Doc styling (#8067)

* Important files

* Styling them all

* Revert "Styling them all"

This reverts commit 7d029395fdae8513b8281cbc2a6c239f8093503e.

* Syling them for realsies

* Fix syntax error

* Fix benchmark_utils

* More fixes

* Fix modeling auto and script

* Remove new line

* Fixes

* More fixes

* Fix more files

* Style

* Add FSMT

* More fixes

* More fixes

* More fixes

* More fixes

* Fixes

* More fixes

* More fixes

* Last fixes

* Make sphinx happy

src/transformers/configuration_pegasus.py

@@ -68,12 +68,11 @@ task_specific_params = {
 class PegasusConfig(BartConfig):
     """
     This is the configuration class to store the configuration of a
-    :class:`~transformers.PegasusForConditionalGeneration`. It is used to
-    instantiate a Pegasus model according to the specified arguments, defining the model architecture.
+    :class:`~transformers.PegasusForConditionalGeneration`. It is used to instantiate a Pegasus model according to the
+    specified arguments, defining the model architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
     Args:
         vocab_size (:obj:`int`, `optional`, defaults to 96103):
@@ -94,8 +93,8 @@ class PegasusConfig(BartConfig):
         encoder_ffn_dim (:obj:`int`, `optional`, defaults to 4096):
             Dimensionality of the "intermediate" (i.e., feed-forward) layer in decoder.
         activation_function (:obj:`str` or :obj:`function`, `optional`, defaults to :obj:`"gelu"`):
-            The non-linear activation function (function or string) in the encoder and pooler.
-            If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
+            The non-linear activation function (function or string) in the encoder and pooler. If string,
+            :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
         dropout (:obj:`float`, `optional`, defaults to 0.1):
             The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
         attention_dropout (:obj:`float`, `optional`, defaults to 0.0):
@@ -105,8 +104,8 @@ class PegasusConfig(BartConfig):
         classifier_dropout (:obj:`float`, `optional`, defaults to 0.0):
             The dropout ratio for classifier.
         max_position_embeddings (:obj:`int`, `optional`, defaults to 1024):
-            The maximum sequence length that this model might ever be used with.
-            Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
         init_std (:obj:`float`, `optional`, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         add_bias_logits (:obj:`bool`, `optional`, defaults to :obj:`False`):
@@ -128,11 +127,11 @@ class PegasusConfig(BartConfig):
         bos_token_id (:obj:`int`, `optional`, defaults to 0)
             Beginning of stream token id.
         encoder_layerdrop: (:obj:`float`, `optional`, defaults to 0.0):
-            The LayerDrop probability for the encoder. See the `LayerDrop paper
-            <see https://arxiv.org/abs/1909.11556>`__ for more details.
+            The LayerDrop probability for the encoder. See the `LayerDrop paper <see
+            https://arxiv.org/abs/1909.11556>`__ for more details.
         decoder_layerdrop: (:obj:`float`, `optional`, defaults to 0.0):
-            The LayerDrop probability for the decoder. See the `LayerDrop paper
-            <see https://arxiv.org/abs/1909.11556>`__ for more details.
+            The LayerDrop probability for the decoder. See the `LayerDrop paper <see
+            https://arxiv.org/abs/1909.11556>`__ for more details.
         extra_pos_embeddings: (:obj:`int`, `optional`, defaults to 2):
             How many extra learned positional embeddings to use. Should be pad_token_id+1 for bart.
         is_encoder_decoder (:obj:`bool`, `optional`, defaults to :obj:`True`):

src/transformers/configuration_prophetnet.py

@@ -28,22 +28,21 @@ PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 
 class ProphetNetConfig(PretrainedConfig):
     r"""
-    This is the configuration class to store the configuration of a :class:`~transformers.ProphetNetModel`. It is used to
-    instantiate a ProphetNet model according to the specified arguments, defining the model architecture.
+    This is the configuration class to store the configuration of a :class:`~transformers.ProphetNetModel`. It is used
+    to instantiate a ProphetNet model according to the specified arguments, defining the model architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
     Args:
         activation_dropout (:obj:`float`, `optional`, defaults to 0.1):
             The dropout ratio for activations inside the fully connected layer.
         activation_function (:obj:`str` or :obj:`function`, `optional`, defaults to :obj:`"gelu"`):
-            The non-linear activation function (function or string) in the encoder and pooler.
-            If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
+            The non-linear activation function (function or string) in the encoder and pooler. If string,
+            :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
         vocab_size (:obj:`int`, `optional`, defaults to 30522):
-            Vocabulary size of the ProphetNET model. Defines the number of different tokens that can be represented by the
-            :obj:`inputs_ids` passed when calling :class:`~transformers.ProphetNetModel`.
+            Vocabulary size of the ProphetNET model. Defines the number of different tokens that can be represented by
+            the :obj:`inputs_ids` passed when calling :class:`~transformers.ProphetNetModel`.
         hidden_size (:obj:`int`, `optional`, defaults to 1024):
             Dimensionality of the layers and the pooler layer.
         encoder_ffn_dim (:obj:`int`, `optional`, defaults to 4096):
@@ -63,8 +62,8 @@ class ProphetNetConfig(PretrainedConfig):
         dropout (:obj:`float`, `optional`, defaults to 0.1):
             The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
         max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
-            The maximum sequence length that this model might ever be used with.
-            Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
         init_std (:obj:`float`, `optional`, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         add_cross_attention (:obj:`bool`, `optional`, defaults to :obj:`True`):
@@ -78,21 +77,19 @@ class ProphetNetConfig(PretrainedConfig):
         eos_token_id (:obj:`int`, `optional`, defaults to 2)
             End of stream token id.
         ngram (:obj:`int`, `optional`, defaults to 2)
-            Number of future tokens to predict.
-            Set to 1 to be same as traditional Language model to predict next first token.
+            Number of future tokens to predict. Set to 1 to be same as traditional Language model to predict next first
+            token.
         num_buckets (:obj:`int`, `optional`, defaults to 32)
-            The number of buckets to use for each attention layer.
-            This is for relative position calculation. See the `T5 paper
-            <see https://arxiv.org/abs/1910.10683>`__ for more details.
+            The number of buckets to use for each attention layer. This is for relative position calculation. See the
+            `T5 paper <see https://arxiv.org/abs/1910.10683>`__ for more details.
         relative_max_distance (:obj:`int`, `optional`, defaults to 128)
-            Relative distances greater than this number will be put into the last same bucket.
-            This is for relative position calculation. See the `T5 paper
-            <see https://arxiv.org/abs/1910.10683>`__ for more details.
+            Relative distances greater than this number will be put into the last same bucket. This is for relative
+            position calculation. See the `T5 paper <see https://arxiv.org/abs/1910.10683>`__ for more details.
         disable_ngram_loss (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether be trained predicting only the next first token.
         eps (:obj:`float`, `optional`, defaults to 0.0):
-            Controls the ``epsilon`` parameter value for label
-            smoothing in the loss calculation. If set to 0, no label smoothing is performed.
+            Controls the ``epsilon`` parameter value for label smoothing in the loss calculation. If set to 0, no label
+            smoothing is performed.
     """
     model_type = "prophetnet"
 

src/transformers/configuration_rag.py

@@ -21,16 +21,17 @@ from .file_utils import add_start_docstrings
 
 
 RAG_CONFIG_DOC = r"""
-    :class:`~transformers.RagConfig` stores the configuration of a `RagModel`.
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    :class:`~transformers.RagConfig` stores the configuration of a `RagModel`. Configuration objects inherit from
+    :class:`~transformers.PretrainedConfig` and can be used to control the model outputs. Read the documentation from
+    :class:`~transformers.PretrainedConfig` for more information.
 
