fix

Remove '\n' before adding token into vocab

pytorch_transformers/tokenization_bert.py

@@ -69,6 +69,7 @@ def load_vocab(vocab_file):
     with open(vocab_file, "r", encoding="utf-8") as reader:
         tokens = reader.readlines()
     for index, token in enumerate(tokens):
+        token = token[:-1]
         vocab[token] = index
     return vocab