Checks whether the last character in text is one of a punctuation, control or whitespace character.

Checks whether the first character in text is one of a punctuation, control or whitespace character.

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base class PreTraine

Splits punctuation on a piece of text.

Strips accents from a piece of text.

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Tie or clone module weights depending of whether we are using TorchScript or not

Adds whitespace around any CJK character.

Returns a dictionary containing the encoded sequence or sequence pair and additional information: the mask for sequence classificatio

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens

Copied from fairseq for no_repeat_ngram in beam_search

Clean up a list of simple English tokenization artifacts like spaces before punctuations and abreviated forms.

Converts a sequence of ids (integer) in a string, using the tokenizer and vocabulary with options to remove special tokens and clean

repetition penalty (from CTRL paper https://arxiv.org/abs/1909.05858).

Constructs a `Config` from a Python dictionary of parameters. Args: config_dict (:obj:`Dict[str, any]`):

Args: depth (int): Depth of caller conext, use 0 for caller depth. Default value: 0. Returns: str: module name of th

From a `pretrained_model_name_or_path`, resolve to a dictionary of parameters, to be used for instantiating a Config using `from_dict

Makes broadcastable attention mask and causal mask so that future and maked tokens are ignored. Arguments: attention_mask: torch.

Given a URL, look for the corresponding file in the local cache. If it's not there, download it. Then return the path to the cached file.

# Prepare head mask if needed # 1.0 in head_mask indicate we keep the head attention_probs has shape bsz x n_heads x N x N

Returns the model's output embeddings. Returns: :obj:`nn.Module`: A torch module mapping hidden states t

Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Initialize random seed.

type: torch.Tensor -> torch.Tensor

If there are enough hypotheses and that none of the hypotheses being generated can become better than the worst one in the heap, then

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL,

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Loads a vocabulary file into a dictionary.

Performs any necessary transformations before tokenization. This method should pop the arguments from kwargs and return kwargs as well.

Prune a Conv1D layer (a model parameters) to keep only entries in index. A Conv1D work as a Linear layer (see e.g. BERT) but the weights are

Prunes heads of the base model. Arguments: heads_to_prune: dict with keys being selected layer indices (`int`) and asso

Make sure that all the special tokens attributes of the tokenizer (tokenizer.mask_token, tokenizer.cls_token, ...) are in the vocabulary.

Save the sentencepiece vocabulary (copy original file) and special tokens file to a directory. Args: vocab_path (:obj:`s

Set model's input embeddings Args: value (:obj:`nn.Module`): A module mapping vocabulary to hidden state

Set random seed.

Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002. Args: inputs: A float tensor of arbitrary shape.

Removes all attributes from config which correspond to the default config attributes for better readability and serializes to a Pytho

Save this instance to a json file. Args: json_file_path (:obj:`string`): Path to the JSON file in which

Convert the model into training mode while keep layers freezed.

Truncates a sequence pair in place to the maximum length. Args: ids: list of tokenized input ids. Can be obtained from a string

Convert `url` into a hashed filename in a repeatable way. If `etag` is specified, append its hash to the url's, delimited by a period.

Copy a model state_dict to cpu. Args: state_dict (OrderedDict): Model weights on GPU. Returns: OrderedDict: Model weights on

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image