ValueError: not enough values to unpack (expected 5, got 3) Bidirectional GRU attention based Keras

I wanted to implement attention based Bidirectional GRU model

lstm = layers.Bidirectional(layers.GRU(20, return_sequences = True, dropout=0.8), name="bi_lstm_0")(embedded_sequences)

# Getting our LSTM outputs
(lstm, forward_h, forward_c, backward_h, backward_c) = layers.Bidirectional(layers.GRU(20, return_sequences=True, return_state=True, dropout=0.8), name="bi_lstm_1")(lstm)

Getting Error below

ValueError: not enough values to unpack (expected 5, got 3)