modeling

class RemBertModel(vocab_size, input_embedding_size=256, hidden_size=1152, num_hidden_layers=32, num_attention_heads=18, intermediate_size=4608, hidden_act='gelu', hidden_dropout_prob=0, attention_probs_dropout_prob=0, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, pad_token_id=0, layer_norm_eps=1e-12)[源代码]

基类：paddlenlp.transformers.rembert.modeling.RembertPretrainedModel

The bare RemBERT Model transformer 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 RemBertModel. 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 RemBertModel.

  • input_embedding_size (int, optional) -- Dimensionality of the embedding layer. Defaults to 256.

  • hidden_size (int, optional) -- Dimensionality of the encoder layer and pooler layer. Defaults to 1152.

  • num_hidden_layers (int, optional) -- Number of hidden layers in the Transformer encoder. Defaults to 32.

  • num_attention_heads (int, optional) -- Number of attention heads for each attention layer in the Transformer encoder. Defaults to 18.

  • 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 token_type_ids. Defaults to 16.

  • 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 BertPretrainedModel.init_weights() for how weights are initialized in BertModel.

  • pad_token_id (int, optional) -- The index of padding token in the token vocabulary. Defaults to 0.

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=None, token_type_ids=None, position_ids=None, attention_mask=None)[源代码]

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

参数

  • input_ids (Tensor) -- Indices of input sequence tokens in the vocabulary. They are numerical representations of tokens that build the input sequence. Its data type should be int64 and it has a shape of [batch_size, sequence_length].

  • token_type_ids (Tensor, optional) --

    Segment token indices to indicate different portions of the inputs. Selected in the range [0, type_vocab_size - 1]. If type_vocab_size is 2, which means the inputs have two portions. Indices can either be 0 or 1:

    • 0 corresponds to a sentence A token,

    • 1 corresponds to a sentence B token.

    Its data type should be int64 and it has a shape of [batch_size, sequence_length]. Defaults to None, which means we don't add segment 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]. Shape as (batch_size, num_tokens) and dtype as int64. Defaults to None.

  • attention_mask (Tensor, optional) -- Mask used in multi-head attention to avoid performing attention on 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]. Defaults to None, which means nothing needed to be prevented attention to.

返回

Returns tuple (sequence_output, pooled_output)

With the fields:

  • sequence_output (Tensor):

    Sequence of hidden-states at the last layer of the model. It's data type should be float32 and its shape is [batch_size, sequence_length, hidden_size].

  • pooled_output (Tensor):

    The output of first token ([CLS]) in sequence. We "pool" the model by simply taking the hidden state corresponding to the first token. Its data type should be float32 and its shape is [batch_size, hidden_size].

返回类型

tuple

示例

import paddle
from paddlenlp.transformers import RemBertModel, RemBertTokenizer

tokenizer = RemBertTokenizer.from_pretrained('rembert')
model = RemBertModel.from_pretrained('rembert')

inputs = tokenizer("欢迎使用百度飞桨!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
output = model(**inputs)
class RemBertForMaskedLM(rembert)[源代码]

基类：paddlenlp.transformers.rembert.modeling.RembertPretrainedModel

RemBert Model with a masked language modeling head on top.

参数

rembert (RemBertModel) -- An instance of RemBertModel.

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=None)[源代码]
参数
返回

Returns tensor prediction_scores, The scores of masked token prediction. Its data type should be float32 and shape is [batch_size, sequence_length, vocab_size].

返回类型

Tensor

示例

import paddle
from paddlenlp.transformers import RemBertForMaskedLM, RemBertTokenizer

tokenizer = RemBertTokenizer.from_pretrained('rembert')
model = RemBertForMaskedLM.from_pretrained('rembert')

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

logits = model(**inputs)
class RemBertForQuestionAnswering(rembert)[源代码]

基类：paddlenlp.transformers.rembert.modeling.RembertPretrainedModel

RemBert 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

rembert (RemBertModel) -- An instance of RemBertModel.

forward(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None)[源代码]

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

参数
返回

Returns tuple (start_logits, end_logits).

