transformers/pr_33892/en/model_doc/t5.md

T5

T5 is a encoder-decoder transformer available in a range of sizes from 60M to 11B parameters. It is designed to handle a wide range of NLP tasks by treating them all as text-to-text problems. This eliminates the need for task-specific architectures because T5 converts every NLP task into a text generation task.

To formulate every task as text generation, each task is prepended with a task-specific prefix (e.g., translate English to German: ..., summarize: ...). This enables T5 to handle tasks like translation, summarization, question answering, and more.

You can find all official T5 checkpoints under the T5 collection.

Click on the T5 models in the right sidebar for more examples of how to apply T5 to different language tasks.

The example below demonstrates how to generate text with Pipeline, AutoModel, and how to translate with T5 from the command line.

import torch
from transformers import pipeline

pipeline = pipeline(
    task="text2text-generation",
    model="google-t5/t5-base",
    dtype=torch.float16,
    device=0
)
pipeline("translate English to French: The weather is nice today.")

import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "google-t5/t5-base"
    )
model = AutoModelForSeq2SeqLM.from_pretrained(
    "google-t5/t5-base",
    dtype=torch.float16,
    device_map="auto"
    )

input_ids = tokenizer("translate English to French: The weather is nice today.", return_tensors="pt").to(model.device)

output = model.generate(**input_ids, cache_implementation="static")
print(tokenizer.decode(output[0], skip_special_tokens=True))

echo -e "translate English to French: The weather is nice today." | transformers run --task text2text-generation --model google-t5/t5-base --device 0

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the Quantization overview for more available quantization backends.

The example below uses torchao to only quantize the weights to int4.

# pip install torchao
import torch
from transformers import TorchAoConfig, AutoModelForSeq2SeqLM, AutoTokenizer

quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
model = AutoModelForSeq2SeqLM.from_pretrained(
    "google/t5-v1_1-xl",
    dtype=torch.bfloat16,
    device_map="auto",
    quantization_config=quantization_config
)

tokenizer = AutoTokenizer.from_pretrained("google/t5-v1_1-xl")
input_ids = tokenizer("translate English to French: The weather is nice today.", return_tensors="pt").to(model.device)

output = model.generate(**input_ids, cache_implementation="static")
print(tokenizer.decode(output[0], skip_special_tokens=True))

Notes

• You can pad the encoder inputs on the left or right because T5 uses relative scalar embeddings.
• T5 models need a slightly higher learning rate than the default used in Trainer. Typically, values of 1e-4 and 3e-4 work well for most tasks.

T5Config[[transformers.T5Config]]

class transformers.T5Configtransformers.T5Confighttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/configuration_t5.py#L27[{"name": "vocab_size", "val": " = 32128"}, {"name": "d_model", "val": " = 512"}, {"name": "d_kv", "val": " = 64"}, {"name": "d_ff", "val": " = 2048"}, {"name": "num_layers", "val": " = 6"}, {"name": "num_decoder_layers", "val": " = None"}, {"name": "num_heads", "val": " = 8"}, {"name": "relative_attention_num_buckets", "val": " = 32"}, {"name": "relative_attention_max_distance", "val": " = 128"}, {"name": "dropout_rate", "val": " = 0.1"}, {"name": "layer_norm_epsilon", "val": " = 1e-06"}, {"name": "initializer_factor", "val": " = 1.0"}, {"name": "feed_forward_proj", "val": " = 'relu'"}, {"name": "is_encoder_decoder", "val": " = True"}, {"name": "use_cache", "val": " = True"}, {"name": "pad_token_id", "val": " = 0"}, {"name": "eos_token_id", "val": " = 1"}, {"name": "classifier_dropout", "val": " = 0.0"}, {"name": "**kwargs", "val": ""}]- 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. The inner_dim of the projection layer will be defined as num_heads * d_kv.
• 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.
• relative_attention_max_distance (int, optional, defaults to 128) -- The maximum distance of the longer sequences for the bucket separation.
• dropout_rate (float, optional, defaults to 0.1) -- The ratio for all dropout layers.
• classifier_dropout (float, optional, defaults to 0.0) -- The dropout ratio for classifier.
• 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).0

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 google-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[[transformers.T5Tokenizer]]

class transformers.T5Tokenizertransformers.T5Tokenizerhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/tokenization_t5.py#L45[{"name": "vocab_file", "val": ""}, {"name": "eos_token", "val": " = ''"}, {"name": "unk_token", "val": " = ''"}, {"name": "pad_token", "val": " = ''"}, {"name": "extra_ids", "val": " = 100"}, {"name": "additional_special_tokens", "val": " = None"}, {"name": "sp_model_kwargs", "val": ": typing.Optional[dict[str, typing.Any]] = None"}, {"name": "legacy", "val": " = None"}, {"name": "add_prefix_space", "val": " = True"}, {"name": "**kwargs", "val": ""}]- 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 vocabulary for use as sentinels. These tokens are accessible as "<extra_id_{%d}>" where "{%d}" is a number between 0 and extra_ids-1. These tokens can be retrieved by calling get_sentinel_tokens method and token ids can be by calling get_sentinel_token_ids method 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.

