U
,-eT @ 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 ZdZddgZd&d d fd
d
Zeeef d ddZ e
dd Z d'e e e
e e ee e d fdd
Zd(e e e
e e e e dddZee e ddd Zd d Zd d Zd!d" Zd)ee
e ee d#d$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.
Z input_idsZattention_mask[PAD][BOS][EOS][MASK][CLS][SEP] N)returnc
s t |trt|dddn|}t |tr4t|dddn|}t |trPt|dddn|}t |trlt|dddn|}t |trt|dddn|}t |trt|dddn|}d| _||||||d| _t| j| _t jf |||||||d| d S )NF)lstriprstrip )r r ) pad_token bos_token eos_token
mask_token cls_token sep_tokenmodel_max_length)
isinstancestrr _utf_vocab_sizeZ_added_tokens_decoderlen_num_special_tokenssuper__init__) selfr r r r r r r kwargs __class__ u/var/www/html/Darija-Ai-Train/env/lib/python3.8/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( Zvocabitokenr, r, r- get_vocabe s z PerceiverTokenizer.get_vocabc C s | j S r. )r# )r( r, r, r-
vocab_sizem s z PerceiverTokenizer.vocab_sizeF) token_ids_0 token_ids_1already_has_special_tokensr c sf |rt j||ddS |dkr8dgdgt| 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)r7 r8 r9 Nr r )r& get_special_tokens_maskr$ )r( r7 r8 r9 r* r, r- r: q s z*PerceiverTokenizer.get_special_tokens_mask)r7 r8 r c C s@ |dkr | j g| | jg S | j g| | jg | | jg S dS )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)Z cls_token_idZ sep_token_id)r( r7 r8 r, r, r- build_inputs_with_special_tokens s z3PerceiverTokenizer.build_inputs_with_special_tokens)textr c 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, )r0 ).0r3 r, r, r-
s z0PerceiverTokenizer._tokenize..utf-8)encode)r( r< tokensr, r, r- _tokenize s z PerceiverTokenizer._tokenizec C s& t |dkr| j}nt|| j }|S )z0Converts a token (str) in an id using the vocab.r )r$ Z unk_token_idordr% )r( r4 Ztoken_idr, r, r- _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.)r0 r% )r( indexr4 r, r, r- _convert_id_to_token s z'PerceiverTokenizer._convert_id_to_tokenc C sP d}|D ]4}|| j kr&t|d}ntt|g}||7 }q|jddd}|S )z:Converts a sequence of tokens (string) in a single string. r? replace)errors)r2 r" r@ bytesrC decode)r( rA bstringr4 Z
tok_stringstringr, r, r- convert_tokens_to_string s
z+PerceiverTokenizer.convert_tokens_to_string)save_directoryfilename_prefixr c C s dS )Nr, r, )r( rO rP r, r, r- save_vocabulary s z"PerceiverTokenizer.save_vocabulary)r r r
r r r r )NF)N)N)__name__
__module__ __qualname____doc__Zmodel_input_namesr' r r" intr5 propertyr6 r r boolr: r; rB rD rF rN r rQ
__classcell__r, r, r* r- r
sD
)
r
N)rU typingr r r r Ztokenization_utilsr r utilsr Z
get_loggerrR loggerr
r, r, r, r- s