Apply quality and style requirements

src/transformers/__init__.py

@@ -29,10 +29,8 @@ from .configuration_gpt2 import GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, GPT2Config
 from .configuration_mmbt import MMBTConfig
 from .configuration_openai import OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP, OpenAIGPTConfig
 from .configuration_roberta import ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, RobertaConfig
-from .configuration_camembert import CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, CamembertConfig
 from .configuration_t5 import T5_PRETRAINED_CONFIG_ARCHIVE_MAP, T5Config
 from .configuration_transfo_xl import TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP, TransfoXLConfig
-
 # Configurations
 from .configuration_utils import PretrainedConfig
 from .configuration_xlm import XLM_PRETRAINED_CONFIG_ARCHIVE_MAP, XLMConfig
@@ -57,7 +55,6 @@ from .data import (
     xnli_processors,
     xnli_tasks_num_labels,
 )
-
 # Files and general utilities
 from .file_utils import (
     CONFIG_NAME,
@@ -74,10 +71,8 @@ from .file_utils import (
     is_tf_available,
     is_torch_available,
 )
-
 # Model Cards
 from .modelcard import ModelCard
-
 # TF 2.0 <=> PyTorch conversion utilities
 from .modeling_tf_pytorch_utils import (
     convert_tf_weight_name_to_pt_weight_name,
@@ -88,7 +83,6 @@ from .modeling_tf_pytorch_utils import (
     load_tf2_model_in_pytorch_model,
     load_tf2_weights_in_pytorch_model,
 )
-
 # Pipelines
 from .pipelines import (
     CsvPipelineDataFormat,
@@ -114,7 +108,6 @@ from .tokenization_openai import OpenAIGPTTokenizer
 from .tokenization_roberta import RobertaTokenizer
 from .tokenization_t5 import T5Tokenizer
 from .tokenization_transfo_xl import TransfoXLCorpus, TransfoXLTokenizer
-
 # Tokenizers
 from .tokenization_utils import PreTrainedTokenizer
 from .tokenization_xlm import XLMTokenizer

src/transformers/convert_pytorch_checkpoint_to_tf2.py

@@ -22,12 +22,12 @@ import os
 from transformers import (
     ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
     BERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
+    CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
     CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP,
     DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
     GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP,
     OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP,
     ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP,
-    CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
     T5_PRETRAINED_CONFIG_ARCHIVE_MAP,
     TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP,
     XLM_PRETRAINED_CONFIG_ARCHIVE_MAP,
@@ -35,17 +35,18 @@ from transformers import (
     XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP,
     AlbertConfig,
     BertConfig,
+    CamembertConfig,
     CTRLConfig,
     DistilBertConfig,
     GPT2Config,
     OpenAIGPTConfig,
     RobertaConfig,
-    CamembertConfig,
     T5Config,
     TFAlbertForMaskedLM,
     TFBertForPreTraining,
     TFBertForQuestionAnswering,
     TFBertForSequenceClassification,
+    TFCamembertForMaskedLM,
     TFCTRLLMHeadModel,
     TFDistilBertForMaskedLM,
     TFDistilBertForQuestionAnswering,
@@ -53,8 +54,6 @@ from transformers import (
     TFOpenAIGPTLMHeadModel,
     TFRobertaForMaskedLM,
     TFRobertaForSequenceClassification,
-    TFCamembertForMaskedLM,
-    TFCamembertForSequenceClassification,
     TFT5WithLMHeadModel,
     TFTransfoXLLMHeadModel,
     TFXLMRobertaForMaskedLM,

src/transformers/modeling_tf_camembert.py

@@ -18,8 +18,6 @@
 
 import logging
 
-import tensorflow as tf
-
 from .configuration_camembert import CamembertConfig
 from .file_utils import add_start_docstrings
 from .modeling_tf_roberta import (
@@ -29,21 +27,22 @@ from .modeling_tf_roberta import (
     TFRobertaModel,
 )
 
+
 logger = logging.getLogger(__name__)
 
 TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
-    #"camembert-base": "https://s3.amazonaws.com/models.huggingface.co/bert/camembert-base-tf_model.h5"
+    # "camembert-base": "https://s3.amazonaws.com/models.huggingface.co/bert/camembert-base-tf_model.h5"
 }
 
 
 CAMEMBERT_START_DOCSTRING = r"""    The CamemBERT model was proposed in
     `CamemBERT: a Tasty French Language Model`_
     by Louis Martin, Benjamin Muller, Pedro Javier Ortiz Suárez, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah, and Benoît Sagot. It is based on Facebook's RoBERTa model released in 2019.
-    
+
     It is a model trained on 138GB of French text.
-    
+
     This implementation is the same as RoBERTa.
-    
+
     This model is a tf.keras.Model `tf.keras.Model`_ sub-class. Use it as a regular TF 2.0 Keras Model and
     refer to the TF 2.0 documentation for all matter related to general usage and behavior.
 
