make style (#11442)

src/transformers/models/xlm_roberta/tokenization_xlm_roberta.py

@@ -270,7 +270,7 @@ class XLMRobertaTokenizer(PreTrainedTokenizer):
         return self.sp_model.encode(text, out_type=str)
 
     def _convert_token_to_id(self, token):
-        """ Converts a token (str) in an id using the vocab. """
+        """Converts a token (str) in an id using the vocab."""
         if token in self.fairseq_tokens_to_ids:
             return self.fairseq_tokens_to_ids[token]
         spm_id = self.sp_model.PieceToId(token)

src/transformers/models/xlnet/tokenization_xlnet.py

@@ -189,7 +189,7 @@ class XLNetTokenizer(PreTrainedTokenizer):
         return outputs
 
     def _tokenize(self, text, sample=False):
-        """ Tokenize a string. """
+        """Tokenize a string."""
         text = self.preprocess_text(text)
 
         if not sample:
@@ -213,7 +213,7 @@ class XLNetTokenizer(PreTrainedTokenizer):
         return new_pieces
 
     def _convert_token_to_id(self, token):
-        """ Converts a token (str) in an id using the vocab. """
+        """Converts a token (str) in an id using the vocab."""
         return self.sp_model.PieceToId(token)
 
     def _convert_id_to_token(self, index):

src/transformers/testing_utils.py

@@ -389,7 +389,7 @@ if is_tf_available():
 
 
 def require_torch_gpu(test_case):
-    """Decorator marking a test that requires CUDA and PyTorch. """
+    """Decorator marking a test that requires CUDA and PyTorch."""
     if torch_device != "cuda":
         return unittest.skip("test requires CUDA")(test_case)
     else:
@@ -593,14 +593,14 @@ class CaptureStd:
 
 
 class CaptureStdout(CaptureStd):
-    """ Same as CaptureStd but captures only stdout """
+    """Same as CaptureStd but captures only stdout"""
 
     def __init__(self):
         super().__init__(err=False)
 
 
 class CaptureStderr(CaptureStd):
-    """ Same as CaptureStd but captures only stderr """
+    """Same as CaptureStd but captures only stderr"""
 
     def __init__(self):
         super().__init__(out=False)

src/transformers/tokenization_utils_base.py

@@ -88,7 +88,7 @@ else:
 
     @dataclass
     class EncodingFast:
-        """ This is dummy class because without the `tokenizers` library we don't have these objects anyway """
+        """This is dummy class because without the `tokenizers` library we don't have these objects anyway"""
 
         pass
 

src/transformers/trainer.py

@@ -805,7 +805,7 @@ class Trainer:
         return len(dataloader.dataset)
 
     def _hp_search_setup(self, trial: Union["optuna.Trial", Dict[str, Any]]):
-        """ HP search setup code """
+        """HP search setup code"""
         self._trial = trial
 
         if self.hp_search_backend is None or trial is None:

src/transformers/trainer_callback.py

@@ -92,14 +92,14 @@ class TrainerState:
             self.log_history = []
 
     def save_to_json(self, json_path: str):
-        """ Save the content of this instance in JSON format inside :obj:`json_path`."""
+        """Save the content of this instance in JSON format inside :obj:`json_path`."""
         json_string = json.dumps(dataclasses.asdict(self), indent=2, sort_keys=True) + "\n"
         with open(json_path, "w", encoding="utf-8") as f:
             f.write(json_string)
 
     @classmethod
     def load_from_json(cls, json_path: str):
-        """ Create an instance from the content of :obj:`json_path`."""
+        """Create an instance from the content of :obj:`json_path`."""
         with open(json_path, "r", encoding="utf-8") as f:
             text = f.read()
         return cls(**json.loads(text))
@@ -141,15 +141,15 @@ class TrainerControl:
     should_log: bool = False
 
     def _new_training(self):
-        """ Internal method that resets the variable for a new training. """
+        """Internal method that resets the variable for a new training."""
         self.should_training_stop = False
 
     def _new_epoch(self):
-        """ Internal method that resets the variable for a new epoch. """
+        """Internal method that resets the variable for a new epoch."""
         self.should_epoch_stop = False
 
     def _new_step(self):
-        """ Internal method that resets the variable for a new step. """
+        """Internal method that resets the variable for a new step."""
         self.should_save = False
         self.should_evaluate = False
         self.should_log = False
@@ -275,7 +275,7 @@ class TrainerCallback:
 
 
 class CallbackHandler(TrainerCallback):
-    """ Internal class that just calls the list of callbacks in order. """
+    """Internal class that just calls the list of callbacks in order."""
 
     def __init__(self, callbacks, model, tokenizer, optimizer, lr_scheduler):
         self.callbacks = []

src/transformers/trainer_pt_utils.py

@@ -294,14 +294,14 @@ def get_tpu_sampler(dataset: torch.utils.data.dataset.Dataset, bach_size: int):
 
 
 def nested_new_like(arrays, num_samples, padding_index=-100):
-    """ Create the same nested structure as `arrays` with a first dimension always at `num_samples`."""
+    """Create the same nested structure as `arrays` with a first dimension always at `num_samples`."""
     if isinstance(arrays, (list, tuple)):
         return type(arrays)(nested_new_like(x, num_samples) for x in arrays)
     return np.full_like(arrays, padding_index, shape=(num_samples, *arrays.shape[1:]))
 
 
 def expand_like(arrays, new_seq_length, padding_index=-100):
-    """ Expand the `arrays` so that the second dimension grows to `new_seq_length`. Uses `padding_index` for padding."""
+    """Expand the `arrays` so that the second dimension grows to `new_seq_length`. Uses `padding_index` for padding."""
     result = np.full_like(arrays, padding_index, shape=(arrays.shape[0], new_seq_length) + arrays.shape[2:])
     result[:, : arrays.shape[1]] = arrays
     return result

src/transformers/trainer_utils.py

@@ -320,7 +320,7 @@ class TrainerMemoryTracker:
         self.init_reported = False
 
     def derive_stage(self):
-        """ derives the stage/caller name automatically """
+        """derives the stage/caller name automatically"""
         caller = inspect.currentframe().f_back.f_back.f_code.co_name
         if caller in self.stages:
             return self.stages[caller]
@@ -330,7 +330,7 @@ class TrainerMemoryTracker:
             )
 
     def cpu_mem_used(self):
-        """ get resident set size memory for the current process """
+        """get resident set size memory for the current process"""
         return self.process.memory_info().rss
 
     def peak_monitor_func(self):
@@ -346,7 +346,7 @@ class TrainerMemoryTracker:
                 break
 
     def start(self):
-        """ start tracking for the caller's stage """
+        """start tracking for the caller's stage"""
         if self.skip_memory_metrics:
             return
 
@@ -376,7 +376,7 @@ class TrainerMemoryTracker:
         peak_monitor_thread.start()
 
     def stop(self, stage):
-        """ stop tracking for the passed stage """
+        """stop tracking for the passed stage"""
 
         # deal with nested calls of eval during train - simply ignore those
         if self.cur_stage is not None and self.cur_stage != stage:
@@ -416,7 +416,7 @@ class TrainerMemoryTracker:
         self.cur_stage = None
 
     def update_metrics(self, stage, metrics):
-        """ stop tracking for the passed stage """
+        """stop tracking for the passed stage"""
         if self.skip_memory_metrics:
             return
 
@@ -438,7 +438,7 @@ class TrainerMemoryTracker:
                     metrics[f"{stage}_mem_gpu_{t}_delta"] = self.gpu[stage][t]
 
     def stop_and_update_metrics(self, metrics=None):
-        """ combine stop + update in one call for simpler code """
+        """combine stop + update in one call for simpler code"""
         if self.skip_memory_metrics:
             return
 

src/transformers/utils/versions.py

@@ -115,12 +115,12 @@ def require_version(requirement: str, hint: Optional[str] = None) -> None:
 
 
 def require_version_core(requirement):
-    """ require_version wrapper which emits a core-specific hint on failure """
+    """require_version wrapper which emits a core-specific hint on failure"""
     hint = "Try: pip install transformers -U or pip install -e '.[dev]' if you're working with git master"
     return require_version(requirement, hint)
 
 
 def require_version_examples(requirement):
-    """ require_version wrapper which emits examples-specific hint on failure """
+    """require_version wrapper which emits examples-specific hint on failure"""
     hint = "Try: pip install -r examples/requirements.txt"
     return require_version(requirement, hint)

tests/deepspeed/test_deepspeed.py

@@ -122,7 +122,7 @@ class TrainerIntegrationDeepSpeed(TestCasePlus, TrainerIntegrationCommon):
         transformers.integrations._is_deepspeed_zero3_enabled = None
 