     Args:
         title_sep (:obj:`str`, `optional`, defaults to  ``" / "``):
-            Separator inserted between the title and the text of the retrieved document when calling :class:`~transformers.RagRetriever`.
+            Separator inserted between the title and the text of the retrieved document when calling
+            :class:`~transformers.RagRetriever`.
         doc_sep (:obj:`str`, `optional`, defaults to  ``" // "``):
-            Separator inserted between the the text of the retrieved document and the original input when calliang :class:`~transformers.RagRetriever`.
+            Separator inserted between the the text of the retrieved document and the original input when calliang
+            :class:`~transformers.RagRetriever`.
         n_docs (:obj:`int`, `optional`, defaults to 5):
             Number of documents to retrieve.
         max_combined_length (:obj:`int`, `optional`, defaults to 300):
@@ -41,8 +42,8 @@ RAG_CONFIG_DOC = r"""
             Retrieval batch size, defined as the number of queries issues concurrently to the faiss index excapsulated
             :class:`~transformers.RagRetriever`.
         dataset (:obj:`str`, `optional`, defaults to :obj:`"wiki_dpr"`):
-            A dataset identifier of the indexed dataset in HuggingFace Datasets (list all available datasets and
-            ids using :obj:`datasets.list_datasets()`).
+            A dataset identifier of the indexed dataset in HuggingFace Datasets (list all available datasets and ids
+            using :obj:`datasets.list_datasets()`).
         dataset_split (:obj:`str`, `optional`, defaults to :obj:`"train"`)
             Which split of the :obj:`dataset` to load.
         index_name (:obj:`str`, `optional`, defaults to :obj:`"compressed"`)
@@ -59,13 +60,13 @@ RAG_CONFIG_DOC = r"""
             Only relevant if ``return_loss`` is set to :obj:`True`. Controls the ``epsilon`` parameter value for label
             smoothing in the loss calculation. If set to 0, no label smoothing is performed.
         do_marginalize (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            If :obj:`True`, the logits are marginalized over all documents
-            by making use of ``torch.nn.functional.log_softmax``.
+            If :obj:`True`, the logits are marginalized over all documents by making use of
+            ``torch.nn.functional.log_softmax``.
         reduce_loss (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether or not to reduce the NLL loss using the ``torch.Tensor.sum`` operation.
         do_deduplication (:obj:`bool`, `optional`, defaults to :obj:`True`):
-            Whether or not to deduplicate the generations from different context documents for a given input.
-            Has to be set to :obj:`False` if used while training with distributed backend.
+            Whether or not to deduplicate the generations from different context documents for a given input. Has to be
+            set to :obj:`False` if used while training with distributed backend.
         exclude_bos_score (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether or not to disregard the BOS token when computing the loss.
         output_retrieved(:obj:`bool`, `optional`, defaults to :obj:`False`):
@@ -160,7 +161,8 @@ class RagConfig(PretrainedConfig):
         cls, question_encoder_config: PretrainedConfig, generator_config: PretrainedConfig, **kwargs
     ) -> PretrainedConfig:
         r"""
-        Instantiate a :class:`~transformers.EncoderDecoderConfig` (or a derived class) from a pre-trained encoder model configuration and decoder model configuration.
+        Instantiate a :class:`~transformers.EncoderDecoderConfig` (or a derived class) from a pre-trained encoder model
+        configuration and decoder model configuration.
 
         Returns:
             :class:`EncoderDecoderConfig`: An instance of a configuration object
@@ -169,7 +171,8 @@ class RagConfig(PretrainedConfig):
 
     def to_dict(self):
         """
-        Serializes this instance to a Python dictionary. Override the default :meth:`~transformers.PretrainedConfig.to_dict`.
+        Serializes this instance to a Python dictionary. Override the default
+        :meth:`~transformers.PretrainedConfig.to_dict`.
 
         Returns:
             :obj:`Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,

src/transformers/configuration_reformer.py

@@ -32,16 +32,15 @@ class ReformerConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a :class:`~transformers.ReformerModel`. It is used to
     instantiate a Reformer model according to the specified arguments, defining the model architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
     Args:
         attention_head_size (:obj:`int`, `optional`, defaults to 64):
             Dimensionality of the projected key, query and value vectors
         attn_layers (:obj:`List[str]`, `optional`, defaults to :obj:`["local", "lsh", "local", "lsh", "local", "lsh"]`):
-            List of attention layer types in ascending order. It can be chosen between a
-            LSHSelfAttention layer (:obj:`"lsh"`) and a LocalSelfAttention layer (:obj:`"local"`).
+            List of attention layer types in ascending order. It can be chosen between a LSHSelfAttention layer
+            (:obj:`"lsh"`) and a LocalSelfAttention layer (:obj:`"local"`).
 
             For more information on LSHSelfAttention layer, see `LSH Self Attention
             <reformer.html#lsh-self-attention>`__. For more information on LocalSelfAttention layer, see `Local Self
@@ -65,9 +64,9 @@ class ReformerConfig(PretrainedConfig):
             For more information on how axial position embeddings work, see `Axial Position Encodings
             <reformer.html#axial-positional-encodings>`__.
         chunk_size_lm_head (:obj:`int`, `optional`, defaults to 0):
-            The chunk size of the final language model feed forward head layer.
-            A chunk size of 0 means that the feed forward layer is not chunked.
-            A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time.
+            The chunk size of the final language model feed forward head layer. A chunk size of 0 means that the feed
+            forward layer is not chunked. A chunk size of n means that the feed forward layer processes n <
+            sequence_length embeddings at a time.
 
             For more information on feed forward chunking, see `How does Feed Forward Chunking work?
             <../glossary.html#feed-forward-chunking>`__.
@@ -81,8 +80,7 @@ class ReformerConfig(PretrainedConfig):
             :obj:`None` to ensure fully random rotations in local sensitive hashing scheme.
         hidden_act (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"relu"`):
             The non-linear activation function (function or string) in the feed forward layer in the residual attention
-            block.
-            If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
+            block. If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
         hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.05):
             The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
         hidden_size (:obj:`int`, `optional`, defaults to 256):
@@ -97,8 +95,8 @@ class ReformerConfig(PretrainedConfig):
             The epsilon used by the layer normalization layers.
         local_chunk_length (:obj:`int`, `optional`, defaults to 64):
             Length of chunk which attends to itself in :obj:`LocalSelfAttention`. Chunking reduces memory complexity
-            from sequence length x sequence length (self attention) to
-            chunk length x chunk length x sequence length / chunk length (chunked self attention).
+            from sequence length x sequence length (self attention) to chunk length x chunk length x sequence length /
+            chunk length (chunked self attention).
         local_num_chunks_before (:obj:`int`, `optional`, defaults to 1):
             Number of previous neighbouring chunks to attend to in :obj:`LocalSelfAttention` layer to itself.
         local_num_chunks_after (:obj:`int`, `optional`, defaults to 0):
@@ -108,8 +106,8 @@ class ReformerConfig(PretrainedConfig):
             The dropout ratio for the attention probabilities in :obj:`LocalSelfAttention`.
         lsh_attn_chunk_length (:obj:`int`, `optional`, defaults to 64):
             Length of chunk which attends to itself in :obj:`LSHSelfAttention`. Chunking reduces memory complexity from
-            sequence length x sequence length (self attention) to
-            chunk length x chunk length x sequence length / chunk length (chunked self attention).
+            sequence length x sequence length (self attention) to chunk length x chunk length x sequence length / chunk
+            length (chunked self attention).
         lsh_num_chunks_before (:obj:`int`, `optional`, defaults to 1):
             Number of previous neighbouring chunks to attend to in :obj:`LSHSelfAttention` layer to itself.
         lsh_num_chunks_after (:obj:`int`, `optional`, defaults to 0):
@@ -117,23 +115,22 @@ class ReformerConfig(PretrainedConfig):
         lsh_attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
             The dropout ratio for the attention probabilities in :obj:`LSHSelfAttention`.
         max_position_embeddings (:obj:`int`, `optional`, defaults to 4096):
-            The maximum sequence length that this model might ever be used with.
-            Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
         num_attention_heads (:obj:`int`, `optional`, defaults to 12):
             Number of attention heads for each attention layer in the Transformer encoder.
         num_buckets (:obj:`int` or :obj:`List[int]`, `optional`):
             Number of buckets, the key query vectors can be "hashed into" using the locality sensitive hashing scheme.
-            Each query key vector is hashed into a hash in :obj:`1, ..., num_buckets`.
-            The number of buckets can also be factorized into a list for improved memory complexity. In this case, each
-            query key vector is hashed into a hash in
-            :obj:`1-1, 1-2, ..., num_buckets[0]-1, ..., num_buckets[0]-num_buckets[1]` if :obj:`num_buckets` is
-            factorized into two factors.
-            The number of buckets (or the product the factors) should approximately equal
-            sequence length / lsh_chunk_length. If :obj:`num_buckets` not set, a good value is calculated on the fly.
+            Each query key vector is hashed into a hash in :obj:`1, ..., num_buckets`. The number of buckets can also
+            be factorized into a list for improved memory complexity. In this case, each query key vector is hashed
+            into a hash in :obj:`1-1, 1-2, ..., num_buckets[0]-1, ..., num_buckets[0]-num_buckets[1]` if
+            :obj:`num_buckets` is factorized into two factors. The number of buckets (or the product the factors)
+            should approximately equal sequence length / lsh_chunk_length. If :obj:`num_buckets` not set, a good value
+            is calculated on the fly.
         num_hashes (:obj:`int`, `optional`, defaults to 1):
-            Number of hashing rounds (e.g., number of random rotations) in Local Sensitive Hashing scheme.
-            The higher :obj:`num_hashes`, the more accurate the :obj:`LSHSelfAttention` becomes, but also the more
-            memory and time intensive the hashing becomes.
+            Number of hashing rounds (e.g., number of random rotations) in Local Sensitive Hashing scheme. The higher
+            :obj:`num_hashes`, the more accurate the :obj:`LSHSelfAttention` becomes, but also the more memory and time
+            intensive the hashing becomes.
         pad_token_id (:obj:`int`, `optional`, defaults to 0):
             The token id for the padding token.
         vocab_size (:obj:`int`, `optional`, defaults to 320):\

