ELECTRA¶
Overview¶
The ELECTRA model was proposed in the paper. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. ELECTRA is a new pre-training approach which trains two transformer models: the generator and the discriminator. The generator’s role is to replace tokens in a sequence, and is therefore trained as a masked language model. The discriminator, which is the model we’re interested in, tries to identify which tokens were replaced by the generator in the sequence.
The abstract from the paper is the following:
Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to downstream NLP tasks, they generally require large amounts of compute to be effective. As an alternative, we propose a more sample-efficient pre-training task called replaced token detection. Instead of masking the input, our approach corrupts it by replacing some tokens with plausible alternatives sampled from a small generator network. Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not. Thorough experiments demonstrate this new pre-training task is more efficient than MLM because the task is defined over all input tokens rather than just the small subset that was masked out. As a result, the contextual representations learned by our approach substantially outperform the ones learned by BERT given the same model size, data, and compute. The gains are particularly strong for small models; for example, we train a model on one GPU for 4 days that outperforms GPT (trained using 30x more compute) on the GLUE natural language understanding benchmark. Our approach also works well at scale, where it performs comparably to RoBERTa and XLNet while using less than 1/4 of their compute and outperforms them when using the same amount of compute.
Tips:
ELECTRA is the pre-training approach, therefore there is nearly no changes done to the underlying model: BERT. The only change is the separation of the embedding size and the hidden size -> The embedding size is generally smaller, while the hidden size is larger. An additional projection layer (linear) is used to project the embeddings from their embedding size to the hidden size. In the case where the embedding size is the same as the hidden size, no projection layer is used.
The ELECTRA checkpoints saved using Google Research’s implementation contain both the generator and discriminator. The conversion script requires the user to name which model to export into the correct architecture. Once converted to the HuggingFace format, these checkpoints may be loaded into all available ELECTRA models, however. This means that the discriminator may be loaded in the ElectraForMaskedLM model, and the generator may be loaded in the ElectraForPreTraining model (the classification head will be randomly initialized as it doesn’t exist in the generator).
The original code can be found here.
ElectraConfig¶
-
class
transformers.
ElectraConfig
(vocab_size=30522, embedding_size=128, hidden_size=256, num_hidden_layers=12, num_attention_heads=4, intermediate_size=1024, 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, layer_norm_eps=1e-12, summary_type='first', summary_use_proj=True, summary_activation='gelu', summary_last_dropout=0.1, pad_token_id=0, **kwargs)[source]¶ This is the configuration class to store the configuration of a
ElectraModel
. It is used to instantiate an ELECTRA model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the ELECTRA google/electra-small-discriminator architecture.Configuration objects inherit from
PretrainedConfig
and can be used to control the model outputs. Read the documentation fromPretrainedConfig
for more information.- Parameters
vocab_size (
int
, optional, defaults to 30522) – Vocabulary size of the ELECTRA model. Defines the different tokens that can be represented by the inputs_ids passed to the forward method ofElectraModel
.embedding_size (
int
, optional, defaults to 128) – Dimensionality of the encoder layers and the pooler layer.hidden_size (
int
, optional, defaults to 256) – Dimensionality of the encoder layers and the pooler layer.num_hidden_layers (
int
, optional, defaults to 12) – Number of hidden layers in the Transformer encoder.num_attention_heads (
int
, optional, defaults to 4) – Number of attention heads for each attention layer in the Transformer encoder.intermediate_size (
int
, optional, defaults to 1024) – Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.hidden_act (
str
orfunction
, optional, defaults to “gelu”) – The non-linear activation function (function or string) in the encoder and pooler. If string, “gelu”, “relu”, “swish” and “gelu_new” are supported.hidden_dropout_prob (
float
, optional, defaults to 0.1) – The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.attention_probs_dropout_prob (
float
, optional, defaults to 0.1) – The dropout ratio for the attention probabilities.max_position_embeddings (
int
, optional, defaults to 512) – The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).type_vocab_size (
int
, optional, defaults to 2) – The vocabulary size of the token_type_ids passed intoElectraModel
.initializer_range (
float
, optional, defaults to 0.02) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices.layer_norm_eps (
float
, optional, defaults to 1e-12) – The epsilon used by the layer normalization layers.summary_type (
string
, optional, defaults to “first”) –Argument used when doing sequence summary. Used in for the multiple choice head in
ElectraForMultipleChoice
. Is one of the following options:’last’ => take the last token hidden state (like XLNet)
’first’ => take the first token hidden state (like Bert)
’mean’ => take the mean of all tokens hidden states
’cls_index’ => supply a Tensor of classification token position (GPT/GPT-2)
’attn’ => Not implemented now, use multi-head attention
summary_use_proj (
boolean
, optional, defaults toTrue
) – Argument used when doing sequence summary. Used in for the multiple choice head inElectraForMultipleChoice
. Add a projection after the vector extractionsummary_activation (
string
orNone
, optional) – Argument used when doing sequence summary. Used in for the multiple choice head inElectraForMultipleChoice
. ‘gelu’ => add a gelu activation to the output, Other => no activation.summary_last_dropout (
float
, optional, defaults to 0.0) – Argument used when doing sequence summary. Used in for the multiple choice head inElectraForMultipleChoice
. Add a dropout after the projection and activation
Example:
>>> from transformers import ElectraModel, ElectraConfig >>> # Initializing a ELECTRA electra-base-uncased style configuration >>> configuration = ElectraConfig() >>> # Initializing a model from the electra-base-uncased style configuration >>> model = ElectraModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config
ElectraTokenizer¶
-
class
transformers.
ElectraTokenizer
(vocab_file, do_lower_case=True, do_basic_tokenize=True, never_split=None, unk_token='[UNK]', sep_token='[SEP]', pad_token='[PAD]', cls_token='[CLS]', mask_token='[MASK]', tokenize_chinese_chars=True, strip_accents=None, **kwargs)[source]¶ Constructs an Electra tokenizer.
ElectraTokenizer
is identical toBertTokenizer
and runs end-to-end tokenization: punctuation splitting + wordpiece.Refer to superclass
BertTokenizer
for usage examples and documentation concerning parameters.
ElectraTokenizerFast¶
-
class
transformers.
ElectraTokenizerFast
(vocab_file, do_lower_case=True, unk_token='[UNK]', sep_token='[SEP]', pad_token='[PAD]', cls_token='[CLS]', mask_token='[MASK]', clean_text=True, tokenize_chinese_chars=True, strip_accents=None, wordpieces_prefix='##', **kwargs)[source]¶ Constructs a “Fast” Electra Fast tokenizer (backed by HuggingFace’s tokenizers library).
ElectraTokenizerFast
is identical toBertTokenizerFast
and runs end-to-end tokenization: punctuation splitting + wordpiece.Refer to superclass
BertTokenizerFast
for usage examples and documentation concerning parameters.
Electra specific outputs¶
-
class
transformers.modeling_electra.
ElectraForPreTrainingOutput
(loss: Optional[torch.FloatTensor] = None, logits: torch.FloatTensor = None, hidden_states: Optional[Tuple[torch.FloatTensor]] = None, attentions: Optional[Tuple[torch.FloatTensor]] = None)[source]¶ Output type of
ElectraForPreTrainingModel
.- Parameters
loss (optional, returned when
labels
is provided,torch.FloatTensor
of shape(1,)
) – Total loss of the ELECTRA objective.logits (
torch.FloatTensor
of shape(batch_size, sequence_length)
) – Prediction scores of the head (scores for each token before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) –Tuple of
torch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) –Tuple of
torch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
-
class
transformers.modeling_tf_electra.
TFElectraForPreTrainingOutput
(logits: tensorflow.python.framework.ops.Tensor = None, hidden_states: Optional[Tuple[tensorflow.python.framework.ops.Tensor]] = None, attentions: Optional[Tuple[tensorflow.python.framework.ops.Tensor]] = None)[source]¶ Output type of
TFElectraForPreTrainingModel
.- Parameters
loss (optional, returned when
labels
is provided,tf.Tensor
of shape(1,)
) – Total loss of the ELECTRA objective.logits (
tf.Tensor
of shape(batch_size, sequence_length)
) – Prediction scores of the head (scores for each token before SoftMax).hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) –Tuple of
tf.Tensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) –Tuple of
tf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
ElectraModel¶
-
class
transformers.
ElectraModel
(config)[source]¶ The bare Electra Model transformer outputting raw hidden-states without any specific head on top. Identical to the BERT model except that it uses an additional linear layer between the embedding layer and the encoder if the hidden size and embedding size are different.Both the generator and discriminator checkpoints may be loaded into this model. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
config_class
¶ alias of
transformers.configuration_electra.ElectraConfig
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶ The
ElectraModel
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Segment token indices to indicate first and second portions of the inputs. Indices are selected in
[0, 1]
:0
corresponds to a sentence A token,1
corresponds to a sentence B tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.encoder_hidden_states (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.encoder_attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) – Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.
- Returns
A
BaseModelOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) – Sequence of hidden-states at the output of the last layer of the model.hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
BaseModelOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import ElectraTokenizer, ElectraModel >>> import torch >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = ElectraModel.from_pretrained('google/electra-small-discriminator', return_dict=True) >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> outputs = model(**inputs) >>> last_hidden_states = outputs.last_hidden_state
ElectraForPreTraining¶
-
class
transformers.
ElectraForPreTraining
(config)[source]¶ Electra model with a binary classification head on top as used during pre-training for identifying generated tokens.
It is recommended to load the discriminator checkpoint into that model. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶ The
ElectraForPreTraining
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Segment token indices to indicate first and second portions of the inputs. Indices are selected in
[0, 1]
:0
corresponds to a sentence A token,1
corresponds to a sentence B tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.encoder_hidden_states (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.encoder_attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) – Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) –If set to
True
, the model will return aModelOutput
instead of a plain tuple.- labels (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional): Labels for computing the ELECTRA loss. Input should be a sequence of tokens (see
input_ids
docstring) Indices should be in[0, 1]
.0
indicates the token is an original token,1
indicates the token was replaced.
- labels (
- Returns
A
ElectraForPreTrainingOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (optional, returned when
labels
is provided,torch.FloatTensor
of shape(1,)
) – Total loss of the ELECTRA objective.logits (
torch.FloatTensor
of shape(batch_size, sequence_length)
) – Prediction scores of the head (scores for each token before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
Examples:
>>> from transformers import ElectraTokenizer, ElectraForPreTraining >>> import torch >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = ElectraForPreTraining.from_pretrained('google/electra-small-discriminator') >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0) # Batch size 1 >>> logits = model(input_ids).logits
- Return type
ElectraForPreTrainingOutput
ortuple(torch.FloatTensor)
ElectraForMaskedLM¶
-
class
transformers.
ElectraForMaskedLM
(config)[source]¶ Electra model with a language modeling head on top.
Even though both the discriminator and generator may be loaded into this model, the generator is the only model of the two to have been trained for the masked language modeling task. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None, **kwargs)[source]¶ The
ElectraForMaskedLM
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Segment token indices to indicate first and second portions of the inputs. Indices are selected in
[0, 1]
:0
corresponds to a sentence A token,1
corresponds to a sentence B tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.encoder_hidden_states (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.encoder_attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) – Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.labels (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) – Labels for computing the masked language modeling loss. Indices should be in[-100, 0, ..., config.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, ..., config.vocab_size]
kwargs (
Dict[str, any]
, optional, defaults to {}) – Used to hide legacy arguments that have been deprecated.
- Returns
A
MaskedLMOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) – Masked languaged modeling (MLM) loss.logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) – Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
MaskedLMOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import ElectraTokenizer, ElectraForMaskedLM >>> import torch >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = ElectraForMaskedLM.from_pretrained('google/electra-small-discriminator', return_dict=True) >>> input_ids = tokenizer("Hello, my dog is cute", return_tensors="pt")["input_ids"] >>> outputs = model(input_ids, labels=input_ids) >>> loss = outputs.loss >>> prediction_logits = outputs.logits
ElectraForSequenceClassification¶
-
class
transformers.
ElectraForSequenceClassification
(config)[source]¶ ELECTRA Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶ The
ElectraForSequenceClassification
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Segment token indices to indicate first and second portions of the inputs. Indices are selected in
[0, 1]
:0
corresponds to a sentence A token,1
corresponds to a sentence B tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.encoder_hidden_states (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.encoder_attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) – Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.labels (
torch.LongTensor
of shape(batch_size,)
, optional) – Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]
. Ifconfig.num_labels == 1
a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1
a classification loss is computed (Cross-Entropy).
- Returns
A
SequenceClassifierOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) – Classification (or regression if config.num_labels==1) loss.logits (
torch.FloatTensor
of shape(batch_size, config.num_labels)
) – Classification (or regression if config.num_labels==1) scores (before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
SequenceClassifierOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import ElectraTokenizer, ElectraForSequenceClassification >>> import torch >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = ElectraForSequenceClassification.from_pretrained('google/electra-small-discriminator', return_dict=True) >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> labels = torch.tensor([1]).unsqueeze(0) # Batch size 1 >>> outputs = model(**inputs, labels=labels) >>> loss = outputs.loss >>> logits = outputs.logits
ElectraForMultipleChoice¶
-
class
transformers.
ElectraForMultipleChoice
(config)[source]¶ ELECTRA Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶ The
ElectraForMultipleChoice
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Segment token indices to indicate first and second portions of the inputs. Indices are selected in
[0, 1]
:0
corresponds to a sentence A token,1
corresponds to a sentence B tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.encoder_hidden_states (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.encoder_attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) – Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.labels (
torch.LongTensor
of shape(batch_size,)
, optional) – Labels for computing the multiple choice classification loss. Indices should be in[0, ..., num_choices-1]
where num_choices is the size of the second dimension of the input tensors. (see input_ids above)
- Returns
A
MultipleChoiceModelOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
torch.FloatTensor
of shape (1,), optional, returned whenlabels
is provided) – Classification loss.logits (
torch.FloatTensor
of shape(batch_size, num_choices)
) – num_choices is the second dimension of the input tensors. (see input_ids above).Classification scores (before SoftMax).
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
MultipleChoiceModelOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import ElectraTokenizer, ElectraForMultipleChoice >>> import torch >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = ElectraForMultipleChoice.from_pretrained('google/electra-small-discriminator', return_dict=True) >>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced." >>> choice0 = "It is eaten with a fork and a knife." >>> choice1 = "It is eaten while held in the hand." >>> labels = torch.tensor(0).unsqueeze(0) # choice0 is correct (according to Wikipedia ;)), batch size 1 >>> encoding = tokenizer([[prompt, prompt], [choice0, choice1]], return_tensors='pt', padding=True) >>> outputs = model(**{k: v.unsqueeze(0) for k,v in encoding.items()}, labels=labels) # batch size is 1 >>> # the linear classifier still needs to be trained >>> loss = outputs.loss >>> logits = outputs.logits
ElectraForTokenClassification¶
-
class
transformers.
ElectraForTokenClassification
(config)[source]¶ Electra model with a token classification head on top.
Both the discriminator and generator may be loaded into this model. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶ The
ElectraForTokenClassification
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Segment token indices to indicate first and second portions of the inputs. Indices are selected in
[0, 1]
:0
corresponds to a sentence A token,1
corresponds to a sentence B tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.encoder_hidden_states (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.encoder_attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) – Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.labels (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) – Labels for computing the token classification loss. Indices should be in[0, ..., config.num_labels - 1]
.
- Returns
A
TokenClassifierOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) – Classification loss.logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.num_labels)
) – Classification scores (before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
TokenClassifierOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import ElectraTokenizer, ElectraForTokenClassification >>> import torch >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = ElectraForTokenClassification.from_pretrained('google/electra-small-discriminator', return_dict=True) >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> labels = torch.tensor([1] * inputs["input_ids"].size(1)).unsqueeze(0) # Batch size 1 >>> outputs = model(**inputs, labels=labels) >>> loss = outputs.loss >>> logits = outputs.logits
ElectraForQuestionAnswering¶
-
class
transformers.
ElectraForQuestionAnswering
(config)[source]¶ ELECTRA Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of the hidden-states output to compute span start logits and span end logits). This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
config_class
¶ alias of
transformers.configuration_electra.ElectraConfig
-
forward
(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, start_positions=None, end_positions=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶ The
ElectraForQuestionAnswering
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Segment token indices to indicate first and second portions of the inputs. Indices are selected in
[0, 1]
:0
corresponds to a sentence A token,1
corresponds to a sentence B tokenposition_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.encoder_hidden_states (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) – Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.encoder_attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) – Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.start_positions (
torch.LongTensor
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 (
torch.LongTensor
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.
- Returns
A
QuestionAnsweringModelOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftorch.FloatTensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) – Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.start_logits (
torch.FloatTensor
of shape(batch_size, sequence_length,)
) – Span-start scores (before SoftMax).end_logits (
torch.FloatTensor
of shape(batch_size, sequence_length,)
) – Span-end scores (before SoftMax).hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
QuestionAnsweringModelOutput
ortuple(torch.FloatTensor)
Example:
>>> from transformers import ElectraTokenizer, ElectraForQuestionAnswering >>> import torch >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = ElectraForQuestionAnswering.from_pretrained('google/electra-small-discriminator', return_dict=True) >>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet" >>> inputs = tokenizer(question, text, return_tensors='pt') >>> start_positions = torch.tensor([1]) >>> end_positions = torch.tensor([3]) >>> outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions) >>> loss = outputs.loss >>> start_scores = outputs.start_logits >>> end_scores = outputs.end_logits
TFElectraModel¶
-
class
transformers.
TFElectraModel
(*args, **kwargs)[source]¶ The bare Electra Model transformer outputting raw hidden-states without any specific head on top. Identical to the BERT model except that it uses an additional linear layer between the embedding layer and the encoder if the hidden size and embedding size are different.Both the generator and discriminator checkpoints may be loaded into this model. This model is a tf.keras.Model sub-class. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
a single Tensor with input_ids only and nothing else:
model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({'input_ids': input_ids, 'token_type_ids': token_type_ids})
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
call
(inputs, **kwargs)[source]¶ The
TFElectraModel
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.position_ids (
Numpy array
ortf.Tensor
of shape{0}
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
Numpy array
ortf.Tensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length, embedding_dim)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.training (
boolean
, optional, defaults toFalse
) – Whether to activate dropout modules (if set toTrue
) during training or to de-activate them (if set toFalse
) for evaluation.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.
- Returns
A
TFBaseModelOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftf.Tensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.last_hidden_state (
tf.Tensor
of shape(batch_size, sequence_length, hidden_size)
) – Sequence of hidden-states at the output of the last layer of the model.hidden_states (
tuple(tf.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftf.Tensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
TFBaseModelOutput
ortuple(tf.Tensor)
Example:
>>> from transformers import ElectraTokenizer, TFElectraModel >>> import tensorflow as tf >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = TFElectraModel.from_pretrained('google/electra-small-discriminator') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") >>> outputs = model(inputs) >>> last_hidden_states = outputs[0] # The last hidden-state is the first element of the output tuple
TFElectraForPreTraining¶
-
class
transformers.
TFElectraForPreTraining
(*args, **kwargs)[source]¶ Electra model with a binary classification head on top as used during pre-training for identifying generated tokens.
Even though both the discriminator and generator may be loaded into this model, the discriminator is the only model of the two to have the correct classification head to be used for this model. This model is a tf.keras.Model sub-class. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
a single Tensor with input_ids only and nothing else:
model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({'input_ids': input_ids, 'token_type_ids': token_type_ids})
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
call
(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, training=False)[source]¶ The
TFElectraForPreTraining
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.position_ids (
Numpy array
ortf.Tensor
of shape{0}
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
Numpy array
ortf.Tensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length, embedding_dim)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.training (
boolean
, optional, defaults toFalse
) – Whether to activate dropout modules (if set toTrue
) during training or to de-activate them (if set toFalse
) for evaluation.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.
- Returns
A
TFElectraForPreTrainingOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftf.Tensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (optional, returned when
labels
is provided,tf.Tensor
of shape(1,)
) – Total loss of the ELECTRA objective.logits (
tf.Tensor
of shape(batch_size, sequence_length)
) – Prediction scores of the head (scores for each token before SoftMax).hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftf.Tensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
Examples:
>>> import tensorflow as tf >>> from transformers import ElectraTokenizer, TFElectraForPreTraining >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = TFElectraForPreTraining.from_pretrained('google/electra-small-discriminator') >>> input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute"))[None, :] # Batch size 1 >>> outputs = model(input_ids) >>> scores = outputs[0]
- Return type
TFElectraForPreTrainingOutput
ortuple(tf.Tensor)
TFElectraForMaskedLM¶
-
class
transformers.
TFElectraForMaskedLM
(*args, **kwargs)[source]¶ Electra model with a language modeling head on top.
Even though both the discriminator and generator may be loaded into this model, the generator is the only model of the two to have been trained for the masked language modeling task. This model is a tf.keras.Model sub-class. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
a single Tensor with input_ids only and nothing else:
model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({'input_ids': input_ids, 'token_type_ids': token_type_ids})
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
call
(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False)[source]¶ The
TFElectraForMaskedLM
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.position_ids (
Numpy array
ortf.Tensor
of shape{0}
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
Numpy array
ortf.Tensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length, embedding_dim)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.training (
boolean
, optional, defaults toFalse
) – Whether to activate dropout modules (if set toTrue
) during training or to de-activate them (if set toFalse
) for evaluation.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.labels (
tf.Tensor
of shape(batch_size, sequence_length)
, optional) – Labels for computing the masked language modeling loss. Indices should be in[-100, 0, ..., config.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, ..., config.vocab_size]
- Returns
A
TFMaskedLMOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftf.Tensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
tf.Tensor
of shape(1,)
, optional, returned whenlabels
is provided) – Masked languaged modeling (MLM) loss.logits (
tf.Tensor
of shape(batch_size, sequence_length, config.vocab_size)
) – Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftf.Tensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
TFMaskedLMOutput
ortuple(tf.Tensor)
- Example::
>>> from transformers import ElectraTokenizer, TFElectraForMaskedLM >>> import tensorflow as tf
>>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-generator') >>> model = TFElectraForMaskedLM.from_pretrained('google/electra-small-generator')
>>> input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True))[None, :] # Batch size 1
>>> outputs = model(input_ids) >>> prediction_scores = outputs[0]
TFElectraForSequenceClassification¶
-
class
transformers.
TFElectraForSequenceClassification
(*args, **kwargs)[source]¶ ELECTRA Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks. This model is a tf.keras.Model sub-class. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
a single Tensor with input_ids only and nothing else:
model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({'input_ids': input_ids, 'token_type_ids': token_type_ids})
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
call
(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False)[source]¶ The
TFElectraForSequenceClassification
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.position_ids (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
Numpy array
ortf.Tensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length, embedding_dim)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.training (
boolean
, optional, defaults toFalse
) – Whether to activate dropout modules (if set toTrue
) during training or to de-activate them (if set toFalse
) for evaluation.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.labels (
tf.Tensor
of shape(batch_size,)
, optional) – Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]
. Ifconfig.num_labels == 1
a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1
a classification loss is computed (Cross-Entropy).
- Returns
A
TFSequenceClassifierOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftf.Tensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
tf.Tensor
of shape(1,)
, optional, returned whenlabels
is provided) – Classification (or regression if config.num_labels==1) loss.logits (
tf.Tensor
of shape(batch_size, config.num_labels)
) – Classification (or regression if config.num_labels==1) scores (before SoftMax).hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftf.Tensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
TFSequenceClassifierOutput
ortuple(tf.Tensor)
Example:
>>> from transformers import ElectraTokenizer, TFElectraForSequenceClassification >>> import tensorflow as tf >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = TFElectraForSequenceClassification.from_pretrained('google/electra-small-discriminator') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") >>> inputs["labels"] = tf.reshape(tf.constant(1), (-1, 1)) # Batch size 1 >>> outputs = model(inputs) >>> loss, logits = outputs[:2]
TFElectraForMultipleChoice¶
-
class
transformers.
TFElectraForMultipleChoice
(*args, **kwargs)[source]¶ ELECTRA Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks. This model is a tf.keras.Model sub-class. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
a single Tensor with input_ids only and nothing else:
model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({'input_ids': input_ids, 'token_type_ids': token_type_ids})
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
call
(inputs, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False)[source]¶ The
TFElectraForMultipleChoice
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.position_ids (
Numpy array
ortf.Tensor
of shape(batch_size, num_choices, sequence_length)
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
Numpy array
ortf.Tensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length, embedding_dim)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.training (
boolean
, optional, defaults toFalse
) – Whether to activate dropout modules (if set toTrue
) during training or to de-activate them (if set toFalse
) for evaluation.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.labels (
tf.Tensor
of shape(batch_size,)
, optional) – Labels for computing the multiple choice classification loss. Indices should be in[0, ..., num_choices]
where num_choices is the size of the second dimension of the input tensors. (see input_ids above)
- Returns
A
TFMultipleChoiceModelOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftf.Tensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
tf.Tensor
of shape (1,), optional, returned whenlabels
is provided) – Classification loss.logits (
tf.Tensor
of shape(batch_size, num_choices)
) – num_choices is the second dimension of the input tensors. (see input_ids above).Classification scores (before SoftMax).
hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftf.Tensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
TFMultipleChoiceModelOutput
ortuple(tf.Tensor)
Example:
>>> from transformers import ElectraTokenizer, TFElectraForMultipleChoice >>> import tensorflow as tf >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = TFElectraForMultipleChoice.from_pretrained('google/electra-small-discriminator') >>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced." >>> choice0 = "It is eaten with a fork and a knife." >>> choice1 = "It is eaten while held in the hand." >>> encoding = tokenizer([[prompt, prompt], [choice0, choice1]], return_tensors='tf', padding=True) >>> inputs = {k: tf.expand_dims(v, 0) for k, v in encoding.items()} >>> outputs = model(inputs) # batch size is 1 >>> # the linear classifier still needs to be trained >>> logits = outputs[0]
-
property
dummy_inputs
¶ Dummy inputs to build the network.
- Returns
tf.Tensor with dummy inputs
TFElectraForTokenClassification¶
-
class
transformers.
TFElectraForTokenClassification
(*args, **kwargs)[source]¶ Electra model with a token classification head on top.
Both the discriminator and generator may be loaded into this model. This model is a tf.keras.Model sub-class. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
a single Tensor with input_ids only and nothing else:
model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({'input_ids': input_ids, 'token_type_ids': token_type_ids})
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
call
(inputs, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, labels=None, training=False)[source]¶ The
TFElectraForTokenClassification
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.position_ids (
Numpy array
ortf.Tensor
of shape{0}
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
Numpy array
ortf.Tensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length, embedding_dim)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.training (
boolean
, optional, defaults toFalse
) – Whether to activate dropout modules (if set toTrue
) during training or to de-activate them (if set toFalse
) for evaluation.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.labels (
tf.Tensor
of shape(batch_size, sequence_length)
, optional) – Labels for computing the token classification loss. Indices should be in[0, ..., config.num_labels - 1]
.
- Returns
A
TFTokenClassifierOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftf.Tensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
tf.Tensor
of shape(1,)
, optional, returned whenlabels
is provided) – Classification loss.logits (
tf.Tensor
of shape(batch_size, sequence_length, config.num_labels)
) – Classification scores (before SoftMax).hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftf.Tensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
TFTokenClassifierOutput
ortuple(tf.Tensor)
Example:
>>> from transformers import ElectraTokenizer, TFElectraForTokenClassification >>> import tensorflow as tf >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = TFElectraForTokenClassification.from_pretrained('google/electra-small-discriminator') >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf") >>> input_ids = inputs["input_ids"] >>> inputs["labels"] = tf.reshape(tf.constant([1] * tf.size(input_ids).numpy()), (-1, tf.size(input_ids))) # Batch size 1 >>> outputs = model(inputs) >>> loss, scores = outputs[:2]
TFElectraForQuestionAnswering¶
-
class
transformers.
TFElectraForQuestionAnswering
(*args, **kwargs)[source]¶ Electra Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of the hidden-states output to compute span start logits and span end logits). This model is a tf.keras.Model sub-class. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
Note
TF 2.0 models accepts two formats as inputs:
having all inputs as keyword arguments (like PyTorch models), or
having all inputs as a list, tuple or dict in the first positional arguments.
This second option is useful when using
tf.keras.Model.fit()
method which currently requires having all the tensors in the first argument of the model call function:model(inputs)
.If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
a single Tensor with input_ids only and nothing else:
model(inputs_ids)
a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([input_ids, attention_mask])
ormodel([input_ids, attention_mask, token_type_ids])
a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({'input_ids': input_ids, 'token_type_ids': token_type_ids})
- Parameters
config (
ElectraConfig
) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out thefrom_pretrained()
method to load the model weights.
-
call
(inputs, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, return_dict=None, start_positions=None, end_positions=None, training=False)[source]¶ The
TFElectraForQuestionAnswering
forward method, overrides the__call__()
special method.Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.- Parameters
input_ids (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
) –Indices of input sequence tokens in the vocabulary.
Indices can be obtained using
transformers.ElectraTokenizer
. Seetransformers.PreTrainedTokenizer.encode()
andtransformers.PreTrainedTokenizer.__call__()
for details.attention_mask (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length)
, optional) –Mask to avoid performing attention on padding token indices. Mask values selected in
[0, 1]
:1
for tokens that are NOT MASKED,0
for MASKED tokens.position_ids (
Numpy array
ortf.Tensor
of shape{0}
, optional) –Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
[0, config.max_position_embeddings - 1]
.head_mask (
Numpy array
ortf.Tensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) – Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:1
indicates the head is not masked,0
indicates the head is masked.inputs_embeds (
Numpy array
ortf.Tensor
of shape(batch_size, sequence_length, embedding_dim)
, optional) – Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.training (
boolean
, optional, defaults toFalse
) – Whether to activate dropout modules (if set toTrue
) during training or to de-activate them (if set toFalse
) for evaluation.output_attentions (
bool
, optional) – If set toTrue
, the attentions tensors of all attention layers are returned. Seeattentions
under returned tensors for more detail.output_hidden_states (
bool
, optional) – If set toTrue
, the hidden states of all layers are returned. Seehidden_states
under returned tensors for more detail.return_dict (
bool
, optional) – If set toTrue
, the model will return aModelOutput
instead of a plain tuple.start_positions (
tf.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 (
tf.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.
- Returns
A
TFQuestionAnsweringModelOutput
(ifreturn_dict=True
is passed or whenconfig.return_dict=True
) or a tuple oftf.Tensor
comprising various elements depending on the configuration (ElectraConfig
) and inputs.loss (
tf.Tensor
of shape(1,)
, optional, returned whenlabels
is provided) – Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.start_logits (
tf.Tensor
of shape(batch_size, sequence_length,)
) – Span-start scores (before SoftMax).end_logits (
tf.Tensor
of shape(batch_size, sequence_length,)
) – Span-end scores (before SoftMax).hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) – Tuple oftf.Tensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) – Tuple oftf.Tensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
- Return type
TFQuestionAnsweringModelOutput
ortuple(tf.Tensor)
Example:
>>> from transformers import ElectraTokenizer, TFElectraForQuestionAnswering >>> import tensorflow as tf >>> tokenizer = ElectraTokenizer.from_pretrained('google/electra-small-discriminator') >>> model = TFElectraForQuestionAnswering.from_pretrained('google/electra-small-discriminator') >>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet" >>> input_dict = tokenizer(question, text, return_tensors='tf') >>> start_scores, end_scores = model(input_dict) >>> all_tokens = tokenizer.convert_ids_to_tokens(input_dict["input_ids"].numpy()[0]) >>> answer = ' '.join(all_tokens[tf.math.argmax(start_scores, 1)[0] : tf.math.argmax(end_scores, 1)[0]+1])