# BART **免責事項:** 何か奇妙なものを見つけた場合は、[Github 問題](https://github.com/huggingface/transformers/issues/new?assignees=&labels=&template=bug-report.md&title) を提出し、割り当ててください。 @patrickvonplaten ## Overview Bart モデルは、[BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation、 翻訳と理解](https://huggingface.co/papers/1910.13461) Mike Lewis、Yinhan Liu、Naman Goyal、Marjan 著 ガズビニネジャド、アブデルラフマン・モハメド、オメル・レヴィ、ベス・ストヤノフ、ルーク・ゼトルモイヤー、2019年10月29日。 要約によると、 - Bart は、双方向エンコーダ (BERT など) を備えた標準の seq2seq/機械翻訳アーキテクチャを使用します。 左から右へのデコーダ (GPT など)。 - 事前トレーニング タスクには、元の文の順序をランダムにシャッフルし、新しい埋め込みスキームが含まれます。 ここで、テキストの範囲は単一のマスク トークンに置き換えられます。 - BART は、テキスト生成用に微調整した場合に特に効果的ですが、理解タスクにも適しています。それ RoBERTa のパフォーマンスを GLUE および SQuAD の同等のトレーニング リソースと同等にし、新たな成果を達成します。 さまざまな抽象的な対話、質問応答、要約タスクに関する最先端の結果が得られ、成果が得られます。 ルージュは最大6枚まで。 チップ： - BART は絶対位置埋め込みを備えたモデルであるため、通常は入力を右側にパディングすることをお勧めします。 左。 - エンコーダーとデコーダーを備えたシーケンスツーシーケンス モデル。エンコーダには破損したバージョンのトークンが供給され、デコーダには元のトークンが供給されます（ただし、通常のトランスフォーマー デコーダと同様に、将来のワードを隠すためのマスクがあります）。次の変換の構成は、エンコーダーの事前トレーニング タスクに適用されます。 * ランダムなトークンをマスクします (BERT と同様) * ランダムなトークンを削除します * k 個のトークンのスパンを 1 つのマスク トークンでマスクします (0 トークンのスパンはマスク トークンの挿入です) * 文を並べ替えます * ドキュメントを回転して特定のトークンから開始するようにします このモデルは [sshleifer](https://huggingface.co/sshleifer) によって提供されました。著者のコードは [ここ](https://github.com/pytorch/fairseq/tree/master/examples/bart) にあります。 ### Examples - シーケンス間タスク用の BART およびその他のモデルを微調整するための例とスクリプトは、次の場所にあります。 [examples/pytorch/summarization/](https://github.com/huggingface/transformers/tree/main/examples/pytorch/summarization/README.md)。 - Hugging Face `datasets` を使用して [BartForConditionalGeneration](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForConditionalGeneration) をトレーニングする方法の例 オブジェクトは、この [フォーラム ディスカッション](https://discuss.huggingface.co/t/train-bart-for-conditional-generation-e-g-summarization/1904) で見つけることができます。 - [抽出されたチェックポイント](https://huggingface.co/models?search=distilbart) は、この [論文](https://huggingface.co/papers/2010.13002) で説明されています。 ## Implementation Notes - Bart はシーケンスの分類に `token_type_ids` を使用しません。 [BartTokenizer](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.RobertaTokenizer) を使用するか、 [encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) を使用して適切に分割します。 - [BartModel](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartModel) のフォワードパスは、渡されなかった場合、`decoder_input_ids` を作成します。 これは、他のモデリング API とは異なります。この機能の一般的な使用例は、マスクの塗りつぶしです。 - モデルの予測は、次の場合に元の実装と同一になるように意図されています。 `forced_bos_token_id=0`。ただし、これは、渡す文字列が次の場合にのみ機能します。 `fairseq.encode` はスペースで始まります。 - [generate()](/docs/transformers/v5.5.3/ja/main_classes/text_generation#transformers.GenerationMixin.generate) は、次のような条件付き生成タスクに使用する必要があります。 要約については、その docstring の例を参照してください。 - *facebook/bart-large-cnn* 重みをロードするモデルには `mask_token_id` がないか、実行できません。 マスクを埋めるタスク。 ## Mask Filling `facebook/bart-base` および `facebook/bart-large` チェックポイントを使用して、マルチトークン マスクを埋めることができます。 ```python from transformers import BartForConditionalGeneration, BartTokenizer model = BartForConditionalGeneration.from_pretrained("facebook/bart-large", forced_bos_token_id=0) tok = BartTokenizer.from_pretrained("facebook/bart-large") example_english_phrase = "UN Chief Says There Is No in Syria" batch = tok(example_english_phrase, return_tensors="pt") generated_ids = model.generate(batch["input_ids"]) assert tok.batch_decode(generated_ids, skip_special_tokens=True) == [ "UN Chief Says There Is No Plan to Stop Chemical Weapons in Syria" ] ``` ## Resources BART を始めるのに役立つ公式 Hugging Face およびコミュニティ (🌎 で示されている) リソースのリスト。ここに含めるリソースの送信に興味がある場合は、お気軽にプル リクエストを開いてください。審査させていただきます。リソースは、既存のリソースを複製するのではなく、何か新しいものを示すことが理想的です。 - に関するブログ投稿 [分散トレーニング: 🤗 Transformers と Amazon SageMaker を使用した要約のための BART/T5 のトレーニング](https://huggingface.co/blog/sagemaker-distributed-training-seq2seq)。 - 方法に関するノートブック [blurr を使用して fastai で要約するために BART を微調整する](https://colab.research.google.com/github/ohmeow/ohmeow_website/blob/master/posts/2021-05-25-mbart-sequence-classification-with-blurr.ipynb). 🌎 🌎 - 方法に関するノートブック [トレーナー クラスを使用して 2 つの言語で要約するために BART を微調整する](https://colab.research.google.com/github/elsanns/xai-nlp-notebooks/blob/master/fine_tune_bart_summarization_two_langs.ipynb)。 🌎 - [BartForConditionalGeneration](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForConditionalGeneration) は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/pytorch/summarization) および [ノートブック](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/summarization.ipynb)。 - `TFBartForConditionalGeneration` は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/summarization) および [ノートブック](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/summarization-tf.ipynb)。 - `FlaxBartForConditionalGeneration` は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/flax/summarization) でサポートされています。 - [要約](https://huggingface.co/course/chapter7/5?fw=pt#summarization) 🤗 ハグフェイスコースの章。 - [要約タスクガイド](../tasks/summarization) - [BartForConditionalGeneration](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForConditionalGeneration) は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/pytorch/language-modeling#robertabertdistilbert-and-masked-language-modeling) でサポートされており、 [ノートブック](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling.ipynb)。 - `TFBartForConditionalGeneration` は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/language-modeling#run_mlmpy) および [ノートブック](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling-tf.ipynb)。 - `FlaxBartForConditionalGeneration` は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/flax/language-modeling#masked-language-modeling) および [ノートブック]( https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/masked_language_modeling_flax.ipynb)。 - [マスクされた言語モデリング](https://huggingface.co/course/chapter7/3?fw=pt) 🤗 顔ハグ コースの章。 - [マスクされた言語モデリング タスク ガイド](../tasks/masked_lang_modeling) - [ヒンディー語から英語への翻訳に Seq2SeqTrainer を使用して mBART を微調整する方法に関するノート](https://colab.research.google.com/github/vasudevgupta7/huggingface-tutorials/blob/main/translation_training.ipynb)。 🌎 - [BartForConditionalGeneration](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForConditionalGeneration) は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/pytorch/translation) および [ノートブック](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/translation.ipynb)。 - `TFBartForConditionalGeneration` は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/translation) および [ノートブック](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/translation-tf.ipynb)。 - [翻訳タスクガイド](../tasks/translation) 以下も参照してください。 - [テキスト分類タスクガイド(英語版)](../../en/tasks/sequence_classification) - [質問回答タスク ガイド](../tasks/question_answering) - [因果言語モデリング タスク ガイド](../tasks/language_modeling) - [抽出されたチェックポイント](https://huggingface.co/models?search=distilbart) は、この [論文](https://huggingface.co/papers/2010.13002) で説明されています。 ## BartConfig[[transformers.BartConfig]] #### transformers.BartConfig[[transformers.BartConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/configuration_bart.py#L24) This is the configuration class to store the configuration of a BartModel. It is used to instantiate a Bart 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 [facebook/bart-large](https://huggingface.co/facebook/bart-large) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.5.3/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.5.3/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import BartConfig, BartModel >>> # Initializing a BART facebook/bart-large style configuration >>> configuration = BartConfig() >>> # Initializing a model (with random weights) from the facebook/bart-large style configuration >>> model = BartModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** is_encoder_decoder (`bool`, *optional*, defaults to `True`) : Whether the model is used as an encoder/decoder or not. vocab_size (`int`, *optional*, defaults to `50265`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`. max_position_embeddings (`int`, *optional*, defaults to `1024`) : The maximum sequence length that this model might ever be used with. encoder_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer encoder. Will use the same value as `num_layers` if not set. encoder_ffn_dim (`int`, *optional*, defaults to `4096`) : Dimensionality of the "intermediate" (often named feed-forward) layer in encoder. encoder_attention_heads (`int`, *optional*, defaults to `16`) : Number of attention heads for each attention layer in the Transformer encoder. decoder_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set. decoder_ffn_dim (`int`, *optional*, defaults to `4096`) : Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. decoder_attention_heads (`int`, *optional*, defaults to `16`) : Number of attention heads for each attention layer in the Transformer decoder. encoder_layerdrop (`float`, *optional*, defaults to `0.0`) : The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. decoder_layerdrop (`float`, *optional*, defaults to `0.0`) : The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. activation_function (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. d_model (`int`, *optional*, defaults to `1024`) : Size of the encoder layers and the pooler layer. dropout (`Union[float, int]`, *optional*, defaults to `0.1`) : The ratio for all dropout layers. attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. activation_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for activations inside the fully connected layer. init_std (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. classifier_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for classifier. scale_embedding (`bool`, *optional*, defaults to `False`) : Whether to scale embeddings by dividing by sqrt(d_model). use_cache (`bool`, *optional*, defaults to `True`) : Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True` or when the model is a decoder-only generative model. pad_token_id (`int`, *optional*, defaults to `1`) : Token id used for padding in the vocabulary. bos_token_id (`int`, *optional*, defaults to `0`) : Token id used for beginning-of-stream in the vocabulary. eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `2`) : Token id used for end-of-stream in the vocabulary. decoder_start_token_id (`int`, *optional*, defaults to `2`) : If an encoder-decoder model starts decoding with a different token than `bos`, the id of that token. forced_eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `2`) : The id of the token to force as the last generated token when `max_length` is reached. Usually set to `eos_token_id`. 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. tie_word_embeddings (`bool`, *optional*, defaults to `True`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. ## BartTokenizer[[transformers.RobertaTokenizer]] #### transformers.RobertaTokenizer[[transformers.RobertaTokenizer]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/roberta/tokenization_roberta.py#L28) Construct a RoBERTa tokenizer (backed by HuggingFace's tokenizers library). Based on Byte-Pair-Encoding. This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will be encoded differently whether it is at the beginning of the sentence (without space) or not: ```python >>> from transformers import RobertaTokenizer >>> tokenizer = RobertaTokenizer.from_pretrained("FacebookAI/roberta-base") >>> tokenizer("Hello world")["input_ids"] [0, 31414, 232, 2] >>> tokenizer(" Hello world")["input_ids"] [0, 20920, 232, 2] ``` You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer or when you call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance. When used with `is_split_into_words=True`, this tokenizer needs to be instantiated with `add_prefix_space=True`. This tokenizer inherits from [TokenizersBackend](/docs/transformers/v5.5.3/ja/main_classes/tokenizer#transformers.TokenizersBackend) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. **Parameters:** vocab (`str`, `dict` or `list`, *optional*) : Custom vocabulary dictionary. If not provided, vocabulary is loaded from vocab_file. merges (`str` or `list`, *optional*) : Custom merges list. If not provided, merges are loaded from merges_file. errors (`str`, *optional*, defaults to `"replace"`) : Paradigm to follow when decoding bytes to UTF-8. See [bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information. bos_token (`str`, *optional*, defaults to `""`) : 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 `""`) : The end of sequence token. When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the `sep_token`. sep_token (`str`, *optional*, defaults to `""`) : 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. cls_token (`str`, *optional*, defaults to `""`) : 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. 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. pad_token (`str`, *optional*, defaults to `""`) : The token used for padding, for example when batching sequences of different lengths. mask_token (`str`, *optional*, defaults to `""`) : 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 to `False`) : Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (RoBERTa tokenizer detect beginning of words by the preceding space). trim_offsets (`bool`, *optional*, defaults to `True`) : Whether the post processing step should trim offsets to avoid including whitespaces. ## BartTokenizerFast[[transformers.RobertaTokenizer]] #### transformers.RobertaTokenizer[[transformers.RobertaTokenizer]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/roberta/tokenization_roberta.py#L28) Construct a RoBERTa tokenizer (backed by HuggingFace's tokenizers library). Based on Byte-Pair-Encoding. This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will be encoded differently whether it is at the beginning of the sentence (without space) or not: ```python >>> from transformers import RobertaTokenizer >>> tokenizer = RobertaTokenizer.from_pretrained("FacebookAI/roberta-base") >>> tokenizer("Hello world")["input_ids"] [0, 31414, 232, 2] >>> tokenizer(" Hello world")["input_ids"] [0, 20920, 232, 2] ``` You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer or when you call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance. When used with `is_split_into_words=True`, this tokenizer needs to be instantiated with `add_prefix_space=True`. This tokenizer inherits from [TokenizersBackend](/docs/transformers/v5.5.3/ja/main_classes/tokenizer#transformers.TokenizersBackend) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. **Parameters:** vocab (`str`, `dict` or `list`, *optional*) : Custom vocabulary dictionary. If not provided, vocabulary is loaded from vocab_file. merges (`str` or `list`, *optional*) : Custom merges list. If not provided, merges are loaded from merges_file. errors (`str`, *optional*, defaults to `"replace"`) : Paradigm to follow when decoding bytes to UTF-8. See [bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information. bos_token (`str`, *optional*, defaults to `""`) : 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 `""`) : The end of sequence token. When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the `sep_token`. sep_token (`str`, *optional*, defaults to `""`) : 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. cls_token (`str`, *optional*, defaults to `""`) : 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. 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. pad_token (`str`, *optional*, defaults to `""`) : The token used for padding, for example when batching sequences of different lengths. mask_token (`str`, *optional*, defaults to `""`) : 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 to `False`) : Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (RoBERTa tokenizer detect beginning of words by the preceding space). trim_offsets (`bool`, *optional*, defaults to `True`) : Whether the post processing step should trim offsets to avoid including whitespaces. ## BartModel[[transformers.BartModel]] #### transformers.BartModel[[transformers.BartModel]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L680) The bare Bart Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.5.3/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.BartModel.forwardhttps://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L707[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": list[torch.FloatTensor] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` 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/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **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) - **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Indices of decoder input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are decoder input IDs?](../glossary#decoder-input-ids) Bart uses the `eos_token_id` as the starting token for `decoder_input_ids` generation. If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`). For translation and summarization training, `decoder_input_ids` should be provided. If no `decoder_input_ids` is provided, the model will create this tensor by shifting the `input_ids` to the right for denoising pre-training following the paper. - **decoder_attention_mask** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also be used by default. If you want to change padding behavior, you should read `modeling_bart._prepare_decoder_attention_mask` and modify to your needs. See diagram 1 in [the paper](https://huggingface.co/papers/1910.13461) for more information on the default strategy. - **encoder_outputs** (`list[torch.FloatTensor]`, *optional*) -- Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`) `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only `Cache` instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, `DynamicCache` will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.FloatTensor` 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. - **decoder_inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be input (see `past_key_values`). This is useful if you want more control over how to convert `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix. If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value of `inputs_embeds`. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).0[Seq2SeqModelOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqModelOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. The [BartModel](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartModel) 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 decoder of the model. If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output. - **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `EncoderDecoderCache` 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 in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **decoder_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 decoder at the output of each layer plus the optional initial embedding outputs. - **decoder_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 of the decoder, 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` 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. - **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model. - **encoder_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 encoder at the output of each layer plus the optional initial embedding outputs. - **encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads. **Parameters:** config ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) : 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/v5.5.3/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[Seq2SeqModelOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)`` A [Seq2SeqModelOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. ## BartForConditionalGeneration[[transformers.BartForConditionalGeneration]] #### transformers.BartForConditionalGeneration[[transformers.BartForConditionalGeneration]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L801) The BART Model with a language modeling head. Can be used for summarization. This model inherits from [PreTrainedModel](/docs/transformers/v5.5.3/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.BartForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L833[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": list[torch.FloatTensor] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` 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/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **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) - **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Indices of decoder input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are decoder input IDs?](../glossary#decoder-input-ids) Bart uses the `eos_token_id` as the starting token for `decoder_input_ids` generation. If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`). For translation and summarization training, `decoder_input_ids` should be provided. If no `decoder_input_ids` is provided, the model will create this tensor by shifting the `input_ids` to the right for denoising pre-training following the paper. - **decoder_attention_mask** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also be used by default. If you want to change padding behavior, you should read `modeling_bart._prepare_decoder_attention_mask` and modify to your needs. See diagram 1 in [the paper](https://huggingface.co/papers/1910.13461) for more information on the default strategy. - **encoder_outputs** (`list[torch.FloatTensor]`, *optional*) -- Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`) `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only `Cache` instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, `DynamicCache` will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.FloatTensor` 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. - **decoder_inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be input (see `past_key_values`). This is useful if you want more control over how to convert `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix. If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value of `inputs_embeds`. - **labels** (`torch.LongTensor` 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]`. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).0[Seq2SeqLMOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqLMOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. The [BartForConditionalGeneration](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForConditionalGeneration) 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) -- Language modeling loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `EncoderDecoderCache` 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 in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **decoder_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 decoder at the output of each layer plus the initial embedding outputs. - **decoder_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 of the decoder, 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` 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. - **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model. - **encoder_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 encoder at the output of each layer plus the initial embedding outputs. - **encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads. Example summarization: ```python >>> from transformers import AutoTokenizer, BartForConditionalGeneration >>> model = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn") >>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn") >>> ARTICLE_TO_SUMMARIZE = ( ... "PG&E stated it scheduled the blackouts in response to forecasts for high winds " ... "amid dry conditions. The aim is to reduce the risk of wildfires. Nearly 800 thousand customers were " ... "scheduled to be affected by the shutoffs which were expected to last through at least midday tomorrow." ... ) >>> inputs = tokenizer([ARTICLE_TO_SUMMARIZE], max_length=1024, return_tensors="pt") >>> # Generate Summary >>> summary_ids = model.generate(inputs["input_ids"], num_beams=2, min_length=0, max_length=20) >>> tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] 'PG&E scheduled the blackouts in response to forecasts for high winds amid dry conditions' ``` Mask filling example: ```python >>> from transformers import AutoTokenizer, BartForConditionalGeneration >>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base") >>> model = BartForConditionalGeneration.from_pretrained("facebook/bart-base") >>> TXT = "My friends are but they eat too many carbs." >>> input_ids = tokenizer([TXT], return_tensors="pt")["input_ids"] >>> logits = model(input_ids).logits >>> masked_index = (input_ids[0] == tokenizer.mask_token_id).nonzero().item() >>> probs = logits[0, masked_index].softmax(dim=0) >>> values, predictions = probs.topk(5) >>> tokenizer.decode(predictions).split() ['not', 'good', 'healthy', 'great', 'very'] ``` **Parameters:** config ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) : 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/v5.5.3/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[Seq2SeqLMOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)`` A [Seq2SeqLMOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. ## BartForSequenceClassification[[transformers.BartForSequenceClassification]] #### transformers.BartForSequenceClassification[[transformers.BartForSequenceClassification]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L970) Bart model with a sequence classification/head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks. This model inherits from [PreTrainedModel](/docs/transformers/v5.5.3/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.BartForSequenceClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L984[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": list[torch.FloatTensor] | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` 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/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **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) - **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Indices of decoder input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are decoder input IDs?](../glossary#decoder-input-ids) Bart uses the `eos_token_id` as the starting token for `decoder_input_ids` generation. If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`). For translation and summarization training, `decoder_input_ids` should be provided. If no `decoder_input_ids` is provided, the model will create this tensor by shifting the `input_ids` to the right for denoising pre-training following the paper. - **decoder_attention_mask** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also be used by default. If you want to change padding behavior, you should read `modeling_bart._prepare_decoder_attention_mask` and modify to your needs. See diagram 1 in [the paper](https://huggingface.co/papers/1910.13461) for more information on the default strategy. - **encoder_outputs** (`list[torch.FloatTensor]`, *optional*) -- Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`) `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. - **inputs_embeds** (`torch.FloatTensor` 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. - **decoder_inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be input (see `past_key_values`). This is useful if you want more control over how to convert `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix. If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value of `inputs_embeds`. - **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) -- Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels > 1` a classification loss is computed (Cross-Entropy). - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).0[Seq2SeqSequenceClassifierOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqSequenceClassifierOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. The [BartForSequenceClassification](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForSequenceClassification) 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 `label` is provided) -- Classification (or regression if config.num_labels==1) loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`) -- Classification (or regression if config.num_labels==1) scores (before SoftMax). - **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `EncoderDecoderCache` 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 in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **decoder_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 decoder at the output of each layer plus the initial embedding outputs. - **decoder_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 of the decoder, 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` 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. - **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model. - **encoder_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 encoder at the output of each layer plus the initial embedding outputs. - **encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads. Example of single-label classification: ```python >>> import torch >>> from transformers import AutoTokenizer, BartForSequenceClassification >>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large") >>> model = BartForSequenceClassification.from_pretrained("facebook/bart-large") >>> 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 = BartForSequenceClassification.from_pretrained("facebook/bart-large", num_labels=num_labels) >>> labels = torch.tensor([1]) >>> loss = model(**inputs, labels=labels).loss >>> round(loss.item(), 2) ... ``` Example of multi-label classification: ```python >>> import torch >>> from transformers import AutoTokenizer, BartForSequenceClassification >>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large") >>> model = BartForSequenceClassification.from_pretrained("facebook/bart-large", 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 = BartForSequenceClassification.from_pretrained( ... "facebook/bart-large", 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).loss ``` **Parameters:** config ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) : 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/v5.5.3/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[Seq2SeqSequenceClassifierOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput) or `tuple(torch.FloatTensor)`` A [Seq2SeqSequenceClassifierOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. ## BartForQuestionAnswering[[transformers.BartForQuestionAnswering]] #### transformers.BartForQuestionAnswering[[transformers.BartForQuestionAnswering]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L1095) The Bart 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](/docs/transformers/v5.5.3/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.BartForQuestionAnswering.forwardhttps://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L1108[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": list[torch.FloatTensor] | None = None"}, {"name": "start_positions", "val": ": torch.LongTensor | None = None"}, {"name": "end_positions", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | 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/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **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) - **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Indices of decoder input sequence tokens in the vocabulary. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are decoder input IDs?](../glossary#decoder-input-ids) Bart uses the `eos_token_id` as the starting token for `decoder_input_ids` generation. If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`). For translation and summarization training, `decoder_input_ids` should be provided. If no `decoder_input_ids` is provided, the model will create this tensor by shifting the `input_ids` to the right for denoising pre-training following the paper. - **decoder_attention_mask** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) -- Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also be used by default. If you want to change padding behavior, you should read `modeling_bart._prepare_decoder_attention_mask` and modify to your needs. See diagram 1 in [the paper](https://huggingface.co/papers/1910.13461) for more information on the default strategy. - **encoder_outputs** (`list[torch.FloatTensor]`, *optional*) -- Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`) `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. - **start_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) -- Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence are not taken into account for computing the loss. - **end_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) -- Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence are not taken into account for computing the loss. - **inputs_embeds** (`torch.FloatTensor` 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. - **decoder_inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be input (see `past_key_values`). This is useful if you want more control over how to convert `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix. If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value of `inputs_embeds`. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).0[Seq2SeqQuestionAnsweringModelOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqQuestionAnsweringModelOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. The [BartForQuestionAnswering](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForQuestionAnswering) 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) -- Total span extraction loss is the sum of a Cross-Entropy for the start and end positions. - **start_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) -- Span-start scores (before SoftMax). - **end_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) -- Span-end scores (before SoftMax). - **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `EncoderDecoderCache` 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 in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **decoder_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 decoder at the output of each layer plus the initial embedding outputs. - **decoder_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 of the decoder, 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` 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. - **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model. - **encoder_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 encoder at the output of each layer plus the initial embedding outputs. - **encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads. Example: ```python >>> from transformers import AutoTokenizer, BartForQuestionAnswering >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large") >>> model = BartForQuestionAnswering.from_pretrained("facebook/bart-large") >>> 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) ... ``` **Parameters:** config ([BartForQuestionAnswering](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForQuestionAnswering)) : 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/v5.5.3/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[Seq2SeqQuestionAnsweringModelOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`` A [Seq2SeqQuestionAnsweringModelOutput](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. ## BartForCausalLM[[transformers.BartForCausalLM]] #### transformers.BartForCausalLM[[transformers.BartForCausalLM]] [Source](https://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L1220) BART decoder with a language modeling head on top (linear layer with weights tied to the input embeddings). This model inherits from [PreTrainedModel](/docs/transformers/v5.5.3/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.BartForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/v5.5.3/src/transformers/models/bart/modeling_bart.py#L1242[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "encoder_hidden_states", "val": ": torch.FloatTensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` 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/v5.5.3/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.3/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **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) - **encoder_hidden_states** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder. - **encoder_attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only `Cache` instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, `DynamicCache` will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.FloatTensor` 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.LongTensor` 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]`. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). - **logits_to_keep** (`Union[int, torch.Tensor]`, *optional*, defaults to `0`) -- If an `int`, compute logits for the last `logits_to_keep` tokens. If `0`, calculate logits for all `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size. If a `torch.Tensor`, must be 1D corresponding to the indices to keep in the sequence length dimension. This is useful when using packed tensor format (single dimension for batch and sequence length).0[CausalLMOutputWithCrossAttentions](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithCrossAttentions](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs. The [BartForCausalLM](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForCausalLM) 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) -- Language modeling loss (for next-token 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). - **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` 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)`. Cross attentions weights 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 attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. Example: ```python >>> from transformers import AutoTokenizer, BartForCausalLM >>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base") >>> model = BartForCausalLM.from_pretrained("facebook/bart-base") >>> assert model.config.is_decoder, f"{model.__class__} has to be configured as a decoder." >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt") >>> outputs = model(**inputs) >>> logits = outputs.logits >>> expected_shape = [1, inputs.input_ids.shape[-1], model.config.vocab_size] >>> list(logits.shape) == expected_shape True ``` **Parameters:** config ([BartForCausalLM](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartForCausalLM)) : 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/v5.5.3/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[CausalLMOutputWithCrossAttentions](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`` A [CausalLMOutputWithCrossAttentions](/docs/transformers/v5.5.3/ja/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) 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 ([BartConfig](/docs/transformers/v5.5.3/ja/model_doc/bart#transformers.BartConfig)) and inputs.