Struct QuantizedEmbedding

pub struct QuantizedEmbedding {
    pub group_size: i32,
    pub bits: i32,
    pub scales: Param<Array>,
    pub biases: Param<Array>,
    pub inner: Embedding,
}

The same as Embedding but with a quantized weight matrix.

Fields

group_size: i32

Quantization group size. Default to QuantizedEmbedding::DEFAULT_GROUP_SIZE

bits: i32

Bits per parameter. Default to QuantizedEmbedding::DEFAULT_BITS

scales: Param<Array>

Scales

biases: Param<Array>

Biases

inner: Embedding

Inner embedding

Implementations

impl QuantizedEmbedding

pub fn new( embedding_count: impl Into<i32>, dimensions: impl Into<i32>, ) -> Result<Self, <<Self as Buildable>::Builder as Builder<Self>>::Error>

Creates a new instance of QuantizedEmbedding.

impl QuantizedEmbedding

pub const DEFAULT_GROUP_SIZE: i32 = 64i32

Default group size

pub const DEFAULT_BITS: i32 = 4i32

Default bits

pub fn try_from_embedding( embedding: Embedding, group_size: impl Into<Option<i32>>, bits: impl Into<Option<i32>>, ) -> Result<Self, Exception>

Convert an embedding layer to a quantized embedding layer.

Params

• embedding: The embedding layer to convert.
• group_size: The group size to use for the quantized weight. Default to QuantizedEmbedding::DEFAULT_GROUP_SIZE
• bits: The bit width to use for the quantized weight. Default to QuantizedEmbedding::DEFAULT_BITS

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

Call the embedding layer as a linear layer.

Use this for example when input embedding and output projection weights are tied.

Trait Implementations

impl Buildable for QuantizedEmbedding

type Builder = QuantizedEmbeddingBuilder

The builder type for this buildable type

impl Builder<QuantizedEmbedding> for QuantizedEmbeddingBuilder

type Error = Exception

Error with building

fn build(self) -> Result<QuantizedEmbedding, Self::Error>

Build the type

impl Clone for QuantizedEmbedding

fn clone(&self) -> QuantizedEmbedding

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizedEmbedding

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

Formats the value using the given formatter.

impl Module<&Array> for QuantizedEmbedding

type Error = Exception

Error type for the module.

type Output = Array

Output type of the module.

fn forward(&mut self, x: &Array) -> Result<Array, Self::Error>

Forward pass of the module.

fn training_mode(&mut self, mode: bool)

Set whether the module is in training mode.

impl ModuleParameters for QuantizedEmbedding

fn freeze_parameters(&mut self, recursive: bool)

Freeze all parameters in the module.

fn unfreeze_parameters(&mut self, recursive: bool)

Unfreeze all parameters in the module.

fn parameters(&self) -> ModuleParamRef<'_>

Get references to the module parameters.

fn parameters_mut(&mut self) -> ModuleParamMut<'_>

Get mutable references to the module parameters.

fn trainable_parameters(&self) -> ModuleParamRef<'_>

Get references to the trainable parameters. A parameter is trainable if it is NOT frozen.

fn all_frozen(&self) -> Option<bool>

Check if all parameters in the module are frozen. Returns None if there are no parameters.

fn any_frozen(&self) -> Option<bool>

Check if any parameter in the module is frozen. Returns None if there are no parameters.

fn update(&mut self, parameters: ModuleParam)

Update the module parameters.

fn update_flattened(&mut self, flattened_parameters: FlattenedModuleParam)

Update the module parameters from a flattened representation.

impl TryFrom<Embedding> for QuantizedEmbedding

type Error = Exception

The type returned in the event of a conversion error.

fn try_from(embedding: Embedding) -> Result<Self, Self::Error>

Performs the conversion.