# ALBERT[[albert]]

[ALBERT](https://huggingface.co/papers/1909.11942)는 [BERT](./bert)의 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](https://huggingface.co/albert) 조직에서 확인하실 수 있습니다.

> [!TIP]
> 오른쪽 사이드바의 ALBERT 모델을 클릭하시면 다양한 언어 작업에 ALBERT를 적용하는 예시를 더 확인하실 수 있습니다.

아래 예시는 [Pipeline](/docs/transformers/v4.57.1/ko/main_classes/pipelines#transformers.Pipeline), [AutoModel](/docs/transformers/v4.57.1/ko/model_doc/auto#transformers.AutoModel) 그리고 커맨드라인에서 `[MASK]` 토큰을 예측하는 방법을 보여줍니다.

```py
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)
```

```py
import torch
from transformers import AutoModelForMaskedLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("albert/albert-base-v2")
model = AutoModelForMaskedLM.from_pretrained(
    "albert/albert-base-v2",
    dtype=torch.float16,
    attn_implementation="sdpa",
    device_map="auto"
)

prompt = "식물은 [MASK]이라고 알려진 과정을 통해 에너지를 생성합니다."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)
    mask_token_index = torch.where(inputs["input_ids"] == tokenizer.mask_token_id)[1]
    predictions = outputs.logits[0, mask_token_index]

top_k = torch.topk(predictions, k=5).indices.tolist()
for token_id in top_k[0]:
    print(f"예측: {tokenizer.decode([token_id])}")
```

```bash
echo -e "Plants create [MASK] through a process known as photosynthesis." | transformers run --task fill-mask --model albert-base-v2 --device 0
```

## 참고 사항[[notes]]

- BERT는 절대 위치 임베딩을 사용하므로, 오른쪽에 입력이 패딩돼야 합니다.
- 임베딩 크기 `E`는 히든 크기 `H`와 다릅니다. 임베딩은 문맥에 독립적(각 토큰마다 하나의 임베딩 벡터)이고, 은닉 상태는 문맥에 의존적(토큰 시퀀스마다 하나의 은닉 상태)입니다. 임베딩 행렬은 `V x E`(V: 어휘 크기)이므로, 일반적으로 `H >> E`가 더 논리적입니다. `E 

- `AlbertForSequenceClassification`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/pytorch/text-classification)에서 지원됩니다.

- `TFAlbertForSequenceClassification`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/text-classification)에서 지원됩니다.

- `FlaxAlbertForSequenceClassification`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/flax/text-classification)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/text_classification_flax.ipynb)에서 지원됩니다.
- [텍스트 분류 작업 가이드](../tasks/sequence_classification)에서 모델 사용법을 확인하세요.

- `AlbertForTokenClassification`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/pytorch/token-classification)에서 지원됩니다.

- `TFAlbertForTokenClassification`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/token-classification)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/token_classification-tf.ipynb)에서 지원됩니다.

- `FlaxAlbertForTokenClassification`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/flax/token-classification)에서 지원됩니다.
- 🤗 Hugging Face의 [토큰 분류](https://huggingface.co/course/chapter7/2?fw=pt) 강좌
- [토큰 분류 작업 가이드](../tasks/token_classification)에서 모델 사용법을 확인하세요.

- `AlbertForMaskedLM`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/pytorch/language-modeling#robertabertdistilbert-and-masked-language-modeling)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling.ipynb)에서 지원됩니다.
- `TFAlbertForMaskedLM`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/language-modeling#run_mlmpy)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling-tf.ipynb)에서 지원됩니다.
- `FlaxAlbertForMaskedLM`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/flax/language-modeling#masked-language-modeling)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/masked_language_modeling_flax.ipynb)에서 지원됩니다.
- 🤗 Hugging Face의 [마스킹 언어 모델링](https://huggingface.co/course/chapter7/3?fw=pt) 강좌
- [마스킹 언어 모델링 작업 가이드](../tasks/masked_language_modeling)에서 모델 사용법을 확인하세요.

- `AlbertForQuestionAnswering`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/pytorch/question-answering)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/question_answering.ipynb)에서 지원됩니다.
- `TFAlbertForQuestionAnswering`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/question-answering)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/question_answering-tf.ipynb)에서 지원됩니다.
- `FlaxAlbertForQuestionAnswering`은 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/flax/question-answering)에서 지원됩니다.
- [질의응답](https://huggingface.co/course/chapter7/7?fw=pt) 🤗 Hugging Face 강좌의 챕터.
- [질의응답 작업 가이드](../tasks/question_answering)에서 모델 사용법을 확인하세요.

**다중 선택(Multiple choice)**

- [AlbertForMultipleChoice](/docs/transformers/v4.57.1/ko/model_doc/albert#transformers.AlbertForMultipleChoice)는 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/pytorch/multiple-choice)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/multiple_choice.ipynb)에서 지원됩니다.
- `TFAlbertForMultipleChoice`는 이 [예제 스크립트](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/multiple-choice)와 [노트북](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/multiple_choice-tf.ipynb)에서 지원됩니다.

- [다중 선택 작업 가이드](../tasks/multiple_choice)에서 모델 사용법을 확인하세요.

## AlbertConfig[[albertconfig]][[transformers.AlbertConfig]]

#### transformers.AlbertConfig[[transformers.AlbertConfig]]

[Source](https://github.com/huggingface/transformers/blob/v4.57.1/src/transformers/models/albert/configuration_albert.py#L25)

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](https://huggingface.co/albert/albert-xxlarge-v2) architecture.

Configuration objects inherit from [PretrainedConfig](/docs/transformers/v4.57.1/ko/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the
documentation from [PretrainedConfig](/docs/transformers/v4.57.1/ko/main_classes/configuration#transformers.PretrainedConfig) for more information.

Examples:

```python
>>> 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.config
```

**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 the `inputs_ids` passed when calling `AlbertModel` or `TFAlbertModel`.

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 (`str` or `Callable`, *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 the `token_type_ids` passed when calling `AlbertModel` or `TFAlbertModel`.

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.)](https://huggingface.co/papers/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://huggingface.co/papers/2009.13658).

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.

## AlbertTokenizer[[alberttokenizer]]

[[autodoc]] AlbertTokenizer - build_inputs_with_special_tokens - get_special_tokens_mask - create_token_type_ids_from_sequences - save_vocabulary

## AlbertTokenizerFast[[alberttokenizerfast]][[transformers.AlbertTokenizerFast]]

#### transformers.AlbertTokenizerFast[[transformers.AlbertTokenizerFast]]

[Source](https://github.com/huggingface/transformers/blob/v4.57.1/src/transformers/models/albert/tokenization_albert_fast.py#L38)

Construct a "fast" ALBERT tokenizer (backed by HuggingFace's *tokenizers* library). Based on
[Unigram](https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=unigram#models). This
tokenizer inherits from [PreTrainedTokenizerFast](/docs/transformers/v4.57.1/ko/main_classes/tokenizer#transformers.PreTrainedTokenizerFast) which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods

build_inputs_with_special_tokenstransformers.AlbertTokenizerFast.build_inputs_with_special_tokenshttps://github.com/huggingface/transformers/blob/v4.57.1/src/transformers/models/albert/tokenization_albert_fast.py#L133[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}]- **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.0`List[int]`list of [input IDs](../glossary#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]`

**Parameters:**

vocab_file (`str`) : [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that contains the vocabulary necessary to instantiate a tokenizer.

do_lower_case (`bool`, *optional*, defaults to `True`) : Whether or not to lowercase the input when tokenizing.

remove_space (`bool`, *optional*, defaults to `True`) : Whether or not to strip the text when tokenizing (removing excess spaces before and after the string).

keep_accents (`bool`, *optional*, defaults to `False`) : 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 the `sep_token`.

unk_token (`str`, *optional*, defaults to `""`) : 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 `""`) : 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.

**Returns:**

``List[int]``

list of [input IDs](../glossary#input-ids) with the appropriate special tokens.

## Albert 특화 출력[[albert-specific-outputs]][[transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput]]

#### transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput[[transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput]]

[Source](https://github.com/huggingface/transformers/blob/v4.57.1/src/transformers/models/albert/modeling_albert.py#L578)

Output type of `AlbertForPreTraining`.

**Parameters:**

loss (`*optional*`, returned when `labels` is provided, `torch.FloatTensor` of shape `(1,)`) : Total loss as the sum of the masked language modeling loss and the next sequence prediction (classification) loss.

prediction_logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) : Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

sop_logits (`torch.FloatTensor` of 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 when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) : Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

#### transformers.models.albert.modeling_tf_albert.TFAlbertForPreTrainingOutput[[transformers.models.albert.modeling_tf_albert.TFAlbertForPreTrainingOutput]]

[Source](https://github.com/huggingface/transformers/blob/v4.57.1/src/transformers/models/albert/modeling_tf_albert.py#L728)

Output type of `TFAlbertForPreTraining`.

**Parameters:**

prediction_logits (`tf.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`) : Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

sop_logits (`tf.Tensor` of shape `(batch_size, 2)`) : Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax).

hidden_states (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) : Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.  Hidden-states of the model at the output of each layer plus the initial embedding outputs.

attentions (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) : Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

## AlbertModel[[albertmodel]]

[[autodoc]] AlbertModel - forward

## AlbertForPreTraining[[albertforpretraining]]

[[autodoc]] AlbertForPreTraining - forward

## AlbertForMaskedLM[[albertformaskedlm]]

[[autodoc]] AlbertForMaskedLM - forward

## AlbertForSequenceClassification[[albertforsequenceclassification]]

[[autodoc]] AlbertForSequenceClassification - forward

## AlbertForMultipleChoice[[albertformultiplechoice]][[transformers.AlbertForMultipleChoice]]

#### transformers.AlbertForMultipleChoice[[transformers.AlbertForMultipleChoice]]

[Source](https://github.com/huggingface/transformers/blob/v4.57.1/src/transformers/models/albert/modeling_albert.py#L1237)

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](/docs/transformers/v4.57.1/ko/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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.

forwardtransformers.AlbertForMultipleChoice.forwardhttps://github.com/huggingface/transformers/blob/v4.57.1/src/transformers/models/albert/modeling_albert.py#L1248[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "token_type_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "position_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "head_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`) --
  Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v4.57.1/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.__call__()](/docs/transformers/v4.57.1/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) and
  [PreTrainedTokenizer.encode()](/docs/transformers/v4.57.1/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.

  [What are attention masks?](../glossary#attention-mask)
- **token_type_ids** (`torch.LongTensor` of 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.

  [What are token type IDs?](../glossary#token-type-ids)
- **position_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`, *optional*) --
  Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
  config.max_position_embeddings - 1]`.

  [What are position IDs?](../glossary#position-ids)
- **head_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) --
  Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:

  - 1 indicates the head is **not masked**,
  - 0 indicates the head is **masked**.
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, num_choices, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
  num_choices-1]` where *num_choices* is the size of the second dimension of the input tensors. (see
  *input_ids* above)
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v4.57.1/ko/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput](/docs/transformers/v4.57.1/ko/model_doc/albert#transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput) or `tuple(torch.FloatTensor)`A [transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput](/docs/transformers/v4.57.1/ko/model_doc/albert#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](/docs/transformers/v4.57.1/ko/model_doc/albert#transformers.AlbertConfig)) and inputs.

- **loss** (`*optional*`, returned when `labels` is provided, `torch.FloatTensor` of shape `(1,)`) -- Total loss as the sum of the masked language modeling loss and the next sequence prediction
  (classification) loss.
- **prediction_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
- **sop_logits** (`torch.FloatTensor` of 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 when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
  heads.
The [AlbertForMultipleChoice](/docs/transformers/v4.57.1/ko/model_doc/albert#transformers.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:

```python
>>> 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.logits
```

**Parameters:**

config ([AlbertConfig](/docs/transformers/v4.57.1/ko/model_doc/albert#transformers.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()](/docs/transformers/v4.57.1/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput](/docs/transformers/v4.57.1/ko/model_doc/albert#transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput) or `tuple(torch.FloatTensor)``

A [transformers.models.albert.modeling_albert.AlbertForPreTrainingOutput](/docs/transformers/v4.57.1/ko/model_doc/albert#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](/docs/transformers/v4.57.1/ko/model_doc/albert#transformers.AlbertConfig)) and inputs.

- **loss** (`*optional*`, returned when `labels` is provided, `torch.FloatTensor` of shape `(1,)`) -- Total loss as the sum of the masked language modeling loss and the next sequence prediction
  (classification) loss.
- **prediction_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
- **sop_logits** (`torch.FloatTensor` of 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 when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.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 when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
  heads.

## AlbertForTokenClassification[[albertfortokenclassification]]

[[autodoc]] AlbertForTokenClassification - forward

## AlbertForQuestionAnswering[[albertforquestionanswering]]

[[autodoc]] AlbertForQuestionAnswering - forward

## TFAlbertModel[[tfalbertmodel]]

[[autodoc]] TFAlbertModel - call

## TFAlbertForPreTraining[[tfalbertforpretraining]]

[[autodoc]] TFAlbertForPreTraining - call

## TFAlbertForMaskedLM[[tfalbertformaskedlm]]

[[autodoc]] TFAlbertForMaskedLM - call

## TFAlbertForSequenceClassification[[tfalbertforsequenceclassification]]

[[autodoc]] TFAlbertForSequenceClassification - call

## TFAlbertForMultipleChoice[[tfalbertformultiplechoice]]

[[autodoc]] TFAlbertForMultipleChoice - call

## TFAlbertForTokenClassification[[tfalbertfortokenclassification]]

[[autodoc]] TFAlbertForTokenClassification - call

## TFAlbertForQuestionAnswering[[tfalbertforquestionanswering]]

[[autodoc]] TFAlbertForQuestionAnswering - call

## FlaxAlbertModel[[flaxalbertmodel]]

[[autodoc]] FlaxAlbertModel - **call**

## FlaxAlbertForPreTraining[[flaxalbertforpretraining]]

[[autodoc]] FlaxAlbertForPreTraining - **call**

## FlaxAlbertForMaskedLM[[flaxalbertformaskedlm]]

[[autodoc]] FlaxAlbertForMaskedLM - **call**

## FlaxAlbertForSequenceClassification[[flaxalbertforsequenceclassification]]

[[autodoc]] FlaxAlbertForSequenceClassification - **call**

## FlaxAlbertForMultipleChoice[[flaxalbertformultiplechoice]]

[[autodoc]] FlaxAlbertForMultipleChoice - **call**

## FlaxAlbertForTokenClassification[[flaxalbertfortokenclassification]]

[[autodoc]] FlaxAlbertForTokenClassification - **call**

## FlaxAlbertForQuestionAnswering[[flaxalbertforquestionanswering]]

[[autodoc]] FlaxAlbertForQuestionAnswering - **call**