modeling¶
-
class
RobertaModel
(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=512, type_vocab_size=16, initializer_range=0.02, pad_token_id=0, layer_norm_eps=1e-12, cls_token_id=101)[源代码]¶ 基类:
paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel
The bare Roberta Model 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
inRobertaModel
. Also is the vocab size of token embedding matrix. Defines the number of different tokens that can be represented by theinputs_ids
passed when callingRobertaModel
.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
tointermediate_size
, and then projected back tohidden_size
. Typicallyintermediate_size
is larger thanhidden_size
. Defaults to3072
.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
passed when callingRobertaModel
. Defaults to2
.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
RobertaPretrainedModel._init_weights()
for how weights are initialized inRobertaModel
.pad_token_id (int, optional) -- The index of padding token in the token vocabulary. Defaults to
0
.cls_token_id (int, optional) -- The index of cls token in the token vocabulary. Defaults to
101
.
-
forward
(input_ids, token_type_ids=None, position_ids=None, attention_mask=None, output_hidden_states=False)[源代码]¶ - 参数
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].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.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]
. It's data type should beint64
and has a shape of [batch_size, sequence_length]. Defaults toNone
.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 haveFalse
values and the others haveTrue
values. When the data type is int, themasked
tokens have0
values and the others have1
values. When the data type is float, themasked
tokens have-INF
values and the others have0
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 toNone
, which means nothing needed to be prevented attention to.output_hidden_states (bool, optional) -- Whether or not to output hidden states for all hidden layers. Defaults to
False
.
- 返回
Returns tuple (
sequence_output
,pooled_output
) by default. Returns (encoder_outputs
,pooled_output
) if output_hidden_states isTrue
.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].
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].
- 返回类型
tuple
示例
import paddle from paddlenlp.transformers import RobertaModel, RobertaTokenizer tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext') model = RobertaModel.from_pretrained('roberta-wwm-ext') 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
RobertaPretrainedModel
(name_scope=None, dtype='float32')[源代码]¶ 基类:
paddlenlp.transformers.model_utils.PretrainedModel
An abstract class for pretrained RoBerta models. It provides RoBerta related
model_config_file
,pretrained_init_configuration
,resource_files_names
,pretrained_resource_files_map
,base_model_prefix
for downloading and loading pretrained models. SeePretrainedModel
for more details.-
base_model_class
¶ alias of
paddlenlp.transformers.roberta.modeling.RobertaModel
-
-
class
RobertaForSequenceClassification
(roberta, num_classes=2, dropout=None)[源代码]¶ 基类:
paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel
Roberta Model with a linear layer on top of the output layer, designed for sequence classification/regression tasks like GLUE tasks.
- 参数
roberta (
RobertaModel
) -- An instance ofRobertaModel
.num_classes (int, optional) -- The number of classes. Defaults to
2
.dropout (float, optional) -- The dropout probability for output of Roberta. If None, use the same value as
hidden_dropout_prob
ofRobertaModel
instanceroberta
. Defaults toNone
.
-
forward
(input_ids, token_type_ids=None, position_ids=None, attention_mask=None, output_hidden_states=False)[源代码]¶ - 参数
input_ids (Tensor) -- See
RobertaModel
.token_type_ids (Tensor, optional) -- See
RobertaModel
.position_ids (Tensor, optional) -- See
RobertaModel
.attention_mask (Tensor, optional) -- See
RobertaModel
.output_hidden_states (bool, optional) -- See
RobertaModel
.
- 返回
Returns tensor
logits
by default. Returns tuple (logits
,encoder_outputs
) if output_hidden_states is set toTrue
.With the fields:
logits
(Tensor):a tensor of the input text classification logits. Its data type should be float32 and it has a shape of [batch_size, num_classes].
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 a shape of [batch_size, sequence_length, hidden_size].
- 返回类型
Tensor or tuple
示例
import paddle from paddlenlp.transformers import RobertaForSequenceClassification, RobertaTokenizer tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext') model = RobertaForSequenceClassification.from_pretrained('roberta-wwm-ext') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
-
class
RobertaForTokenClassification
(roberta, num_classes=2, dropout=None)[源代码]¶ 基类:
paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel
Roberta Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks.
- 参数
roberta (
RobertaModel
) -- An instance ofRobertaModel
.num_classes (int, optional) -- The number of classes. Defaults to
2
.dropout (float, optional) -- The dropout probability for output of Roberta. If None, use the same value as
hidden_dropout_prob
ofRobertaModel
instanceroberta
. Defaults toNone
.
-
forward
(input_ids, token_type_ids=None, position_ids=None, attention_mask=None, output_hidden_states=False)[源代码]¶ - 参数
input_ids (Tensor) -- See
RobertaModel
.token_type_ids (Tensor, optional) -- See
RobertaModel
.position_ids (Tensor, optional) -- See
RobertaModel
.attention_mask (Tensor, optional) -- See
RobertaModel
.output_hidden_states (bool, optional) -- See
RobertaModel
.
- 返回
Returns tensor
logits
by default. Returns tuple (logits
,encoder_outputs
) if output_hidden_states is set toTrue
.With the fields:
logits
(Tensor):a tensor of the input token classification logits. Shape as
[batch_size, sequence_length, num_classes]
and dtype asfloat32
.
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 a shape of [batch_size, sequence_length, hidden_size].
- 返回类型
Tensor or tuple
示例
import paddle from paddlenlp.transformers import RobertaForTokenClassification, RobertaTokenizer tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext') model = RobertaForTokenClassification.from_pretrained('roberta-wwm-ext') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
-
class
RobertaForQuestionAnswering
(roberta)[源代码]¶ 基类:
paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel
- Roberta 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
roberta (
RobertaModel
) -- An instance of RobertaModel.
-
forward
(input_ids, token_type_ids=None, position_ids=None, attention_mask=None, output_hidden_states=False)[源代码]¶ - 参数
input_ids (Tensor) -- See
RobertaModel
.token_type_ids (Tensor, optional) -- See
RobertaModel
.position_ids (Tensor, optional) -- See
RobertaModel
.attention_mask (Tensor, optional) -- See
RobertaModel
.output_hidden_states (bool, optional) -- See
RobertaModel
.
- 返回
Returns tuple (
start_logits
,end_logits
) by default if output_hidden_states isFalse
. Returns tuple (start_logits
,end_logits
,encoder_outputs
) if output_hidden_states is set toTrue
.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].
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 a shape of [batch_size, sequence_length, hidden_size].
- 返回类型
tuple
示例
import paddle from paddlenlp.transformers import RobertaForSequenceClassification, RobertaTokenizer tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext') model = RobertaForSequenceClassification.from_pretrained('roberta-wwm-ext') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
- Roberta Model with a linear layer on top of the hidden-states output to compute
-
class
RobertaForMaskedLM
(roberta)[源代码]¶ 基类:
paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel
Roberta Model with a
masked language modeling
head on top.- 参数
( (bert) -- class:RobertaModel`): An instance of
RobertaModel
.
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, output_hidden_states=False)[源代码]¶ - 参数
input_ids (Tensor) -- See
RobertaModel
.token_type_ids (Tensor, optional) -- See
RobertaModel
.position_ids (Tensor, optional) -- See
RobertaModel
.attention_mask (Tensor, optional) -- See
RobertaModel
.output_hidden_states (bool, optional) -- See
RobertaModel
.
- 返回
Returns tensor
prediction_scores
by default. Returns tuple (prediction_scores
,encoder_outputs
) if output_hidden_states is set toTrue
.With the fields:
prediction_scores
(Tensor):The scores of masked token prediction. Its data type should be float32 and shape is [batch_size, sequence_length, vocab_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 a shape of [batch_size, sequence_length, hidden_size].
- 返回类型
Tensor or tuple
示例
import paddle from paddlenlp.transformers import RobertaForMaskedLM, RobertaTokenizer tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext') model = RobertaForMaskedLM.from_pretrained('roberta-wwm-ext') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs) print(logits.shape) # [1, 13, 30522]
-
class
RobertaForMultipleChoice
(roberta)[源代码]¶ 基类:
paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel
-
class
RobertaForCausalLM
(roberta)[源代码]¶ 基类:
paddlenlp.transformers.roberta.modeling.RobertaPretrainedModel
Roberta Model with a
Causal language modeling
head on top.- 参数
( (bert) -- class:RobertaModel`): An instance of
RobertaModel
.
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, output_hidden_states=False)[源代码]¶ - 参数
input_ids (Tensor) -- See
RobertaModel
.token_type_ids (Tensor, optional) -- See
RobertaModel
.position_ids (Tensor, optional) -- See
RobertaModel
.attention_mask (Tensor, optional) -- See
RobertaModel
.output_hidden_states (bool, optional) -- See
RobertaModel
.
- 返回
Returns tensor
prediction_scores
by default. Returns tuple (prediction_scores
,encoder_outputs
) if output_hidden_states is set toTrue
.With the fields:
prediction_scores
(Tensor):The scores of masked token prediction. Its data type should be float32 and shape is [batch_size, sequence_length, vocab_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 a shape of [batch_size, sequence_length, hidden_size].
- 返回类型
Tensor or tuple
示例
import paddle from paddlenlp.transformers import RobertaForCausalLM, RobertaTokenizer tokenizer = RobertaTokenizer.from_pretrained('roberta-wwm-ext') model = RobertaForCausalLM.from_pretrained('roberta-wwm-ext') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs) print(logits.shape) # [1, 13, 30522]