transformers documentation

T5

# T5

## Overview

The T5 model was presented in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu.

The abstract from the paper is the following:

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. Our systematic study compares pretraining objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new “Colossal Clean Crawled Corpus”, we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code.

Tips:

• T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format. T5 works well on a variety of tasks out-of-the-box by prepending a different prefix to the input corresponding to each task, e.g., for translation: translate English to German: …, for summarization: summarize: ….

• T5 uses relative scalar embeddings. Encoder input padding can be done on the left and on the right.

• See the training, inference and scripts sections below for all details regarding usage.

T5 comes in different sizes:

Based on the original T5 model, Google has released some follow-up works:

• T5v1.1: T5v1.1 is an improved version of T5 with some architectural tweaks, and is pre-trained on C4 only without mixing in the supervised tasks. Refer to the documentation of T5v1.1 which can be found here.

• mT5: mT5 is a multilingual T5 model. It is pre-trained on the mC4 corpus, which includes 101 languages. Refer to the documentation of mT5 which can be found here.

• byT5: byT5 is a T5 model pre-trained on byte sequences rather than SentencePiece subword token sequences. Refer to the documentation of byT5 which can be found here.

All checkpoints can be found on the hub.

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

## Training

T5 is an encoder-decoder model and converts all NLP problems into a text-to-text format. It is trained using teacher forcing. This means that for training, we always need an input sequence and a corresponding target sequence. The input sequence is fed to the model using input_ids. The target sequence is shifted to the right, i.e., prepended by a start-sequence token and fed to the decoder using the decoder_input_ids. In teacher-forcing style, the target sequence is then appended by the EOS token and corresponds to the labels. The PAD token is hereby used as the start-sequence token. T5 can be trained / fine-tuned both in a supervised and unsupervised fashion.

One can use T5ForConditionalGeneration (or the Tensorflow/Flax variant), which includes the language modeling head on top of the decoder.

• Unsupervised denoising training

In this setup, spans of the input sequence are masked by so-called sentinel tokens (a.k.a unique mask tokens) and the output sequence is formed as a concatenation of the same sentinel tokens and the real masked tokens. Each sentinel token represents a unique mask token for this sentence and should start with <extra_id_0>, <extra_id_1>, … up to <extra_id_99>. As a default, 100 sentinel tokens are available in T5Tokenizer.

For instance, the sentence “The cute dog walks in the park” with the masks put on “cute dog” and “the” should be processed as follows:

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("t5-small")
model = T5ForConditionalGeneration.from_pretrained("t5-small")

input_ids = tokenizer("The <extra_id_0> walks in <extra_id_1> park", return_tensors="pt").input_ids
labels = tokenizer("<extra_id_0> cute dog <extra_id_1> the <extra_id_2>", return_tensors="pt").input_ids
# the forward function automatically creates the correct decoder_input_ids
loss = model(input_ids=input_ids, labels=labels).loss

If you’re interested in pre-training T5 on a new corpus, check out the run_t5_mlm_flax.py script in the Examples directory.

• Supervised training

In this setup, the input sequence and output sequence are a standard sequence-to-sequence input-output mapping. Suppose that we want to fine-tune the model for translation for example, and we have a training example: the input sequence “The house is wonderful.” and output sequence “Das Haus ist wunderbar.”, then they should be prepared for the model as follows:

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("t5-small")
model = T5ForConditionalGeneration.from_pretrained("t5-small")

input_ids = tokenizer("translate English to German: The house is wonderful.", return_tensors="pt").input_ids
labels = tokenizer("Das Haus ist wunderbar.", return_tensors="pt").input_ids
# the forward function automatically creates the correct decoder_input_ids
loss = model(input_ids=input_ids, labels=labels).loss

As you can see, only 2 inputs are required for the model in order to compute a loss: input_ids (which are the input_ids of the encoded input sequence) and labels (which are the input_ids of the encoded target sequence). The model will automatically create the decoder_input_ids based on the labels, by shifting them one position to the right and prepending the config.decoder_start_token_id, which for T5 is equal to 0 (i.e. the id of the pad token). Also note the task prefix: we prepend the input sequence with ‘translate English to German: ’ before encoding it. This will help in improving the performance, as this task prefix was used during T5’s pre-training.

However, the example above only shows a single training example. In practice, one trains deep learning models in batches. This entails that we must pad/truncate examples to the same length. For encoder-decoder models, one typically defines a max_source_length and max_target_length, which determine the maximum length of the input and output sequences respectively (otherwise they are truncated). These should be carefully set depending on the task.

In addition, we must make sure that padding token id’s of the labels are not taken into account by the loss function. In PyTorch and Tensorflow, this can be done by replacing them with -100, which is the ignore_index of the CrossEntropyLoss. In Flax, one can use the decoder_attention_mask to ignore padded tokens from the loss (see the Flax summarization script for details). We also pass attention_mask as additional input to the model, which makes sure that padding tokens of the inputs are ignored. The code example below illustrates all of this.

from transformers import T5Tokenizer, T5ForConditionalGeneration
import torch

tokenizer = T5Tokenizer.from_pretrained("t5-small")
model = T5ForConditionalGeneration.from_pretrained("t5-small")

# the following 2 hyperparameters are task-specific
max_source_length = 512
max_target_length = 128

# Suppose we have the following 2 training examples:
input_sequence_1 = "Welcome to NYC"
output_sequence_1 = "Bienvenue à NYC"

input_sequence_2 = "HuggingFace is a company"
output_sequence_2 = "HuggingFace est une entreprise"

# encode the inputs
task_prefix = "translate English to French: "
input_sequences = [input_sequence_1, input_sequence_2]
encoding = tokenizer(
[task_prefix + sequence for sequence in input_sequences],
max_length=max_source_length,
truncation=True,
return_tensors="pt",
)

# encode the targets
target_encoding = tokenizer(
[output_sequence_1, output_sequence_2], padding="longest", max_length=max_target_length, truncation=True
)
labels = target_encoding.input_ids

# replace padding token id's of the labels by -100
labels = torch.tensor(labels)
labels[labels == tokenizer.pad_token_id] = -100

# forward pass
loss = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels).loss

• T5 models need a slightly higher learning rate than the default one set in the Trainer when using the AdamW optimizer. Typically, 1e-4 and 3e-4 work well for most problems (classification, summarization, translation, question answering, question generation). Note that T5 was pre-trained using the AdaFactor optimizer.

• According to this forum post, task prefixes matter when (1) doing multi-task training (2) your task is similar or related to one of the supervised tasks used in T5’s pre-training mixture (see Appendix D of the paper for the task prefixes used).

• If training on TPU, it is recommended to pad all examples of the dataset to the same length or make use of pad_to_multiple_of to have a small number of predefined bucket sizes to fit all examples in. Dynamically padding batches to the longest example is not recommended on TPU as it triggers a recompilation for every batch shape that is encountered during training thus significantly slowing down the training. only padding up to the longest example in a batch) leads to very slow training on TPU.

## Inference

At inference time, it is recommended to use generate(). This method takes care of encoding the input and feeding the encoded hidden states via cross-attention layers to the decoder and auto-regressively generates the decoder output. Check out this blog post to know all the details about generating text with Transformers. There’s also this blog post which explains how generation works in general in encoder-decoder models.

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("t5-small")
model = T5ForConditionalGeneration.from_pretrained("t5-small")

input_ids = tokenizer("translate English to German: The house is wonderful.", return_tensors="pt").input_ids
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
# Das Haus ist wunderbar.

Note that T5 uses the pad_token_id as the decoder_start_token_id, so when doing generation without using generate(), make sure you start it with the pad_token_id.

The example above only shows a single example. You can also do batched inference, like so:

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("t5-small")
model = T5ForConditionalGeneration.from_pretrained("t5-small")

# when generating, we will use the logits of right-most token to predict the next token
# so the padding should be on the left
tokenizer.pad_token = tokenizer.eos_token  # to avoid an error

task_prefix = "translate English to German: "
sentences = ["The house is wonderful.", "I like to work in NYC."]  # use different length sentences to test batching
inputs = tokenizer([task_prefix + sentence for sentence in sentences], return_tensors="pt", padding=True)

output_sequences = model.generate(
input_ids=inputs["input_ids"],
do_sample=False,  # disable sampling to test if batching affects output
)

print(tokenizer.batch_decode(output_sequences, skip_special_tokens=True))

# ['Das Haus ist wunderbar.', 'Ich arbeite gerne in NYC.']

## Example scripts

T5 is supported by several example scripts, both for pre-training and fine-tuning.

• pre-training: the run_t5_mlm_flax.py script allows you to further pre-train T5 or pre-train T5 from scratch on your own data. The t5_tokenizer_model.py script allows you to further train a T5 tokenizer or train a T5 Tokenizer from scratch on your own data. Note that Flax (a neural network library on top of JAX) is particularly useful to train on TPU hardware.

• fine-tuning: T5 is supported by the official summarization scripts (PyTorch, Tensorflow, and Flax) and translation scripts (PyTorch and Tensorflow). These scripts allow you to easily fine-tune T5 on custom data for summarization/translation.

## T5Config

class transformers.T5Config < >

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

Parameters

• vocab_size (int, optional, defaults to 32128) — Vocabulary size of the T5 model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling T5Model or TFT5Model.
• 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 T5Block.
• 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.
• relative_attention_num_buckets (int, optional, defaults to 32) — The number of buckets to use for each attention layer.
• 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". T5v1.1 uses the "gated-gelu" feed forward projection. Original T5 uses "relu".
• 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 T5Model or a TFT5Model. It is used to instantiate a T5 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 T5 t5-small architecture.

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

## T5Tokenizer

class transformers.T5Tokenizer < >

( vocab_file eos_token = '</s>' unk_token = '<unk>' pad_token = '<pad>' extra_ids = 100 additional_special_tokens = None sp_model_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None **kwargs )

Parameters

• vocab_file (str) — SentencePiece file (generally has a .spm extension) that contains the vocabulary necessary to instantiate a tokenizer.
• eos_token (str, optional, defaults to "</s>") — The end of sequence token.

When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the sep_token.

• unk_token (str, optional, defaults to "<unk>") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
• pad_token (str, optional, defaults to "<pad>") — The token used for padding, for example when batching sequences of different lengths.
• extra_ids (int, optional, defaults to 100) — Add a number of extra ids added to the end of the vocabulary for use as sentinels. These tokens are accessible as “id{%d}>” where ”{%d}” is a number between 0 and extra_ids-1. Extra tokens are indexed from the end of the vocabulary up to beginning (“” is the last token in the vocabulary like in T5 preprocessing see here).
• additional_special_tokens (List[str], optional) — Additional special tokens used by the tokenizer.
• sp_model_kwargs (dict, optional) — Will be passed to the SentencePieceProcessor.__init__() method. The Python wrapper for SentencePiece can be used, among other things, to set:

• enable_sampling: Enable subword regularization.

• nbest_size: Sampling parameters for unigram. Invalid for BPE-Dropout.

• nbest_size = {0,1}: No sampling is performed.
• nbest_size > 1: samples from the nbest_size results.
• nbest_size < 0: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm.
• alpha: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout.

Construct a T5 tokenizer. Based on SentencePiece.

This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

Attributes: sp_model (SentencePieceProcessor): The SentencePiece processor that is used for every conversion (string, tokens and IDs).

build_inputs_with_special_tokens < >

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) List[int]

Parameters

• token_ids_0 (List[int]) — List of IDs to which the special tokens will be added.
• token_ids_1 (List[int], optional) — Optional second list of IDs for sequence pairs.

Returns

List[int]

List of input IDs with the appropriate special tokens.