@@ -52,7 +51,7 @@ CAMEMBERT_START_DOCSTRING = r"""    The CamemBERT model was proposed in
 
     .. _`tf.keras.Model`:
         https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/Model
-    
+
     Note on the model inputs:
         TF 2.0 models accepts two formats as inputs:
 
@@ -60,15 +59,15 @@ CAMEMBERT_START_DOCSTRING = r"""    The CamemBERT model was proposed in
             - having all inputs as a list, tuple or dict in the first positional arguments.
 
         This second option is usefull when using `tf.keras.Model.fit()` method which currently requires having all the tensors in the first argument of the model call function: `model(inputs)`.
-        
+
         If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
-        
+
         - a single Tensor with input_ids only and nothing else: `model(inputs_ids)
         - a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
             `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])`
         - a dictionary with one or several input Tensors associaed to the input names given in the docstring:
             `model({'input_ids': input_ids, 'token_type_ids': token_type_ids})`
-    
+
     Parameters:
         config (:class:`~transformers.CamembertConfig`): Model configuration class with all the parameters of the
             model. Initializing with a config file does not load the weights associated with the model, only the configuration.
@@ -80,21 +79,21 @@ CAMEMBERT_INPUTS_DOCSTRING = r"""
         **input_ids**: ``Numpy array`` or ``tf.Tensor`` of shape ``(batch_size, sequence_length)``:
             Indices of input sequence tokens in the vocabulary.
             To match pre-training, CamemBERT input sequence should be formatted with <s> and </s> tokens as follows:
-            
+
             (a) For sequence pairs:
-                
+
                 ``tokens:         <s> Is this Jacksonville ? </s> </s> No it is not . </s>``
-            
+
             (b) For single sequences:
-                
+
                 ``tokens:         <s> the dog is hairy . </s>``
-            
+
             Fully encoded sequences or sequence pairs can be obtained using the CamembertTokenizer.encode function with
             the ``add_special_tokens`` parameter set to ``True``.
-            
+
             CamemBERT is a model with absolute position embeddings so it's usually advised to pad the inputs on
             the right rather than the left.
-            
+
             See :func:`transformers.PreTrainedTokenizer.encode` and
             :func:`transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
         **attention_mask**: (`optional`) ``Numpy array`` or ``tf.Tensor`` of shape ``(batch_size, sequence_length)``:
@@ -137,19 +136,19 @@ class TFCamembertModel(TFRobertaModel):
             further processed by a Linear layer and a Tanh activation function. The Linear
             layer weights are trained from the next sentence prediction (classification)
             eo match pre-training, CamemBERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:
-            
+
             (a) For sequence pairs:
-                
+
                 ``tokens:         [CLS] is this jack ##son ##ville ? [SEP] [SEP] no it is not . [SEP]``
-                
+
                 ``token_type_ids:   0   0  0    0    0     0       0   0   0     1  1  1  1   1   1``
-            
+
             (b) For single sequences:
-                
+
                 ``tokens:         [CLS] the dog is hairy . [SEP]``
-                
+
                 ``token_type_ids:   0   0   0   0  0     0   0``
-            
+
             objective during Bert pretraining. This output is usually *not* a good summary
             of the semantic content of the input, you're often better with averaging or pooling
             the sequence of hidden-states for the whole input sequence.
@@ -160,15 +159,15 @@ class TFCamembertModel(TFRobertaModel):
         **attentions**: (`optional`, returned when ``config.output_attentions=True``)
             list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
             Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
-    
+
     Examples::
-        
+
         tokenizer = CamembertTokenizer.from_pretrained('camembert-base')
         model = TFCamembertModel.from_pretrained('camembert-base')
         input_ids = tf.constant(tokenizer.encode("J'aime le camembert !"))[None, :]  # Batch size 1
         outputs = model(input_ids)
         last_hidden_states = outputs[0]  # The last hidden-state is the first element of the output tuple
-    
+
     """
     config_class = CamembertConfig
     pretrained_model_archive_map = TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP
@@ -186,7 +185,7 @@ class TFCamembertForMaskedLM(TFRobertaForMaskedLM):
             Indices should be in ``[-1, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring)
             Tokens with indices set to ``-100`` are ignored (masked), the loss is only computed for the tokens with labels
             in ``[0, ..., config.vocab_size]``
-    
+
     Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
         **loss**: (`optional`, returned when ``masked_lm_labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
             Masked language modeling loss.
@@ -199,15 +198,15 @@ class TFCamembertForMaskedLM(TFRobertaForMaskedLM):
         **attentions**: (`optional`, returned when ``config.output_attentions=True``)
             list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
             Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
-    
+
     Examples::
-        
+
         tokenizer = CamembertTokenizer.from_pretrained('camembert-base')
         model = TFCamembertForMaskedLM.from_pretrained('camembert-base')
         input_ids = tf.constant(tokenizer.encode("J'aime le camembert !"))[None, :]  # Batch size 1
         outputs = model(input_ids, masked_lm_labels=input_ids)
         loss, prediction_scores = outputs[:2]
-    
+
     """
     config_class = CamembertConfig
     pretrained_model_archive_map = TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP
@@ -226,7 +225,7 @@ class TFCamembertForSequenceClassification(TFRobertaForSequenceClassification):
             Indices should be in ``[0, ..., config.num_labels]``.
             If ``config.num_labels == 1`` a regression loss is computed (Mean-Square loss),
             If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy).
-    
+
     Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
         **loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
             Classification (or regression if config.num_labels==1) loss.
@@ -239,15 +238,15 @@ class TFCamembertForSequenceClassification(TFRobertaForSequenceClassification):
         **attentions**: (`optional`, returned when ``config.output_attentions=True``)
             list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
             Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
-    
+
     Examples::
-    
+
         tokenizer = CamembertTokenizer.from_pretrained('camembert-base')
         model = TFCamembertForSequenceClassification.from_pretrained('camembert-base')
         input_ids = tf.constant(tokenizer.encode("J'aime le camembert !"))[None, :]  # Batch size 1
         outputs = model(input_ids)
         loss, logits = outputs[:2]
-    
+
     """
     config_class = CamembertConfig
     pretrained_model_archive_map = TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP
@@ -264,7 +263,7 @@ class TFCamembertForTokenClassification(TFRobertaForTokenClassification):
         **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
             Labels for computing the token classification loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
-    
+
     Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
         **loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
             Classification loss.
@@ -277,15 +276,15 @@ class TFCamembertForTokenClassification(TFRobertaForTokenClassification):
         **attentions**: (`optional`, returned when ``config.output_attentions=True``)
             list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
             Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
-    
+
     Examples::
-        
+
         tokenizer = CamembertTokenizer.from_pretrained('camembert-base')
         model = TFCamembertForTokenClassification.from_pretrained('camembert-base')
         input_ids = tf.constant(tokenizer.encode("J'aime le camembert !", add_special_tokens=True))[None, :]  # Batch size 1
         outputs = model(input_ids)
         loss, scores = outputs[:2]
-    
+
     """
     config_class = CamembertConfig
     pretrained_model_archive_map = TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP

templates/adding_a_new_example_script/run_xxx.py

@@ -52,7 +52,6 @@ from utils_squad import (
     write_predictions,
     write_predictions_extended,
 )
-
 # The follwing import is the official SQuAD evaluation script (2.0).
 # You can remove it from the dependencies if you are using this script outside of the library
 # We've added it here for automated tests (see examples/test_examples.py file)
@@ -333,7 +332,8 @@ def evaluate(args, model, tokenizer, prefix=""):
 
 def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=False):
     if args.local_rank not in [-1, 0] and not evaluate:
-        torch.distributed.barrier()  # Make sure only the first process in distributed training process the dataset, and the others will use the cache
+        torch.distributed.barrier()  # Make sure only the first process in distributed training process the dataset,
+        # and the others will use the cache
 
     # Load data features from cache or dataset file
     input_file = args.predict_file if evaluate else args.train_file
@@ -366,7 +366,8 @@ def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=Fal
             torch.save(features, cached_features_file)
 
     if args.local_rank == 0 and not evaluate:
-        torch.distributed.barrier()  # Make sure only the first process in distributed training process the dataset, and the others will use the cache
+        torch.distributed.barrier()  # Make sure only the first process in distributed training process the dataset,
+        # and the others will use the cache
 
     # Convert to Tensors and build dataset
     all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
@@ -620,7 +621,8 @@ def main():
 
     # Load pretrained model and tokenizer
     if args.local_rank not in [-1, 0]:
-        torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab
+        torch.distributed.barrier()  # Make sure only the first process in distributed training will
+        # download model & vocab
 
     args.model_type = args.model_type.lower()
     config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
@@ -641,15 +643,16 @@ def main():
     )
 
     if args.local_rank == 0:
-        torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab
+        torch.distributed.barrier()  # Make sure only the first process in distributed training will
+        # download model & vocab
 
     model.to(args.device)
 
     logger.info("Training/evaluation parameters %s", args)
 
-    # Before we do anything with models, we want to ensure that we get fp16 execution of torch.einsum if args.fp16 is set.
-    # Otherwise it'll default to "promote" mode, and we'll get fp32 operations. Note that running `--fp16_opt_level="O2"` will
-    # remove the need for this code, but it is still valid.
+    # Before we do anything with models, we want to ensure that we get fp16 execution of torch.einsum
+    # if args.fp16 is set. Otherwise it'll default to "promote" mode, and we'll get fp32 operations.
+    # Note that running `--fp16_opt_level="O2"` will remove the need for this code, but it is still valid.
     if args.fp16:
         try:
             import apex

templates/adding_a_new_example_script/utils_xxx.py

@@ -21,7 +21,6 @@ import logging
 import math
 
 from transformers.tokenization_bert import BasicTokenizer, whitespace_tokenize
-
 # Required by XLNet evaluation method to compute optimal threshold (see write_predictions_extended() method)
 from utils_squad_evaluate import find_all_best_thresh_v2, get_raw_scores, make_qid_to_has_ans