Add suggestions.

src/continuiti/networks/multi_head_attention.py

@@ -12,13 +12,14 @@
 class MultiHeadAttention(nn.Module):
     r"""Multi-Head Attention module.
 
-    Module as described in the paper "Attention is All you Need"
-    (https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf) with
-    optional bias for the projections.
+    Module as described in the paper [Attention is All you Need](https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf)
+    with optional bias for the projections.
 
     $$MultiHead(Q,K,V)=Concat(head_1,\dots,head_n)W^O + b^O$$
+
     where
-    $$head_i=Attention(QW_i^Q+b_i^Q, KW_i^K+b_i^K, VW_i^V+b_i^V)$$.
+
+    $$head_i=Attention(QW_i^Q+b_i^Q, KW_i^K+b_i^K, VW_i^V+b_i^V).$$
 
     Args:
         hidden_dim: dimension of the hidden layers (embedding dimension).