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

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

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None already_has_special_tokens: bool = False ) List[int]

Parameters

• token_ids_0 (List[int]) — List of IDs.
• token_ids_1 (List[int], optional) — Optional second list of IDs for sequence pairs.
• already_has_special_tokens (bool, optional, defaults to False) — Whether or not the token list is already formatted with special tokens for the model.

Returns

List[int]

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

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

create_token_type_ids_from_sequences < >

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) List[int]

Parameters

• token_ids_0 (List[int]) — List of IDs.
• token_ids_1 (List[int], optional) — Optional second list of IDs for sequence pairs.

Returns

List[int]

List of zeros.

Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make use of token type ids, therefore a list of zeros is returned.

## T5TokenizerFast

class transformers.T5TokenizerFast < >

( vocab_file = None tokenizer_file = None eos_token = '</s>' unk_token = '<unk>' pad_token = '<pad>' extra_ids = 100 additional_special_tokens = None **kwargs )

Parameters

• vocab_file (str) — SentencePiece file (generally has a .spm extension) that contains the vocabulary necessary to instantiate a tokenizer.
• eos_token (str, optional, defaults to "</s>") — The end of sequence token.

When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the sep_token.

• unk_token (str, optional, defaults to "<unk>") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
• pad_token (str, optional, defaults to "<pad>") — The token used for padding, for example when batching sequences of different lengths.
• extra_ids (int, optional, defaults to 100) — Add a number of extra ids added to the end of the vocabulary for use as sentinels. These tokens are accessible as “id{%d}>” where ”{%d}” is a number between 0 and extra_ids-1. Extra tokens are indexed from the end of the vocabulary up to beginning (“” is the last token in the vocabulary like in T5 preprocessing see here).
• additional_special_tokens (List[str], optional) — Additional special tokens used by the tokenizer.

Construct a “fast” T5 tokenizer (backed by HuggingFace’s tokenizers library). Based on Unigram.

This tokenizer inherits from PreTrainedTokenizerFast which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

build_inputs_with_special_tokens < >

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) List[int]

Parameters

• token_ids_0 (List[int]) — List of IDs to which the special tokens will be added.
• token_ids_1 (List[int], optional) — Optional second list of IDs for sequence pairs.

Returns

List[int]

List of input IDs with the appropriate special tokens.

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

• single sequence: X </s>
• pair of sequences: A </s> B </s>
create_token_type_ids_from_sequences < >

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) List[int]

Parameters

• token_ids_0 (List[int]) — List of IDs.
• token_ids_1 (List[int], optional) — Optional second list of IDs for sequence pairs.

Returns

List[int]

List of zeros.

Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make use of token type ids, therefore a list of zeros is returned.

## T5Model

class transformers.T5Model < >

( config: T5Config )

Parameters

• config (T5Config) — 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 T5 Model transformer outputting raw hidden-states without any specific head on top.

The T5 model was proposed in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. It’s an encoder decoder transformer pre-trained in a text-to-text denoising generative setting.

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 = None attention_mask = None decoder_input_ids = None decoder_attention_mask = None head_mask = None decoder_head_mask = None cross_attn_head_mask = None encoder_outputs = None past_key_values = None inputs_embeds = None decoder_inputs_embeds = None use_cache = None output_attentions = None output_hidden_states = None return_dict = 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. T5 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 T5 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?

T5 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 T5 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]:

• 1 indicates the head is not masked,
• 0 indicates the head is masked.
• 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]:

• 1 indicates the head is not masked,
• 0 indicates the head is masked.
• 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]:

• 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) 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 (T5Config) 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 + 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 + 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 T5Model 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, T5Model

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = T5Model.from_pretrained("t5-small")

>>> input_ids = tokenizer(
...     "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
parallelize < >

( device_map = None )

Parameters

• device_map (Dict[int, list], optional, defaults to None) — A dictionary that maps attention modules to devices. Note that the embedding module and LMHead are always automatically mapped to the first device (for esoteric reasons). That means that the first device should have fewer attention modules mapped to it than other devices. For reference, the t5 models have the following number of attention modules:

• t5-small: 6
• t5-base: 12
• t5-large: 24
• t5-3b: 24
• t5-11b: 24

This is an experimental feature and is a subject to change at a moment’s notice.

Uses a device map to distribute attention modules of the model across several devices. If no device map is given, it will evenly distribute blocks across all devices.

Example:

# Here is an example of a device map on a machine with 4 GPUs using t5-3b, which has a total of 24 attention modules:
model = T5ForConditionalGeneration.from_pretrained("t5-3b")
device_map = {
0: [0, 1, 2],
1: [3, 4, 5, 6, 7, 8, 9],
2: [10, 11, 12, 13, 14, 15, 16],
3: [17, 18, 19, 20, 21, 22, 23],
}
model.parallelize(device_map)
deparallelize < >

( )

Moves the model to cpu from a model parallel state.

Example:

# On a 4 GPU machine with t5-3b:
model = T5ForConditionalGeneration.from_pretrained("t5-3b")
device_map = {
0: [0, 1, 2],
1: [3, 4, 5, 6, 7, 8, 9],
2: [10, 11, 12, 13, 14, 15, 16],
3: [17, 18, 19, 20, 21, 22, 23],
}
model.parallelize(device_map)  # Splits the model across several devices
model.deparallelize()  # Put the model back on cpu and cleans memory by calling torch.cuda.empty_cache()

## T5ForConditionalGeneration

class transformers.T5ForConditionalGeneration < >

( config )

Parameters

• config (T5Config) — 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.

T5 Model with a language modeling head on top.

The T5 model was proposed in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. It’s an encoder decoder transformer pre-trained in a text-to-text denoising generative setting.

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 = None attention_mask = None decoder_input_ids = None decoder_attention_mask = None head_mask = None decoder_head_mask = None cross_attn_head_mask = None encoder_outputs = None past_key_values = None inputs_embeds = None decoder_inputs_embeds = None labels = None use_cache = None output_attentions = None output_hidden_states = None return_dict = 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. T5 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 T5 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?

T5 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 T5 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]:

• 1 indicates the head is not masked,
• 0 indicates the head is masked.
• 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]:

• 1 indicates the head is not masked,
• 0 indicates the head is masked.
• 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]:

• 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) 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 (T5Config) 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 + 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 + 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 T5ForConditionalGeneration 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 T5Tokenizer, T5ForConditionalGeneration

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = T5ForConditionalGeneration.from_pretrained("t5-small")

>>> # training
>>> input_ids = tokenizer("The <extra_id_0> walks in <extra_id_1> park", return_tensors="pt").input_ids
>>> labels = tokenizer("<extra_id_0> cute dog <extra_id_1> the <extra_id_2>", return_tensors="pt").input_ids
>>> outputs = model(input_ids=input_ids, labels=labels)
>>> loss = outputs.loss
>>> logits = outputs.logits

>>> # inference
>>> input_ids = tokenizer(
...     "summarize: 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))
>>> # studies have shown that owning a dog is good for you.
parallelize < >

( device_map = None )

Parameters

• device_map (Dict[int, list], optional, defaults to None) — A dictionary that maps attention modules to devices. Note that the embedding module and LMHead are always automatically mapped to the first device (for esoteric reasons). That means that the first device should have fewer attention modules mapped to it than other devices. For reference, the t5 models have the following number of attention modules:

• t5-small: 6
• t5-base: 12
• t5-large: 24
• t5-3b: 24
• t5-11b: 24

This is an experimental feature and is a subject to change at a moment’s notice.

Uses a device map to distribute attention modules of the model across several devices. If no device map is given, it will evenly distribute blocks across all devices.

Example:

# Here is an example of a device map on a machine with 4 GPUs using t5-3b, which has a total of 24 attention modules:
model = T5ForConditionalGeneration.from_pretrained("t5-3b")
device_map = {
0: [0, 1, 2],
1: [3, 4, 5, 6, 7, 8, 9],
2: [10, 11, 12, 13, 14, 15, 16],
3: [17, 18, 19, 20, 21, 22, 23],
}
model.parallelize(device_map)
deparallelize < >

( )

Moves the model to cpu from a model parallel state.

