fix (#4976)

src/transformers/modeling_tf_electra.py

@@ -348,7 +348,7 @@ ELECTRA_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_tf_flaubert.py

@@ -100,7 +100,7 @@ FLAUBERT_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_tf_gpt2.py

@@ -467,7 +467,7 @@ GPT2_INPUTS_DOCSTRING = r"""
         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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_tf_openai.py

@@ -429,7 +429,7 @@ OPENAI_GPT_INPUTS_DOCSTRING = r"""
         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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 
@@ -568,7 +568,7 @@ class TFOpenAIGPTDoubleHeadsModel(TFOpenAIGPTPreTrainedModel):
         r"""
         mc_token_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, num_choices)`, `optional`, default to index of the last token of the input)
             Index of the classification token in each input sequence.
-            Selected in the range ``[0, input_ids.size(-1) - 1[``.
+            Selected in the range ``[0, input_ids.size(-1) - 1]``.
 
     Return:
         :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.OpenAIGPTConfig`) and inputs:

src/transformers/modeling_tf_roberta.py

@@ -182,7 +182,7 @@ ROBERTA_INPUTS_DOCSTRING = r"""
         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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_tf_t5.py

@@ -855,7 +855,7 @@ T5_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_tf_transfo_xl.py

@@ -692,7 +692,7 @@ TRANSFO_XL_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_tf_xlm.py

@@ -585,7 +585,7 @@ XLM_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_tf_xlm_roberta.py

@@ -62,7 +62,7 @@ XLM_ROBERTA_START_DOCSTRING = r"""
         config (:class:`~transformers.XLMRobertaConfig`): Model configuration class with all the parameters of the
             model. Initializing with a config file does not load the weights associated with the model, only the configuration.
             Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights.
-        output_attentions (:obj:`bool`, `optional`, defaults to `:obj:`None`):
+        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_tf_xlnet.py

@@ -809,7 +809,7 @@ XLNET_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_transfo_xl.py

@@ -622,7 +622,7 @@ TRANSFO_XL_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_xlm.py

@@ -302,7 +302,7 @@ XLM_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_xlm_roberta.py

@@ -53,7 +53,7 @@ XLM_ROBERTA_START_DOCSTRING = r"""
         config (:class:`~transformers.XLMRobertaConfig`): Model configuration class with all the parameters of the
             model. Initializing with a config file does not load the weights associated with the model, only the configuration.
             Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights.
-        output_attentions (:obj:`bool`, `optional`, defaults to `:obj:`None`):
+        output_attentions (:obj:`bool`, `optional`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """
 

src/transformers/modeling_xlnet.py

@@ -618,7 +618,7 @@ XLNET_INPUTS_DOCSTRING = r"""
             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`, defaults to :obj:`None`):
             If set to ``True``, the attentions tensors of all attention layers are returned. See ``attentions`` under returned tensors for more detail.
 """