Fix cross-attention (#210)

* Fix cross-attention

With the current code, ln2 is a no-op. Its output should be passed to the cross-attention layer

* Add name to contributors

ACKNOWLEDGMENTS.md

@@ -7,6 +7,7 @@ with a short description of your contribution(s) below. For example:
 
 MLX was developed with contributions from the following individuals:
   
+- Juarez Bochi: Fixed bug in cross attention.
 
 # Third-Party Software
 

python/mlx/nn/layers/transformer.py

@@ -157,7 +157,7 @@ class TransformerDecoderLayer(Module):
         x = x + y
 
         y = self.ln2(x)
-        y = self.cross_attention(x, memory, memory, memory_mask)
+        y = self.cross_attention(y, memory, memory, memory_mask)
         x = x + y
 
         y = self.ln3(x)