How to use the transformers.file_utils.add_start_docstrings function in transformers

def get_output_embeddings(self):
        return self.transformer.tokens_embed

    def call(self, inputs, **kwargs):
        transformer_outputs = self.transformer(inputs, **kwargs)
        hidden_states = transformer_outputs[0]

        lm_logits = self.transformer.tokens_embed(hidden_states, mode="linear")

        outputs = (lm_logits,) + transformer_outputs[1:]

        return outputs  # lm_logits, (all hidden_states), (attentions)


@add_start_docstrings("""OpenAI GPT Model transformer with a language modeling and a multiple-choice classification
head on top e.g. for RocStories/SWAG tasks. The two heads are two linear layers.
The language modeling head has its weights tied to the input embeddings,
the classification head takes as input the input of a specified classification token index in the input sequence).
""", OPENAI_GPT_START_DOCSTRING, OPENAI_GPT_INPUTS_DOCSTRING)
class TFOpenAIGPTDoubleHeadsModel(TFOpenAIGPTPreTrainedModel):
    r"""
        **mc_token_ids**: (`optional`, default to index of the last token of the input) ``Numpy array`` or ``tf.Tensor`` of shape ``(batch_size, num_choices)``:
            Index of the classification token in each input sequence.
            Selected in the range ``[0, input_ids.size(-1) - 1[``.

    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **lm_prediction_scores**: ``torch.FloatTensor`` of shape ``(batch_size, num_choices, sequence_length, config.vocab_size)``
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
        **mc_prediction_scores**: ``torch.FloatTensor`` of shape ``(batch_size, num_choices)``
            Prediction scores of the multiplechoice classification head (scores for each choice before SoftMax).
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)

head_mask = [None] * self.config.num_hidden_layers

        embedding_output = self.embeddings(input_ids=input_ids, position_ids=position_ids, token_type_ids=token_type_ids, inputs_embeds=inputs_embeds)
        encoder_outputs = self.encoder(embedding_output,
                                       attention_mask=extended_attention_mask,
                                       head_mask=head_mask,
                                       encoder_hidden_states=encoder_hidden_states,
                                       encoder_attention_mask=encoder_extended_attention_mask)
        sequence_output = encoder_outputs[0]
        pooled_output = self.pooler(sequence_output)

        outputs = (sequence_output, pooled_output,) + encoder_outputs[1:]  # add hidden_states and attentions if they are here
        return outputs  # sequence_output, pooled_output, (hidden_states), (attentions)


@add_start_docstrings("""Bert Model with two heads on top as done during the pre-training:
                       a `masked language modeling` head and a `next sentence prediction (classification)` head. """,
                      BERT_START_DOCSTRING,
                      BERT_INPUTS_DOCSTRING)
class BertForPreTraining(BertPreTrainedModel):
    r"""
        **masked_lm_labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
            Labels for computing the masked language modeling loss.
            Indices should be in ``[-1, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring)
            Tokens with indices set to ``-1`` are ignored (masked), the loss is only computed for the tokens with labels
            in ``[0, ..., config.vocab_size]``
        **next_sentence_label**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
            Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair (see ``input_ids`` docstring)
            Indices should be in ``[0, 1]``.
            ``0`` indicates sequence B is a continuation of sequence A,
            ``1`` indicates sequence B is a random sequence.

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**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
            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**.
        **inputs_embeds**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, embedding_dim)``:
            Optionally, instead of passing ``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.
"""

@add_start_docstrings("The bare XLNet Model transformer outputting raw hidden-states without any specific head on top.",
                      XLNET_START_DOCSTRING, XLNET_INPUTS_DOCSTRING)
class XLNetModel(XLNetPreTrainedModel):
    r"""
    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **last_hidden_state**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, hidden_size)``
            Sequence of hidden-states at the last layer of the model.
        **mems**: (`optional`, returned when ``config.mem_len > 0``)
            list of ``torch.FloatTensor`` (one for each layer):
            that contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model
            if config.mem_len > 0 else tuple of None. Can be used to speed up sequential decoding and attend to longer context.
            See details in the docstring of the `mems` input above.
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
            list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings)
            of shape ``(batch_size, sequence_length, hidden_size)``:
            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        **attentions**: (`optional`, returned when ``config.output_attentions=True``)

