Fix DeBERTa docs (#8092)

* Fix DeBERTa docs

* Tokenizer and config

src/transformers/configuration_deberta.py

@@ -28,8 +28,14 @@ DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 
 class DebertaConfig(PretrainedConfig):
     r"""
-    :class:`~transformers.DebertaConfig` is the configuration class to store the configuration of a
-    :class:`~transformers.DebertaModel`.
+    This is the configuration class to store the configuration of a :class:`~transformers.DebertaModel` or a
+    :class:`~transformers.TFDebertaModel`. It is used to instantiate a DeBERTa model according to the specified
+    arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar
+    configuration to that of the DeBERTa `microsoft/deberta-base <https://huggingface.co/microsoft/deberta-base>`__
+    architecture.
+
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
 
     Arguments:
         vocab_size (:obj:`int`, `optional`, defaults to 30522):

src/transformers/modeling_deberta.py

@@ -797,13 +797,18 @@ DEBERTA_INPUTS_DOCSTRING = r"""
 
             `What are input IDs? <../glossary.html#input-ids>`__
         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.
+            Mask to avoid performing attention on padding token indices. Mask values selected in ``[0, 1]``:
+
+            - 1 for tokens that are **not masked**,
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         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
+            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`):
@@ -816,14 +821,13 @@ DEBERTA_INPUTS_DOCSTRING = r"""
             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`):
-            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`):
-            If set to ``True``, the hidden states of all layers are returned. See ``hidden_states`` under returned
+            Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned
             tensors for more detail.
+        output_hidden_states (:obj:`bool`, `optional`):
+            Whether or not to return the hidden states of all layers. See ``hidden_states`` under returned tensors for
+            more detail.
         return_dict (:obj:`bool`, `optional`):
-            If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
-            plain tuple.
+            Whether or not to return a :class:`~transformers.file_utils.ModelOutput` instead of a plain tuple.
 """
 
 

src/transformers/tokenization_deberta.py

@@ -581,7 +581,7 @@ class DebertaTokenizer(PreTrainedTokenizer):
     def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
         """
         Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
-        adding special tokens. A BERT sequence has the following format:
+        adding special tokens. A DeBERTa sequence has the following format:
 
         - single sequence: [CLS] X [SEP]
         - pair of sequences: [CLS] A [SEP] B [SEP]
@@ -608,14 +608,15 @@ class DebertaTokenizer(PreTrainedTokenizer):
         special tokens using the tokenizer ``prepare_for_model`` or ``encode_plus`` methods.
 
         Args:
-            token_ids_0: list of ids (must not contain special tokens)
-            token_ids_1: Optional list of ids (must not contain special tokens), necessary when fetching sequence ids
-                for sequence pairs
-            already_has_special_tokens: (default False) Set to True if the token list is already formated with
-                special tokens for the model
+            token_ids_0 (:obj:`List[int]`):
+                List of IDs.
+            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`):
+                Whether or not the token list is already formatted with special tokens for the model.
 
         Returns:
-            A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+            :obj:`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
         """
 
         if already_has_special_tokens: