modeling

class RoFormerModel(vocab_size, embedding_size=768, 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=1536, type_vocab_size=2, initializer_range=0.02, pad_token_id=0, eos_token_id=102, pool_act='tanh', rotary_value=False)[源代码]

基类:paddlenlp.transformers.roformer.modeling.RoFormerPretrainedModel

The bare RoFormerModel 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.

参数
  • vocab_size (int) -- Vocabulary size of inputs_ids in RoFormerModel. 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 RoFormerModel.

  • embedding_size (int, optional) -- Dimensionality of the embedding layer. Defaults to 768.

  • hidden_size (int, optional) -- Dimensionality of the, 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 token_type_ids. Defaults to 2.

  • initializer_range (float, optional) --

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

    注解

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

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

  • eos_token_id (int, optional) -- The id of the eos token. Defaults to 102.

  • pool_act (str, optional) -- The non-linear activation function in the pooler. Defaults to "tanh".

  • rotary_value (bool, optional) -- Whether or not apply rotay position embeddings to value. Defaults to False.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, past_key_values: Optional[Tuple[Tuple[paddle.Tensor]]] = None, use_cache: Optional[bool] = None, output_hidden_states: Optional[bool] = None, output_attentions: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]

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

参数
  • input_ids (Tensor, optional) -- 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 first and second portions of the inputs. Indices can be either 0 or 1:

    • 0 corresponds to a sentence A token,

    • 1 corresponds to a sentence B token.

    It's data type should be int64 and has a shape of [batch_size, sequence_length]. Defaults to None, which means no segment embeddings is added to token embeddings.

  • attention_mask (Tensor, optional) -- Mask used in multi-head attention to avoid performing attention 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.

  • 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.

返回

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.

示例

import paddle
from paddlenlp.transformers import RoFormerModel, RoFormerTokenizer

tokenizer = RoFormerTokenizer.from_pretrained('roformer-chinese-char-base')
model = RoFormerModel.from_pretrained('roformer-chinese-char-base')

tokenized_inputs = tokenizer("欢迎使用百度飞桨!", return_tensors="pd")
output = model(**tokenized_inputs)
get_input_embeddings()paddle.nn.layer.common.Embedding[源代码]

get input embedding of model

返回

embedding of model

返回类型

nn.Embedding

set_input_embeddings(embedding: paddle.nn.layer.common.Embedding)[源代码]

set new input embedding for model

参数

value (Embedding) -- the new embedding of model

引发

NotImplementedError -- Model has not implement set_input_embeddings method

class RoFormerPretrainedModel(*args, **kwargs)[源代码]

基类:paddlenlp.transformers.model_utils.PretrainedModel

An abstract class for pretrained RoFormer models. It provides RoFormer 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.

init_weights(layer)[源代码]

Initialization hook

base_model_class

alias of paddlenlp.transformers.roformer.modeling.RoFormerModel

class RoFormerForSequenceClassification(roformer, num_classes=2, dropout=None)[源代码]

基类:paddlenlp.transformers.roformer.modeling.RoFormerPretrainedModel

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

参数
  • roformer (RoFormerModel) -- An instance of RoFormerModel.

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

  • dropout (float, optional) -- The dropout probability for output of RoFormer. If None, use the same value as hidden_dropout_prob of RoFormerModel instance roformer. Defaults to None.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_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)[源代码]

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

参数
  • input_ids (Tensor) -- See RoFormerModel.

  • token_type_ids (Tensor, optional) -- See RoFormerModel.

  • attention_mask (Tensor, optional) -- See RoFormerModel.

  • inputs_embeds (Tensor, optional) -- See RoFormerModel.

  • 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.

返回

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.

示例

import paddle
from paddlenlp.transformers import RoFormerForSequenceClassification, RoFormerTokenizer

tokenizer = RoFormerTokenizer.from_pretrained('roformer-chinese-char-base')
model = RoFormerForSequenceClassification.from_pretrained('roformer-chinese-char-base')

tokenized_inputs = tokenizer("欢迎使用百度飞桨!", return_tensors="pd")
logits = model(**tokenized_inputs)
class RoFormerForTokenClassification(roformer, num_classes=2, dropout=None)[源代码]

基类:paddlenlp.transformers.roformer.modeling.RoFormerPretrainedModel

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

参数
  • roformer (RoFormerModel) -- An instance of RoFormerModel.

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

  • dropout (float, optional) -- The dropout probability for output of RoFormer. If None, use the same value as hidden_dropout_prob of RoFormerModel instance roformer. Defaults to None.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_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)[源代码]

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

参数
  • input_ids (Tensor) -- See RoFormerModel.

  • token_type_ids (Tensor, optional) -- See RoFormerModel.

  • attention_mask (Tensor, optional) -- See RoFormerModel.

  • inputs_embeds (Tensor, optional) -- See RoFormerModel.

  • 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.

返回

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.

示例

import paddle
from paddlenlp.transformers import RoFormerForTokenClassification, RoFormerTokenizer

tokenizer = RoFormerTokenizer.from_pretrained('roformer-chinese-char-base')
model = RoFormerForTokenClassification.from_pretrained('roformer-chinese-char-base')

tokenized_inputs = tokenizer("欢迎使用百度飞桨!", return_tensors="pd")
logits = model(**tokenized_inputs)
class RoFormerForQuestionAnswering(roformer, dropout=None)[源代码]

基类:paddlenlp.transformers.roformer.modeling.RoFormerPretrainedModel

RoFormer 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.

参数
  • roformer (RoFormerModel) -- An instance of RoFormerModel.

  • dropout (float, optional) -- The dropout probability for output of RoFormer. If None, use the same value as hidden_dropout_prob of RoFormerModel instance roformer. Defaults to None.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_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)[源代码]

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

参数
  • input_ids (Tensor) -- See RoFormerModel.

  • token_type_ids (Tensor, optional) -- See RoFormerModel.

  • attention_mask (Tensor, optional) -- See RoFormerModel.

  • inputs_embeds (Tensor, optional) -- See RoFormerModel.

  • 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.

返回

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.

示例

import paddle
from paddlenlp.transformers import RoFormerForQuestionAnswering, RoFormerTokenizer

tokenizer = RoFormerTokenizer.from_pretrained('roformer-chinese-char-base')
model = RoFormerForQuestionAnswering.from_pretrained('roformer-chinese-char-base')

tokenized_inputs = tokenizer("欢迎使用百度飞桨!", return_tensors="pd")
outputs = model(**tokenized_inputs)
class RoFormerForMaskedLM(roformer)[源代码]

基类:paddlenlp.transformers.roformer.modeling.RoFormerPretrainedModel

RoFormer Model with a masked language modeling head on top.

参数

( (roformer) -- class:RoFormerModel`): An instance of RoFormerModel.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_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)[源代码]

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

参数
  • input_ids (Tensor) -- See RoFormerModel.

  • token_type_ids (Tensor, optional) -- See RoFormerModel.

  • attention_mask (Tensor, optional) -- See RoFormerModel.

  • inputs_embeds (Tensor, optional) -- See RoFormerModel.

  • 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.

返回

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.

示例

import paddle
from paddlenlp.transformers import RoFormerForMaskedLM, RoFormerTokenizer

tokenizer = RoFormerTokenizer.from_pretrained('roformer-chinese-char-base')
model = RoFormerForMaskedLM.from_pretrained('roformer-chinese-char-base')

tokenized_inputs = tokenizer("欢迎使用百度飞桨!", return_tensors="pd")
logits = model(**tokenized_inputs)
class RoFormerForMultipleChoice(roformer, num_choices=2, dropout=None)[源代码]

基类:paddlenlp.transformers.roformer.modeling.RoFormerPretrainedModel

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

参数
  • roformer (RoFormerModel) -- An instance of RoFormerModel.

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

  • dropout (float, optional) -- The dropout probability for output of RoFormer. If None, use the same value as hidden_dropout_prob of RoFormerModel instance roformer. Defaults to None.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_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)[源代码]

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

参数
  • input_ids (Tensor) -- See RoFormerModel and shape as [batch_size, num_choice, sequence_length].

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

  • attention_mask (Tensor, optional) -- See RoFormerModel and shape as [batch_size, num_choice, sequence_length].

  • inputs_embeds (Tensor, optional) -- See RoFormerModel.

  • 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.

返回

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.

示例

import paddle
from paddlenlp.transformers import RoFormerForMultipleChoice, RoFormerTokenizer

tokenizer = RoFormerTokenizer.from_pretrained('roformer-chinese-char-base')
model = RoFormerForMultipleChoice.from_pretrained('roformer-chinese-char-base')

data = [
    {
        "question": "如何打开ipad屏幕?",
        "answer1": "按音量按钮。",
        "answer2": "按下锁定按钮。",
        "label": 1,
    },
    {
        "question": "如何缩进一些文本?",
        "answer1": "在开始写之前留一些空格。",
        "answer2": "按空格键。",
        "label": 0,
    },
]

text = []
text_pair = []
for d in data:
    text.append(d["question"])
    text_pair.append(d["answer1"])
    text.append(d["question"])
    text_pair.append(d["answer2"])

tokenized_inputs = tokenizer(text, text_pair, padding=True, return_tensors="pd")
reshaped_logits = model(**tokenized_inputs)
print(reshaped_logits.shape)
# [2, 2]
class RoFormerForCausalLM(roformer)[源代码]

基类:paddlenlp.transformers.roformer.modeling.RoFormerPretrainedModel

RoFormer Model with a Causal language modeling head on top.

参数

( (roformer) -- class:RoFormerModel`): An instance of RoFormerModel.

forward(input_ids: Optional[paddle.Tensor] = None, token_type_ids: Optional[paddle.Tensor] = None, attention_mask: Optional[paddle.Tensor] = None, inputs_embeds: Optional[paddle.Tensor] = None, labels: Optional[paddle.Tensor] = None, past_key_values: Optional[Tuple[Tuple[paddle.Tensor]]] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None)[源代码]

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

参数
  • input_ids (Tensor) -- See RoFormerModel.

  • token_type_ids (Tensor, optional) -- See RoFormerModel.

  • attention_mask (Tensor, optional) -- See RoFormerModel.

  • inputs_embeds (Tensor, optional) -- See RoFormerModel.

  • labels (Tensor of shape (batch_size, sequence_length), optional) -- Labels for computing the left-to-right language modeling loss (next word prediction). 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].

  • past_key_values (tuple(tuple(Tensor)), optional) -- See RoFormerModel.

  • use_cache (Tensor, optional) -- See RoFormerModel.

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

返回

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

示例

import paddle
from paddlenlp.transformers import RoFormerForCausalLM, RoFormerTokenizer

tokenizer = RoFormerTokenizer.from_pretrained('roformer-chinese-sim-char-ft-base')
model = RoFormerForCausalLM.from_pretrained('roformer-chinese-sim-char-ft-base')

tokenized_inputs = tokenizer("欢迎使用百度飞桨!", return_tensors="pd")
logits = model(**tokenized_inputs)
print(logits.shape)
# [1, 11, 12000]