Add a dictionary of special tokens (eos, pad, cls...) to the encoder and link them to class attributes. If special tokens are NOT in

All the additional special tokens you may want to use (list of strings). Log an error if used while not having been set.

Ids of all the additional special tokens in the vocabulary (list of integers). Log an error if used while not having been set.

List the vocabulary indices of the special tokens ('<unk>', '<cls>'...) mapped to class attributes (cls_token, unk_token...).

List all the special tokens ('<unk>', '<cls>'...) mapped to class attributes Convert tokens of AddedToken type in string. All

List all the special tokens ('<unk>', '<cls>'...) mapped to class attributes Keep the tokens as AddedToken if they are of this type.

This function chunks the `input_tensors` into smaller input tensor parts of size `chunk_size` over the dimension `chunk_dim`. It then applies

Beginning of sentence token (string). Log an error if used while not having been set.

Id of the beginning of sentence token in the vocabulary. Log an error if used while not having been set.

Get the index of the token in the encoded output comprising a character in the original string for a sequence of the batch.

Get the word in the original string corresponding to a character in the original string of a sequence of the batch. Can be c

Classification token (string). E.g. to extract a summary of an input sequence leveraging self-attention along the full depth of the model. Log an err

Id of the classification token in the vocabulary. E.g. to extract a summary of an input sequence leveraging self-attention along the full depth of th

Converts a sequence of tokens (string) in a single string.

Creates a mask from the two sequences passed to be used in a sequence-pair classification task. A BERT sequence pair mask has the fol

Get torch.device from module, assuming that the whole module has one device.

Get torch.dtype from module, assuming that the whole module has one dtype.

Dummy inputs to do a forward pass in the network. Returns: torch.Tensor with dummy inputs

Return the list all encoding from the tokenization process Returns: List[EncodingFast] or None if input was tokenized through Python

End of sentence token (string). Log an error if used while not having been set.

Id of the end of sentence token in the vocabulary. Log an error if used while not having been set.

Return the url and etag (which may be ``None``) stored for `filename`. Raise ``EnvironmentError`` if `filename` or its stored metadata do not

x: b, 512, 104, 104 text: b, 512

Forward function. Args: x: input features with shape of (num_windows*B, N, C) mask: (0/-inf) mask with shape of (num

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function.

Forward function.

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

vis: b c n text: b c n

Args: **p_mask**: (`optional`) ``torch.FloatTensor`` of shape `(batch_size, seq_len)` invalid position mask such as query

Args: One of ``start_states``, ``start_positions`` should be not None. If both are set, ``start_positions`` overrides ``start

Args: One of ``start_states``, ``start_positions`` should be not None. If both are set, ``start_positions`` overrides

hidden_states: float Tensor in shape [bsz, ..., seq_len, hidden_size], the hidden-states of the last layer. cls_index: [optional] positio

r""" Return: :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`

r""" labels (``torch.LongTensor`` of shape ``(batch_size, sequence_length)``, `optional`, defaults to :obj:`None`): Labels for com

r""" labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`): Labels f

r""" labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`): Labels f

r""" next_sentence_label (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`): Labels for

r""" labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`): Labels for computing the

r""" labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`): Labels for computing the

r""" labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`): Labels f

r""" start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`): Labels for posi

Constructs a `Config` from the path to a json file of parameters. Args: json_file (:obj:`string`): Path

r""" Instantiate a :class:`~transformers.PreTrainedTokenizer` (or a derived class) from a predefined tokenizer. Args: pre

r""" Instantiate a :class:`~transformers.PretrainedConfig` (or a derived class) from a pre-trained model configuration. Args:

Implementation of the gelu activation function currently in Google Bert repo (identical to OpenAI GPT). Also see https://arxiv.org/abs/1606.0

Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, where

r""" Generates sequences for models with a LM head. The method currently supports greedy decoding, beam-search decoding, sampling with temperature, sa