Transformers documentation

LongT5

Join the Hugging Face community

to get started

# LongT5

## Overview

The LongT5 model was proposed in LongT5: Efficient Text-To-Text Transformer for Long Sequences by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung and Yinfei Yang. It’s an encoder-decoder transformer pre-trained in a text-to-text denoising generative setting. LongT5 model is an extension of T5 model, and it enables using one of the two different efficient attention mechanisms - (1) Local attention, or (2) Transient-Global attention.

The abstract from the paper is the following:

Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models. In this paper, we present a new model, called LongT5, with which we explore the effects of scaling both the input length and model size at the same time. Specifically, we integrated attention ideas from long-input transformers (ETC), and adopted pre-training strategies from summarization pre-training (PEGASUS) into the scalable T5 architecture. The result is a new attention mechanism we call {\em Transient Global} (TGlobal), which mimics ETC’s local/global attention mechanism, but without requiring additional side-inputs. We are able to achieve state-of-the-art results on several summarization tasks and outperform the original T5 models on question answering tasks.

Tips:

• LongT5ForConditionalGeneration is an extension of T5ForConditionalGeneration exchanging the traditional encoder self-attention layer with efficient either local attention or transient-global (tglobal) attention.
• Unlike the T5 model, LongT5 does not use a task prefix. Furthermore, it uses a different pre-training objective inspired by the pre-training of [PegasusForConditionalGeneration].
• LongT5 model is designed to work efficiently and very well on long-range sequence-to-sequence tasks where the input sequence exceeds commonly used 512 tokens. It is capable of handling input sequences of a length up to 16,384 tokens.
• For Local Attention, the sparse sliding-window local attention operation allows a given token to attend only r tokens to the left and right of it (with r=127 by default). Local Attention does not introduce any new parameters to the model. The complexity of the mechanism is linear in input sequence length l: O(l*r).
• Transient Global Attention is an extension of the Local Attention. It, furthermore, allows each input token to interact with all other tokens in the layer. This is achieved via splitting an input sequence into blocks of a fixed length k (with a default k=16). Then, a global token for such a block is obtained via summing and normalizing the embeddings of every token in the block. Thanks to this, the attention allows each token to attend to both nearby tokens like in Local attention, and also every global token like in the case of standard global attention (transient represents the fact the global tokens are constructed dynamically within each attention operation). As a consequence, TGlobal attention introduces a few new parameters — global relative position biases and a layer normalization for global token’s embedding. The complexity of this mechanism is O(l(r + l/k)).
• An example showing how to evaluate a fine-tuned LongT5 model on the pubmed dataset is below.
>>> import evaluate
>>> from transformers import AutoTokenizer, LongT5ForConditionalGeneration

>>> dataset = load_dataset("scientific_papers", "pubmed", split="validation")
>>> model = (
...     LongT5ForConditionalGeneration.from_pretrained("Stancld/longt5-tglobal-large-16384-pubmed-3k_steps")
...     .to("cuda")
...     .half()
... )
>>> tokenizer = AutoTokenizer.from_pretrained("Stancld/longt5-tglobal-large-16384-pubmed-3k_steps")

...     inputs_dict = tokenizer(
...         batch["article"], max_length=16384, padding="max_length", truncation=True, return_tensors="pt"
...     )
...     input_ids = inputs_dict.input_ids.to("cuda")
...     batch["predicted_abstract"] = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
...     return batch

>>> result = dataset.map(generate_answer, batched=True, batch_size=2)
>>> rouge.compute(predictions=result["predicted_abstract"], references=result["abstract"])

This model was contributed by stancld. The original code can be found here.

