add fourth chapter

cn-Book/4.从零开始实现一个用于文本生成的 GPT 模型.md

@@ -668,13 +668,13 @@ layers.4.0.weight has gradient mean of 1.3258541822433472
 >
 >      - 根据反向传播的原理，**无快捷连接**时，梯度必须逐层传递，如下：
 >
->      $$ \frac{\partial L}{\partial X_{1}}=\frac{\partial L}{\partial X_{3}} \cdot \frac{\partial X_{3}}{\partial X_{2}} \cdot \frac{\partial X_{2}}{\partial X_{1}} $$
+>         $$ \frac{\partial L}{\partial X_{1}}=\frac{\partial L}{\partial X_{3}} \cdot \frac{\partial X_{3}}{\partial X_{2}} \cdot \frac{\partial X_{2}}{\partial X_{1}} $$
 >
 >      这里，如果某一层的梯度值很小，那么梯度会被逐层缩小，导致梯度消失。
 >
 >      - **有快捷连接**时，假设我们在每一层之间都添加快捷连接，梯度的传播路径就多了一条直接路径：
 >
->        $$ \frac{\partial L}{\partial X_{1}}=\frac{\partial L}{\partial\left(X_{1}+F\left(X_{1}\right)\right)} \cdot\left(1+\frac{\partial F\left(X_{1}\right)}{\partial X_{1}}\right) $$
+>        $$\frac{\partial L}{\partial X_{1}}=\frac{\partial L}{\partial\left(X_{1}+F\left(X_{1}\right)\right)} \cdot\left(1+\frac{\partial F\left(X_{1}\right)}{\partial X_{1}}\right)$$
 >
 >        这样，即使 $` \frac{\partial F\left(X_{1}\right)}{\partial X_{1}} `$ 很小，梯度依然可以通过 111 这条路径直接传递到更前面的层。