src/transformers/configuration_retribert.py

@@ -28,13 +28,11 @@ RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 
 class RetriBertConfig(PretrainedConfig):
     r"""
-    This is the configuration class to store the configuration of a :class:`~transformers.RetriBertModel`.
-    It is used to instantiate a RetriBertModel model according to the specified arguments, defining the model
-    architecture.
+    This is the configuration class to store the configuration of a :class:`~transformers.RetriBertModel`. It is used
+    to instantiate a RetriBertModel model according to the specified arguments, defining the model architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
 
     Args:
@@ -50,15 +48,15 @@ class RetriBertConfig(PretrainedConfig):
         intermediate_size (:obj:`int`, `optional`, defaults to 3072):
             Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
         hidden_act (:obj:`str` or :obj:`function`, `optional`, defaults to :obj:`"gelu"`):
-            The non-linear activation function (function or string) in the encoder and pooler.
-            If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
+            The non-linear activation function (function or string) in the encoder and pooler. If string,
+            :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
         hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
             The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
-            The maximum sequence length that this model might ever be used with.
-            Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
         type_vocab_size (:obj:`int`, `optional`, defaults to 2):
             The vocabulary size of the `token_type_ids` passed into :class:`~transformers.BertModel`.
         initializer_range (:obj:`float`, `optional`, defaults to 0.02):

src/transformers/configuration_roberta.py

@@ -38,12 +38,11 @@ class RobertaConfig(BertConfig):
     arguments, defining the model architecture.
 
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
-    The :class:`~transformers.RobertaConfig` class directly inherits :class:`~transformers.BertConfig`.
-    It reuses the same defaults. Please check the parent class for more information.
+    The :class:`~transformers.RobertaConfig` class directly inherits :class:`~transformers.BertConfig`. It reuses the
+    same defaults. Please check the parent class for more information.
 
     Examples::
 

src/transformers/configuration_squeezebert.py

@@ -29,19 +29,17 @@ SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 
 class SqueezeBertConfig(PretrainedConfig):
     r"""
-    This is the configuration class to store the configuration of a :class:`~transformers.SqueezeBertModel`.
-    It is used to instantiate a SqueezeBERT model according to the specified arguments, defining the model
-    architecture.
+    This is the configuration class to store the configuration of a :class:`~transformers.SqueezeBertModel`. It is used
+    to instantiate a SqueezeBERT model according to the specified arguments, defining the model architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
 
     Args:
         vocab_size (:obj:`int`, `optional`, defaults to 30522):
-            Vocabulary size of the SqueezeBERT model. Defines the number of different tokens that can be
-            represented by the :obj:`inputs_ids` passed when calling :class:`~transformers.SqueezeBertModel`.
+            Vocabulary size of the SqueezeBERT model. Defines the number of different tokens that can be represented by
+            the :obj:`inputs_ids` passed when calling :class:`~transformers.SqueezeBertModel`.
         hidden_size (:obj:`int`, `optional`, defaults to 768):
             Dimensionality of the encoder layers and the pooler layer.
         num_hidden_layers (:obj:`int`, `optional`, defaults to 12):
@@ -51,15 +49,15 @@ class SqueezeBertConfig(PretrainedConfig):
         intermediate_size (:obj:`int`, `optional`, defaults to 3072):
             Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
         hidden_act (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"gelu"`):
-            The non-linear activation function (function or string) in the encoder and pooler.
-            If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
+            The non-linear activation function (function or string) in the encoder and pooler. If string,
+            :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
         hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
             The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
-            The maximum sequence length that this model might ever be used with.
-            Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
         type_vocab_size (:obj:`int`, `optional`, defaults to 2):
             The vocabulary size of the :obj:`token_type_ids` passed when calling :class:`~transformers.BertModel` or
             :class:`~transformers.TFBertModel`.
@@ -85,7 +83,7 @@ class SqueezeBertConfig(PretrainedConfig):
         output_groups (:obj:`int`, `optional`, defaults to 4):
             The number of groups in the third feed forward network layer.
 
-    Example:
+    Examples::
 
         >>> from transformers import SqueezeBertModel, SqueezeBertConfig
 
@@ -98,9 +96,8 @@ class SqueezeBertConfig(PretrainedConfig):
         >>> # Accessing the model configuration
         >>> configuration = model.config
 
-    Attributes:
-        pretrained_config_archive_map (Dict[str, str]):
-            A dictionary containing all the available pre-trained checkpoints.
+    Attributes: pretrained_config_archive_map (Dict[str, str]): A dictionary containing all the available pre-trained
+    checkpoints.
     """
     pretrained_config_archive_map = SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
     model_type = "squeezebert"