Example:

# On a 4 GPU machine with t5-3b:
model = T5ForConditionalGeneration.from_pretrained("t5-3b")
device_map = {
0: [0, 1, 2],
1: [3, 4, 5, 6, 7, 8, 9],
2: [10, 11, 12, 13, 14, 15, 16],
3: [17, 18, 19, 20, 21, 22, 23],
}
model.parallelize(device_map)  # Splits the model across several devices
model.deparallelize()  # Put the model back on cpu and cleans memory by calling torch.cuda.empty_cache()

## T5EncoderModel

class transformers.T5EncoderModel < >

( config: T5Config )

Parameters

• config (T5Config) — 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 T5 Model transformer outputting encoder’s raw hidden-states without any specific head on top.

The T5 model was proposed in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. It’s an encoder decoder transformer pre-trained in a text-to-text denoising generative setting.

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 = None attention_mask = None head_mask = None inputs_embeds = None output_attentions = None output_hidden_states = None return_dict = 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. T5 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 T5 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]:

• 1 indicates the head is not masked,
• 0 indicates the head is masked.
• 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 (T5Config) 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 + 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(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 T5EncoderModel 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, T5EncoderModel

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = T5EncoderModel.from_pretrained("t5-small")
>>> input_ids = tokenizer(
...     "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
parallelize < >

( device_map = None )

Parameters

• device_map (Dict[int, list], optional, defaults to None) — A dictionary that maps attention modules to devices. Note that the embedding module and LMHead are always automatically mapped to the first device (for esoteric reasons). That means that the first device should have fewer attention modules mapped to it than other devices. For reference, the t5 models have the following number of attention modules:

• t5-small: 6
• t5-base: 12
• t5-large: 24
• t5-3b: 24
• t5-11b: 24

This is an experimental feature and is a subject to change at a moment’s notice.

Uses a device map to distribute attention modules of the model across several devices. If no device map is given, it will evenly distribute blocks across all devices.

Example:

# Here is an example of a device map on a machine with 4 GPUs using t5-3b, which has a total of 24 attention modules:
model = T5ForConditionalGeneration.from_pretrained("t5-3b")
device_map = {
0: [0, 1, 2],
1: [3, 4, 5, 6, 7, 8, 9],
2: [10, 11, 12, 13, 14, 15, 16],
3: [17, 18, 19, 20, 21, 22, 23],
}
model.parallelize(device_map)
deparallelize < >

( )

Moves the model to cpu from a model parallel state.

Example:

# On a 4 GPU machine with t5-3b:
model = T5ForConditionalGeneration.from_pretrained("t5-3b")
device_map = {
0: [0, 1, 2],
1: [3, 4, 5, 6, 7, 8, 9],
2: [10, 11, 12, 13, 14, 15, 16],
3: [17, 18, 19, 20, 21, 22, 23],
}
model.parallelize(device_map)  # Splits the model across several devices
model.deparallelize()  # Put the model back on cpu and cleans memory by calling torch.cuda.empty_cache()

## TFT5Model

class transformers.TFT5Model < >

( *args **kwargs )

Parameters

• config (T5Config) — 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 T5 Model transformer outputting raw hidden-stateswithout any specific head on top.

The T5 model was proposed in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. It’s an encoder decoder transformer pre-trained in a text-to-text denoising generative setting.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TF 2.0 models accepts two formats as inputs:

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

This second option is useful when using tf.keras.Model.fit method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

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

( input_ids = None attention_mask = None decoder_input_ids = None decoder_attention_mask = None head_mask = None decoder_head_mask = None encoder_outputs = None past_key_values = None inputs_embeds = None decoder_inputs_embeds = None use_cache = None output_attentions = None output_hidden_states = None return_dict = None training = False **kwargs ) transformers.modeling_tf_outputs.TFSeq2SeqModelOutput or tuple(tf.Tensor)

Parameters

• input_ids (tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. T5 is a model with relative position embeddings so you should be able to pad the inputs on the right or the left.