• legacy (bool, optional) -- Whether or not the legacy behaviour of the tokenizer should be used. Legacy is before the merge of #24622 and #25224 which includes fixes to properly handle tokens that appear after special tokens. A simple example:

  • legacy=True:

>>> from transformers import T5Tokenizer

>>> tokenizer = T5Tokenizer.from_pretrained("google-t5/t5-base", legacy=True)
>>> tokenizer.encode("Hello <extra_id_0>.")
[8774, 32099, 3, 5, 1]

• legacy=False:

>>> from transformers import T5Tokenizer

>>> tokenizer = T5Tokenizer.from_pretrained("google-t5/t5-base", legacy=False)
>>> tokenizer.encode("Hello <extra_id_0>.")  # the extra space `[3]` is no longer here
[8774, 32099, 5, 1]

Checkout the pull request for more details.

• add_prefix_space (bool, optional, defaults to False) -- Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word.
• sp_model (SentencePieceProcessor) -- The SentencePiece processor that is used for every conversion (string, tokens and IDs).0

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.

build_inputs_with_special_tokenstransformers.T5Tokenizer.build_inputs_with_special_tokenshttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/tokenization_t5.py#L317[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}]- 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.0list[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>

get_special_tokens_masktransformers.T5Tokenizer.get_special_tokens_maskhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/tokenization_t5.py#L248[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}, {"name": "already_has_special_tokens", "val": ": bool = False"}]- 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.0list[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_sequencestransformers.T5Tokenizer.create_token_type_ids_from_sequenceshttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/tokenization_t5.py#L295[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}]- token_ids_0 (list[int]) -- List of IDs.

• token_ids_1 (list[int], optional) -- Optional second list of IDs for sequence pairs.0list[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.

save_vocabularytransformers.T5Tokenizer.save_vocabularyhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/tokenization_t5.py#L430[{"name": "save_directory", "val": ": str"}, {"name": "filename_prefix", "val": ": typing.Optional[str] = None"}]

T5TokenizerFast[[transformers.T5TokenizerFast]]

class transformers.T5TokenizerFasttransformers.T5TokenizerFasthttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/tokenization_t5_fast.py#L41[{"name": "vocab_file", "val": " = None"}, {"name": "tokenizer_file", "val": " = None"}, {"name": "eos_token", "val": " = ''"}, {"name": "unk_token", "val": " = ''"}, {"name": "pad_token", "val": " = ''"}, {"name": "extra_ids", "val": " = 100"}, {"name": "additional_special_tokens", "val": " = None"}, {"name": "add_prefix_space", "val": " = None"}, {"name": "**kwargs", "val": ""}]- 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 vocabulary for use as sentinels. These tokens are accessible as "<extra_id_{%d}>" where "{%d}" is a number between 0 and extra_ids-1. These tokens can be retrieved by calling get_sentinel_tokens method and token ids can be by calling get_sentinel_token_ids method

• additional_special_tokens (list[str], optional) -- Additional special tokens used by the tokenizer.

• add_prefix_space (bool, optional) -- Whether or not the tokenizer should automatically add a prefix space

• from_slow (book, optional, defaults to False) -- Whether or not the tokenizer should be converted from a slow one. If add_prefix_space is set, this will be set to True.0

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_tokenstransformers.T5TokenizerFast.build_inputs_with_special_tokenshttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/tokenization_t5_fast.py#L176[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}]- 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.0list[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_sequencestransformers.T5TokenizerFast.create_token_type_ids_from_sequenceshttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/tokenization_t5_fast.py#L202[{"name": "token_ids_0", "val": ": list"}, {"name": "token_ids_1", "val": ": typing.Optional[list[int]] = None"}]- token_ids_0 (list[int]) -- List of IDs.

• token_ids_1 (list[int], optional) -- Optional second list of IDs for sequence pairs.0list[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[[transformers.T5Model]]

class transformers.T5Modeltransformers.T5Modelhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L971[{"name": "config", "val": ": T5Config"}]- 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.0

The bare T5 Model outputting raw hidden-states without any specific head on top.

