Transformers documentation
ALBERT
ALBERT
ALBERT는 BERT의 확장성과 학습 시 메모리 한계를 해결하기 위해 설계된 모델입니다. 이 모델은 두 가지 파라미터 감소 기법을 도입합니다. 첫 번째는 임베딩 행렬 분해(factorized embedding parametrization)로, 큰 어휘 임베딩 행렬을 두 개의 작은 행렬로 분해하여 히든 사이즈를 늘려도 파라미터 수가 크게 증가하지 않도록 합니다. 두 번째는 계층 간 파라미터 공유(cross-layer parameter sharing)로, 여러 계층이 파라미터를 공유하여 학습해야 할 파라미터 수를 줄입니다.
ALBERT는 BERT에서 발생하는 GPU/TPU 메모리 한계, 긴 학습 시간, 갑작스런 성능 저하 문제를 해결하기 위해 만들어졌습니다. ALBERT는 파라미터를 줄이기 위해 두 가지 기법을 사용하여 메모리 사용량을 줄이고 BERT의 학습 속도를 높입니다:
- 임베딩 행렬 분해: 큰 어휘 임베딩 행렬을 두 개의 더 작은 행렬로 분해하여 메모리 사용량을 줄입니다.
- 계층 간 파라미터 공유: 각 트랜스포머 계층마다 별도의 파라미터를 학습하는 대신, 여러 계층이 파라미터를 공유하여 학습해야 할 가중치 수를 더욱 줄입니다.
ALBERT는 BERT와 마찬가지로 절대 위치 임베딩(absolute position embeddings)을 사용하므로, 입력 패딩은 오른쪽에 적용해야 합니다. 임베딩 크기는 128이며, BERT의 768보다 작습니다. ALBERT는 한 번에 최대 512개의 토큰을 처리할 수 있습니다.
모든 공식 ALBERT 체크포인트는 ALBERT 커뮤니티 조직에서 확인하실 수 있습니다.
오른쪽 사이드바의 ALBERT 모델을 클릭하시면 다양한 언어 작업에 ALBERT를 적용하는 예시를 더 확인하실 수 있습니다.
아래 예시는 Pipeline, AutoModel 그리고 커맨드라인에서 [MASK] 토큰을 예측하는 방법을 보여줍니다.
import torch
from transformers import pipeline
pipeline = pipeline(
task="fill-mask",
model="albert-base-v2",
dtype=torch.float16,
device=0
)
pipeline("식물은 광합성이라고 알려진 과정을 통해 [MASK]를 생성합니다.", top_k=5)참고 사항
- BERT는 절대 위치 임베딩을 사용하므로, 오른쪽에 입력이 패딩돼야 합니다.
- 임베딩 크기
E는 히든 크기H와 다릅니다. 임베딩은 문맥에 독립적(각 토큰마다 하나의 임베딩 벡터)이고, 은닉 상태는 문맥에 의존적(토큰 시퀀스마다 하나의 은닉 상태)입니다. 임베딩 행렬은V x E(V: 어휘 크기)이므로, 일반적으로H >> E가 더 논리적입니다.E < H일 때 모델 파라미터가 더 적어집니다.
참고 자료
아래 섹션의 자료들은 공식 Hugging Face 및 커뮤니티(🌎 표시) 자료로, AlBERT를 시작하는 데 도움이 됩니다. 여기에 추가할 자료가 있다면 Pull Request를 보내주세요! 기존 자료와 중복되지 않고 새로운 내용을 담고 있으면 좋습니다.
AlbertForSequenceClassification은 이 예제 스크립트에서 지원됩니다.
TFAlbertForSequenceClassification은 이 예제 스크립트에서 지원됩니다.FlaxAlbertForSequenceClassification은 이 예제 스크립트와 노트북에서 지원됩니다.텍스트 분류 작업 가이드에서 모델 사용법을 확인하세요.
AlbertForTokenClassification은 이 예제 스크립트에서 지원됩니다.
FlaxAlbertForTokenClassification은 이 예제 스크립트에서 지원됩니다.🤗 Hugging Face의 토큰 분류 강좌
토큰 분류 작업 가이드에서 모델 사용법을 확인하세요.
- AlbertForMaskedLM은 이 예제 스크립트와 노트북에서 지원됩니다.
TFAlbertForMaskedLM은 이 예제 스크립트와 노트북에서 지원됩니다.FlaxAlbertForMaskedLM은 이 예제 스크립트와 노트북에서 지원됩니다.- 🤗 Hugging Face의 마스킹 언어 모델링 강좌
- 마스킹 언어 모델링 작업 가이드에서 모델 사용법을 확인하세요.
- AlbertForQuestionAnswering은 이 예제 스크립트와 노트북에서 지원됩니다.
TFAlbertForQuestionAnswering은 이 예제 스크립트와 노트북에서 지원됩니다.FlaxAlbertForQuestionAnswering은 이 예제 스크립트에서 지원됩니다.- 질의응답 🤗 Hugging Face 강좌의 챕터.
- 질의응답 작업 가이드에서 모델 사용법을 확인하세요.
다중 선택(Multiple choice)
AlbertForMultipleChoice는 이 예제 스크립트와 노트북에서 지원됩니다.
다중 선택 작업 가이드에서 모델 사용법을 확인하세요.
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 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. - 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. - 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. - 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. 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 >( do_lower_case: bool = True keep_accents: bool = False bos_token: str = '[CLS]' eos_token: str = '[SEP]' unk_token: str = '<unk>' sep_token: str = '[SEP]' pad_token: str = '<pad>' cls_token: str = '[CLS]' mask_token: str = '[MASK]' add_prefix_space: bool = True trim_offsets: bool = True vocab: typing.Optional[dict] = None vocab_file: typing.Optional[str] = None **kwargs )
Parameters
- do_lower_case (
bool, optional, defaults toTrue) — Whether or not to lowercase the input when tokenizing. - 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. - add_prefix_space (
bool, optional, defaults toTrue) — Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. - trim_offsets (
bool, optional, defaults toTrue) — Whether the post processing step should trim offsets to avoid including whitespaces. - vocab (
dict, optional) — Custom vocabulary dictionary. If not provided, vocabulary is loaded from vocab_file. - vocab_file (
str, optional) — SentencePiece file (generally has a .model extension) that contains the vocabulary necessary to instantiate a tokenizer.
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
get_special_tokens_mask
< source >( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None already_has_special_tokens: bool = False ) → A list of integers in the range [0, 1]
Parameters
- token_ids_0 — List of IDs for the (possibly already formatted) sequence.
- token_ids_1 — Unused when
already_has_special_tokens=True. Must be None in that case. - already_has_special_tokens — Whether the sequence is already formatted with special tokens.
Returns
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.
For fast tokenizers, data collators call this with already_has_special_tokens=True to build a mask over an
already-formatted sequence. In that case, we compute the mask by checking membership in all_special_ids.
AlbertTokenizerFast
class transformers.AlbertTokenizer
< source >( do_lower_case: bool = True keep_accents: bool = False bos_token: str = '[CLS]' eos_token: str = '[SEP]' unk_token: str = '<unk>' sep_token: str = '[SEP]' pad_token: str = '<pad>' cls_token: str = '[CLS]' mask_token: str = '[MASK]' add_prefix_space: bool = True trim_offsets: bool = True vocab: typing.Optional[dict] = None vocab_file: typing.Optional[str] = None **kwargs )
Parameters
- do_lower_case (
bool, optional, defaults toTrue) — Whether or not to lowercase the input when tokenizing. - 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. - add_prefix_space (
bool, optional, defaults toTrue) — Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. - trim_offsets (
bool, optional, defaults toTrue) — Whether the post processing step should trim offsets to avoid including whitespaces. - vocab (
dict, optional) — Custom vocabulary dictionary. If not provided, vocabulary is loaded from vocab_file. - vocab_file (
str, optional) — SentencePiece file (generally has a .model extension) that contains the vocabulary necessary to instantiate a tokenizer.
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
Albert 특화 출력
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 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]. - 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
Moduleinstance 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 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]. - 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
Moduleinstance 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 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]. - 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
Moduleinstance 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 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]. - 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
Moduleinstance 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 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]. - 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
Moduleinstance 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 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]. - 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
Moduleinstance 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 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]. - 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
Moduleinstance 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)
...