## LongT5Config

### class transformers.LongT5Config

< >

( vocab_size = 32128 d_model = 512 d_kv = 64 d_ff = 2048 num_layers = 6 num_decoder_layers = None num_heads = 8 local_radius = 127 global_block_size = 16 relative_attention_num_buckets = 32 relative_attention_max_distance = 128 dropout_rate = 0.1 layer_norm_epsilon = 1e-06 initializer_factor = 1.0 feed_forward_proj = 'relu' is_encoder_decoder = True encoder_attention_type = 'local' use_cache = True pad_token_id = 0 eos_token_id = 1 **kwargs )

Parameters

• vocab_size (int, optional, defaults to 32128) — Vocabulary size of the LongT5 model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling LongT5Model.
• d_model (int, optional, defaults to 512) — Size of the encoder layers and the pooler layer.
• d_kv (int, optional, defaults to 64) — Size of the key, query, value projections per attention head. d_kv has to be equal to d_model // num_heads.
• d_ff (int, optional, defaults to 2048) — Size of the intermediate feed forward layer in each LongT5Block.
• num_layers (int, optional, defaults to 6) — Number of hidden layers in the Transformer encoder.
• num_decoder_layers (int, optional) — Number of hidden layers in the Transformer decoder. Will use the same value as num_layers if not set.
• num_heads (int, optional, defaults to 8) — Number of attention heads for each attention layer in the Transformer encoder.
• local_radius (int, optional, defaults to 127) — Number of tokens to the left/right for each token to locally self-attend in a local attention mechanism.
• global_block_size (int, optional, defaults to 16) — Lenght of blocks an input sequence is divided into for a global token representation. Used only for encoder_attention_type = "transient-global".
• relative_attention_num_buckets (int, optional, defaults to 32) — The number of buckets to use for each attention layer.
• relative_attention_max_distance (int, optional, defaults to 128) — The maximum distance of the longer sequences for the bucket separation.
• dropout_rate (float, optional, defaults to 0.1) — The ratio for all dropout layers.
• layer_norm_eps (float, optional, defaults to 1e-6) — The epsilon used by the layer normalization layers.
• initializer_factor (float, optional, defaults to 1) — A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing).
• feed_forward_proj (string, optional, defaults to "relu") — Type of feed forward layer to be used. Should be one of "relu" or "gated-gelu". LongT5v1.1 uses the "gated-gelu" feed forward projection. Original LongT5 implementation uses "gated-gelu".
• encoder_attention_type (string, optional, defaults to "local") — Type of encoder attention to be used. Should be one of "local" or "transient-global", which are supported by LongT5 implementation.
• use_cache (bool, optional, defaults to True) — Whether or not the model should return the last key/values attentions (not used by all models).

This is the configuration class to store the configuration of a LongT5Model or a FlaxLongT5Model. It is used to instantiate a LongT5 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 LongT5 google/long-t5-local-base architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

## LongT5Model

### class transformers.LongT5Model

< >

( config: LongT5Config )

Parameters

• config (LongT5Config) — 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() method to load the model weights.

The bare LONGT5 Model transformer outputting raw hidden-states without any specific head on top.

The LongT5 model was proposed in LongT5: Efficient Text-To-Text Transformer for Long Sequences by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung and Yinfei Yang. It’s an encoder-decoder transformer pre-trained in a text-to-text denoising generative setting. LongT5 model is an extension of T5 model, and it enables using one of the two different efficient attention mechanisms - (1) Local attention, or (2) Transient-Global attention.

This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

#### forward

< >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None decoder_input_ids: typing.Optional[torch.LongTensor] = None decoder_attention_mask: typing.Optional[torch.BoolTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None decoder_head_mask: typing.Optional[torch.FloatTensor] = None cross_attn_head_mask: typing.Optional[torch.Tensor] = None encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None inputs_embeds: typing.Optional[torch.Tensor] = None decoder_inputs_embeds: typing.Optional[torch.Tensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) 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. LongT5 is a model with relative position embeddings so you should be able to pad the inputs on both the right and the left.

Indices can be obtained using T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for detail.

What are input IDs?

To know more on how to prepare input_ids for pretraining take a look a LONGT5 Training.

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

• 1 for tokens that are not masked,
• 0 for tokens that are masked.

• 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 T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are decoder input IDs?

LONGT5 uses the pad_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).

To know more on how to prepare decoder_input_ids for pretraining take a look at LONGT5 Training.

