modeling¶
-
class
ChineseBertModel
(vocab_size=23236, 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, pool_act='tanh', layer_norm_eps=1e-12, glyph_embedding_dim=1728, pinyin_map_len=32)[源代码]¶ 基类:
paddlenlp.transformers.chinesebert.modeling.ChineseBertPretrainedModel
The bare ChineseBert 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.
- 参数
vocab_size (int) -- Vocabulary size of
inputs_ids
inBChineseBertModel
. Also is the vocab size of token embedding matrix. Defines the number of different tokens that can be represented by theinputs_ids
passed when callingChineseBertModel
.hidden_size (int, optional) -- Dimensionality of the embedding layer, encoder layer 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
token_type_ids
. 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
BertPretrainedModel.init_weights()
for how weights are initialized inBertModel
.pad_token_id (int, optional) -- The index of padding token in the token vocabulary. Defaults to
0
.pooled_act (str, optional) -- The non-linear activation function in the pooling layer. Defaults to
"tanh"
.layer_norm_eps -- The epsilon of layernorm. Defaults to
1e-12
.glyph_embedding_dim (int, optional) -- The dim of glyph_embedding. Defaults to
1728
.pinyin_map_len=32 (int, optional) -- The length of pinyin map. Defaults to
32
.
-
forward
(input_ids, pinyin_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, output_hidden_states=False)[源代码]¶ The ChineseBert forward method, overrides the
__call__()
special method.- 参数
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].pinyin_ids (Tensor, optional) -- Indices of input sequence tokens pinyin. We apply a CNN model with width 2 on the pinyin sequence, followed by max-pooling to derive the resulting pinyin embedding. This makes output dimensionality immune to the length of the input pinyin sequence. The length of the input pinyin sequence is fixed at 8. Its data type should be
int64
and it has a shape of [batch_size, sequence_length, 8]. Defaults toNone
, which means we don't add pinyin embeddings.token_type_ids (Tensor, optional) --
Segment token indices to indicate different portions of the inputs. Selected in the range
[0, type_vocab_size - 1]
. Iftype_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 toNone
, which means we don't add segment 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]
. Shape as(batch_size, num_tokens)
and dtype as int64. Defaults toNone
.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 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]
. Defaults toNone
, which means nothing needed to be prevented attention to.output_hidden_states (bool, optional) -- Whether to return the output of each hidden layers. Defaults to
False
.
- 返回
Returns tuple (
sequence_output
,pooled_output
) or (encoder_outputs
,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].
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 ChineseBertModel, ChineseBertTokenizer tokenizer = ChineseBertTokenizer.from_pretrained('ChineseBERT-base') model = ChineseBertModel.from_pretrained('ChineseBERT-base') inputs = tokenizer("欢迎使用百度飞桨!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} output = model(**inputs)
-
class
ChineseBertPretrainedModel
(*args, **kwargs)[源代码]¶ 基类:
paddlenlp.transformers.model_utils.PretrainedModel
An abstract class for pretrained ChineseBert models. It provides ChineseBert 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.chinesebert.modeling.ChineseBertModel
-
-
class
ChineseBertForPretraining
(chinesebert)[源代码]¶ 基类:
paddlenlp.transformers.chinesebert.modeling.ChineseBertPretrainedModel
ChineseBert Model with pretraining tasks on top.
- 参数
chinesebert (
ChineseBertModel
) -- An instance ofChineseBertModel
.
-
forward
(input_ids, pinyin_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, masked_positions=None)[源代码]¶ - 参数
input_ids (Tensor) -- See
ChineseBertModel
.pinyin_ids (Tensor, optional) -- See
ChineseBertModel
.token_type_ids (Tensor, optional) -- See
ChineseBertModel
.position_ids (Tensor, optional) -- See
ChineseBertModel
.attention_mask (Tensor, optional) -- See
ChineseBertModel
.masked_positions (Tensor, optional) -- See
ChineseBertPretrainingHeads
.
- 返回
Returns tuple (
prediction_scores
,seq_relationship_score
).With the fields:
prediction_scores
(Tensor):The scores of masked token prediction. Its data type should be float32. If
masked_positions
is None, its shape is [batch_size, sequence_length, vocab_size]. Otherwise, its shape is [batch_size, mask_token_num, vocab_size].
seq_relationship_score
(Tensor):The scores of next sentence prediction. Its data type should be float32 and its shape is [batch_size, 2].
- 返回类型
tuple
-
class
ChineseBertPretrainingCriterion
(vocab_size)[源代码]¶ 基类:
paddle.fluid.dygraph.layers.Layer
- 参数
vocab_size (int) -- Vocabulary size of
inputs_ids
inChineseBertModel
. Defines the number of different tokens that can be represented by theinputs_ids
passed when callingChineseBertBertModel
.
-
forward
(prediction_scores, seq_relationship_score, masked_lm_labels, next_sentence_labels, masked_lm_scale)[源代码]¶ - 参数
prediction_scores (Tensor) -- The scores of masked token prediction. Its data type should be float32. If
masked_positions
is None, its shape is [batch_size, sequence_length, vocab_size]. Otherwise, its shape is [batch_size, mask_token_num, vocab_size]seq_relationship_score (Tensor) -- The scores of next sentence prediction. Its data type should be float32 and its shape is [batch_size, 2]
masked_lm_labels (Tensor) -- The labels of the masked language modeling, its dimensionality is equal to
prediction_scores
. Its data type should be int64. Ifmasked_positions
is None, its shape is [batch_size, sequence_length, 1]. Otherwise, its shape is [batch_size, mask_token_num, 1]next_sentence_labels (Tensor) -- The labels of the next sentence prediction task, the dimensionality of
next_sentence_labels
is equal toseq_relation_labels
. Its data type should be int64 and its shape is [batch_size, 1]masked_lm_scale (Tensor or int) -- The scale of masked tokens. Used for the normalization of masked language modeling loss. If it is a
Tensor
, its data type should be int64 and its shape is equal toprediction_scores
.
- 返回
The pretraining loss, equals to the sum of
masked_lm_loss
plus the mean ofnext_sentence_loss
. Its data type should be float32 and its shape is [1].- 返回类型
Tensor
-
class
ChineseBertForSequenceClassification
(chinesebert, num_classes=2, dropout=None)[源代码]¶ 基类:
paddlenlp.transformers.chinesebert.modeling.ChineseBertPretrainedModel
ChineseBert Model with a linear layer on top of the output layer, designed for sequence classification/regression tasks like GLUE tasks.
- 参数
chinesebert (
ChineseBertModel
) -- An instance of ChineseBertModel.num_classes (int, optional) -- The number of classes. Defaults to
2
.dropout (float, optional) -- The dropout probability for output of ChineseBert. If None, use the same value as
hidden_dropout_prob
ofChineseBertModel
instancechinesebert
. Defaults to None.
-
forward
(input_ids, pinyin_ids=None, token_type_ids=None, position_ids=None, attention_mask=None)[源代码]¶ The ChineseBertForSequenceClassification forward method, overrides the __call__() special method.
- 参数
input_ids (Tensor) -- See
ChineseBertModel
.pinyin_ids (Tensor, optional) -- See
ChineseBertModel
.token_type_ids (Tensor, optional) -- See
ChineseBertModel
.position_ids (Tensor, optional) -- See
ChineseBertModel
.attention_mask (list, optional) -- See
ChineseBertModel
.
- 返回
Returns tensor
logits
, a tensor of the input text classification logits. Shape as[batch_size, num_classes]
and dtype as float32.- 返回类型
Tensor
示例
import paddle from paddlenlp.transformers.chinesebert.modeling import ChineseBertForSequenceClassification from paddlenlp.transformers.chinesebert.tokenizer import ChineseBertTokenizer tokenizer = ChineseBertTokenizer.from_pretrained('ChineseBERT-base') model = ChineseBertForSequenceClassification.from_pretrained('ChineseBERT-base', num_classes=2) inputs = tokenizer("欢迎使用百度飞桨!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs) print(logits.shape) # [1, 2]
-
class
ChineseBertForTokenClassification
(chinesebert, num_classes=2, dropout=None)[源代码]¶ 基类:
paddlenlp.transformers.chinesebert.modeling.ChineseBertPretrainedModel
ChineseBert Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks.
- 参数
chinesebert (
ChineseBertModel
) -- An instance of ChineseBertModel.num_classes (int, optional) -- The number of classes. Defaults to
2
.dropout (float, optional) -- The dropout probability for output of ChineseBert. If None, use the same value as
hidden_dropout_prob
ofChineseBertModel
instancechinesebert
. Defaults to None.
-
forward
(input_ids, pinyin_ids=None, token_type_ids=None, position_ids=None, attention_mask=None)[源代码]¶ The ChineseBertForTokenClassification forward method, overrides the __call__() special method.
- 参数
input_ids (Tensor) -- See
ChineseBertModel
.pinyin_ids (Tensor, optional) -- See
ChineseBertModel
.token_type_ids (Tensor, optional) -- See
ChineseBertModel
.position_ids (Tensor, optional) -- See
ChineseBertModel
.attention_mask (list, optional) -- See
ChineseBertModel
.
- 返回
Returns tensor
logits
, a tensor of the input token classification logits. Shape as[batch_size, sequence_length, num_classes]
and dtype asfloat32
.- 返回类型
Tensor
示例
import paddle from paddlenlp.transformers.chinesebert.modeling import ChineseBertForSequenceClassification from paddlenlp.transformers.chinesebert.tokenizer import ChineseBertTokenizer tokenizer = ChineseBertTokenizer.from_pretrained('ChineseBERT-base') model = ChineseBertForSequenceClassification.from_pretrained('ChineseBERT-base', num_classes=2) inputs = tokenizer("欢迎使用百度飞桨!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs) print(logits.shape) # [1, 13, 2]
-
class
ChineseBertForQuestionAnswering
(chinesebert)[源代码]¶ 基类:
paddlenlp.transformers.chinesebert.modeling.ChineseBertPretrainedModel
ChineseBert Model with a linear layer on top of the hidden-states output to compute
span_start_logits
andspan_end_logits
, designed for question-answering tasks like SQuAD.- 参数
ChineseBert (
ChineseBertModel
) -- An instance of ChineseBertModel.dropout (float, optional) -- The dropout probability for output of ChineseBert. If None, use the same value as
hidden_dropout_prob
ofChineseBertModel
instancechinesebert
. Defaults toNone
.
-
forward
(input_ids, pinyin_ids=None, token_type_ids=None)[源代码]¶ The ChineseBertForQuestionAnswering forward method, overrides the __call__() special method.
- 参数
input_ids (Tensor) -- See
ChineseBertModel
.pinyin_ids (Tensor, optional) -- See
ChineseBertModel
.token_type_ids (Tensor, optional) -- See
ChineseBertModel
.
- 返回
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].
- 返回类型
tuple
示例
import paddle from paddlenlp.transformers.chinesebert.modeling import ChineseBertForQuestionAnswering from paddlenlp.transformers.chinesebert.tokenizer import ChineseBertTokenizer tokenizer = ChineseBertTokenizer.from_pretrained('ChineseBERT-base') model = ChineseBertForQuestionAnswering.from_pretrained('ChineseBERT-base') inputs = tokenizer("欢迎使用百度飞桨!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} outputs = model(**inputs) start_logits = outputs[0] end_logits = outputs[1]