src/transformers/configuration_t5.py

@@ -32,36 +32,34 @@ T5_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class T5Config(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a :class:`~transformers.T5Model` or a
-    :class:`~transformers.TFT5Model`. It is used to instantiate a T5 model according to the specified
-    arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar
-    configuration to that of the T5 `t5-small <https://huggingface.co/t5-small>`__ architecture.
+    :class:`~transformers.TFT5Model`. It is used to instantiate a T5 model according to the specified arguments,
+    defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration
+    to that of the T5 `t5-small <https://huggingface.co/t5-small>`__ architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
     Arguments:
         vocab_size (:obj:`int`, `optional`, defaults to 32128):
             Vocabulary size of the T5 model. Defines the number of different tokens that can be represented by the
-            :obj:`inputs_ids` passed when calling :class:`~transformers.T5Model` or
-            :class:`~transformers.TFT5Model`.
+            :obj:`inputs_ids` passed when calling :class:`~transformers.T5Model` or :class:`~transformers.TFT5Model`.
         n_positions (:obj:`int`, `optional`, defaults to 512):
             The maximum sequence length that this model might ever be used with. Typically set this to something large
             just in case (e.g., 512 or 1024 or 2048).
         d_model (:obj:`int`, `optional`, defaults to 512):
             Size of the encoder layers and the pooler layer.
         d_kv (:obj:`int`, `optional`, defaults to 64):
-            Size of the key, query, value projections per attention head. :obj:`d_kv` has to be equal to
-            :obj:`d_model // num_heads`.
+            Size of the key, query, value projections per attention head. :obj:`d_kv` has to be equal to :obj:`d_model
+            // num_heads`.
         d_ff (:obj:`int`, `optional`, defaults to 2048):
             Size of the intermediate feed forward layer in each :obj:`T5Block`.
         num_layers (:obj:`int`, `optional`, defaults to 6):
             Number of hidden layers in the Transformer encoder.
         num_decoder_layers (:obj:`int`, `optional`):
-            Number of hidden layers in the Transformer decoder. Will use the same value as :obj:`num_layers` if not set.
+            Number of hidden layers in the Transformer decoder. Will use the same value as :obj:`num_layers` if not
+            set.
         num_heads (:obj:`int`, `optional`, defaults to 8):
-            Number of attention heads for each attention layer in
-            the Transformer encoder.
+            Number of attention heads for each attention layer in the Transformer encoder.
         relative_attention_num_buckets (:obj:`int`, `optional`, defaults to 32):
             The number of buckets to use for each attention layer.
         dropout_rate (:obj:`float`, `optional`, defaults to 0.1):

src/transformers/configuration_transfo_xl.py

@@ -32,13 +32,12 @@ TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class TransfoXLConfig(PretrainedConfig):
     """
     This is the configuration class to store the configuration of a :class:`~transformers.TransfoXLModel` or a
-    :class:`~transformers.TFTransfoXLModel`. It is used to instantiate a Transformer-XL model according to the specified
-    arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar
-    configuration to that of the `Transformer XL <https://huggingface.co/transfo-xl-wt103>`__ architecture.
+    :class:`~transformers.TFTransfoXLModel`. It is used to instantiate a Transformer-XL model according to the
+    specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a
+    similar configuration to that of the `Transformer XL <https://huggingface.co/transfo-xl-wt103>`__ architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
     Args:
         vocab_size (:obj:`int`, `optional`, defaults to 267735):

src/transformers/configuration_utils.py

@@ -29,27 +29,26 @@ logger = logging.get_logger(__name__)
 
 
 class PretrainedConfig(object):
-    r"""Base class for all configuration classes.
-    Handles a few parameters common to all models' configurations as well as methods for loading/downloading/saving
-    configurations.
+    r"""
+    Base class for all configuration classes. Handles a few parameters common to all models' configurations as well as
+    methods for loading/downloading/saving configurations.
 
-    Note:
-        A configuration file can be loaded and saved to disk. Loading the configuration file and using this file to
-        initialize a model does **not** load the model weights.
-        It only affects the model's configuration.
+    Note: A configuration file can be loaded and saved to disk. Loading the configuration file and using this file to
+    initialize a model does **not** load the model weights. It only affects the model's configuration.
 
     Class attributes (overridden by derived classes)
+
         - **model_type** (:obj:`str`): An identifier for the model type, serialized into the JSON file, and used to
           recreate the correct object in :class:`~transformers.AutoConfig`.
-        - **is_composition** (:obj:`bool`): Whether the config class is composed of multiple
-          sub-configs. In this case the config has to be initialized from two or more configs of
-          type :class:`~transformers.PretrainedConfig` like: :class:`~transformers.EncoderDecoderConfig` or
-          :class:`~RagConfig`.
+        - **is_composition** (:obj:`bool`): Whether the config class is composed of multiple sub-configs. In this case
+          the config has to be initialized from two or more configs of type :class:`~transformers.PretrainedConfig`
+          like: :class:`~transformers.EncoderDecoderConfig` or :class:`~RagConfig`.
 
     Args:
         name_or_path (:obj:`str`, `optional`, defaults to :obj:`""`):
-            Store the string that was passed to :func:`~transformers.PreTrainedModel.from_pretrained` or :func:`~transformers.TFPreTrainedModel.from_pretrained`
-            as ``pretrained_model_name_or_path`` if the configuration was created with such a method.
+            Store the string that was passed to :func:`~transformers.PreTrainedModel.from_pretrained` or
+            :func:`~transformers.TFPreTrainedModel.from_pretrained` as ``pretrained_model_name_or_path`` if the
+            configuration was created with such a method.
         output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether or not the model should return all hidden-states.
         output_attentions (:obj:`bool`, `optional`, defaults to :obj:`False`):
@@ -57,68 +56,72 @@ class PretrainedConfig(object):
         use_cache (:obj:`bool`, `optional`, defaults to :obj:`True`):
             Whether or not the model should return the last key/values attentions (not used by all models).
         return_dict (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            Whether or not the model should return a :class:`~transformers.file_utils.ModelOutput` instead of a
-            plain tuple.
+            Whether or not the model should return a :class:`~transformers.file_utils.ModelOutput` instead of a plain
+            tuple.
         is_encoder_decoder (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether the model is used as an encoder/decoder or not.
         is_decoder (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether the model is used as decoder or not (in which case it's used as an encoder).
         add_cross_attention (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            Whether cross-attention layers should be added to the model. Note, this option is only relevant for models that can be used as decoder models within the `:class:~transformers.EncoderDecoderModel` class, which consists of all models in ``AUTO_MODELS_FOR_CAUSAL_LM``.
+            Whether cross-attention layers should be added to the model. Note, this option is only relevant for models
+            that can be used as decoder models within the `:class:~transformers.EncoderDecoderModel` class, which
+            consists of all models in ``AUTO_MODELS_FOR_CAUSAL_LM``.
         tie_encoder_decoder (:obj:`bool`, `optional`, defaults to :obj:`False`)
-            Whether all encoder weights should be tied to their equivalent decoder weights. This requires the encoder and decoder model to have the exact same parameter names.
+            Whether all encoder weights should be tied to their equivalent decoder weights. This requires the encoder
+            and decoder model to have the exact same parameter names.
         prune_heads (:obj:`Dict[int, List[int]]`, `optional`, defaults to :obj:`{}`):
-            Pruned heads of the model. The keys are the selected layer indices and the associated values, the list
-            of heads to prune in said layer.
+            Pruned heads of the model. The keys are the selected layer indices and the associated values, the list of
+            heads to prune in said layer.
 
-            For instance ``{1: [0, 2], 2: [2, 3]}`` will prune heads 0 and 2 on layer 1 and heads 2 and 3 on layer
-            2.
+            For instance ``{1: [0, 2], 2: [2, 3]}`` will prune heads 0 and 2 on layer 1 and heads 2 and 3 on layer 2.
         xla_device (:obj:`bool`, `optional`):
             A flag to indicate if TPU are available or not.
         chunk_size_feed_forward (:obj:`int`, `optional`, defaults to :obj:`0`):
-            The chunk size of all feed forward layers in the residual attention blocks.
-            A chunk size of :obj:`0` means that the feed forward layer is not chunked.
-            A chunk size of n means that the feed forward layer processes :obj:`n` < sequence_length embeddings at a time.
-            For more information on feed forward chunking, see `How does Feed Forward Chunking work? <../glossary.html#feed-forward-chunking>`__ .
+            The chunk size of all feed forward layers in the residual attention blocks. A chunk size of :obj:`0` means
+            that the feed forward layer is not chunked. A chunk size of n means that the feed forward layer processes
+            :obj:`n` < sequence_length embeddings at a time. For more information on feed forward chunking, see `How
+            does Feed Forward Chunking work? <../glossary.html#feed-forward-chunking>`__ .
 
