# BROS

## Overview

BROS モデルは、Teakgyu Hon、Donghyun Kim、Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park によって [BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents](https://huggingface.co/papers/2108.04539) で提案されました。 

BROS は *BERT Relying On Spatality* の略です。これは、一連のトークンとその境界ボックスを入力として受け取り、一連の隠れ状態を出力するエンコーダー専用の Transformer モデルです。 BROS は、絶対的な空間情報を使用する代わりに、相対的な空間情報をエンコードします。

BERT で使用されるトークンマスク言語モデリング目標 (TMLM) と新しいエリアマスク言語モデリング目標 (AMLM) の 2 つの目標で事前トレーニングされています。
TMLM では、トークンはランダムにマスクされ、モデルは空間情報と他のマスクされていないトークンを使用してマスクされたトークンを予測します。
AMLM は TMLM の 2D バージョンです。テキスト トークンをランダムにマスクし、TMLM と同じ情報で予測しますが、テキスト ブロック (領域) をマスクします。

`BrosForTokenClassification`には、BrosModel の上に単純な線形層があります。各トークンのラベルを予測します。
`BrosSpadeEEForTokenClassification`には、BrosModel の上に`initial_token_classifier`と`subsequent_token_classifier`があります。 `initial_token_classifier` は各エンティティの最初のトークンを予測するために使用され、`subsequent_token_classifier` はエンティティ内の次のトークンを予測するために使用されます。 `BrosSpadeELForTokenClassification`には BrosModel の上に`entity_linker`があります。 `entity_linker` は 2 つのエンティティ間の関係を予測するために使用されます。

`BrosForTokenClassification`と`BrosSpadeEEForTokenClassification`は基本的に同じジョブを実行します。ただし、`BrosForTokenClassification`は入力トークンが完全にシリアル化されていることを前提としています (トークンは 2D 空間に存在するため、これは非常に困難な作業です)。一方、`BrosSpadeEEForTokenClassification`は 1 つのトークンから次の接続トークンを予測するため、シリアル化エラーの処理をより柔軟に行うことができます。

`BrosSpadeELForTokenClassification` はエンティティ内のリンク タスクを実行します。これら 2 つのエンティティが何らかの関係を共有する場合、(あるエンティティの) 1 つのトークンから (別のエンティティの) 別のトークンへの関係を予測します。

BROS は、明示的な視覚機能に依存せずに、FUNSD、SROIE、CORD、SciTSR などの Key Information Extraction (KIE) ベンチマークで同等以上の結果を達成します。

論文の要約は次のとおりです。

*文書画像からの重要情報抽出 (KIE) には、2 次元 (2D) 空間におけるテキストの文脈的および空間的意味論を理解する必要があります。最近の研究の多くは、文書画像の視覚的特徴とテキストおよびそのレイアウトを組み合わせることに重点を置いた事前トレーニング済み言語モデルを開発することで、この課題を解決しようとしています。一方、このペーパーでは、テキストとレイアウトの効果的な組み合わせという基本に立ち返ってこの問題に取り組みます。具体的には、BROS (BERT Relying On Spatality) という名前の事前トレーニング済み言語モデルを提案します。この言語モデルは、2D 空間内のテキストの相対位置をエンコードし、エリア マスキング戦略を使用してラベルのないドキュメントから学習します。 2D 空間内のテキストを理解するためのこの最適化されたトレーニング スキームにより、BROS は、視覚的な特徴に依存することなく、4 つの KIE ベンチマーク (FUNSD、SROIE*、CORD、および SciTSR) で以前の方法と比較して同等以上のパフォーマンスを示しました。また、この論文では、KIE タスクにおける 2 つの現実世界の課題 ((1) 間違ったテキスト順序によるエラーの最小化、および (2) 少数の下流例からの効率的な学習) を明らかにし、以前の方法に対する BROS の優位性を実証します。*

このモデルは [jinho8345](https://huggingface.co/jinho8345) によって寄稿されました。元のコードは [ここ](https://github.com/clovaai/bros) にあります。

## Usage tips and examples

- [forward()](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosModel.forward) には、`input_ids` と `bbox` (バウンディング ボックス) が必要です。各境界ボックスは、(x0、y0、x1、y1) 形式 (左上隅、右下隅) である必要があります。境界ボックスの取得は外部 OCR システムに依存します。 「x」座標はドキュメント画像の幅で正規化する必要があり、「y」座標はドキュメント画像の高さで正規化する必要があります。

```python
def expand_and_normalize_bbox(bboxes, doc_width, doc_height):
    # here, bboxes are numpy array

    # Normalize bbox -> 0 ~ 1
    bboxes[:, [0, 2]] = bboxes[:, [0, 2]] / width
    bboxes[:, [1, 3]] = bboxes[:, [1, 3]] / height
```

- [`~transformers.BrosForTokenClassification.forward`、`~transformers.BrosSpadeEEForTokenClassification.forward`、`~transformers.BrosSpadeEEForTokenClassification.forward`] では、損失計算に `input_ids` と `bbox` だけでなく `box_first_token_mask` も必要です。これは、各ボックスの先頭以外のトークンを除外するためのマスクです。このマスクは、単語から `input_ids` を作成するときに境界ボックスの開始トークン インデックスを保存することで取得できます。次のコードで`box_first_token_mask`を作成できます。

```python
def make_box_first_token_mask(bboxes, words, tokenizer, max_seq_length=512):

    box_first_token_mask = np.zeros(max_seq_length, dtype=np.bool_)

    # encode(tokenize) each word from words (list[str])
    input_ids_list: list[list[int]] = [tokenizer.encode(e, add_special_tokens=False) for e in words]

    # get the length of each box
    tokens_length_list: list[int] = [len(l) for l in input_ids_list]

    box_end_token_indices = np.array(list(itertools.accumulate(tokens_length_list)))
    box_start_token_indices = box_end_token_indices - np.array(tokens_length_list)

    # filter out the indices that are out of max_seq_length
    box_end_token_indices = box_end_token_indices[box_end_token_indices < max_seq_length - 1]
    if len(box_start_token_indices) > len(box_end_token_indices):
        box_start_token_indices = box_start_token_indices[: len(box_end_token_indices)]

    # set box_start_token_indices to True
    box_first_token_mask[box_start_token_indices] = True

    return box_first_token_mask

```

## Resources

- デモ スクリプトは [こちら](https://github.com/clovaai/bros) にあります。

## BrosConfig[[transformers.BrosConfig]]

#### transformers.BrosConfig[[transformers.BrosConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/configuration_bros.py#L24)

This is the configuration class to store the configuration of a BrosModel. It is used to instantiate a Bros
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 [jinho8345/bros-base-uncased](https://huggingface.co/jinho8345/bros-base-uncased)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Examples:

```python
>>> from transformers import BrosConfig, BrosModel

>>> # Initializing a BROS jinho8345/bros-base-uncased style configuration
>>> configuration = BrosConfig()

>>> # Initializing a model from the jinho8345/bros-base-uncased style configuration
>>> model = BrosModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```

**Parameters:**

vocab_size (`int`, *optional*, defaults to `30522`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`.

hidden_size (`int`, *optional*, defaults to `768`) : Dimension of the hidden representations.

num_hidden_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer decoder.

num_attention_heads (`int`, *optional*, defaults to `12`) : Number of attention heads for each attention layer in the Transformer decoder.

intermediate_size (`int`, *optional*, defaults to `3072`) : Dimension of the MLP representations.

hidden_act (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc.

hidden_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

attention_probs_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout ratio for the attention probabilities.

max_position_embeddings (`int`, *optional*, defaults to `512`) : The maximum sequence length that this model might ever be used with.

type_vocab_size (`int`, *optional*, defaults to `2`) : The vocabulary size of the `token_type_ids`.

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.

pad_token_id (`int`, *optional*, defaults to `0`) : Token id used for padding in the vocabulary.

dim_bbox (`int`, *optional*, defaults to 8) : The dimension of the bounding box coordinates. (x0, y1, x1, y0, x1, y1, x0, y1)

bbox_scale (`float`, *optional*, defaults to 100.0) : The scale factor of the bounding box coordinates.

n_relations (`int`, *optional*, defaults to 1) : The number of relations for SpadeEE(entity extraction), SpadeEL(entity linking) head.

classifier_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout ratio for classifier.

is_decoder (`bool`, *optional*, defaults to `False`) : Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.

add_cross_attention (`bool`, *optional*, defaults to `False`) : Whether cross-attention layers should be added to the model.

## BrosProcessor[[transformers.BrosProcessor]]

#### transformers.BrosProcessor[[transformers.BrosProcessor]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/processing_bros.py#L38)

Constructs a BrosProcessor which wraps a tokenizer into a single processor.

[BrosProcessor](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosProcessor) offers all the functionalities of [BertTokenizer](/docs/transformers/v5.8.0/ja/model_doc/bert#transformers.BertTokenizer). See the
[~BertTokenizer](/docs/transformers/v5.8.0/ja/model_doc/bert#transformers.BertTokenizer) for more information.

__call__transformers.BrosProcessor.__call__https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/processing_utils.py#L631[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None"}, {"name": "text", "val": ": str | list[str] | list[list[str]] | None = None"}, {"name": "videos", "val": ": typing.Union[list['PIL.Image.Image'], numpy.ndarray, ForwardRef('torch.Tensor'), list[numpy.ndarray], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list[numpy.ndarray]], list[list['torch.Tensor']], transformers.video_utils.URL, list[transformers.video_utils.URL], list[list[transformers.video_utils.URL]], transformers.video_utils.Path, list[transformers.video_utils.Path], list[list[transformers.video_utils.Path]], NoneType] = None"}, {"name": "audio", "val": ": typing.Union[numpy.ndarray, ForwardRef('torch.Tensor'), collections.abc.Sequence[numpy.ndarray], collections.abc.Sequence['torch.Tensor'], NoneType] = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ProcessingKwargs]"}]- **images** (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `list[PIL.Image.Image]`, `list[np.ndarray]`, `list[torch.Tensor]`) --
  The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
  tensor. Both channels-first and channels-last formats are supported.
- **text** (`TextInput`, `PreTokenizedInput`, `list[TextInput]`, `list[PreTokenizedInput]`, *optional*) --
  The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
  (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
  `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
- **videos** (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`) --
  The video or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch
  tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported.
- **audio** (`np.ndarray`, `torch.Tensor`, `list[np.ndarray]`, `list[torch.Tensor]`) --
  The audio or batch of audio to be prepared. Each audio can be a NumPy array or PyTorch
  tensor.
- **return_tensors** (`str` or [TensorType](/docs/transformers/v5.8.0/ja/internal/file_utils#transformers.TensorType), *optional*) --
  If set, will return tensors of a particular framework. Acceptable values are:

  - `'pt'`: Return PyTorch `torch.Tensor` objects.
  - `'np'`: Return NumPy `np.ndarray` objects.0[BatchFeature](/docs/transformers/v5.8.0/ja/main_classes/feature_extractor#transformers.BatchFeature)A [BatchFeature](/docs/transformers/v5.8.0/ja/main_classes/feature_extractor#transformers.BatchFeature) object with processed inputs in a dict format.

Main method to prepare for model inputs. This method forwards the each modality argument to its own processor
along with `kwargs`. Please refer to the docstring of the each processor attributes for more information.

**Parameters:**

tokenizer (`BertTokenizer`) : The tokenizer is a required input.

**Returns:**

`[BatchFeature](/docs/transformers/v5.8.0/ja/main_classes/feature_extractor#transformers.BatchFeature)`

A [BatchFeature](/docs/transformers/v5.8.0/ja/main_classes/feature_extractor#transformers.BatchFeature) object with processed inputs in a dict format.

## BrosModel[[transformers.BrosModel]]

#### transformers.BrosModel[[transformers.BrosModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/modeling_bros.py#L500)

The bare Bros Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/ja/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.BrosModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/modeling_bros.py#L523[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "bbox", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "token_type_ids", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "encoder_hidden_states", "val": ": torch.Tensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.Tensor` of 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](/docs/transformers/v5.8.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **bbox** (`'torch.FloatTensor'` of shape '(batch_size, num_boxes, 4)') --
  Bounding box coordinates for each token in the input sequence. Each bounding box is a list of four values
  (x1, y1, x2, y2), where (x1, y1) is the top left corner, and (x2, y2) is the bottom right corner of the
  bounding box.
- **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

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

  [What are attention masks?](../glossary#attention-mask)
- **token_type_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.Tensor` of shape `(batch_size, 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.
- **encoder_hidden_states** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
  if the model is configured as a decoder.
- **encoder_attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
  the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.0[BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) 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 ([BrosConfig](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosConfig)) and inputs.
The [BrosModel](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosModel) 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.

- **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model.
- **pooler_output** (`torch.FloatTensor` of 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 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.
- **cross_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=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 of the decoder's cross-attention layer, after the attention softmax, used to compute the
  weighted average in the cross-attention heads.
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `Cache` instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
  `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values`
  input) to speed up sequential decoding.

Examples:

```python
>>> import torch
>>> from transformers import BrosProcessor, BrosModel

>>> processor = BrosProcessor.from_pretrained("jinho8345/bros-base-uncased")

>>> model = BrosModel.from_pretrained("jinho8345/bros-base-uncased")

>>> encoding = processor("Hello, my dog is cute", add_special_tokens=False, return_tensors="pt")
>>> bbox = torch.tensor([[[0, 0, 1, 1]]]).repeat(1, encoding["input_ids"].shape[-1], 1)
>>> encoding["bbox"] = bbox

>>> outputs = model(**encoding)
>>> last_hidden_states = outputs.last_hidden_state
```

**Parameters:**

config ([BrosModel](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosModel)) : 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/v5.8.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

add_pooling_layer (`bool`, *optional*, defaults to `True`) : Whether to add a pooling layer

**Returns:**

`[BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or `tuple(torch.FloatTensor)``

A [BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) 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 ([BrosConfig](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosConfig)) and inputs.

## BrosForTokenClassification[[transformers.BrosForTokenClassification]]

#### transformers.BrosForTokenClassification[[transformers.BrosForTokenClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/modeling_bros.py#L621)

The Bros 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](/docs/transformers/v5.8.0/ja/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.BrosForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/modeling_bros.py#L637[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "bbox", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "bbox_first_token_mask", "val": ": torch.Tensor | None = None"}, {"name": "token_type_ids", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.Tensor` of 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](/docs/transformers/v5.8.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **bbox** (`'torch.FloatTensor'` of shape '(batch_size, num_boxes, 4)') --
  Bounding box coordinates for each token in the input sequence. Each bounding box is a list of four values
  (x1, y1, x2, y2), where (x1, y1) is the top left corner, and (x2, y2) is the bottom right corner of the
  bounding box.
- **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

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

  [What are attention masks?](../glossary#attention-mask)
- **bbox_first_token_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to indicate the first token of each bounding box. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **token_type_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.Tensor` of shape `(batch_size, 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.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
  config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
  (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.0[TokenClassifierOutput](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`A [TokenClassifierOutput](/docs/transformers/v5.8.0/ja/main_classes/output#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 ([BrosConfig](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosConfig)) and inputs.
The [BrosForTokenClassification](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosForTokenClassification) 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.

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Classification loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.num_labels)`) -- Classification scores (before SoftMax).
- **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned 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.

Examples:

```python
>>> import torch
>>> from transformers import BrosProcessor, BrosForTokenClassification

>>> processor = BrosProcessor.from_pretrained("jinho8345/bros-base-uncased")

>>> model = BrosForTokenClassification.from_pretrained("jinho8345/bros-base-uncased")

>>> encoding = processor("Hello, my dog is cute", add_special_tokens=False, return_tensors="pt")
>>> bbox = torch.tensor([[[0, 0, 1, 1]]]).repeat(1, encoding["input_ids"].shape[-1], 1)
>>> encoding["bbox"] = bbox

>>> outputs = model(**encoding)
```

**Parameters:**

config ([BrosForTokenClassification](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosForTokenClassification)) : 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/v5.8.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[TokenClassifierOutput](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)``

A [TokenClassifierOutput](/docs/transformers/v5.8.0/ja/main_classes/output#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 ([BrosConfig](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosConfig)) and inputs.

## BrosSpadeEEForTokenClassification[[transformers.BrosSpadeEEForTokenClassification]]

#### transformers.BrosSpadeEEForTokenClassification[[transformers.BrosSpadeEEForTokenClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/modeling_bros.py#L721)

Bros Model with a token classification head on top (initial_token_layers and subsequent_token_layer on top of the
hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks. The initial_token_classifier is used to
predict the first token of each entity, and the subsequent_token_classifier is used to predict the subsequent
tokens within an entity. Compared to BrosForTokenClassification, this model is more robust to serialization errors
since it predicts next token from one token.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/ja/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.BrosSpadeEEForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/modeling_bros.py#L749[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "bbox", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "bbox_first_token_mask", "val": ": torch.Tensor | None = None"}, {"name": "token_type_ids", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "initial_token_labels", "val": ": torch.Tensor | None = None"}, {"name": "subsequent_token_labels", "val": ": torch.Tensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.Tensor` of 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](/docs/transformers/v5.8.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **bbox** (`'torch.FloatTensor'` of shape '(batch_size, num_boxes, 4)') --
  Bounding box coordinates for each token in the input sequence. Each bounding box is a list of four values
  (x1, y1, x2, y2), where (x1, y1) is the top left corner, and (x2, y2) is the bottom right corner of the
  bounding box.
- **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

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

  [What are attention masks?](../glossary#attention-mask)
- **bbox_first_token_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to indicate the first token of each bounding box. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **token_type_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.Tensor` of shape `(batch_size, 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.
- **initial_token_labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for the initial token classification.
- **subsequent_token_labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for the subsequent token classification.0`BrosSpadeOutput` or `tuple(torch.FloatTensor)`A `BrosSpadeOutput` 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 ([BrosConfig](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosConfig)) and inputs.
The [BrosSpadeEEForTokenClassification](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosSpadeEEForTokenClassification) 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.

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Classification loss.
- **initial_token_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.num_labels)`) -- Classification scores for entity initial tokens (before SoftMax).
- **subsequent_token_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, sequence_length+1)`) -- Classification scores for entity sequence tokens (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.

Examples:

```python
>>> import torch
>>> from transformers import BrosProcessor, BrosSpadeEEForTokenClassification

>>> processor = BrosProcessor.from_pretrained("jinho8345/bros-base-uncased")

>>> model = BrosSpadeEEForTokenClassification.from_pretrained("jinho8345/bros-base-uncased")

>>> encoding = processor("Hello, my dog is cute", add_special_tokens=False, return_tensors="pt")
>>> bbox = torch.tensor([[[0, 0, 1, 1]]]).repeat(1, encoding["input_ids"].shape[-1], 1)
>>> encoding["bbox"] = bbox

>>> outputs = model(**encoding)
```

**Parameters:**

config ([BrosSpadeEEForTokenClassification](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosSpadeEEForTokenClassification)) : 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/v5.8.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

``BrosSpadeOutput` or `tuple(torch.FloatTensor)``

A `BrosSpadeOutput` 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 ([BrosConfig](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosConfig)) and inputs.

## BrosSpadeELForTokenClassification[[transformers.BrosSpadeELForTokenClassification]]

#### transformers.BrosSpadeELForTokenClassification[[transformers.BrosSpadeELForTokenClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/modeling_bros.py#L862)

Bros Model with a token classification head on top (a entity_linker layer on top of the hidden-states output) e.g.
for Entity-Linking. The entity_linker is used to predict intra-entity links (one entity to another entity).

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/ja/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.BrosSpadeELForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bros/modeling_bros.py#L879[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "bbox", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "bbox_first_token_mask", "val": ": torch.Tensor | None = None"}, {"name": "token_type_ids", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.Tensor` of 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](/docs/transformers/v5.8.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **bbox** (`'torch.FloatTensor'` of shape '(batch_size, num_boxes, 4)') --
  Bounding box coordinates for each token in the input sequence. Each bounding box is a list of four values
  (x1, y1, x2, y2), where (x1, y1) is the top left corner, and (x2, y2) is the bottom right corner of the
  bounding box.
- **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

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

  [What are attention masks?](../glossary#attention-mask)
- **bbox_first_token_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to indicate the first token of each bounding box. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **token_type_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.Tensor` of shape `(batch_size, 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.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
  config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
  (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.0[TokenClassifierOutput](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`A [TokenClassifierOutput](/docs/transformers/v5.8.0/ja/main_classes/output#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 ([BrosConfig](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosConfig)) and inputs.
The [BrosSpadeELForTokenClassification](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosSpadeELForTokenClassification) 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.

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Classification loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.num_labels)`) -- Classification scores (before SoftMax).
- **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned 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.

Examples:

```python
>>> import torch
>>> from transformers import BrosProcessor, BrosSpadeELForTokenClassification

>>> processor = BrosProcessor.from_pretrained("jinho8345/bros-base-uncased")

>>> model = BrosSpadeELForTokenClassification.from_pretrained("jinho8345/bros-base-uncased")

>>> encoding = processor("Hello, my dog is cute", add_special_tokens=False, return_tensors="pt")
>>> bbox = torch.tensor([[[0, 0, 1, 1]]]).repeat(1, encoding["input_ids"].shape[-1], 1)
>>> encoding["bbox"] = bbox

>>> outputs = model(**encoding)
```

**Parameters:**

config ([BrosSpadeELForTokenClassification](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosSpadeELForTokenClassification)) : 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/v5.8.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[TokenClassifierOutput](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)``

A [TokenClassifierOutput](/docs/transformers/v5.8.0/ja/main_classes/output#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 ([BrosConfig](/docs/transformers/v5.8.0/ja/model_doc/bros#transformers.BrosConfig)) and inputs.