blob: 2b416e6c009055caa1f51e5e57fc5cb283255323 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
|
"""Normalization layers for transfromers.
Copied from lucidrains:
https://github.com/lucidrains/x-transformers/blob/main/x_transformers/x_transformers.py
"""
import torch
from torch import nn
from torch import Tensor
class RMSNorm(nn.Module):
"""Root mean square layer normalization."""
def __init__(self, dim: int, eps: float = 1e-8) -> None:
super().__init__()
self.scale = dim ** -0.5
self.eps = eps
self.g = nn.Parameter(torch.ones(dim))
def forward(self, x: Tensor) -> Tensor:
"""Applies normalization."""
norm = torch.norm(x, dim=-1, keepdim=True) * self.scale
return x / norm.clamp(min=self.eps) * self.g
|
