modeling¶

class RobertaModel(config: paddlenlp.transformers.roberta.configuration.RobertaConfig, add_pooling_layer=True)[源代码]¶

基类：paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

The bare Roberta Model outputting raw hidden-states.

This model inherits from PretrainedModel. Refer to the superclass documentation for the generic methods.

This model is also a Paddle paddle.nn.Layer subclass. Use it as a regular Paddle Layer and refer to the Paddle documentation for all matter related to general usage and behavior.

参数

vocab_size (int) -- Vocabulary size of inputs_ids in RobertaModel. Also is the vocab size of token embedding matrix. Defines the number of different tokens that can be represented by the inputs_ids passed when calling RobertaModel.
hidden_size (int, optional) -- Dimensionality of the embedding layer, encoder layers and pooler layer. Defaults to 768.
num_hidden_layers (int, optional) -- Number of hidden layers in the Transformer encoder. Defaults to 12.
num_attention_heads (int, optional) -- Number of attention heads for each attention layer in the Transformer encoder. Defaults to 12.
intermediate_size (int, optional) -- Dimensionality of the feed-forward (ff) layer in the encoder. Input tensors to ff layers are firstly projected from hidden_size to intermediate_size, and then projected back to hidden_size. Typically intermediate_size is larger than hidden_size. Defaults to 3072.
hidden_act (str, optional) -- The non-linear activation function in the feed-forward layer. "gelu", "relu" and any other paddle supported activation functions are supported. Defaults to "gelu".
hidden_dropout_prob (float, optional) -- The dropout probability for all fully connected layers in the embeddings and encoder. Defaults to 0.1.
attention_probs_dropout_prob (float, optional) -- The dropout probability used in MultiHeadAttention in all encoder layers to drop some attention target. Defaults to 0.1.
max_position_embeddings (int, optional) -- The maximum value of the dimensionality of position encoding, which dictates the maximum supported length of an input sequence. Defaults to 512.
type_vocab_size (int, optional) -- The vocabulary size of the token_type_ids passed when calling RobertaModel. Defaults to 2.
initializer_range (float, optional) --
The standard deviation of the normal initializer. Defaults to 0.02.

注解

A normal_initializer initializes weight matrices as normal distributions. See RobertaPretrainedModel._init_weights() for how weights are initialized in RobertaModel.
pad_token_id (int, optional) -- The index of padding token in the token vocabulary. Defaults to 0.
cls_token_id (int, optional) -- The index of cls token in the token vocabulary. Defaults to 101.

get_input_embeddings()[源代码]¶

get input embedding of model

返回: embedding of model
返回类型: nn.Embedding

set_input_embeddings(value)[源代码]¶

set new input embedding for model

参数: value (Embedding) -- the new embedding of model
引发: NotImplementedError -- Model has not implement set_input_embeddings method

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, position_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, past_key_values: Optional[Tuple[Tuple[paddle.Tensor]]] = None, inputs_embeds: Optional[paddle.Tensor] = None, use_cache: Optional[bool] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]¶

参数

input_ids (Tensor) -- Indices of input sequence tokens in the vocabulary. They are numerical representations of tokens that build the input sequence. It's data type should be int64 and has a shape of [batch_size, sequence_length].
token_type_ids (Tensor, optional) --
Segment token indices to indicate first and second portions of the inputs. Indices can be either 0 or 1:
- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
It's data type should be int64 and has a shape of [batch_size, sequence_length]. Defaults to None, which means no segment embeddings is added to token embeddings.
position_ids (Tensor, optional) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, max_position_embeddings - 1]. It's data type should be int64 and has a shape of [batch_size, sequence_length]. Defaults to None.
attention_mask (Tensor, optional) -- Mask used in multi-head attention to avoid performing attention to some unwanted positions, usually the paddings or the subsequent positions. Its data type can be int, float and bool. When the data type is bool, the masked tokens have False values and the others have True values. When the data type is int, the masked tokens have 0 values and the others have 1 values. When the data type is float, the masked tokens have -INF values and the others have 0 values. It is a tensor with shape broadcasted to [batch_size, num_attention_heads, sequence_length, sequence_length]. For example, its shape can be [batch_size, sequence_length], [batch_size, sequence_length, sequence_length], [batch_size, num_attention_heads, sequence_length, sequence_length]. Defaults to None, which means nothing needed to be prevented attention to.
past_key_values (tuple(tuple(Tensor)), optional) -- The length of tuple equals to the number of layers, and each inner tuple haves 4 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)) which contains precomputed key and value hidden states of the attention blocks. If past_key_values are used, the user can optionally input only the last input_ids (those that don't have their past key value states given to this model) of shape (batch_size, 1) instead of all input_ids of shape (batch_size, sequence_length).
inputs_embeds (Tensor, optional) -- If you want to control how to convert inputs_ids indices into associated vectors, you can pass an embedded representation directly instead of passing inputs_ids.
use_cache (bool, optional) -- If set to True, past_key_values key value states are returned. Defaults to None.
output_hidden_states (bool, optional) -- Whether to return the hidden states of all layers. Defaults to False.
output_attentions (bool, optional) -- Whether to return the attentions tensors of all attention layers. Defaults to False.
return_dict (bool, optional) -- Whether to return a ModelOutput object. If False, the output will be a tuple of tensors. Defaults to False.

