# BART

## BART

[![Models](https://img.shields.io/badge/All_model_pages-bart-blueviolet)](https://huggingface.co/models?filter=bart)[![Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/docs-demos/bart-large-mnli)

**DISCLAIMER:** If you see something strange, file a [Github Issue](https://github.com/huggingface/transformers/issues/new?assignees=\&labels=\&template=bug-report.md\&title) and assign @patrickvonplaten

### Overview

The Bart model was proposed in [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://arxiv.org/abs/1910.13461) by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer on 29 Oct, 2019.

According to the abstract,

* Bart uses a standard seq2seq/machine translation architecture with a bidirectional encoder (like BERT) and a left-to-right decoder (like GPT).
* The pretraining task involves randomly shuffling the order of the original sentences and a novel in-filling scheme, where spans of text are replaced with a single mask token.
* BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa with comparable training resources on GLUE and SQuAD, achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 6 ROUGE.

Tips:

* BART is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.
* Sequence-to-sequence model with an encoder and a decoder. Encoder is fed a corrupted version of the tokens, decoder is fed the original tokens (but has a mask to hide the future words like a regular transformers decoder). A composition of the following transformations are applied on the pretraining tasks for the encoder:
  * mask random tokens (like in BERT)
  * delete random tokens
  * mask a span of k tokens with a single mask token (a span of 0 tokens is an insertion of a mask token)
  * permute sentences
  * rotate the document to make it start at a specific token

This model was contributed by [sshleifer](https://huggingface.co/sshleifer). The Authors’ code can be found [here](https://github.com/pytorch/fairseq/tree/master/examples/bart).

#### Examples

* Examples and scripts for fine-tuning BART and other models for sequence to sequence tasks can be found in [examples/pytorch/summarization/](https://github.com/huggingface/transformers/tree/main/examples/pytorch/summarization/README.md).
* An example of how to train [BartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartForConditionalGeneration) with a BOINC AI `datasets` object can be found in this [forum discussion](https://discuss.huggingface.co/t/train-bart-for-conditional-generation-e-g-summarization/1904).
* [Distilled checkpoints](https://huggingface.co/models?search=distilbart) are described in this [paper](https://arxiv.org/abs/2010.13002).

### Implementation Notes

* Bart doesn’t use `token_type_ids` for sequence classification. Use [BartTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartTokenizer) or [encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) to get the proper splitting.
* The forward pass of [BartModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartModel) will create the `decoder_input_ids` if they are not passed. This is different than some other modeling APIs. A typical use case of this feature is mask filling.
* Model predictions are intended to be identical to the original implementation when `forced_bos_token_id=0`. This only works, however, if the string you pass to `fairseq.encode` starts with a space.
* [generate()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/text_generation#transformers.GenerationMixin.generate) should be used for conditional generation tasks like summarization, see the example in that docstrings.
* Models that load the *facebook/bart-large-cnn* weights will not have a `mask_token_id`, or be able to perform mask-filling tasks.

### Mask Filling

The `facebook/bart-base` and `facebook/bart-large` checkpoints can be used to fill multi-token masks.

Copied

```
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 <mask> 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

A list of official BOINC AI and community (indicated by 🌎) resources to help you get started with BART. If you’re interested in submitting a resource to be included here, please feel free to open a Pull Request and we’ll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

Summarization

* A blog post on [Distributed Training: Train BART/T5 for Summarization using ](https://huggingface.co/blog/sagemaker-distributed-training-seq2seq)🌎[ Transformers and Amazon SageMaker](https://huggingface.co/blog/sagemaker-distributed-training-seq2seq).
* A notebook on how to [finetune BART for summarization with fastai using blurr](https://colab.research.google.com/github/ohmeow/ohmeow_website/blob/master/posts/2021-05-25-mbart-sequence-classification-with-blurr.ipynb). 🌎
* A notebook on how to [finetune BART for summarization in two languages with Trainer class](https://colab.research.google.com/github/elsanns/xai-nlp-notebooks/blob/master/fine_tune_bart_summarization_two_langs.ipynb). 🌎
* [BartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartForConditionalGeneration) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/summarization) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/summarization.ipynb).
* [TFBartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.TFBartForConditionalGeneration) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/summarization) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/summarization-tf.ipynb).
* [FlaxBartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.FlaxBartForConditionalGeneration) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/flax/summarization).
* [Summarization](https://huggingface.co/course/chapter7/5?fw=pt#summarization) chapter of the 🌎 BOINC AI course.
* [Summarization task guide](https://huggingface.co/docs/transformers/tasks/summarization)

Fill-Mask

* [BartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartForConditionalGeneration) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/language-modeling#robertabertdistilbert-and-masked-language-modeling) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling.ipynb).
* [TFBartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.TFBartForConditionalGeneration) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/language-modeling#run_mlmpy) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling-tf.ipynb).
* [FlaxBartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.FlaxBartForConditionalGeneration) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/flax/language-modeling#masked-language-modeling) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/masked_language_modeling_flax.ipynb).
* [Masked language modeling](https://huggingface.co/course/chapter7/3?fw=pt) chapter of the 🌎 BOINC AI Course.
* [Masked language modeling task guide](https://huggingface.co/docs/transformers/tasks/masked_language_modeling)

Translation

* A notebook on how to [finetune mBART using Seq2SeqTrainer for Hindi to English translation](https://colab.research.google.com/github/vasudevgupta7/huggingface-tutorials/blob/main/translation_training.ipynb). 🌎
* [BartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartForConditionalGeneration) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/translation) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/translation.ipynb).
* [TFBartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.TFBartForConditionalGeneration) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/translation) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/translation-tf.ipynb).
* [Translation task guide](https://huggingface.co/docs/transformers/tasks/translation)

See also:

* [Text classification task guide](https://huggingface.co/docs/transformers/tasks/sequence_classification)
* [Question answering task guide](https://huggingface.co/docs/transformers/tasks/question_answering)
* [Causal language modeling task guide](https://huggingface.co/docs/transformers/tasks/language_modeling)

### BartConfig

#### class transformers.BartConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/configuration_bart.py#L35)

( vocab\_size = 50265max\_position\_embeddings = 1024encoder\_layers = 12encoder\_ffn\_dim = 4096encoder\_attention\_heads = 16decoder\_layers = 12decoder\_ffn\_dim = 4096decoder\_attention\_heads = 16encoder\_layerdrop = 0.0decoder\_layerdrop = 0.0activation\_function = 'gelu'd\_model = 1024dropout = 0.1attention\_dropout = 0.0activation\_dropout = 0.0init\_std = 0.02classifier\_dropout = 0.0scale\_embedding = Falseuse\_cache = Truenum\_labels = 3pad\_token\_id = 1bos\_token\_id = 0eos\_token\_id = 2is\_encoder\_decoder = Truedecoder\_start\_token\_id = 2forced\_eos\_token\_id = 2\*\*kwargs )

Parameters

* **vocab\_size** (`int`, *optional*, defaults to 50265) — Vocabulary size of the BART model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [BartModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartModel) or [TFBartModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.TFBartModel).
* **d\_model** (`int`, *optional*, defaults to 1024) — Dimensionality of the layers and the pooler layer.
* **encoder\_layers** (`int`, *optional*, defaults to 12) — Number of encoder layers.
* **decoder\_layers** (`int`, *optional*, defaults to 12) — Number of decoder layers.
* **encoder\_attention\_heads** (`int`, *optional*, defaults to 16) — Number of attention heads for each attention layer in the Transformer encoder.
* **decoder\_attention\_heads** (`int`, *optional*, defaults to 16) — Number of attention heads for each attention layer in the Transformer decoder.
* **decoder\_ffn\_dim** (`int`, *optional*, defaults to 4096) — Dimensionality of the “intermediate” (often named feed-forward) layer in decoder.
* **encoder\_ffn\_dim** (`int`, *optional*, defaults to 4096) — Dimensionality of the “intermediate” (often named feed-forward) layer in decoder.
* **activation\_function** (`str` or `function`, *optional*, defaults to `"gelu"`) — The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported.
* **dropout** (`float`, *optional*, defaults to 0.1) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
* **attention\_dropout** (`float`, *optional*, defaults to 0.0) — The dropout ratio for the attention probabilities.
* **activation\_dropout** (`float`, *optional*, defaults to 0.0) — The dropout ratio for activations inside the fully connected layer.
* **classifier\_dropout** (`float`, *optional*, defaults to 0.0) — The dropout ratio for classifier.
* **max\_position\_embeddings** (`int`, *optional*, defaults to 1024) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
* **init\_std** (`float`, *optional*, defaults to 0.02) — The standard deviation of the truncated\_normal\_initializer for initializing all weight matrices.
* **encoder\_layerdrop** (`float`, *optional*, defaults to 0.0) — The LayerDrop probability for the encoder. See the \[LayerDrop paper]\(see <https://arxiv.org/abs/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://arxiv.org/abs/1909.11556>) for more details.
* **scale\_embedding** (`bool`, *optional*, defaults to `False`) — Scale embeddings by diving 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).
* **num\_labels** (`int`, *optional*, defaults to 3) — The number of labels to use in [BartForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartForSequenceClassification).
* **forced\_eos\_token\_id** (`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`.

This is the configuration class to store the configuration of a [BartModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.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 BART [facebook/bart-large](https://huggingface.co/facebook/bart-large) architecture.

Configuration objects inherit from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) for more information.

Example:

Copied

