tjr d Z ddlmZmZmZmZmZ ddlmZ ddl m
Z
ddl m Z e j
e Zddd d
Z G d d e
Zd gZd
S )z*Fast Tokenization class for model DeBERTa. )
AddedToken Tokenizerdecoderspre_tokenizers
processors)BPE )TokenizersBackend)loggingz
vocab.jsonz
merges.txtztokenizer.json)
vocab_file merges_filetokenizer_filec e Zd ZdZeZg dZeZ dd e e
e e f z dz d e e e z dz f fd
Z
ede fd Zej d Z xZS )DebertaTokenizera
Construct a "fast" DeBERTa tokenizer (backed by HuggingFace's *tokenizers* library). Based on byte-level
Byte-Pair-Encoding.
This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
be encoded differently whether it is at the beginning of the sentence (without space) or not:
```python
>>> from transformers import DebertaTokenizer
>>> tokenizer = DebertaTokenizer.from_pretrained("microsoft/deberta-base")
>>> tokenizer("Hello world")["input_ids"]
[1, 31414, 232, 2]
>>> tokenizer(" Hello world")["input_ids"]
[1, 20920, 232, 2]
```
You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer, but since
the model was not pretrained this way, it might yield a decrease in performance.
When used with `is_split_into_words=True`, this tokenizer needs to be instantiated with `add_prefix_space=True`.
This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should
refer to this superclass for more information regarding those methods.
Args:
vocab_file (`str`, *optional*):
Path to the vocabulary file.
merges_file (`str`, *optional*):
Path to the merges file.
tokenizer_file (`str`, *optional*):
The path to a tokenizer file to use instead of the vocab file.
errors (`str`, *optional*, defaults to `"replace"`):
Paradigm to follow when decoding bytes to UTF-8. See
[bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information.
bos_token (`str`, *optional*, defaults to `"[CLS]"`):
The beginning of sequence token.
eos_token (`str`, *optional*, defaults to `"[SEP]"`):
The end of sequence token.
sep_token (`str`, *optional*, defaults to `"[SEP]"`):
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 `"[CLS]"`):
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 `"[PAD]"`):
The token used for padding, for example when batching sequences of different lengths.
mask_token (`str`, *optional*, defaults to `"[MASK]"`):
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.
add_prefix_space (`bool`, *optional*, defaults to `False`):
Whether or not to add an initial space to the input. This allows to treat the leading word just as any
other word. (Deberta tokenizer detect beginning of words by the preceding space).
) input_idsattention_masktoken_type_idsNreplace[CLS][SEP][UNK][PAD][MASK]Fvocabmergesc
| | _ ||nLt | dt | dt | dt | dt |
di| _ |pg | _ t t | j | j d d ddd | _ d | j _ t j | | j _
t j | j _ t j d||||||| |
| d
| t j | j d | j | j d | j d | j d
| j | j | j f| j | j fg | j _ d S )Nr r F)r r dropout unk_tokencontinuing_subword_prefixend_of_word_suffixfuse_unk)add_prefix_space) errors bos_token eos_tokenr" sep_token cls_token pad_token
mask_tokenr& z $A z $B )singlepairspecial_tokens )r& str_vocab_mergesr r
_tokenizer
normalizerr ByteLevel
pre_tokenizerr decodersuper__init__r TemplateProcessingr+ r* cls_token_id sep_token_idpost_processor)selfr r r' r( r) r* r+ r" r, r- r& kwargs __class__s n/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/deberta/tokenization_deberta.pyr< zDebertaTokenizer.__init__a s !1
E IIIIJ
| # k| *,#%
&*"(6(@Rb(c(c(c%"*"4"6"6
! -
*4)Fn::$.::N]]]] ]]T^]] !23 !23 *
*
*
&&& returnc ~ | j #| j rt d dS t | 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.
Deberta tokenizer has a special mask token to be used in the fill-mask pipeline. The mask token will greedily
comprise the space before the *[MASK]*.
Nz(Using mask_token, but it is not set yet.) _mask_tokenverboseloggererrorr3 )rA s rD r- zDebertaTokenizer.mask_token sA #|
I GHHH44#$$$rE c f t |t rt |dd n|}|| _ dS )zg
Overriding the default behavior of the mask token to have it eat the space before it.
TF)lstriprstripN)
isinstancer3 r rH )rA values rD r- zDebertaTokenizer.mask_token s> AK5RU@V@Va
5e<<<<\a rE ) NNr r r r r r r r F)__name__
__module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesmodel_input_namesr modelr3 dictintlistr< propertyr- setter
__classcell__)rC s @rD r r s
> >@ *III E .2)- C
C
T#s(^#d*C
d3i$&C
C
C
C
C
C
J %C % % % X % ! ! ! ! ! ! !rE r N)rT
tokenizersr r r r r tokenizers.modelsr tokenization_utils_tokenizersr
utilsr
get_loggerrQ rJ rU r __all__r2 rE rD re s 1 0 R R R R R R R R R R R R R R ! ! ! ! ! ! > > > > > >
H % %#/ `pqq a! a! a! a! a!( a! a! a!H
rE