Fix the type annotations of three parameters found in two constructors (#1268)

Summary:
As their names suggest, the parameters `embedding_dim`, `ffn_embedding_dim`, and `num_attention_heads` should have type `int`, not `float`.

Also validated by https://github.com/pytorch/fairseq/blob/b5f41f828b0ec9b67fa60aceb0778073d1b368b2/fairseq/modules/sparse_transformer_sentence_encoder.py#L22#L24.
Pull Request resolved: https://github.com/pytorch/fairseq/pull/1268

Differential Revision: D18372518

Pulled By: myleott

fbshipit-source-id: 666739b6270a975536785886068a975e07312bb0

fairseq/modules/sparse_transformer_sentence_encoder_layer.py

@@ -14,9 +14,9 @@ class SparseTransformerSentenceEncoderLayer(TransformerSentenceEncoderLayer):
 
     def __init__(
         self,
-        embedding_dim: float = 768,
-        ffn_embedding_dim: float = 3072,
-        num_attention_heads: float = 8,
+        embedding_dim: int = 768,
+        ffn_embedding_dim: int = 3072,
+        num_attention_heads: int = 8,
         dropout: float = 0.1,
         attention_dropout: float = 0.1,
         activation_dropout: float = 0.1,

fairseq/modules/transformer_sentence_encoder_layer.py

@@ -22,9 +22,9 @@ class TransformerSentenceEncoderLayer(nn.Module):
 
     def __init__(
         self,
-        embedding_dim: float = 768,
-        ffn_embedding_dim: float = 3072,
-        num_attention_heads: float = 8,
+        embedding_dim: int = 768,
+        ffn_embedding_dim: int = 3072,
+        num_attention_heads: int = 8,
         dropout: float = 0.1,
         attention_dropout: float = 0.1,
         activation_dropout: float = 0.1,