Indices can be obtained using BertTokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.

What are input IDs?

To know more on how to prepare inputs for pretraining take a look at T5 Training.

• decoder_input_ids (tf.Tensor of shape (batch_size, target_sequence_length), optional) — Provide for sequence to sequence training. T5 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 T5 Training.

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

• 1 for tokens that are not masked,
• 0 for tokens that are masked.
• decoder_attention_mask (tf.Tensor 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 — (tf.Tensor 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]:

• 1 indicates the head is not masked,
• 0 indicates the head is masked.

Returns

transformers.modeling_tf_outputs.TFSeq2SeqModelOutput or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFSeq2SeqModelOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (T5Config) and inputs.

• last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the decoder of the model.

If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.

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

Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see past_key_values input) to speed up sequential decoding.

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

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

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

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

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

Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

• encoder_last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model.

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

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

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

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

The TFT5Model 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 T5Tokenizer, TFT5Model

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = TFT5Model.from_pretrained("t5-small")

>>> input_ids = tokenizer(
...     "Studies have been shown that owning a dog is good for you", return_tensors="tf"
>>> ).input_ids  # Batch size 1
>>> decoder_input_ids = tokenizer("Studies show that", return_tensors="tf").input_ids  # Batch size 1

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

## TFT5ForConditionalGeneration

class transformers.TFT5ForConditionalGeneration < >

( *args **kwargs )

Parameters

• config (T5Config) — 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.

T5 Model with a language modeling head on top.

The T5 model was proposed in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. It’s an encoder decoder transformer pre-trained in a text-to-text denoising generative setting.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TF 2.0 models accepts two formats as inputs:

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

This second option is useful when using tf.keras.Model.fit method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

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

( input_ids = None attention_mask = None decoder_input_ids = None decoder_attention_mask = None head_mask = None decoder_head_mask = None encoder_outputs = None past_key_values = None inputs_embeds = None decoder_inputs_embeds = None labels = None use_cache = None output_attentions = None output_hidden_states = None return_dict = None training = False **kwargs ) transformers.modeling_tf_outputs.TFSeq2SeqLMOutput or tuple(tf.Tensor)

Parameters

• input_ids (tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. T5 is a model with relative position embeddings so you should be able to pad the inputs on the right or the left.

Indices can be obtained using BertTokenizer. See PreTrainedTokenizer.call() and PreTrainedTokenizer.encode() for details.

What are input IDs?

To know more on how to prepare inputs for pretraining take a look at T5 Training.

• decoder_input_ids (tf.Tensor of shape (batch_size, target_sequence_length), optional) — Provide for sequence to sequence training. T5 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 T5 Training.

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

• 1 for tokens that are not masked,
• 0 for tokens that are masked.
• decoder_attention_mask (tf.Tensor 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 — (tf.Tensor 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]:

• 1 indicates the head is not masked,
• 0 indicates the head is masked.

Returns

transformers.modeling_tf_outputs.TFSeq2SeqLMOutput or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFSeq2SeqLMOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (T5Config) and inputs.

• loss (tf.Tensor of shape (n,), optional, where n is the number of non-masked labels, returned when labels is provided) — Language modeling loss.

• logits (tf.Tensor of shape (batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

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

Contains pre-computed hidden-states (key and values in the attention blocks) of the decoder that can be used (see past_key_values input) to speed up sequential decoding.

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

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

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

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

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

Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

• encoder_last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model.

