# BigBirdPegasus

## BigBirdPegasus

### Overview

The BigBird model was proposed in [Big Bird: Transformers for Longer Sequences](https://arxiv.org/abs/2007.14062) by Zaheer, Manzil and Guruganesh, Guru and Dubey, Kumar Avinava and Ainslie, Joshua and Alberti, Chris and Ontanon, Santiago and Pham, Philip and Ravula, Anirudh and Wang, Qifan and Yang, Li and others. BigBird, is a sparse-attention based transformer which extends Transformer based models, such as BERT to much longer sequences. In addition to sparse attention, BigBird also applies global attention as well as random attention to the input sequence. Theoretically, it has been shown that applying sparse, global, and random attention approximates full attention, while being computationally much more efficient for longer sequences. As a consequence of the capability to handle longer context, BigBird has shown improved performance on various long document NLP tasks, such as question answering and summarization, compared to BERT or RoBERTa.

The abstract from the paper is the following:

*Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. We show that BigBird is a universal approximator of sequence functions and is Turing complete, thereby preserving these properties of the quadratic, full attention model. Along the way, our theoretical analysis reveals some of the benefits of having O(1) global tokens (such as CLS), that attend to the entire sequence as part of the sparse attention mechanism. The proposed sparse attention can handle sequences of length up to 8x of what was previously possible using similar hardware. As a consequence of the capability to handle longer context, BigBird drastically improves performance on various NLP tasks such as question answering and summarization. We also propose novel applications to genomics data.*

Tips:

* For an in-detail explanation on how BigBird’s attention works, see [this blog post](https://huggingface.co/blog/big-bird).
* BigBird comes with 2 implementations: **original\_full** & **block\_sparse**. For the sequence length < 1024, using **original\_full** is advised as there is no benefit in using **block\_sparse** attention.
* The code currently uses window size of 3 blocks and 2 global blocks.
* Sequence length must be divisible by block size.
* Current implementation supports only **ITC**.
* Current implementation doesn’t support **num\_random\_blocks = 0**.
* BigBirdPegasus uses the [PegasusTokenizer](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pegasus/tokenization_pegasus.py).
* BigBird is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

The original code can be found [here](https://github.com/google-research/bigbird).

### Documentation resources

* [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)
* [Translation task guide](https://huggingface.co/docs/transformers/tasks/translation)
* [Summarization task guide](https://huggingface.co/docs/transformers/tasks/summarization)

### BigBirdPegasusConfig

#### class transformers.BigBirdPegasusConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py#L43)

( vocab\_size = 96103max\_position\_embeddings = 4096encoder\_layers = 16encoder\_ffn\_dim = 4096encoder\_attention\_heads = 16decoder\_layers = 16decoder\_ffn\_dim = 4096decoder\_attention\_heads = 16encoder\_layerdrop = 0.0decoder\_layerdrop = 0.0use\_cache = Trueis\_encoder\_decoder = Trueactivation\_function = 'gelu\_new'd\_model = 1024dropout = 0.1attention\_dropout = 0.0activation\_dropout = 0.0init\_std = 0.02decoder\_start\_token\_id = 2classifier\_dropout = 0.0scale\_embedding = Truepad\_token\_id = 0bos\_token\_id = 2eos\_token\_id = 1attention\_type = 'block\_sparse'block\_size = 64num\_random\_blocks = 3use\_bias = False\*\*kwargs )

Parameters

* **vocab\_size** (`int`, *optional*, defaults to 96103) — Vocabulary size of the BigBirdPegasus model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [BigBirdPegasusModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusModel).
* **d\_model** (`int`, *optional*, defaults to 1024) — Dimension of the layers and the pooler layer.
* **encoder\_layers** (`int`, *optional*, defaults to 16) — Number of encoder layers.
* **decoder\_layers** (`int`, *optional*, defaults to 16) — 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) — Dimension of the “intermediate” (often named feed-forward) layer in decoder.
* **encoder\_ffn\_dim** (`int`, *optional*, defaults to 4096) — Dimension of the “intermediate” (often named feed-forward) layer in decoder.
* **activation\_function** (`str` or `function`, *optional*, defaults to `"gelu_new"`) — The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported.
* **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 4096) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 1024 or 2048 or 4096).
* **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.
* **use\_cache** (`bool`, *optional*, defaults to `True`) — Whether or not the model should return the last key/values attentions (not used by all models).
* **attention\_type** (`str`, *optional*, defaults to `"block_sparse"`) — Whether to use block sparse attention (with n complexity) as introduced in paper or original attention layer (with n^2 complexity) in encoder. Possible values are `"original_full"` and `"block_sparse"`.
* **use\_bias** (`bool`, *optional*, defaults to `False`) — Whether to use bias in query, key, value.
* **block\_size** (`int`, *optional*, defaults to 64) — Size of each block. Useful only when `attention_type == "block_sparse"`.
* **num\_random\_blocks** (`int`, *optional*, defaults to 3) — Each query is going to attend these many number of random blocks. Useful only when `attention_type == "block_sparse"`.
* **scale\_embeddings** (`bool`, *optional*, defaults to `True`) — Whether to rescale embeddings with (hidden\_size \*\* 0.5).

This is the configuration class to store the configuration of a [BigBirdPegasusModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusModel). It is used to instantiate an BigBirdPegasus 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 BigBirdPegasus [google/bigbird-pegasus-large-arxiv](https://huggingface.co/google/bigbird-pegasus-large-arxiv) 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 BigBirdPegasusConfig, BigBirdPegasusModel

>>> # Initializing a BigBirdPegasus bigbird-pegasus-base style configuration
>>> configuration = BigBirdPegasusConfig()

>>> # Initializing a model (with random weights) from the bigbird-pegasus-base style configuration
>>> model = BigBirdPegasusModel(configuration)

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

### BigBirdPegasusModel

#### class transformers.BigBirdPegasusModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py#L2361)

( config: BigBirdPegasusConfig )

Parameters

* **config** ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) — 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 BigBirdPegasus 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 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/bigbird_pegasus/modeling_bigbird_pegasus.py#L2390)

( 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*) — Provide for translation and summarization training. By default, the model will create this tensor by shifting the `input_ids` to the right, 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_bigbird_pegasus._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.
* **decoder\_head\_mask** (`torch.Tensor` of shape `(num_layers, num_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**.
* **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 ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) 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 [BigBirdPegasusModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusModel) 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, BigBirdPegasusModel
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-pegasus-large-arxiv")
>>> model = BigBirdPegasusModel.from_pretrained("google/bigbird-pegasus-large-arxiv")

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

>>> last_hidden_states = outputs.last_hidden_state
```

### BigBirdPegasusForConditionalGeneration

#### class transformers.BigBirdPegasusForConditionalGeneration

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py#L2491)

( config: BigBirdPegasusConfig )

Parameters

* **config** ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) — 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 BigBirdPegasus 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 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/bigbird_pegasus/modeling_bigbird_pegasus.py#L2531)

( 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*) — Provide for translation and summarization training. By default, the model will create this tensor by shifting the `input_ids` to the right, 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_bigbird_pegasus._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.
* **decoder\_head\_mask** (`torch.Tensor` of shape `(num_layers, num_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**.
* **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 ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) 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 [BigBirdPegasusForConditionalGeneration](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusForConditionalGeneration) 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, BigBirdPegasusForConditionalGeneration

>>> model = BigBirdPegasusForConditionalGeneration.from_pretrained("google/bigbird-pegasus-large-arxiv")
>>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-pegasus-large-arxiv")

>>> ARTICLE_TO_SUMMARIZE = (
...     "The dominant sequence transduction models are based on complex recurrent or convolutional neural "
...     "networks in an encoder-decoder configuration. The best performing models also connect the encoder "
...     "and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, "
...     "based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. "
...     "Experiments on two machine translation tasks show these models to be superior in quality "
...     "while being more parallelizable and requiring significantly less time to train."
... )
>>> inputs = tokenizer([ARTICLE_TO_SUMMARIZE], max_length=4096, return_tensors="pt", truncation=True)

>>> # Generate Summary
>>> summary_ids = model.generate(inputs["input_ids"], num_beams=4, max_length=15)
>>> tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
'dominant sequence models are based on recurrent or convolutional neural networks .'
```

### BigBirdPegasusForSequenceClassification

#### class transformers.BigBirdPegasusForSequenceClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py#L2667)

( config: BigBirdPegasusConfig\*\*kwargs )

Parameters

* **config** ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) — 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.

BigBirdPegasus 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 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/bigbird_pegasus/modeling_bigbird_pegasus.py#L2683)

( 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*) — Provide for translation and summarization training. By default, the model will create this tensor by shifting the `input_ids` to the right, 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_bigbird_pegasus._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.
* **decoder\_head\_mask** (`torch.Tensor` of shape `(num_layers, num_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**.
* **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 ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) 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 [BigBirdPegasusForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusForSequenceClassification) 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, BigBirdPegasusForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-pegasus-large-arxiv")
>>> model = BigBirdPegasusForSequenceClassification.from_pretrained("google/bigbird-pegasus-large-arxiv")

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

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_id = logits.argmax().item()

>>> # 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 = BigBirdPegasusForSequenceClassification.from_pretrained("google/bigbird-pegasus-large-arxiv", num_labels=num_labels)

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

Example of multi-label classification:

Copied

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

>>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-pegasus-large-arxiv")
>>> model = BigBirdPegasusForSequenceClassification.from_pretrained("google/bigbird-pegasus-large-arxiv", 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 = BigBirdPegasusForSequenceClassification.from_pretrained(
...     "google/bigbird-pegasus-large-arxiv", 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
```

### BigBirdPegasusForQuestionAnswering

#### class transformers.BigBirdPegasusForQuestionAnswering

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py#L2796)

( config )

Parameters

* **config** ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) — 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.

BigBirdPegasus 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 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/bigbird_pegasus/modeling_bigbird_pegasus.py#L2811)

( 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*) — Provide for translation and summarization training. By default, the model will create this tensor by shifting the `input_ids` to the right, 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_bigbird_pegasus._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.
* **decoder\_head\_mask** (`torch.Tensor` of shape `(num_layers, num_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**.
* **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 ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) 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 [BigBirdPegasusForQuestionAnswering](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusForQuestionAnswering) 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, BigBirdPegasusForQuestionAnswering
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-pegasus-large-arxiv")
>>> model = BigBirdPegasusForQuestionAnswering.from_pretrained("google/bigbird-pegasus-large-arxiv")

>>> 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]

>>> # 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
```

### BigBirdPegasusForCausalLM

#### class transformers.BigBirdPegasusForCausalLM

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py#L2928)

( config )

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py#L2961)

( 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.Tuple\[typing.Tuple\[torch.Tensor]]] = 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 ([BigBirdPegasusConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bigbird_pegasus#transformers.BigBirdPegasusConfig)) 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, BigBirdPegasusForCausalLM

>>> tokenizer = AutoTokenizer.from_pretrained("google/bigbird-pegasus-large-arxiv")
>>> model = BigBirdPegasusForCausalLM.from_pretrained(
...     "google/bigbird-pegasus-large-arxiv", 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
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://boinc-ai.gitbook.io/transformers/api/models/text-models/bigbirdpegasus.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.