modeling

class ErnieGramModel(vocab_size, emb_size=768, 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=2, initializer_range=0.02, pad_token_id=0, rel_pos_size=None)[源代码]

基类:paddlenlp.transformers.ernie_gram.modeling.ErnieGramPretrainedModel

The bare ERNIE-Gram 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 the ERNIE-Gram model. Also is the vocab size of token embedding matrix.

  • 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 encoders. 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. Defaults to 2.

  • initializer_range (float, optional) --

    The standard deviation of the normal initializer for initializing all weight matrices. Defaults to 0.02.

    注解

    A normal_initializer initializes weight matrices as normal distributions. See ErniePretrainedModel._init_weights() for how weights are initialized in ErnieGramModel.

  • rel_pos_size (int, optional) -- The relative position size just for ERNIE-Gram English model. Defaults to None.

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

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=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, config.max_position_embeddings - 1]. Defaults to None. Shape as (batch_sie, num_tokens) and dtype as int32 or int64.

  • 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]. 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]. We use whole-word-mask in ERNIE, so the whole word will have the same value. For example, "使用" as a word, "使" and "用" will have the same value. 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 ErnieGramModel, ErnieGramTokenizer

tokenizer = ErnieGramTokenizer.from_pretrained('ernie-gram-zh')
model = ErnieGramModel.from_pretrained('ernie-gram-zh)

inputs = tokenizer("欢迎使用百度飞桨!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
sequence_output, pooled_output = model(**inputs)
class ErnieGramForSequenceClassification(ernie_gram, num_classes=2, dropout=None)[源代码]

基类:paddlenlp.transformers.ernie_gram.modeling.ErnieGramPretrainedModel

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

参数
  • ernie_gram (ErnieGramModel) -- An instance of paddlenlp.transformers.ErnieGramModel.

  • num_classes (int, optional) -- The number of classes. Default to 2.

  • dropout (float, optional) -- The dropout probability for output of ERNIE-Gram. If None, use the same value as hidden_dropout_prob of paddlenlp.transformers.ErnieGramModel instance. Defaults to None.

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

tokenizer = ErnieGramTokenizer.from_pretrained('ernie-gram-zh')
model = ErnieGramForSequenceClassification.from_pretrained('ernie-gram-zh')

inputs = tokenizer("欢迎使用百度飞桨!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
logits = model(**inputs)
class ErnieGramForTokenClassification(ernie_gram, num_classes=2, dropout=None)[源代码]

基类:paddlenlp.transformers.ernie_gram.modeling.ErnieGramPretrainedModel

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

参数
  • ernie_gram (ErnieGramModel) -- An instance of ErnieGramModel.

  • num_classes (int, optional) -- The number of classes. Default to 2.

  • dropout (float, optional) -- The dropout probability for output of ERNIE-Gram. If None, use the same value as hidden_dropout_prob of ErnieGramModel instance ernie_gram. Defaults to None.

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

tokenizer = ErnieGramTokenizer.from_pretrained('ernie-gram-zh')
model = ErnieGramForTokenClassification.from_pretrained('ernie-gram-zh')

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

基类:paddlenlp.transformers.ernie_gram.modeling.ErnieGramPretrainedModel

ERNIE-Gram 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

ernie_gram (ErnieGramModel) -- An instance of ErnieGramModel.

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

tokenizer = ErnieGramTokenizer.from_pretrained('ernie-gram-zh')
model = ErnieGramForQuestionAnswering.from_pretrained('ernie-gram-zh')

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