modeling

class ErnieModel(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=2, initializer_range=0.02, pad_token_id=0, task_type_vocab_size=3, task_id=0, use_task_id=False, enable_recompute=False)[source]

Bases: paddlenlp.transformers.ernie.modeling.ErniePretrainedModel

The bare ERNIE 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.

Parameters
  • vocab_size (int) – Vocabulary size of inputs_ids in ErnieModel. 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 ErnieModel.

  • 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. Defaults to 2.

  • initializer_range (float, optional) –

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

    Note

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

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

get_input_embeddings()[source]

get input embedding of model

Returns

embedding of model

Return type

nn.Embedding

set_input_embeddings(value)[source]

set new input embedding for model

Parameters

value (Embedding) – the new embedding of model

Raises

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, task_type_ids: 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)[source]
Parameters
  • 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 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]. 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.

    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.

Returns

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.

Example

import paddle
from paddlenlp.transformers import ErnieModel, ErnieTokenizer

tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0')
model = ErnieModel.from_pretrained('ernie-1.0')

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 ErniePretrainedModel(*args, **kwargs)[source]

Bases: paddlenlp.transformers.model_utils.PretrainedModel

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

init_weights(layer)[source]

Initialization hook

base_model_class

alias of paddlenlp.transformers.ernie.modeling.ErnieModel

class ErnieForSequenceClassification(ernie, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.ernie.modeling.ErniePretrainedModel

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

Parameters
  • ernie (ErnieModel) – An instance of paddlenlp.transformers.ErnieModel.

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

  • dropout (float, optional) – The dropout probability for output of ERNIE. If None, use the same value as hidden_dropout_prob of paddlenlp.transformers.ErnieModel instance. 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)[source]
Parameters
  • input_ids (Tensor) – See ErnieModel.

  • token_type_ids (Tensor, optional) – See ErnieModel.

  • position_ids (Tensor, optional) – See ErnieModel.

  • attention_mask (Tensor, optional) – See ErnieModel.

  • inputs_embeds (Tensor, optional) – See ErnieModel.

  • 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.

Returns

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.

Example

import paddle
from paddlenlp.transformers import ErnieForSequenceClassification, ErnieTokenizer

tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0')
model = ErnieForSequenceClassification.from_pretrained('ernie-1.0')

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

Bases: paddlenlp.transformers.ernie.modeling.ErniePretrainedModel

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

Parameters
  • ernie (ErnieModel) – An instance of ErnieModel.

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

  • dropout (float, optional) – The dropout probability for output of ERNIE. If None, use the same value as hidden_dropout_prob of ErnieModel instance ernie. 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)[source]
Parameters
  • input_ids (Tensor) – See ErnieModel.

  • token_type_ids (Tensor, optional) – See ErnieModel.

  • position_ids (Tensor, optional) – See ErnieModel.

  • attention_mask (Tensor, optional) – See ErnieModel.

  • inputs_embeds (Tensor, optional) – See ErnieModel.

  • 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.

Returns

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.

Example

import paddle
from paddlenlp.transformers import ErnieForTokenClassification, ErnieTokenizer

tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0')
model = ErnieForTokenClassification.from_pretrained('ernie-1.0')

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

Bases: paddlenlp.transformers.ernie.modeling.ErniePretrainedModel

Ernie 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.

Parameters

ernie (ErnieModel) – An instance of ErnieModel.

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)[source]
Parameters
  • input_ids (Tensor) – See ErnieModel.

  • token_type_ids (Tensor, optional) – See ErnieModel.

  • position_ids (Tensor, optional) – See ErnieModel.

  • attention_mask (Tensor, optional) – See ErnieModel.

  • inputs_embeds (Tensor, optional) – See ErnieModel.

  • 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.

Returns

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.

Example

import paddle
from paddlenlp.transformers import ErnieForQuestionAnswering, ErnieTokenizer

tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0')
model = ErnieForQuestionAnswering.from_pretrained('ernie-1.0')

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

Bases: paddlenlp.transformers.ernie.modeling.ErniePretrainedModel

Ernie Model with a masked language modeling head and a sentence order prediction head on top.

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, masked_positions: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, labels: Optional[paddle.Tensor] = None, next_sentence_label: Optional[paddle.Tensor] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[source]
Parameters
  • input_ids (Tensor) – See ErnieModel.

  • token_type_ids (Tensor, optional) – See ErnieModel.

  • position_ids (Tensor, optional) – See ErnieModel.

  • attention_mask (Tensor, optional) – See ErnieModel.

  • inputs_embeds (Tensor, optional) – See ErnieModel.

  • 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].

  • next_sentence_label (Tensor of shape (batch_size,), optional) –

    Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair (see input_ids docstring) Indices should be in [0, 1]:

    • 0 indicates sequence B is a continuation of sequence A,

    • 1 indicates sequence B is a random sequence.

  • 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 ErnieForPreTrainingOutput object. If False, the output will be a tuple of tensors. Defaults to False.

Returns

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

class ErniePretrainingCriterion(with_nsp_loss=True)[source]

Bases: paddle.fluid.dygraph.layers.Layer

The loss output of Ernie Model during the pretraining: a masked language modeling head and a next sentence prediction (classification) head.

forward(prediction_scores, seq_relationship_score, masked_lm_labels, next_sentence_labels=None)[source]
Parameters
  • prediction_scores (Tensor) – The scores of masked token prediction. Its data type should be float32. If masked_positions is None, its shape is [batch_size, sequence_length, vocab_size]. Otherwise, its shape is [batch_size, mask_token_num, vocab_size]

  • seq_relationship_score (Tensor) – The scores of next sentence prediction. Its data type should be float32 and its shape is [batch_size, 2]

  • masked_lm_labels (Tensor) – The labels of the masked language modeling, its dimensionality is equal to prediction_scores. Its data type should be int64. If masked_positions is None, its shape is [batch_size, sequence_length, 1]. Otherwise, its shape is [batch_size, mask_token_num, 1]

  • next_sentence_labels (Tensor) – The labels of the next sentence prediction task, the dimensionality of next_sentence_labels is equal to seq_relation_labels. Its data type should be int64 and its shape is [batch_size, 1]

Returns

The pretraining loss, equals to the sum of masked_lm_loss plus the mean of next_sentence_loss. Its data type should be float32 and its shape is [1].

Return type

Tensor

class ErnieForMaskedLM(ernie)[source]

Bases: paddlenlp.transformers.ernie.modeling.ErniePretrainedModel

Ernie Model with a masked language modeling head on top.

Parameters

ernie (ErnieModel) – An instance of ErnieModel.

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, masked_positions: 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)[source]
Parameters
  • input_ids (Tensor) – See ErnieModel.

  • token_type_ids (Tensor, optional) – See ErnieModel.

  • position_ids (Tensor, optional) – See ErnieModel.

  • attention_mask (Tensor, optional) – See ErnieModel.

  • masked_positions – masked positions of output.

  • inputs_embeds (Tensor, optional) – See ErnieModel.

  • 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.

Returns

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.

Example

import paddle
from paddlenlp.transformers import ErnieForMaskedLM, ErnieTokenizer

tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0')
model = ErnieForMaskedLM.from_pretrained('ernie-1.0')

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, 17, 18000]
class ErnieForMultipleChoice(ernie, num_choices=2, dropout=None)[source]

Bases: paddlenlp.transformers.ernie.modeling.ErniePretrainedModel

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

Parameters
  • ernie (ErnieModel) – An instance of ErnieModel.

  • num_choices (int, optional) – The number of choices. Defaults to 2.

  • dropout (float, optional) – The dropout probability for output of Ernie. If None, use the same value as hidden_dropout_prob of ErnieModel instance ernie. 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)[source]

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

Parameters
  • input_ids (Tensor) – See ErnieModel and shape as [batch_size, num_choice, sequence_length].

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

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

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

  • inputs_embeds (Tensor, optional) – See ErnieModel and shape as [batch_size, num_choice, sequence_length, hidden_size].

  • 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.

Returns

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.