modeling¶
-
class
ElectraModel
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
The bare Electra 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
inElectraModel
. Also is the vocab size of token embedding matrix. Defines the number of different tokens that can be represented by theinputs_ids
passed when callingElectraModel
.embedding_size (int, optional) – Dimensionality of the embedding layer.
hidden_size (int, optional) – Dimensionality of the encoder layer and pooler layer.
num_hidden_layers (int, optional) – Number of hidden layers in the Transformer encoder.
num_attention_heads (int, optional) – Number of attention heads for each attention layer in the Transformer encoder.
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
.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.hidden_dropout_prob (float, optional) – The dropout probability for all fully connected layers in the embeddings and encoder.
attention_probs_dropout_prob (float, optional) – The dropout probability used in MultiHeadAttention in all encoder layers to drop some attention target.
max_position_embeddings (int, optional) – The maximum value of the dimensionality of position encoding, which dictates the maximum supported length of an input sequence.
type_vocab_size (int, optional) – The vocabulary size of
token_type_ids
.initializer_range (float, optional) –
The standard deviation of the normal initializer.
Note
A normal_initializer initializes weight matrices as normal distributions. See
ElectraPretrainedModel.init_weights()
for how weights are initialized inElectraModel
.pad_token_id (int, optional) – The index of padding token in the token vocabulary.
-
get_input_embeddings
()[source]¶ get input embedding of model
- Returns
embedding of model
- Return type
nn.Embedding
-
set_input_embeddings
(value)[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
-
forward
(input_ids, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None, past_key_values=None, use_cache=None, output_attentions=False, output_hidden_states=False, return_dict=False)[source]¶ The ElectraModel 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]
. 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.inputs_embeds (Tensor, optional) – Instead of passing input_ids you can choose to directly pass an embedded representation. This is useful for use cases such as P-Tuning, where you want more control over how to convert input_ids indices into the embedding space. Its data type should be
float32
and it has a shape of [batch_size, sequence_length, embedding_size].past_key_values (tuple(tuple(Tensor)), optional) – Precomputed key and value hidden states of the attention blocks of each layer. This can be used to speedup auto-regressive decoding for generation tasks or to support use cases such as Prefix-Tuning where vectors are prepended to each attention layer. The length of tuple equals to the number of layers, and each tuple having 2 tensors of shape
(batch_size, num_heads, past_key_values_length, embed_size_per_head)
) 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
QuestionAnsweringModelOutput
object. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- Returns
Returns tensor
encoder_outputs
, which is the output at the last layer of the model. Its data type should be float32 and has a shape of [batch_size, sequence_length, hidden_size].- Return type
Tensor
Example
import paddle from paddlenlp.transformers import ElectraModel, ElectraTokenizer tokenizer = ElectraTokenizer.from_pretrained('electra-small') model = ElectraModel.from_pretrained('electra-small') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} output = model(**inputs)
-
class
ElectraPretrainedModel
(*args, **kwargs)[source]¶ Bases:
paddlenlp.transformers.model_utils.PretrainedModel
An abstract class for pretrained Electra models. It provides Electra 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.-
config_class
¶ alias of
paddlenlp.transformers.electra.configuration.ElectraConfig
-
base_model_class
¶ alias of
paddlenlp.transformers.electra.modeling.ElectraModel
-
-
class
ElectraForTotalPretraining
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
Electra Model for pretraining tasks.
- Parameters
generator (
ElectraGenerator
) – An instance ofElectraGenerator
.discriminator (
ElectraDiscriminator
) – An instance ofElectraDiscriminator
.
-
get_input_embeddings
()[source]¶ get input embedding of model
- Returns
embedding of model
- Return type
nn.Embedding
-
get_output_embeddings
()[source]¶ To be overwrited for models with output embeddings
- Returns
the otuput embedding of model
- Return type
Optional[Embedding]
-
forward
(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, raw_input_ids=None, generator_labels=None)[source]¶ The ElectraForPretraining forward method, overrides the __call__() special method.
- Parameters
input_ids (Tensor) – See
ElectraModel
.token_type_ids (Tensor, optional) – See
ElectraModel
.position_ids (Tensor, optional) – See
ElectraModel
.attention_mask (list, optional) – See
ElectraModel
.raw_input_ids (Tensor, optional) – Raw inputs used to get discriminator labels. Its data type should be
int64
and it has a shape of [batch_size, sequence_length].generator_labels (Tensor, optional) – Labels to compute the discriminator inputs. Its data type should be int64 and its shape is [batch_size, sequence_length]. The value for unmasked tokens should be -100 and value for masked tokens should be 0.
- Returns
Returns tuple (generator_logits, disc_logits, disc_labels, attention_mask).
With the fields:
generator_logits
(Tensor):The scores of Electra Generator. Its data type should be int64 and its shape is [batch_size, sequence_length, vocab_size].
disc_logits
(Tensor):The the prediction result of replaced tokens. Its data type should be float32 and if batch_size>1, its shape is [batch_size, sequence_length], if batch_size=1, its shape is [sequence_length].
disc_labels
(Tensor):The labels of electra discriminator. Its data type should be int32, and its shape is [batch_size, sequence_length].
attention_mask
(Tensor):See
ElectraModel
. Its data type should be bool.
- Return type
tuple
-
class
ElectraDiscriminator
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
The Electra Discriminator can detect the tokens that are replaced by the Electra Generator.
- Parameters
electra (
ElectraModel
) – An instance ofElectraModel
.
-
forward
(input_ids, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None)[source]¶ - Parameters
input_ids (Tensor) – See
ElectraModel
.token_type_ids (Tensor, optional) – See
ElectraModel
.position_ids (Tensor, optional) – See
ElectraModel
.attention_mask (Tensor, optional) – See
ElectraModel
.inputs_embeds (Tensor, optional) – See
ElectraModel
.
- Returns
Returns tensor
logits
, the prediction result of replaced tokens. Its data type should be float32 and if batch_size>1, its shape is [batch_size, sequence_length], if batch_size=1, its shape is [sequence_length].- Return type
Tensor
Example
import paddle from paddlenlp.transformers import ElectraDiscriminator, ElectraTokenizer tokenizer = ElectraTokenizer.from_pretrained('electra-small') model = ElectraDiscriminator.from_pretrained('electra-small') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
-
class
ElectraGenerator
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
The Electra Generator will replace some tokens of the given sequence, it is trained as a masked language model.
- Parameters
electra (
ElectraModel
) – An instance ofElectraModel
.
-
get_input_embeddings
()[source]¶ get input embedding of model
- Returns
embedding of model
- Return type
nn.Embedding
-
set_input_embeddings
(value)[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
-
forward
(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None, labels=None, output_attentions=False, output_hidden_states=False, return_dict=False)[source]¶ - Parameters
input_ids (Tensor) – See
ElectraModel
.token_type_ids (Tensor, optional) – See
ElectraModel
.position_ids (Tensor, optional) – See
ElectraModel
.attention_mask (Tensor, optional) – See
ElectraModel
.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
.
- Returns
Returns tensor
prediction_scores
, the scores of Electra Generator. Its data type should be int64 and its shape is [batch_size, sequence_length, vocab_size].- Return type
Tensor
Example
import paddle from paddlenlp.transformers import ElectraGenerator, ElectraTokenizer tokenizer = ElectraTokenizer.from_pretrained('electra-small') model = ElectraGenerator.from_pretrained('electra-small') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} prediction_scores = model(**inputs)
-
class
ElectraClassificationHead
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddle.fluid.dygraph.layers.Layer
Perform sentence-level classification tasks.
- Parameters
hidden_size (int) – Dimensionality of the embedding layer.
hidden_dropout_prob (float) – The dropout probability for all fully connected layers.
num_classes (int) – The number of classes.
activation (str) – The activation function name between layers.
-
forward
(features, **kwargs)[source]¶ The ElectraClassificationHead forward method, overrides the __call__() special method.
- Parameters
features (Tensor) – Input sequence, usually the
sequence_output
of electra model. Its data type should be float32 and its shape is [batch_size, sequence_length, hidden_size].- Returns
Returns a tensor of the input text classification logits. Shape as
[batch_size, num_classes]
and dtype as float32.- Return type
Tensor
-
class
ElectraForSequenceClassification
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
Electra Model with a linear layer on top of the output layer, designed for sequence classification/regression tasks like GLUE tasks.
- Parameters
electra (
ElectraModel
) – An instance of ElectraModel.num_classes (int, optional) – The number of classes. Defaults to
2
.dropout (float, optional) – The dropout probability for output of Electra. If None, use the same value as
hidden_dropout_prob
ofElectraModel
instanceelectra
. Defaults to None.activation (str, optional) – The activation function name for classifier. Defaults to “gelu”.
layer_norm_eps (float, optional) – The epsilon to initialize nn.LayerNorm layers. Defaults to 1e-12.
-
forward
(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None, labels=None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None)[source]¶ The ElectraForSequenceClassification forward method, overrides the __call__() special method.
- Parameters
input_ids (Tensor) – See
ElectraModel
.token_type_ids (Tensor, optional) – See
ElectraModel
.position_ids (Tensor, optional) – See
ElectraModel
.attention_mask (list, optional) – See
ElectraModel
.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
.
- 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 ElectraForSequenceClassification from paddlenlp.transformers import ElectraTokenizer tokenizer = ElectraTokenizer.from_pretrained('electra-small') model = ElectraForSequenceClassification.from_pretrained('electra-small') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
-
class
ElectraForTokenClassification
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
Electra Model with a linear layer on top of the hidden-states output layer, designed for token classification tasks like NER tasks.
- Parameters
electra (
ElectraModel
) – An instance of ElectraModel.num_classes (int, optional) – The number of classes. Defaults to
2
.dropout (float, optional) – The dropout probability for output of Electra. If None, use the same value as
hidden_dropout_prob
ofElectraModel
instanceelectra
. Defaults to None.
-
forward
(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None, labels: Optional[paddle.Tensor] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None)[source]¶ The ElectraForTokenClassification forward method, overrides the __call__() special method.
- Parameters
input_ids (Tensor) – See
ElectraModel
.token_type_ids (Tensor, optional) – See
ElectraModel
.position_ids (Tensor, optional) – See
ElectraModel
.attention_mask (list, optional) – See
ElectraModel
.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
QuestionAnsweringModelOutput
object. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- Returns
Returns tensor
logits
, a tensor of the input token classification logits. Shape as[batch_size, sequence_length, num_classes]
and dtype asfloat32
.- Return type
Tensor
Example
import paddle from paddlenlp.transformers import ElectraForTokenClassification from paddlenlp.transformers import ElectraTokenizer tokenizer = ElectraTokenizer.from_pretrained('electra-small') model = ElectraForTokenClassification.from_pretrained('electra-small') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} logits = model(**inputs)
-
class
ElectraPretrainingCriterion
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddle.fluid.dygraph.layers.Layer
- Parameters
vocab_size (int) – Vocabulary size of
inputs_ids
inElectraModel
. Defines the number of different tokens that can be represented by theinputs_ids
passed when callingElectraModel
.gen_weight (float) – The weight of the Electra Generator.
disc_weight (float) – The weight of the Electra Discriminator.
-
forward
(generator_prediction_scores, discriminator_prediction_scores, generator_labels, discriminator_labels, attention_mask)[source]¶ - Parameters
generator_prediction_scores (Tensor) – The scores of masked token prediction. Its data type should be float32. and its shape is [batch_size, sequence_length, vocab_size].
discriminator_prediction_scores (Tensor) – The scores of masked token prediction. Its data type should be float32. and its shape is [batch_size, sequence_length] or [sequence length] if batch_size=1.
generator_labels (Tensor) – The labels of the generator, its dimensionality is equal to
generator_prediction_scores
. Its data type should be int64 and its shape is [batch_size, sequence_size, 1].discriminator_labels (Tensor) – The labels of the discriminator, its dimensionality is equal to
discriminator_prediction_scores
. The labels should be numbers between 0 and 1. Its data type should be float32 and its shape is [batch_size, sequence_size] or [sequence length] if batch_size=1.attention_mask (Tensor) – See
ElectraModel
.
- Returns
The pretraining loss, equals to weighted generator loss plus the weighted discriminator loss. Its data type should be float32 and its shape is [1].
- Return type
Tensor
-
class
ElectraForMultipleChoice
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
Electra Model with a linear layer on top of the hidden-states output layer, designed for multiple choice tasks like RocStories/SWAG tasks.
- Parameters
electra (
ElectraModel
) – An instance of ElectraModel.num_choices (int, optional) – The number of choices. Defaults to
2
.dropout (float, optional) – The dropout probability for output of Electra. If None, use the same value as
hidden_dropout_prob
ofElectraModel
instanceelectra
. Defaults to None.
-
forward
(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None, labels: Optional[paddle.Tensor] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None)[source]¶ The ElectraForMultipleChoice forward method, overrides the __call__() special method.
- Parameters
input_ids (Tensor) – See
ElectraModel
and shape as [batch_size, num_choice, sequence_length].token_type_ids (Tensor, optional) – See
ElectraModel
and shape as [batch_size, num_choice, sequence_length].position_ids (Tensor, optional) – See
ElectraModel
and shape as [batch_size, num_choice, sequence_length].attention_mask (list, optional) – See
ElectraModel
and shape as [batch_size, num_choice, sequence_length].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
QuestionAnsweringModelOutput
object. IfFalse
, the output will be a tuple of tensors. Defaults toFalse
.
- Returns
Returns tensor
reshaped_logits
, a tensor of the multiple choice classification logits. Shape as[batch_size, num_choice]
and dtype asfloat32
.- Return type
Tensor
Example
import paddle from paddlenlp.transformers import ElectraForMultipleChoice, ElectraTokenizer from paddlenlp.data import Pad, Dict tokenizer = ElectraTokenizer.from_pretrained('electra-small') model = ElectraForMultipleChoice.from_pretrained('electra-small', num_choices=2) data = [ { "question": "how do you turn on an ipad screen?", "answer1": "press the volume button.", "answer2": "press the lock button.", "label": 1, }, { "question": "how do you indent something?", "answer1": "leave a space before starting the writing", "answer2": "press the spacebar", "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) batchify_fn = lambda samples, fn=Dict( { "input_ids": Pad(axis=0, pad_val=tokenizer.pad_token_id), # input_ids "token_type_ids": Pad( axis=0, pad_val=tokenizer.pad_token_type_id ), # token_type_ids } ): fn(samples) inputs = batchify_fn(inputs) reshaped_logits = model( input_ids=paddle.to_tensor(inputs[0], dtype="int64"), token_type_ids=paddle.to_tensor(inputs[1], dtype="int64"), ) print(reshaped_logits.shape) # [2, 2]
-
class
ElectraForQuestionAnswering
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
Electra 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.- Parameters
electra (
ElectraModel
) – An instance of ElectraModel.
-
forward
(input_ids, token_type_ids=None, position_ids=None, attention_mask=None, inputs_embeds=None, start_positions: Optional[paddle.Tensor] = None, end_positions: Optional[paddle.Tensor] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None)[source]¶ The ElectraForQuestionAnswering forward method, overrides the __call__() special method.
- Parameters
input_ids (Tensor) – See
ElectraModel
.token_type_ids (Tensor, optional) – See
ElectraModel
.position_ids (Tensor, optional) – See
ElectraModel
.attention_mask (list, optional) – See
ElectraModel
.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
.
- 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 ElectraForQuestionAnswering, ElectraTokenizer tokenizer = ElectraTokenizer.from_pretrained('electra-small') model = ElectraForQuestionAnswering.from_pretrained('electra-small') inputs = tokenizer("Welcome to use PaddlePaddle and PaddleNLP!") inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} outputs = model(**inputs) start_logits = outputs[0] end_logits = outputs[1]
-
ElectraForMaskedLM
¶ alias of
paddlenlp.transformers.electra.modeling.ElectraGenerator
-
ElectraForPretraining
¶ alias of
paddlenlp.transformers.electra.modeling.ElectraForTotalPretraining
-
class
ErnieHealthForTotalPretraining
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraForTotalPretraining
ERNIE-Health Model for pretraining task.
- Parameters
generator (
ElectraGenerator
) – An instance ofElectraGenerator
.( (discriminator) – class:
ErnieHealthDiscriminator): An instance of :class:`ErnieHealthDiscriminator
.
-
sample_negatives_from_softmax
(logits, raw_inputs, use_softmax_sample=True)[source]¶ Sample K=5 non-original negative samples for candidate set.
- Returns
Returns tensor
neg_samples_ids
, a tensor of the negative samples of original inputs. Shape as ` [batch_size, sequence_length, K, vocab_size]` and dtype asint64
.- Return type
Tensor
-
forward
(input_ids=None, token_type_ids=None, position_ids=None, attention_mask=None, raw_input_ids=None, generator_labels=None, return_dict: Optional[bool] = None)[source]¶ The ElectraForPretraining forward method, overrides the __call__() special method.
- Parameters
input_ids (Tensor) – See
ElectraModel
.token_type_ids (Tensor, optional) – See
ElectraModel
.position_ids (Tensor, optional) – See
ElectraModel
.attention_mask (list, optional) – See
ElectraModel
.raw_input_ids (Tensor, optional) – Raw inputs used to get discriminator labels. Its data type should be
int64
and it has a shape of [batch_size, sequence_length].generator_labels (Tensor, optional) – Labels to compute the discriminator inputs. Its data type should be int64 and its shape is [batch_size, sequence_length]. The value for unmasked tokens should be -100 and value for masked tokens should be 0.
- Returns
Returns tuple (generator_logits, disc_logits, disc_labels, attention_mask).
With the fields:
generator_logits
(Tensor):The scores of Electra Generator. Its data type should be int64 and its shape is [batch_size, sequence_length, vocab_size].
disc_logits
(Tensor):The the prediction result of replaced tokens. Its data type should be float32 and if batch_size>1, its shape is [batch_size, sequence_length], if batch_size=1, its shape is [sequence_length].
disc_labels
(Tensor):The labels of electra discriminator. Its data type should be int32, and its shape is [batch_size, sequence_length].
attention_mask
(Tensor):See
ElectraModel
. Its data type should be bool.
- Return type
tuple
-
class
ErnieHealthPretrainingCriterion
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddle.fluid.dygraph.layers.Layer
- Parameters
vocab_size (int) – Vocabulary size of
inputs_ids
inElectraModel
. Defines the number of different tokens that can be represented by theinputs_ids
passed when callingElectraModel
.gen_weight (float) – The weight of the Electra Generator.
disc_weight (float) – The weight of the Electra Discriminator.
-
forward
(generator_logits, generator_labels, logits_rtd, logits_mts, logits_csp, discriminator_labels, attention_mask)[source]¶ - Parameters
generator_logits (Tensor) – The scores of masked token prediction. Its data type should be float32. and its shape is [batch_size, sequence_length, vocab_size].
generator_labels (Tensor) – The labels of the generator, its dimensionality is equal to
generator_prediction_scores
. Its data type should be int64 and its shape is [batch_size, sequence_size, 1].logits_rtd (Tensor) – The scores of masked token prediction. Its data type should be float32. and its shape is [batch_size, sequence_length] or [sequence length] if batch_size=1.
discriminator_labels (Tensor) – The labels of the discriminator, its dimensionality is equal to
discriminator_prediction_scores
. The labels should be numbers between 0 and 1. Its data type should be float32 and its shape is [batch_size, sequence_size] or [sequence length] if batch_size=1.attention_mask (Tensor) – See
ElectraModel
.
- Returns
The pretraining loss, equals to weighted generator loss plus the weighted discriminator loss. Its data type should be float32 and its shape is [1].
- Return type
Tensor
-
class
ErnieHealthDiscriminator
(config: paddlenlp.transformers.electra.configuration.ElectraConfig)[source]¶ Bases:
paddlenlp.transformers.electra.modeling.ElectraPretrainedModel
- The Discriminators in ERNIE-Health (https://arxiv.org/abs/2110.07244), including
token-level Replaced Token Detection (RTD) task
token-level Multi-Token Selection (MTS) task
sequence-level Contrastive Sequence Prediction (CSP) task.
- Parameters
electra (
ElectraModel
) – An instance ofElectraModel
.
-
forward
(input_ids, candidate_ids, token_type_ids=None, position_ids=None, attention_mask=None)[source]¶ - Parameters
input_ids (Tensor) – See
ElectraModel
.candidate_ids (Tensor) – The candidate indices of input sequence tokens in the vocabulary for MTS task. Its data type should be
int64
and it has a shape of [batch_size, sequence_length].token_type_ids (Tensor, optional) – See
ElectraModel
.position_ids (Tensor, optional) – See
ElectraModel
.attention_mask (Tensor, optional) – See
ElectraModel
.
- Returns
Returns list of tensors, the prediction results of RTD, MTS and CSP. The logits’ data type should be float32 and if batch_size > 1,
the shape of
logits_rtd
is [batch_size, sequence_length],the shape of
logits_mts
is [batch_size, sequence_length, num_candidate],the shape of
logits_csp
is [batch_size, 128].
If batch_size=1, the shapes are [sequence_length], [sequence_length, num_cadidate], [128], separately.
- Return type
Tensor