```
>>> 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
```

### BartTokenizer

#### class transformers.BartTokenizer

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/tokenization_bart.py#L101)

( vocab\_filemerges\_fileerrors = 'replace'bos\_token = '\<s>'eos\_token = '\</s>'sep\_token = '\</s>'cls\_token = '\<s>'unk\_token = '\<unk>'pad\_token = '\<pad>'mask\_token = '\<mask>'add\_prefix\_space = False\*\*kwargs )

Parameters

* **vocab\_file** (`str`) — Path to the vocabulary file.
* **merges\_file** (`str`) — Path to the 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 `"<s>"`) — 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 `"</s>"`) — 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 `"</s>"`) — 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 `"<s>"`) — 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 `"<unk>"`) — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
* **pad\_token** (`str`, *optional*, defaults to `"<pad>"`) — The token used for padding, for example when batching sequences of different lengths.
* **mask\_token** (`str`, *optional*, defaults to `"<mask>"`) — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict.
* **add\_prefix\_space** (`bool`, *optional*, defaults 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. (BART tokenizer detect beginning of words by the preceding space).

Constructs a BART tokenizer, which is smilar to the ROBERTa tokenizer, using byte-level 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:

Copied

```
>>> from transformers import BartTokenizer

>>> tokenizer = BartTokenizer.from_pretrained("facebook/bart-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 will add a space before each word (even the first one).

This tokenizer inherits from [PreTrainedTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizer) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

**build\_inputs\_with\_special\_tokens**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/tokenization_bart.py#L340)

( token\_ids\_0: typing.List\[int]token\_ids\_1: typing.Optional\[typing.List\[int]] = None ) → `List[int]`

Parameters

* **token\_ids\_0** (`List[int]`) — List of IDs to which the special tokens will be added.
* **token\_ids\_1** (`List[int]`, *optional*) — Optional second list of IDs for sequence pairs.

Returns

`List[int]`

List of [input IDs](https://huggingface.co/docs/transformers/glossary#input-ids) with the appropriate special tokens.

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A BART sequence has the following format:

* single sequence: `<s> X </s>`
* pair of sequences: `<s> A </s></s> B </s>`

**convert\_tokens\_to\_string**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/tokenization_bart.py#L305)

( tokens )

Converts a sequence of tokens (string) in a single string.

**create\_token\_type\_ids\_from\_sequences**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/tokenization_bart.py#L392)

( token\_ids\_0: typing.List\[int]token\_ids\_1: typing.Optional\[typing.List\[int]] = None ) → `List[int]`

Parameters

* **token\_ids\_0** (`List[int]`) — List of IDs.
* **token\_ids\_1** (`List[int]`, *optional*) — Optional second list of IDs for sequence pairs.

Returns

`List[int]`

List of zeros.

Create a mask from the two sequences passed to be used in a sequence-pair classification task. BART does not make use of token type ids, therefore a list of zeros is returned.

**get\_special\_tokens\_mask**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/tokenization_bart.py#L365)

( token\_ids\_0: typing.List\[int]token\_ids\_1: typing.Optional\[typing.List\[int]] = Nonealready\_has\_special\_tokens: bool = False ) → `List[int]`

Parameters

* **token\_ids\_0** (`List[int]`) — List of IDs.
* **token\_ids\_1** (`List[int]`, *optional*) — Optional second list of IDs for sequence pairs.
* **already\_has\_special\_tokens** (`bool`, *optional*, defaults to `False`) — Whether or not the token list is already formatted with special tokens for the model.

Returns

`List[int]`

A list of integers in the range \[0, 1]: 1 for a special token, 0 for a sequence token.

Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` method.

### BartTokenizerFast

#### class transformers.BartTokenizerFast

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/tokenization_bart_fast.py#L70)

( vocab\_file = Nonemerges\_file = Nonetokenizer\_file = Noneerrors = 'replace'bos\_token = '\<s>'eos\_token = '\</s>'sep\_token = '\</s>'cls\_token = '\<s>'unk\_token = '\<unk>'pad\_token = '\<pad>'mask\_token = '\<mask>'add\_prefix\_space = Falsetrim\_offsets = True\*\*kwargs )

Parameters

* **vocab\_file** (`str`) — Path to the vocabulary file.
* **merges\_file** (`str`) — Path to the 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 `"<s>"`) — 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 `"</s>"`) — 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 `"</s>"`) — 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 `"<s>"`) — 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 `"<unk>"`) — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
* **pad\_token** (`str`, *optional*, defaults to `"<pad>"`) — The token used for padding, for example when batching sequences of different lengths.
* **mask\_token** (`str`, *optional*, defaults to `"<mask>"`) — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict.
* **add\_prefix\_space** (`bool`, *optional*, defaults 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. (BART 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.

Construct a “fast” BART tokenizer (backed by BOINC AI’s *tokenizers* library), derived from the GPT-2 tokenizer, using byte-level 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:

Copied

```
>>> from transformers import BartTokenizerFast

>>> tokenizer = BartTokenizerFast.from_pretrained("facebook/bart-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 [PreTrainedTokenizerFast](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

**create\_token\_type\_ids\_from\_sequences**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/tokenization_bart_fast.py#L291)

( token\_ids\_0: typing.List\[int]token\_ids\_1: typing.Optional\[typing.List\[int]] = None ) → `List[int]`

Parameters

* **token\_ids\_0** (`List[int]`) — List of IDs.
* **token\_ids\_1** (`List[int]`, *optional*) — Optional second list of IDs for sequence pairs.

Returns

`List[int]`

List of zeros.

Create a mask from the two sequences passed to be used in a sequence-pair classification task. BART does not make use of token type ids, therefore a list of zeros is returned.

### BartModel

#### class transformers.BartModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1180)

( config: BartConfig )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

The bare BART Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/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.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1209)

( input\_ids: LongTensor = Noneattention\_mask: typing.Optional\[torch.Tensor] = Nonedecoder\_input\_ids: typing.Optional\[torch.LongTensor] = Nonedecoder\_attention\_mask: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Nonedecoder\_head\_mask: typing.Optional\[torch.Tensor] = Nonecross\_attn\_head\_mask: typing.Optional\[torch.Tensor] = Noneencoder\_outputs: typing.Optional\[typing.List\[torch.FloatTensor]] = Nonepast\_key\_values: typing.Optional\[typing.List\[torch.FloatTensor]] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonedecoder\_inputs\_embeds: typing.Optional\[torch.FloatTensor] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.Seq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/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://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **head\_mask** (`torch.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **decoder\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **cross\_attn\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **encoder\_outputs** (`tuple(tuple(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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.

  If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_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`).
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_outputs.Seq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.Seq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.

The [BartModel](https://huggingface.co/docs/transformers/v4.34.1/en/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.

Example:

Copied

```
>>> from transformers import AutoTokenizer, BartModel
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base")
>>> model = BartModel.from_pretrained("facebook/bart-base")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
```

### BartForConditionalGeneration

#### class transformers.BartForConditionalGeneration

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1307)

( config: BartConfig )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

The BART Model with a language modeling head. Can be used for summarization. This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/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.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1347)

( input\_ids: LongTensor = Noneattention\_mask: typing.Optional\[torch.Tensor] = Nonedecoder\_input\_ids: typing.Optional\[torch.LongTensor] = Nonedecoder\_attention\_mask: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Nonedecoder\_head\_mask: typing.Optional\[torch.Tensor] = Nonecross\_attn\_head\_mask: typing.Optional\[torch.Tensor] = Noneencoder\_outputs: typing.Optional\[typing.List\[torch.FloatTensor]] = Nonepast\_key\_values: typing.Optional\[typing.List\[torch.FloatTensor]] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonedecoder\_inputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.Seq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/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://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **head\_mask** (`torch.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **decoder\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **cross\_attn\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **encoder\_outputs** (`tuple(tuple(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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.

  If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_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`).
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **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]`.

Returns

[transformers.modeling\_outputs.Seq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.Seq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.

The [BartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/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.

Summarization example:

Copied

```
>>> 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:

Copied

```
>>> from transformers import AutoTokenizer, BartForConditionalGeneration

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base")
>>> model = BartForConditionalGeneration.from_pretrained("facebook/bart-base")

>>> TXT = "My friends are <mask> 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']
```

### BartForSequenceClassification

#### class transformers.BartForSequenceClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1483)

( config: BartConfig\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

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](https://huggingface.co/docs/transformers/v4.34.1/en/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.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1499)

( input\_ids: LongTensor = Noneattention\_mask: typing.Optional\[torch.Tensor] = Nonedecoder\_input\_ids: typing.Optional\[torch.LongTensor] = Nonedecoder\_attention\_mask: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Nonedecoder\_head\_mask: typing.Optional\[torch.Tensor] = Nonecross\_attn\_head\_mask: typing.Optional\[torch.Tensor] = Noneencoder\_outputs: typing.Optional\[typing.List\[torch.FloatTensor]] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonedecoder\_inputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.Seq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/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://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **head\_mask** (`torch.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **decoder\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **cross\_attn\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **encoder\_outputs** (`tuple(tuple(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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.

  If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_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`).
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **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).

Returns

[transformers.modeling\_outputs.Seq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.Seq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.

The [BartForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/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.