     def get_config_dict(self, stage):
-        """ As the tests modify the dict, always make a copy """
+        """As the tests modify the dict, always make a copy"""
         config = deepcopy(self.ds_config_dict[stage])
         if stage == ZERO3:
             # This setting slows things down, so don't enable it by default unless needed by a test.
@@ -430,7 +430,7 @@ class TrainerIntegrationDeepSpeed(TestCasePlus, TrainerIntegrationCommon):
 @require_deepspeed
 @require_torch_gpu
 class TestDeepSpeedWithLauncher(TestCasePlus):
-    """ This class is for testing via an external script - can do multiple gpus """
+    """This class is for testing via an external script - can do multiple gpus"""
 
     # Tests to devise #
     #

tests/test_modeling_common.py

@@ -1122,7 +1122,7 @@ class ModelTesterMixin:
 
         # a candidate for testing_utils
         def get_current_gpu_memory_use():
-            """ returns a list of cuda memory allocations per GPU in MBs"""
+            """returns a list of cuda memory allocations per GPU in MBs"""
 
             per_device_memory = []
             for id in range(torch.cuda.device_count()):

tests/test_modeling_funnel.py

@@ -42,7 +42,7 @@ if is_torch_available():
 
 
 class FunnelModelTester:
-    """You can also import this e.g, from .test_modeling_funnel import FunnelModelTester """
+    """You can also import this e.g, from .test_modeling_funnel import FunnelModelTester"""
 
     def __init__(
         self,

tests/test_modeling_layoutlm.py

@@ -36,7 +36,7 @@ if is_torch_available():
 
 
 class LayoutLMModelTester:
-    """You can also import this e.g from .test_modeling_layoutlm import LayoutLMModelTester """
+    """You can also import this e.g from .test_modeling_layoutlm import LayoutLMModelTester"""
 
     def __init__(
         self,

tests/test_modeling_lxmert.py

@@ -40,7 +40,7 @@ if is_torch_available():
 
 
 class LxmertModelTester:
-    """You can also import this e.g from .test_modeling_bart import BartModelTester """
+    """You can also import this e.g from .test_modeling_bart import BartModelTester"""
 
     def __init__(
         self,

tests/test_modeling_tapas.py

@@ -63,7 +63,7 @@ if is_torch_available():
 
 
 class TapasModelTester:
-    """You can also import this e.g from .test_modeling_tapas import TapasModelTester """
+    """You can also import this e.g from .test_modeling_tapas import TapasModelTester"""
 
     def __init__(
         self,

tests/test_modeling_tf_funnel.py

@@ -39,7 +39,7 @@ if is_tf_available():
 
 
 class TFFunnelModelTester:
-    """You can also import this e.g, from .test_modeling_funnel import FunnelModelTester """
+    """You can also import this e.g, from .test_modeling_funnel import FunnelModelTester"""
 
     def __init__(
         self,

tests/test_tokenization_common.py

@@ -58,7 +58,7 @@ NON_ENGLISH_TAGS = ["chinese", "dutch", "french", "finnish", "german", "multilin
 
 
 def filter_non_english(_, pretrained_name: str):
-    """ Filter all the model for non-english language """
+    """Filter all the model for non-english language"""
     return not any([lang in pretrained_name for lang in NON_ENGLISH_TAGS])
 
 

tests/test_tokenization_fsmt.py

@@ -100,7 +100,7 @@ class FSMTTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
         self.assertEqual(tokenizer.tgt_vocab_size, 21)
 
     def test_full_tokenizer(self):
-        """ Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt """
+        """Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt"""
         tokenizer = FSMTTokenizer(self.langs, self.src_vocab_file, self.tgt_vocab_file, self.merges_file)
 
         text = "lower"

tests/test_tokenization_layoutlm.py

@@ -70,5 +70,5 @@ class LayoutLMTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
         self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
 
     def test_special_tokens_as_you_expect(self):
-        """If you are training a seq2seq model that expects a decoder_prefix token make sure it is prepended to decoder_input_ids """
+        """If you are training a seq2seq model that expects a decoder_prefix token make sure it is prepended to decoder_input_ids"""
         pass

tests/test_tokenization_xlm.py

@@ -72,7 +72,7 @@ class XLMTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
         return input_text, output_text
 
     def test_full_tokenizer(self):
-        """ Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt """
+        """Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt"""
         tokenizer = XLMTokenizer(self.vocab_file, self.merges_file)
 
         text = "lower"