make style (huggingface#11442)

examples/legacy/question-answering/run_squad.py

@@ -74,7 +74,7 @@ def to_list(tensor):
 
 
 def train(args, train_dataset, model, tokenizer):
-    """ Train the model """
+    """Train the model"""
     if args.local_rank in [-1, 0]:
         tb_writer = SummaryWriter()
 

examples/legacy/run_openai_gpt.py

@@ -61,7 +61,7 @@ def accuracy(out, labels):
 
 
 def load_rocstories_dataset(dataset_path):
-    """ Output a list of tuples(story, 1st continuation, 2nd continuation, label) """
+    """Output a list of tuples(story, 1st continuation, 2nd continuation, label)"""
     with open(dataset_path, encoding="utf_8") as f:
         f = csv.reader(f)
         output = []
@@ -184,7 +184,7 @@ def main():
 
     # Load and encode the datasets
     def tokenize_and_encode(obj):
-        """ Tokenize and encode a nested object """
+        """Tokenize and encode a nested object"""
         if isinstance(obj, str):
             return tokenizer.convert_tokens_to_ids(tokenizer.tokenize(obj))
         elif isinstance(obj, int):

examples/legacy/run_swag.py

@@ -276,7 +276,7 @@ def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=Fal
 
 
 def train(args, train_dataset, model, tokenizer):
-    """ Train the model """
+    """Train the model"""
     if args.local_rank in [-1, 0]:
         tb_writer = SummaryWriter()
 

examples/legacy/seq2seq/minify_dataset.py

@@ -19,7 +19,7 @@
 
 
 def minify(src_dir: str, dest_dir: str, n: int):
-    """Write first n lines of each file f in src_dir to dest_dir/f """
+    """Write first n lines of each file f in src_dir to dest_dir/f"""
     src_dir = Path(src_dir)
     dest_dir = Path(dest_dir)
     dest_dir.mkdir(exist_ok=True)

examples/research_projects/bert-loses-patience/run_glue_with_pabee.py

@@ -71,7 +71,7 @@ def set_seed(args):
 
 
 def train(args, train_dataset, model, tokenizer):
-    """ Train the model """
+    """Train the model"""
     if args.local_rank in [-1, 0]:
         tb_writer = SummaryWriter()
 

examples/research_projects/bertabs/modeling_bertabs.py

@@ -251,7 +251,7 @@ def forward(
         return output, state  # , state
 
     def init_decoder_state(self, src, memory_bank, with_cache=False):
-        """ Init decoder state """
+        """Init decoder state"""
         state = TransformerDecoderState(src)
         if with_cache:
             state._init_cache(memory_bank, self.num_layers)
@@ -479,11 +479,11 @@ def forward(
         head_count = self.head_count
 
         def shape(x):
-            """  projection """
+            """projection"""
             return x.view(batch_size, -1, head_count, dim_per_head).transpose(1, 2)
 
         def unshape(x):
-            """  compute context """
+            """compute context"""
             return x.transpose(1, 2).contiguous().view(batch_size, -1, head_count * dim_per_head)
 
         # 1) Project key, value, and query.
@@ -571,12 +571,12 @@ class DecoderState(object):
     """
 
     def detach(self):
-        """ Need to document this """
+        """Need to document this"""
         self.hidden = tuple([_.detach() for _ in self.hidden])
         self.input_feed = self.input_feed.detach()
 
     def beam_update(self, idx, positions, beam_size):
-        """ Need to document this """
+        """Need to document this"""
         for e in self._all:
             sizes = e.size()
             br = sizes[1]
@@ -592,7 +592,7 @@ def map_batch_fn(self, fn):
 
 
 class TransformerDecoderState(DecoderState):
-    """ Transformer Decoder state base class """
+    """Transformer Decoder state base class"""
 
     def __init__(self, src):
         """
@@ -638,7 +638,7 @@ def _init_cache(self, memory_bank, num_layers):
             self.cache["layer_{}".format(l)] = layer_cache
 
