fix gpt-2 unk token test

docs/README.md

@@ -57,4 +57,4 @@ It should build the static app that will be available under `/docs/_build/html`
 ## Adding a new element to the tree (toc-tree)
 
 Accepted files are reStructuredText (.rst) and Markdown (.md). Create a file with its extension and put it
-in the source directory. You can then link it to the toc-tree by putting the filename without the extension.
+in the source directory. You can then link it to the toc-tree by putting the filename without the extension.
\ No newline at end of file

pytorch_transformers/tokenization_gpt2.py

@@ -177,7 +177,9 @@ class GPT2Tokenizer(PreTrainedTokenizer):
 
     def _convert_token_to_id(self, token):
         """ Converts a token (str/unicode) in an id using the vocab. """
-        return self.encoder.get(token)
+        if token in self.encoder:
+            return self.encoder.get(token)
+        return self.encoder.get(self.unk_token)
 
     def _convert_id_to_token(self, index):
         """Converts an index (integer) in a token (string/unicode) using the vocab."""