9i%1SSKrSSKJr SSKrSSKJr SSKJr SSKJr SSK J r SSK J r SSK Jr SSKJr S S KJrJr S S KJr \R."5r"S S \R05r"SS\R05r"SS\R05r"SS\R05r\ R:"\R<\R>S9"SS\55r g)N)CrossEntropyLoss)ACT2FN)Models)MODELS)AttentionFillMaskModelOutput)logger)Tasks) SbertModelSbertPreTrainedModel) SbertConfigc.^\rSrSrU4SjrSrSrU=r$)SbertPredictionHeadTransform#cp>[TU]5 [R"URUR5Ul[ UR[5(a[URUl OURUl [R"URURS9Ul g)N)eps) super__init__nnLinear hidden_sizedense isinstance hidden_actstrrtransform_act_fn LayerNormlayer_norm_epsselfconfig __class__s j/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/modelscope/models/nlp/structbert/fill_mask.pyr%SbertPredictionHeadTransform.__init__%s YYv1163E3EF f'' - -$*6+<+<$=D !$*$5$5D !   F$9$9;clURU5nURU5nURU5nU$N)rrrr hidden_statess r#forward$SbertPredictionHeadTransform.forward/s4 =1 --m< }5 r%)rrr__name__ __module__ __qualname____firstlineno__rr*__static_attributes__ __classcell__r"s@r#rr#s;r%rc.^\rSrSrU4SjrSrSrU=r$)SbertLMPredictionHead6c>[TU]5 [U5Ul[R "UR UR5Ulgr') rrr transformrrr vocab_sizedecoderrs r#rSbertLMPredictionHead.__init__8s: 5f=yy!3!3V5F5FG r%cJURU5nURU5nU$r')r8r:r(s r#r*SbertLMPredictionHead.forward@s$}5  ]3 r%)r:r8r,r3s@r#r5r56sHr%r5c.^\rSrSrU4SjrSrSrU=r$)SbertOnlyMLMHeadFcB>[TU]5 [U5Ulgr')rrr5 predictionsrs r#rSbertOnlyMLMHead.__init__Hs 08r%c(URU5nU$r'rB)r sequence_outputprediction_scoress r#r*SbertOnlyMLMHead.forwardLs ,,_=  r%rEr,r3s@r#r?r?Fs9!!r%r?c.^\rSrSrU4SjrSrSrU=r$)SbertPreTrainingHeadsQc>[TU]5 [U5Ul[R "UR S5Ulg)N)rrr5rBrrrseq_relationshiprs r#rSbertPreTrainingHeads.__init__Ss4 08 " &*<*`__ subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. Preprocessor: This is the fill_mask model of StructBERT, the preprocessor of this model is `modelscope.preprocessors.FillMaskTransformersPreprocessor`. Parameters: config (:class:`~modelscope.models.nlp.structbert.SbertConfig`): Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights. pooler position_idszpredictions.decoder.biasr!c >[TU]U5 UR(a[R S5 [ U5Ul[U5UlUR5 g)NzlIf you want to use `SbertForMaskedLM` make sure `config.is_decoder=False` for bi-directional self-attention.) rr is_decoderrwarningr bertr?cls init_weights)r r!kwargsr"s r#rSbertForMaskedLM.__init__{sP     NN1 2v& #F+ r%cBURRR$r'r_rBr:)r s r#get_output_embeddings&SbertForMaskedLM.get_output_embeddingssxx##+++r%c8XRRlgr'rd)r new_embeddingss r#set_output_embeddings&SbertForMaskedLM.set_output_embeddingss'5$r%c U bU OURRn URUUUUUUUUU U U S9 n U SnURU5nSnU bF[ 5nU"UR SURR 5U R S55nU (dU4U SS-nUbU4U-$U$[UUU RU RUS9$)u Args: input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`): Indices of input sequence tokens in the vocabulary. Indices can be obtained using :class:`~modelscope.models.nlp.structbert.SbertTokenizer`. See :meth:`transformers.PreTrainedTokenizer.encode` and :meth:`transformers.PreTrainedTokenizer.__call__` for details. `What are input IDs? <../glossary.html#input-ids>`__ attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Mask to avoid performing attention on padding token indices. Mask values selected in ``[0, 1]``: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. `What are attention masks? <../glossary.html#attention-mask>`__ token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Segment token indices to indicate first and second portions of the inputs. Indices are selected in ``[0, 1]``: - 0 corresponds to a `sentence A` token, - 1 corresponds to a `sentence B` token. `What are token type IDs? <../glossary.html#token-type-ids>`_ position_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Indices of positions of each input sequence tokens in the position embeddings. Selected in the range ``[0, config.max_position_embeddings - 1]``. head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`): Mask to nullify selected heads of the self-attention modules. Mask values selected in ``[0, 1]``: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`): Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert :obj:`input_ids` indices into associated vectors than the model's internal embedding lookup matrix. output_attentions (:obj:`bool`, `optional`): Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned tensors for more detail. output_hidden_states (:obj:`bool`, `optional`): Whether or not to return the hidden states of all layers. See ``hidden_states`` under returned tensors for more detail. return_dict (:obj:`bool`, `optional`): Whether or not to return a :class:`~transformers.ModelOutput` instead of a plain tuple. labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Labels for computing the masked language modeling loss. Indices should be in ``[-100, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring) Tokens with indices set to ``-100`` are ignored (masked), the loss is only computed for the tokens with labels in ``[0, ..., config.vocab_size]`` Returns: Returns `modelscope.outputs.AttentionFillMaskModelOutput` Examples: >>> from modelscope.models import Model >>> from modelscope.preprocessors import Preprocessor, FillMaskTransformersPreprocessor >>> model = Model.from_pretrained('damo/nlp_structbert_fill-mask_chinese-large') >>> preprocessor = FillMaskTransformersPreprocessor('damo/nlp_structbert_fill-mask_chinese-large') >>> # Call the model, return some tensors >>> print(model(**preprocessor('你师父差得动你，你师父可[MASK]不动我。'))) >>> # Call the pipeline >>> from modelscope.pipelines import pipeline >>> pipeline_ins = pipeline('fill-mask', model=model, preprocessor=preprocessor) >>> print(pipeline_ins('你师父差得动你，你师父可[MASK]不动我。')) N) attention_masktoken_type_idsrZ head_mask inputs_embedsencoder_hidden_statesencoder_attention_maskoutput_attentionsoutput_hidden_states return_dictrrM)losslogitsr) attentions input_ids) r!use_return_dictr^r_rviewr9rr)rx)r ryrlrmrZrnrorprqlabelsrrrsrtoutputsrFrGmasked_lm_lossloss_fctoutputs r#r*SbertForMaskedLM.forwardsn&1% &IIr%)r^r_) NNNNNNNNNNNNr')r-r.r/r0__doc__"_keys_to_ignore_on_load_unexpected_keys_to_ignore_on_load_missingr rrerir*rr1r2r3s@r#rWrW^st,+4&4'# { ,6 "#!{ ~6:JJr%rW)!rtorch.nnrtorch.utils.checkpointrtransformers.activationsrmodelscope.metainformodelscope.models.builderrmodelscope.outputsrmodelscope.utilsrloggingmodelscope.utils.constantr backboner r configurationr get_loggerModulerr5r?rJregister_module fill_mask structbertrWr%r#rs$ %+&,;.+6&    299& BII  !ryy! 9BII 9V5F5FGJ+JHJr%