modeling#

class ConvBertModel(config: ConvBertConfig)[source]#

Bases: ConvBertPretrainedModel

The bare ConvBert 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:

config (ConvBertConfig) – An instance of ConvBertConfig

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: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[source]#

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

Parameters:

  • 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. If its data type is int, the values should be either 0 or 1.

    • 1 for tokens that not masked,

    • 0 for tokens that masked.

    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.

    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.

  • inputs_embeds (Tensor, optional) – Instead of passing input_ids you can choose to directly pass an embedded representation.

  • 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 ConvBertModel, ConvBertTokenizer

tokenizer = ConvBertTokenizer.from_pretrained('convbert-base')
model = ConvBertModel.from_pretrained('convbert-base')

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

alias of ConvBertGenerator

class ConvBertPretrainedModel(*args, **kwargs)[source]#

Bases: PretrainedModel

An abstract class for pretrained ConvBert models. It provides ConvBert 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 ConvBertConfig

tie_weights()[source]#

Tie the weights between the input embeddings and the output embeddings.

base_model_class#

alias of ConvBertModel

class ConvBertForTotalPretraining(config: ConvBertConfig)[source]#

Bases: ConvBertPretrainedModel

Combine generator with discriminator for Replaced Token Detection (RTD) pretraining.

get_input_embeddings()[source]#

get input embedding of model

Returns:

embedding of model

Return type:

nn.Embedding

get_output_embeddings()[source]#

To be overwrited for models with output embeddings

Returns:

the otuput embedding of model

Return type:

Optional[Embedding]

get_discriminator_inputs(inputs, raw_inputs, generator_logits, generator_labels, use_softmax_sample)[source]#

Sample from the generator to create discriminator input.

forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, raw_input_ids: Tensor | None = None, generator_labels: Tensor | None = None)[source]#
Parameters:

  • input_ids (Tensor) – See ConvBertModel.

  • token_type_ids (Tensor, optional) – See ConvBertModel.

  • position_ids (Tensor, optional) – See ConvBertModel.

  • attention_mask (Tensor, optional) – See ConvBertModel.

  • raw_input_ids (Tensor, optional) – The raw input_ids. Its data type should be int64 and it has a shape of [batch_size, sequence_length].

  • generator_labels (Tensor, optional) – The generator labels. Its data type should be int64 and it has a shape of [batch_size, sequence_length].

Returns:

Returns tuple (generator_logits, disc_logits, disc_labels, attention_mask).

With the fields:

  • generator_logits (Tensor):

    a tensor of the generator prediction logits. Shape as [batch_size, sequence_length, vocab_size] and dtype as float32.

  • disc_logits (Tensor):

    a tensor of the discriminator prediction logits. Shape as [batch_size, sequence_length] and dtype as float32.

  • disc_labels (Tensor):

    a tensor of the discriminator prediction labels. Shape as [batch_size, sequence_length] and dtype as int64.

  • attention_mask (Tensor):

    See ConvBertModel.

Return type:

tuple

class ConvBertDiscriminator(config: ConvBertConfig)[source]#

Bases: ConvBertPretrainedModel

ConvBert Model with a discriminator prediction head on top.

Parameters:

config (ConvBertConfig) – An instance of ConvBertConfig

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None)[source]#

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

Parameters:

  • 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. If its data type is int, the values should be either 0 or 1.

    • 1 for tokens that not masked,

    • 0 for tokens that masked.

    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.

  • inputs_embeds (Tensor, optional) – Instead of passing input_ids you can choose to directly pass an embedded representation.

Returns:

Returns tensor logits, a tensor of the discriminator prediction logits. Shape as [batch_size, sequence_length] and dtype as float32.

Return type:

Tensor

Example

import paddle
from paddlenlp.transformers import ConvBertDiscriminatorPredictions, ConvBertTokenizer

tokenizer = ConvBertTokenizer.from_pretrained('convbert-base')
model = ConvBertDiscriminator.from_pretrained('convbert-base')

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

Bases: ConvBertPretrainedModel

ConvBert Model with a generator prediction head on top.

Parameters:

config (ConvBertConfig) – An instance of ConvBertConfig

get_input_embeddings()[source]#

get input embedding of model

Returns:

embedding of model

Return type:

nn.Embedding

forward(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None, labels=None, output_attentions=False, output_hidden_states=False, return_dict=False)[source]#

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

Parameters:
Returns:

Returns tensor prediction_scores, a tensor of the generator prediction scores. Shape as [batch_size, sequence_length, vocab_size] and dtype as float32.

Return type:

Tensor

Example

import paddle
from paddlenlp.transformers import ConvBertGenerator, ConvBertTokenizer

tokenizer = ConvBertTokenizer.from_pretrained('convbert-base')
model = ConvBertGenerator.from_pretrained('convbert-base')

inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!")
inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()}
prediction_scores = model(**inputs)
class ConvBertClassificationHead(config: ConvBertConfig)[source]#

Bases: Layer

ConvBert head for sentence-level classification tasks.

