关于Annotated Transformer Encoder LayerNorm实现正确性的问询

• Transformer原论文规定的子层输出逻辑为：LayerNorm(x + Dropout(SubLayer(x)))，即LayerNorm要在**Dropout(子层输出)**之后应用，属于「后归一化」结构。
• 但《Annotated Transformer》中的实现将LayerNorm置于子层之前，逻辑为：x + Dropout(SubLayer(LayerNorm(x)))，与原论文顺序完全相反，对应代码如下：

class SublayerConnection(nn.Module):
    """
    A residual connection followed by a layer norm.
    Note for code simplicity the norm is first as opposed to last.
    """

    def __init__(self, size, dropout):
        super(SublayerConnection, self).__init__()
        self.norm = LayerNorm(size)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x, sublayer):
        "Apply residual connection to any sublayer with the same size."
        return x + self.dropout(sublayer(self.norm(x)))   # <--- LayerNorm before SubLayer

从严格贴合原论文设计的角度看，这个实现不符合规定，但代码注释已明确说明「为了代码简洁将归一化放在前面而非后面」，属于故意采用的变体。这种「预归一化」的方式后续在实践中被证明训练更稳定，如今不少Transformer衍生架构也会采用，但确实和原论文的原始设计存在差异。

内容的提问来源于stack exchange，提问作者mon