sg) d Z ddlZddlmZmZmZ ddlmZ ddlm Z m
Z
ddl m Z ddl
mZ d d
lmZ ej" e Zd d d
dZ G d de Zy)z*Fast Tokenization class for model DeBERTa. N)ListOptionalTuple)pre_tokenizers )
AddedToken
BatchEncoding)PreTrainedTokenizerFast)logging )DebertaTokenizerz
vocab.jsonz
merges.txtztokenizer.json)
vocab_file merges_filetokenizer_filec ( e Zd ZdZeZg dZeZ d fd Z e
de fd Z e j d Z ddee deee dee fd Z ddee deee dee fd
Zdef fd Zdef fd Zdd
e dee dee fdZ xZS )DebertaTokenizerFasta
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 DebertaTokenizerFast
>>> tokenizer = DebertaTokenizerFast.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_idsc
t | ||f||||| |||
| | d
|
|
j dd | _ t j
| j j j }|j d| | k7 r;t t |j d }| |d< |di || j _ | | _ y )N)
r errors bos_token eos_token unk_token sep_token cls_token pad_token
mask_tokenadd_prefix_space
add_bos_tokenFr type )
super__init__popr jsonloadsbackend_tokenizer
pre_tokenizer __getstate__getgetattrr r )selfr r r r r r r r r r r r kwargs
pre_tok_state
pre_tok_class __class__s h/var/www/html/venv/lib/python3.12/site-packages/transformers/models/deberta/tokenization_deberta_fast.pyr$ z DebertaTokenizerFast.__init__f s
* ! -
$ZZ ?
4#9#9#G#G#T#T#VW
/1A BFV V #NM4E4Ef4M NM0@M, -3@3Q=3QD " " 0 0 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.
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_tokenverboseloggererrorstr)r- s r2 r z DebertaTokenizerFast.mask_token s8 #|| GH4##$$r3 c R t |t rt |dd n|}|| _ y)zg
Overriding the default behavior of the mask token to have it eat the space before it.
TF)lstriprstripN)
isinstancer: r r6 )r- values r2 r z DebertaTokenizerFast.mask_token s) AK5RU@V
5e<\a r3 token_ids_0 token_ids_1c | | j g|z | j gz S | j g}| j g}||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. A DeBERTa sequence has the following format:
- single sequence: [CLS] X [SEP]
- pair of sequences: [CLS] A [SEP] B [SEP]
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@ rA clsseps r2 build_inputs_with_special_tokensz5DebertaTokenizerFast.build_inputs_with_special_tokens sb & %%&48I8I7JJ J ! ![ 3&4s::r3 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. A DeBERTa
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 |
```
If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s).
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 )rD rC len)r- r@ rA rF rE s r2 $create_token_type_ids_from_sequencesz9DebertaTokenizerFast.create_token_type_ids_from_sequences st . ! ! s[(3./1#5 53$s*+qc1C c8I4JaS4PPPr3 c |j dd }| j s!|r J d| j j d t | |i |S Nis_split_into_wordsFzYou need to instantiate z? with add_prefix_space=True to use it with pretokenized inputs.)r+ r r1 __name__r# _batch_encode_plusr- argsr. rM r1 s r2 rO z'DebertaTokenizerFast._batch_encode_plus sb $jj)> F$$,?
&t~~'>'>&? @2
2
?
w)4:6::r3 c |j dd }| j s!|r J d| j j d t | |i |S rL )r+ r r1 rN r# _encode_plusrP s r2 rS z!DebertaTokenizerFast._encode_plus sb $jj)> F$$,?
&t~~'>'>&? @2
2
?
w#T4V44r3 save_directoryfilename_prefixc f | j j j || }t | S )N)name)
_tokenizermodelsavetuple)r- rT rU filess r2 save_vocabularyz$DebertaTokenizerFast.save_vocabulary s+ %%**>*PU|r3 ) NNNreplace[CLS][SEP]r` r_ z[UNK]z[PAD]z[MASK]F)N)rN
__module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesmodel_input_namesr
slow_tokenizer_classr$ propertyr: r setterr intr rG rJ r rO rS r r]
__classcell__)r1 s @r2 r r ! s) >@ *I+ '1R %C % % ! ! JN; 9;3;DI3F;
c;4 JN Q 9 Q3;DI3F Q
c Q>;] ;5} 5 c HSM ]bcf]g r3 r )rc r& typingr r r
tokenizersr tokenization_utils_baser r tokenization_utils_fastr
utilsr tokenization_debertar
get_loggerrN r8 rd r r" r3 r2 rs sS 1 ( ( % @ > 2
H %#/ `pq V 2 V r3