modeling

class ErnieMModel(vocab_size, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, hidden_act='gelu', hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=514, initializer_range=0.02, pad_token_id=1)[source]

Bases: paddlenlp.transformers.ernie_m.modeling.ErnieMPretrainedModel

The bare ERNIE-M 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 ErnieMModel. 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 ErnieMModel.

  • 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 ErnieMPretrainedModel._init_weights() for how weights are initialized in ErnieMModel.

  • 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]
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].

  • 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]. 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 ([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].

Return type

tuple

Example

import paddle
from paddlenlp.transformers import ErnieMModel, ErnieMTokenizer

tokenizer = ErnieMTokenizer.from_pretrained('ernie-m-base')
model = ErnieMModel.from_pretrained('ernie-m-base')

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 ErnieMPretrainedModel(name_scope=None, dtype='float32')[source]

Bases: paddlenlp.transformers.model_utils.PretrainedModel

An abstract class for pretrained ERNIE-M models. It provides ERNIE-M 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_m.modeling.ErnieMModel

class ErnieMForSequenceClassification(ernie_m, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.ernie_m.modeling.ErnieMPretrainedModel

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

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

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

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

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

tokenizer = ErnieMTokenizer.from_pretrained('ernie-m-base')
model = ErnieMForSequenceClassification.from_pretrained('ernie-m-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 ErnieMForTokenClassification(ernie_m, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.ernie_m.modeling.ErnieMPretrainedModel

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

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

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

  • dropout (float, optional) – The dropout probability for output of ERNIE-M. If None, use the same value as hidden_dropout_prob of ErnieMModel instance ernie_m. Defaults to None.

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

tokenizer = ErnieMTokenizer.from_pretrained('ernie-m-base')
model = ErnieMForTokenClassification.from_pretrained('ernie-m-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 ErnieMForQuestionAnswering(ernie_m)[source]

Bases: paddlenlp.transformers.ernie_m.modeling.ErnieMPretrainedModel

Ernie-M 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 (ErnieMModel) – An instance of ErnieMModel.

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

tokenizer = ErnieMTokenizer.from_pretrained('ernie-m-base')
model = ErnieMForQuestionAnswering.from_pretrained('ernie-m-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 ErnieMForMultipleChoice(ernie_m, num_choices=2, dropout=None)[source]

Bases: paddlenlp.transformers.ernie_m.modeling.ErnieMPretrainedModel

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

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

  • 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 ErnieMModel instance ernie-m. Defaults to None.

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

The ErnieMForMultipleChoice forward method, overrides the __call__() special method. :param input_ids: See ErnieMModel and shape as [batch_size, num_choice, sequence_length]. :type input_ids: Tensor :param position_ids: See ErnieMModel and shape as [batch_size, num_choice, sequence_length]. :type position_ids: Tensor, optional :param attention_mask: See ErnieMModel and shape as [batch_size, num_choice, sequence_length]. :type attention_mask: list, optional

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