sgw d Z ddlZddlmZmZ ddlmZ ddlmZ ddl m
Z
ddl m Z d d
l
mZ e j e Zd d d
dZ G d de
Zy)z$Tokenization classes for OpenAI GPT. N)OptionalTuple)pre_tokenizers )
BatchEncoding)PreTrainedTokenizerFast)logging )
GPT2Tokenizerz
vocab.jsonz
merges.txtztokenizer.json)
vocab_file merges_filetokenizer_filec e Zd ZdZeZddgZeZ d fd Z de
f fd Z de
f fd Z d de
d ee
dee
fd
Z xZS )
GPT2TokenizerFasta
Construct a "fast" GPT-2 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 GPT2TokenizerFast
>>> tokenizer = GPT2TokenizerFast.from_pretrained("openai-community/gpt2")
>>> tokenizer("Hello world")["input_ids"]
[15496, 995]
>>> tokenizer(" Hello world")["input_ids"]
[18435, 995]
```
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*):
Path to [tokenizers](https://github.com/huggingface/tokenizers) file (generally has a .json extension) that
contains everything needed to load the tokenizer.
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. (GPT2 tokenizer detect beginning of words by the preceding space).
input_idsattention_maskc ~ t | d|||||||d| |j dd | _ t j
| j j j } | j d| |k7 r;t t | j d }
|| d< |
di | | j _ || _ y )N)r r
r unk_token bos_token eos_tokenadd_prefix_space
add_bos_tokenFr type )
super__init__popr jsonloadsbackend_tokenizer
pre_tokenizer __getstate__getgetattrr r ) selfr r
r r r r r kwargs
pre_tok_state
pre_tok_class __class__s b/var/www/html/venv/lib/python3.12/site-packages/transformers/models/gpt2/tokenization_gpt2_fast.pyr zGPT2TokenizerFast.__init__X s
!#) -
$ZZ ?
4#9#9#G#G#T#T#VW
/1A BFV V #NM4E4Ef4M NM0@M, -3@3Q=3QD " " 0 0 returnc |j dd }| j s!|r J d| j j d t | |i |S Nis_split_into_wordsFzYou need to instantiate z? with add_prefix_space=True to use it with pretokenized inputs.)r# r r) __name__r _batch_encode_plusr% argsr& r/ r) s r* r1 z$GPT2TokenizerFast._batch_encode_plusx sb $jj)> F$$,?
&t~~'>'>&? @2
2
?
w)4:6::r+ c |j dd }| j s!|r J d| j j d t | |i |S r. )r# r r) r0 r _encode_plusr2 s r* r5 z GPT2TokenizerFast._encode_plus sb $jj)> F$$,?
&t~~'>'>&? @2
2
?
w#T4V44r+ save_directoryfilename_prefixc f | j j j || }t | S )N)name)
_tokenizermodelsavetuple)r% r6 r7 filess r* save_vocabularyz!GPT2TokenizerFast.save_vocabulary s+ %%**>*PU|r+ )NNN
<|endoftext|>r@ r@ F)N)r0
__module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesmodel_input_namesr slow_tokenizer_classr r r1 r5 strr r r?
__classcell__)r) s @r* r r ! s} 0d *$&67( !!! 1@;] ;5} 5 c HSM ]bcf]g r+ r )rC r typingr r
tokenizersr tokenization_utils_baser tokenization_utils_fastr utilsr tokenization_gpt2r
get_loggerr0 loggerrD r r r+ r* rR sP + " % 4 > ,
H %#/ `pq l / l r+