transformers/docs/source/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.

Tip

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",
    torch_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",
    torch_dtype=torch.float16,
    device_map="auto"
    )

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

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",
    torch_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("cuda")

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

autodoc T5Config

T5Tokenizer

autodoc T5Tokenizer - build_inputs_with_special_tokens - get_special_tokens_mask - create_token_type_ids_from_sequences - save_vocabulary

T5TokenizerFast

autodoc T5TokenizerFast

T5Model

autodoc T5Model - forward

T5ForConditionalGeneration

autodoc T5ForConditionalGeneration - forward

T5EncoderModel

autodoc T5EncoderModel - forward

T5ForSequenceClassification

autodoc T5ForSequenceClassification - forward

T5ForTokenClassification

autodoc T5ForTokenClassification - forward

T5ForQuestionAnswering

autodoc T5ForQuestionAnswering - forward

TFT5Model

autodoc TFT5Model - call

TFT5ForConditionalGeneration

autodoc TFT5ForConditionalGeneration - call

TFT5EncoderModel

autodoc TFT5EncoderModel - call

FlaxT5Model

autodoc FlaxT5Model - call - encode - decode

FlaxT5ForConditionalGeneration

autodoc FlaxT5ForConditionalGeneration - call - encode - decode

FlaxT5EncoderModel

autodoc FlaxT5EncoderModel - call