modeling

class ErnieCtmModel(vocab_size, embedding_size=128, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=16, initializer_range=0.02, pad_token_id=0, use_content_summary=True, content_summary_index=1)

Bases: paddlenlp.transformers.ernie_ctm.modeling.ErnieCtmPretrainedModel

forward(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, content_clone=False)

Forward process.

class ErnieCtmWordtagModel(ernie_ctm, num_tag, num_cls_label, crf_lr=100, ignore_index=0)

Bases: paddlenlp.transformers.ernie_ctm.modeling.ErnieCtmPretrainedModel

Wordtag task model.

forward(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, lengths=None, tag_labels=None, cls_label=None)

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

• *inputs (tuple) – unpacked tuple arguments

• **kwargs (dict) – unpacked dict arguments