Struct Embedding 

pub struct Embedding {
    pub weight: Array,
}

A lookup table of dims-dimensional vectors for integer ids (MLX’s nn.Embedding).

Fields

weight: Array

The table, [num_embeddings, dims].

Implementations

impl Embedding

pub fn new(num_embeddings: usize, dims: usize) -> Result<Self>

A table drawn from a normal distribution with standard deviation 1/√dims, as MLX.

pub fn forward(&self, x: &Array) -> Result<Array>

The rows for the ids in x: shape x.shape + [dims].

pub fn as_linear(&self, x: &Array) -> Result<Array>

x Wᵀ: the table used as an output projection (tied embeddings).

Trait Implementations

impl Clone for Embedding

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Embedding

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

Formats the value using the given formatter.

impl Module for Embedding

fn visit(&mut self, p: &mut Parameters<'_>)

Reports every parameter and submodule to p, frozen ones included.

fn parameters(&self) -> Vec<(String, Array)>

Every parameter with its path (layers.0.weight), in visiting order.

fn trainable_parameters(&self) -> Vec<(String, Array)>

The parameters that are trained (not frozen), with their paths.

fn update_trainable(&mut self, values: &[Array]) -> Result<()>

Replaces the trainable parameters, given in the order of Module::trainable_parameters (as optimizers return them).

fn load_weights( &mut self, weights: impl IntoIterator<Item = (String, Array)>, strict: bool, ) -> Result<()>

Replaces parameters by path, as MLX’s load_weights: each weight must have its parameter’s shape (the dtype is kept as loaded). With strict, every parameter must be given and no unknown names are allowed.