modeling

class SkepModel(vocab_size: int, hidden_size: Optional[int] = 768, num_hidden_layers: Optional[int] = 12, num_attention_heads: Optional[int] = 12, intermediate_size: Optional[int] = 3072, hidden_act: Optional[str] = 'gelu', hidden_dropout_prob: Optional[float] = 0.1, attention_probs_dropout_prob: Optional[float] = 0.1, max_position_embeddings: Optional[int] = 512, type_vocab_size: Optional[int] = 2, initializer_range: Optional[float] = 0.02, pad_token_id: Optional[int] = 0)[源代码]

基类:paddlenlp.transformers.skep.modeling.SkepPretrainedModel

The bare SKEP 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.

More details refer to SKEP.

参数
  • vocab_size (int) -- Vocabulary size of inputs_ids in SKEPModel. Defines the number of different tokens that can be represented by the inputs_ids passed when calling SKEPModel.

  • hidden_size (int, optional) -- Dimensionality of the embedding layer, encoder layers and the 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. The dimensionality of position encoding is the dimensionality of the sequence in TinyBertModel. Defaults to 512.

  • type_vocab_size (int, optional) -- The vocabulary size of the token_type_ids passed when calling SkepModel. 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 SkepPretrainedModel.init_weights() for how weights are initialized in SkepModel.

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

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, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]

The SkepModel 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, optionals) -- 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 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.

  • 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.

  • 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).

  • 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.

if the reuslt is tuple: 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].

示例

import paddle
from paddlenlp.transformers import SkepModel, SkepTokenizer

tokenizer = SkepTokenizer.from_pretrained('skep_ernie_2.0_large_en')
model = SkepModel.from_pretrained('skep_ernie_2.0_large_en')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP! ")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
output = model(**inputs)
get_input_embeddings()paddle.nn.layer.common.Embedding[源代码]

get skep input word embedding

返回

the input word embedding of skep mdoel

返回类型

nn.Embedding

set_input_embeddings(embedding: paddle.nn.layer.common.Embedding)paddle.nn.layer.common.Embedding[源代码]

set skep input embedding

返回

the instance of new word embedding

返回类型

nn.Embedding

class SkepPretrainedModel(*args, **kwargs)[源代码]

基类:paddlenlp.transformers.model_utils.PretrainedModel

An abstract class for pretrained Skep models. It provides Skep 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.

init_weights(layer)[源代码]

Initialization hook

base_model_class

alias of paddlenlp.transformers.skep.modeling.SkepModel

class SkepForSequenceClassification(skep, num_classes=2, dropout=None)[源代码]

基类:paddlenlp.transformers.skep.modeling.SkepPretrainedModel

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

参数
  • skep (SkepModel) -- An instance of SkepModel.

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

  • dropout (float, optional) -- The dropout probability for output of SKEP. If None, use the same value as hidden_dropout_prob of SkepModel instance skep. 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, labels: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]

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

参数
  • input_ids (Tensor) -- See SkepModel.

  • token_type_ids (Tensor, optional) -- See SkepModel.

  • position_ids (Tensor, optional) -- See SkepModel.

  • attention_mask (Tensor, optional) -- See SkepModel.

  • 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).

  • inputs_embeds (Tensor, optional) -- See SkepModel.

  • 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 SkepForSequenceClassification, SkepTokenizer

tokenizer = SkepTokenizer.from_pretrained('skep_ernie_2.0_large_en')
model = SkepForSequenceClassification.from_pretrained('skep_ernie_2.0_large_en')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
logits = model(**inputs)
class SkepForTokenClassification(skep, num_classes=2, dropout=None)[源代码]

基类:paddlenlp.transformers.skep.modeling.SkepPretrainedModel

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

参数
  • skep (SkepModel) -- An instance of SkepModel.

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

  • dropout (float, optional) -- The dropout probability for output of SKEP. If None, use the same value as hidden_dropout_prob of SkepModel instance skep. 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, labels: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]

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

参数
  • input_ids (Tensor) -- See SkepModel.

  • token_type_ids (Tensor, optional) -- See SkepModel.

  • position_ids (Tensor, optional) -- See SkepModel.

  • attention_mask (Tensor, optional) -- See SkepModel.

  • labels (Tensor of shape (batch_size, sequence_length), optional) -- Labels for computing the token classification loss. Indices should be in [0, ..., num_classes - 1].

  • inputs_embeds (Tensor, optional) -- See SkepModel.

  • 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 SkepForTokenClassification, SkepTokenizer

tokenizer = SkepTokenizer.from_pretrained('skep_ernie_2.0_large_en')
model = SkepForTokenClassification.from_pretrained('skep_ernie_2.0_large_en')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
logits = model(**inputs)
class SkepCrfForTokenClassification(skep: paddlenlp.transformers.skep.modeling.SkepModel, num_classes: int = 3)[源代码]

基类:paddlenlp.transformers.skep.modeling.SkepPretrainedModel

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

参数
  • skep (SkepModel) -- An instance of SkepModel.

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

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, seq_lens: Optional[paddle.Tensor] = None, labels: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]

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

参数
  • input_ids (Tensor) -- See SkepModel.

  • token_type_ids (Tensor, optional) -- See SkepModel.

  • position_ids (Tensor, optional) -- See SkepModel.

  • attention_mask (Tensor, optional) -- See SkepModel.

  • seq_lens (Tensor, optional) -- The input length tensor storing real length of each sequence for correctness. Its data type should be int64 and its shape is [batch_size]. Defaults to None.

  • labels (Tensor, optional) -- The input label tensor. Its data type should be int64 and its shape is [batch_size, sequence_length].

  • inputs_embeds (Tensor, optional) -- See SkepModel.

  • 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.

if return_dict is False, Returns tensor loss if labels is not None. Otherwise, returns tensor prediction.

  • loss (Tensor):

    The crf loss. Its data type is float32 and its shape is [batch_size].

  • prediction (Tensor):

    The prediction tensor containing the highest scoring tag indices. Its data type is int64 and its shape is [batch_size, sequence_length].