     def repeat_beam_size_times(self, beam_size):
-        """ Repeat beam_size times along batch dimension. """
+        """Repeat beam_size times along batch dimension."""
         self.src = self.src.data.repeat(1, beam_size, 1)
 
     def map_batch_fn(self, fn):

examples/research_projects/bertabs/test_utils_summarization.py

@@ -25,19 +25,19 @@ def setUp(self):
         self.block_size = 10
 
     def test_fit_to_block_sequence_too_small(self):
-        """ Pad the sequence with 0 if the sequence is smaller than the block size."""
+        """Pad the sequence with 0 if the sequence is smaller than the block size."""
         sequence = [1, 2, 3, 4]
         expected_output = [1, 2, 3, 4, 0, 0, 0, 0, 0, 0]
         self.assertEqual(truncate_or_pad(sequence, self.block_size, 0), expected_output)
 
     def test_fit_to_block_sequence_fit_exactly(self):
-        """ Do nothing if the sequence is the right size. """
+        """Do nothing if the sequence is the right size."""
         sequence = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
         expected_output = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
         self.assertEqual(truncate_or_pad(sequence, self.block_size, 0), expected_output)
 
     def test_fit_to_block_sequence_too_big(self):
-        """ Truncate the sequence if it is too long. """
+        """Truncate the sequence if it is too long."""
         sequence = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
         expected_output = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
         self.assertEqual(truncate_or_pad(sequence, self.block_size, 0), expected_output)

examples/research_projects/bertabs/utils_summarization.py

@@ -47,7 +47,7 @@ def __init__(self, path="", prefix="train"):
             self.documents.append(path_to_story)
 
     def __len__(self):
-        """ Returns the number of documents. """
+        """Returns the number of documents."""
         return len(self.documents)
 
     def __getitem__(self, idx):

examples/research_projects/bertology/run_bertology.py

@@ -49,14 +49,14 @@
 
 
 def entropy(p):
-    """ Compute the entropy of a probability distribution """
+    """Compute the entropy of a probability distribution"""
     plogp = p * torch.log(p)
     plogp[p == 0] = 0
     return -plogp.sum(dim=-1)
 
 
 def print_2d_tensor(tensor):
-    """ Print a 2D tensor """
+    """Print a 2D tensor"""
     logger.info("lv, h >\t" + "\t".join(f"{x + 1}" for x in range(len(tensor))))
     for row in range(len(tensor)):
         if tensor.dtype != torch.long:

examples/research_projects/bertology/run_prune_gpt.py

@@ -36,7 +36,7 @@ def save_model(model, dirpath):
 
 
 def entropy(p, unlogit=False):
-    """ Compute the entropy of a probability distribution """
+    """Compute the entropy of a probability distribution"""
     exponent = 2
     if unlogit:
         p = torch.pow(p, exponent)
@@ -46,7 +46,7 @@ def entropy(p, unlogit=False):
 
 
 def print_2d_tensor(tensor):
-    """ Print a 2D tensor """
+    """Print a 2D tensor"""
     logger.info("lv, h >\t" + "\t".join(f"{x + 1}" for x in range(len(tensor))))
     for row in range(len(tensor)):
         if tensor.dtype != torch.long:

examples/research_projects/deebert/run_glue_deebert.py

@@ -70,7 +70,7 @@ def get_wanted_result(result):
 
 
 def train(args, train_dataset, model, tokenizer, train_highway=False):
-    """ Train the model """
+    """Train the model"""
     if args.local_rank in [-1, 0]:
         tb_writer = SummaryWriter()
 

examples/research_projects/distillation/run_squad_w_distillation.py

@@ -92,7 +92,7 @@ def to_list(tensor):
 
 
 def train(args, train_dataset, model, tokenizer, teacher=None):
-    """ Train the model """
+    """Train the model"""
     if args.local_rank in [-1, 0]:
         tb_writer = SummaryWriter()
 

examples/research_projects/mm-imdb/run_mmimdb.py

@@ -64,7 +64,7 @@ def set_seed(args):
 
