o ߥi[(@sddlZddlmZddlZddlmZddlmZddlmZddl m Z ddl m Z ddlmZdd lmZmZe Z ejejejd ejejejd ejejejd Gd d d eZdS) N)CrossEntropyLoss)Models)MODELS)'AttentionTokenClassificationModelOutput)logger)Tasks)MGeoMGeoPreTrainedModel) module_namecsTeZdZdZdgZd deffdd Z              d dd ZZS) MGeoForTokenClassificationa Bert Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks, word-segmentation. This model inherits from :class:`~transformers.PreTrainedModel`. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch `torch.nn.Module `__ 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 Bert, the preprocessor of this model is `modelscope.preprocessors.TokenClassificationTransformersPreprocessor`. Trainer: This model is a normal PyTorch model, and can be trained by variable trainers, like EpochBasedTrainer, NlpEpochBasedTrainer, or trainers from other frameworks. The preferred trainer in ModelScope is NlpEpochBasedTrainer. 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 single-modal finetune_modec slt||j|_t||jt||dd|jdur|jn|j}t ||_ t |j |j|_ |dS)NF)add_pooling_layer)super__init__ num_labelssetattrbase_model_prefixr classifier_dropouthidden_dropout_probnnDropoutdropoutLinear hidden_size classifier post_init)selfconfigrkwargsr __class__k/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/multi_modal/mgeo/token_classification.pyrBs    z#MGeoForTokenClassification.__init__Nc Cs| dur| n|jj} |j|||||||| | | |d }|d}||}||}d}|durgt}|durZ|ddk}|d|j}t ||dt |j  |}|||}n ||d|j|d}| s}|f|dd}|dur{|f|S|St |||j|j| | dS)a 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. 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**. 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. 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,)`, `optional`): Labels for computing the sequence classification/regression loss. Indices should be in :obj:`[0, ..., config.num_labels - 1]`. If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss), If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy). offset_mapping (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Indices of positions of each input sequence tokens in the sentence. Selected in the range ``[0, sequence_length - 1]``. label_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**. Returns: Returns `modelscope.outputs.AttentionTokenClassificationModelOutput` Examples: >>> from modelscope.models import Model >>> from modelscope.preprocessors import Preprocessor >>> model = Model.from_pretrained('damo/nlp_bert_word-segmentation_chinese-base') >>> preprocessor = Preprocessor.from_pretrained('damo/nlp_bert_word-segmentation_chinese-base') >>> print(model(**preprocessor(('This is a test', 'This is also a test')))) N) attention_masktoken_type_ids position_ids head_mask inputs_embedsoutput_attentionsoutput_hidden_states return_dictgis_listgis_tprr)losslogits hidden_states attentionsoffset_mapping label_mask)r use_return_dictbertrrrviewrtorchwheretensor ignore_indextype_asrr4r5)r input_idsr&r'r(r)r*labelsr+r,r-r6r7r.r/outputssequence_outputr3r2loss_fct active_loss active_logits active_labelsoutputr$r$r%forwardQsTf    z"MGeoForTokenClassification.forward)r)NNNNNNNNNNNNNN) __name__ __module__ __qualname____doc__"_keys_to_ignore_on_load_unexpectedstrrrI __classcell__r$r$r"r%r !s&r )r;torch.nnrtorch.utils.checkpointrmodelscope.metainformodelscope.models.builderrmodelscope.outputsrmodelscope.utilsrloggingmodelscope.utils.constantrbackboner r get_loggerregister_moduletoken_classificationmgeopart_of_speechword_segmentationr r$r$r$r%s