---
title: "LayerNorm"
sidebar_label: "LayerNorm"
description: "The clika_runtime.nn LayerNorm class."
---

<!-- Generated by tools/api_reference/generate_api_docs.py. Do not edit. -->

LayerNorm(normalized_shape, eps=1e-05, elementwise_affine=True, bias=True, device=None, dtype=None, *, activation=None)

    ``y = (x - mean) / sqrt(var + eps) * weight + bias`` with the statistics
    over the last dimension, of size ``normalized_shape``.

    Args:
        normalized_shape: the trailing size (an int, or a one-element
            sequence).
        eps: added to the variance for numerical stability.
        elementwise_affine: declare the ``weight`` (and ``bias``) slots;
            ``False`` is not served by this layer (use
            ``nn.functional.layer_norm``).
        bias: declare the bias slot.
        device: where the layer's tensors live; ``None`` declares on the
            cpu.
        dtype: the weight dtype the layer declares; ``None`` declares the
            default dtype (:func:`~clika_runtime.get_default_dtype`). A
            ``load_state_dict`` casts the checkpoint to the declared dtype;
            ``assign=True`` adopts the checkpoint's own dtype instead.
        activation: a fused epilogue applied to every output (a name such
            as ``"gelu"`` or an :class:`~clika_runtime.Activation`
            value); ``None`` for none.
    

## `__init__`

```python
__init__(self, normalized_shape: 'int | Sequence[int]', eps: 'float' = 1e-05, elementwise_affine: 'bool' = True, bias: 'bool' = True, device: 'Device | str | None' = None, dtype: 'DtypeLike | None' = None, *, activation: 'ActivationLike' = None) -> 'None'
```

Initialize self.  See help(type(self)) for accurate signature.

## `extra_repr`

```python
extra_repr(self) -> 'str'
```

extra_repr() -> str

One line of per-class detail for :meth:`__repr__`; a layer prints
its geometry here (``in_features=64, out_features=256``).

## `forward`

```python
forward(self, input: 'Tensor') -> 'Tensor'
```

forward(input) -> Tensor

``[*, normalized_shape]`` to the same shape; the output dtype follows
the input.

## `set_weights`

```python
set_weights(self, weight: 'Tensor', bias: 'Tensor | None' = None) -> 'None'
```

set_weights(weight, bias=None) -> None

Bind the declared slots directly; raises RuntimeError on a shape
mismatch.