Struct RmsNorm

pub struct RmsNorm {
    pub weight: Param<Array>,
    pub eps: f32,
}

Applies Root Mean Square normalization [1] to the inputs.

Concretely:

weight * x * MLX.rsqrt(x.square().mean() + eps)

where weight is initialized with ones and eps is a small float to ensure the numerical stability of inverse square root.

References

1. https://arxiv.org/abs/1910.07467

Fields

weight: Param<Array>

Weight

eps: f32

A small float to ensure the numerical stability

Implementations

impl RmsNorm

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

Creates a new instance of RmsNorm.

impl RmsNorm

pub const DEFAULT_EPS: f32 = 9.99999974E-6f32

Default value for eps.

Trait Implementations

impl Buildable for RmsNorm

type Builder = RmsNormBuilder

The builder type for this buildable type

impl Builder<RmsNorm> for RmsNormBuilder

type Error = Exception

Error with building

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

Build the type

impl Clone for RmsNorm

fn clone(&self) -> RmsNorm

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for RmsNorm

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

Formats the value using the given formatter.

impl Module<&Array> for RmsNorm

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 RmsNorm

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.