src/modeling/dummy_modeling_xlnet.py [1040:1119]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        output_attentions=None,
        output_hidden_states=None,
    ):
        r"""
        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, num_predict)`, `optional`, defaults to :obj:`None`):
            Labels for masked language modeling.
            `num_predict` corresponds to `target_mapping.shape[1]`. If `target_mapping` is `None`, then `num_predict` corresponds to `sequence_length`.
            The labels should correspond to the masked input words that should be predicted and depends on `target_mapping`. Note in order to perform standard auto-regressive language modeling a `<mask>` token has to be added to the `input_ids` (see `prepare_inputs_for_generation` fn and examples below)
            Indices are selected in ``[-100, 0, ..., config.vocab_size]``
            All labels set to ``-100`` are ignored, the loss is only
            computed for labels in ``[0, ..., config.vocab_size]``

    Return:
        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.XLNetConfig`) and inputs:
        loss (:obj:`torch.FloatTensor` of shape `(1,)`, `optional`, returned when ``labels`` is provided)
            Language modeling loss.
        prediction_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, num_predict, config.vocab_size)`):
            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
            `num_predict` corresponds to `target_mapping.shape[1]`. If `target_mapping` is `None`, then `num_predict` corresponds to `sequence_length`.
        mems (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers`):
            Contains pre-computed hidden-states (key and values in the attention blocks).
            Can be used (see `past` input) to speed up sequential decoding. The token ids which have their past given to this model
            should not be passed as input ids as they have already been computed.
        hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_hidden_states=True`` is passed or when ``config.output_hidden_states=True``):
            Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
            of shape :obj:`(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_attentions=True`` is passed or when ``config.output_attentions=True``):
            Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
            :obj:`(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::

        from transformers import XLNetTokenizer, XLNetLMHeadModel
        import torch

        tokenizer = XLNetTokenizer.from_pretrained('xlnet-large-cased')
        model = XLNetLMHeadModel.from_pretrained('xlnet-large-cased')

        # We show how to setup inputs to predict a next token using a bi-directional context.
        input_ids = torch.tensor(tokenizer.encode("Hello, my dog is very <mask>", add_special_tokens=False)).unsqueeze(0)  # We will predict the masked token
        perm_mask = torch.zeros((1, input_ids.shape[1], input_ids.shape[1]), dtype=torch.float)
        perm_mask[:, :, -1] = 1.0  # Previous tokens don't see last token
        target_mapping = torch.zeros((1, 1, input_ids.shape[1]), dtype=torch.float)  # Shape [1, 1, seq_length] => let's predict one token
        target_mapping[0, 0, -1] = 1.0  # Our first (and only) prediction will be the last token of the sequence (the masked token)

        outputs = model(input_ids, perm_mask=perm_mask, target_mapping=target_mapping)
        next_token_logits = outputs[0]  # Output has shape [target_mapping.size(0), target_mapping.size(1), config.vocab_size]

        # The same way can the XLNetLMHeadModel be used to be trained by standard auto-regressive language modeling.
        input_ids = torch.tensor(tokenizer.encode("Hello, my dog is very <mask>", add_special_tokens=False)).unsqueeze(0)  # We will predict the masked token
        labels = torch.tensor(tokenizer.encode("cute", add_special_tokens=False)).unsqueeze(0)
        assert labels.shape[0] == 1, 'only one word will be predicted'
        perm_mask = torch.zeros((1, input_ids.shape[1], input_ids.shape[1]), dtype=torch.float)
        perm_mask[:, :, -1] = 1.0  # Previous tokens don't see last token as is done in standard auto-regressive lm training
        target_mapping = torch.zeros((1, 1, input_ids.shape[1]), dtype=torch.float)  # Shape [1, 1, seq_length] => let's predict one token
        target_mapping[0, 0, -1] = 1.0  # Our first (and only) prediction will be the last token of the sequence (the masked token)

        outputs = model(input_ids, perm_mask=perm_mask, target_mapping=target_mapping, labels=labels)
        loss, next_token_logits = outputs[:2]  # Output has shape [target_mapping.size(0), target_mapping.size(1), config.vocab_size]

