I’m trying to build a model for training data in python using TensorFlow, but it’s failing to build. Does anyone see any problems?

I’ve tried this so far:

def create_model(num_words, embedding_dim, lstm1_dim, lstm2_dim, num_categories):
    tf.random.set_seed(200)
    model = Sequential([layers.Dense(num_categories, activation='softmax'), layers.Embedding(num_words, embedding_dim),
                        layers.Bidirectional(layers.LSTM(lstm1_dim, return_sequences=True)), layers.Bidirectional(layers.LSTM(lstm2_dim))])
    
    model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy']) 
  
    return model

model = create_model(NUM_WORDS, EMBEDDING_DIM, 32, 16, 5)

print(model)

Whenever I print(model) it says <Sequential name=sequential, built=False>.