[doc] remove the implied defaults to :obj:`None`, s/True/ :obj:`True/, etc. (#6956)

* remove the implied defaults to :obj:`None`

* fix bug in the original

* replace to :obj:`True`, :obj:`False`

src/transformers/modeling_tf_electra.py

@@ -408,33 +408,33 @@ ELECTRA_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        position_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
 
             `What are position IDs? <../glossary.html#position-ids>`__
-        head_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, embedding_dim)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, embedding_dim)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
         training (:obj:`boolean`, `optional`, defaults to :obj:`False`):
             Whether to activate dropout modules (if set to :obj:`True`) during training or to de-activate them
             (if set to :obj:`False`) for evaluation.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -597,7 +597,7 @@ class TFElectraForMaskedLM(TFElectraPreTrainedModel, TFMaskedLanguageModelingLos
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the masked language modeling loss.
             Indices should be in ``[-100, 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
@@ -699,7 +699,7 @@ class TFElectraForSequenceClassification(TFElectraPreTrainedModel, TFSequenceCla
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the sequence classification/regression loss.
             Indices should be in :obj:`[0, ..., config.num_labels - 1]`.
             If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
@@ -789,7 +789,7 @@ class TFElectraForMultipleChoice(TFElectraPreTrainedModel, TFMultipleChoiceLoss)
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)
@@ -906,7 +906,7 @@ class TFElectraForTokenClassification(TFElectraPreTrainedModel, TFTokenClassific
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the token classification loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
         """
@@ -986,11 +986,11 @@ class TFElectraForQuestionAnswering(TFElectraPreTrainedModel, TFQuestionAnswerin
         training=False,
     ):
         r"""
-        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
-        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the end of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.

src/transformers/modeling_tf_flaubert.py

@@ -64,49 +64,49 @@ FLAUBERT_INPUTS_DOCSTRING = r"""
             See :func:`transformers.PreTrainedTokenizer.encode` and
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
             `What are attention masks? <../glossary.html#attention-mask>`__
-        langs (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        langs (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             A parallel sequence of tokens to be used to indicate the language of each token in the input.
             Indices are languages ids which can be obtained from the language names by using two conversion mappings
             provided in the configuration of the model (only provided for multilingual models).
             More precisely, the `language name -> language id` mapping is in `model.config.lang2id` (dict str -> int) and
             the `language id -> language name` mapping is `model.config.id2lang` (dict int -> str).
             See usage examples detailed in the `multilingual documentation <https://huggingface.co/transformers/multilingual.html>`__.
-        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        position_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
             `What are position IDs? <../glossary.html#position-ids>`_
-        lengths (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        lengths (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size,)`, `optional`):
             Length of each sentence that can be used to avoid performing attention on padding token indices.
             You can also use `attention_mask` for the same result (see above), kept here for compatbility.
             Indices selected in ``[0, ..., input_ids.size(-1)]``:
-        cache (:obj:`Dict[str, tf.Tensor]`, `optional`, defaults to :obj:`None`):
+        cache (:obj:`Dict[str, tf.Tensor]`, `optional`):
             dictionary with ``tf.Tensor`` that contains pre-computed
             hidden-states (key and values in the attention blocks) as computed by the model
             (see `cache` output below). Can be used to speed up sequential decoding.
             The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
-        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """

src/transformers/modeling_tf_gpt2.py

@@ -505,39 +505,39 @@ GPT2_INPUTS_DOCSTRING = r"""
             (see `past` output below). Can be used to speed up sequential decoding.
             The token ids which have their past given to this model
             should not be passed as `input_ids` as they have already been computed.
-        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
 
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        position_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
 
             `What are position IDs? <../glossary.html#position-ids>`_
-        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
         training (:obj:`boolean`, `optional`, defaults to :obj:`False`):
             Whether to activate dropout modules (if set to :obj:`True`) during training or to de-activate them
             (if set to :obj:`False`) for evaluation.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -608,7 +608,7 @@ class TFGPT2LMHeadModel(TFGPT2PreTrainedModel, TFCausalLanguageModelingLoss):
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the cross entropy classification loss.
             Indices should be in ``[0, ..., config.vocab_size - 1]``.
         """

src/transformers/modeling_tf_longformer.py

@@ -1260,14 +1260,14 @@ LONGFORMER_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
 
-        global_attention_mask (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        global_attention_mask (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Mask to decide the attention given on each token, local attention or global attenion.
             Tokens with global attention attends to all other tokens, and all other tokens attend to them. This is important for
             task-specific finetuning because it makes the model more flexible at representing the task. For example,
@@ -1277,26 +1277,26 @@ LONGFORMER_INPUTS_DOCSTRING = r"""
             ``0`` for local attention (a sliding window attention),
             ``1`` for global attention (tokens that attend to all other tokens, and all other tokens attend to them).
 