     Parameters for sequence generation
-        - **max_length** (:obj:`int`, `optional`, defaults to 20) -- Maximum length that will be used by
-          default in the :obj:`generate` method of the model.
-        - **min_length** (:obj:`int`, `optional`, defaults to 10) -- Minimum length that will be used by
-          default in the :obj:`generate` method of the model.
-        - **do_sample** (:obj:`bool`, `optional`, defaults to :obj:`False`) -- Flag that will be used by default in
-          the :obj:`generate` method of the model. Whether or not to use sampling ; use greedy decoding otherwise.
-        - **early_stopping** (:obj:`bool`, `optional`, defaults to :obj:`False`) -- Flag that will be used by
-          default in the :obj:`generate` method of the model. Whether to stop the beam search when at least
-          ``num_beams`` sentences are finished per batch or not.
-        - **num_beams** (:obj:`int`, `optional`, defaults to 1) -- Number of beams for beam search that will be
-          used by default in the :obj:`generate` method of the model. 1 means no beam search.
+
+        - **max_length** (:obj:`int`, `optional`, defaults to 20) -- Maximum length that will be used by default in the
+          :obj:`generate` method of the model.
+        - **min_length** (:obj:`int`, `optional`, defaults to 10) -- Minimum length that will be used by default in the
+          :obj:`generate` method of the model.
+        - **do_sample** (:obj:`bool`, `optional`, defaults to :obj:`False`) -- Flag that will be used by default in the
+          :obj:`generate` method of the model. Whether or not to use sampling ; use greedy decoding otherwise.
+        - **early_stopping** (:obj:`bool`, `optional`, defaults to :obj:`False`) -- Flag that will be used by default
+          in the :obj:`generate` method of the model. Whether to stop the beam search when at least ``num_beams``
+          sentences are finished per batch or not.
+        - **num_beams** (:obj:`int`, `optional`, defaults to 1) -- Number of beams for beam search that will be used by
+          default in the :obj:`generate` method of the model. 1 means no beam search.
         - **temperature** (:obj:`float`, `optional`, defaults to 1) -- The value used to module the next token
           probabilities that will be used by default in the :obj:`generate` method of the model. Must be strictly
           positive.
-        - **top_k** (:obj:`int`, `optional`, defaults to 50) -- Number of highest probability vocabulary tokens to
-          keep for top-k-filtering that will be used by default in the :obj:`generate` method of the model.
-        - **top_p** (:obj:`float`, `optional`, defaults to 1) --  Value that will be used by default in the
-          :obj:`generate` method of the model for ``top_p``. If set to float < 1, only the most probable tokens
-          with probabilities that add up to ``top_p`` or higher are kept for generation.
-        - **repetition_penalty** (:obj:`float`, `optional`, defaults to 1) -- Parameter for repetition penalty
-          that will be used by default in the :obj:`generate` method of the model. 1.0 means no penalty.
-        - **length_penalty** (:obj:`float`, `optional`, defaults to 1) -- Exponential penalty to the length that
-          will be used by default in the :obj:`generate` method of the model.
-        - **no_repeat_ngram_size** (:obj:`int`, `optional`, defaults to 0) -- Value that will be used by default
-          in the :obj:`generate` method of the model for ``no_repeat_ngram_size``. If set to int > 0, all ngrams of
-          that size can only occur once.
-        - **bad_words_ids** (:obj:`List[int]`, `optional`) -- List of token ids that are not allowed to be
-          generated that will be used by default in the :obj:`generate` method of the model. In order to get the
-          tokens of the words that should not appear in the generated text, use
-          :obj:`tokenizer.encode(bad_word, add_prefix_space=True)`.
-        - **num_return_sequences** (:obj:`int`, `optional`, defaults to 1) -- Number of independently computed
-          returned sequences for each element in the batch that will be used by default in the :obj:`generate`
-          method of the model.
+        - **top_k** (:obj:`int`, `optional`, defaults to 50) -- Number of highest probability vocabulary tokens to keep
+          for top-k-filtering that will be used by default in the :obj:`generate` method of the model.
+        - **top_p** (:obj:`float`, `optional`, defaults to 1) -- Value that will be used by default in the
+          :obj:`generate` method of the model for ``top_p``. If set to float < 1, only the most probable tokens with
+          probabilities that add up to ``top_p`` or higher are kept for generation.
+        - **repetition_penalty** (:obj:`float`, `optional`, defaults to 1) -- Parameter for repetition penalty that
+          will be used by default in the :obj:`generate` method of the model. 1.0 means no penalty.
+        - **length_penalty** (:obj:`float`, `optional`, defaults to 1) -- Exponential penalty to the length that will
+          be used by default in the :obj:`generate` method of the model.
+        - **no_repeat_ngram_size** (:obj:`int`, `optional`, defaults to 0) -- Value that will be used by default in the
+          :obj:`generate` method of the model for ``no_repeat_ngram_size``. If set to int > 0, all ngrams of that size
+          can only occur once.
+        - **bad_words_ids** (:obj:`List[int]`, `optional`) -- List of token ids that are not allowed to be generated
+          that will be used by default in the :obj:`generate` method of the model. In order to get the tokens of the
+          words that should not appear in the generated text, use :obj:`tokenizer.encode(bad_word,
+          add_prefix_space=True)`.
+        - **num_return_sequences** (:obj:`int`, `optional`, defaults to 1) -- Number of independently computed returned
+          sequences for each element in the batch that will be used by default in the :obj:`generate` method of the
+          model.
 
     Parameters for fine-tuning tasks
-        - **architectures** (:obj:`List[str]`, `optional`) -- Model architectures that can be used with the
-          model pretrained weights.
+
+        - **architectures** (:obj:`List[str]`, `optional`) -- Model architectures that can be used with the model
+          pretrained weights.
         - **finetuning_task** (:obj:`str`, `optional`) -- Name of the task used to fine-tune the model. This can be
           used when converting from an original (TensorFlow or PyTorch) checkpoint.
         - **id2label** (:obj:`Dict[int, str]`, `optional`) -- A map from index (for instance prediction index, or
@@ -126,27 +129,32 @@ class PretrainedConfig(object):
         - **label2id** (:obj:`Dict[str, int]`, `optional`) -- A map from label to index for the model.
         - **num_labels** (:obj:`int`, `optional`) -- Number of labels to use in the last layer added to the model,
           typically for a classification task.
-        - **task_specific_params** (:obj:`Dict[str, Any]`, `optional`) -- Additional keyword arguments to store for
-          the current task.
+        - **task_specific_params** (:obj:`Dict[str, Any]`, `optional`) -- Additional keyword arguments to store for the
+          current task.
 
     Parameters linked to the tokenizer
-        - **prefix** (:obj:`str`, `optional`) -- A specific prompt that should be added at the beginning of each
-          text before calling the model.
+
+        - **prefix** (:obj:`str`, `optional`) -- A specific prompt that should be added at the beginning of each text
+          before calling the model.
         - **bos_token_id** (:obj:`int`, `optional`)) -- The id of the `beginning-of-stream` token.
         - **pad_token_id** (:obj:`int`, `optional`)) -- The id of the `padding` token.
         - **eos_token_id** (:obj:`int`, `optional`)) -- The id of the `end-of-stream` token.
-        - **decoder_start_token_id** (:obj:`int`, `optional`)) -- If an encoder-decoder model starts decoding with
-          a different token than `bos`, the id of that token.
+        - **decoder_start_token_id** (:obj:`int`, `optional`)) -- If an encoder-decoder model starts decoding with a
+          different token than `bos`, the id of that token.
         - **sep_token_id** (:obj:`int`, `optional`)) -- The id of the `separation` token.
 
     PyTorch specific parameters
+
         - **torchscript** (:obj:`bool`, `optional`, defaults to :obj:`False`) -- Whether or not the model should be
           used with Torchscript.
-        - **tie_word_embeddings** (:obj:`bool`, `optional`, defaults to :obj:`True`) -- Whether the model's input and output word embeddings should be tied. Note that this is only relevant if the model has a output word embedding layer.
+        - **tie_word_embeddings** (:obj:`bool`, `optional`, defaults to :obj:`True`) -- Whether the model's input and
+          output word embeddings should be tied. Note that this is only relevant if the model has a output word
+          embedding layer.
 
     TensorFlow specific parameters
-        - **use_bfloat16** (:obj:`bool`, `optional`, defaults to :obj:`False`) -- Whether or not the model should
-          use BFloat16 scalars (only used by some TensorFlow models).
+
+        - **use_bfloat16** (:obj:`bool`, `optional`, defaults to :obj:`False`) -- Whether or not the model should use
+          BFloat16 scalars (only used by some TensorFlow models).
     """
     model_type: str = ""
     is_composition: bool = False
@@ -293,15 +301,14 @@ class PretrainedConfig(object):
                 Path to a directory in which a downloaded pretrained model configuration should be cached if the
                 standard cache should not be used.
             force_download (:obj:`bool`, `optional`, defaults to :obj:`False`):
-                Whether or not to force to (re-)download the configuration files and override the cached versions if they
-                exist.
+                Whether or not to force to (re-)download the configuration files and override the cached versions if
+                they exist.
             resume_download (:obj:`bool`, `optional`, defaults to :obj:`False`):
                 Whether or not to delete incompletely received file. Attempts to resume the download if such a file
                 exists.
             proxies (:obj:`Dict[str, str]`, `optional`):
-                A dictionary of proxy servers to use by protocol or endpoint, e.g.,
-                :obj:`{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}.`
-                The proxies are used on each request.
+                A dictionary of proxy servers to use by protocol or endpoint, e.g., :obj:`{'http': 'foo.bar:3128',
+                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
             return_unused_kwargs (:obj:`bool`, `optional`, defaults to :obj:`False`):
                 If :obj:`False`, then this function returns just the final configuration object.
 
@@ -310,8 +317,8 @@ class PretrainedConfig(object):
                 the part of ``kwargs`` which has not been used to update ``config`` and is otherwise ignored.
             kwargs (:obj:`Dict[str, Any]`, `optional`):
                 The values in kwargs of any keys which are configuration attributes will be used to override the loaded
-                values. Behavior concerning key/value pairs whose keys are *not* configuration attributes is
-                controlled by the ``return_unused_kwargs`` keyword parameter.
+                values. Behavior concerning key/value pairs whose keys are *not* configuration attributes is controlled
+                by the ``return_unused_kwargs`` keyword parameter.
 
         Returns:
             :class:`PretrainedConfig`: The configuration object instantiated from this pretrained model.
@@ -337,8 +344,8 @@ class PretrainedConfig(object):
     @classmethod
     def get_config_dict(cls, pretrained_model_name_or_path: str, **kwargs) -> Tuple[Dict[str, Any], Dict[str, Any]]:
         """
-        From a ``pretrained_model_name_or_path``, resolve to a dictionary of parameters, to be used
-        for instantiating a :class:`~transformers.PretrainedConfig` using ``from_dict``.
+        From a ``pretrained_model_name_or_path``, resolve to a dictionary of parameters, to be used for instantiating a
+        :class:`~transformers.PretrainedConfig` using ``from_dict``.
 
         Parameters:
             pretrained_model_name_or_path (:obj:`str`):
@@ -469,9 +476,8 @@ class PretrainedConfig(object):
 
     def to_diff_dict(self) -> Dict[str, Any]:
         """
-        Removes all attributes from config which correspond to the default
-        config attributes for better readability and serializes to a Python
-        dictionary.
+        Removes all attributes from config which correspond to the default config attributes for better readability and
+        serializes to a Python dictionary.
 
         Returns:
             :obj:`Dict[str, Any]`: Dictionary of all the attributes that make up this configuration instance,

src/transformers/configuration_xlm.py

@@ -37,19 +37,17 @@ XLM_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class XLMConfig(PretrainedConfig):
     """
     This is the configuration class to store the configuration of a :class:`~transformers.XLMModel` or a
-    :class:`~transformers.TFXLMModel`. It is used to instantiate a XLM model according to the specified
-    arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar
-    configuration to that of the `xlm-mlm-en-2048 <https://huggingface.co/xlm-mlm-en-2048>`__ architecture.
+    :class:`~transformers.TFXLMModel`. It is used to instantiate a XLM model according to the specified arguments,
+    defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration
+    to that of the `xlm-mlm-en-2048 <https://huggingface.co/xlm-mlm-en-2048>`__ architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
     Args:
         vocab_size (:obj:`int`, `optional`, defaults to 30145):
             Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the
-            :obj:`inputs_ids` passed when calling :class:`~transformers.XLMModel` or
-            :class:`~transformers.TFXLMModel`.
+            :obj:`inputs_ids` passed when calling :class:`~transformers.XLMModel` or :class:`~transformers.TFXLMModel`.
         emb_dim (:obj:`int`, `optional`, defaults to 2048):
             Dimensionality of the encoder layers and the pooler layer.
         n_layer (:obj:`int`, `optional`, defaults to 12):
@@ -57,8 +55,7 @@ class XLMConfig(PretrainedConfig):
         n_head (:obj:`int`, `optional`, defaults to 16):
             Number of attention heads for each attention layer in the Transformer encoder.
         dropout (:obj:`float`, `optional`, defaults to 0.1):
-            The dropout probability for all fully connected
-            layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_dropout (:obj:`float`, `optional`, defaults to 0.1):
             The dropout probability for the attention mechanism
         gelu_activation (:obj:`bool`, `optional`, defaults to :obj:`True`):
@@ -66,28 +63,25 @@ class XLMConfig(PretrainedConfig):
         sinusoidal_embeddings (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether or not to use sinusoidal positional embeddings instead of absolute positional embeddings.
         causal (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            Whether or not the model should behave in a causal manner.
-            Causal models use a triangular attention mask in order to only attend to the left-side context instead
-            if a bidirectional context.
+            Whether or not the model should behave in a causal manner. Causal models use a triangular attention mask in
+            order to only attend to the left-side context instead if a bidirectional context.
         asm (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether or not to use an adaptive log softmax projection layer instead of a linear layer for the prediction
             layer.
         n_langs (:obj:`int`, `optional`, defaults to 1):
             The number of languages the model handles. Set to 1 for monolingual models.
         use_lang_emb (:obj:`bool`, `optional`, defaults to :obj:`True`)
-            Whether to use language embeddings. Some models use additional language embeddings, see
-            `the multilingual models page <http://huggingface.co/transformers/multilingual.html#xlm-language-embeddings>`__
-            for information on how to use them.
+            Whether to use language embeddings. Some models use additional language embeddings, see `the multilingual
+            models page <http://huggingface.co/transformers/multilingual.html#xlm-language-embeddings>`__ for
+            information on how to use them.
         max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
-            The maximum sequence length that this model might
-            ever be used with. Typically set this to something large just in case
-            (e.g., 512 or 1024 or 2048).
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
         embed_init_std (:obj:`float`, `optional`, defaults to 2048^-0.5):
-            The standard deviation of the truncated_normal_initializer for
-            initializing the embedding matrices.
+            The standard deviation of the truncated_normal_initializer for initializing the embedding matrices.
         init_std (:obj:`int`, `optional`, defaults to 50257):
-            The standard deviation of the truncated_normal_initializer for
-            initializing all weight matrices except the embedding matrices.
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices except the
+            embedding matrices.
         layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12):
             The epsilon used by the layer normalization layers.
         bos_index (:obj:`int`, `optional`, defaults to 0):
@@ -135,8 +129,7 @@ class XLMConfig(PretrainedConfig):
         mask_token_id (:obj:`int`, `optional`, defaults to 0):
             Model agnostic parameter to identify masked tokens when generating text in an MLM context.
         lang_id (:obj:`int`, `optional`, defaults to 1):
-            The ID of the language used by the model. This parameter is used when generating
-            text in a given language.
+            The ID of the language used by the model. This parameter is used when generating text in a given language.
 
