GPT-2 TensorFlow block class

gpt-2-block.py

def block(x, scope, *, past, hparams):
    with tf.variable_scope(scope):
        nx = x.shape[-1].value
        a, present = attn(norm(x, 'ln_1'), 'attn', nx, past=past, hparams=hparams)
        x = x + a
        m = mlp(norm(x, 'ln_2'), 'mlp', nx*4, hparams=hparams)
        x = x + m
        return x, present