tokenizers/pr_2119/en/api/encoding.md

Encoding

Encoding[[tokenizers.Encoding]]

The Encoding represents the output of a Tokenizer.

It holds all the information about the tokenized input, including the token IDs, token strings, attention masks, offsets, and more. This is the main data structure returned by encode() and encode_batch().

Example:

>>> from tokenizers import Tokenizer
>>> tokenizer = Tokenizer.from_pretrained("bert-base-uncased")
>>> encoding = tokenizer.encode("Hello, world!")
>>> encoding.ids
[101, 7592, 1010, 2088, 999, 102]
>>> encoding.tokens
['[CLS]', 'hello', ',', 'world', '!', '[SEP]']
>>> encoding.offsets
[(0, 0), (0, 5), (5, 6), (7, 12), (12, 13), (0, 0)]

List[int]The attention mask The attention mask

This indicates to the LM which tokens should be attended to, and which should not. This is especially important when batching sequences, where we need to applying padding.

List[int]The list of IDs The generated IDs

The IDs are the main input to a Language Model. They are the token indices, the numerical representations that a LM understands.

intThe number of sequences in this Encoding The number of sequences represented

A List of Tuple[int, int]The list of offsets The offsets associated to each token

These offsets let's you slice the input string, and thus retrieve the original part that led to producing the corresponding token.

A List of overflowing Encoding

When using truncation, the Tokenizer takes care of splitting the output into as many pieces as required to match the specified maximum length. This field lets you retrieve all the subsequent pieces.

When you use pairs of sequences, the overflowing pieces will contain enough variations to cover all the possible combinations, while respecting the provided maximum length.

A List of Optional[int]A list of optional sequence index. The generated sequence indices.

They represent the index of the input sequence associated to each token. The sequence id can be None if the token is not related to any input sequence, like for example with special tokens.

List[int]The special tokens mask The special token mask

This indicates which tokens are special tokens, and which are not.

List[str]The list of tokens The generated tokens

They are the string representation of the IDs.

List[int]The list of type ids The generated type IDs

Generally used for tasks like sequence classification or question answering, these tokens let the LM know which input sequence corresponds to each tokens.

A List of Optional[int]A list of optional word index. The generated word indices.

They represent the index of the word associated to each token. When the input is pre-tokenized, they correspond to the ID of the given input label, otherwise they correspond to the words indices as defined by the PreTokenizer that was used.

For special tokens and such (any token that was generated from something that was not part of the input), the output is None

A List of Optional[int]A list of optional word index. The generated word indices.

This is deprecated and will be removed in a future version. Please use ~tokenizers.Encoding.word_ids instead.

They represent the index of the word associated to each token. When the input is pre-tokenized, they correspond to the ID of the given input label, otherwise they correspond to the words indices as defined by the PreTokenizer that was used.

For special tokens and such (any token that was generated from something that was not part of the input), the output is None

• char_pos (int) -- The position of a char in the input string

• sequence_index (int, defaults to 0) -- The index of the sequence that contains the target charintThe index of the token that contains this char in the encoded sequence Get the token that contains the char at the given position in the input sequence.

• char_pos (int) -- The position of a char in the input string

• sequence_index (int, defaults to 0) -- The index of the sequence that contains the target charintThe index of the word that contains this char in the input sequence Get the word that contains the char at the given position in the input sequence.

• encodings (A List of Encoding) -- The list of encodings that should be merged in one

• growing_offsets (bool, defaults to True) -- Whether the offsets should accumulate while mergingEncodingThe resulting Encoding Merge the list of encodings into one final Encoding

• length (int) -- The desired length

• direction -- (str, defaults to right): The expected padding direction. Can be either right or left

• pad_id (int, defaults to 0) -- The ID corresponding to the padding token

• pad_type_id (int, defaults to 0) -- The type ID corresponding to the padding token

• pad_token (str, defaults to [PAD]) -- The pad token to use Pad the Encoding at the given length

Set the given sequence index

Set the given sequence index for the whole range of tokens contained in this Encoding.

• token_index (int) -- The index of a token in the encoded sequence.Tuple[int, int]The token offsets (first, last + 1) Get the offsets of the token at the given index.

The returned offsets are related to the input sequence that contains the token. In order to determine in which input sequence it belongs, you must call ~tokenizers.Encoding.token_to_sequence().

• token_index (int) -- The index of a token in the encoded sequence.intThe sequence id of the given token Get the index of the sequence represented by the given token.

In the general use case, this method returns 0 for a single sequence or the first sequence of a pair, and 1 for the second sequence of a pair

• token_index (int) -- The index of a token in the encoded sequence.intThe index of the word in the relevant input sequence. Get the index of the word that contains the token in one of the input sequences.

The returned word index is related to the input sequence that contains the token. In order to determine in which input sequence it belongs, you must call ~tokenizers.Encoding.token_to_sequence().

• max_length (int) -- The desired length

• stride (int, defaults to 0) -- The length of previous content to be included in each overflowing piece

• direction (str, defaults to right) -- Truncate direction Truncate the Encoding at the given length

If this Encoding represents multiple sequences, when truncating this information is lost. It will be considered as representing a single sequence.

• word_index (int) -- The index of a word in one of the input sequences.

• sequence_index (int, defaults to 0) -- The index of the sequence that contains the target wordTuple[int, int]The range of characters (span) (first, last + 1) Get the offsets of the word at the given index in one of the input sequences.

• word_index (int) -- The index of a word in one of the input sequences.

• sequence_index (int, defaults to 0) -- The index of the sequence that contains the target wordTuple[int, int]The range of tokens: (first, last + 1) Get the encoded tokens corresponding to the word at the given index in one of the input sequences.

The Rust API Reference is available directly on the Docs.rs website.

The node API has not been documented yet.