# Codeblock 7b
   def forward(self, features):  #(1)
      
       residual = features  #(2)
       print(f'features & residual\t: {residual.size()}')
      
       #(3)
       features, self_attn_weights = self.self_attention(query=features,
                                                         key=features,
                                                         value=features)
       print(f'after self attention\t: {features.size()}')
       print(f"self attn weights\t: {self_attn_weights.shape}")
      
       features = self.layer_norm_0(features + residual)  #(4)
       print(f'after norm\t\t: {features.size()}')
      

       residual = features
       print(f'\nfeatures & residual\t: {residual.size()}')
      
       features = self.ffn(features)  #(5)
       print(f'after ffn\t\t: {features.size()}')
      
       features = self.layer_norm_1(features + residual)
       print(f'after norm\t\t: {features.size()}')
      
       return features