modeling

class RobertaModel(vocab_size, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act='gelu', 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)

Bases: paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=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

class RobertaPretrainedModel(name_scope=None, dtype='float32')

Bases: paddlenlp.transformers.model_utils.PretrainedModel

An abstract class for pretrained RoBERTa models. It provides RoBERTa related model_config_file, resource_files_names, pretrained_resource_files_map, pretrained_init_configuration, base_model_prefix for downloading and loading pretrained models. See PretrainedModel for more details.

init_weights(layer)

Initialization hook

base_model_class

alias of paddlenlp.transformers.roberta.modeling.RobertaModel

class RobertaForSequenceClassification(roberta, num_classes=2, dropout=None)

Bases: paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

Model for sentence (pair) classification task with RoBERTa. :param roberta: An instance of RobertaModel. :type roberta: RobertaModel :param num_classes: The number of classes. Default 2 :type num_classes: int, optional :param dropout: The dropout probability for output of RoBERTa.

If None, use the same value as hidden_dropout_prob of RobertaModel instance Roberta. Default None

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=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

class RobertaForTokenClassification(roberta, num_classes=2, dropout=None)

Bases: paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=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

class RobertaForQuestionAnswering(roberta, dropout=None)

Bases: paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

forward(input_ids, token_type_ids=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