• decoder_attention_mask (torch.BoolTensor 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.
• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules in the encoder. Mask values selected in [0, 1]:

• decoder_head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules in the decoder. Mask values selected in [0, 1]:

• cross_attn_head_mask (torch.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in [0, 1]:

• 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) 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)) of length config.n_layers with each tuple having 4 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)) — 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).

• 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 instead of a plain tuple.

Returns

transformers.modeling_outputs.Seq2SeqModelOutput or tuple(torch.FloatTensor)

A 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 (LongT5Config) 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 LongT5Model 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:

>>> from transformers import T5Tokenizer, LongT5Model

>>> # Let's try a very long encoder input.
>>> input_ids = tokenizer(
...     100 * "Studies have been shown that owning a dog is good for you", return_tensors="pt"
... ).input_ids  # Batch size 1

>>> decoder_input_ids = tokenizer("Studies show that", return_tensors="pt").input_ids  # Batch size 1

>>> # forward pass
>>> outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)
>>> last_hidden_states = outputs.last_hidden_state

## LongT5ForConditionalGeneration

### class transformers.LongT5ForConditionalGeneration

< >

( config: LongT5Config )

Parameters

• config (LongT5Config) — 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() method to load the model weights.

LONGT5 Model with a language modeling head on top.

The LongT5 model was proposed in LongT5: Efficient Text-To-Text Transformer for Long Sequences by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung and Yinfei Yang. It’s an encoder-decoder transformer pre-trained in a text-to-text denoising generative setting. LongT5 model is an extension of T5 model, and it enables using one of the two different efficient attention mechanisms - (1) Local attention, or (2) Transient-Global attention.

This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

#### forward

< >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None decoder_input_ids: typing.Optional[torch.LongTensor] = None decoder_attention_mask: typing.Optional[torch.BoolTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None decoder_head_mask: typing.Optional[torch.FloatTensor] = None cross_attn_head_mask: typing.Optional[torch.Tensor] = None encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None decoder_inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) 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. LongT5 is a model with relative position embeddings so you should be able to pad the inputs on both the right and the left.

Indices can be obtained using T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for detail.

What are input IDs?

To know more on how to prepare input_ids for pretraining take a look a LONGT5 Training.

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

• 1 for tokens that are not masked,
• 0 for tokens that are masked.

• 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 T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are decoder input IDs?

LONGT5 uses the pad_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).

To know more on how to prepare decoder_input_ids for pretraining take a look at LONGT5 Training.

• decoder_attention_mask (torch.BoolTensor 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.
• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules in the encoder. Mask values selected in [0, 1]:

• decoder_head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules in the decoder. Mask values selected in [0, 1]:

• cross_attn_head_mask (torch.Tensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the cross-attention modules in the decoder. Mask values selected in [0, 1]:

• 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) 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)) of length config.n_layers with each tuple having 4 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)) — 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).

• 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 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 [-100, 0, ..., config.vocab_size - 1]. All labels set to -100 are ignored (masked), the loss is only computed for labels in [0, ..., config.vocab_size]

Returns

transformers.modeling_outputs.Seq2SeqLMOutput or tuple(torch.FloatTensor)

A 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 (LongT5Config) 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 LongT5ForConditionalGeneration 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.

Examples:

>>> from transformers import AutoTokenizer, LongT5ForConditionalGeneration

>>> tokenizer = AutoTokenizer.from_pretrained("Stancld/longt5-tglobal-large-16384-pubmed-3k_steps")
>>> model = LongT5ForConditionalGeneration.from_pretrained(
...     "Stancld/longt5-tglobal-large-16384-pubmed-3k_steps"
... )

>>> # Let's try a very long input.
>>> input_ids = tokenizer(
...     "summarize: " + 100 * "studies have shown that owning a dog is good for you ", return_tensors="pt"
... ).input_ids  # Batch size 1

>>> outputs = model.generate(input_ids)
>>> print(tokenizer.decode(outputs[0], skip_special_tokens=True))
abstractthe aim of this article is to summarize the studies have shown that owning a dog

## LongT5EncoderModel

### class transformers.LongT5EncoderModel

< >

( config: LongT5Config )

Parameters

• config (LongT5Config) — 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() method to load the model weights.

The bare LONGT5 Model transformer outputting encoder’s raw hidden-states without any specific head on top.

The LongT5 model was proposed in LongT5: Efficient Text-To-Text Transformer for Long Sequences by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung and Yinfei Yang. It’s an encoder-decoder transformer pre-trained in a text-to-text denoising generative setting. LongT5 model is an extension of T5 model, and it enables using one of the two different efficient attention mechanisms - (1) Local attention, or (2) Transient-Global attention.

This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

#### forward

< >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) transformers.modeling_outputs.BaseModelOutput or tuple(torch.FloatTensor)

Parameters

• input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. LongT5 is a model with relative position embeddings so you should be able to pad the inputs on both the right and the left.

Indices can be obtained using T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for detail.

To know more on how to prepare input_ids for pretraining take a look a LONGT5 Training.

• attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

• 1 for tokens that are not masked,
• 0 for tokens that are masked.

• head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:

• 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.
• 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 instead of a plain tuple.

Returns

transformers.modeling_outputs.BaseModelOutput or tuple(torch.FloatTensor)

A transformers.modeling_outputs.BaseModelOutput 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 (LongT5Config) 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 model.

• hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

• attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

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

The LongT5EncoderModel 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:

>>> from transformers import AutoTokenizer, LongT5ForConditionalGeneration

>>> input_ids = tokenizer(
...     100 * "Studies have been shown that owning a dog is good for you ", return_tensors="pt"
... ).input_ids  # Batch size 1
>>> outputs = model(input_ids=input_ids)
>>> last_hidden_states = outputs.last_hidden_state

## FlaxLongT5Model

### class transformers.FlaxLongT5Model

< >

( config: LongT5Config input_shape: typing.Tuple[int] = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True **kwargs )

#### __call__

< >

( input_ids: ndarray attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None decoder_input_ids: ndarray = None decoder_attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None train: bool = False params: dict = None dropout_rng: PRNGKey = None ) 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. LongT5 is a model with relative position embeddings so you should be able to pad the inputs on both the right and the left.

Indices can be obtained using T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for detail.

What are input IDs?

To know more on how to prepare input_ids for pretraining take a look a LONGT5 Training.

• 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.

• 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 T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are decoder input IDs?

LONGT5 uses the pad_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).

To know more on how to prepare decoder_input_ids for pretraining take a look at LONGT5 Training.

• 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.
• encoder_outputs (tuple(tuple(jnp.ndarray), optional) — Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size) 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(jnp.ndarray)) of length config.n_layers with each tuple having 4 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)) — 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).

Returns

transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput or tuple(torch.FloatTensor)

A 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 (LongT5Config) 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 FlaxLongT5PreTrainedModel 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:

>>> from transformers import T5Tokenizer, FlaxLongT5Model

>>> tokenizer = T5Tokenizer.from_pretrained("t5-base")

>>> input_ids = tokenizer(
...     "Studies have been shown that owning a dog is good for you", return_tensors="np"
... ).input_ids
>>> decoder_input_ids = tokenizer("Studies show that", return_tensors="np").input_ids

>>> # forward pass
>>> outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)
>>> last_hidden_states = outputs.last_hidden_state

#### encode

< >

( input_ids: ndarray attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None train: bool = False params: dict = None dropout_rng: PRNGKey = None ) 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. LongT5 is a model with relative position embeddings so you should be able to pad the inputs on both the right and the left.

Indices can be obtained using T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for detail.

To know more on how to prepare input_ids for pretraining take a look a LONGT5 Training.

• 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.

• 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 instead of a plain tuple.

Returns

transformers.modeling_flax_outputs.FlaxBaseModelOutput or tuple(torch.FloatTensor)

A 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.longt5.configuration_longt5.LongT5Config'>) 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:

>>> from transformers import T5Tokenizer, FlaxLongT5ForConditionalGeneration

>>> tokenizer = T5Tokenizer.from_pretrained("t5-base")

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

#### decode

< >

( decoder_input_ids encoder_outputs encoder_attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None decoder_attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None past_key_values: dict = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None train: bool = False params: dict = None dropout_rng: PRNGKey = None ) 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 T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are decoder input IDs?

For training, decoder_input_ids should be provided.

• 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.

• 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 for more information on the default strategy.

• 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 instead of a plain tuple.

A 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.longt5.configuration_longt5.LongT5Config'>) 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:

>>> from transformers import T5Tokenizer, FlaxLongT5ForConditionalGeneration
>>> import jax.numpy as jnp

>>> tokenizer = T5Tokenizer.from_pretrained("t5-base")

>>> text = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer(text, return_tensors="np")
>>> 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

## FlaxLongT5ForConditionalGeneration

### class transformers.FlaxLongT5ForConditionalGeneration

< >

( config: LongT5Config input_shape: typing.Tuple[int] = (1, 1) seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True **kwargs )

#### __call__

< >

( input_ids: ndarray attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None decoder_input_ids: ndarray = None decoder_attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None train: bool = False params: dict = None dropout_rng: PRNGKey = None ) 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. LongT5 is a model with relative position embeddings so you should be able to pad the inputs on both the right and the left.

Indices can be obtained using T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for detail.

What are input IDs?

To know more on how to prepare input_ids for pretraining take a look a LONGT5 Training.

• 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.

• 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 T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are decoder input IDs?

LONGT5 uses the pad_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).

To know more on how to prepare decoder_input_ids for pretraining take a look at LONGT5 Training.

• 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.
• encoder_outputs (tuple(tuple(jnp.ndarray), optional) — Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size) 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(jnp.ndarray)) of length config.n_layers with each tuple having 4 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)) — 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).

Returns

transformers.modeling_flax_outputs.FlaxSeq2SeqLMOutput or tuple(torch.FloatTensor)

A 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 (LongT5Config) 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 FlaxLongT5PreTrainedModel 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:

>>> from transformers import T5Tokenizer, FlaxLongT5ForConditionalGeneration

>>> tokenizer = T5Tokenizer.from_pretrained("t5-base")

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

>>> # Generate Summary
>>> summary_ids = model.generate(inputs["input_ids"]).sequences
>>> print(tokenizer.decode(summary_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False))

#### encode

< >

( input_ids: ndarray attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None train: bool = False params: dict = None dropout_rng: PRNGKey = None ) 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. LongT5 is a model with relative position embeddings so you should be able to pad the inputs on both the right and the left.

Indices can be obtained using T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for detail.

To know more on how to prepare input_ids for pretraining take a look a LONGT5 Training.

• 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.

• 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 instead of a plain tuple.

Returns

transformers.modeling_flax_outputs.FlaxBaseModelOutput or tuple(torch.FloatTensor)

A 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.longt5.configuration_longt5.LongT5Config'>) 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:

>>> from transformers import T5Tokenizer, FlaxLongT5ForConditionalGeneration

>>> tokenizer = T5Tokenizer.from_pretrained("t5-base")

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

#### decode

< >

( decoder_input_ids encoder_outputs encoder_attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None decoder_attention_mask: typing.Optional[jax._src.numpy.ndarray.ndarray] = None past_key_values: dict = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None train: bool = False params: dict = None dropout_rng: PRNGKey = None ) 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 T5Tokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are decoder input IDs?

For training, decoder_input_ids should be provided.

• 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.

• 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 for more information on the default strategy.

• 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 instead of a plain tuple.

Returns

transformers.modeling_flax_outputs.FlaxCausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)

A 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.longt5.configuration_longt5.LongT5Config'>) 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:

>>> from transformers import T5Tokenizer, FlaxLongT5ForConditionalGeneration
>>> import jax.numpy as jnp

>>> tokenizer = T5Tokenizer.from_pretrained("t5-base")
>>> logits = outputs.logits