update documentation

Calling the parent constructor is needed, otherwise it will fail with the following error:
RuntimeError: It looks like you are subclassing `Model` and you forgot to call `super(YourClass, self).__init__()`. Always start with this line.
PiperOrigin-RevId: 207823589

tensorflow/python/keras/engine/training.py

@@ -74,6 +74,7 @@ class Model(Network):
   class MyModel(tf.keras.Model):
 
     def __init__(self):
+      super(MyModel, self).__init__()
       self.dense1 = tf.keras.layers.Dense(4, activation=tf.nn.relu)
       self.dense2 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)
 
@@ -94,6 +95,7 @@ def call(self, inputs):
   class MyModel(tf.keras.Model):
 
     def __init__(self):
+      super(MyModel, self).__init__()
       self.dense1 = tf.keras.layers.Dense(4, activation=tf.nn.relu)
       self.dense2 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)
       self.dropout = tf.keras.layers.Dropout(0.5)