qi " d Z ddlmZmZmZmZmZ ddlmZ ddl m
Z
ddl m Z ddl
mZ ej e Zdd d
Z G d d e Zd gZy
)z Tokenization classes for MPNet. ) Tokenizerdecoders normalizerspre_tokenizers
processors) WordPiece )
AddedToken)TokenizersBackend)loggingz vocab.txtztokenizer.json)
vocab_filetokenizer_filec e Zd ZdZeZddgZeZ d
de e
e e f z dz f fd
Z e
de fd Zej d Z xZS ) MPNetTokenizera
Construct a MPNet tokenizer (backed by HuggingFace's *tokenizers* library). Based on WordPiece.
This tokenizer inherits from [`TokenizersBackend`] which contains most of the main methods. Users should
refer to this superclass for more information regarding those methods.
Args:
vocab (`str` or `dict[str, int]`, *optional*):
Dictionary mapping tokens to their IDs. If not provided, an empty vocab is initialized.
do_lower_case (`bool`, *optional*, defaults to `True`):
Whether or not to lowercase the input when tokenizing.
bos_token (`str`, *optional*, defaults to `""`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
When building a sequence using special tokens, this is not the token that is used for the beginning of
sequence. The token used is the `cls_token`.
eos_token (`str`, *optional*, defaults to `""`):
The end of sequence token.
When building a sequence using special tokens, this is not the token that is used for the end of sequence.
The token used is the `sep_token`.
sep_token (`str`, *optional*, defaults to `""`):
The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
sequence classification or for a text and a question for question answering. It is also used as the last
token of a sequence built with special tokens.
cls_token (`str`, *optional*, defaults to `""`):
The classifier token which is used when doing sequence classification (classification of the whole sequence
instead of per-token classification). It is the first token of the sequence when built with special tokens.
unk_token (`str`, *optional*, defaults to `"[UNK]"`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
pad_token (`str`, *optional*, defaults to `""`):
The token used for padding, for example when batching sequences of different lengths.
mask_token (`str`, *optional*, defaults to `""`):
The token used for masking values. This is the token used when training this model with masked language
modeling. This is the token which the model will try to predict.
tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see [this
issue](https://github.com/huggingface/transformers/issues/328)).
strip_accents (`bool`, *optional*):
Whether or not to strip all accents. If this option is not specified, then it will be determined by the
value for `lowercase` (as in the original BERT).
input_idsattention_maskNvocabc ||ni | _ t t | j t | | _ t j d|
| | | j _ t j | j _
t j d | j _ || _
t |t rt |dd n|}t |t rt |dd n|}t |t rt |dd n|}t |t rt |dd n|}t |t rt |dd n|}t |t rt |dd n|}t | t rt | dd n| } t! | D d|||||||| |
| d
| t | j$ }
t | j& }| j( | j( nd }| j* | j* nd
}t- j. |
d | d |
d | d
| d| d|
|f||fg | j _ y )N) unk_tokenT)
clean_texthandle_chinese_chars
strip_accents lowercasez##)prefixFlstriprstrip)
do_lower_case bos_token eos_token sep_token cls_tokenr pad_token
mask_tokentokenize_chinese_charsr r z:0 $A:0 z:0z:0 z:0 $B:1 z:1)singlepairspecial_tokens )_vocabr r str
_tokenizerr BertNormalizer
normalizerr BertPreTokenizer
pre_tokenizerr decoderr
isinstancer
super__init__r" r! cls_token_id sep_token_idr TemplateProcessingpost_processor)selfr r r r r! r" r r# r$ r% r kwargscls_strsep_strr6 r7 __class__s ^/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/mpnet/tokenization_mpnet.pyr5 zMPNetTokenizer.__init__Y s; % 0eb $IdkkS^$TU &1%?%?!7'# &
" )7(G(G(I% #+"4"4D"A + JTT]_bIcJyuEir IST]_bIcJyuEir IST]_bIcJyuEir IST]_bIcJyuEir IST]_bIcJyuEir IST]_bIcJyuEir KUU_adJeZ
4Fku
' !#9'
dnn%dnn%,0,=,=,It((q ,0,=,=,It((q )3)F)F Yhwir29HWIS '"M,',' *
& returnc | j "| j rt j d yt | j S )a?
`str`: Mask token, to use when training a model with masked-language modeling. Log an error if used while not
having been set.
MPNet tokenizer has a special mask token to be usable in the fill-mask pipeline. The mask token will greedily
comprise the space before the **.
Nz(Using mask_token, but it is not set yet.) _mask_tokenverboseloggererrorr, )r: s r? r$ zMPNetTokenizer.mask_token s8 #|| GH4##$$r@ c R t |t rt |dd n|}|| _ y)z
Overriding the default behavior of the mask token to have it eat the space before it.
This is needed to preserve backward compatibility with all the previously used models based on MPNet.
TFr N)r3 r, r
rC )r: values r? r$ zMPNetTokenizer.mask_token s) AK5RU@V
5e<\a r@ ) NT