@add_start_docstrings(AutoModel.__doc__)
def model(*args, **kwargs):
    r"""
            # Using torch.hub !
            import torch

            model = torch.hub.load('huggingface/transformers', 'model', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
            model = torch.hub.load('huggingface/transformers', 'model', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
            model = torch.hub.load('huggingface/transformers', 'model', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
            assert model.config.output_attention == True
            # Loading from a TF checkpoint file instead of a PyTorch model (slower)
            config = AutoConfig.from_json_file('./tf_model/bert_tf_model_config.json')
            model = torch.hub.load('huggingface/transformers', 'model', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)

        """

    return AutoModel.from_pretrained(*args, **kwargs)

self.input_embeddings = input_embeddings

    def build(self, input_shape):
        self.bias = self.add_weight(shape=(self.vocab_size,),
                                    initializer='zeros',
                                    trainable=True,
                                    name='bias')
        super(TFDistilBertLMHead, self).build(input_shape)

    def call(self, hidden_states):
        hidden_states = self.input_embeddings(hidden_states, mode="linear")
        hidden_states = hidden_states + self.bias
        return hidden_states


@add_start_docstrings("""DistilBert Model with a `masked language modeling` head on top. """,
                      DISTILBERT_START_DOCSTRING, DISTILBERT_INPUTS_DOCSTRING)
class TFDistilBertForMaskedLM(TFDistilBertPreTrainedModel):
    r"""
    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **prediction_scores**: ``tf.Tensor`` of shape ``(batch_size, sequence_length, config.vocab_size)``
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
            list of ``tf.Tensor`` (one for the output of each layer + the output of the embeddings)
            of shape ``(batch_size, sequence_length, hidden_size)``:
            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        **attentions**: (`optional`, returned when ``config.output_attentions=True``)
            list of ``tf.Tensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

    Examples::

outputs = (logits,) + transformer_outputs[1:]  # Keep mems, hidden states, attentions if there are in it

        if labels is not None:
            if self.num_labels == 1:
                #  We are doing regression
                loss_fct = MSELoss()
                loss = loss_fct(logits.view(-1), labels.view(-1))
            else:
                loss_fct = CrossEntropyLoss()
                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
            outputs = (loss,) + outputs

        return outputs  # return (loss), logits, (mems), (hidden states), (attentions)


@add_start_docstrings("""XLNet Model with a token classification head on top (a linear layer on top of
                      the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks. """,
                      XLNET_START_DOCSTRING,
                      XLNET_INPUTS_DOCSTRING)
class XLNetForTokenClassification(XLNetPreTrainedModel):
    r"""
    Inputs:
        **input_ids**: ``torch.LongTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
            Indices of input sequence tokens in the vocabulary.
            The second dimension of the input (`num_choices`) indicates the number of choices to scores.
        **token_type_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
            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``
        **attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``:
            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 values selected in ``[0, 1]``:
            ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
        **token_type_ids**: (`optional`) ``Numpy array`` or ``tf.Tensor`` of shape ``(batch_size, sequence_length)``:
            A parallel sequence of tokens (can be used to indicate various portions of the inputs).
            The embeddings from these tokens will be summed with the respective token embeddings.
            Indices are selected in the vocabulary (unlike BERT which has a specific vocabulary for segment indices).
        **position_ids**: (`optional`) ``Numpy array`` or ``tf.Tensor`` of shape ``(batch_size, sequence_length)``:
            Indices of positions of each input sequence tokens in the position embeddings.
            Selected in the range ``[0, config.max_position_embeddings - 1]``.
        **head_mask**: (`optional`) ``Numpy array`` or ``tf.Tensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
            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**.
"""