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.

forwardtransformers.T5Model.forwardhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1012[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "decoder_input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "decoder_attention_mask", "val": ": typing.Optional[torch.BoolTensor] = None"}, {"name": "encoder_outputs", "val": ": typing.Optional[tuple[tuple[torch.FloatTensor]]] = None"}, {"name": "past_key_values", "val": ": typing.Optional[transformers.cache_utils.Cache] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "decoder_inputs_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "use_cache", "val": ": typing.Optional[bool] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "cache_position", "val": ": typing.Optional[torch.LongTensor] = None"}]- 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 AutoTokenizer. 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.

  What are attention masks?

• decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) -- Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using AutoTokenizer. 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.

• encoder_outputs (tuple[tuple[torch.FloatTensor]], optional) -- Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• past_key_values (~cache_utils.Cache, optional) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the past_key_values returned by the model at a previous stage of decoding, when use_cache=True or config.use_cache=True.

  Only Cache instance is allowed as input, see our kv cache guide. If no past_key_values are passed, DynamicCache will be initialized by default.

  The model will output the same cache format that is fed as input.

  If past_key_values are used, the user is expected to input only unprocessed input_ids (those that don't have their past key value states given to this model) of shape (batch_size, unprocessed_length) instead of all input_ids of shape (batch_size, sequence_length).

• inputs_embeds (torch.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.

• decoder_inputs_embeds (torch.Tensor 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.

• cache_position (torch.LongTensor of shape (sequence_length), optional) -- Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.0transformers.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 (EncoderDecoderCache, optional, returned when use_cache=True is passed or when config.use_cache=True) -- It is a EncoderDecoderCache instance. For more details, see our kv cache guide.

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

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

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

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

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

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

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

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

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

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

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

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

The 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 AutoTokenizer, T5Model

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-small")
>>> model = T5Model.from_pretrained("google-t5/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

>>> # preprocess: Prepend decoder_input_ids with start token which is pad token for T5Model.
>>> # This is not needed for torch's T5ForConditionalGeneration as it does this internally using labels arg.
>>> decoder_input_ids = model._shift_right(decoder_input_ids)

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

T5ForConditionalGeneration[[transformers.T5ForConditionalGeneration]]

class transformers.T5ForConditionalGenerationtransformers.T5ForConditionalGenerationhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1135[{"name": "config", "val": ": T5Config"}]- 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.0

T5 Model with a language modeling head on top.

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.

forwardtransformers.T5ForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1180[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "decoder_input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "decoder_attention_mask", "val": ": typing.Optional[torch.BoolTensor] = None"}, {"name": "encoder_outputs", "val": ": typing.Optional[tuple[tuple[torch.Tensor]]] = None"}, {"name": "past_key_values", "val": ": typing.Optional[transformers.cache_utils.Cache] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "decoder_inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "use_cache", "val": ": typing.Optional[bool] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}, {"name": "cache_position", "val": ": typing.Optional[torch.LongTensor] = None"}]- 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 AutoTokenizer. 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.

  What are attention masks?

• decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) -- Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using AutoTokenizer. 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.

• encoder_outputs (tuple[tuple[torch.Tensor]], optional) -- Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• past_key_values (~cache_utils.Cache, optional) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the past_key_values returned by the model at a previous stage of decoding, when use_cache=True or config.use_cache=True.

  Only Cache instance is allowed as input, see our kv cache guide. If no past_key_values are passed, DynamicCache will be initialized by default.

  The model will output the same cache format that is fed as input.

  If past_key_values are used, the user is expected to input only unprocessed input_ids (those that don't have their past key value states given to this model) of shape (batch_size, unprocessed_length) instead of all input_ids of shape (batch_size, sequence_length).

• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

• decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, target_sequence_length, hidden_size), optional) -- Optionally, instead of passing decoder_input_ids you can choose to directly pass an embedded representation. If past_key_values is used, optionally only the last decoder_inputs_embeds have to be input (see past_key_values). This is useful if you want more control over how to convert decoder_input_ids indices into associated vectors than the model's internal embedding lookup matrix.

  If decoder_input_ids and decoder_inputs_embeds are both unset, decoder_inputs_embeds takes the value of inputs_embeds.

• labels (torch.LongTensor of shape (batch_size,), 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]

• 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.

• cache_position (torch.LongTensor of shape (sequence_length), optional) -- Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.0transformers.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 (EncoderDecoderCache, optional, returned when use_cache=True is passed or when config.use_cache=True) -- It is a EncoderDecoderCache instance. For more details, see our kv cache guide.