返回

An instance of BaseModelOutputWithPoolingAndCrossAttentions if return_dict=True. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields of BaseModelOutputWithPoolingAndCrossAttentions.

示例

import paddle
from paddlenlp.transformers import RobertaModel, RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext')
model = RobertaModel.from_pretrained('roberta-wwm-ext')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
sequence_output, pooled_output = model(**inputs)

class RobertaPretrainedModel(*args, **kwargs)[源代码]¶

基类：paddlenlp.transformers.model_utils.PretrainedModel

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

config_class¶: alias of paddlenlp.transformers.roberta.configuration.RobertaConfig

init_weights(layer)[源代码]¶: Initialization hook

base_model_class¶: alias of paddlenlp.transformers.roberta.modeling.RobertaModel

class RobertaForSequenceClassification(config: paddlenlp.transformers.roberta.configuration.RobertaConfig)[源代码]¶

基类：paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

Roberta Model with a linear layer on top of the output layer, designed for sequence classification/regression tasks like GLUE tasks.

参数

roberta (RobertaModel) -- An instance of RobertaModel.
num_classes (int, optional) -- The number of classes. Defaults to 2.
dropout (float, optional) -- The dropout probability for output of Roberta. If None, use the same value as hidden_dropout_prob of RobertaModel instance roberta. Defaults to None.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, position_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, labels: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]¶

参数

input_ids (Tensor) -- See RobertaModel.
token_type_ids (Tensor, optional) -- See RobertaModel.
position_ids (Tensor, optional) -- See RobertaModel.
attention_mask (Tensor, optional) -- See RobertaModel.
inputs_embeds (Tensor, optional) -- See RobertaModel.
labels (Tensor of shape (batch_size,), optional) -- Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., num_classes - 1]. If num_classes == 1 a regression loss is computed (Mean-Square loss), If num_classes > 1 a classification loss is computed (Cross-Entropy).
output_hidden_states (bool, optional) -- Whether to return the hidden states of all layers. Defaults to False.
output_attentions (bool, optional) -- Whether to return the attentions tensors of all attention layers. Defaults to False.
return_dict (bool, optional) -- Whether to return a SequenceClassifierOutput object. If False, the output will be a tuple of tensors. Defaults to False.

返回

An instance of SequenceClassifierOutput if return_dict=True. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields of SequenceClassifierOutput.

示例

import paddle
from paddlenlp.transformers import RobertaForSequenceClassification, RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext')
model = RobertaForSequenceClassification.from_pretrained('roberta-wwm-ext')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
logits = model(**inputs)

class RobertaForTokenClassification(config: paddlenlp.transformers.roberta.configuration.RobertaConfig)[源代码]¶

基类：paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

Roberta Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks.

参数

roberta (RobertaModel) -- An instance of RobertaModel.
num_classes (int, optional) -- The number of classes. Defaults to 2.
dropout (float, optional) -- The dropout probability for output of Roberta. If None, use the same value as hidden_dropout_prob of RobertaModel instance roberta. Defaults to None.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, position_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, labels: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]¶

参数

input_ids (Tensor) -- See RobertaModel.
token_type_ids (Tensor, optional) -- See RobertaModel.
position_ids (Tensor, optional) -- See RobertaModel.
attention_mask (Tensor, optional) -- See RobertaModel.
inputs_embeds (Tensor, optional) -- See RobertaModel.
labels (Tensor of shape (batch_size, sequence_length), optional) -- Labels for computing the token classification loss. Indices should be in [0, ..., num_classes - 1].
output_hidden_states (bool, optional) -- Whether to return the hidden states of all layers. Defaults to False.
output_attentions (bool, optional) -- Whether to return the attentions tensors of all attention layers. Defaults to False.
return_dict (bool, optional) -- Whether to return a TokenClassifierOutput object. If False, the output will be a tuple of tensors. Defaults to False.

