T5

by Google AI

About the model:

This entry collates T5 base, T5X, and FLAN T5

Model type:

Text

Model performance class:

Limited

Link to the model:

https://huggingface.co/docs/transformers/en/model_doc/t5

Base models:

End model:

T5X

End model license:

Apache-2.0

About the organisation:

Major technology company, operator of Google Search.

Link to the organisation:

https://ai.google

Model release date:

October 2019

Availability

Base Model Data

C4; pretraining T5X on The Pile and for finetuning on SQuAD and MNLI.

https://github.com/google-research/t5x https://github.com/google-research/text-to-text-transfer-transformer/blob/main/README.md#dataset-preparation

End User Model Data

finetuning on SQuAD and MNLI

Base Model Weights

https://github.com/google-research/text-to-text-transfer-transformer?tab=readme-ov-file#released-model-checkpoints

End User Model Weights

https://github.com/google-research/t5x

Training Code

https://github.com/google-research/t5x

Documentation

Code Documentation

https://github.com/google-research/t5x

Hardware Architecture

https://arxiv.org/pdf/1910.10683

Preprint

https://arxiv.org/pdf/1910.10683

Paper

http://www.jmlr.org/papers/v21/20-074.html

Modelcard

https://huggingface.co/docs/transformers/en/model_doc/t5 https://huggingface.co/google-t5/t5-11b

Datasheet

https://huggingface.co/google-t5/t5-11b#training-details

Access

Package

API and Meta Prompts

Licenses

weights under apache 2.0, base model data unclear

Is this information not up to date?

Contribute here ->

Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 10 March 2026, website content last updated 11 March 2026.