Fix value_dim in TransformerDecoder's cross-attn layer (#667)

* Fix  in TransformerDecoder's cross-attn layer

* Revert UT

Author: abheesht17

keras_nlp/layers/transformer_decoder.py

@@ -165,7 +165,7 @@ def _build(self, input_shape, has_cross_attention):
             self._cross_attention_layer = keras.layers.MultiHeadAttention(
                 num_heads=self.num_heads,
                 key_dim=head_dim,
-                value_dim=hidden_dim,
+                value_dim=head_dim,
                 dropout=self.dropout,
                 kernel_initializer=clone_initializer(self.kernel_initializer),
                 bias_initializer=clone_initializer(self.bias_initializer),