modeling

class RoFormerv2Model(vocab_size, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act='relu', hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, pad_token_id=0, rotary_value=False, use_bias=False)[source]

Bases: paddlenlp.transformers.roformerv2.modeling.RoFormerv2PretrainedModel

The bare RoFormerv2 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 RoFormerv2Model. 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 RoFormerv2Model.

  • 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 "relu".

  • 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.

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

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

  • use_bias (bool, optional) – Whether or not use bias. Defaults to False.

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

The RoFormerv2Model 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.

  • 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 0.0 values and the others have 1.0 values. It is a tensor with shape broadcasted to [batch_size, num_attention_heads, sequence_length, sequence_length]. Currently, we only support 2D attention_mask. Defaults to None, which means pad_token_id will be ignored.

  • output_hidden_states (bool, optional) – Whether to return the output of each hidden layers. Defaults to False.

Returns

Returns sequence_output or encoder_outputs.

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].

  • encoder_outputs (List(Tensor)):

    A list of Tensor containing hidden-states of the model at each hidden layer in the Transformer encoder. The length of the list is num_hidden_layers. Each Tensor has a data type of float32 and its shape is [batch_size, sequence_length, hidden_size].

Return type

tuple

Example

import paddle
from paddlenlp.transformers import RoFormerv2Model, RoFormerv2Tokenizer

tokenizer = RoFormerv2Tokenizer.from_pretrained('roformer_v2_chinese_char_base')
model = RoFormerv2Model.from_pretrained('roformer_v2_chinese_char_base')

inputs = tokenizer("欢迎使用百度飞桨!")
inputs = {k:paddle.to_tensor([v], dtype="int64") for (k, v) in inputs.items()}
output = model(**inputs)
get_input_embeddings()paddle.nn.layer.common.Embedding[source]

get input embedding of model

Returns

embedding of model

Return type

nn.Embedding

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

class RoFormerv2ForMaskedLM(roformerv2)[source]

Bases: paddlenlp.transformers.roformerv2.modeling.RoFormerv2PretrainedModel

RoFormerv2 Model with a masked language modeling head on top.

Parameters

roformerv2 (RoFormerv2Model) – An instance of RoFormerv2Model.

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

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

Return type

Tensor

Example

import paddle
from paddlenlp.transformers import RoFormerv2ForMaskedLM, RoFormerv2Tokenizer

tokenizer = RoFormerv2Tokenizer.from_pretrained('roformer_v2_chinese_char_base')
model = RoFormerv2ForMaskedLM.from_pretrained('roformer_v2_chinese_char_base')

inputs = tokenizer("欢迎使用百度飞桨!")
inputs = {k:paddle.to_tensor([v], dtype="int64") for (k, v) in inputs.items()}

logits = model(**inputs)
print(logits.shape)
# [1, 11, 12000]
class RoFormerv2PretrainedModel(*args, **kwargs)[source]

Bases: paddlenlp.transformers.model_utils.PretrainedModel

An abstract class for pretrained RoFormerv2 models. It provides RoFormerv2 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)[source]

Initialization hook

base_model_class

alias of paddlenlp.transformers.roformerv2.modeling.RoFormerv2Model

class RoFormerv2ForSequenceClassification(roformerv2, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.roformerv2.modeling.RoFormerv2PretrainedModel

RoFormerv2 Model with a linear layer on top of the output layer, designed for sequence classification/regression tasks like GLUE tasks.

Parameters
  • roformerv2 (RoFormerv2Model) – An instance of paddlenlp.transformers.RoFormerv2Model.

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

  • dropout (float, optional) – The dropout probability for output of RoFormerv2. If None, use the same value as hidden_dropout_prob of paddlenlp.transformers.RoFormerv2Model instance. Defaults to None.

forward(input_ids, token_type_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 RoFormerv2ForSequenceClassification, RoFormerv2Tokenizer

tokenizer = RoFormerv2Tokenizer.from_pretrained('roformer_v2_chinese_char_base')
model = RoFormerv2ForSequenceClassification.from_pretrained('roformer_v2_chinese_char_base')

inputs = tokenizer("欢迎使用百度飞桨!")
inputs = {k:paddle.to_tensor([v], dtype="int64") for (k, v) in inputs.items()}
logits = model(**inputs)
class RoFormerv2ForTokenClassification(roformerv2, num_classes=2, dropout=None)[source]

Bases: paddlenlp.transformers.roformerv2.modeling.RoFormerv2PretrainedModel

RoFormerv2 Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks.

Parameters
  • roformerv2 (RoFormerv2Model) – An instance of paddlenlp.transformers.RoFormerv2Model.

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

  • dropout (float, optional) – The dropout probability for output of RoFormerv2. If None, use the same value as hidden_dropout_prob of paddlenlp.transformers.RoFormerv2Model instance. Defaults to None.

forward(input_ids, token_type_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 RoFormerv2ForTokenClassification, RoFormerv2Tokenizer

tokenizer = RoFormerv2Tokenizer.from_pretrained('roformer_v2_chinese_char_base')
model = RoFormerv2ForTokenClassification.from_pretrained('roformer_v2_chinese_char_base')

inputs = tokenizer("欢迎使用百度飞桨!")
inputs = {k:paddle.to_tensor([v], dtype="int64") for (k, v) in inputs.items()}
logits = model(**inputs)
class RoFormerv2ForQuestionAnswering(roformerv2, dropout=None)[source]

Bases: paddlenlp.transformers.roformerv2.modeling.RoFormerv2PretrainedModel

RoFormerv2 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
  • roformerv2 (RoFormerv2Model) – An instance of RoFormerv2Model.

  • dropout (float, optional) – The dropout probability for output of RoFormerv2. If None, use the same value as hidden_dropout_prob of RoFormerv2Model instance roformerv2. Defaults to None.

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

The RoFormerv2ForQuestionAnswering 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 RoFormerv2ForQuestionAnswering, RoFormerv2Tokenizer

tokenizer = RoFormerv2Tokenizer.from_pretrained('roformer_v2_chinese_char_base')
model = RoFormerv2ForQuestionAnswering.from_pretrained('roformer_v2_chinese_char_base')

inputs = tokenizer("欢迎使用百度飞桨!")
inputs = {k:paddle.to_tensor([v], dtype="int64") for (k, v) in inputs.items()}
outputs = model(**inputs)

start_logits = outputs[0]
end_logits = outputs[1]
class RoFormerv2ForMultipleChoice(roformerv2, num_choices=2, dropout=None)[source]

Bases: paddlenlp.transformers.roformerv2.modeling.RoFormerv2PretrainedModel

RoFormerv2 Model with a linear layer on top of the hidden-states output layer, designed for multiple choice tasks like RocStories/SWAG tasks.

Parameters
  • roformerv2 (RoFormerv2Model) – An instance of RoFormerv2Model.

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

  • dropout (float, optional) – The dropout probability for output of RoFormerv2. If None, use the same value as hidden_dropout_prob of RoFormerv2Model instance roformerv2. Defaults to None.

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

The RoFormerv2ForMultipleChoice forward method, overrides the __call__() special method.

Parameters
  • input_ids (Tensor) – See RoFormerv2Model and shape as [batch_size, num_choice, sequence_length].

  • token_type_ids (Tensor, optional) – See RoFormerv2Model and shape as [batch_size, num_choice, sequence_length].

  • attention_mask (list, optional) – See RoFormerv2Model 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

import paddle
from paddlenlp.transformers import RoFormerv2ForMultipleChoice, RoFormerv2Tokenizer
from paddlenlp.data import Pad

tokenizer = RoFormerv2Tokenizer.from_pretrained('roformer_v2_chinese_char_base')
model = RoFormerv2ForMultipleChoice.from_pretrained('roformer_v2_chinese_char_base', num_choices=2)

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"])

inputs = tokenizer(text, text_pair)
input_ids = Pad(axis=0, pad_val=tokenizer.pad_token_id)(inputs["input_ids"])
token_type_ids = Pad(axis=0, pad_val=tokenizer.pad_token_type_id)(inputs["token_type_ids"])

reshaped_logits = model(
    input_ids=paddle.to_tensor(input_ids, dtype="int64"),
    token_type_ids=paddle.to_tensor(token_type_ids, dtype="int64"),
)
print(reshaped_logits.shape)
# [2, 2]