@add_start_docstrings("The bare CTRL Model transformer outputting raw hidden-states without any specific head on top.",
                                            CTRL_START_DOCSTRING, CTRL_INPUTS_DOCSTRING)
class TFCTRLModel(TFCTRLPreTrainedModel):
    r"""
    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **last_hidden_state**: ``tf.Tensor`` of shape ``(batch_size, sequence_length, hidden_size)``
            Sequence of hidden-states at the last layer of the model.
        **past**:
            list of ``tf.Tensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
            that contains pre-computed hidden-states (key and values in the attention blocks).
            Can be used (see `past` input) to speed up sequential decoding.
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
            list of ``tf.Tensor`` (one for the output of each layer + the output of the embeddings)
            of shape ``(batch_size, sequence_length, hidden_size)``:
            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        **attentions**: (`optional`, returned when ``config.output_attentions=True``)
            list of ``tf.Tensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:

self.roberta = TFRobertaMainLayer(config, name="roberta")
        self.classifier = TFRobertaClassificationHead(config, name="classifier")
    
    def call(self, inputs, **kwargs):
        outputs = self.roberta(inputs, **kwargs)

        sequence_output = outputs[0]
        logits = self.classifier(sequence_output, training=kwargs.get('training', False))

        outputs = (logits,) + outputs[2:]

        return outputs  # logits, (hidden_states), (attentions)


@add_start_docstrings("""RoBERTa Model with a token classification head on top (a linear layer on top of
    the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks. """,
    ROBERTA_START_DOCSTRING, ROBERTA_INPUTS_DOCSTRING)
class TFRobertaForTokenClassification(TFRobertaPreTrainedModel):
    r"""
    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **scores**: ``Numpy array`` or ``tf.Tensor`` of shape ``(batch_size, sequence_length, config.num_labels)``
            Classification scores (before SoftMax).
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
            list of ``Numpy array`` or ``tf.Tensor`` (one for the output of each layer + the output of the embeddings)
            of shape ``(batch_size, sequence_length, hidden_size)``:
            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        **attentions**: (`optional`, returned when ``config.output_attentions=True``)
            list of ``Numpy array`` or ``tf.Tensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

    Examples::

Mask values selected in ``[0, 1]``:
            ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
        **token_type_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
            A parallel sequence of tokens (can be used to indicate various portions of the inputs).
            The embeddings from these tokens will be summed with the respective token embeddings.
            Indices are selected in the vocabulary (unlike BERT which has a specific vocabulary for segment indices).
        **position_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
            Indices of positions of each input sequence tokens in the position embeddings.
            Selected in the range ``[0, config.max_position_embeddings - 1]``.
        **head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
            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**.
"""

@add_start_docstrings("The bare CTRL Model transformer outputting raw hidden-states without any specific head on top.",
                                            CTRL_START_DOCSTRING, CTRL_INPUTS_DOCSTRING)
class CTRLModel(CTRLPreTrainedModel):
    r"""
    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **last_hidden_state**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, hidden_size)``
            Sequence of hidden-states at the last layer of the model.
        **past**:
            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
            that contains pre-computed hidden-states (key and values in the attention blocks).
            Can be used (see `past` input) to speed up sequential decoding.
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
            list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings)
            of shape ``(batch_size, sequence_length, hidden_size)``:
            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        **attentions**: (`optional`, returned when ``config.output_attentions=True``)
            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:

if labels is not None:
            if self.num_labels == 1:
                #  We are doing regression
                loss_fct = MSELoss()
                loss = loss_fct(logits.view(-1), labels.view(-1))
            else:
                loss_fct = CrossEntropyLoss()
                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
            outputs = (loss,) + outputs

        return outputs  # (loss), logits, (hidden_states), (attentions)        




@add_start_docstrings("""Bert Model with a multiple choice classification head on top (a linear layer on top of
                      the pooled output and a softmax) e.g. for RocStories/SWAG tasks. """,
                      BERT_START_DOCSTRING,
                      BERT_INPUTS_DOCSTRING)
class BertForMultipleChoice(BertPreTrainedModel):
    r"""
        **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
            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)

    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
            Classification loss.
        **classification_scores**: ``torch.FloatTensor`` of shape ``(batch_size, num_choices)`` where `num_choices` is the size of the second dimension
            of the input tensors. (see `input_ids` above).
            Classification scores (before SoftMax).