fix add_n doc (eng) (#28464)

fix the add_n english doc

python/paddle/tensor/math.py

@@ -717,36 +717,40 @@ def sum(x, axis=None, dtype=None, keepdim=False, name=None):
 @templatedoc(op_type="sum")
 def add_n(inputs, name=None):
     """
-    ${comment}
+    This OP is used to sum one or more Tensor of the input.
+    
+    For example:
+
+    .. code-block:: text
     
         Case 1:
-    ::
+
             Input:
-            Input. Shape = [2, 3]
-            Input = [[1, 2, 3],
+                input.shape = [2, 3]
+                input = [[1, 2, 3],
                          [4, 5, 6]]
 
             Output:
-            The output. Shape = [2, 3]
-            Output = [[1, 2, 3],
+                output.shape = [2, 3]
+                output = [[1, 2, 3],
                           [4, 5, 6]]
 
         Case 2:
-    ::
+       
             Input:
                 First input:
-            Input1. Shape = [2, 3]
+                    input1.shape = [2, 3]
                     Input1 = [[1, 2, 3],
                               [4, 5, 6]]
 
                 The second input:
-            Input2. Shape = [2, 3]
-            Input2 = [[7, 8, 9],
+                    input2.shape = [2, 3]
+                    input2 = [[7, 8, 9],
                               [10, 11, 12]]
 
                 Output:
-            The output. Shape = [2, 3]
-            Output = [[8, 10, 12],
+                    output.shape = [2, 3]
+                    output = [[8, 10, 12],
                               [14, 16, 18]]
 
     Args: