modeling#
- class ErnieModel(config: ErnieConfig)[源代码]#
-
The bare ERNIE 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:
config (
ErnieConfig
) -- An instance of ErnieConfig used to construct ErnieModel
- set_input_embeddings(value)[源代码]#
set new input embedding for model
- 参数:
value (Embedding) -- the new embedding of model
- 抛出:
NotImplementedError -- Model has not implement
set_input_embeddings
method
- forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, task_type_ids: Tensor | None = None, past_key_values: Tuple[Tuple[Tensor]] | None = None, inputs_embeds: Tensor | None = None, use_cache: bool | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[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 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]
. 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 ERNIE, 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 toNone
, 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 passinginputs_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. Ifpast_key_values
are used, the user can optionally input only the lastinput_ids
(those that don't have their past key value states given to this model) of shape(batch_size, 1)
instead of allinput_ids
of shape(batch_size, sequence_length)
.use_cache (
bool
, optional) -- If set toTrue
,past_key_values
key value states are returned. Defaults toNone
.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. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- 返回:
An instance of
BaseModelOutputWithPoolingAndCrossAttentions
ifreturn_dict=True
. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields ofBaseModelOutputWithPoolingAndCrossAttentions
.
示例
import paddle from paddlenlp.transformers import ErnieModel, ErnieTokenizer tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0') model = ErnieModel.from_pretrained('ernie-1.0') 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 ErniePretrainedModel(*args, **kwargs)[源代码]#
-
An abstract class for pretrained ERNIE models. It provides ERNIE related
model_config_file
,pretrained_init_configuration
,resource_files_names
,pretrained_resource_files_map
,base_model_prefix
for downloading and loading pretrained models. Refer toPretrainedModel
for more details.- config_class#
ErnieConfig
的别名
- base_model_class#
ErnieModel
的别名
- class ErnieForSequenceClassification(config)[源代码]#
-
Ernie Model with a linear layer on top of the output layer, designed for sequence classification/regression tasks like GLUE tasks.
- 参数:
config (
ErnieConfig
) -- An instance of ErnieConfig used to construct ErnieForSequenceClassification.
- forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, labels: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[源代码]#
- 参数:
input_ids (Tensor) -- See
ErnieModel
.token_type_ids (Tensor, optional) -- See
ErnieModel
.position_ids (Tensor, optional) -- See
ErnieModel
.attention_mask (Tensor, optional) -- See
ErnieModel
.inputs_embeds (Tensor, optional) -- See
ErnieModel
.labels (Tensor of shape
(batch_size,)
, optional) -- Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., num_labels - 1]
. Ifnum_labels == 1
a regression loss is computed (Mean-Square loss), Ifnum_labels > 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. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- 返回:
An instance of
SequenceClassifierOutput
ifreturn_dict=True
. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields ofSequenceClassifierOutput
.
示例
import paddle from paddlenlp.transformers import ErnieForSequenceClassification, ErnieTokenizer tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0') model = ErnieForSequenceClassification.from_pretrained('ernie-1.0') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
- class ErnieForTokenClassification(config: ErnieConfig)[源代码]#
-
ERNIE Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks.
- 参数:
config (
ErnieConfig
) -- An instance of ErnieConfigused to construct ErnieForTokenClassification.
- forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, labels: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[源代码]#
- 参数:
input_ids (Tensor) -- See
ErnieModel
.token_type_ids (Tensor, optional) -- See
ErnieModel
.position_ids (Tensor, optional) -- See
ErnieModel
.attention_mask (Tensor, optional) -- See
ErnieModel
.inputs_embeds (Tensor, optional) -- See
ErnieModel
.labels (Tensor of shape
(batch_size, sequence_length)
, optional) -- Labels for computing the token classification loss. Indices should be in[0, ..., num_labels - 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. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- 返回:
An instance of
TokenClassifierOutput
ifreturn_dict=True
. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields ofTokenClassifierOutput
.
示例
import paddle from paddlenlp.transformers import ErnieForTokenClassification, ErnieTokenizer tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0') model = ErnieForTokenClassification.from_pretrained('ernie-1.0') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
- class ErnieForQuestionAnswering(config)[源代码]#
-
Ernie 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:
config (
ErnieConfig
) -- An instance of ErnieConfig used to construct ErnieForQuestionAnswering.
- forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, start_positions: Tensor | None = None, end_positions: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[源代码]#
- 参数:
input_ids (Tensor) -- See
ErnieModel
.token_type_ids (Tensor, optional) -- See
ErnieModel
.position_ids (Tensor, optional) -- See
ErnieModel
.attention_mask (Tensor, optional) -- See
ErnieModel
.inputs_embeds (Tensor, optional) -- See
ErnieModel
.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. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- 返回:
An instance of
QuestionAnsweringModelOutput
ifreturn_dict=True
. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields ofQuestionAnsweringModelOutput
.
示例
import paddle from paddlenlp.transformers import ErnieForQuestionAnswering, ErnieTokenizer tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0') model = ErnieForQuestionAnswering.from_pretrained('ernie-1.0') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
- class ErnieForPretraining(config: ErnieConfig)[源代码]#
-
Ernie Model with a
masked language modeling
head and asentence order prediction
head on top.- get_output_embeddings()[源代码]#
To be overwrited for models with output embeddings
- 返回:
the otuput embedding of model
- 返回类型:
Optional[Embedding]
- forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, masked_positions: Tensor | None = None, inputs_embeds: Tensor | None = None, labels: Tensor | None = None, next_sentence_label: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[源代码]#
- 参数:
input_ids (Tensor) -- See
ErnieModel
.token_type_ids (Tensor, optional) -- See
ErnieModel
.position_ids (Tensor, optional) -- See
ErnieModel
.attention_mask (Tensor, optional) -- See
ErnieModel
.inputs_embeds (Tensor, optional) -- See
ErnieModel
.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]
(seeinput_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]
.next_sentence_label (Tensor of shape
(batch_size,)
, optional) --Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair (see
input_ids
docstring) Indices should be in[0, 1]
:0 indicates sequence B is a continuation of sequence A,
1 indicates sequence B is a random sequence.
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
ErnieForPreTrainingOutput
object. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- 返回:
An instance of
ErnieForPreTrainingOutput
ifreturn_dict=True
. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields ofErnieForPreTrainingOutput
.
- class ErniePretrainingCriterion(with_nsp_loss=True)[源代码]#
基类:
Layer
The loss output of Ernie Model during the pretraining: a
masked language modeling
head and anext sentence prediction (classification)
head.- forward(prediction_scores, seq_relationship_score, masked_lm_labels, next_sentence_labels=None)[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]
- 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 ErnieForMaskedLM(config: ErnieConfig)[源代码]#
-
Ernie Model with a
masked language modeling
head on top.- 参数:
config (
ErnieConfig
) -- An instance of ErnieConfig used to construct ErnieForMaskedLM.
- get_output_embeddings()[源代码]#
To be overwrited for models with output embeddings
- 返回:
the otuput embedding of model
- 返回类型:
Optional[Embedding]
- forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, masked_positions: Tensor | None = None, inputs_embeds: Tensor | None = None, labels: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[源代码]#
- 参数:
input_ids (Tensor) -- See
ErnieModel
.token_type_ids (Tensor, optional) -- See
ErnieModel
.position_ids (Tensor, optional) -- See
ErnieModel
.attention_mask (Tensor, optional) -- See
ErnieModel
.masked_positions -- masked positions of output.
inputs_embeds (Tensor, optional) -- See
ErnieModel
.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]
(seeinput_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. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- 返回:
An instance of
MaskedLMOutput
ifreturn_dict=True
. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields ofMaskedLMOutput
.
示例
import paddle from paddlenlp.transformers import ErnieForMaskedLM, ErnieTokenizer tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0') model = ErnieForMaskedLM.from_pretrained('ernie-1.0') 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, 17, 18000]
- class ErnieForMultipleChoice(config: ErnieConfig)[源代码]#
-
Ernie Model with a linear layer on top of the hidden-states output layer, designed for multiple choice tasks like RocStories/SWAG tasks.
- 参数:
config (
ErnieConfig
) -- An instance of ErnieConfig used to construct ErnieForMultipleChoice
- forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, labels: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[源代码]#
The ErnieForMultipleChoice forward method, overrides the __call__() special method.
- 参数:
input_ids (Tensor) -- See
ErnieModel
and shape as [batch_size, num_choice, sequence_length].token_type_ids (Tensor, optional) -- See
ErnieModel
and shape as [batch_size, num_choice, sequence_length].position_ids (Tensor, optional) -- See
ErnieModel
and shape as [batch_size, num_choice, sequence_length].attention_mask (list, optional) -- See
ErnieModel
and shape as [batch_size, num_choice, sequence_length].inputs_embeds (Tensor, optional) -- See
ErnieModel
and shape as [batch_size, num_choice, sequence_length, hidden_size].labels (Tensor of shape
(batch_size, )
, optional) -- Labels for computing the multiple choice classification loss. Indices should be in[0, ..., num_choices-1]
wherenum_choices
is the size of the second dimension of the input tensors. (Seeinput_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. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- 返回:
An instance of
MultipleChoiceModelOutput
ifreturn_dict=True
. Otherwise it returns a tuple of tensors corresponding to ordered and not None (depending on the input arguments) fields ofMultipleChoiceModelOutput
.
- class UIE(config: ErnieConfig)[源代码]#
-
Ernie Model with two linear layer on top of the hidden-states output to compute
start_prob
andend_prob
, designed for Universal Information Extraction. :param config: An instance of ErnieConfig used to construct UIE :type config:ErnieConfig
- forward(input_ids: Tensor | None = None, token_type_ids: Tensor | None = None, position_ids: Tensor | None = None, attention_mask: Tensor | None = None, inputs_embeds: Tensor | None = None, return_dict: Tensor | None = None)[源代码]#
- 参数:
input_ids (Tensor) -- See
ErnieModel
.token_type_ids (Tensor, optional) -- See
ErnieModel
.position_ids (Tensor, optional) -- See
ErnieModel
.attention_mask (Tensor, optional) -- See
ErnieModel
.
示例
- class UTC(config: ErnieConfig)[源代码]#
-
Ernie Model with two linear layer on the top of the hidden-states output to compute probability of candidate labels, designed for Unified Tag Classification.
- forward(input_ids, token_type_ids, position_ids, attention_mask, omask_positions, cls_positions, inputs_embeds: Tensor | None = None, output_hidden_states: bool | None = None, output_attentions: bool | None = None, return_dict: bool | None = None)[源代码]#
- 参数:
input_ids (Tensor) -- See
ErnieModel
.token_type_ids (Tensor) -- See
ErnieModel
.position_ids (Tensor) -- See
ErnieModel
.attention_mask (Tensor) -- See
ErnieModel
.omask_positions (Tensor of shape
(batch_size, max_option)
) -- Masked positions of [O-MASK] tokens padded with 0.cls_positions (Tensor of shape
(batch_size)
) -- Masked positions of the second [CLS] token.labels (Tensor of shape
(num_labels_in_batch,)
, optional) -- Labels for computing classification loss.