Enforce target version for black.

This should stabilize formatting.

.circleci/config.yml

@@ -101,7 +101,7 @@ jobs:
             # we need a version of isort with https://github.com/timothycrosley/isort/pull/1000
             - run: sudo pip install git+git://github.com/timothycrosley/isort.git@e63ae06ec7d70b06df9e528357650281a3d3ec22#egg=isort
             - run: sudo pip install .[tf,torch,quality]
-            - run: black --check --line-length 119 examples templates tests src utils
+            - run: black --check --line-length 119 --target-version py35 examples templates tests src utils
             - run: isort --check-only --recursive examples templates tests src utils
             - run: flake8 examples templates tests src utils
     check_repository_consistency:

Makefile

@@ -3,14 +3,14 @@
 # Check that source code meets quality standards
 
 quality:
-	black --check --line-length 119 examples templates tests src utils
+	black --check --line-length 119 --target-version py35 examples templates tests src utils
 	isort --check-only --recursive examples templates tests src utils
 	flake8 examples templates tests src utils
 
 # Format source code automatically
 
 style:
-	black --line-length 119 examples templates tests src utils
+	black --line-length 119 --target-version py35 examples templates tests src utils
 	isort --recursive examples templates tests src utils
 
 # Run tests for the library

src/transformers/modeling_encoder_decoder.py

@@ -325,7 +325,7 @@ class Model2Model(PreTrainedEncoderDecoder):
             encoder_pretrained_model_name_or_path=pretrained_model_name_or_path,
             decoder_pretrained_model_name_or_path=pretrained_model_name_or_path,
             *args,
-            **kwargs
+            **kwargs,
         )
 
         return model

src/transformers/modeling_tf_utils.py

@@ -250,7 +250,7 @@ class TFPreTrainedModel(tf.keras.Model):
                 return_unused_kwargs=True,
                 force_download=force_download,
                 resume_download=resume_download,
-                **kwargs
+                **kwargs,
             )
         else:
             model_kwargs = kwargs

src/transformers/modeling_utils.py

@@ -355,7 +355,7 @@ class PreTrainedModel(nn.Module):
                 force_download=force_download,
                 resume_download=resume_download,
                 proxies=proxies,
-                **kwargs
+                **kwargs,
             )
         else:
             model_kwargs = kwargs

src/transformers/pipelines.py

@@ -643,7 +643,7 @@ class QuestionAnsweringPipeline(Pipeline):
             framework=framework,
             args_parser=QuestionAnsweringArgumentHandler(),
             device=device,
-            **kwargs
+            **kwargs,
         )
 
     @staticmethod

src/transformers/tokenization_albert.py

@@ -87,7 +87,7 @@ class AlbertTokenizer(PreTrainedTokenizer):
             pad_token=pad_token,
             cls_token=cls_token,
             mask_token=mask_token,
-            **kwargs
+            **kwargs,
         )
 
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens

src/transformers/tokenization_bert.py

@@ -169,7 +169,7 @@ class BertTokenizer(PreTrainedTokenizer):
             pad_token=pad_token,
             cls_token=cls_token,
             mask_token=mask_token,
-            **kwargs
+            **kwargs,
         )
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens
         self.max_len_sentences_pair = self.max_len - 3  # take into account special tokens
@@ -560,7 +560,7 @@ class BertTokenizerFast(PreTrainedTokenizerFast):
             pad_token=pad_token,
             cls_token=cls_token,
             mask_token=mask_token,
-            **kwargs
+            **kwargs,
         )
 
         self._tokenizer = tk.Tokenizer(tk.models.WordPiece.from_files(vocab_file, unk_token=unk_token))

src/transformers/tokenization_bert_japanese.py

@@ -113,7 +113,7 @@ class BertJapaneseTokenizer(BertTokenizer):
             pad_token=pad_token,
             cls_token=cls_token,
             mask_token=mask_token,
-            **kwargs
+            **kwargs,
         )
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens
         self.max_len_sentences_pair = self.max_len - 3  # take into account special tokens