-        token_type_ids (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
 
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        position_ids (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
 
             `What are position IDs? <../glossary.html#position-ids>`_
-        inputs_embeds (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -1368,7 +1368,7 @@ class TFLongformerForMaskedLM(TFLongformerPreTrainedModel, TFMaskedLanguageModel
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the masked language modeling loss.
             Indices should be in ``[-100, 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
@@ -1452,11 +1452,11 @@ class TFLongformerForQuestionAnswering(TFLongformerPreTrainedModel, TFQuestionAn
         training=False,
     ):
         r"""
-        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
-        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the end of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.

src/transformers/modeling_tf_lxmert.py

@@ -940,13 +940,13 @@ LXMERT_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        token_type_ids (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
@@ -955,7 +955,7 @@ LXMERT_INPUTS_DOCSTRING = r"""
         visual_feats: (:obj:`tf.Tensor` of shape :obj:՝(batch_size, num_visual_features, visual_feat_dim)՝):
             This input represents visual features. They ROI pooled object features from bounding boxes using a faster-RCNN model)
             These are currently not provided by the transformers library
-        visual_attention_mask (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        visual_attention_mask (:obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
@@ -1246,7 +1246,7 @@ class TFLxmertForPreTraining(TFLxmertPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        masked_lm_labels (``tf.Tensor`` of shape ``(batch_size, sequence_length)``, `optional`, defaults to :obj:`None`):
+        masked_lm_labels (``tf.Tensor`` of shape ``(batch_size, sequence_length)``, `optional`):
             Labels for computing the masked language modeling loss.
             Indices should be in ``[-100, 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
@@ -1255,7 +1255,7 @@ class TFLxmertForPreTraining(TFLxmertPreTrainedModel):
             each key is named after each one of the visual losses and each element of the tuple is of the shape
             ``(batch_size, num_features)`` and ``(batch_size, num_features, visual_feature_dim)``
             for each the label id and the label score respectively
-        matched_label (``tf.Tensor`` of shape ``(batch_size,)``, `optional`, defaults to :obj:`None`):
+        matched_label (``tf.Tensor`` of shape ``(batch_size,)``, `optional`):
             Labels for computing the whether or not the text input matches the image (classification) loss. Input should be a sequence pair (see :obj:`input_ids` docstring)
             Indices should be in ``[0, 1]``.
             ``0`` indicates that the sentence does not match the image

src/transformers/modeling_tf_mobilebert.py

@@ -891,39 +891,39 @@ MOBILEBERT_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        token_type_ids (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
 
             `What are token type IDs? <../glossary.html#token-type-ids>`__
-        position_ids (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
 
             `What are position IDs? <../glossary.html#position-ids>`__
-        head_mask (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, embedding_dim)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`np.ndarray` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, embedding_dim)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can  to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
         training (:obj:`boolean`, `optional`, defaults to :obj:`False`):
             Whether to activate dropout modules (if set to :obj:`True`) during training or to de-activate them
             (if set to :obj:`False`) for evaluation.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -1035,7 +1035,7 @@ class TFMobileBertForMaskedLM(TFMobileBertPreTrainedModel, TFMaskedLanguageModel
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the masked language modeling loss.
             Indices should be in ``[-100, 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
@@ -1174,7 +1174,7 @@ class TFMobileBertForSequenceClassification(TFMobileBertPreTrainedModel, TFSeque
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the sequence classification/regression loss.
             Indices should be in :obj:`[0, ..., config.num_labels - 1]`.
             If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
@@ -1258,11 +1258,11 @@ class TFMobileBertForQuestionAnswering(TFMobileBertPreTrainedModel, TFQuestionAn
         training=False,
     ):
         r"""
-        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
-        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the end of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
@@ -1362,7 +1362,7 @@ class TFMobileBertForMultipleChoice(TFMobileBertPreTrainedModel, TFMultipleChoic
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)
@@ -1480,7 +1480,7 @@ class TFMobileBertForTokenClassification(TFMobileBertPreTrainedModel, TFTokenCla
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the token classification loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
         """

src/transformers/modeling_tf_openai.py

@@ -454,39 +454,39 @@ OPENAI_GPT_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
 