        """
        transformer_outputs = self.transformer(
            input_ids,
            attention_mask=attention_mask,
            mems=mems,
            perm_mask=perm_mask,
            target_mapping=target_mapping,
            token_type_ids=token_type_ids,
            input_mask=input_mask,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/modeling/dummy_modeling_xlnet.py [1585:1663]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        output_attentions=None,
        output_hidden_states=None,
    ):
        r"""
        start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
            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`):
            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.
        is_impossible (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`, defaults to :obj:`None`):
            Labels whether a question has an answer or no answer (SQuAD 2.0)
        cls_index (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`, defaults to :obj:`None`):
            Labels for position (index) of the classification token to use as input for computing plausibility of the answer.
        p_mask (``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``, `optional`, defaults to :obj:`None`):
            Optional mask of tokens which can't be in answers (e.g. [CLS], [PAD], ...).
            1.0 means token should be masked. 0.0 mean token is not masked.

    Returns:
        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.XLNetConfig`) and inputs:
        loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned if both :obj:`start_positions` and :obj:`end_positions` are provided):
            Classification loss as the sum of start token, end token (and is_impossible if provided) classification losses.
        start_top_log_probs (``torch.FloatTensor`` of shape ``(batch_size, config.start_n_top)``, `optional`, returned if ``start_positions`` or ``end_positions`` is not provided):
            Log probabilities for the top config.start_n_top start token possibilities (beam-search).
        start_top_index (``torch.LongTensor`` of shape ``(batch_size, config.start_n_top)``, `optional`, returned if ``start_positions`` or ``end_positions`` is not provided):
            Indices for the top config.start_n_top start token possibilities (beam-search).
        end_top_log_probs (``torch.FloatTensor`` of shape ``(batch_size, config.start_n_top * config.end_n_top)``, `optional`, returned if ``start_positions`` or ``end_positions`` is not provided):
            Log probabilities for the top ``config.start_n_top * config.end_n_top`` end token possibilities (beam-search).
        end_top_index (``torch.LongTensor`` of shape ``(batch_size, config.start_n_top * config.end_n_top)``, `optional`, returned if ``start_positions`` or ``end_positions`` is not provided):
            Indices for the top ``config.start_n_top * config.end_n_top`` end token possibilities (beam-search).
        cls_logits (``torch.FloatTensor`` of shape ``(batch_size,)``, `optional`, returned if ``start_positions`` or ``end_positions`` is not provided):
            Log probabilities for the ``is_impossible`` label of the answers.
        mems (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers`):
            Contains pre-computed hidden-states (key and values in the attention blocks).
            Can be used (see `past` input) to speed up sequential decoding. The token ids which have their past given to this model
            should not be passed as input ids as they have already been computed.
        hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_hidden_states=True`` is passed or when ``config.output_hidden_states=True``):
            Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
            of shape :obj:`(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_attentions=True`` is passed or when ``config.output_attentions=True``):
            Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
            :obj:`(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.

        Example::

            >>> from transformers import XLNetTokenizer, XLNetForQuestionAnswering
            >>> import torch

            >>> tokenizer =  XLNetTokenizer.from_pretrained('xlnet-base-cased')
            >>> model = XLNetForQuestionAnswering.from_pretrained('xlnet-base-cased')

            >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
            >>> start_positions = torch.tensor([1])
            >>> end_positions = torch.tensor([3])
            >>> outputs = model(input_ids, start_positions=start_positions, end_positions=end_positions)

            >>> loss = outputs[0]
        """
        transformer_outputs = self.transformer(
            input_ids,
            attention_mask=attention_mask,
            mems=mems,
            perm_mask=perm_mask,
            target_mapping=target_mapping,
            token_type_ids=token_type_ids,
            input_mask=input_mask,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -