modeling

class MPNetModel(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=514, initializer_range=0.02, relative_attention_num_buckets=32, layer_norm_eps=1e-05, pad_token_id=1)[source]

Bases: paddlenlp.transformers.mpnet.modeling.MPNetPretrainedModel

The bare MPNet 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 MPNetModel. 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 MPNetModel.

  • hidden_size (int, optional) – Dimensionality of the embedding layer, encoder layer 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 514.

  • initializer_range (float, optional) –

    The standard deviation of the normal initializer. Defaults to 0.02.

    Note

    A normal_initializer initializes weight matrices as normal distributions. See MPNetPretrainedModel.init_weights() for how weights are initialized in MPNetModel.

  • relative_attention_num_buckets (int, optional) – The number of buckets to use for each attention layer. Defaults to 32.

  • layer_norm_eps (float, optional) – The epsilon used by the layer normalization layers. Defaults to 1e-5.

  • pad_token_id (int, optional) – The index of padding token in the token vocabulary. Defaults to 1.

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

The MPNetModel 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].

  • 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.

Returns

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 (<s>) 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].

Return type

tuple

Example

import paddle
from paddlenlp.transformers import MPNetModel, MPNetTokenizer

tokenizer = MPNetTokenizer.from_pretrained('mpnet-base')
model = MPNetModel.from_pretrained('mpnet-base')

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

Bases: paddlenlp.transformers.model_utils.PretrainedModel

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

init_weights(layer)[source]

Initialization hook

base_model_class

alias of paddlenlp.transformers.mpnet.modeling.MPNetModel

class MPNetForMaskedLM(mpnet)[source]

Bases: paddlenlp.transformers.mpnet.modeling.MPNetPretrainedModel

MPNet Model with a language modeling head on top.

Parameters

MPNet (MPNetModel) – An instance of MPNetModel.

forward(input_ids, position_ids=None, attention_mask=None, labels=None)[source]
Parameters
  • input_ids (Tensor) – See MPNetModel.

  • position_ids (Tensor, optional) – See MPNetModel.

  • attention_mask (Tensor, optional) – See MPNetModel.

  • labels (Tensor, optional) – The Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., vocab_size] Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., vocab_size] Its shape is [batch_size, sequence_length].

Returns

Returns tuple (masked_lm_loss, prediction_scores, ``sequence_output`).

With the fields:

  • masked_lm_loss (Tensor):

    The masked lm loss. Its data type should be float32 and its shape is [1].

  • prediction_scores (Tensor):

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

  • sequence_output (Tensor):

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

Return type

tuple

class MPNetForSequenceClassification(mpnet, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.mpnet.modeling.MPNetPretrainedModel

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

Parameters
  • mpnet (MPNetModel) – An instance of MPNetModel.

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

  • dropout (float, optional) – The dropout probability for output of MPNet. If None, use the same value as hidden_dropout_prob of MPNetModel instance mpnet. Defaults to None.

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

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

Parameters
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 MPNetForSequenceClassification, MPNetTokenizer

tokenizer = MPNetTokenizer.from_pretrained('mpnet-base')
model = MPNetForSequenceClassification.from_pretrained('mpnet-base')

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

logits = outputs[0]
class MPNetForMultipleChoice(mpnet, num_choices=2, dropout=None)[source]

Bases: paddlenlp.transformers.mpnet.modeling.MPNetPretrainedModel

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

Parameters
  • mpnet (MPNetModel) – An instance of MPNetModel.

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

  • dropout (float, optional) – The dropout probability for output of MPNet. If None, use the same value as hidden_dropout_prob of MPNetModel instance mpnet. Defaults to None.

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

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

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

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

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

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

class MPNetForTokenClassification(mpnet, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.mpnet.modeling.MPNetPretrainedModel

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

Parameters
  • mpnet (MPNetModel) – An instance of MPNetModel.

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

  • dropout (float, optional) – The dropout probability for output of MPNet. If None, use the same value as hidden_dropout_prob of MPNetModel instance mpnet. Defaults to None.

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

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

Parameters
Returns

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

Return type

Tensor

Example

import paddle
from paddlenlp.transformers import MPNetForTokenClassification, MPNetTokenizer

tokenizer = MPNetTokenizer.from_pretrained('mpnet-base')
model = MPNetForTokenClassification.from_pretrained('mpnet-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 MPNetForQuestionAnswering(mpnet, num_classes=2)[source]

Bases: paddlenlp.transformers.mpnet.modeling.MPNetPretrainedModel

MPNet 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
  • mpnet (MPNetModel) – An instance of MPNetModel.

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

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

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

Parameters
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 MPNetForQuestionAnswering, MPNetTokenizer

tokenizer = MPNetTokenizer.from_pretrained('mpnet-base')
model = MPNetForQuestionAnswering.from_pretrained('mpnet-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]