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        position_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
 
             `What are position IDs? <../glossary.html#position-ids>`_
-        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
         training (:obj:`boolean`, `optional`, defaults to :obj:`False`):
             Whether to activate dropout modules (if set to :obj:`True`) during training or to de-activate them
             (if set to :obj:`False`) for evaluation.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -548,7 +548,7 @@ class TFOpenAIGPTLMHeadModel(TFOpenAIGPTPreTrainedModel, TFCausalLanguageModelin
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the cross entropy classification loss.
             Indices should be in ``[0, ..., config.vocab_size - 1]``.
         """

src/transformers/modeling_tf_roberta.py

@@ -168,39 +168,39 @@ ROBERTA_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        token_type_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
 
             `What are token type IDs? <../glossary.html#token-type-ids>`__
-        position_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
 
             `What are position IDs? <../glossary.html#position-ids>`__
-        head_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, embedding_dim)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, embedding_dim)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
         training (:obj:`boolean`, `optional`, defaults to :obj:`False`):
             Whether to activate dropout modules (if set to :obj:`True`) during training or to de-activate them
             (if set to :obj:`False`) for evaluation.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -291,7 +291,7 @@ class TFRobertaForMaskedLM(TFRobertaPreTrainedModel, TFMaskedLanguageModelingLos
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the masked language modeling loss.
             Indices should be in ``[-100, 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
@@ -397,7 +397,7 @@ class TFRobertaForSequenceClassification(TFRobertaPreTrainedModel, TFSequenceCla
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the sequence classification/regression loss.
             Indices should be in :obj:`[0, ..., config.num_labels - 1]`.
             If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
@@ -487,7 +487,7 @@ class TFRobertaForMultipleChoice(TFRobertaPreTrainedModel, TFMultipleChoiceLoss)
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)
@@ -600,7 +600,7 @@ class TFRobertaForTokenClassification(TFRobertaPreTrainedModel, TFTokenClassific
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the token classification loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
         """
@@ -681,11 +681,11 @@ class TFRobertaForQuestionAnswering(TFRobertaPreTrainedModel, TFQuestionAnswerin
         training=False,
     ):
         r"""
-        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
-        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the end of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.

src/transformers/modeling_tf_t5.py

@@ -890,18 +890,18 @@ T5_INPUTS_DOCSTRING = r"""
             `T5 Training <./t5.html#training>`__.
             See :func:`transformers.PreTrainedTokenizer.encode` and
             :func:`transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
-        decoder_input_ids (:obj:`tf.Tensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`, defaults to :obj:`None`):
+        decoder_input_ids (:obj:`tf.Tensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`):
             Provide for sequence to sequence training. T5 uses the pad_token_id as the starting token for decoder_input_ids generation.
             If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`).
-        attention_mask (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
-        encoder_outputs (:obj:`tuple(tuple(tf.FloatTensor)`, `optional`, defaults to :obj:`None`):
+        encoder_outputs (:obj:`tuple(tuple(tf.FloatTensor)`, `optional`):
             Tuple consists of (`last_hidden_state`, `optional`: `hidden_states`, `optional`: `attentions`)
-            `last_hidden_state` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`) is a sequence of hidden-states at the output of the last layer of the encoder.
+            `last_hidden_state` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`) is a sequence of hidden-states at the output of the last layer of the encoder.
             Used in the cross-attention of the decoder.
-        decoder_attention_mask (:obj:`tf.Tensor` of shape :obj:`(batch_size, tgt_seq_len)`, `optional`, defaults to :obj:`None`):
+        decoder_attention_mask (:obj:`tf.Tensor` of shape :obj:`(batch_size, tgt_seq_len)`, `optional`):
             Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.
         past_key_values (:obj:`tuple(tuple(tf.Tensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
             Contains pre-computed key and value hidden-states of the attention blocks.
@@ -910,21 +910,21 @@ T5_INPUTS_DOCSTRING = r"""
             (those that don't have their past key value states given to this model) of shape :obj:`(batch_size, 1)`
         use_cache (:obj:`bool`, `optional`, defaults to :obj:`True`):
             If `use_cache` is True, `past_key_values` are returned and can be used to speed up decoding (see `past_key_values`).
-        inputs_embeds (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`inputs` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `inputs` indices into associated vectors
             than the model's internal embedding lookup matrix.
-        decoder_inputs_embeds (:obj:`tf.Tensor` of shape :obj:`(batch_size, target_sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        decoder_inputs_embeds (:obj:`tf.Tensor` of shape :obj:`(batch_size, target_sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`decoder_input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `decoder_input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
             To know more on how to prepare :obj:`decoder_input_ids` for pre-training take a look at
             `T5 Training <./t5.html#training>`__.
-        head_mask: (:obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask: (:obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 
@@ -1206,7 +1206,7 @@ class TFT5ForConditionalGeneration(TFT5PreTrainedModel, TFCausalLanguageModeling
         **kwargs,
     ):
         r"""
-            labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+            labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
                 Labels for computing the cross entropy classification loss.
                 Indices should be in ``[0, ..., config.vocab_size - 1]``.
 

