Tokenizer
Last updated
Last updated
PythonRustNode
( model )
Parameters
model () — The core algorithm that this Tokenizer should be using.
A Tokenizer works as a pipeline. It processes some raw text as input and outputs an .
propertydecoder
The optional Decoder in use by the Tokenizer
propertymodel
The in use by the Tokenizer
propertynormalizer
The optional in use by the Tokenizer
propertypadding
Returns
(dict, optional)
A dict with the current padding parameters if padding is enabled
Get the current padding parameters
Cannot be set, use enable_padding() instead
propertypost_processor
The optional PostProcessor in use by the Tokenizer
propertypre_tokenizer
propertytruncation
Returns
(dict, optional)
A dict with the current truncation parameters if truncation is enabled
Get the currently set truncation parameters
Cannot set, use enable_truncation() instead
add_special_tokens
( tokens ) → int
Parameters
Returns
int
The number of tokens that were created in the vocabulary
Add the given special tokens to the Tokenizer.
If these tokens are already part of the vocabulary, it just let the Tokenizer know about them. If they don’t exist, the Tokenizer creates them, giving them a new id.
These special tokens will never be processed by the model (ie won’t be split into multiple tokens), and they can be removed from the output when decoding.
add_tokens
( tokens ) → int
Parameters
Returns
int
The number of tokens that were created in the vocabulary
Add the given tokens to the vocabulary
The given tokens are added only if they don’t already exist in the vocabulary. Each token then gets a new attributed id.
decode
( idsskip_special_tokens = True ) → str
Parameters
ids (A List/Tuple of int) — The list of ids that we want to decode
skip_special_tokens (bool, defaults to True) — Whether the special tokens should be removed from the decoded string
Returns
str
The decoded string
Decode the given list of ids back to a string
This is used to decode anything coming back from a Language Model
decode_batch
( sequencesskip_special_tokens = True ) → List[str]
Parameters
sequences (List of List[int]) — The batch of sequences we want to decode
skip_special_tokens (bool, defaults to True) — Whether the special tokens should be removed from the decoded strings
Returns
List[str]
A list of decoded strings
Decode a batch of ids back to their corresponding string
enable_padding
( direction = 'right'pad_id = 0pad_type_id = 0pad_token = '[PAD]'length = Nonepad_to_multiple_of = None )
Parameters
direction (str, optional, defaults to right) — The direction in which to pad. Can be either right or left
pad_to_multiple_of (int, optional) — If specified, the padding length should always snap to the next multiple of the given value. For example if we were going to pad witha length of 250 but pad_to_multiple_of=8 then we will pad to 256.
pad_id (int, defaults to 0) — The id to be used when padding
pad_type_id (int, defaults to 0) — The type id to be used when padding
pad_token (str, defaults to [PAD]) — The pad token to be used when padding
length (int, optional) — If specified, the length at which to pad. If not specified we pad using the size of the longest sequence in a batch.
Enable the padding
enable_truncation
( max_lengthstride = 0strategy = 'longest_first'direction = 'right' )
Parameters
max_length (int) — The max length at which to truncate
stride (int, optional) — The length of the previous first sequence to be included in the overflowing sequence
strategy (str, optional, defaults to longest_first) — The strategy used to truncation. Can be one of longest_first, only_first or only_second.
direction (str, defaults to right) — Truncate direction
Enable truncation
encode
Parameters
sequence (~tokenizers.InputSequence) — The main input sequence we want to encode. This sequence can be either raw text or pre-tokenized, according to the is_pretokenized argument:
If is_pretokenized=False: TextInputSequence
If is_pretokenized=True: PreTokenizedInputSequence()
pair (~tokenizers.InputSequence, optional) — An optional input sequence. The expected format is the same that for sequence.
is_pretokenized (bool, defaults to False) — Whether the input is already pre-tokenized
add_special_tokens (bool, defaults to True) — Whether to add the special tokens
Returns
The encoded result
Encode the given sequence and pair. This method can process raw text sequences as well as already pre-tokenized sequences.
Example:
Here are some examples of the inputs that are accepted:
Copied
encode_batch
( inputis_pretokenized = Falseadd_special_tokens = True ) → A List of [`~tokenizers.Encoding“]
Parameters
input (A List/`Tuple of ~tokenizers.EncodeInput) — A list of single sequences or pair sequences to encode. Each sequence can be either raw text or pre-tokenized, according to the is_pretokenized argument:
If is_pretokenized=False: TextEncodeInput()
If is_pretokenized=True: PreTokenizedEncodeInput()
is_pretokenized (bool, defaults to False) — Whether the input is already pre-tokenized
add_special_tokens (bool, defaults to True) — Whether to add the special tokens
Returns
A List of [`~tokenizers.Encoding“]
The encoded batch
Encode the given batch of inputs. This method accept both raw text sequences as well as already pre-tokenized sequences.