返回

An instance of TokenClassifierOutput if return_dict=True. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields of TokenClassifierOutput.

示例

import paddle
from paddlenlp.transformers import RobertaForTokenClassification, RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext')
model = RobertaForTokenClassification.from_pretrained('roberta-wwm-ext')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
logits = model(**inputs)

class RobertaForQuestionAnswering(config: paddlenlp.transformers.roberta.configuration.RobertaConfig)[源代码]¶

基类：paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

Roberta Model with a linear layer on top of the hidden-states output to compute span_start_logits: and span_end_logits, designed for question-answering tasks like SQuAD.

参数: roberta (RobertaModel) -- An instance of RobertaModel.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, position_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, start_positions: Optional[paddle.Tensor] = None, end_positions: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]¶

参数

input_ids (Tensor) -- See RobertaModel.
token_type_ids (Tensor, optional) -- See RobertaModel.
position_ids (Tensor, optional) -- See RobertaModel.
attention_mask (Tensor, optional) -- See RobertaModel.
inputs_embeds (Tensor, optional) -- See RobertaModel.
start_positions (Tensor of shape (batch_size,), optional) -- Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.
end_positions (Tensor of shape (batch_size,), optional) -- Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.
output_hidden_states (bool, optional) -- Whether to return the hidden states of all layers. Defaults to False.
output_attentions (bool, optional) -- Whether to return the attentions tensors of all attention layers. Defaults to False.
return_dict (bool, optional) -- Whether to return a QuestionAnsweringModelOutput object. If False, the output will be a tuple of tensors. Defaults to False.

返回

An instance of QuestionAnsweringModelOutput if return_dict=True. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields of QuestionAnsweringModelOutput.

示例

import paddle
from paddlenlp.transformers import RobertaForSequenceClassification, RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext')
model = RobertaForSequenceClassification.from_pretrained('roberta-wwm-ext')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
logits = model(**inputs)

class RobertaForMaskedLM(config: paddlenlp.transformers.roberta.configuration.RobertaConfig)[源代码]¶

基类：paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

Roberta Model with a masked language modeling head on top.

参数: ( (bert) -- class:RobertaModel`): An instance of RobertaModel.

get_output_embeddings()[源代码]¶

To be overwrited for models with output embeddings

返回: the otuput embedding of model
返回类型: Optional[Embedding]

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, position_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, labels: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]¶

参数

input_ids (Tensor) -- See RobertaModel.
token_type_ids (Tensor, optional) -- See RobertaModel.
position_ids (Tensor, optional) -- See RobertaModel.
attention_mask (Tensor, optional) -- See RobertaModel.
inputs_embeds (Tensor, optional) -- See RobertaModel.
labels (Tensor of shape (batch_size, sequence_length), optional) -- Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., 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, ..., vocab_size]
output_hidden_states (bool, optional) -- Whether to return the hidden states of all layers. Defaults to False.
output_attentions (bool, optional) -- Whether to return the attentions tensors of all attention layers. Defaults to False.
return_dict (bool, optional) -- Whether to return a MaskedLMOutput object. If False, the output will be a tuple of tensors. Defaults to False.

返回

An instance of MaskedLMOutput if return_dict=True. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields of MaskedLMOutput.

示例

import paddle
from paddlenlp.transformers import RobertaForMaskedLM, RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext')
model = RobertaForMaskedLM.from_pretrained('roberta-wwm-ext')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}

logits = model(**inputs)
print(logits.shape)
# [1, 13, 30522]

class RobertaForMultipleChoice(config: paddlenlp.transformers.roberta.configuration.RobertaConfig)[源代码]¶

基类：paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

RoBerta Model with a linear layer on top of the hidden-states output layer, designed for multiple choice tasks like RocStories/SWAG tasks.

参数

bert (RobertaModel) -- An instance of RobertaModel.
num_choices (int, optional) -- The number of choices. Defaults to 2.
dropout (float, optional) -- The dropout probability for output of Bert. If None, use the same value as hidden_dropout_prob of RobertaModel instance bert. Defaults to None.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, position_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, labels: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]¶

The RobertaForMultipleChoice forward method, overrides the __call__() special method.

