o
hT @ sV d Z ddlmZmZmZmZ ddlmZmZ ddl m
Z
e
e Z
G dd deZdS ) z" Tokenization class for Perceiver. )DictListOptionalTuple )
AddedTokenPreTrainedTokenizer)loggingc
s e Zd ZdZddgZ
d( d) fd
d
Zd eeef fddZ e
dd Z d*de e de
e e ded e e f fdd
Z d+de e de
e e d e e fddZded e e fd d Zd d Zd d! Zd"d# Zd+d$ed%e
e d ee fd&d'Z ZS ),PerceiverTokenizeraS
Construct a Perceiver tokenizer. The Perceiver simply uses raw bytes utf-8 encoding.
This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.
Args:
pad_token (`str`, *optional*, defaults to `"[PAD]"`):
The token used for padding, for example when batching sequences of different lengths.
bos_token (`str`, *optional*, defaults to `"[BOS]"`):
The BOS token (reserved in the vocab, but not actually used).
eos_token (`str`, *optional*, defaults to `"[EOS]"`):
The end of sequence token (reserved in the vocab, but not actually used).
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`.
mask_token (`str`, *optional*, defaults to `"[MASK]"`):
The MASK token, useful for masked language modeling.
cls_token (`str`, *optional*, defaults to `"[CLS]"`):
The CLS token (reserved in the vocab, but not actually used).
sep_token (`str`, *optional*, defaults to `"[SEP]"`):
The separator token, which is used when building a sequence from two sequences.
input_idsattention_mask[PAD][BOS][EOS][MASK][CLS][SEP] returnNc
s t |tr t|dddn|}t |trt|dddn|}t |tr(t|dddn|}t |tr6t|dddn|}t |trDt|dddn|}t |trRt|dddn|}d| _||||||d| _t| j| _t jd|||||||d| d S )NF)lstriprstrip )r r ) pad_token bos_token eos_token
mask_token cls_token sep_tokenmodel_max_length )
isinstancestrr _utf_vocab_size_added_tokens_decoderlen_num_special_tokenssuper__init__) selfr r r r r r! r" kwargs __class__r# j/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/perceiver/tokenization_perceiver.pyr+ < s4
zPerceiverTokenizer.__init__c C s: i }t | jD ]
}t|}|| j ||< q|| j |S N)ranger& chrr) updateadded_tokens_encoder)r, vocabitokenr# r# r0 get_vocabe s z PerceiverTokenizer.get_vocabc C s | j S r1 )r& )r, r# r# r0
vocab_sizem s z PerceiverTokenizer.vocab_sizeF token_ids_0 token_ids_1already_has_special_tokensc sf |r t j||ddS |du r dgdgt| dg S dgdgt| dg dgt| dg S )a
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer `prepare_for_model` method.
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not the token list is already formatted with special tokens for the model.
Returns:
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
T)r; r< r= Nr r )r* get_special_tokens_maskr( )r, r; r< r= r. r# r0 r> q s .z*PerceiverTokenizer.get_special_tokens_maskc C s< |du r| j g| | jg S | j g| | jg | | jg S )af
Build model inputs from a sequence or a pair of sequence for sequence classification tasks. A 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.
N) cls_token_id sep_token_id)r, r; r< r# r# r0 build_inputs_with_special_tokens s z3PerceiverTokenizer.build_inputs_with_special_tokenstextc C s dd | dD }|S )zPTake as input a string and return a list of strings (tokens) for words/sub-wordsc S s g | ]}t |qS r# )r3 ).0r7 r# r# r0
s z0PerceiverTokenizer._tokenize..utf-8)encode)r, rB tokensr# r# r0 _tokenize s z PerceiverTokenizer._tokenizec C s( t |dkr | j}|S t|| j }|S )z0Converts a token (str) in an id using the vocab.r )r( unk_token_idordr) )r, r8 token_idr# r# r0 _convert_token_to_id s
z'PerceiverTokenizer._convert_token_to_idc C s t || j }|S )z=Converts an index (integer) in a token (str) using the vocab.)r3 r) )r, indexr8 r# r# r0 _convert_id_to_token s z'PerceiverTokenizer._convert_id_to_tokenc C sP d}|D ]}|| j v rt|d}ntt|g}||7 }q|jddd}|S )z:Converts a sequence of tokens (string) in a single string. rE replace)errors)r5 r% rF bytesrJ decode)r, rG bstringr8
tok_stringstringr# r# r0 convert_tokens_to_string s
z+PerceiverTokenizer.convert_tokens_to_stringsave_directoryfilename_prefixc C s dS )Nr# r# )r, rX rY r# r# r0 save_vocabulary s z"PerceiverTokenizer.save_vocabulary)r
r r r r r r )r N)NFr1 )__name__
__module__ __qualname____doc__model_input_namesr+ r r% intr9 propertyr: r r boolr> rA rH rL rN rW r rZ
__classcell__r# r# r. r0 r
sN
)
(
r
N)r^ typingr r r r tokenization_utilsr r utilsr
get_loggerr[ loggerr
r# r# r# r0 s