Black 20 release

examples/contrib/mm-imdb/utils_mmimdb.py

@@ -138,6 +138,9 @@ def get_image_transforms():
             transforms.Resize(256),
             transforms.CenterCrop(224),
             transforms.ToTensor(),
-            transforms.Normalize(mean=[0.46777044, 0.44531429, 0.40661017], std=[0.12221994, 0.12145835, 0.14380469],),
+            transforms.Normalize(
+                mean=[0.46777044, 0.44531429, 0.40661017],
+                std=[0.12221994, 0.12145835, 0.14380469],
+            ),
         ]
     )

examples/contrib/run_camembert.py

@@ -30,7 +30,11 @@ def fill_mask(masked_input, model, tokenizer, topk=5):
             )
         else:
             topk_filled_outputs.append(
-                (masked_input.replace(masked_token, predicted_token), values[index].item(), predicted_token,)
+                (
+                    masked_input.replace(masked_token, predicted_token),
+                    values[index].item(),
+                    predicted_token,
+                )
             )
     return topk_filled_outputs
 

examples/contrib/run_openai_gpt.py

@@ -71,10 +71,10 @@ def load_rocstories_dataset(dataset_path):
 
 
 def pre_process_datasets(encoded_datasets, input_len, cap_length, start_token, delimiter_token, clf_token):
-    """ Pre-process datasets containing lists of tuples(story, 1st continuation, 2nd continuation, label)
+    """Pre-process datasets containing lists of tuples(story, 1st continuation, 2nd continuation, label)
 
-        To Transformer inputs of shape (n_batch, n_alternative, length) comprising for each batch, continuation:
-        input_ids[batch, alternative, :] = [start_token] + story[:cap_length] + [delimiter_token] + cont1[:cap_length] + [clf_token]
+    To Transformer inputs of shape (n_batch, n_alternative, length) comprising for each batch, continuation:
+    input_ids[batch, alternative, :] = [start_token] + story[:cap_length] + [delimiter_token] + cont1[:cap_length] + [clf_token]
     """
     tensor_datasets = []
     for dataset in encoded_datasets:
@@ -83,7 +83,10 @@ def pre_process_datasets(encoded_datasets, input_len, cap_length, start_token, d
         mc_token_ids = np.zeros((n_batch, 2), dtype=np.int64)
         lm_labels = np.full((n_batch, 2, input_len), fill_value=-100, dtype=np.int64)
         mc_labels = np.zeros((n_batch,), dtype=np.int64)
-        for i, (story, cont1, cont2, mc_label), in enumerate(dataset):
+        for (
+            i,
+            (story, cont1, cont2, mc_label),
+        ) in enumerate(dataset):
             with_cont1 = [start_token] + story[:cap_length] + [delimiter_token] + cont1[:cap_length] + [clf_token]
             with_cont2 = [start_token] + story[:cap_length] + [delimiter_token] + cont2[:cap_length] + [clf_token]
             input_ids[i, 0, : len(with_cont1)] = with_cont1

examples/contrib/run_swag.py

@@ -629,7 +629,9 @@ def main():
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab
 
     config = AutoConfig.from_pretrained(args.config_name if args.config_name else args.model_name_or_path)
-    tokenizer = AutoTokenizer.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name_or_path,)
+    tokenizer = AutoTokenizer.from_pretrained(
+        args.tokenizer_name if args.tokenizer_name else args.model_name_or_path,
+    )
     model = AutoModelForMultipleChoice.from_pretrained(
         args.model_name_or_path, from_tf=bool(".ckpt" in args.model_name_or_path), config=config
     )