9i0<SSKJrJrJrJr SSKrSSKJr SSK J r SSK J r SSK JrJr SSKJr SSKJr SS KJrJr S /r\R0"\R2\R2S 9\R0"\R2\R4S 9"S S \555rg) )AnyDictOptionalUnionN) Pipelines)Model) OutputKeys)PipelineTensor) PIPELINES) Preprocessor) ModelFileTasksFillMaskPipeline) module_namec ^\rSrSrS S\\\4S\\S\S\4U4Sjjjr S\ \\ 4S\ \\ 44S jr S\ \\ 4S\ \\ 44S jrS rU=r$) rmodel preprocessor config_filedevicec >[T U]UUUUUURSS5URS05S9 [UR[ 5(dS[ R35eUc3[R"URR4UUS.UD6Ul URR5 [URS5(dS 5eg) aThe inference pipeline for all the fill mask sub-tasks. Args: model (`str` or `Model` or module instance): A model instance or a model local dir or a model id in the model hub. preprocessor (`Preprocessor`, `optional`): A Preprocessor instance. kwargs (dict, `optional`): Extra kwargs passed into the preprocessor's constructor. Examples: >>> from modelscope.pipelines import pipeline >>> pipeline_ins = pipeline('fill-mask', model='damo/nlp_structbert_fill-mask_english-large') >>> input = 'Everything in [MASK] you call reality is really [MASK] a reflection of your [MASK].' >>> print(pipeline_ins(input)) Examples: >>> from modelscope.pipelines import pipeline >>> pipeline_ins = pipeline('fill-mask', model='damo/nlp_ponet_fill-mask_english-base') >>> input = 'Everything in [MASK] you call reality is really [MASK] a reflection of your [MASK].' >>> print(pipeline_ins(input)) NOTE2: Please pay attention to the model's special tokens. If bert based model(bert, structbert, etc.) is used, the mask token is '[MASK]'. If the xlm-roberta(xlm-roberta, veco, etc.) based model is used, the mask token is ''. To view other examples please check tests/pipelines/test_fill_mask.py. compileFcompile_options)rrrr auto_collaterrz,please check whether model config exists in N)first_sequencesequence_lengthmask_idz9The input preprocessor should have the mask_id attribute.)super__init__pop isinstancerrr CONFIGURATIONr from_pretrained model_dirrevalhasattr) selfrrrrrrrkwargs __class__s k/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/modelscope/pipelines/nlp/fill_mask_pipeline.pyr FillMaskPipeline.__init__sJ %#%JJy%0"JJ'8"=  ?$**e,, U:9;R;R:S T U,   , < < $$!- /! !D     y   G F G inputsreturnc *UR"S0UDUD6$)N)r)r(r.forward_paramss r+forwardFillMaskPipeline.forwardRszz5F5n55r-cU[RR5R5R 5nU[R R5R5R 5n[ R"USS9n[ R"X0RR:HUU5n/nUH/nURRUSSS9nURU5 M1 [RU0$)aprocess the prediction results Args: inputs (Dict[str, Any]): The model outputs. The output should follow some rules: 1. Values can be retrieved by keys(dict-like, or the __getitem__ method is overriden) 2. 'logits' and 'input_ids' key exists. Models in modelscope will return the output dataclass `modelscope.outputs.FillMaskModelOutput`. Returns: Dict[str, str]: the prediction results )axisT)skip_special_tokensclean_up_tokenization_spaces)r LOGITSdetachcpunumpy INPUT_IDSnpargmaxwhererrdecodeappendTEXT) r(r.logits input_idspred_idsrst_ids pred_stringsids pred_strings r+ postprocessFillMaskPipeline.postprocessVs ))*113779??A://0779==?EEG 99V"-((9(9(9(A(AA8$& C++22$(-133K    , ..r-)r)NNgpuTsentence)__name__ __module__ __qualname____firstlineno__rrstrrr r rrr3r rL__static_attributes__ __classcell__)r*s@r+rrs9=$($" *!$9GeSj)9G' 59G"9G 9G9Gv6d38n6%)#s(^6/$sF{"3/S&[8I//r-)typingrrrrr=r?modelscope.metainformodelscope.modelsrmodelscope.outputsr modelscope.pipelines.baser r modelscope.pipelines.builderr modelscope.preprocessorsr modelscope.utils.constantrr__all__register_module fill_maskfill_mask_ponetrr1r-r+rds.-)#)6216   5?? 8K8KL  OO!:!:<[/x[/<M[/r-