add 'padding_idx=0' for BertEmbeddings

pytorch_pretrained_bert/modeling.py

@@ -238,9 +238,9 @@ class BertEmbeddings(nn.Module):
     """
     def __init__(self, config):
         super(BertEmbeddings, self).__init__()
-        self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size)
-        self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)
-        self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size)
+        self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=0)
+        self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size, padding_idx=0)
+        self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size, padding_idx=0)
 
         # self.LayerNorm is not snake-cased to stick with TensorFlow model variable name and be able to load
         # any TensorFlow checkpoint file