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

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

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

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

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

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

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

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

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

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

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

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

The 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 AutoTokenizer, T5ForConditionalGeneration

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-small")
>>> model = T5ForConditionalGeneration.from_pretrained("google-t5/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.

T5EncoderModel[[transformers.T5EncoderModel]]

class transformers.T5EncoderModeltransformers.T5EncoderModelhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1330[{"name": "config", "val": ": T5Config"}]- 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.0

The bare T5 Model outputting raw hidden-states without any specific head on top.

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.

forwardtransformers.T5EncoderModel.forwardhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1360[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- 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 AutoTokenizer. 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.

  What are attention masks?

• 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.0transformers.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, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

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

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

The 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 AutoTokenizer, T5EncoderModel

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-small")
>>> model = T5EncoderModel.from_pretrained("google-t5/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

T5ForSequenceClassification[[transformers.T5ForSequenceClassification]]

class transformers.T5ForSequenceClassificationtransformers.T5ForSequenceClassificationhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1413[{"name": "config", "val": ": T5Config"}]- 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.0

T5 model with a sequence classification/head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

This model inherits from PreTrainedModel. 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.

forwardtransformers.T5ForSequenceClassification.forwardhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1425[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "decoder_input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "decoder_attention_mask", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "encoder_outputs", "val": ": typing.Optional[list[torch.FloatTensor]] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "decoder_inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "use_cache", "val": ": typing.Optional[bool] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- 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 AutoTokenizer. 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.Tensor of shape (batch_size, sequence_length), optional) -- Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

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

  What are attention masks?

• decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) -- Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using AutoTokenizer. 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.

• encoder_outputs (list[torch.FloatTensor], optional) -- Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

• decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, target_sequence_length, hidden_size), optional) -- Optionally, instead of passing decoder_input_ids you can choose to directly pass an embedded representation. If past_key_values is used, optionally only the last decoder_inputs_embeds have to be input (see past_key_values). This is useful if you want more control over how to convert decoder_input_ids indices into associated vectors than the model's internal embedding lookup matrix.

  If decoder_input_ids and decoder_inputs_embeds are both unset, decoder_inputs_embeds takes the value of inputs_embeds.

• labels (torch.LongTensor of shape (batch_size,), optional) -- Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

• use_cache (bool, optional) -- If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

• 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.0transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput or tuple(torch.FloatTensor)A transformers.modeling_outputs.Seq2SeqSequenceClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (T5Config) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when label is provided) -- Classification (or regression if config.num_labels==1) loss.

• logits (torch.FloatTensor of shape (batch_size, config.num_labels)) -- Classification (or regression if config.num_labels==1) scores (before SoftMax).

• past_key_values (EncoderDecoderCache, optional, returned when use_cache=True is passed or when config.use_cache=True) -- It is a EncoderDecoderCache instance. For more details, see our kv cache guide.

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

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

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

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

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

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

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

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

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

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

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

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

The T5ForSequenceClassification forward method, overrides the __call__ special method.

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

Example of single-label classification:

>>> import torch
>>> from transformers import AutoTokenizer, T5ForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-small")
>>> model = T5ForSequenceClassification.from_pretrained("google-t5/t5-small")

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

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

>>> predicted_class_id = logits.argmax().item()
>>> model.config.id2label[predicted_class_id]
...

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = T5ForSequenceClassification.from_pretrained("google-t5/t5-small", num_labels=num_labels)

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

Example of multi-label classification:

>>> import torch
>>> from transformers import AutoTokenizer, T5ForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-small")
>>> model = T5ForSequenceClassification.from_pretrained("google-t5/t5-small", problem_type="multi_label_classification")

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

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

>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = T5ForSequenceClassification.from_pretrained(
...     "google-t5/t5-small", num_labels=num_labels, problem_type="multi_label_classification"
... )

>>> labels = torch.sum(
...     torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).loss

T5ForTokenClassification[[transformers.T5ForTokenClassification]]

class transformers.T5ForTokenClassificationtransformers.T5ForTokenClassificationhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1556[{"name": "config", "val": ": T5Config"}]- 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.0

The T5 transformer with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks.

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.

forwardtransformers.T5ForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1570[{"name": "input_ids", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "labels", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- 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 AutoTokenizer. 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.Tensor of shape (batch_size, sequence_length), optional) -- Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

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

  What are attention masks?

• inputs_embeds (torch.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.

• labels (torch.LongTensor of shape (batch_size, sequence_length), optional) -- Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].

