+
jX < R t ^ RIt^ RIt^ RIt^ RIHt ^ RIt^ RIH t H
t
H t H t ^ RI
Ht ^RIHtHtHtHtHtHtHtHtHtHt ^RIHt ^RI H t H t H t ] P@ ! ]!4 t"]#]$]$3, t%]&]%, t'](t)]&]), t*Rt+R R
R R /t,R
t- ! R R]4 t.R.t/R# )z Tokenization classes for mLUKE.N)Mapping) Tokenizerdecoders normalizerspre_tokenizers)Unigram)
ENCODE_KWARGS_DOCSTRING
AddedToken
BatchEncoding EncodedInputPaddingStrategy
TensorType TextInput
TextInputPairTruncationStrategy to_py_obj)TokenizersBackend)add_end_docstringsis_torch_tensorlogging ▁
vocab_filezsentencepiece.bpe.modelentity_vocab_filezentity_vocab.jsonav
return_token_type_ids (`bool`, *optional*):
Whether to return token type IDs. If left to the default, will return the token type IDs according to
the specific tokenizer's default, defined by the `return_outputs` attribute.
[What are token type IDs?](../glossary#token-type-ids)
return_attention_mask (`bool`, *optional*):
Whether to return the attention mask. If left to the default, will return the attention mask according
to the specific tokenizer's default, defined by the `return_outputs` attribute.
[What are attention masks?](../glossary#attention-mask)
return_overflowing_tokens (`bool`, *optional*, defaults to `False`):
Whether or not to return overflowing token sequences. If a pair of sequences of input ids (or a batch
of pairs) is provided with `truncation_strategy = longest_first` or `True`, an error is raised instead
of returning overflowing tokens.
return_special_tokens_mask (`bool`, *optional*, defaults to `False`):
Whether or not to return special tokens mask information.
return_offsets_mapping (`bool`, *optional*, defaults to `False`):
Whether or not to return `(char_start, char_end)` for each token.
This is only available on fast tokenizers inheriting from [`PreTrainedTokenizerFast`], if using
Python's tokenizer, this method will raise `NotImplementedError`.
return_length (`bool`, *optional*, defaults to `False`):
Whether or not to return the lengths of the encoded inputs.
verbose (`bool`, *optional*, defaults to `True`):
Whether or not to print more information and warnings.
**kwargs: passed to the `self.tokenize()` method
Return:
[`BatchEncoding`]: A [`BatchEncoding`] with the following fields:
- **input_ids** -- List of token ids to be fed to a model.
[What are input IDs?](../glossary#input-ids)
- **token_type_ids** -- List of token type ids to be fed to a model (when `return_token_type_ids=True` or
if *"token_type_ids"* is in `self.model_input_names`).
[What are token type IDs?](../glossary#token-type-ids)
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
`return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names`).
[What are attention masks?](../glossary#attention-mask)
- **entity_ids** -- List of entity ids to be fed to a model.
[What are input IDs?](../glossary#input-ids)
- **entity_position_ids** -- List of entity positions in the input sequence to be fed to a model.
- **entity_token_type_ids** -- List of entity token type ids to be fed to a model (when
`return_token_type_ids=True` or if *"entity_token_type_ids"* is in `self.model_input_names`).
[What are token type IDs?](../glossary#token-type-ids)
- **entity_attention_mask** -- List of indices specifying which entities should be attended to by the model
(when `return_attention_mask=True` or if *"entity_attention_mask"* is in `self.model_input_names`).
[What are attention masks?](../glossary#attention-mask)
- **entity_start_positions** -- List of the start positions of entities in the word token sequence (when
`task="entity_span_classification"`).
- **entity_end_positions** -- List of the end positions of entities in the word token sequence (when
`task="entity_span_classification"`).
- **overflowing_tokens** -- List of overflowing tokens sequences (when a `max_length` is specified and
`return_overflowing_tokens=True`).
- **num_truncated_tokens** -- Number of tokens truncated (when a `max_length` is specified and
`return_overflowing_tokens=True`).