src/transformers/tokenization_camembert.py

@@ -76,7 +76,7 @@ class CamembertTokenizer(PreTrainedTokenizer):
             pad_token=pad_token,
             mask_token=mask_token,
             additional_special_tokens=additional_special_tokens,
-            **kwargs
+            **kwargs,
         )
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens
         self.max_len_sentences_pair = self.max_len - 4  # take into account special tokens

src/transformers/tokenization_roberta.py

@@ -95,7 +95,7 @@ class RobertaTokenizer(GPT2Tokenizer):
             cls_token=cls_token,
             pad_token=pad_token,
             mask_token=mask_token,
-            **kwargs
+            **kwargs,
         )
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens
         self.max_len_sentences_pair = self.max_len - 4  # take into account special tokens

src/transformers/tokenization_t5.py

@@ -96,7 +96,7 @@ class T5Tokenizer(PreTrainedTokenizer):
             unk_token=unk_token,
             pad_token=pad_token,
             additional_special_tokens=additional_special_tokens,
-            **kwargs
+            **kwargs,
         )
 
         try:

src/transformers/tokenization_utils.py

@@ -817,7 +817,7 @@ class PreTrainedTokenizer(object):
             truncation_strategy=truncation_strategy,
             pad_to_max_length=pad_to_max_length,
             return_tensors=return_tensors,
-            **kwargs
+            **kwargs,
         )
 
         return encoded_inputs["input_ids"]

src/transformers/tokenization_xlm.py

@@ -586,7 +586,7 @@ class XLMTokenizer(PreTrainedTokenizer):
             cls_token=cls_token,
             mask_token=mask_token,
             additional_special_tokens=additional_special_tokens,
-            **kwargs
+            **kwargs,
         )
 
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens

src/transformers/tokenization_xlm_roberta.py

@@ -83,7 +83,7 @@ class XLMRobertaTokenizer(PreTrainedTokenizer):
             cls_token=cls_token,
             pad_token=pad_token,
             mask_token=mask_token,
-            **kwargs
+            **kwargs,
         )
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens
         self.max_len_sentences_pair = self.max_len - 4  # take into account special tokens

src/transformers/tokenization_xlnet.py

@@ -86,7 +86,7 @@ class XLNetTokenizer(PreTrainedTokenizer):
             cls_token=cls_token,
             mask_token=mask_token,
             additional_special_tokens=additional_special_tokens,
-            **kwargs
+            **kwargs,
         )
 
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens

templates/adding_a_new_model/tokenization_xxx.py

@@ -115,7 +115,7 @@ class XxxTokenizer(PreTrainedTokenizer):
             pad_token=pad_token,
             cls_token=cls_token,
             mask_token=mask_token,
-            **kwargs
+            **kwargs,
         )
         self.max_len_single_sentence = self.max_len - 2  # take into account special tokens
         self.max_len_sentences_pair = self.max_len - 3  # take into account special tokens

tests/test_tokenization_bert.py

@@ -84,7 +84,7 @@ class BertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
         tokenizer = self.get_tokenizer()
         rust_tokenizer = self.get_rust_tokenizer(add_special_tokens=False)
 
-        sequence = u"UNwant\u00E9d,running"
+        sequence = "UNwant\u00E9d,running"
 
         tokens = tokenizer.tokenize(sequence)
         rust_tokens = rust_tokenizer.tokenize(sequence)

tests/test_tokenization_gpt2.py

@@ -96,7 +96,7 @@ class GPT2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
         tokenizer = self.get_tokenizer()
         rust_tokenizer = self.get_rust_tokenizer(add_special_tokens=False, add_prefix_space=True)
 
-        sequence = u"lower newer"
+        sequence = "lower newer"
 
         # Testing tokenization
         tokens = tokenizer.tokenize(sequence, add_prefix_space=True)