modeling

class PPMiniLMModel(vocab_size, vocab_file, 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, do_lower_case=True, is_split_into_words=False, max_seq_len=128, pad_to_max_seq_len=False)[source]

Bases: paddlenlp.transformers.ppminilm.modeling.PPMiniLMPretrainedModel

The bare PPMiniLM 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 PPMiniLMModel. 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 PPMiniLMModel.

  • 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 PPMiniLMPretrainedModel._init_weights() for how weights are initialized in PPMiniLMModel.

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

forward(input_ids, token_type_ids=None, position_ids=None, attention_mask=None)[source]
Parameters
  • input_ids (Tensor, List[string]) – If input_ids is a Tensor object, it is an 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]. If input_ids is a list of string, self.use_faster_tokenizer should be True, and the network contains faster_tokenizer operator.

  • token_type_ids (Tensor, string, optional) –

    If token_type_ids is a Tensor object: 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.

    If token_type_ids is a list of string: self.use_faster_tokenizer should be True, and the network contains faster_tokenizer operator.

  • 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 PPMiniLM, 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.

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 PPMiniLMModel, PPMiniLMTokenizer

tokenizer = PPMiniLMTokenizer.from_pretrained('ppminilm-6l-768h')
model = PPMiniLMModel.from_pretrained('ppminilm-6l-768h')

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

Bases: paddlenlp.experimental.model_utils.FasterPretrainedModel

An abstract class for pretrained PPMiniLM models. It provides PPMiniLM 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.ppminilm.modeling.PPMiniLMModel

class PPMiniLMForSequenceClassification(ppminilm, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.ppminilm.modeling.PPMiniLMPretrainedModel

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

Parameters
  • ppminilm (PPMiniLMModel) – An instance of paddlenlp.transformers.PPMiniLMModel.

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

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

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

  • token_type_ids (Tensor, optional) – See PPMiniLMModel.

  • position_ids (Tensor, optional) – See PPMiniLMModel.

  • attention_mask (Tensor, optional) – See MiniLMModel.

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 PPMiniLMForSequenceClassification, PPMiniLMTokenizer

tokenizer = PPMiniLMTokenizer.from_pretrained('ppminilm-6l-768h')
model = PPMiniLMForSequenceClassification.from_pretrained('ppminilm-6l-768h0')

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

Bases: paddlenlp.transformers.ppminilm.modeling.PPMiniLMPretrainedModel

PPMiniLM 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

ppminilm (PPMiniLMModel) – An instance of PPMiniLMModel.

forward(input_ids, token_type_ids=None, 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 PPMiniLMForQuestionAnswering, PPMiniLMTokenizer

tokenizer = PPMiniLMTokenizer.from_pretrained('ppminilm-6l-768h')
model = PPMiniLMForQuestionAnswering.from_pretrained('ppminilm-6l-768h')

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

Bases: paddlenlp.transformers.ppminilm.modeling.PPMiniLMPretrainedModel

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

Parameters
  • ppminilm (PPMiniLMModel) – An instance of PPMiniLMModel.

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

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

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

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

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

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

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

  • attention_mask (list, optional) – See PPMiniLMModel 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