sgi d Z ddlZddlmZmZ ddlmZ ddlmZ ddl m
Z
e
j e Z
dd iZ G d
d e Zy) z Tokenization classes for Bloom. N)OptionalTuple )
BatchEncoding)PreTrainedTokenizerFast)loggingtokenizer_fileztokenizer.jsonc e Zd ZdZeZddgZdZ d fd Zde f fd Z
de f fd Z d
d e d
e
e dee fd Z xZS )BloomTokenizerFasta~
Construct a "fast" Bloom 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 BloomTokenizerFast
>>> tokenizer = BloomTokenizerFast.from_pretrained("bigscience/bloom")
>>> tokenizer("Hello world")["input_ids"]
[59414, 8876]
>>> tokenizer(" Hello world")["input_ids"]
[86153, 8876]
```
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`):
Path to the vocabulary file.
merges_file (`str`):
Path to the merges 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.
unk_token (`str`, *optional*, defaults to `<|endoftext|>`):
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.
bos_token (`str`, *optional*, defaults to `<|endoftext|>`):
The beginning of sequence token.
eos_token (`str`, *optional*, defaults to `<|endoftext|>`):
The end of sequence token.
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. (Bloom tokenizer detect beginning of words by the preceding space).
trim_offsets (`bool`, *optional*, defaults to `True`):
Whether or not the post-processing step should trim offsets to avoid including whitespaces.
input_idsattention_maskNc
t
| d||||||||| d |
t j | j j
} t j | j j } |r$| j dd } | j dd } t j | | j _ t j | | j _ || _ y )N)
vocab_file merges_filer unk_token bos_token eos_token pad_tokenadd_prefix_space clean_up_tokenization_spacess "add_prefix_space":falses "add_prefix_space": true )
super__init__pickledumpsbackend_tokenizer
pre_tokenizerdecoderreplaceloadsr )selfr r r r r r r r r kwargs
pre_tok_state
decoder_state __class__s d/var/www/html/venv/lib/python3.12/site-packages/transformers/models/bloom/tokenization_bloom_fast.pyr zBloomTokenizerFast.__init__X s
!#) -)E
T%;%;%I%IJ
T%;%;%C%CD
) 1 12MOj kM ) 1 12MOj kM/5||M/J ,)/ m)D & 0 returnc |j dd }| j s%|r#t 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.)getr Exceptionr% __name__r _batch_encode_plusr! argsr" r+ r% s r& r/ z%BloomTokenizerFast._batch_encode_plus~ sb $jj)> F%%-@*4>>+B+B*C D( (
w)4:6::r' c |j dd }| j s%|r#t d| j j d t | |i |S r* )r, r r- r% r. r _encode_plusr0 s r& r3 z BloomTokenizerFast._encode_plus sb $jj)> F%%-@*4>>+B+B*C D( (
w#T4V44r' save_directoryfilename_prefixc f | j j j || }t | S )N)name)
_tokenizermodelsavetuple)r! r4 r5 filess r& save_vocabularyz"BloomTokenizerFast.save_vocabulary s+ %%**>*PU|r' ) NNNzzzzFF)N)r.
__module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesmodel_input_namesslow_tokenizer_classr r r/ r3 strr r r=
__classcell__)r% s @r& r r s 2h *$&67
%*$1L;] ; 5} 5 c HSM ]bcf]g r' r )r@ r typingr r tokenization_utils_baser tokenization_utils_fastr utilsr
get_loggerr. loggerrA r r r' r& rM sH &
" 4 >
H %%'78 w 0 w r'