sg& d dl mZmZmZ ddlmZ ddlmZ ddlm Z ej e Z ddd d
Z
G d d e Zy
) )ListOptionalTuple )PreTrainedTokenizerFast)logging )HerbertTokenizerz
vocab.jsonz
merges.txtztokenizer.json)
vocab_file merges_filetokenizer_filec
e Zd ZdZeZeZ d
fd Z dde e
de e e
de e
fdZ dde e
de e e
de
de e
f fd
Z dde e
de e e
de e
fd Zdd
ed e e dee fd Z xZS )HerbertTokenizerFastam
Construct a "Fast" BPE tokenizer for HerBERT (backed by HuggingFace's *tokenizers* library).
Peculiarities:
- uses BERT's pre-tokenizer: BertPreTokenizer splits tokens on spaces, and also on punctuation. Each occurrence of
a punctuation character will be treated separately.
This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the methods. Users should refer to the
superclass for more information regarding methods.
Args:
vocab_file (`str`):
Path to the vocabulary file.
merges_file (`str`):
Path to the merges file.
c
6 t
| ||f||||||d| y )N)r
cls_token unk_token pad_token
mask_token sep_token)super__init__) selfr r r
r r r r r kwargs __class__s h/var/www/html/venv/lib/python3.12/site-packages/transformers/models/herbert/tokenization_herbert_fast.pyr z HerbertTokenizerFast.__init__2 s;
* !
token_ids_0 token_ids_1returnc f | j g}| j g}|||z |z S ||z |z |z |z S )a
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
adding special tokens. An HerBERT, like BERT sequence has the following format:
- single sequence: ` X `
- pair of sequences: ` A B `
Args:
token_ids_0 (`List[int]`):
List of IDs to which the special tokens will be added.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
) cls_token_id sep_token_id)r r r clsseps r build_inputs_with_special_tokensz5HerbertTokenizerFast.build_inputs_with_special_tokensJ sP ( ! ! $s* *[ 3&4s::r already_has_special_tokensc |rt | ||d S |dgdgt | z z dgz S dgdgt | z z dgz dgt | z z dgz S )a
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer `prepare_for_model` method.
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not the token list is already formatted with special tokens for the model.
Returns:
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
T)r r r& r r )r get_special_tokens_masklen)r r r r& r s r r( z,HerbertTokenizerFast.get_special_tokens_maske s $ &72 '[]a 3
31#K 001QC7 7sqcC ,,-3sS=M7MNRSQTTTr c | j g}| j g}|t ||z |z dgz S t ||z |z dgz t ||z dgz z S )a{
Create a mask from the two sequences passed to be used in a sequence-pair classification task. HerBERT, like
BERT sequence pair mask has the following format:
```
0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
| first sequence | second sequence |
```
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
r r )r" r! r) )r r r r$ r# s r $create_token_type_ids_from_sequencesz9HerbertTokenizerFast.create_token_type_ids_from_sequences st * ! ! s[(3./1#5 53$s*+qc1C c8I4JaS4PPPr save_directoryfilename_prefixc f | j j j || }t | S )N)name)
_tokenizermodelsavetuple)r r, r- filess r save_vocabularyz$HerbertTokenizerFast.save_vocabulary s+ %%**>*PU|r )NNNzzzzz)N)NF)__name__
__module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesr
slow_tokenizer_classr r intr r% boolr( r+ strr r5
__classcell__)r s @r r r s
$ *+
2 JN; 9;3;DI3F;
c;8 sxU 9U3;DI3FUkoU
cU8 JNQ 9Q3;DI3FQ
cQ8 c HSM ]bcf]g r r N)typingr r r tokenization_utils_fastr utilsr tokenization_herbertr
get_loggerr6 loggerr: r r r rH sG ) ( > 2
H %#/ `pq B 2 B r