Fix squeezebert docs (#7587)

* Configuration

* Modeling

* Tokenization

* Obliterate the trailing spaces

* From underlines to long underlines

docs/source/model_doc/squeezebert.rst

 SqueezeBERT
-----------------------------------------------------
+-----------------------------------------------------------------------------------------------------------------------
 
 Overview
-~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 The SqueezeBERT model was proposed in
 `SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
@@ -40,14 +40,14 @@ Tips:
   `squeezebert/squeezebert-mnli-headless` checkpoint.
 
 SqueezeBertConfig
-~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertConfig
     :members:
 
 
 SqueezeBertTokenizer
-~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertTokenizer
     :members: build_inputs_with_special_tokens, get_special_tokens_mask,
@@ -55,49 +55,49 @@ SqueezeBertTokenizer
 
 
 SqueezeBertTokenizerFast
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertTokenizerFast
     :members:
 
 
 SqueezeBertModel
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertModel
     :members:
 
 
 SqueezeBertForMaskedLM
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertForMaskedLM
     :members:
 
 
 SqueezeBertForSequenceClassification
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertForSequenceClassification
     :members:
 
 
 SqueezeBertForMultipleChoice
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertForMultipleChoice
     :members:
 
 
 SqueezeBertForTokenClassification
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertForTokenClassification
     :members:
 
 
 SqueezeBertForQuestionAnswering
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.SqueezeBertForQuestionAnswering
     :members:

src/transformers/configuration_squeezebert.py

@@ -39,52 +39,51 @@ class SqueezeBertConfig(PretrainedConfig):
 
 
     Args:
-        vocab_size (:obj:`int`, optional, defaults to 30522):
-            Vocabulary size of the SqueezeBERT model. Defines the different tokens that
-            can be represented by the :obj:`inputs_ids` passed to the forward method of :class:`~transformers.SqueezeBertModel`.
-        hidden_size (:obj:`int`, optional, defaults to 512):
+        vocab_size (:obj:`int`, `optional`, defaults to 30522):
+            Vocabulary size of the SqueezeBERT model. Defines the number of different tokens that can be
+            represented by the :obj:`inputs_ids` passed when calling :class:`~transformers.SqueezeBertModel`.
+        hidden_size (:obj:`int`, `optional`, defaults to 768):
             Dimensionality of the encoder layers and the pooler layer.
-        num_hidden_layers (:obj:`int`, optional, defaults to 24):
+        num_hidden_layers (:obj:`int`, `optional`, defaults to 12):
             Number of hidden layers in the Transformer encoder.
-        num_attention_heads (:obj:`int`, optional, defaults to 4):
+        num_attention_heads (:obj:`int`, `optional`, defaults to 12):
             Number of attention heads for each attention layer in the Transformer encoder.
-        intermediate_size (:obj:`int`, optional, defaults to 512):
-            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
-        hidden_act (:obj:`str` or :obj:`function`, optional, defaults to :obj:`"gelu"`):
+        intermediate_size (:obj:`int`, `optional`, defaults to 3072):
+            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
+        hidden_act (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"gelu"`):
             The non-linear activation function (function or string) in the encoder and pooler.
-            If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"`, :obj:`"gelu_new"`, :obj:`"gelu_fast"`,
-            and :obj:`"mish"` are supported.
-        hidden_dropout_prob (:obj:`float`, optional, defaults to 0.0):
-            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
-        attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0.1):
+            If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"swish"` and :obj:`"gelu_new"` are supported.
+        hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
+            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+        attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
             The dropout ratio for the attention probabilities.
-        max_position_embeddings (:obj:`int`, optional, defaults to 512):
+        max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
             The maximum sequence length that this model might ever be used with.
             Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
-        type_vocab_size (:obj:`int`, optional, defaults to 2):
-            The vocabulary size of the :obj:`token_type_ids` passed into :class:`~transformers.SqueezeBertModel`.
-        initializer_range (:obj:`float`, optional, defaults to 0.02):
+        type_vocab_size (:obj:`int`, `optional`, defaults to 2):
+            The vocabulary size of the :obj:`token_type_ids` passed when calling :class:`~transformers.BertModel` or
+            :class:`~transformers.TFBertModel`.
+        initializer_range (:obj:`float`, `optional`, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        layer_norm_eps (:obj:`float`, optional, defaults to 1e-12):
-            The epsilon used by the layer normalization layers.
+        layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12):
 
-        pad_token_id (:obj:`int`, optional, defaults to 0):
+        pad_token_id (:obj:`int`, `optional`, defaults to 0):
             The ID of the token in the word embedding to use as padding.
-        embedding_size (:obj:`int`, optional, defaults to 128):
+        embedding_size (:obj:`int`, `optional`, defaults to 768):
             The dimension of the word embedding vectors.
 
-        q_groups (:obj:`int`, optional, defaults to 4):
-            The number of groups in Q layer
-        k_groups (:obj:`int`, optional, defaults to 4):
-            The number of groups in K layer
-        v_groups (:obj:`int`, optional, defaults to 4):
-            The number of groups in V layer
-        post_attention_groups (:obj:`int`, optional, defaults to 1):
-            The number of groups in the first feed forward network layer
-        intermediate_groups (:obj:`int`, optional, defaults to 4):
-            The number of groups in the second feed forward network layer
-        output_groups (:obj:`int`, optional, defaults to 4):
-            The number of groups in the third feed forward network layer
+        q_groups (:obj:`int`, `optional`, defaults to 4):
+            The number of groups in Q layer.
+        k_groups (:obj:`int`, `optional`, defaults to 4):
+            The number of groups in K layer.
+        v_groups (:obj:`int`, `optional`, defaults to 4):
+            The number of groups in V layer.
+        post_attention_groups (:obj:`int`, `optional`, defaults to 1):
+            The number of groups in the first feed forward network layer.
+        intermediate_groups (:obj:`int`, `optional`, defaults to 4):
+            The number of groups in the second feed forward network layer.
+        output_groups (:obj:`int`, `optional`, defaults to 4):
+            The number of groups in the third feed forward network layer.
 
