[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/tokenization_mbart.py

@@ -108,7 +108,7 @@ class MBartTokenizer(XLMRobertaTokenizer):
         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
@@ -145,7 +145,7 @@ class MBartTokenizer(XLMRobertaTokenizer):
         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:

src/transformers/tokenization_pegasus.py

@@ -93,7 +93,7 @@ class PegasusTokenizer(ReformerTokenizer):
         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:

src/transformers/tokenization_reformer.py

@@ -74,7 +74,7 @@ class ReformerTokenizer(PreTrainedTokenizer):
             token instead.
         pad_token (:obj:`string`, `optional`, defaults to "<pad>"):
             The token used for padding, for example when batching sequences of different lengths.
-        additional_special_tokens (:obj:`List[str]`, `optional`, defaults to :obj:`None`):
+        additional_special_tokens (:obj:`List[str]`, `optional`):
             Additional special tokens used by the tokenizer.
     """
 

src/transformers/tokenization_roberta.py

@@ -185,7 +185,7 @@ class RobertaTokenizer(GPT2Tokenizer):
         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:
@@ -207,7 +207,7 @@ class RobertaTokenizer(GPT2Tokenizer):
         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
@@ -237,7 +237,7 @@ class RobertaTokenizer(GPT2Tokenizer):
         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:
@@ -376,7 +376,7 @@ class RobertaTokenizerFast(GPT2TokenizerFast):
         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_t5.py

@@ -89,7 +89,7 @@ class T5Tokenizer(PreTrainedTokenizer):
             These tokens are accessible as "<extra_id_{%d}>" where "{%d}" is a number between 0 and extra_ids-1.
             Extra tokens are indexed from the end of the vocabulary up to beginnning ("<extra_id_0>" is the last token in the vocabulary like in T5 preprocessing
             see: https://github.com/google-research/text-to-text-transfer-transformer/blob/9fd7b14a769417be33bc6c850f9598764913c833/t5/data/preprocessors.py#L2117)
-        additional_special_tokens (:obj:`List[str]`, `optional`, defaults to :obj:`None`):
+        additional_special_tokens (:obj:`List[str]`, `optional`):
             Additional special tokens used by the tokenizer.
     """
 
@@ -204,7 +204,7 @@ class T5Tokenizer(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:

src/transformers/tokenization_xlm.py

@@ -578,9 +578,9 @@ class XLMTokenizer(PreTrainedTokenizer):
             modeling. This is the token which the model will try to predict.
         additional_special_tokens (:obj:`List[str]`, `optional`, defaults to :obj:`["<special0>","<special1>","<special2>","<special3>","<special4>","<special5>","<special6>","<special7>","<special8>","<special9>"]`):
             List of additional special tokens.
-        lang2id (:obj:`Dict[str, int]`, `optional`, defaults to :obj:`None`):
+        lang2id (:obj:`Dict[str, int]`, `optional`):
             Dictionary mapping languages string identifiers to their IDs.
-        id2lang (:obj:`Dict[int, str`, `optional`, defaults to :obj:`None`):
+        id2lang (:obj:`Dict[int, str`, `optional`):
             Dictionary mapping language IDs to their string identifiers.
         do_lowercase_and_remove_accent (:obj:`bool`, `optional`, defaults to :obj:`True`):
             Whether to lowercase and remove accents when tokenizing.
@@ -863,7 +863,7 @@ class XLMTokenizer(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:
@@ -887,7 +887,7 @@ class XLMTokenizer(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
@@ -930,7 +930,7 @@ class XLMTokenizer(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_xlm_roberta.py

@@ -188,7 +188,7 @@ class XLMRobertaTokenizer(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:
@@ -211,7 +211,7 @@ class XLMRobertaTokenizer(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
@@ -242,7 +242,7 @@ class XLMRobertaTokenizer(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_xlnet.py

@@ -250,7 +250,7 @@ class XLNetTokenizer(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:
@@ -272,7 +272,7 @@ class XLNetTokenizer(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
@@ -307,7 +307,7 @@ class XLNetTokenizer(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:

templates/adding_a_new_model/modeling_tf_xxx.py

@@ -296,39 +296,39 @@ XXX_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:`{0}`, `optional`, defaults to :obj:`None`):
+        attention_mask (:obj:`Numpy array` 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:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        token_type_ids (:obj:`Numpy array` 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:`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.
 """
@@ -388,7 +388,7 @@ class TFXxxForMaskedLM(TFXxxPreTrainedModel, TFMaskedLanguageModelingLoss):
         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
@@ -470,7 +470,7 @@ class TFXxxForSequenceClassification(TFXxxPreTrainedModel, 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 :obj:`[0, ..., config.num_labels - 1]`.
             If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
@@ -562,7 +562,7 @@ class TFXxxForMultipleChoice(TFXxxPreTrainedModel, 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)s after the attention softmax, used to compute the weighted average in the self-attention
@@ -685,7 +685,7 @@ class TFXxxForTokenClassification(TFXxxPreTrainedModel, 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]``.
         """
@@ -767,11 +767,11 @@ class TFXxxForQuestionAnswering(TFXxxPreTrainedModel, TFQuestionAnsweringLoss):
         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.

templates/adding_a_new_model/modeling_xxx.py

@@ -233,36 +233,36 @@ XXX_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.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
-        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
 
             `What are token type IDs? <../glossary.html#token-type-ids>`_
-        position_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+        position_ids (:obj:`torch.LongTensor` 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:`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.
 """
@@ -399,7 +399,7 @@ class XxxForMaskedLM(XxxPreTrainedModel):
         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 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
@@ -476,7 +476,7 @@ class XxxForSequenceClassification(XxxPreTrainedModel):
         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),
@@ -559,7 +559,7 @@ class XxxForMultipleChoice(XxxPreTrainedModel):
         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-1]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)
@@ -649,7 +649,7 @@ class XxxForTokenClassification(XxxPreTrainedModel):
         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]``.
         """
@@ -735,11 +735,11 @@ class XxxForQuestionAnswering(XxxPreTrainedModel):
         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.

templates/adding_a_new_model/tokenization_xxx.py

@@ -90,7 +90,7 @@ class XxxTokenizer(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:`str`, `optional`, defaults to :obj:`"[UNK]"`):
@@ -202,7 +202,7 @@ class XxxTokenizer(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:
@@ -224,7 +224,7 @@ class XxxTokenizer(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
@@ -262,7 +262,7 @@ class XxxTokenizer(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: