For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Python class

ConstantLayerNorm

`ConstantLayerNorm`

class max.nn.ConstantLayerNorm(dims, device, dtype, eps=1e-05)

source

Bases: Module

Layer normalization block with constant gamma and beta values.

When called, ConstantLayerNorm accepts a TensorValue and returns a normalized TensorValue of the same shape.

Parameters:

dims (int | tuple[int, ...])
device (DeviceRef)
dtype (DType)
eps (float)

`beta`

beta: npt.NDArray[np.floating[Any]]

source

`device`

device: DeviceRef

source

`dtype`

dtype: DType

source

`eps`

eps: float = 1e-05

source

`gamma`

gamma: npt.NDArray[np.floating[Any]]

source

ConstantLayerNorm​

beta​

device​

dtype​

eps​

gamma​