Example of single-label classification:

Copied

```
>>> import torch
>>> from transformers import AutoTokenizer, BartForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("valhalla/bart-large-sst2")
>>> model = BartForSequenceClassification.from_pretrained("valhalla/bart-large-sst2")

>>> 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]
'POSITIVE'

>>> # 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("valhalla/bart-large-sst2", num_labels=num_labels)

>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
0.0
```

Example of multi-label classification:

Copied

```
>>> import torch
>>> from transformers import AutoTokenizer, BartForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("valhalla/bart-large-sst2")
>>> model = BartForSequenceClassification.from_pretrained("valhalla/bart-large-sst2", 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(
...     "valhalla/bart-large-sst2", 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
```

### BartForQuestionAnswering

#### class transformers.BartForQuestionAnswering

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1613)

( config )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

BART Model 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](https://huggingface.co/docs/transformers/v4.34.1/en/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.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1628)

( input\_ids: Tensor = Noneattention\_mask: typing.Optional\[torch.Tensor] = Nonedecoder\_input\_ids: typing.Optional\[torch.LongTensor] = Nonedecoder\_attention\_mask: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Nonedecoder\_head\_mask: typing.Optional\[torch.Tensor] = Nonecross\_attn\_head\_mask: typing.Optional\[torch.Tensor] = Noneencoder\_outputs: typing.Optional\[typing.List\[torch.FloatTensor]] = Nonestart\_positions: typing.Optional\[torch.LongTensor] = Noneend\_positions: typing.Optional\[torch.LongTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonedecoder\_inputs\_embeds: typing.Optional\[torch.FloatTensor] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.Seq2SeqQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/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://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **head\_mask** (`torch.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **decoder\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **cross\_attn\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **encoder\_outputs** (`tuple(tuple(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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.

  If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_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`).
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **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.

Returns

[transformers.modeling\_outputs.Seq2SeqQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.Seq2SeqQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.

The [BartForQuestionAnswering](https://huggingface.co/docs/transformers/v4.34.1/en/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.

Example:

Copied

```
>>> from transformers import AutoTokenizer, BartForQuestionAnswering
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("valhalla/bart-large-finetuned-squadv1")
>>> model = BartForQuestionAnswering.from_pretrained("valhalla/bart-large-finetuned-squadv1")

>>> 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)
' nice puppet'

>>> # 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)
0.59
```

### BartForCausalLM

#### class transformers.BartForCausalLM

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1751)

( config )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

BART decoder with with a language modeling head on top (linear layer with weights tied to the input embeddings).

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/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.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_bart.py#L1784)

( input\_ids: LongTensor = Noneattention\_mask: typing.Optional\[torch.Tensor] = Noneencoder\_hidden\_states: typing.Optional\[torch.FloatTensor] = Noneencoder\_attention\_mask: typing.Optional\[torch.FloatTensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Nonecross\_attn\_head\_mask: typing.Optional\[torch.Tensor] = Nonepast\_key\_values: typing.Optional\[typing.List\[torch.FloatTensor]] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.CausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/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]`:
* **head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **cross\_attn\_head\_mask** (`torch.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the cross-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. The two additional tensors are only required when the model is used as a decoder in a Sequence to Sequence model.

  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.

  If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
* **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`).
  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_outputs.CausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.CausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **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** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `torch.FloatTensor` tuples of length `config.n_layers`, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant if `config.is_decoder = True`.

  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:

Copied

```
>>> from transformers import AutoTokenizer, BartForCausalLM

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base")
>>> model = BartForCausalLM.from_pretrained("facebook/bart-base", add_cross_attention=False)
>>> 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
```

### TFBartModel

#### class transformers.TFBartModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_tf_bart.py#L1151)

( \*args\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel.from_pretrained) method to load the model weights.

The bare BART Model outputting raw hidden-states without any specific head on top. This model inherits from [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). 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 [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in `transformers` accept two formats as input:

* having all inputs as keyword arguments (like PyTorch models), or
* having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

* a single Tensor with `input_ids` only and nothing else: `model(input_ids)`
* a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])`
* a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})`

Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

**call**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_tf_bart.py#L1165)

( input\_ids: TFModelInputType | None = Noneattention\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_input\_ids: np.ndarray | tf.Tensor | None = Nonedecoder\_attention\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_position\_ids: np.ndarray | tf.Tensor | None = Nonehead\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_head\_mask: np.ndarray | tf.Tensor | None = Nonecross\_attn\_head\_mask: np.ndarray | tf.Tensor | None = Noneencoder\_outputs: Optional\[Union\[Tuple, TFBaseModelOutput]] = Nonepast\_key\_values: Optional\[Tuple\[Tuple\[Union\[np.ndarray, tf.Tensor]]]] = Noneinputs\_embeds: np.ndarray | tf.Tensor | None = Nonedecoder\_inputs\_embeds: np.ndarray | tf.Tensor | None = Noneuse\_cache: Optional\[bool] = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonetraining: Optional\[bool] = False\*\*kwargs ) → [transformers.modeling\_tf\_outputs.TFSeq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqModelOutput) or `tuple(tf.Tensor)`

Parameters

* **input\_ids** (`tf.Tensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`tf.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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_input\_ids** (`tf.Tensor` of shape `(batch_size, target_sequence_length)`, *optional*) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/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** (`tf.Tensor` of shape `(batch_size, target_sequence_length)`, *optional*) — will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.
* **decoder\_position\_ids** (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **head\_mask** (`tf.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **decoder\_head\_mask** (`tf.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **cross\_attn\_head\_mask** (`tf.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the cross-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **encoder\_outputs** (`tf.FloatTensor`, *optional*) — hidden states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. of shape `(batch_size, sequence_length, hidden_size)` is a sequence of
* **past\_key\_values** (`Tuple[Tuple[tf.Tensor]]` of length `config.n_layers`) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
* **use\_cache** (`bool`, *optional*, defaults to `True`) — If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). Set to `False` during training, `True` during generation
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
* **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

[transformers.modeling\_tf\_outputs.TFSeq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqModelOutput) or `tuple(tf.Tensor)`

A [transformers.modeling\_tf\_outputs.TFSeq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqModelOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **last\_hidden\_state** (`tf.Tensor` 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** (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads, sequence_length, embed_size_per_head)`).

  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.
* **decoder\_hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
* **decoder\_attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

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

  Attentions weights 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** (`tf.Tensor` 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(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
* **encoder\_attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

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

The [TFBartModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.TFBartModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, TFBartModel
>>> import tensorflow as tf

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large")
>>> model = TFBartModel.from_pretrained("facebook/bart-large")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="tf")
>>> outputs = model(inputs)

>>> last_hidden_states = outputs.last_hidden_state
```

### TFBartForConditionalGeneration

#### class transformers.TFBartForConditionalGeneration

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_tf_bart.py#L1256)

( \*args\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel.from_pretrained) method to load the model weights.

The BART Model with a language modeling head. Can be used for summarization. This model inherits from [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). 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 [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in `transformers` accept two formats as input:

* having all inputs as keyword arguments (like PyTorch models), or
* having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

* a single Tensor with `input_ids` only and nothing else: `model(input_ids)`
* a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])`
* a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})`

Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

**call**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_tf_bart.py#L1292)

( input\_ids: TFModelInputType | None = Noneattention\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_input\_ids: np.ndarray | tf.Tensor | None = Nonedecoder\_attention\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_position\_ids: np.ndarray | tf.Tensor | None = Nonehead\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_head\_mask: np.ndarray | tf.Tensor | None = Nonecross\_attn\_head\_mask: np.ndarray | tf.Tensor | None = Noneencoder\_outputs: Optional\[TFBaseModelOutput] = Nonepast\_key\_values: Optional\[Tuple\[Tuple\[Union\[np.ndarray, tf.Tensor]]]] = Noneinputs\_embeds: np.ndarray | tf.Tensor | None = Nonedecoder\_inputs\_embeds: np.ndarray | tf.Tensor | None = Noneuse\_cache: Optional\[bool] = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonelabels: tf.Tensor | None = Nonetraining: Optional\[bool] = False ) → [transformers.modeling\_tf\_outputs.TFSeq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqLMOutput) or `tuple(tf.Tensor)`

Parameters

* **input\_ids** (`tf.Tensor` of shape `({0})`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`tf.Tensor` of shape `({0})`, *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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_input\_ids** (`tf.Tensor` of shape `(batch_size, target_sequence_length)`, *optional*) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/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** (`tf.Tensor` of shape `(batch_size, target_sequence_length)`, *optional*) — will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.
* **decoder\_position\_ids** (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **head\_mask** (`tf.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **decoder\_head\_mask** (`tf.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **cross\_attn\_head\_mask** (`tf.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the cross-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **encoder\_outputs** (`tf.FloatTensor`, *optional*) — hidden states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. of shape `(batch_size, sequence_length, hidden_size)` is a sequence of
* **past\_key\_values** (`Tuple[Tuple[tf.Tensor]]` of length `config.n_layers`) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
* **use\_cache** (`bool`, *optional*, defaults to `True`) — If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). Set to `False` during training, `True` during generation
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
* **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
* **labels** (`tf.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]`.

Returns

[transformers.modeling\_tf\_outputs.TFSeq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqLMOutput) or `tuple(tf.Tensor)`

A [transformers.modeling\_tf\_outputs.TFSeq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqLMOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **loss** (`tf.Tensor` of shape `(n,)`, *optional*, where n is the number of non-masked labels, returned when `labels` is provided) — Language modeling loss.
* **logits** (`tf.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
* **past\_key\_values** (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads, sequence_length, embed_size_per_head)`).

  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.
* **decoder\_hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
* **decoder\_attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

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

  Attentions weights 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** (`tf.Tensor` 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(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
* **encoder\_attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

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

The [TFBartForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.TFBartForConditionalGeneration) 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.

Summarization example:

Copied

```
>>> from transformers import AutoTokenizer, TFBartForConditionalGeneration

>>> model = TFBartForConditionalGeneration.from_pretrained("facebook/bart-large")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large")

>>> ARTICLE_TO_SUMMARIZE = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer([ARTICLE_TO_SUMMARIZE], max_length=1024, return_tensors="tf")

>>> # Generate Summary
>>> summary_ids = model.generate(inputs["input_ids"], num_beams=4, max_length=5)
>>> print(tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False))
```

Mask filling example:

Copied

```
>>> from transformers import AutoTokenizer, TFBartForConditionalGeneration

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large")
>>> TXT = "My friends are <mask> but they eat too many carbs."

>>> model = TFBartForConditionalGeneration.from_pretrained("facebook/bart-large")
>>> input_ids = tokenizer([TXT], return_tensors="tf")["input_ids"]
>>> logits = model(input_ids).logits
>>> probs = tf.nn.softmax(logits[0])
>>> # probs[5] is associated with the mask token
```

### TFBartForSequenceClassification

#### class transformers.TFBartForSequenceClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_tf_bart.py#L1445)

( \*args\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel.from_pretrained) method to load the model weights.

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 [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). 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 [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in `transformers` accept two formats as input:

* having all inputs as keyword arguments (like PyTorch models), or
* having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

* a single Tensor with `input_ids` only and nothing else: `model(input_ids)`
* a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])`
* a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"input_ids": input_ids, "token_type_ids": token_type_ids})`

Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

**call**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_tf_bart.py#L1453)

( input\_ids: TFModelInputType | None = Noneattention\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_input\_ids: np.ndarray | tf.Tensor | None = Nonedecoder\_attention\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_position\_ids: np.ndarray | tf.Tensor | None = Nonehead\_mask: np.ndarray | tf.Tensor | None = Nonedecoder\_head\_mask: np.ndarray | tf.Tensor | None = Nonecross\_attn\_head\_mask: np.ndarray | tf.Tensor | None = Noneencoder\_outputs: Optional\[TFBaseModelOutput] = Nonepast\_key\_values: Optional\[Tuple\[Tuple\[Union\[np.ndarray, tf.Tensor]]]] = Noneinputs\_embeds: np.ndarray | tf.Tensor | None = Nonedecoder\_inputs\_embeds: np.ndarray | tf.Tensor | None = Noneuse\_cache: Optional\[bool] = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonelabels: tf.Tensor | None = Nonetraining: Optional\[bool] = False ) → [transformers.modeling\_tf\_outputs.TFSeq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqSequenceClassifierOutput) or `tuple(tf.Tensor)`

Parameters

* **input\_ids** (`tf.Tensor` of shape `({0})`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`tf.Tensor` of shape `({0})`, *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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_input\_ids** (`tf.Tensor` of shape `(batch_size, target_sequence_length)`, *optional*) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/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** (`tf.Tensor` of shape `(batch_size, target_sequence_length)`, *optional*) — will be made by default and ignore pad tokens. It is not recommended to set this for most use cases.
* **decoder\_position\_ids** (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **head\_mask** (`tf.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the encoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **decoder\_head\_mask** (`tf.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the attention modules in the decoder. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **cross\_attn\_head\_mask** (`tf.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*) — Mask to nullify selected heads of the cross-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **encoder\_outputs** (`tf.FloatTensor`, *optional*) — hidden states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. of shape `(batch_size, sequence_length, hidden_size)` is a sequence of
* **past\_key\_values** (`Tuple[Tuple[tf.Tensor]]` of length `config.n_layers`) — contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
* **use\_cache** (`bool`, *optional*, defaults to `True`) — If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). Set to `False` during training, `True` during generation
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
* **training** (`bool`, *optional*, defaults to `False`) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
* **labels** (`tf.Tensor` of shape `(batch_size, sequence_length)`, *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).

Returns

[transformers.modeling\_tf\_outputs.TFSeq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqSequenceClassifierOutput) or `tuple(tf.Tensor)`

A [transformers.modeling\_tf\_outputs.TFSeq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSeq2SeqSequenceClassifierOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **loss** (`tf.Tensor` of shape `(1,)`, *optional*, returned when `label` is provided) — Classification (or regression if config.num\_labels==1) loss.
* **logits** (`tf.Tensor` of shape `(batch_size, config.num_labels)`) — Classification (or regression if config.num\_labels==1) scores (before SoftMax).
* **past\_key\_values** (`List[tf.Tensor]`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — List of `tf.Tensor` of length `config.n_layers`, with each tensor of shape `(2, batch_size, num_heads, sequence_length, embed_size_per_head)`).

  Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see `past_key_values` input) to speed up sequential decoding.
* **decoder\_hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
* **decoder\_attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
* **cross\_attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`
* **encoder\_last\_hidden\_state** (`tf.Tensor` 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(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
* **encoder\_attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

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

The [TFBartForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.TFBartForSequenceClassification) 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.

### FlaxBartModel

#### class transformers.FlaxBartModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1241)

( config: BartConfiginput\_shape: typing.Tuple\[int] = (1, 1)seed: int = 0dtype: dtype = \<class 'jax.numpy.float32'>\_do\_init: bool = True\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights.
* **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) — The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs).

  This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`.

  **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.**

  If you wish to change the dtype of the model parameters, see [to\_fp16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to\_bf16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).

The bare Bart Model transformer outputting raw hidden-states without any specific head on top. This model inherits from [FlaxPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel). 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 Flax Linen [flax.nn.Module](https://flax.readthedocs.io/en/latest/_autosummary/flax.nn.module.html) subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

* [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit)
* [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation)
* [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap)
* [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)

**\_\_call\_\_**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1176)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_input\_ids: typing.Optional\[jax.Array] = Nonedecoder\_attention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Nonedecoder\_position\_ids: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxSeq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`, *optional*) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **position\_ids** (`numpy.ndarray` 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.max_position_embeddings - 1]`.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxSeq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxSeq2SeqModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqModelOutput) 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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **last\_hidden\_state** (`jnp.ndarray` 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** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
* **decoder\_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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** (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
* **encoder\_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

The `FlaxBartPreTrainedModel` forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartModel

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base")
>>> model = FlaxBartModel.from_pretrained("facebook/bart-base")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="jax")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
```

**encode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L999)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **position\_ids** (`numpy.ndarray` 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.max_position_embeddings - 1]`.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) 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 (`<class 'transformers.models.bart.configuration_bart.BartConfig'>`) and inputs.

* **last\_hidden\_state** (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **hidden\_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

Example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors="jax")
>>> encoder_outputs = model.encode(**inputs)
```

**decode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1062)

( decoder\_input\_idsencoder\_outputsencoder\_attention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_attention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_position\_ids: typing.Optional\[jax.Array] = Nonepast\_key\_values: dict = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) or `tuple(torch.FloatTensor)`

Parameters

* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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.
* **encoder\_outputs** (`tuple(tuple(jnp.ndarray)`) — 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.
* **encoder\_attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_attention\_mask** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **past\_key\_values** (`Dict[str, np.ndarray]`, *optional*, returned by `init_cache` or when passing previous `past_key_values`) — Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape *\[batch\_size, max\_length]*.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) 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 (`<class 'transformers.models.bart.configuration_bart.BartConfig'>`) and inputs.

* **last\_hidden\_state** (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer 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** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if `config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.
* **hidden\_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

Example:

Copied

```
>>> import jax.numpy as jnp
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors="jax")
>>> encoder_outputs = model.encode(**inputs)

>>> decoder_start_token_id = model.config.decoder_start_token_id
>>> decoder_input_ids = jnp.ones((inputs.input_ids.shape[0], 1), dtype="i4") * decoder_start_token_id

>>> outputs = model.decode(decoder_input_ids, encoder_outputs)
>>> last_decoder_hidden_states = outputs.last_hidden_state
```

### FlaxBartForConditionalGeneration

#### class transformers.FlaxBartForConditionalGeneration

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1325)

( config: BartConfiginput\_shape: typing.Tuple\[int] = (1, 1)seed: int = 0dtype: dtype = \<class 'jax.numpy.float32'>\_do\_init: bool = True\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights.
* **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) — The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs).

  This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`.

  **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.**

  If you wish to change the dtype of the model parameters, see [to\_fp16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to\_bf16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).

The BART Model with a language modeling head. Can be used for summarization. This model inherits from [FlaxPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel). 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 Flax Linen [flax.nn.Module](https://flax.readthedocs.io/en/latest/_autosummary/flax.nn.module.html) subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

* [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit)
* [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation)
* [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap)
* [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)

**\_\_call\_\_**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1176)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_input\_ids: typing.Optional\[jax.Array] = Nonedecoder\_attention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Nonedecoder\_position\_ids: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxSeq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`, *optional*) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **position\_ids** (`numpy.ndarray` 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.max_position_embeddings - 1]`.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxSeq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxSeq2SeqLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput) 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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **logits** (`jnp.ndarray` 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** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
* **decoder\_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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** (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
* **encoder\_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

The `FlaxBartPreTrainedModel` 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.

Summarization example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> ARTICLE_TO_SUMMARIZE = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer([ARTICLE_TO_SUMMARIZE], max_length=1024, return_tensors="np")

>>> # Generate Summary
>>> summary_ids = model.generate(inputs["input_ids"]).sequences
>>> print(tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False))
```

Mask filling example:

Copied

```
>>> import jax
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large")

>>> TXT = "My friends are <mask> but they eat too many carbs."
>>> input_ids = tokenizer([TXT], return_tensors="jax")["input_ids"]

>>> logits = model(input_ids).logits
>>> masked_index = (input_ids[0] == tokenizer.mask_token_id).nonzero()[0].item()
>>> probs = jax.nn.softmax(logits[0, masked_index], axis=0)
>>> values, predictions = jax.lax.top_k(probs, k=1)

>>> tokenizer.decode(predictions).split()
```

**encode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L999)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **position\_ids** (`numpy.ndarray` 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.max_position_embeddings - 1]`.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) 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 (`<class 'transformers.models.bart.configuration_bart.BartConfig'>`) and inputs.

* **last\_hidden\_state** (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **hidden\_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

Example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors="jax")
>>> encoder_outputs = model.encode(**inputs)
```

**decode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1329)

( decoder\_input\_idsencoder\_outputsencoder\_attention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_attention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_position\_ids: typing.Optional\[jax.Array] = Nonepast\_key\_values: dict = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxCausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`

Parameters

* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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.
* **encoder\_outputs** (`tuple(tuple(jnp.ndarray)`) — 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.
* **encoder\_attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_attention\_mask** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **past\_key\_values** (`Dict[str, np.ndarray]`, *optional*, returned by `init_cache` or when passing previous `past_key_values`) — Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape *\[batch\_size, max\_length]*.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxCausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxCausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions) 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 (`<class 'transformers.models.bart.configuration_bart.BartConfig'>`) and inputs.

* **logits** (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `jnp.ndarray` tuples of length `config.n_layers`, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant if `config.is_decoder = True`.

  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:

Copied

```
>>> import jax.numpy as jnp
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors="jax")
>>> encoder_outputs = model.encode(**inputs)

>>> decoder_start_token_id = model.config.decoder_start_token_id
>>> decoder_input_ids = jnp.ones((inputs.input_ids.shape[0], 1), dtype="i4") * decoder_start_token_id

>>> outputs = model.decode(decoder_input_ids, encoder_outputs)
>>> logits = outputs.logits
```

### FlaxBartForSequenceClassification

#### class transformers.FlaxBartForSequenceClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1638)

( config: BartConfiginput\_shape: typing.Tuple\[int] = (1, 1)seed: int = 0dtype: dtype = \<class 'jax.numpy.float32'>\_do\_init: bool = True\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights.
* **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) — The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs).

  This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`.

  **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.**

  If you wish to change the dtype of the model parameters, see [to\_fp16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to\_bf16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).

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 [FlaxPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel). 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 Flax Linen [flax.nn.Module](https://flax.readthedocs.io/en/latest/_autosummary/flax.nn.module.html) subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

* [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit)
* [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation)
* [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap)
* [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)

**\_\_call\_\_**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1176)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_input\_ids: typing.Optional\[jax.Array] = Nonedecoder\_attention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Nonedecoder\_position\_ids: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxSeq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqSequenceClassifierOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`, *optional*) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **position\_ids** (`numpy.ndarray` 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.max_position_embeddings - 1]`.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxSeq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqSequenceClassifierOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxSeq2SeqSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqSequenceClassifierOutput) 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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **logits** (`jnp.ndarray` of shape `(batch_size, config.num_labels)`) — Classification (or regression if config.num\_labels==1) scores (before SoftMax).
* **past\_key\_values** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
* **decoder\_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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** (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
* **encoder\_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

The `FlaxBartPreTrainedModel` forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base")
>>> model = FlaxBartForSequenceClassification.from_pretrained("facebook/bart-base")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="jax")

>>> outputs = model(**inputs)
>>> logits = outputs.logits
```

**encode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L999)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **position\_ids** (`numpy.ndarray` 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.max_position_embeddings - 1]`.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) 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 (`<class 'transformers.models.bart.configuration_bart.BartConfig'>`) and inputs.

* **last\_hidden\_state** (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **hidden\_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

Example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors="jax")
>>> encoder_outputs = model.encode(**inputs)
```

**decode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1062)

( decoder\_input\_idsencoder\_outputsencoder\_attention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_attention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_position\_ids: typing.Optional\[jax.Array] = Nonepast\_key\_values: dict = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) or `tuple(torch.FloatTensor)`

Parameters

* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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.
* **encoder\_outputs** (`tuple(tuple(jnp.ndarray)`) — 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.
* **encoder\_attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_attention\_mask** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **past\_key\_values** (`Dict[str, np.ndarray]`, *optional*, returned by `init_cache` or when passing previous `past_key_values`) — Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape *\[batch\_size, max\_length]*.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) 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 (`<class 'transformers.models.bart.configuration_bart.BartConfig'>`) and inputs.

* **last\_hidden\_state** (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer 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** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if `config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.
* **hidden\_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

Example:

Copied

```
>>> import jax.numpy as jnp
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors="jax")
>>> encoder_outputs = model.encode(**inputs)

>>> decoder_start_token_id = model.config.decoder_start_token_id
>>> decoder_input_ids = jnp.ones((inputs.input_ids.shape[0], 1), dtype="i4") * decoder_start_token_id

>>> outputs = model.decode(decoder_input_ids, encoder_outputs)
>>> last_decoder_hidden_states = outputs.last_hidden_state
```

### FlaxBartForQuestionAnswering

#### class transformers.FlaxBartForQuestionAnswering

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1724)

( config: BartConfiginput\_shape: typing.Tuple\[int] = (1, 1)seed: int = 0dtype: dtype = \<class 'jax.numpy.float32'>\_do\_init: bool = True\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights.
* **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) — The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs).

  This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`.

  **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.**

  If you wish to change the dtype of the model parameters, see [to\_fp16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to\_bf16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).

BART Model 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 [FlaxPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel). 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 Flax Linen [flax.nn.Module](https://flax.readthedocs.io/en/latest/_autosummary/flax.nn.module.html) subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

* [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit)
* [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation)
* [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap)
* [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)

**\_\_call\_\_**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1176)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_input\_ids: typing.Optional\[jax.Array] = Nonedecoder\_attention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Nonedecoder\_position\_ids: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxSeq2SeqQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqQuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`, *optional*) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **position\_ids** (`numpy.ndarray` 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.max_position_embeddings - 1]`.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxSeq2SeqQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqQuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxSeq2SeqQuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxSeq2SeqQuestionAnsweringModelOutput) 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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **start\_logits** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Span-start scores (before SoftMax).
* **end\_logits** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Span-end scores (before SoftMax).
* **past\_key\_values** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
* **decoder\_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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** (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
* **encoder\_attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

The `FlaxBartPreTrainedModel` forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartForQuestionAnswering

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base")
>>> model = FlaxBartForQuestionAnswering.from_pretrained("facebook/bart-base")

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
>>> inputs = tokenizer(question, text, return_tensors="jax")

>>> outputs = model(**inputs)
>>> start_scores = outputs.start_logits
>>> end_scores = outputs.end_logits
```

**encode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L999)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`jnp.ndarray` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **position\_ids** (`numpy.ndarray` 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.max_position_embeddings - 1]`.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxBaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutput) 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 (`<class 'transformers.models.bart.configuration_bart.BartConfig'>`) and inputs.

* **last\_hidden\_state** (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **hidden\_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

Example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors="jax")
>>> encoder_outputs = model.encode(**inputs)
```

**decode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1062)

( decoder\_input\_idsencoder\_outputsencoder\_attention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_attention\_mask: typing.Optional\[jax.Array] = Nonedecoder\_position\_ids: typing.Optional\[jax.Array] = Nonepast\_key\_values: dict = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) or `tuple(torch.FloatTensor)`

Parameters

* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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.
* **encoder\_outputs** (`tuple(tuple(jnp.ndarray)`) — 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.
* **encoder\_attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_attention\_mask** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **past\_key\_values** (`Dict[str, np.ndarray]`, *optional*, returned by `init_cache` or when passing previous `past_key_values`) — Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape *\[batch\_size, max\_length]*.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPastAndCrossAttentions) 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 (`<class 'transformers.models.bart.configuration_bart.BartConfig'>`) and inputs.

* **last\_hidden\_state** (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer 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** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if `config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  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.
* **hidden\_states** (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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.

Example:

Copied

```
>>> import jax.numpy as jnp
>>> from transformers import AutoTokenizer, FlaxBartForConditionalGeneration

>>> model = FlaxBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, max_length=1024, return_tensors="jax")
>>> encoder_outputs = model.encode(**inputs)

>>> decoder_start_token_id = model.config.decoder_start_token_id
>>> decoder_input_ids = jnp.ones((inputs.input_ids.shape[0], 1), dtype="i4") * decoder_start_token_id

>>> outputs = model.decode(decoder_input_ids, encoder_outputs)
>>> last_decoder_hidden_states = outputs.last_hidden_state
```

### FlaxBartForCausalLM

#### class transformers.FlaxBartForCausalLM

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1960)

( config: BartConfiginput\_shape: typing.Tuple\[int] = (1, 1)seed: int = 0dtype: dtype = \<class 'jax.numpy.float32'>\_do\_init: bool = True\*\*kwargs )

Parameters

* **config** ([BartConfig](https://huggingface.co/docs/transformers/v4.34.1/en/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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.from_pretrained) method to load the model weights.
* **dtype** (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`) — The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs).

  This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given `dtype`.

  **Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.**

  If you wish to change the dtype of the model parameters, see [to\_fp16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_fp16) and [to\_bf16()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel.to_bf16).

Bart Decoder Model with a language modeling head on top (linear layer with weights tied to the input embeddings) e.g for autoregressive tasks.

This model inherits from [FlaxPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.FlaxPreTrainedModel). 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 Flax Linen [flax.nn.Module](https://flax.readthedocs.io/en/latest/_autosummary/flax.nn.module.html) subclass. Use it as a regular Flax Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

* [Just-In-Time (JIT) compilation](https://jax.readthedocs.io/en/latest/jax.html#just-in-time-compilation-jit)
* [Automatic Differentiation](https://jax.readthedocs.io/en/latest/jax.html#automatic-differentiation)
* [Vectorization](https://jax.readthedocs.io/en/latest/jax.html#vectorization-vmap)
* [Parallelization](https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap)

**\_\_call\_\_**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bart/modeling_flax_bart.py#L1798)

( input\_ids: Arrayattention\_mask: typing.Optional\[jax.Array] = Noneposition\_ids: typing.Optional\[jax.Array] = Noneencoder\_hidden\_states: typing.Optional\[jax.Array] = Noneencoder\_attention\_mask: typing.Optional\[jax.Array] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonetrain: bool = Falseparams: dict = Nonepast\_key\_values: dict = Nonedropout\_rng: PRNGKey = None ) → [transformers.modeling\_flax\_outputs.FlaxCausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`

Parameters

* **decoder\_input\_ids** (`jnp.ndarray` of shape `(batch_size, target_sequence_length)`) — Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are decoder input IDs?](https://huggingface.co/docs/transformers/glossary#decoder-input-ids)

  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.
* **encoder\_outputs** (`tuple(tuple(jnp.ndarray)`) — 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.
* **encoder\_attention\_mask** (`jnp.ndarray` 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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **decoder\_attention\_mask** (`jnp.ndarray` 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 modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy.
* **decoder\_position\_ids** (`numpy.ndarray` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each decoder input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.
* **past\_key\_values** (`Dict[str, np.ndarray]`, *optional*, returned by `init_cache` or when passing previous `past_key_values`) — Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast auto-regressive decoding. Pre-computed key and value hidden-states are of shape *\[batch\_size, max\_length]*.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_flax\_outputs.FlaxCausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_flax\_outputs.FlaxCausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions) 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](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bart#transformers.BartConfig)) and inputs.

* **logits** (`jnp.ndarray` 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(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `jnp.ndarray` (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** (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `jnp.ndarray` tuples of length `config.n_layers`, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant if `config.is_decoder = True`.

  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.

The `FlaxBartDecoderPreTrainedModel` forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, FlaxBartForCausalLM

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/bart-base")
>>> model = FlaxBartForCausalLM.from_pretrained("facebook/bart-base")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="np")
>>> outputs = model(**inputs)

>>> # retrieve logts for next token
>>> next_token_logits = outputs.logits[:, -1]
```