 
 def train(args, train_dataset, model, tokenizer, criterion):
-    """ Train the model """
+    """Train the model"""
     if args.local_rank in [-1, 0]:
         tb_writer = SummaryWriter()
 

examples/research_projects/movement-pruning/emmental/modeling_bert_masked.py

@@ -393,7 +393,7 @@ class MaskedBertPreTrainedModel(PreTrainedModel):
     base_model_prefix = "bert"
 
     def _init_weights(self, module):
-        """ Initialize the weights """
+        """Initialize the weights"""
         if isinstance(module, (nn.Linear, nn.Embedding)):
             # Slightly different from the TF version which uses truncated_normal for initialization
             # cf https://github.com/pytorch/pytorch/pull/5617

examples/research_projects/movement-pruning/masked_run_glue.py

@@ -105,7 +105,7 @@ def regularization(model: nn.Module, mode: str):
 
 
 def train(args, train_dataset, model, tokenizer, teacher=None):
-    """ Train the model """
+    """Train the model"""
     if args.local_rank in [-1, 0]:
         tb_writer = SummaryWriter(log_dir=args.output_dir)
 

examples/research_projects/movement-pruning/masked_run_squad.py

@@ -113,7 +113,7 @@ def to_list(tensor):
 
 
 def train(args, train_dataset, model, tokenizer, teacher=None):
-    """ Train the model """
+    """Train the model"""
     if args.local_rank in [-1, 0]:
         tb_writer = SummaryWriter(log_dir=args.output_dir)
 

src/transformers/commands/lfs.py

@@ -96,7 +96,7 @@ def write_msg(msg: Dict):
 
 
 def read_msg() -> Optional[Dict]:
-    """Read Line delimited JSON from stdin. """
+    """Read Line delimited JSON from stdin."""
     msg = json.loads(sys.stdin.readline().strip())
 
     if "terminate" in (msg.get("type"), msg.get("event")):

src/transformers/data/processors/utils.py

@@ -124,7 +124,7 @@ def _read_tsv(cls, input_file, quotechar=None):
 
 
 class SingleSentenceClassificationProcessor(DataProcessor):
-    """ Generic processor for a single sentence classification data set."""
+    """Generic processor for a single sentence classification data set."""
 
     def __init__(self, labels=None, examples=None, mode="classification", verbose=False):
         self.labels = [] if labels is None else labels

src/transformers/file_utils.py

@@ -1462,7 +1462,7 @@ def wrapper(*args, **kwargs):
 
 
 def is_tensor(x):
-    """ Tests if ``x`` is a :obj:`torch.Tensor`, :obj:`tf.Tensor` or :obj:`np.ndarray`. """
+    """Tests if ``x`` is a :obj:`torch.Tensor`, :obj:`tf.Tensor` or :obj:`np.ndarray`."""
     if is_torch_available():
         import torch
 
@@ -1684,7 +1684,7 @@ def _get_module(self, module_name: str) -> ModuleType:
 
 
 def copy_func(f):
-    """ Returns a copy of a function f."""
+    """Returns a copy of a function f."""
     # Based on http://stackoverflow.com/a/6528148/190597 (Glenn Maynard)
     g = types.FunctionType(f.__code__, f.__globals__, name=f.__name__, argdefs=f.__defaults__, closure=f.__closure__)
     g = functools.update_wrapper(g, f)

src/transformers/modelcard.py

@@ -215,6 +215,6 @@ def to_json_string(self):
         return json.dumps(self.to_dict(), indent=2, sort_keys=True) + "\n"
 
     def to_json_file(self, json_file_path):
-        """ Save this instance to a json file."""
+        """Save this instance to a json file."""
         with open(json_file_path, "w", encoding="utf-8") as writer:
             writer.write(self.to_json_string())

src/transformers/models/albert/modeling_albert.py

@@ -71,7 +71,7 @@
 
 
 def load_tf_weights_in_albert(model, config, tf_checkpoint_path):
-    """ Load tf checkpoints in a pytorch model."""
+    """Load tf checkpoints in a pytorch model."""
     try:
         import re
 

src/transformers/models/albert/modeling_tf_albert.py

@@ -189,7 +189,7 @@ def call(
 
 
 class TFAlbertAttention(tf.keras.layers.Layer):
-    """ Contains the complete attention sublayer, including both dropouts and layer norm. """
+    """Contains the complete attention sublayer, including both dropouts and layer norm."""
 
