Transformers documentation
ALBERT
ALBERT
概要
ALBERTモデルは、「ALBERT: A Lite BERT for Self-supervised Learning of Language Representations」という論文でZhenzhong Lan、Mingda Chen、Sebastian Goodman、Kevin Gimpel、Piyush Sharma、Radu Soricutによって提案されました。BERTのメモリ消費を減らしトレーニングを高速化するためのパラメータ削減技術を2つ示しています：
- 埋め込み行列を2つの小さな行列に分割する。
- グループ間で分割された繰り返し層を使用する。
論文の要旨は以下の通りです：
自然言語表現の事前学習時にモデルのサイズを増やすと、下流タスクのパフォーマンスが向上することがしばしばあります。しかし、ある時点でさらなるモデルの増大は、GPU/TPUのメモリ制限、長い訓練時間、予期せぬモデルの劣化といった問題のために困難になります。これらの問題に対処するために、我々はBERTのメモリ消費を低減し、訓練速度を高めるための2つのパラメータ削減技術を提案します。包括的な実証的証拠は、我々の提案方法が元のBERTに比べてはるかによくスケールするモデルを生み出すことを示しています。また、文間の一貫性をモデリングに焦点を当てた自己教師あり損失を使用し、複数の文が含まれる下流タスクに一貫して助けとなることを示します。その結果、我々の最良のモデルは、BERT-largeに比べてパラメータが少ないにもかかわらず、GLUE、RACE、SQuADベンチマークで新たな最先端の結果を確立します。
このモデルはlysandreにより提供されました。このモデルのjaxバージョンはkamalkrajにより提供されました。オリジナルのコードはこちらで見ることができます。
使用上のヒント
- ALBERTは絶対位置埋め込みを使用するモデルなので、通常、入力を左側ではなく右側にパディングすることが推奨されます。
- ALBERTは繰り返し層を使用するためメモリ使用量は小さくなりますが、同じ数の（繰り返し）層を反復しなければならないため、隠れ層の数が同じであればBERTのようなアーキテクチャと同様の計算コストがかかります。
- 埋め込みサイズEは隠れサイズHと異なりますが、これは埋め込みが文脈に依存しない（一つの埋め込みベクトルが一つのトークンを表す）のに対し、隠れ状態は文脈に依存する（1つの隠れ状態がトークン系列を表す）ため、H >> Eとすることがより論理的です。また、埋め込み行列のサイズはV x Eと大きいです（Vは語彙サイズ）。E < Hであれば、パラメータは少なくなります。
- 層はパラメータを共有するグループに分割されています（メモリ節約のため）。次文予測（NSP: Next Sentence Prediction）は文の順序予測に置き換えられます：入力では、2つの文AとB（それらは連続している）があり、Aに続いてBを与えるか、Bに続いてAを与えます。モデルはそれらが入れ替わっているかどうかを予測する必要があります。
参考資料
AlbertConfig
class transformers.AlbertConfig
< source >( vocab_size = 30000 embedding_size = 128 hidden_size = 4096 num_hidden_layers = 12 num_hidden_groups = 1 num_attention_heads = 64 intermediate_size = 16384 inner_group_num = 1 hidden_act = 'gelu_new' hidden_dropout_prob = 0 attention_probs_dropout_prob = 0 max_position_embeddings = 512 type_vocab_size = 2 initializer_range = 0.02 layer_norm_eps = 1e-12 classifier_dropout_prob = 0.1 position_embedding_type = 'absolute' pad_token_id = 0 bos_token_id = 2 eos_token_id = 3 **kwargs )
Parameters
- vocab_size (
int, optional, defaults to 30000) — Vocabulary size of the ALBERT model. Defines the number of different tokens that can be represented by theinputs_idspassed when calling AlbertModel orTFAlbertModel. - embedding_size (
int, optional, defaults to 128) — Dimensionality of vocabulary embeddings. - hidden_size (
int, optional, defaults to 4096) — 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_hidden_groups (
int, optional, defaults to 1) — Number of groups for the hidden layers, parameters in the same group are shared. - num_attention_heads (
int, optional, defaults to 64) — Number of attention heads for each attention layer in the Transformer encoder. - intermediate_size (
int, optional, defaults to 16384) — The dimensionality of the “intermediate” (often named feed-forward) layer in the Transformer encoder. - inner_group_num (
int, optional, defaults to 1) — The number of inner repetition of attention and ffn. - hidden_act (
strorCallable, optional, defaults to"gelu_new") — The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu","relu","silu"and"gelu_new"are supported. - hidden_dropout_prob (
float, optional, defaults to 0) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. - attention_probs_dropout_prob (
float, optional, defaults to 0) — 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 (e.g., 512 or 1024 or 2048). - type_vocab_size (
int, optional, defaults to 2) — The vocabulary size of thetoken_type_idspassed when calling AlbertModel orTFAlbertModel. - 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. - classifier_dropout_prob (
float, optional, defaults to 0.1) — The dropout ratio for attached classifiers. - position_embedding_type (
str, optional, defaults to"absolute") — Type of position embedding. Choose one of"absolute","relative_key","relative_key_query". For positional embeddings use"absolute". For more information on"relative_key", please refer to Self-Attention with Relative Position Representations (Shaw et al.). For more information on"relative_key_query", please refer to Method 4 in Improve Transformer Models with Better Relative Position Embeddings (Huang et al.). - pad_token_id (
int, optional, defaults to 0) — Padding token id. - bos_token_id (
int, optional, defaults to 2) — Beginning of stream token id. - eos_token_id (
int, optional, defaults to 3) — End of stream token id.
This is the configuration class to store the configuration of a AlbertModel or a TFAlbertModel. It is used
to instantiate an ALBERT 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 ALBERT
albert/albert-xxlarge-v2 architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Examples:
>>> from transformers import AlbertConfig, AlbertModel
>>> # Initializing an ALBERT-xxlarge style configuration
>>> albert_xxlarge_configuration = AlbertConfig()
>>> # Initializing an ALBERT-base style configuration
>>> albert_base_configuration = AlbertConfig(
... hidden_size=768,
... num_attention_heads=12,
... intermediate_size=3072,
... )
>>> # Initializing a model (with random weights) from the ALBERT-base style configuration
>>> model = AlbertModel(albert_xxlarge_configuration)
>>> # Accessing the model configuration
>>> configuration = model.configAlbertTokenizer
class transformers.AlbertTokenizer
< source >( vocab_file do_lower_case = True remove_space = True keep_accents = False bos_token = '[CLS]' eos_token = '[SEP]' unk_token = '<unk>' sep_token = '[SEP]' pad_token = '<pad>' cls_token = '[CLS]' mask_token = '[MASK]' sp_model_kwargs: typing.Optional[dict[str, typing.Any]] = None **kwargs )
Parameters
- vocab_file (
str) — SentencePiece file (generally has a .spm extension) that contains the vocabulary necessary to instantiate a tokenizer. - do_lower_case (
bool, optional, defaults toTrue) — Whether or not to lowercase the input when tokenizing. - remove_space (
bool, optional, defaults toTrue) — Whether or not to strip the text when tokenizing (removing excess spaces before and after the string). - keep_accents (
bool, optional, defaults toFalse) — Whether or not to keep accents when tokenizing. - bos_token (
str, optional, defaults to"[CLS]") — The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the
cls_token. - eos_token (
str, optional, defaults to"[SEP]") — The end of sequence token.When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the
sep_token. - unk_token (
str, optional, defaults to"<unk>") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. - sep_token (
str, optional, defaults to"[SEP]") — The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens. - pad_token (
str, optional, defaults to"<pad>") — The token used for padding, for example when batching sequences of different lengths. - cls_token (
str, optional, defaults to"[CLS]") — The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. - mask_token (
str, optional, defaults to"[MASK]") — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict. - sp_model_kwargs (
dict, optional) — Will be passed to theSentencePieceProcessor.__init__()method. The Python wrapper for SentencePiece can be used, among other things, to set:-
enable_sampling: Enable subword regularization. -
nbest_size: Sampling parameters for unigram. Invalid for BPE-Dropout.nbest_size = {0,1}: No sampling is performed.nbest_size > 1: samples from the nbest_size results.nbest_size < 0: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm.
-
alpha: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout.
-
- sp_model (
SentencePieceProcessor) — The SentencePiece processor that is used for every conversion (string, tokens and IDs).
Construct an ALBERT tokenizer. Based on SentencePiece.
This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.
build_inputs_with_special_tokens
< source >( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None ) → List[int]
Parameters
- token_ids_0 (
List[int]) — List of IDs to which the special tokens will be added. - token_ids_1 (
List[int], optional) — Optional second list of IDs for sequence pairs.
Returns
List[int]
List of input IDs with the appropriate special tokens.
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. An ALBERT sequence has the following format:
- single sequence:
[CLS] X [SEP] - pair of sequences:
[CLS] A [SEP] B [SEP]
get_special_tokens_mask
< source >( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None already_has_special_tokens: bool = False ) → List[int]
Parameters
- token_ids_0 (
List[int]) — List of IDs. - token_ids_1 (
List[int], optional) — Optional second list of IDs for sequence pairs. - already_has_special_tokens (
bool, optional, defaults toFalse) — Whether or not the token list is already formatted with special tokens for the model.
Returns
List[int]
A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer prepare_for_model method.
create_token_type_ids_from_sequences
< source >( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None ) → list[int]
Create the token type IDs corresponding to the sequences passed. What are token type IDs?
Should be overridden in a subclass if the model has a special way of building those.
AlbertTokenizerFast
class transformers.AlbertTokenizerFast
< source >( vocab_file = None tokenizer_file = None do_lower_case = True remove_space = True keep_accents = False bos_token = '[CLS]' eos_token = '[SEP]' unk_token = '<unk>' sep_token = '[SEP]' pad_token = '<pad>' cls_token = '[CLS]' mask_token = '[MASK]' **kwargs )
Parameters
- vocab_file (
str) — SentencePiece file (generally has a .spm extension) that contains the vocabulary necessary to instantiate a tokenizer. - do_lower_case (
bool, optional, defaults toTrue) — Whether or not to lowercase the input when tokenizing. - remove_space (
bool, optional, defaults toTrue) — Whether or not to strip the text when tokenizing (removing excess spaces before and after the string). - keep_accents (
bool, optional, defaults toFalse) — Whether or not to keep accents when tokenizing. - bos_token (
str, optional, defaults to"[CLS]") — The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the
cls_token. - eos_token (
str, optional, defaults to"[SEP]") — The end of sequence token. .. note:: When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is thesep_token. - unk_token (
str, optional, defaults to"<unk>") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. - sep_token (
str, optional, defaults to"[SEP]") — The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens. - pad_token (
str, optional, defaults to"<pad>") — The token used for padding, for example when batching sequences of different lengths. - cls_token (
str, optional, defaults to"[CLS]") — The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. - mask_token (
str, optional, defaults to"[MASK]") — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict.
Construct a “fast” ALBERT tokenizer (backed by HuggingFace’s tokenizers library). Based on Unigram. This tokenizer inherits from PreTrainedTokenizerFast which contains most of the main methods. Users should refer to this superclass for more information regarding those methods
build_inputs_with_special_tokens
< source >( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None ) → List[int]
Parameters
- token_ids_0 (
List[int]) — List of IDs to which the special tokens will be added - token_ids_1 (
List[int], optional) — Optional second list of IDs for sequence pairs.
Returns
List[int]
list of input IDs with the appropriate special tokens.
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. An ALBERT sequence has the following format:
- single sequence:
[CLS] X [SEP] - pair of sequences:
[CLS] A [SEP] B [SEP]
Albert specific outputs
class transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput
< source >( loss: typing.Optional[torch.FloatTensor] = None prediction_logits: typing.Optional[torch.FloatTensor] = None sop_logits: typing.Optional[torch.FloatTensor] = None hidden_states: typing.Optional[tuple[torch.FloatTensor]] = None attentions: typing.Optional[tuple[torch.FloatTensor]] = None )
Parameters
- loss (
*optional*, returned whenlabelsis provided,torch.FloatTensorof shape(1,)) — Total loss as the sum of the masked language modeling loss and the next sequence prediction (classification) loss. - prediction_logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - sop_logits (
torch.FloatTensorof shape(batch_size, 2)) — Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax). - hidden_states (
tuple[torch.FloatTensor], optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + 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 optional initial embedding outputs.
- attentions (
tuple[torch.FloatTensor], optional, returned whenoutput_attentions=Trueis 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.
Output type of AlbertForPreTraining.
AlbertModel
class transformers.AlbertModel
< source >( config: AlbertConfig add_pooling_layer: bool = True )
Parameters
- config (AlbertConfig) — 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 the from_pretrained() method to load the model weights.
- add_pooling_layer (
bool, optional, defaults toTrue) — Whether to add a pooling layer
The bare Albert Model outputting raw hidden-states without any specific head on top.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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 tokens that are masked.
- token_type_ids (
torch.LongTensorof 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 token.
- position_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.n_positions - 1]. - head_mask (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix.
Returns
transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutputWithPooling or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (AlbertConfig) and inputs.
-
last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model. -
pooler_output (
torch.FloatTensorof shape(batch_size, hidden_size)) — Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + 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 optional initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis 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.
The AlbertModel forward method, overrides the __call__ special method.
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.
AlbertForPreTraining
class transformers.AlbertForPreTraining
< source >( config: AlbertConfig )
Parameters
- config (AlbertConfig) — 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 the from_pretrained() method to load the model weights.
Albert Model with two heads on top as done during the pretraining: a masked language modeling head and a
sentence order prediction (classification) head.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None sentence_order_label: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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 tokens that are masked.
- token_type_ids (
torch.LongTensorof 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 token.
- position_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.n_positions - 1]. - head_mask (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - labels (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Labels for computing the masked language modeling loss. Indices should be in[-100, 0, ..., config.vocab_size](seeinput_idsdocstring) Tokens with indices set to-100are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size] - sentence_order_label (
torch.LongTensorof shape(batch_size,), optional) — Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair (seeinput_idsdocstring) Indices should be in[0, 1].0indicates original order (sequence A, then sequence B),1indicates switched order (sequence B, then sequence A).
Returns
transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or tuple(torch.FloatTensor)
A transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (AlbertConfig) and inputs.
-
loss (
*optional*, returned whenlabelsis provided,torch.FloatTensorof shape(1,)) — Total loss as the sum of the masked language modeling loss and the next sequence prediction (classification) loss. -
prediction_logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
sop_logits (
torch.FloatTensorof shape(batch_size, 2)) — Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax). -
hidden_states (
tuple[torch.FloatTensor], optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + 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 optional initial embedding outputs.
-
attentions (
tuple[torch.FloatTensor], optional, returned whenoutput_attentions=Trueis 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.
The AlbertForPreTraining forward method, overrides the __call__ special method.
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.
Example:
>>> from transformers import AutoTokenizer, AlbertForPreTraining
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("albert/albert-base-v2")
>>> model = AlbertForPreTraining.from_pretrained("albert/albert-base-v2")
>>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)
>>> # Batch size 1
>>> outputs = model(input_ids)
>>> prediction_logits = outputs.prediction_logits
>>> sop_logits = outputs.sop_logitsAlbertForMaskedLM
class transformers.AlbertForMaskedLM
< source >( config )
Parameters
- config (AlbertForMaskedLM) — 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 the from_pretrained() method to load the model weights.
The Albert Model with a language modeling head on top.”
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.MaskedLMOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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 tokens that are masked.
- token_type_ids (
torch.LongTensorof 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 token.
- position_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.n_positions - 1]. - head_mask (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - labels (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Labels for computing the masked language modeling loss. Indices should be in[-100, 0, ..., config.vocab_size](seeinput_idsdocstring) Tokens with indices set to-100are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size]
Returns
transformers.modeling_outputs.MaskedLMOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.MaskedLMOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (AlbertConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Masked language modeling (MLM) loss. -
logits (
torch.FloatTensorof 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=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + 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 optional initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis 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.
The AlbertForMaskedLM forward method, overrides the __call__ special method.
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.
Example:
>>> import torch
>>> from transformers import AutoTokenizer, AlbertForMaskedLM
>>> tokenizer = AutoTokenizer.from_pretrained("albert/albert-base-v2")
>>> model = AlbertForMaskedLM.from_pretrained("albert/albert-base-v2")
>>> # add mask_token
>>> inputs = tokenizer("The capital of [MASK] is Paris.", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> # retrieve index of [MASK]
>>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]
>>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
>>> tokenizer.decode(predicted_token_id)
'france'AlbertForSequenceClassification
class transformers.AlbertForSequenceClassification
< source >( config: AlbertConfig )
Parameters
- config (AlbertConfig) — 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 the from_pretrained() method to load the model weights.
Albert 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 inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.SequenceClassifierOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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 tokens that are masked.
- token_type_ids (
torch.LongTensorof 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 token.
- position_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.n_positions - 1]. - head_mask (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - labels (
torch.LongTensorof shape(batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]. Ifconfig.num_labels == 1a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.SequenceClassifierOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.SequenceClassifierOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (AlbertConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensorof 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=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + 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 optional initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis 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.
The AlbertForSequenceClassification forward method, overrides the __call__ special method.
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.
Example of single-label classification:
>>> import torch
>>> from transformers import AutoTokenizer, AlbertForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("albert/albert-xxlarge-v2")
>>> model = AlbertForSequenceClassification.from_pretrained("albert/albert-xxlarge-v2")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_id = logits.argmax().item()
>>> model.config.id2label[predicted_class_id]
...
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = AlbertForSequenceClassification.from_pretrained("albert/albert-xxlarge-v2", num_labels=num_labels)
>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...Example of multi-label classification:
>>> import torch
>>> from transformers import AutoTokenizer, AlbertForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("albert/albert-xxlarge-v2")
>>> model = AlbertForSequenceClassification.from_pretrained("albert/albert-xxlarge-v2", problem_type="multi_label_classification")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = AlbertForSequenceClassification.from_pretrained(
... "albert/albert-xxlarge-v2", num_labels=num_labels, problem_type="multi_label_classification"
... )
>>> labels = torch.sum(
... torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).lossAlbertForMultipleChoice
class transformers.AlbertForMultipleChoice
< source >( config: AlbertConfig )
Parameters
- config (AlbertConfig) — 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 the from_pretrained() method to load the model weights.
The Albert 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 inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, num_choices, sequence_length)) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.
- attention_mask (
torch.FloatTensorof 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 tokens that are masked.
- token_type_ids (
torch.LongTensorof shape(batch_size, num_choices, 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 token.
- position_ids (
torch.LongTensorof 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 (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, num_choices, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - labels (
torch.LongTensorof 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
transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or tuple(torch.FloatTensor)
A transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (AlbertConfig) and inputs.
-
loss (
*optional*, returned whenlabelsis provided,torch.FloatTensorof shape(1,)) — Total loss as the sum of the masked language modeling loss and the next sequence prediction (classification) loss. -
prediction_logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
sop_logits (
torch.FloatTensorof shape(batch_size, 2)) — Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax). -
hidden_states (
tuple[torch.FloatTensor], optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + 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 optional initial embedding outputs.
-
attentions (
tuple[torch.FloatTensor], optional, returned whenoutput_attentions=Trueis 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.
The AlbertForMultipleChoice forward method, overrides the __call__ special method.
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.
Example:
>>> from transformers import AutoTokenizer, AlbertForMultipleChoice
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("albert/albert-xxlarge-v2")
>>> model = AlbertForMultipleChoice.from_pretrained("albert/albert-xxlarge-v2")
>>> 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.logitsAlbertForTokenClassification
class transformers.AlbertForTokenClassification
< source >( config: AlbertConfig )
Parameters
- config (AlbertConfig) — 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 the from_pretrained() method to load the model weights.
The Albert transformer with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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 tokens that are masked.
- token_type_ids (
torch.LongTensorof 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 token.
- position_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.n_positions - 1]. - head_mask (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - labels (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Labels for computing the token classification loss. Indices should be in[0, ..., config.num_labels - 1].
Returns
transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.TokenClassifierOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (AlbertConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification loss. -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.num_labels)) — Classification scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + 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 optional initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis 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.
The AlbertForTokenClassification forward method, overrides the __call__ special method.
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.
Example:
>>> from transformers import AutoTokenizer, AlbertForTokenClassification
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("albert/albert-xxlarge-v2")
>>> model = AlbertForTokenClassification.from_pretrained("albert/albert-xxlarge-v2")
>>> inputs = tokenizer(
... "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
... )
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_token_class_ids = logits.argmax(-1)
>>> # Note that tokens are classified rather then input words which means that
>>> # there might be more predicted token classes than words.
>>> # Multiple token classes might account for the same word
>>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
>>> predicted_tokens_classes
...
>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...AlbertForQuestionAnswering
class transformers.AlbertForQuestionAnswering
< source >( config: AlbertConfig )
Parameters
- config (AlbertConfig) — 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 the from_pretrained() method to load the model weights.
The Albert transformer with a span classification head on top for extractive question-answering tasks like
SQuAD (a linear layer on top of the hidden-states output to compute span start logits and span end logits).
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None start_positions: typing.Optional[torch.LongTensor] = None end_positions: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensorof 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 tokens that are masked.
- token_type_ids (
torch.LongTensorof 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 token.
- position_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.n_positions - 1]. - head_mask (
torch.FloatTensorof 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.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - start_positions (
torch.LongTensorof 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.LongTensorof 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
transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or tuple(torch.FloatTensor)
A transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (AlbertConfig) and inputs.
-
loss (
*optional*, returned whenlabelsis provided,torch.FloatTensorof shape(1,)) — Total loss as the sum of the masked language modeling loss and the next sequence prediction (classification) loss. -
prediction_logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
sop_logits (
torch.FloatTensorof shape(batch_size, 2)) — Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax). -
hidden_states (
tuple[torch.FloatTensor], optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + 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 optional initial embedding outputs.
-
attentions (
tuple[torch.FloatTensor], optional, returned whenoutput_attentions=Trueis 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.
The AlbertForQuestionAnswering forward method, overrides the __call__ special method.
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.
Example:
>>> from transformers import AutoTokenizer, AlbertForQuestionAnswering
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("albert/albert-xxlarge-v2")
>>> model = AlbertForQuestionAnswering.from_pretrained("albert/albert-xxlarge-v2")
>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**inputs)
>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()
>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
>>> tokenizer.decode(predict_answer_tokens, skip_special_tokens=True)
...
>>> # target is "nice puppet"
>>> target_start_index = torch.tensor([14])
>>> target_end_index = torch.tensor([15])
>>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
>>> loss = outputs.loss
>>> round(loss.item(), 2)
...