Устройство трансформеров — теория и практика с нуля — Encoder block

class EncoderBlock(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout=0.1):
        super().__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.ffn = PositionwiseFFN(d_model, d_ff, dropout)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x, mask=None):
        attn_out = self.self_attn(x, mask)
        x = self.norm1(x + self.dropout(attn_out))
        ffn_out = self.ffn(x)
        x = self.norm2(x + self.dropout(ffn_out))
        return x