GPT-2

        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

        residual = hidden_states
        hidden_states = self.ln_1(hidden_states)
        attn_output, _ = self.attn(
            hidden_states,
            past_key_values=past_key_values,
            attention_mask=attention_mask,
            use_cache=use_cache,
            **kwargs,
        )

… lines 281–281 omitted …

        hidden_states = attn_output + residual

… lines 283–302 omitted …

        residual = hidden_states
        hidden_states = self.ln_2(hidden_states)
        feed_forward_hidden_states = self.mlp(hidden_states)
        # residual connection
        hidden_states = residual + feed_forward_hidden_states

def norm(x, scope, *, axis=-1, epsilon=1e-5):
    """Normalize to mean = 0, std = 1, then do a diagonal affine transform."""
    with tf.variable_scope(scope):
        n_state = x.shape[-1].value
        g = tf.get_variable('g', [n_state], initializer=tf.constant_initializer(1))
        b = tf.get_variable('b', [n_state], initializer=tf.constant_initializer(0))
        u = tf.reduce_mean(x, axis=axis, keepdims=True)
        s = tf.reduce_mean(tf.square(x-u), axis=axis, keepdims=True)
        x = (x - u) * tf.rsqrt(s + epsilon)
        x = x*g + b
        return x

… lines 39–162 omitted …

        for layer, past in enumerate(pasts):
            h, present = block(h, 'h%d' % layer, past=past, hparams=hparams)
            presents.append(present)
        results['present'] = tf.stack(presents, axis=1)
        h = norm(h, 'ln_f')

        self.h = nn.ModuleList([GPT2Block(config, layer_idx=i) for i in range(config.num_hidden_layers)])
        self.ln_f = nn.LayerNorm(self.embed_dim, eps=config.layer_norm_epsilon)