     def __init__(self, config: AlbertConfig, **kwargs):
         super().__init__(**kwargs)

src/transformers/models/albert/tokenization_albert.py

@@ -187,7 +187,7 @@ def preprocess_text(self, inputs):
         return outputs
 
     def _tokenize(self, text, sample=False):
-        """ Tokenize a string. """
+        """Tokenize a string."""
         text = self.preprocess_text(text)
 
         if not sample:
@@ -211,7 +211,7 @@ def _tokenize(self, text, sample=False):
         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/models/barthez/tokenization_barthez.py

@@ -223,7 +223,7 @@ def _tokenize(self, text):
         return self.sp_model.EncodeAsPieces(text)
 
     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/bert/modeling_bert.py

@@ -703,7 +703,7 @@ class BertPreTrainedModel(PreTrainedModel):
     _keys_to_ignore_on_load_missing = [r"position_ids"]
 
     def _init_weights(self, module):
-        """ Initialize the weights """
+        """Initialize the weights"""
         if isinstance(module, nn.Linear):
             # Slightly different from the TF version which uses truncated_normal for initialization
             # cf https://github.com/pytorch/pytorch/pull/5617

src/transformers/models/bert/tokenization_bert.py

@@ -233,15 +233,15 @@ def _tokenize(self, text):
         return split_tokens
 
     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.vocab.get(token, self.vocab.get(self.unk_token))
 
     def _convert_id_to_token(self, index):
         """Converts an index (integer) in a token (str) using the vocab."""
         return self.ids_to_tokens.get(index, self.unk_token)
 
     def convert_tokens_to_string(self, tokens):
-        """ Converts a sequence of tokens (string) in a single string. """
+        """Converts a sequence of tokens (string) in a single string."""
         out_string = " ".join(tokens).replace(" ##", "").strip()
         return out_string
 

src/transformers/models/bert_generation/modeling_bert_generation.py

@@ -177,7 +177,7 @@ class BertGenerationPreTrainedModel(PreTrainedModel):
     _keys_to_ignore_on_load_missing = [r"position_ids"]
 
     def _init_weights(self, module):
-        """ Initialize the weights """
+        """Initialize the weights"""
         if isinstance(module, nn.Linear):
             # Slightly different from the TF version which uses truncated_normal for initialization
             # cf https://github.com/pytorch/pytorch/pull/5617

src/transformers/models/bert_generation/tokenization_bert_generation.py

@@ -119,7 +119,7 @@ def _tokenize(self, text, sample=False):
         return 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.piece_to_id(token)
 
     def _convert_id_to_token(self, index):
@@ -128,7 +128,7 @@ def _convert_id_to_token(self, index):
         return token
 
     def convert_tokens_to_string(self, tokens):
-        """ Converts a sequence of tokens (string) in a single string. """
+        """Converts a sequence of tokens (string) in a single string."""
         out_string = self.sp_model.decode_pieces(tokens)
         return out_string
 

src/transformers/models/bertweet/tokenization_bertweet.py

@@ -368,15 +368,15 @@ def normalizeToken(self, token):
             return token
 
     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.encoder.get(token, self.encoder.get(self.unk_token))
 
     def _convert_id_to_token(self, index):
         """Converts an index (integer) in a token (str) using the vocab."""
         return self.decoder.get(index, self.unk_token)
 
     def convert_tokens_to_string(self, tokens):
-        """ Converts a sequence of tokens (string) in a single string. """
+        """Converts a sequence of tokens (string) in a single string."""
         out_string = " ".join(tokens).replace("@@ ", "").strip()
         return out_string