Post-attention processing.

Records the host_call structure.

Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).

Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).

Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).

Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).

Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).

Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).

Reshapes a >= rank 2 tensor to a rank 2 tensor (i.e., a matrix).

Save a model and its configuration file to a directory, so that it can be re-loaded using the `:func:`~transformers.PreTrainedModel.from_

Make sure we are sharing the input and output embeddings. Export to TorchScript can't handle parameter sharing so we are cloning them

Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given voca

Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given voca

Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given voca

Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given voca

Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given voca

Runs basic whitespace cleaning and splitting on a piece of text.

Runs basic whitespace cleaning and splitting on a peice of text.

Runs basic whitespace cleaning and splitting on a piece of text.

Runs basic whitespace cleaning and splitting on a piece of text.

Runs basic whitespace cleaning and splitting on a piece of text.

Runs basic whitespace cleaning and splitting on a piece of text.

Runs basic whitespace cleaning and splitting on a piece of text.

Runs basic whitespace cleaning and splitting on a piece of text.

Runs basic whitespace cleaning and splitting on a piece of text.

Compute softmax probability over raw logits.

Compute softmax probability over raw logits.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Get the n-best logits from a list.

Get the n-best logits from a list.

Get the n-best logits from a list.

Get the n-best logits from a list.

Get the n-best logits from a list.

Get the n-best logits from a list.

Get the n-best logits from a list.

Sample a permutation of the factorization order, and create an attention mask accordingly. Args: inputs: int64 Tensor in shape [seq_len],

Sample `goal_num_predict` tokens for partial prediction. About `mask_beta` tokens are chosen in a context of `mask_alpha` tokens.

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

Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based vocabulary or sub-words for sub-wo

Adds whitespace around any CJK character.

Truncates a sequence pair in place to the maximum length.

Truncates a sequence pair in place to the maximum length.

Truncates a sequence pair in place to the maximum length.

Truncates a sequence pair in place to the maximum length.

Truncates a sequence pair in place to the maximum length.

Truncates a sequence pair in place to the maximum length.

Truncates a sequence pair in place to the maximum length.

Add a list of new tokens to the tokenizer class. If the new tokens are not in the vocabulary, they are added to it with indices start

See base class.

See base class.

See base class.

See base class.

See base class.

Performs multi-headed attention from `from_tensor` to `to_tensor`. This is an implementation of multi-headed attention based on "Attention is all

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

Given something that might be a URL (or might be a local path), determine which. If it's a URL, download the file and cache it, and retur