With the fields:

  • start_logits (Tensor):

    A tensor of the input token classification logits, indicates the start position of the labelled span. Its data type should be float32 and its shape is [batch_size, sequence_length].

  • end_logits (Tensor):

    A tensor of the input token classification logits, indicates the end position of the labelled span. Its data type should be float32 and its shape is [batch_size, sequence_length].

返回类型

tuple

示例

import paddle
from paddlenlp.transformers import RemBertForQuestionAnswering
from paddlenlp.transformers import RemBertTokenizer

tokenizer = RemBertTokenizer.from_pretrained('rembert')
model = RemBertForQuestionAnswering.from_pretrained('rembert')

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

start_logits = outputs[0]
end_logits = outputs[1]
class RemBertForSequenceClassification(rembert, num_classes)[源代码]

基类：paddlenlp.transformers.rembert.modeling.RembertPretrainedModel

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

参数

  • rembert (RemBertModel) -- An instance of RemBertModel.

  • num_classes (int, optional) -- The number of classes.

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=None)[源代码]

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

参数
返回

Returns tensor logits, a tensor of the input text classification logits. Shape as [batch_size, num_classes] and dtype as float32.

返回类型

Tensor

示例

import paddle
from paddlenlp.transformers import RemBertForSequenceClassification
from paddlenlp.transformers import RemBertTokenizer

tokenizer = RemBertTokenizer.from_pretrained('rembert')
model = RemBertForQuestionAnswering.from_pretrained('rembert', num_classes=2)

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
outputs = model(**inputs)
class RemBertForMultipleChoice(rembert, num_choices)[源代码]

基类：paddlenlp.transformers.rembert.modeling.RembertPretrainedModel

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

参数

  • rembert (RemBertModel) -- An instance of RemBertModel.

  • num_choices (int) -- The number of choices.

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=None)[源代码]

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

参数

  • input_ids (Tensor) -- See RemBertModel and shape as [batch_size, num_choice, sequence_length].

  • token_type_ids (Tensor, optional) -- See RemBertModel and shape as [batch_size, num_choice, sequence_length].

  • position_ids (Tensor, optional) -- See RemBertModel and shape as [batch_size, num_choice, sequence_length].

  • attention_mask (list, optional) -- See RemBertModel and shape as [batch_size, num_choice, sequence_length].

返回

Returns tensor reshaped_logits, a tensor of the multiple choice classification logits. Shape as [batch_size, num_choice] and dtype as float32.

返回类型

Tensor

示例

import paddle
from paddlenlp.transformers import RemBertForMultipleChoice, RemBertTokenizer
from paddlenlp.data import Pad, Dict

tokenizer = RemBertTokenizer.from_pretrained('rembert')
model = RemBertForMultipleChoice.from_pretrained('rembert', 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"),
)
class RembertPretrainedModel(*args, **kwargs)[源代码]

基类：paddlenlp.transformers.model_utils.PretrainedModel

init_weights(layer)[源代码]

Initialization hook

base_model_class

alias of paddlenlp.transformers.rembert.modeling.RemBertModel

class RemBertForTokenClassification(rembert, num_classes=2)[源代码]

基类：paddlenlp.transformers.rembert.modeling.RembertPretrainedModel

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

参数

  • rembert (RemBertModel) -- An instance of RemBertModel.

  • num_classes (int) -- The number of classes.

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=None)[源代码]

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

参数
返回

Returns tensor logits, a tensor of the input token classification logits. Shape as [batch_size, sequence_length, num_classes] and dtype as float32.

返回类型

Tensor

示例

import paddle
from paddlenlp.transformers import RemBertForTokenClassification
from paddlenlp.transformers import RemBertTokenizer

tokenizer = RemBertTokenizer.from_pretrained('rembert')
model = RemBertForTokenClassification.from_pretrained('rembert')

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)