Example:
Here are some examples of the inputs that are accepted:
Copied
from_buffer
Parameters
Returns
The new tokenizer
from_file
Parameters
Returns
The new tokenizer
from_pretrained
Parameters
identifier (str) — The identifier of a Model on the BOINC AI Hub, that contains a tokenizer.json file
revision (str, defaults to main) — A branch or commit id
auth_token (str, optional, defaults to None) — An optional auth token used to access private repositories on the BOINC AI Hub
Returns
The new tokenizer
from_str
Parameters
Returns
The new tokenizer
get_vocab
( with_added_tokens = True ) → Dict[str, int]
Parameters
with_added_tokens (bool, defaults to True) — Whether to include the added tokens
Returns
Dict[str, int]
The vocabulary
Get the underlying vocabulary
get_vocab_size
( with_added_tokens = True ) → int
Parameters
with_added_tokens (bool, defaults to True) — Whether to include the added tokens
Returns
int
The size of the vocabulary
Get the size of the underlying vocabulary
id_to_token
( id ) → Optional[str]
Parameters
id (int) — The id to convert
Returns
Optional[str]
An optional token, None if out of vocabulary
Convert the given id to its corresponding token if it exists
no_padding
( )
Disable padding
no_truncation
( )
Disable truncation
num_special_tokens_to_add
( is_pair )
Return the number of special tokens that would be added for single/pair sentences. :param is_pair: Boolean indicating if the input would be a single sentence or a pair :return:
post_process
Parameters
add_special_tokens (bool) — Whether to add the special tokens
Returns
The final post-processed encoding
Apply all the post-processing steps to the given encodings.
The various steps are:
Truncate according to the set truncation params (provided with enable_truncation())
Apply the PostProcessor
Pad according to the set padding params (provided with enable_padding())
save
( pathpretty = True )
Parameters
path (str) — A path to a file in which to save the serialized tokenizer.
pretty (bool, defaults to True) — Whether the JSON file should be pretty formatted.
to_str
( pretty = False ) → str
Parameters
pretty (bool, defaults to False) — Whether the JSON string should be pretty formatted.
Returns
str
A string representing the serialized Tokenizer
token_to_id
( token ) → Optional[int]
Parameters
token (str) — The token to convert
Returns
Optional[int]
An optional id, None if out of vocabulary
Convert the given token to its corresponding id if it exists
train
( filestrainer = None )
Parameters
files (List[str]) — A list of path to the files that we should use for training
trainer (~tokenizers.trainers.Trainer, optional) — An optional trainer that should be used to train our Model
Train the Tokenizer using the given files.
Reads the files line by line, while keeping all the whitespace, even new lines. If you want to train from data store in-memory, you can check train_from_iterator()
train_from_iterator
( iteratortrainer = Nonelength = None )
Parameters
iterator (Iterator) — Any iterator over strings or list of strings
trainer (~tokenizers.trainers.Trainer, optional) — An optional trainer that should be used to train our Model
length (int, optional) — The total number of sequences in the iterator. This is used to provide meaningful progress tracking
Train the Tokenizer using the provided iterator.
You can provide anything that is a Python Iterator
A list of sequences List[str]
A generator that yields str or List[str]
A Numpy array of strings
…
The optional in use by the Tokenizer
tokens (A List of or str) — The list of special tokens we want to add to the vocabulary. Each token can either be a string or an instance of for more customization.
tokens (A List of or str) — The list of tokens we want to add to the vocabulary. Each token can be either a string or an instance of for more customization.
( sequencepair = Noneis_pretokenized = Falseadd_special_tokens = True ) →
( buffer ) →
buffer (bytes) — A buffer containing a previously serialized
Instantiate a new from the given buffer.
( path ) →
path (str) — A path to a local JSON file representing a previously serialized
Instantiate a new from the file at the given path.
( identifierrevision = 'main'auth_token = None ) →
Instantiate a new from an existing file on the BOINC AI Hub.
( json ) →
json (str) — A valid JSON string representing a previously serialized
Instantiate a new from the given JSON string.
( encodingpair = Noneadd_special_tokens = True ) →
encoding () — The corresponding to the main sequence.
pair (, optional) — An optional corresponding to the pair sequence.
Save the to the file at the given path.
Gets a serialized string representing this .