     Example:
 

src/transformers/modeling_squeezebert.py

@@ -42,10 +42,6 @@ logger = logging.get_logger(__name__)
 _CONFIG_FOR_DOC = "SqueezeBertConfig"
 _TOKENIZER_FOR_DOC = "SqueezeBertTokenizer"
 
-####################################################
-# This list contrains shortcut names for some of
-# the pretrained weights provided with the models
-####################################################
 SQUEEZEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "squeezebert/squeezebert-uncased",
     "squeezebert/squeezebert-mnli",
@@ -407,11 +403,17 @@ class SqueezeBertPreTrainedModel(PreTrainedModel):
             module.bias.data.zero_()
 
 
-SQUEEZEBERT_START_DOCSTRING = r"""    The SqueezeBERT model was proposed in
+SQUEEZEBERT_START_DOCSTRING = r"""
+
+    The SqueezeBERT model was proposed in
     `SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
     <https://arxiv.org/abs/2006.11316>`__ by Forrest N. Iandola, Albert E. Shaw, Ravi Krishna, and Kurt W. Keutzer
 
-    This model is a PyTorch `torch.nn.Module <https://pytorch.org/docs/stable/nn.html#torch.nn.Module>`_ sub-class.
+    This model inherits from :class:`~transformers.PreTrainedModel`. Check the superclass documentation for the generic
+    methods the library implements for all its model (such as downloading or saving, resizing the input embeddings,
+    pruning heads etc.)
+
+    This model is also a PyTorch `torch.nn.Module <https://pytorch.org/docs/stable/nn.html#torch.nn.Module>`__ subclass.
     Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general
     usage and behavior.
 
@@ -445,47 +447,55 @@ SQUEEZEBERT_START_DOCSTRING = r"""    The SqueezeBERT model was proposed in
 """
 
 SQUEEZEBERT_INPUTS_DOCSTRING = r"""
-    Inputs:
-        input_ids (:obj:`torch.LongTensor` of shape :obj:`{0}`):
+    Args:
+        input_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`):
             Indices of input sequence tokens in the vocabulary.
 
-            Indices can be obtained using :class:`transformers.SqueezeBertTokenizer`.
-            See :func:`transformers.PreTrainedTokenizer.encode` and
-            :func:`transformers.PreTrainedTokenizer.__call__` for details.
+            Indices can be obtained using :class:`~transformers.SqueezeBertTokenizer`.
+            See :meth:`transformers.PreTrainedTokenizer.encode` and
+            :meth:`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.
+
+            - 1 for tokens that are **not masked**,
+            - 0 for tokens that are **maked**.
 
             `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
+            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`):
+
+            - 1 indicates the head is **not masked**,
+            - 0 indicates the head is **masked**.
+
+        inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`({0}, 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`):
-            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`):
-            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`):
-            If set to ``True``, the model will return a :class:`~transformers.file_utils.ModelOutput` instead of a
-            plain tuple.
+            This is useful if you want more control over how to convert :obj:`input_ids` indices into associated
+            vectors than the model's internal embedding lookup matrix.
+        output_attentions (:obj:`bool`, `optional`):
+            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`):
+            Whether or not to return a :class:`~transformers.file_utils.ModelOutput` instead of a plain tuple.
 """
 
 
@@ -625,7 +635,7 @@ class SqueezeBertForMaskedLM(SqueezeBertPreTrainedModel):
         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
@@ -702,7 +712,7 @@ class SqueezeBertForSequenceClassification(SqueezeBertPreTrainedModel):
         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),
@@ -787,7 +797,7 @@ class SqueezeBertForMultipleChoice(SqueezeBertPreTrainedModel):
         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)
@@ -877,7 +887,7 @@ class SqueezeBertForTokenClassification(SqueezeBertPreTrainedModel):
         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]``.
         """
@@ -927,8 +937,9 @@ class SqueezeBertForTokenClassification(SqueezeBertPreTrainedModel):
 
 
 @add_start_docstrings(
-    """SqueezeBERT Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear
-    layers on top of the hidden-states output to compute `span start logits` and `span end logits`). """,
+    """SqueezeBERT Model with a span classification head on top for extractive question-answering tasks like SQuAD
+     (a linear layers on top of the hidden-states output to compute `span start logits` and `span end logits`).
+     """,
     SQUEEZEBERT_START_DOCSTRING,
 )
 class SqueezeBertForQuestionAnswering(SqueezeBertPreTrainedModel):
@@ -963,11 +974,11 @@ class SqueezeBertForQuestionAnswering(SqueezeBertPreTrainedModel):
         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.

src/transformers/tokenization_squeezebert.py

@@ -65,8 +65,8 @@ class SqueezeBertTokenizerFast(BertTokenizerFast):
     r"""
     Constructs a  "Fast" SqueezeBert tokenizer (backed by HuggingFace's `tokenizers` library).
 
-    :class:`~transformers.SqueezeBertTokenizerFast` is identical to :class:`~transformers.BertTokenizerFast` and runs end-to-end
-    tokenization: punctuation splitting + wordpiece.
+    :class:`~transformers.SqueezeBertTokenizerFast` is identical to :class:`~transformers.BertTokenizerFast` and
+    runs end-to-end tokenization: punctuation splitting + wordpiece.
 
     Refer to superclass :class:`~transformers.BertTokenizerFast` for usage examples and documentation concerning
     parameters.