     Examples::
 

src/transformers/configuration_xlm_prophetnet.py

@@ -28,8 +28,8 @@ XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 
 class XLMProphetNetConfig(ProphetNetConfig):
     """
-    This class overrides :class:`~transformers.ProphetNetConfig`. Please check the
-    superclass for the appropriate documentation alongside usage examples.
+    This class overrides :class:`~transformers.ProphetNetConfig`. Please check the superclass for the appropriate
+    documentation alongside usage examples.
     """
 
     model_type = "xlm-prophetnet"

src/transformers/configuration_xlm_roberta.py

@@ -33,8 +33,8 @@ XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 
 class XLMRobertaConfig(RobertaConfig):
     """
-    This class overrides :class:`~transformers.RobertaConfig`. Please check the
-    superclass for the appropriate documentation alongside usage examples.
+    This class overrides :class:`~transformers.RobertaConfig`. Please check the superclass for the appropriate
+    documentation alongside usage examples.
     """
 
     model_type = "xlm-roberta"

src/transformers/configuration_xlnet.py

@@ -32,13 +32,12 @@ XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class XLNetConfig(PretrainedConfig):
     """
     This is the configuration class to store the configuration of a :class:`~transformers.XLNetModel` or a
-    :class:`~transformers.TFXLNetModel`. It is used to instantiate a XLNet model according to the specified
-    arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar
-    configuration to that of the `xlnet-large-cased <https://huggingface.co/xlnet-large-cased>`__ architecture.
+    :class:`~transformers.TFXLNetModel`. It is used to instantiate a XLNet model according to the specified arguments,
+    defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration
+    to that of the `xlnet-large-cased <https://huggingface.co/xlnet-large-cased>`__ architecture.
 
-    Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
-    to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
-    for more information.
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
     Args:
         vocab_size (:obj:`int`, `optional`, defaults to 32000):
@@ -54,8 +53,8 @@ class XLNetConfig(PretrainedConfig):
         d_inner (:obj:`int`, `optional`, defaults to 4096):
             Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
         ff_activation (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"gelu"`):
-            The non-linear activation function (function or string) in the
-            If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
+            The non-linear activation function (function or string) in the If string, :obj:`"gelu"`, :obj:`"relu"`,
+            :obj:`"swish"` and :obj:`"gelu_new"` are supported.
         untie_r (:obj:`bool`, `optional`, defaults to :obj:`True`):
             Whether or not to untie relative position biases
         attn_type (:obj:`str`, `optional`, defaults to :obj:`"bi"`):
@@ -67,18 +66,16 @@ class XLNetConfig(PretrainedConfig):
         dropout (:obj:`float`, `optional`, defaults to 0.1):
             The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         mem_len (:obj:`int` or :obj:`None`, `optional`):
-            The number of tokens to cache. The key/value pairs that have already been pre-computed
-            in a previous forward pass won't be re-computed. See the
-            `quickstart <https://huggingface.co/transformers/quickstart.html#using-the-past>`__
-            for more information.
+            The number of tokens to cache. The key/value pairs that have already been pre-computed in a previous
+            forward pass won't be re-computed. See the `quickstart
+            <https://huggingface.co/transformers/quickstart.html#using-the-past>`__ for more information.
         reuse_len (:obj:`int`, `optional`):
             The number of tokens in the current batch to be cached and reused in the future.
         bi_data (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            Whether or not to use bidirectional input pipeline. Usually set to :obj:`True` during
-            pretraining and :obj:`False` during finetuning.
+            Whether or not to use bidirectional input pipeline. Usually set to :obj:`True` during pretraining and
+            :obj:`False` during finetuning.
         clamp_len (:obj:`int`, `optional`, defaults to -1):
-            Clamp all relative distances larger than clamp_len.
-            Setting this attribute to -1 means no clamping.
+            Clamp all relative distances larger than clamp_len. Setting this attribute to -1 means no clamping.
         same_length (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether or not to use the same attention length for each token.
         summary_type (:obj:`str`, `optional`, defaults to "last"):

src/transformers/convert_bert_original_tf2_checkpoint_to_pytorch.py

 """
-This script can be used to convert a head-less TF2.x Bert model to PyTorch,
-as published on the official GitHub: https://github.com/tensorflow/models/tree/master/official/nlp/bert
+This script can be used to convert a head-less TF2.x Bert model to PyTorch, as published on the official GitHub:
+https://github.com/tensorflow/models/tree/master/official/nlp/bert
 
-TF2.x uses different variable names from the original BERT (TF 1.4) implementation.
-The script re-maps the TF2.x Bert weight names to the original names, so the model can be imported with Huggingface/transformer.
+TF2.x uses different variable names from the original BERT (TF 1.4) implementation. The script re-maps the TF2.x Bert
+weight names to the original names, so the model can be imported with Huggingface/transformer.
 
 You may adapt this script to include classification/MLM/NSP/etc. heads.
 """

src/transformers/convert_bert_pytorch_checkpoint_to_original_tf.py

@@ -28,12 +28,13 @@ from transformers import BertModel
 def convert_pytorch_checkpoint_to_tf(model: BertModel, ckpt_dir: str, model_name: str):
 
     """
-    Args
+    Args:
         model: BertModel Pytorch model instance to be converted
         ckpt_dir: Tensorflow model directory
         model_name: model name
 
     Currently supported HF models:
+
         - Y BertModel
         - N BertForMaskedLM
         - N BertForPreTraining

src/transformers/convert_graph_to_onnx.py

@@ -77,7 +77,8 @@ class OnnxConverterArgumentParser(ArgumentParser):
 
 def generate_identified_filename(filename: Path, identifier: str) -> Path:
     """
-    Append a string-identifier at the end (before the extension,  if any) to the provided filepath.
+    Append a string-identifier at the end (before the extension, if any) to the provided filepath
+
     Args:
         filename: pathlib.Path The actual path object we would like to add an identifier suffix
         identifier: The suffix to add
@@ -89,7 +90,8 @@ def generate_identified_filename(filename: Path, identifier: str) -> Path:
 
 def check_onnxruntime_requirements(minimum_version: Version):
     """
-    Check onnxruntime is installed and if the installed version match is recent enough.
+    Check onnxruntime is installed and if the installed version match is recent enough
+
     Raises:
         ImportError: If onnxruntime is not installed or too old version is found
     """
@@ -117,7 +119,8 @@ def check_onnxruntime_requirements(minimum_version: Version):
 
 def ensure_valid_input(model, tokens, input_names):
     """
-    Ensure input are presented in the correct order, without any None
+    Ensure input are presented in the correct order, without any Non
+
     Args:
         model: The model used to forward the input data
         tokens: BatchEncoding holding the input data
@@ -144,12 +147,14 @@ def ensure_valid_input(model, tokens, input_names):
 
 def infer_shapes(nlp: Pipeline, framework: str) -> Tuple[List[str], List[str], Dict, BatchEncoding]:
     """
-    Attempt to infer the static vs dynamic axes for each input and output tensors for a specific model.
+    Attempt to infer the static vs dynamic axes for each input and output tensors for a specific model
+
     Args:
         nlp: The pipeline object holding the model to be exported
         framework: The framework identifier to dispatch to the correct inference scheme (pt/tf)
 
