o ߥi+@sddlZddlmZddlmZddlmZddlmZddl m Z ddl m Z ddl mZdd lmZd d lmZmZeZGd d d ejZGdddejZGdddejZe jejejdGdddeZdS)N)nn)CrossEntropyLoss)ACT2FN)Models)MODELS)AttentionFillMaskModelOutput)Tasks) get_logger) PoNetModelPoNetPreTrainedModelc$eZdZfddZddZZS)PoNetPredictionHeadTransformcsVtt|j|j|_t|jtrt |j|_ n|j|_ tj |j|j d|_ dS)N)eps) super__init__rLinear hidden_sizedense isinstance hidden_actstrrtransform_act_fn LayerNormlayer_norm_epsselfconfig __class__Y/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/nlp/ponet/fill_mask.pyr"s   z%PoNetPredictionHeadTransform.__init__cCs"||}||}||}|SN)rrrr hidden_statesr r r!forward,s   z$PoNetPredictionHeadTransform.forward__name__ __module__ __qualname__rr% __classcell__r r rr!r s  rcr )PoNetLMPredictionHeadcsLtt||_tj|j|jdd|_t t |j|_ |j |j_ dS)NF)bias) rrr transformrrr vocab_sizedecoder Parametertorchzerosr,rrr r!r5s   zPoNetLMPredictionHead.__init__cCs||}||}|Sr")r-r/r#r r r!r%Cs  zPoNetLMPredictionHead.forwardr&r r rr!r+3s r+cr )PoNetOnlyMLMHeadcstt||_dSr")rrr+ predictionsrrr r!rKs zPoNetOnlyMLMHead.__init__cCs||}|Sr")r4)rsequence_outputprediction_scoresr r r!r%Os zPoNetOnlyMLMHead.forwardr&r r rr!r3Is r3) module_namecsbeZdZdZdgZddgZfddZddZd d Z dd d Z Z S)PoNetForMaskedLMaxPoNet Model with a `language modeling` head on top. 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 PoNet, the preprocessor of this model is `modelscope.preprocessors.FillMaskPoNetPreprocessor`. Parameters: config (:class:`~modelscope.models.nlp.ponet.PoNetConfig`): 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.biasc s@t||jrtdt|dd|_t||_| dS)NzlIf you want to use `PoNetForMaskedLM` make sure `config.is_decoder=False` for bi-directional self-attention.F)add_pooling_layer) rr is_decoderloggerwarningr ponetr3cls init_weights)rrkwargsrr r!rqs   zPoNetForMaskedLM.__init__cCs |jjjSr"r@r4r/)rr r r!get_output_embeddings~s z&PoNetForMaskedLM.get_output_embeddingscCs||jj_dSr"rC)rnew_embeddingsr r r!set_output_embeddingssz&PoNetForMaskedLM.set_output_embeddingsNcCs| dur| n|jj} |j||||||||| | | | d }|d}||}d}| dur;t}||d|jj| d}| sQ|f|dd}|durO|f|S|St|||j|j |dS)uD 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.ponet.PoNetTokenizer`. 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.file_utils.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 >>> model = Model.from_pretrained('damo/nlp_ponet_fill-mask_chinese-base') >>> preprocessor = Preprocessor.from_pretrained('damo/nlp_ponet_fill-mask_chinese-base') >>> # 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_ids segment_idsr: head_mask inputs_embedsencoder_hidden_statesencoder_attention_maskoutput_attentionsoutput_hidden_states return_dictr)losslogitsr$ attentions input_ids) ruse_return_dictr?r@rviewr.rr$rU)rrVrGrHr:rIrJrKrLrMlabelsrNrOrPoutputsr5r6masked_lm_lossloss_fctoutputr r r!r%sNS zPoNetForMaskedLM.forward) NNNNNNNNNNNNN) r'r(r)__doc__"_keys_to_ignore_on_load_unexpected_keys_to_ignore_on_load_missingrrDrFr%r*r r rr!r8Ts,  r8)torch.utils.checkpointr1rtorch.nnrtransformers.activationsrmodelscope.metainformodelscope.models.builderrmodelscope.outputsrmodelscope.utils.constantrmodelscope.utils.loggerr backboner r r=Modulerr+r3register_module fill_maskr?r8r r r r!s