src/transformers/modeling_tf_transfo_xl.py

@@ -784,19 +784,19 @@ TRANSFO_XL_INPUTS_DOCSTRING = r"""
             Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model
             (see `mems` output below). Can be used to speed up sequential decoding. The token ids which have their mems
             given to this model should not be passed as input ids as they have already been computed.
-        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """

src/transformers/modeling_tf_xlm.py

@@ -599,13 +599,13 @@ XLM_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        langs (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        langs (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             A parallel sequence of tokens to be used to indicate the language of each token in the input.
             Indices are languages ids which can be obtained from the language names by using two conversion mappings
             provided in the configuration of the model (only provided for multilingual models).
@@ -613,39 +613,39 @@ XLM_INPUTS_DOCSTRING = r"""
             the `language id -> language name` mapping is `model.config.id2lang` (dict int -> str).
 
             See usage examples detailed in the `multilingual documentation <https://huggingface.co/transformers/multilingual.html>`__.
-        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
 
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        position_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
 
             `What are position IDs? <../glossary.html#position-ids>`_
-        lengths (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        lengths (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size,)`, `optional`):
             Length of each sentence that can be used to avoid performing attention on padding token indices.
             You can also use `attention_mask` for the same result (see above), kept here for compatbility.
             Indices selected in ``[0, ..., input_ids.size(-1)]``:
-        cache (:obj:`Dict[str, tf.Tensor]`, `optional`, defaults to :obj:`None`):
+        cache (:obj:`Dict[str, tf.Tensor]`, `optional`):
             dictionary with ``tf.Tensor`` that contains pre-computed
             hidden-states (key and values in the attention blocks) as computed by the model
             (see `cache` output below). Can be used to speed up sequential decoding.
             The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
-        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -794,7 +794,7 @@ class TFXLMForSequenceClassification(TFXLMPreTrainedModel, TFSequenceClassificat
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the sequence classification/regression loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
             If ``config.num_labels == 1`` a regression loss is computed (Mean-Square loss),
@@ -893,7 +893,7 @@ class TFXLMForMultipleChoice(TFXLMPreTrainedModel, TFMultipleChoiceLoss):
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)
@@ -1033,7 +1033,7 @@ class TFXLMForTokenClassification(TFXLMPreTrainedModel, TFTokenClassificationLos
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the token classification loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
         """
@@ -1119,11 +1119,11 @@ class TFXLMForQuestionAnsweringSimple(TFXLMPreTrainedModel, TFQuestionAnsweringL
         training=False,
     ):
         r"""
-        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
-        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the end of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.

src/transformers/modeling_tf_xlnet.py

@@ -1064,7 +1064,7 @@ XLNET_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
@@ -1074,44 +1074,44 @@ XLNET_INPUTS_DOCSTRING = r"""
             Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model
             (see `mems` output below). Can be used to speed up sequential decoding. The token ids which have their mems
             given to this model should not be passed as input ids as they have already been computed.
-        perm_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, sequence_length)`, `optional`, defaults to :obj:`None`):
+        perm_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, sequence_length)`, `optional`):
             Mask to indicate the attention pattern for each input token with values selected in ``[0, 1]``:
             If ``perm_mask[k, i, j] = 0``, i attend to j in batch k;
             if ``perm_mask[k, i, j] = 1``, i does not attend to j in batch k.
             If None, each token attends to all the others (full bidirectional attention).
             Only used during pretraining (to define factorization order) or for sequential decoding (generation).
-        target_mapping (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, num_predict, sequence_length)`, `optional`, defaults to :obj:`None`):
+        target_mapping (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, num_predict, sequence_length)`, `optional`):
             Mask to indicate the output tokens to use.
             If ``target_mapping[k, i, j] = 1``, the i-th predict in batch k is on the j-th token.
             Only used during pretraining for partial prediction or for sequential decoding (generation).
-        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
 
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        input_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        input_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Negative of `attention_mask`, i.e. with 0 for real tokens and 1 for padding.
             Kept for compatibility with the original code base.
             You can only uses one of `input_mask` and `attention_mask`
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are MASKED, ``0`` for tokens that are NOT MASKED.
-        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
         use_cache (:obj:`bool`):
             If `use_cache` is True, `mems` are returned and can be used to speed up decoding (see `mems`). Defaults to `True`.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -1213,7 +1213,7 @@ class TFXLNetLMHeadModel(TFXLNetPreTrainedModel, TFCausalLanguageModelingLoss):
         training=False,
     ):
         r"""
-            labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+            labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
                 Labels for computing the cross entropy classification loss.
                 Indices should be in ``[0, ..., config.vocab_size - 1]``.
 
@@ -1333,7 +1333,7 @@ class TFXLNetForSequenceClassification(TFXLNetPreTrainedModel, TFSequenceClassif
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the sequence classification/regression loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
             If ``config.num_labels == 1`` a regression loss is computed (Mean-Square loss),
@@ -1434,7 +1434,7 @@ class TFXLNetForMultipleChoice(TFXLNetPreTrainedModel, TFMultipleChoiceLoss):
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)
@@ -1567,7 +1567,7 @@ class TFXLNetForTokenClassification(TFXLNetPreTrainedModel, TFTokenClassificatio
         training=False,
     ):
         r"""
-        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the token classification loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
         """
@@ -1653,11 +1653,11 @@ class TFXLNetForQuestionAnsweringSimple(TFXLNetPreTrainedModel, TFQuestionAnswer
         training=False,
     ):
         r"""
-        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        start_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
-        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        end_positions (:obj:`tf.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the end of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.

src/transformers/modeling_transfo_xl.py

@@ -697,19 +697,19 @@ TRANSFO_XL_INPUTS_DOCSTRING = r"""
             Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model
             (see `mems` output below). Can be used to speed up sequential decoding. The token ids which have their mems
             given to this model should not be passed as input ids as they have already been computed.
-        head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -1034,7 +1034,7 @@ class TransfoXLLMHeadModel(TransfoXLPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for language modeling.
             Note that the labels **are shifted** inside the model, i.e. you can set ``labels = input_ids``
             Indices are selected in ``[-100, 0, ..., config.vocab_size]``

src/transformers/modeling_xlm.py

@@ -327,13 +327,13 @@ XLM_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        langs (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        langs (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             A parallel sequence of tokens to be used to indicate the language of each token in the input.
             Indices are languages ids which can be obtained from the language names by using two conversion mappings
             provided in the configuration of the model (only provided for multilingual models).
@@ -341,39 +341,39 @@ XLM_INPUTS_DOCSTRING = r"""
             the `language id -> language name` mapping is `model.config.id2lang` (dict int -> str).
 
             See usage examples detailed in the `multilingual documentation <https://huggingface.co/transformers/multilingual.html>`__.
-        token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token
 
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        position_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Indices of positions of each input sequence tokens in the position embeddings.
             Selected in the range ``[0, config.max_position_embeddings - 1]``.
 
             `What are position IDs? <../glossary.html#position-ids>`_
-        lengths (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        lengths (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
             Length of each sentence that can be used to avoid performing attention on padding token indices.
             You can also use `attention_mask` for the same result (see above), kept here for compatbility.
             Indices selected in ``[0, ..., input_ids.size(-1)]``:
-        cache (:obj:`Dict[str, torch.FloatTensor]`, `optional`, defaults to :obj:`None`):
+        cache (:obj:`Dict[str, torch.FloatTensor]`, `optional`):
             dictionary with ``torch.FloatTensor`` that contains pre-computed
             hidden-states (key and values in the attention blocks) as computed by the model
             (see `cache` output below). Can be used to speed up sequential decoding.
             The dictionary object will be modified in-place during the forward pass to add newly computed hidden-states.
-        head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -708,7 +708,7 @@ class XLMWithLMHeadModel(XLMPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for language modeling.
             Note that the labels **are shifted** inside the model, i.e. you can set ``labels = input_ids``
             Indices are selected in ``[-100, 0, ..., config.vocab_size]``
@@ -785,7 +785,7 @@ class XLMForSequenceClassification(XLMPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the sequence classification/regression loss.
             Indices should be in :obj:`[0, ..., config.num_labels - 1]`.
             If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
@@ -872,11 +872,11 @@ class XLMForQuestionAnsweringSimple(XLMPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
-        end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the end of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
@@ -972,19 +972,19 @@ class XLMForQuestionAnswering(XLMPreTrainedModel):
         return_dict=None,
     ):
         r"""
-            start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+            start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
                 Labels for position (index) of the start of the labelled span for computing the token classification loss.
                 Positions are clamped to the length of the sequence (`sequence_length`).
                 Position outside of the sequence are not taken into account for computing the loss.
-            end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+            end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
                 Labels for position (index) of the end of the labelled span for computing the token classification loss.
                 Positions are clamped to the length of the sequence (`sequence_length`).
                 Position outside of the sequence are not taken into account for computing the loss.
-            is_impossible (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`, defaults to :obj:`None`):
+            is_impossible (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`):
                 Labels whether a question has an answer or no answer (SQuAD 2.0)
-            cls_index (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`, defaults to :obj:`None`):
+            cls_index (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`):
                 Labels for position (index) of the classification token to use as input for computing plausibility of the answer.
-            p_mask (``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``, `optional`, defaults to :obj:`None`):
+            p_mask (``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``, `optional`):
                 Optional mask of tokens which can't be in answers (e.g. [CLS], [PAD], ...).
                 1.0 means token should be masked. 0.0 mean token is not masked.
 
@@ -1089,7 +1089,7 @@ class XLMForTokenClassification(XLMPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the token classification loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
         """
@@ -1180,7 +1180,7 @@ class XLMForMultipleChoice(XLMPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        labels (:obj:`torch.Tensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`torch.Tensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)

src/transformers/modeling_xlnet.py

@@ -863,7 +863,7 @@ XLNET_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.__call__` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        attention_mask (:obj:`torch.FloatTensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`torch.FloatTensor` of shape :obj:`{0}`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
@@ -874,44 +874,44 @@ XLNET_INPUTS_DOCSTRING = r"""
             (see `mems` output below). Can be used to speed up sequential decoding. The token ids which have their mems
             given to this model should not be passed as input ids as they have already been computed.
             `use_cache` has to be set to `True` to make use of `mems`.
-        perm_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, sequence_length)`, `optional`, defaults to :obj:`None`):
+        perm_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, sequence_length)`, `optional`):
             Mask to indicate the attention pattern for each input token with values selected in ``[0, 1]``:
             If ``perm_mask[k, i, j] = 0``, i attend to j in batch k;
             if ``perm_mask[k, i, j] = 1``, i does not attend to j in batch k.
             If None, each token attends to all the others (full bidirectional attention).
             Only used during pretraining (to define factorization order) or for sequential decoding (generation).
-        target_mapping (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, num_predict, sequence_length)`, `optional`, defaults to :obj:`None`):
+        target_mapping (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, num_predict, sequence_length)`, `optional`):
             Mask to indicate the output tokens to use.
             If ``target_mapping[k, i, j] = 1``, the i-th predict in batch k is on the j-th token.
             Only used during pretraining for partial prediction or for sequential decoding (generation).
-        token_type_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`, `optional`):
             Segment token indices to indicate first and second portions of the inputs.
             Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
             corresponds to a `sentence B` token. The classifier token should be represented by a ``2``.
 