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

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

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

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

The TFT5ForConditionalGeneration 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 T5Tokenizer, TFT5ForConditionalGeneration

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = TFT5ForConditionalGeneration.from_pretrained("t5-small")

>>> # training
>>> inputs = tokenizer("The <extra_id_0> walks in <extra_id_1> park", return_tensors="tf").input_ids
>>> labels = tokenizer("<extra_id_0> cute dog <extra_id_1> the <extra_id_2>", return_tensors="tf").input_ids
>>> outputs = model(inputs, labels=labels)
>>> loss = outputs.loss
>>> logits = outputs.logits

>>> # inference
>>> inputs = tokenizer(
...     "summarize: studies have shown that owning a dog is good for you", return_tensors="tf"
>>> ).input_ids  # Batch size 1
>>> outputs = model.generate(inputs)
>>> print(tokenizer.decode(outputs[0], skip_special_tokens=True))
>>> # studies have shown that owning a dog is good for you

## TFT5EncoderModel

class transformers.TFT5EncoderModel < >

( *args **kwargs )

Parameters

• config (T5Config) — 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 T5 Model transformer outputting encoder’s raw hidden-stateswithout any specific head on top.

The T5 model was proposed in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. It’s an encoder decoder transformer pre-trained in a text-to-text denoising generative setting.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TF 2.0 models accepts two formats as inputs:

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

This second option is useful when using tf.keras.Model.fit method which currently requires having all the tensors in the first argument of the model call function: model(inputs).

If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :

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

( input_ids attention_mask = None head_mask = None inputs_embeds = None output_attentions = None output_hidden_states = None return_dict = None training = False **kwargs ) transformers.modeling_tf_outputs.TFBaseModelOutput or tuple(tf.Tensor)

Parameters

• inputs (tf.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. T5 is a model with relative position embeddings so you should be able to pad the inputs on the right or the left.

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

To know more on how to prepare inputs for pre-training take a look at T5 Training.

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

• 1 for tokens that are not masked,
• 0 for tokens that are masked.
• inputs_embeds (tf.Tensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix. head_mask — (tf.Tensor 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]:

• 1 indicates the head is not masked,
• 0 indicates the head is 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.
• training (bool, optional, defaults to False) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

transformers.modeling_tf_outputs.TFBaseModelOutput or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFBaseModelOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (T5Config) and inputs.

• last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.

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

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

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

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

The TFT5EncoderModel 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 T5Tokenizer, TFT5EncoderModel

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = TFT5EncoderModel.from_pretrained("t5-small")

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

## FlaxT5Model

__call__ < >

( input_ids: ndarray attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None decoder_input_ids: ndarray = None decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.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. T5 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 T5 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?

T5 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 T5 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 (T5Config) 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 FlaxT5PreTrainedModel 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, FlaxT5Model

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = FlaxT5Model.from_pretrained("t5-small")

>>> 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.lax_numpy.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. T5 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 T5 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.t5.configuration_t5.T5Config'>) 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, FlaxT5ForConditionalGeneration

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = FlaxT5ForConditionalGeneration.from_pretrained("t5-small")

>>> 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.lax_numpy.ndarray] = None decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.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.t5.configuration_t5.T5Config'>) 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, FlaxT5ForConditionalGeneration
>>> import jax.numpy as jnp

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = FlaxT5ForConditionalGeneration.from_pretrained("t5-small")

>>> 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

## FlaxT5ForConditionalGeneration

__call__ < >

( input_ids: ndarray attention_mask: typing.Optional[jax._src.numpy.lax_numpy.ndarray] = None decoder_input_ids: ndarray = None decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.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. T5 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 T5 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?

T5 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 T5 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 (T5Config) 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 FlaxT5PreTrainedModel 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, FlaxT5ForConditionalGeneration

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = FlaxT5ForConditionalGeneration.from_pretrained("t5-small")

>>> 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.lax_numpy.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. T5 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 T5 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.t5.configuration_t5.T5Config'>) 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, FlaxT5ForConditionalGeneration

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = FlaxT5ForConditionalGeneration.from_pretrained("t5-small")

>>> 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.lax_numpy.ndarray] = None decoder_attention_mask: typing.Optional[jax._src.numpy.lax_numpy.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.t5.configuration_t5.T5Config'>) 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, FlaxT5ForConditionalGeneration
>>> import jax.numpy as jnp

>>> tokenizer = T5Tokenizer.from_pretrained("t5-small")
>>> model = FlaxT5ForConditionalGeneration.from_pretrained("t5-small")

>>> text = "summarize: 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