

pub enum AttentionType {
    MHA,
    MQA,
    GQA,
}

The type of attention mechanism in the transformer model.

Variants

MHA

Multi-Head Attention: num_kv_heads == num_heads

MQA

Multi-Query Attention: num_kv_heads == 1

GQA

Grouped-Query Attention: 1 < num_kv_heads < num_heads

Trait Implementations

impl Clone for AttentionType

fn clone(&self) -> AttentionType

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for AttentionType

impl Debug for AttentionType

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for AttentionType

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for AttentionType

impl PartialEq for AttentionType

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for AttentionType

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 AttentionType