Parameters:

config (ConvBertConfig) – An instance of ConvBertConfig

forward(features, **kwargs)[source]#

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters:

  • *inputs (tuple) – unpacked tuple arguments

  • **kwargs (dict) – unpacked dict arguments

class ConvBertForSequenceClassification(config: ConvBertConfig)[source]#

Bases: ConvBertPretrainedModel

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

Parameters:

config (ConvBertConfig) – An instance of ConvBertConfig

forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, labels: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[source]#

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

Parameters:

  • input_ids (Tensor) – See ConvBertModel.

  • token_type_ids (Tensor, optional) – See ConvBertModel.

  • position_ids (Tensor, optional) – See ConvBertModel.

  • attention_mask (Tensor, optional) – See ConvBertModel.

  • inputs_embeds (Tensor, optional) – Instead of passing input_ids you can choose to directly pass an embedded representation.

  • labels (Tensor of shape (batch_size,), optional) – Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., num_labels - 1]. If num_labels == 1 a regression loss is computed (Mean-Square loss), If num_labels > 1 a classification loss is computed (Cross-Entropy).

  • output_hidden_states (bool, optional) – See ConvBertModel.

  • output_attentions (bool, optional) – See ConvBertModel.

  • return_dict (bool, optional) – Whether to return a SequenceClassifierOutput object. If False, the output will be a tuple of tensors. Defaults to False.

Returns:

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

Return type:

Tensor

Example

import paddle
from paddlenlp.transformers import ConvBertForSequenceClassification, ConvBertTokenizer

tokenizer = ConvBertTokenizer.from_pretrained('convbert-base')
model = ConvBertForSequenceClassification.from_pretrained('convbert-base')

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

Bases: ConvBertPretrainedModel

ConvBert Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks. :param config: An instance of ConvBertConfig :type config: ConvBertConfig

forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, labels: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[source]#

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

Parameters:

  • input_ids (Tensor) – See ConvBertModel.

  • token_type_ids (Tensor, optional) – See ConvBertModel.

  • position_ids (Tensor, optional) – See ConvBertModel.

  • attention_mask (Tensor, optional) – See ConvBertModel.

  • inputs_embeds (Tensor, optional) – See ConvBertModel.

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

  • output_hidden_states (bool, optional) – See ConvBertModel.

  • output_attentions (bool, optional) – See ConvBertModel.

  • 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 ConvBertForTokenClassification, ConvBertTokenizer

tokenizer = ConvBertTokenizer.from_pretrained('convbert-base')
model = ConvBertForTokenClassification.from_pretrained('convbert-base')

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

Bases: Layer

Parameters:

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

  • gen_weight (float) – This is the generator weight.

  • disc_weight (float) – This is the discriminator weight.

forward(generator_prediction_scores, discriminator_prediction_scores, generator_labels, discriminator_labels, attention_mask)[source]#

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters:

  • *inputs (tuple) – unpacked tuple arguments

  • **kwargs (dict) – unpacked dict arguments

class ConvBertForQuestionAnswering(config: ConvBertConfig)[source]#

Bases: ConvBertPretrainedModel

ConvBert 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:

config (ConvBertConfig) – An instance of ConvBertConfig

forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, start_positions: Tensor | None = None, end_positions: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[source]#

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

Parameters:

  • input_ids (Tensor) – See ConvBertModel.

  • token_type_ids (Tensor, optional) – See ConvBertModel.

  • position_ids (Tensor, optional) – See ConvBertModel.

  • attention_mask (Tensor, optional) – See ConvBertModel.

  • inputs_embeds (Tensor, optional) – See ConvBertModel.

  • 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) – See ConvBertModel.

  • output_attentions (bool, optional) – See ConvBertModel.

  • return_dict (bool, optional) – Whether to return a QuestionAnsweringModelOutput object. If False, the output will be a tuple of tensors. Defaults to False.

Returns:

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].

Return type:

tuple

Example

import paddle
from paddlenlp.transformers import ConvBertForQuestionAnswering, ConvBertTokenizer

tokenizer = ConvBertTokenizer.from_pretrained('convbert-base')
model = ConvBertForQuestionAnswering.from_pretrained('convbert-base')

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 ConvBertForMultipleChoice(config: ConvBertConfig)[source]#

Bases: ConvBertPretrainedModel

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

Parameters:

config (ConvBertConfig) – An instance of ConvBertConfig

forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, labels: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[source]#

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

Parameters:

  • input_ids (Tensor) – See ConvBertModel.

  • token_type_ids (Tensor, optional) – See ConvBertModel.

  • position_ids (Tensor, optional) – See ConvBertModel.

  • attention_mask (Tensor, optional) – See ConvBertModel.

  • inputs_embeds (Tensor, optional) – See ConvBertModel.

  • 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) – See ConvBertModel.

  • output_attentions (bool, optional) – See ConvBertModel.

  • return_dict (bool, optional) – Whether to return a QuestionAnsweringModelOutput object. If False, the output will be a tuple of tensors. Defaults to False.

Returns:

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

Return type:

Tensor

Example

import paddle
from paddlenlp.transformers import ConvBertForMultipleChoice, ConvBertTokenizer

tokenizer = ConvBertTokenizer.from_pretrained('convbert-base')
model = ConvBertForMultipleChoice.from_pretrained('convbert-base')

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

alias of ConvBertForTotalPretraining