- **special_tokens_mask** -- List of 0s and 1s, with 1 specifying added special tokens and 0 specifying
regular sequence tokens (when `add_special_tokens=True` and `return_special_tokens_mask=True`).
- **length** -- The length of the inputs (when `return_length=True`)
c a a ] tR t^t oRt]tRR.tR,V3R lV 3R llltV 3R lt ]
R 4 t R t R
t
R tR tR-V3R lR llt]! ]]4 R.V3R lV 3R lll4 tRRRRRR]P, ]P0 RR^ R
RRRRRR
R
R
R
R3V3R lV 3R llltRRR]P, ]P0 RR^ R
RRRRRR
R
R
R
R3V3R lV 3R llltV3R lR ltR/V3R lR llt ]! ]]4 R]P, ]P0 RR^ RRRRRR
R
R
R3V3R lR ll4 t ]! ]]4 R0V3R lR ll4 t R1V3R lR llt RR]P, RRR3V3R! lR" llt R2V3R# lR$ llt!R2V3R% lR& llt"R3V3R' lV 3R( lllt#R2V3R) lR* llt$R+t%Vt&V ;t'# )4MLukeTokenizera
Adapted from [`XLMRobertaTokenizer`] and [`LukeTokenizer`]. Based on
[SentencePiece](https://github.com/google/sentencepiece).
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:
vocab_file (`str`):
Path to the vocabulary file.
entity_vocab_file (`str`):
Path to the entity vocabulary file.
bos_token (`str`, *optional*, defaults to `""`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
When building a sequence using special tokens, this is not the token that is used for the beginning of
sequence. The token used is the `cls_token`.
eos_token (`str`, *optional*, defaults to `""`):
The end of sequence token.
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`.
sep_token (`str`, *optional*, defaults to `""`):
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 `""`):
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 `""`):
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 `""`):
The token used for padding, for example when batching sequences of different lengths.
mask_token (`str`, *optional*, defaults to `""`):
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.
task (`str`, *optional*):
Task for which you want to prepare sequences. One of `"entity_classification"`,
`"entity_pair_classification"`, or `"entity_span_classification"`. If you specify this argument, the entity
sequence is automatically created based on the given entity span(s).
max_entity_length (`int`, *optional*, defaults to 32):
The maximum length of `entity_ids`.
max_mention_length (`int`, *optional*, defaults to 30):
The maximum number of tokens inside an entity span.
entity_token_1 (`str`, *optional*, defaults to ``):
The special token used to represent an entity span in a word token sequence. This token is only used when
`task` is set to `"entity_classification"` or `"entity_pair_classification"`.
entity_token_2 (`str`, *optional*, defaults to ``):
The special token used to represent an entity span in a word token sequence. This token is only used when
`task` is set to `"entity_pair_classification"`.
additional_special_tokens (`list[str]`, *optional*, defaults to `["NOTUSED", "NOTUSED"]`):
Additional special tokens used by the tokenizer.
sp_model_kwargs (`dict`, *optional*):
Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
to set:
- `enable_sampling`: Enable subword regularization.
- `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.
- `nbest_size = {0,1}`: No sampling is performed.
- `nbest_size > 1`: samples from the nbest_size results.
- `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
using forward-filtering-and-backward-sampling algorithm.
- `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
BPE-dropout.
Attributes:
sp_model (`SentencePieceProcessor`):
The *SentencePiece* processor that is used for every conversion (string, tokens and IDs).
input_idsattention_maskNc < V ^8 d QhRS[ S[, S[, R, RS[ S[, S[, R, RR/# ) vocabN entity_vocabreturn)strdictlist)format
__classdict__s "m/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/mluke/tokenization_mluke.py __annotate__MLukeTokenizer.__annotate__ sL n n$ TzD 4'%n& Dj4'$.'n*
+n c
< \ V\ 4 ' d \ VR RR7 MTp\ V \ 4 ' d \ V RRR7 MT p \ V \ 4 ' d \ V RRR7 MT p VP RR4 pVf RV9 d VP R4 pVf RV9 d VP R4 p\ V\ 4 ' dC V UUu. uF w ppV\ V4 3NK uppV n \ V P 4 V n M"Ve VV n ^ V n MR..V n ^ V n \ \ V P ^ R7 4 V n \ P ! \ P ! R R
4 \ P ! R R
4 .4 V P n \ P" ! R R
R7 V P n \& P" ! R R
R7 V P n R^ R^R^R^/V n ^V n V P V P, , V P* R& V P* P/ 4 UUu/ uF w ppVVbK uppV n Ve VV n MMVe; \5 VRR7 ;_uu_ 4 p\6 P8 ! V4 V n RRR4 MV
^ V^V^V^/V n WVV3 F# pVV P2 9 g K \; RV R24 h V P2 V
, V n V P2 V, V n V P2 V, V n V P2 V, V n! Wn" Ve VR8X d Wn# M-VR8X d ^V n# M VR8X d ^V n# M\; RV R24 hWn$ . pR/ Fn p VP V R4 p \ V \ \J 34 ' g K3 V F5 pTPM \ V\N 4 ' d \ R0/ VB MT4 K7 Kp V Uu0 uF p\ V4 kK p pW3 F9 p\ V4 p V V 9 g K VPM V4 V PQ V 4 K; WVV3 F< pVV 9 g K VPM \ VRRRR R 7 4 V PQ V4 K> VVR & \R S V ` ! R0/ R VbR VbR VbR!VbR"VbR#VbR$VbR%VbR&V bR'V
bR(\ V 4 bR)\ V 4 bR*V
bR+VbR,VbR-VbRVf TMRbVB V PW 4 R# u uppi u uppi + ' g i EL{; iu upi )1TF)lstriprstripr Nr r )unk_idz``"z''r always) replacementprepend_schemez;^ v;^<64bfghbimpqtmubu;^ v9K'c9KtTUwZ]^aZbOb9K $'c $4 5 5 C
Oc:J6K$K K CG#@ ! * ),O(U)(U Aw#h-/ F(U & )
CZ0vBY$]abc]dhklthu]uBY-0v C(=$>> $O(?.0HI(# V *&1
s v
'+E%,='>?XAXAX'Y $0G0G#0MPU0U(VV +22<@.55e<,33C!G< '2 ( 5HN0 1yy 88;Q 789M 56$;<#NS_D`@a:a 67
33N;4OQ[]de 9 9 9=R !XX %"3(..#5 )&; & N '*>++F'GN8 $% K]
s w'c)
1ws0 V:3V: W W 0 WW W <W c < V ^8 d QhRS[ S[S[ , , S[S[S[3, , S[S[S[S[, 3, , S[S[S[S[3, , , RS[S[, S[, RS[R, RS[R, RS[R, RS[R, RS[R, R S[S[, R, R
S[R S[ /
# ) r rQ r r NrJ r r r r r r! ) r
r$ r# r" r r r r r
)r% r& s "r' r( r) s s `H `H%
}
sL
!" sD &&
'( tC %&
' (`H o-`H $J`H :`H $J`H Dj`H $d{`H j(4/`H `H
`Hr* c
( a \ V\ \ 34 ' d\ \ V^ , \ 4 ' d? V^ , P 4 U
U u/ uF qV U u. uF qV
, NK
up bK pp
p V P
^ , V9 d: \
RV P
^ , R\ VP 4 4 24 hWP
^ , , p V ' g V' d . VR& V# V ^ , p
\ V
\ \ 34 ' dC ^ p\ W, 4 ^ 8X d V^,
pK! V\ V 4 8 d W, ^ , p
\ V
\ \ \ 34 ' g \ V
4 ' d
Vf RMTpMD\ V
\ P 4 ' d
Vf RMTpM\
RV
R\ V
4 R24 hVP 4 F w r\ V4 W& K V P W#V R 7 w ppppVf
V P pWP
^ , , p V ' dH \ V ^ , \ \ 34 ' g% V P# VVVVVVVR
7 p\% WR 7 # \ V 4 o\& ;QJ d- V3R lVP) 4 4 F ' g K R
M" RM ! V3R lVP) 4 4 4 ' d \
R4 hV\* P, 8X dE \/ R V 4 4 pRV9 d \/ R VR, 4 4 M^ p\* P0 p/ p\3 S4 F pVP 4 UUu/ uF w ppVVV, bK pppV P# VVVVVVVR
7 pVP 4 F) w rV
V9 d . VV
& VV
, P5 V4 K+ K \% VVR 7 # u up i u up p
i u uppi )a
Pad a single encoded input or a batch of encoded inputs up to predefined length or to the max sequence length
in the batch. Padding side (left/right) padding token ids are defined at the tokenizer level (with
`self.padding_side`, `self.pad_token_id` and `self.pad_token_type_id`) .. note:: If the `encoded_inputs` passed
are dictionary of numpy arrays or PyTorch tensors the result will use the same type unless
you provide a different tensor type with `return_tensors`. In the case of PyTorch tensors, you will lose the
specific device of your tensors however.
Args:
encoded_inputs ([`BatchEncoding`], list of [`BatchEncoding`], `dict[str, list[int]]`, `dict[str, list[list[int]]` or `list[dict[str, list[int]]]`):
Tokenized inputs. Can represent one input ([`BatchEncoding`] or `dict[str, list[int]]`) or a batch of
tokenized inputs (list of [`BatchEncoding`], *dict[str, list[list[int]]]* or *list[dict[str,
list[int]]]*) so you can use this method during preprocessing as well as in a PyTorch Dataloader
collate function. Instead of `list[int]` you can have tensors (numpy arrays, or PyTorch tensors),
see the note above for the return type.
padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`):
Select a strategy to pad the returned sequences (according to the model's padding side and padding
index) among:
- `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
sequence if provided).
- `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
acceptable input length for the model if that argument is not provided.
- `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
lengths).
max_length (`int`, *optional*):
Maximum length of the returned list and optionally padding length (see above).
max_entity_length (`int`, *optional*):
The maximum length of the entity sequence.
pad_to_multiple_of (`int`, *optional*):
If set will pad the sequence to a multiple of the provided value. This is especially useful to enable
the use of Tensor Cores on NVIDIA hardware with compute capability `>= 7.5` (Volta).
padding_side:
The side on which the model should have padding applied. Should be selected between ['right', 'left'].
Default value is picked from the class attribute of the same name.
return_attention_mask (`bool`, *optional*):
Whether to return the attention mask. If left to the default, will return the attention mask according
to the specific tokenizer's default, defined by the `return_outputs` attribute. [What are attention
masks?](../glossary#attention-mask)
return_tensors (`str` or [`~utils.TensorType`], *optional*):
If set, will return tensors instead of list of python integers. Acceptable values are:
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return Numpy `np.ndarray` objects.
verbose (`bool`, *optional*, defaults to `True`):
Whether or not to print more information and warnings.
zRYou should supply an encoding or a list of encodings to this method that includes z, but you provided r ptnpztype of z
unknown: z6. Should be one of a python, numpy, or pytorch object.)r r r )r rJ r r r r r. c 3 @ <" T F p\ V4 S8g x K R # 5ir rX ).0rx
batch_sizes & r' %MLukeTokenizer.pad.. s E-Ds1v#-Ds TFzLSome items in the output dictionary have a different batch size than others.c 3 8 " T F p\ V4 x K R # 5ir rj rk inputss & r' rm rn s F~VS[[~ r c 3 8 " T F p\ V4 x K R # 5ir rj rp s & r' rm rn s K.JFCKK.Jrr )rT r$ rm r keysrF rh rX r r rh ndarraytyperc r r rJ _padr
anyvaluesr LONGESTmax
MAX_LENGTHr rn )rs rQ r r rJ r r r r r r| examplerequired_input
first_elementr r r _r r rw rx rq r3 rl s &&&&&&&&&& @r' r1 MLukeTokenizer.pads s B ntUm 4 4NSTDUW^9_9_[ijk[l[q[q[s t[sTW#OWCLL#O O[sN t ! !! $N : !!%!7!7!: ;;NtTbTgTgTiOjNkm
((>(>q(AB $35 /0! ! 'q)
mdE] 3 3En+,1
s>** . 5a 8
-#tU);<< }--)7)?^M2::66)7)?^ }oZ]8K7L MK K
- 2 2 4
&/&6# 5 .2-T-TG .U .
*!Z $ $ 6 6 '(>(>q(AB *^A->u
"N"N !YY %"3!1#5 )&; ' N ! L L (
3E^-B-B-DE333E^-B-B-DE E E kl l 6 6 6 F~ FFJO[_mOmKn\.JKKst
/ 9 9
z"A*8*>*>*@A*@$!Qa1g*@FAii%"3!1#5 )&; G &mmo
m+)+M#& c"))%0 . #" ]GG{ $P tZ Bs P P/PPPc < V ^8 d QhRS[ S[S[3, S[, RS[R, RS[R, RS[RS[R, RS[R, RS[R, R S[ /# )
r rQ r NrJ r r r r r! )r# r" r r
r r r )r% r& s "r' r( r) s N N S, ./-?N $JN : N
* N $J
N DjN $d{N
N r* c \ RV9 4 pVf RV P 9 pV\ P 8X d- \ VR, 4 pV' d \ VR, 4 pVe( Ve$ W%, ^ 8w d W%, ^, V, pV' d, Ve( Ve$ W5, ^ 8w d W5, ^, V, pV\ P
8g ;' d= \ VR, 4 V8g ;' g T;' d \ VR, 4 V8g p V' d% RV9 d ^.\ VR, 4 , VR& V' d- V' d% RV9 d ^.\ VR, 4 , VR& V ' Edb V\ VR, 4 ,
p
Ve TM V P pV' d V\ VR, 4 ,
p VR8X Edv V' d? VR, ^ .V
, , VR& V' d VR, ^ .X , , VR& RV9 d? VR, ^ .V
, , VR& V' d VR, ^ .X , , VR& RV9 d VR, ^.V
, , VR& VR, V P .V
, , VR& V' d VR, V P .X , , VR& VR , R.V P , .V , , VR & V P R
8X d7 VR , ^ .V , , VR & VR , ^ .V , , VR & V# VR
8X Edv V' d? ^ .V
, VR, , VR& V' d ^ .X , VR, , VR& RV9 d? ^ .V
, VR, , VR& V' d ^ .X , VR, , VR& RV9 d ^.V
, VR, , VR& V P .V
, VR, , VR& V' d V P .X , VR, , VR& R.V P , .V , VR , , VR & V P R
8X d7 ^ .V , VR , , VR & ^ .V , VR , , VR & V# \ R\ V4 , 4 hV# )a
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
Args:
encoded_inputs:
Dictionary of tokenized inputs (`list[int]`) or batch of tokenized inputs (`list[list[int]]`).
max_length: maximum length of the returned list and optionally padding length (see below).
Will truncate by taking into account the special tokens.
max_entity_length: The maximum length of the entity sequence.
padding_strategy: PaddingStrategy to use for padding.
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
- PaddingStrategy.DO_NOT_PAD: Do not pad
The tokenizer padding sides are defined in self.padding_side:
- 'left': pads on the left of the sequences
- 'right': pads on the right of the sequences
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
`>= 7.5` (Volta).
padding_side:
The side on which the model should have padding applied. Should be selected between ['right', 'left'].
Default value is picked from the class attribute of the same name.
return_attention_mask:
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
r r r entity_attention_maskrightr8 rB r< r? r; r@ rA leftzInvalid padding strategy:rD )
r rF r rz rX r0 r pad_token_idrj rK rI rh r" ) rs rQ r rJ r r r r entities_providedneeds_to_be_padded
differenceentity_differences &&&&&&&& r' rw MLukeTokenizer._pad s P ! !? @ ! ($48N8N$N ! 6 6 6 ^K 89J $'|(D$E! !&8&D*JimnJn%;q@DVVJ
!-"."71<"3"IQ!NRd d - 1K1K K
{+ ,
:
^
^!\\c. *F&GK\&\ !%5^%K01sS 9T5U/UN+ , !6;RZh;h78cC|@\<]6]N2 3 #c.*E&FFJ+7+C<IZIZL $5N<? $~57EFV7W[\Z]`jZj7jN#34( *+B CqcL]F] ] ''>? )N: X `
- pair of sequences: ` A B `
Args:
token_ids_0 (`list[int]`):
List of IDs to which the special tokens will be added.
token_ids_1 (`list[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`list[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
)r r )rs r r clsseps &&& r' rI /MLukeTokenizer.build_inputs_with_special_tokens se ( %%&48I8I7JJ J ! ! 3&,{:S@@r* c p < V ^8 d QhRS[ S[, RS[ S[, R, RS[RS[ S[, /# )r r r Nalready_has_special_tokensr! )r$ r r )r% r& s "r' r( r) sD X X 9X379t3CXhlX
cXr* c < V' d \ SV ` WRR7 # Vf$ ^.^ .\ V4 , , ^., # ^.^ .\ V4 , , ^^., ^ .\ V4 , , ^., # )ad
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 )rp rK rX )rs r r r r s &&&&r' rK &MLukeTokenizer.get_special_tokens_mask s & &72 ']a 3
31#K 001QC7 7sqcC ,,-A61#K@P:PQUVTWWWr* c j < V ^8 d QhRS[ S[, RS[ S[, R, RS[ S[, /# r r )r% r& s "r' r( r) s; L L 9L379t3CL
cLr* c V P .pV P .pVf! \ WA, V, 4 ^ ., # \ WA, V, V, V, V, 4 ^ ., # )a
Create a mask from the two sequences passed to be used in a sequence-pair classification task. XLM-RoBERTa does
not make use of token type ids, therefore a list of zeros is returned.
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 zeros.
)r r rX )rs r r r r s &&& r' rJ 3MLukeTokenizer.create_token_type_ids_from_sequences si $ ! ! s(3./1#5 53$s*S0;>DEKKr* )rZ rW rY rl rk rj ri r rd rb ra rJ rK rI )r4 r6 r6 r4 r. r5 r7 N zzz[UNK]z[PAD]z[MASK]z[MASK2]NN)F)NNNNNTFNNN FNNNNNFFFFT)NNNNN)NNNNNTFNNNr NNNNNFFFFTF)TNNNNNNTr )NF)(__name__
__module__ __qualname____firstlineno____doc__r vocab_files_namesrF rq rr propertyr r r r r r r r 'ENCODE_PLUS_ADDITIONAL_KWARGS_DOCSTRINGr r r0 r rG r r r r r r r1 rw r rI rK rJ __static_attributes____classdictcell__
__classcell__)r r& s @@r' r r sI Rh *$&67n n`
0 : :
]>
/1XY| | Z|B '+/348'+,0#',;,F,F2D2T2T!%(,+0)-#'26-1-1*/+0', # 1m
m
h mq#',;,F,F2D2T2T!%(,+0)-#'26-1-1*/+0', # /M, M,^o o$V
V
p /1XY $(,;,F,F2D2T2T!%(,)-#'%)-1-1*/+0 # 'R R ZR h /1XYe e Ze N`H `HJ "&(,,;,F,F)-#'-1N N `$ $"A A4X X8L L Lr* r )0r r rf r collections.abcr numpyrh r r r r r tokenizers.modelsr tokenization_utils_baser r r
r r r
r r r r tokenization_utils_tokenizersr utilsr r r
get_loggerr rL rm r
EntitySpanr$ r r" Entityr r r r r __all__rS r* r' r s & # G G % ? A A
H %
38_
z" 6l !#<>QSfg I+ 'XBL& BLJ4
r*