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        input_mask (:obj:`torch.FloatTensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        input_mask (:obj:`torch.FloatTensor` of shape :obj:`{0}`, `optional`):
             Mask to avoid performing attention on padding token indices.
             Negative of `attention_mask`, i.e. with 0 for real tokens and 1 for padding.
             Kept for compatibility with the original code base.
             You can only uses one of `input_mask` and `attention_mask`
             Mask values selected in ``[0, 1]``:
             ``1`` for tokens that are MASKED, ``0`` for tokens that are NOT MASKED.
-        head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
+        head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
-        inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+        inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
         use_cache (:obj:`bool`):
             If `use_cache` is True, `mems` are returned and can be used to speed up decoding (see `mems`). Defaults to `True`.
-        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_attentions (:obj:`bool`, `optional`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
-        output_hidden_states (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        output_hidden_states (:obj:`bool`, `optional`):
             If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned tensors for more detail.
-        return_dict (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        return_dict (:obj:`bool`, `optional`):
             If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
             plain tuple.
 """
@@ -1348,7 +1348,7 @@ class XLNetLMHeadModel(XLNetPreTrainedModel):
         return_dict=None,
     ):
         r"""
-            labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, num_predict)`, `optional`, defaults to :obj:`None`):
+            labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, num_predict)`, `optional`):
                 Labels for masked language modeling.
                 `num_predict` corresponds to `target_mapping.shape[1]`. If `target_mapping` is `None`, then `num_predict` corresponds to `sequence_length`.
                 The labels should correspond to the masked input words that should be predicted and depends on `target_mapping`. Note in order to perform standard auto-regressive language modeling a `<mask>` token has to be added to the `input_ids` (see `prepare_inputs_for_generation` fn and examples below)
@@ -1470,7 +1470,7 @@ class XLNetForSequenceClassification(XLNetPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`)
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`)
             Labels for computing the sequence classification/regression loss.
             Indices should be in ``[0, ..., config.num_labels - 1]``.
             If ``config.num_labels == 1`` a regression loss is computed (Mean-Square loss),
@@ -1562,7 +1562,7 @@ class XLNetForTokenClassification(XLNetPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)
@@ -1657,7 +1657,7 @@ class XLNetForMultipleChoice(XLNetPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)
@@ -1757,11 +1757,11 @@ class XLNetForQuestionAnsweringSimple(XLNetPreTrainedModel):
         return_dict=None,
     ):
         r"""
-        start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the start of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
-        end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+        end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
             Labels for position (index) of the end of the labelled span for computing the token classification loss.
             Positions are clamped to the length of the sequence (`sequence_length`).
             Position outside of the sequence are not taken into account for computing the loss.
@@ -1865,19 +1865,19 @@ class XLNetForQuestionAnswering(XLNetPreTrainedModel):
         return_dict=None,
     ):
         r"""
-            start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+            start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
                 Labels for position (index) of the start of the labelled span for computing the token classification loss.
                 Positions are clamped to the length of the sequence (`sequence_length`).
                 Position outside of the sequence are not taken into account for computing the loss.
-            end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
+            end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
                 Labels for position (index) of the end of the labelled span for computing the token classification loss.
                 Positions are clamped to the length of the sequence (`sequence_length`).
                 Position outside of the sequence are not taken into account for computing the loss.
-            is_impossible (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`, defaults to :obj:`None`):
+            is_impossible (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`):
                 Labels whether a question has an answer or no answer (SQuAD 2.0)
-            cls_index (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`, defaults to :obj:`None`):
+            cls_index (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`):
                 Labels for position (index) of the classification token to use as input for computing plausibility of the answer.
-            p_mask (``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``, `optional`, defaults to :obj:`None`):
+            p_mask (``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``, `optional`):
                 Optional mask of tokens which can't be in answers (e.g. [CLS], [PAD], ...).
                 1.0 means token should be masked. 0.0 mean token is not masked.
 

src/transformers/testing_utils.py

@@ -315,7 +315,7 @@ class TestCasePlus(unittest.TestCase):
     def get_auto_remove_tmp_dir(self, tmp_dir=None, after=True, before=False):
         """
         Args:
-            tmp_dir (:obj:`string`, `optional`, defaults to :obj:`None`):
+            tmp_dir (:obj:`string`, `optional`):
                 use this path, if None a unique path will be assigned
             before (:obj:`bool`, `optional`, defaults to :obj:`False`):
                 if `True` and tmp dir already exists make sure to empty it right away

src/transformers/tokenization_albert.py

@@ -246,7 +246,7 @@ class AlbertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of IDs to which the special tokens will be added
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
 
         Returns:
@@ -268,7 +268,7 @@ class AlbertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of ids.
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
             already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
                 Set to True if the token list is already formatted with special tokens for the model
@@ -306,7 +306,7 @@ class AlbertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of ids.
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
 
         Returns:

src/transformers/tokenization_bert.py

@@ -131,7 +131,7 @@ class BertTokenizer(PreTrainedTokenizer):
             Whether to lowercase the input when tokenizing.
         do_basic_tokenize (:obj:`bool`, `optional`, defaults to :obj:`True`):
             Whether to do basic tokenization before WordPiece.
-        never_split (:obj:`Iterable`, `optional`, defaults to :obj:`None`):
+        never_split (:obj:`Iterable`, `optional`):
             Collection of tokens which will never be split during tokenization. Only has an effect when
             :obj:`do_basic_tokenize=True`
         unk_token (:obj:`string`, `optional`, defaults to "[UNK]"):
@@ -154,7 +154,7 @@ class BertTokenizer(PreTrainedTokenizer):
             Whether to tokenize Chinese characters.
             This should likely be deactivated for Japanese:
             see: https://github.com/huggingface/transformers/issues/328
-        strip_accents: (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        strip_accents: (:obj:`bool`, `optional`):
             Whether to strip all accents. If this option is not specified (ie == None),
             then it will be determined by the value for `lowercase` (as in the original Bert).
     """
@@ -253,7 +253,7 @@ class BertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of IDs to which the special tokens will be added
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
 
         Returns:
@@ -275,7 +275,7 @@ class BertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of ids.
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
             already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
                 Set to True if the token list is already formatted with special tokens for the model
@@ -313,7 +313,7 @@ class BertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of ids.
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
 
         Returns:
@@ -599,7 +599,7 @@ class BertTokenizerFast(PreTrainedTokenizerFast):
             Whether to tokenize Chinese characters.
             This should likely be deactivated for Japanese:
             see: https://github.com/huggingface/transformers/issues/328
-        strip_accents: (:obj:`bool`, `optional`, defaults to :obj:`None`):
+        strip_accents: (:obj:`bool`, `optional`):
             Whether to strip all accents. If this option is not specified (ie == None),
             then it will be determined by the value for `lowercase` (as in the original Bert).
         wordpieces_prefix: (:obj:`string`, `optional`, defaults to "##"):
@@ -673,7 +673,7 @@ class BertTokenizerFast(PreTrainedTokenizerFast):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of ids.
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
 
         Returns:

src/transformers/tokenization_camembert.py

@@ -153,7 +153,7 @@ class CamembertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of IDs to which the special tokens will be added
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
 
         Returns:
@@ -176,7 +176,7 @@ class CamembertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of ids.
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
             already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
                 Set to True if the token list is already formatted with special tokens for the model
@@ -206,7 +206,7 @@ class CamembertTokenizer(PreTrainedTokenizer):
         Args:
             token_ids_0 (:obj:`List[int]`):
                 List of ids.
-            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+            token_ids_1 (:obj:`List[int]`, `optional`):
                 Optional second list of IDs for sequence pairs.
 
         Returns:

src/transformers/tokenization_dpr.py

@@ -168,12 +168,12 @@ CUSTOM_DPR_READER_DOCSTRING = r"""
 
             * `True` or `'only_first'`: truncate to a max length specified in `max_length` or to the max acceptable input length for the model if no length is provided (`max_length=None`).
             * `False` or `'do_not_truncate'` (default): No truncation (i.e. can output batch with sequences length greater than the model max admissible input size)
-        max_length (:obj:`Union[int, None]`, `optional`, defaults to :obj:`None`):
+        max_length (:obj:`Union[int, None]`, `optional`):
             Control the length for padding/truncation. Accepts the following values
 
             * `None` (default): This will use the predefined model max length if required by one of the truncation/padding parameters. If the model has no specific max input length (e.g. XLNet) truncation/padding to max length is deactivated.
             * `any integer value` (e.g. `42`): Use this specific maximum length value if required by one of the truncation/padding parameters.
-        return_tensors (:obj:`str`, `optional`, defaults to :obj:`None`):
+        return_tensors (:obj:`str`, `optional`):
             Can be set to 'tf', 'pt' or 'np' to return respectively TensorFlow :obj:`tf.constant`,
             PyTorch :obj:`torch.Tensor` or Numpy :obj: `np.ndarray` instead of a list of python integers.
         return_attention_mask (:obj:`bool`, `optional`, defaults to :obj:`none`):