[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

examples/community/roberta/preprocessing/get_mask.py

@@ -34,8 +34,8 @@ class PreTrainingDataset:
         self.do_whole_word_mask = do_whole_word_mask
         self.max_predictions_per_seq = max_predictions_per_seq
         self.vocab_words = list(tokenizer.vocab.keys())
-        self.rec = re.compile("[\u4E00-\u9FA5]")
-        self.whole_rec = re.compile("##[\u4E00-\u9FA5]")
+        self.rec = re.compile("[\u4e00-\u9fa5]")
+        self.whole_rec = re.compile("##[\u4e00-\u9fa5]")
 
         self.mlm_p = 0.15
         self.mlm_mask_p = 0.8

examples/community/roberta/preprocessing/mask.cpp

@@ -75,15 +75,15 @@ auto get_new_segment(
   return new_segment;
 }
 
-bool startsWith(const std::string &s, const std::string &sub) {
+bool startsWith(const std::string& s, const std::string& sub) {
   return s.find(sub) == 0 ? true : false;
 }
 
 auto create_whole_masked_lm_predictions(
-    std::vector<std::string> &tokens,
-    const std::vector<std::string> &original_tokens,
-    const std::vector<std::string> &vocab_words,
-    std::map<std::string, int> &vocab, const int max_predictions_per_seq,
+    std::vector<std::string>& tokens,
+    const std::vector<std::string>& original_tokens,
+    const std::vector<std::string>& vocab_words,
+    std::map<std::string, int>& vocab, const int max_predictions_per_seq,
     const double masked_lm_prob) {
   // for (auto item : vocab) {
   //     std::cout << "key=" << std::string(py::str(item.first)) << ", "

examples/community/roberta/pretraining/model/deberta_v2.py

@@ -12,7 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-""" PyTorch DeBERTa-v2 model."""
+"""PyTorch DeBERTa-v2 model."""
 
 import math
 from collections.abc import Sequence

examples/images/vit/vit_train_demo.py

@@ -126,11 +126,9 @@ def evaluate_model(
     avg_loss = "{:.4f}".format(accum_loss.item())
     accuracy = "{:.4f}".format(accum_correct.item() / total_num.item())
     if coordinator.is_master():
-        print(
-            f"Evaluation result for epoch {epoch + 1}: \
+        print(f"Evaluation result for epoch {epoch + 1}: \
                 average_loss={avg_loss}, \
-                accuracy={accuracy}."
-        )
+                accuracy={accuracy}.")
 
 
 def main():

examples/tutorial/opt/opt/run_clm.py

@@ -20,6 +20,7 @@ on a text file or a dataset without using HuggingFace Trainer.
 Here is the full list of checkpoints on the hub that can be fine-tuned by this script:
 https://huggingface.co/models?filter=text-generation
 """
+
 # You can also adapt this script on your own causal language modeling task. Pointers for this are left as comments.
 
 import math

examples/tutorial/sequence_parallel/data/__init__.py

@@ -18,7 +18,7 @@ def cyclic_iter(iter):
 def build_train_valid_test_data_iterators(
     train_iters, global_batch_size, eval_interval, eval_iters, dataloader_type="single", **kwargs
 ):
-    (train_dataloader, valid_dataloader, test_dataloader) = (None, None, None)
+    train_dataloader, valid_dataloader, test_dataloader = (None, None, None)
 
     logger = get_dist_logger()
     logger.info("> building train, validation, and test datasets ...", ranks=[0])

examples/tutorial/sequence_parallel/data/datasets/bert_dataset.py

@@ -252,7 +252,7 @@ def build_training_sample(
 
     # Masking.
     max_predictions_per_seq = masked_lm_prob * max_num_tokens
-    (tokens, masked_positions, masked_labels, _) = create_masked_lm_predictions(
+    tokens, masked_positions, masked_labels, _ = create_masked_lm_predictions(
         tokens,
         vocab_id_list,
         vocab_id_to_token_dict,

examples/tutorial/sequence_parallel/data/datasets/data_samplers.py

@@ -14,7 +14,6 @@
 # limitations under the License.
 """Dataloaders."""
 
-
 import torch
 
 from colossalai.legacy.context import ParallelMode