• output_attentions (bool, optional) -- Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

• output_hidden_states (bool, optional) -- Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

• return_dict (bool, optional) -- Whether or not to return a ModelOutput instead of a plain tuple.0transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)A transformers.modeling_outputs.TokenClassifierOutput 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) -- Classification loss.

• logits (torch.FloatTensor of shape (batch_size, sequence_length, config.num_labels)) -- Classification scores (before SoftMax).

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

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

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

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

The T5ForTokenClassification forward method, overrides the __call__ special method.

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

Example:

>>> from transformers import AutoTokenizer, T5ForTokenClassification
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-small")
>>> model = T5ForTokenClassification.from_pretrained("google-t5/t5-small")

>>> inputs = tokenizer(
...     "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
... )

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

>>> predicted_token_class_ids = logits.argmax(-1)

>>> # Note that tokens are classified rather then input words which means that
>>> # there might be more predicted token classes than words.
>>> # Multiple token classes might account for the same word
>>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
>>> predicted_tokens_classes
...

>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...

T5ForQuestionAnswering[[transformers.T5ForQuestionAnswering]]

class transformers.T5ForQuestionAnsweringtransformers.T5ForQuestionAnsweringhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1628[{"name": "config", "val": ": T5Config"}]- 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.0

The T5 transformer with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layer on top of the hidden-states output to compute span start logits and span end logits).

This model inherits from PreTrainedModel. 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.

forwardtransformers.T5ForQuestionAnswering.forwardhttps://github.com/huggingface/transformers/blob/vr_33892/src/transformers/models/t5/modeling_t5.py#L1672[{"name": "input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "attention_mask", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "decoder_input_ids", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "decoder_attention_mask", "val": ": typing.Optional[torch.BoolTensor] = None"}, {"name": "encoder_outputs", "val": ": typing.Optional[tuple[tuple[torch.Tensor]]] = None"}, {"name": "start_positions", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "end_positions", "val": ": typing.Optional[torch.LongTensor] = None"}, {"name": "inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "decoder_inputs_embeds", "val": ": typing.Optional[torch.FloatTensor] = None"}, {"name": "use_cache", "val": ": typing.Optional[bool] = None"}, {"name": "output_attentions", "val": ": typing.Optional[bool] = None"}, {"name": "output_hidden_states", "val": ": typing.Optional[bool] = None"}, {"name": "return_dict", "val": ": typing.Optional[bool] = None"}]- 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 AutoTokenizer. 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.

  What are attention masks?

• decoder_input_ids (torch.LongTensor of shape (batch_size, target_sequence_length), optional) -- Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using AutoTokenizer. 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.

• encoder_outputs (tuple[tuple[torch.Tensor]], optional) -- Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

• start_positions (torch.LongTensor of shape (batch_size,), optional) -- Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

• end_positions (torch.LongTensor of shape (batch_size,), optional) -- Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

• inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) -- Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

• decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, target_sequence_length, hidden_size), optional) -- Optionally, instead of passing decoder_input_ids you can choose to directly pass an embedded representation. If past_key_values is used, optionally only the last decoder_inputs_embeds have to be input (see past_key_values). This is useful if you want more control over how to convert decoder_input_ids indices into associated vectors than the model's internal embedding lookup matrix.

  If decoder_input_ids and decoder_inputs_embeds are both unset, decoder_inputs_embeds takes the value of inputs_embeds.

• use_cache (bool, optional) -- If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

• 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.0transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput or tuple(torch.FloatTensor)A transformers.modeling_outputs.Seq2SeqQuestionAnsweringModelOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (T5Config) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) -- Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.

• start_logits (torch.FloatTensor of shape (batch_size, sequence_length)) -- Span-start scores (before SoftMax).

• end_logits (torch.FloatTensor of shape (batch_size, sequence_length)) -- Span-end scores (before SoftMax).

• past_key_values (EncoderDecoderCache, optional, returned when use_cache=True is passed or when config.use_cache=True) -- It is a EncoderDecoderCache instance. For more details, see our kv cache guide.

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

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

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

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

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

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

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

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

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

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

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

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

The T5ForQuestionAnswering forward method, overrides the __call__ special method.

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

Example:

>>> from transformers import AutoTokenizer, T5ForQuestionAnswering
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-small")
>>> model = T5ForQuestionAnswering.from_pretrained("google-t5/t5-small")

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()

>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
>>> tokenizer.decode(predict_answer_tokens, skip_special_tokens=True)
...

>>> # target is "nice puppet"
>>> target_start_index = torch.tensor([14])
>>> target_end_index = torch.tensor([15])

>>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
>>> loss = outputs.loss
>>> round(loss.item(), 2)
...