refactor: 拆分 module.py 为 components 子包
- rope/linear/norm/embedding/mlp/attention/decoder_block 各自独立文件 - 依赖单向无循环 - 公开接口不变,外部无需修改
This commit is contained in:
@@ -0,0 +1,15 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from torch import Tensor
|
||||
|
||||
|
||||
class RMSNorm(nn.Module):
|
||||
def __init__(self, dim, norm_eps):
|
||||
super().__init__()
|
||||
self.weight = nn.Parameter(torch.ones(dim))
|
||||
self.normalized_shape = (dim,)
|
||||
self.norm_eps = norm_eps
|
||||
|
||||
def forward(self, x: Tensor) -> Tensor:
|
||||
return F.rms_norm(x, self.normalized_shape, self.weight, self.norm_eps)
|
||||
Reference in New Issue
Block a user