As is tradition in this book, I will show you how the entire architecture for this model fits together here:

def build_models(lstm_units, num_encoder_tokens, num_decoder_tokens):
    # train model
    encoder_input = Input(shape=(None, num_encoder_tokens), 
      name='encoder_input')
    encoder_outputs, state_h, state_c = LSTM(lstm_units, 
      return_state=True, name="encoder_lstm")(encoder_input)
    encoder_states = [state_h, state_c]
    decoder_input = Input(shape=(None, num_decoder_tokens), 
      name='decoder_input')
    decoder_lstm = LSTM(lstm_units, return_sequences=True, 
      return_state=True, name="decoder_lstm")
    decoder_outputs, _, _ = decoder_lstm(decoder_input,
                                         initial_state=encoder_states)
    decoder_dense = Dense(num_decoder_tokens, activation='softmax',
                          name='softmax_output')
    decoder_output = decoder_dense(decoder_outputs)
    model = Model([encoder_input, decoder_input], decoder_output)
    model.compile(optimizer='rmsprop', loss='categorical_crossentropy')

    encoder_model = Model(encoder_input, encoder_states)
    decoder_state_input_h = Input(shape=(lstm_units,))
    decoder_state_input_c = Input(shape=(lstm_units,))
    decoder_states_inputs = [decoder_state_input_h, 
      decoder_state_input_c]
    decoder_outputs, state_h, state_c = decoder_lstm(
        decoder_input, initial_state=decoder_states_inputs)
    decoder_states = [state_h, state_c]
    decoder_outputs = decoder_dense(decoder_outputs)
    decoder_model = Model(
        [decoder_input] + decoder_states_inputs,
        [decoder_outputs] + decoder_states)

    return model, encoder_model, decoder_model

Note that we are returning all three models here. After the training model is trained, I will serialize all three with the keras model.save() method.