Now, let's start by defining the model inputs as placeholders. The inputs of the model will be training data and the targets. We will also use a parameter called keep_probability for the dropout layer, which helps the model avoid overfitting:

def build_model_inputs(batch_size, num_steps):
    
    # Declare placeholders for the input and output variables
    inputs_x = tf.placeholder(tf.int32, [batch_size, num_steps], name='inputs')
    targets_y = tf.placeholder(tf.int32, [batch_size, num_steps], name='targets')
    
    # define the keep_probability for the dropout layer
    keep_probability = tf.placeholder(tf.float32, name='keep_prob')
    
    return inputs_x, targets_y, keep_probability