     Returns:
+
         - List of the inferred input variable names
         - List of the inferred output variable names
         - Dictionary with input/output variables names as key and shape tensor as value
@@ -206,7 +211,8 @@ def infer_shapes(nlp: Pipeline, framework: str) -> Tuple[List[str], List[str], D
 
 def load_graph_from_args(pipeline_name: str, framework: str, model: str, tokenizer: Optional[str] = None) -> Pipeline:
     """
-    Convert the set of arguments provided through the CLI to an actual pipeline reference (tokenizer + model)
+    Convert the set of arguments provided through the CLI to an actual pipeline reference (tokenizer + model
+
     Args:
         pipeline_name: The kind of pipeline to use (ner, question-answering, etc.)
         framework: The actual model to convert the pipeline from ("pt" or "tf")
@@ -234,7 +240,8 @@ def load_graph_from_args(pipeline_name: str, framework: str, model: str, tokeniz
 
 def convert_pytorch(nlp: Pipeline, opset: int, output: Path, use_external_format: bool):
     """
-    Export a PyTorch backed pipeline to ONNX Intermediate Representation (IR)
+    Export a PyTorch backed pipeline to ONNX Intermediate Representation (IR
+
     Args:
         nlp: The pipeline to be exported
         opset: The actual version of the ONNX operator set to use
@@ -272,7 +279,8 @@ def convert_pytorch(nlp: Pipeline, opset: int, output: Path, use_external_format
 
 def convert_tensorflow(nlp: Pipeline, opset: int, output: Path):
     """
-    Export a TensorFlow backed pipeline to ONNX Intermediate Representation (IR)
+    Export a TensorFlow backed pipeline to ONNX Intermediate Representation (IR
+
     Args:
         nlp: The pipeline to be exported
         opset: The actual version of the ONNX operator set to use
@@ -316,7 +324,8 @@ def convert(
     pipeline_name: str = "feature-extraction",
 ):
     """
-    Convert the pipeline object to the ONNX Intermediate Representation (IR) format.
+    Convert the pipeline object to the ONNX Intermediate Representation (IR) format
+
     Args:
         framework: The framework the pipeline is backed by ("pt" or "tf")
         model: The name of the model to load for the pipeline
@@ -349,8 +358,9 @@ def convert(
 
 def optimize(onnx_model_path: Path) -> Path:
     """
-    Load the model at the specified path and let onnxruntime look at transformations on the graph
-    to enable all the optimizations possible
+    Load the model at the specified path and let onnxruntime look at transformations on the graph to enable all the
+    optimizations possibl
+
     Args:
         onnx_model_path: filepath where the model binary description is stored
 
@@ -373,7 +383,8 @@ def optimize(onnx_model_path: Path) -> Path:
 
 def quantize(onnx_model_path: Path) -> Path:
     """
-    Quantize the weights of the model from float32 to in8 to allow very efficient inference on modern CPU.
+    Quantize the weights of the model from float32 to in8 to allow very efficient inference on modern CPU
+
     Args:
         onnx_model_path: Path to location the exported ONNX model is stored
 

src/transformers/convert_marian_tatoeba_to_pytorch.py

@@ -27,14 +27,16 @@ LANG_CODE_PATH = "lang_code_data/language-codes-3b2.csv"
 
 
 class TatoebaConverter:
-    """Convert Tatoeba-Challenge models to huggingface format.
+    """
+    Convert Tatoeba-Challenge models to huggingface format.
 
     Steps:
 
         1. convert numpy state dict to hf format (same code as OPUS-MT-Train conversion).
-        2. rename opus model to huggingface format. This means replace each alpha3 code with an alpha2 code if a unique one existes.
-           e.g. aav-eng -> aav-en, heb-eng -> he-en
-        3. write a model card containing the original Tatoeba-Challenge/README.md and extra info about alpha3 group members.
+        2. rename opus model to huggingface format. This means replace each alpha3 code with an alpha2 code if a unique
+           one existes. e.g. aav-eng -> aav-en, heb-eng -> he-en
+        3. write a model card containing the original Tatoeba-Challenge/README.md and extra info about alpha3 group
+           members.
     """
 
     def __init__(self, save_dir="marian_converted"):
@@ -148,8 +150,9 @@ class TatoebaConverter:
         repo_root=DEFAULT_REPO,
         dry_run=False,
     ) -> str:
-        """Copy the most recent model's readme section from opus, and add metadata.
-        upload command: aws s3 sync model_card_dir s3://models.huggingface.co/bert/Helsinki-NLP/ --dryrun
+        """
+        Copy the most recent model's readme section from opus, and add metadata. upload command: aws s3 sync
+        model_card_dir s3://models.huggingface.co/bert/Helsinki-NLP/ --dryrun
         """
         short_pair = remove_prefix(hf_model_id, "opus-mt-")
         extra_metadata = self.metadata.loc[short_pair].drop("2m")

src/transformers/convert_marian_to_pytorch.py

@@ -152,8 +152,9 @@ def convert_opus_name_to_hf_name(x):
 
 
 def convert_hf_name_to_opus_name(hf_model_name):
-    """Relies on the assumption that there are no language codes like pt_br in models that are not in
-    GROUP_TO_OPUS_NAME."""
+    """
+    Relies on the assumption that there are no language codes like pt_br in models that are not in GROUP_TO_OPUS_NAME.
+    """
     hf_model_name = remove_prefix(hf_model_name, ORG_NAME)
     if hf_model_name in GROUP_TO_OPUS_NAME:
         opus_w_prefix = GROUP_TO_OPUS_NAME[hf_model_name]
@@ -173,6 +174,7 @@ def get_system_metadata(repo_root):
     )
 
 
+# docstyle-ignore
 FRONT_MATTER_TEMPLATE = """---
 language:
 {}
@@ -181,7 +183,6 @@ tags:
 
 license: apache-2.0
 ---
-
 """
 DEFAULT_REPO = "Tatoeba-Challenge"
 DEFAULT_MODEL_DIR = os.path.join(DEFAULT_REPO, "models")
@@ -194,8 +195,9 @@ def write_model_card(
     dry_run=False,
     extra_metadata={},
 ) -> str:
-    """Copy the most recent model's readme section from opus, and add metadata.
-    upload command: aws s3 sync model_card_dir s3://models.huggingface.co/bert/Helsinki-NLP/ --dryrun
+    """
+    Copy the most recent model's readme section from opus, and add metadata. upload command: aws s3 sync model_card_dir
+    s3://models.huggingface.co/bert/Helsinki-NLP/ --dryrun
     """
     import pandas as pd
 

src/transformers/convert_slow_tokenizer.py

@@ -12,10 +12,11 @@
 # 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.
-""" Utilities to convert slow tokenizers in their fast tokenizers counterparts.
+"""
+ Utilities to convert slow tokenizers in their fast tokenizers counterparts.
 
-    All the conversions are grouped here to gather SentencePiece dependencies outside of
-    the fast tokenizers files and allow to make our dependency on SentencePiece optional.
+    All the conversions are grouped here to gather SentencePiece dependencies outside of the fast tokenizers files and
+    allow to make our dependency on SentencePiece optional.
 """
 
 from typing import Dict, List, Tuple
@@ -31,8 +32,7 @@ from .file_utils import requires_sentencepiece
 
 class SentencePieceExtractor:
     """
-    Extractor implementation for SentencePiece trained models.
-    https://github.com/google/sentencepiece
+    Extractor implementation for SentencePiece trained models. https://github.com/google/sentencepiece
     """
 
     def __init__(self, model: str):
@@ -602,7 +602,8 @@ SLOW_TO_FAST_CONVERTERS = {
 
 
 def convert_slow_tokenizer(transformer_tokenizer) -> Tokenizer:
-    """Utilities to convert a slow tokenizer instance in a fast tokenizer instance.
+    """
+    Utilities to convert a slow tokenizer instance in a fast tokenizer instance.
 
     Args:
         transformer_tokenizer (:class:`~transformers.tokenization_utils_base.PreTrainedTokenizer`):