参数

input_ids (Tensor) -- See RobertaModel and shape as [batch_size, num_choice, sequence_length].
token_type_ids (Tensor, optional) -- See RobertaModel and shape as [batch_size, num_choice, sequence_length].
position_ids (Tensor, optional) -- See RobertaModel and shape as [batch_size, num_choice, sequence_length].
attention_mask (list, optional) -- See RobertaModel and shape as [batch_size, num_choice, sequence_length].
inputs_embeds (list, optional) -- See RobertaModel and shape as [batch_size, num_choice, sequence_length].
labels (Tensor of shape (batch_size, ), optional) -- Labels for computing the multiple choice classification loss. Indices should be in [0, ..., num_choices-1] where num_choices is the size of the second dimension of the input tensors. (See input_ids above)
output_hidden_states (bool, optional) -- Whether to return the hidden states of all layers. Defaults to False.
output_attentions (bool, optional) -- Whether to return the attentions tensors of all attention layers. Defaults to False.
return_dict (bool, optional) -- Whether to return a MultipleChoiceModelOutput object. If False, the output will be a tuple of tensors. Defaults to False.

返回

An instance of MultipleChoiceModelOutput if return_dict=True. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields of MultipleChoiceModelOutput.

示例

import paddle
from paddlenlp.transformers import BertForMultipleChoice, BertTokenizer
from paddlenlp.data import Pad, Dict

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForMultipleChoice.from_pretrained('bert-base-uncased', num_choices=2)

data = [
    {
        "question": "how do you turn on an ipad screen?",
        "answer1": "press the volume button.",
        "answer2": "press the lock button.",
        "label": 1,
    },
    {
        "question": "how do you indent something?",
        "answer1": "leave a space before starting the writing",
        "answer2": "press the spacebar",
        "label": 0,
    },
]

text = []
text_pair = []
for d in data:
    text.append(d["question"])
    text_pair.append(d["answer1"])
    text.append(d["question"])
    text_pair.append(d["answer2"])

inputs = tokenizer(text, text_pair)
batchify_fn = lambda samples, fn=Dict(
    {
        "input_ids": Pad(axis=0, pad_val=tokenizer.pad_token_id),  # input_ids
        "token_type_ids": Pad(
            axis=0, pad_val=tokenizer.pad_token_type_id
        ),  # token_type_ids
    }
): fn(samples)
inputs = batchify_fn(inputs)

reshaped_logits = model(
    input_ids=paddle.to_tensor(inputs[0], dtype="int64"),
    token_type_ids=paddle.to_tensor(inputs[1], dtype="int64"),
)
print(reshaped_logits.shape)
# [2, 2]

class RobertaForCausalLM(config: paddlenlp.transformers.roberta.configuration.RobertaConfig)[源代码]¶

基类：paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel

Roberta Model with a Causal language modeling head on top.

参数: ( (bert) -- class:RobertaModel`): An instance of RobertaModel.

get_output_embeddings()[源代码]¶

To be overwrited for models with output embeddings

返回: the otuput embedding of model
返回类型: Optional[Embedding]

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, position_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, past_key_values: Optional[Tuple[Tuple[paddle.Tensor]]] = None, use_cache: Optional[bool] = None, labels: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]¶

参数

input_ids (Tensor) -- See RobertaModel.
token_type_ids (Tensor, optional) -- See RobertaModel.
position_ids (Tensor, optional) -- See RobertaModel.
attention_mask (Tensor, optional) -- See RobertaModel.
inputs_embeds (Tensor, optional) -- See RobertaModel.
past_key_values (tuple(tuple(Tensor)), optional) -- See RobertaModel.
use_cache (Tensor, optional) -- See RobertaModel.
attention_mask -- See RobertaModel.
labels (Tensor of shape (batch_size, sequence_length), optional) -- Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in [-100, 0, ..., 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, ..., vocab_size].
output_hidden_states (bool, optional) -- Whether to return the hidden states of all layers. Defaults to False.
output_attentions (bool, optional) -- Whether to return the attentions tensors of all attention layers. Defaults to False.
return_dict (bool, optional) -- Whether to return a CausalLMOutputWithCrossAttentions object. If False, the output will be a tuple of tensors. Defaults to False.

返回

An instance of CausalLMOutputWithCrossAttentions if return_dict=True. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields of CausalLMOutputWithCrossAttentions.

示例

import paddle
from paddlenlp.transformers import RobertaForCausalLM, RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext')
model = RobertaForCausalLM.from_pretrained('roberta-wwm-ext')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}

logits = model(**inputs)
print(logits.shape)
# [1, 13, 30522]