Chronos-T5 (Mini) is a time series foundation model hosted on Hugging Face under the autogluon organization. It belongs to the class of pretrained models for time series forecasting and is based on the T5 architecture for text2text-generation tasks applied to time series data.
The model carries tags for time series forecasting, transformers, safetensors, and foundation models. Its associated papers are listed as arxiv:2403.07815 and arxiv:1910.10683. An update note indicates that related Chronos-Bolt and original Chronos models became available on Amazon SageMaker JumpStart in February 2025.
It is delivered as a model repository on Hugging Face that can be loaded through the Transformers library. Example code shows importing AutoTokenizer and AutoModelForSeq2SeqLM, then instantiating the tokenizer and model directly from the repository identifier with an option for automatic device mapping. Notebooks for Google Colab and Kaggle are referenced for further usage examples.
The license is apache-2.0. The repository provides files and versions along with instructions for use with libraries, inference providers, notebooks, and local applications.
In the Data science & ML workbench space, Chronos T5 Mini takes a focused approach. It focuses on forecasting future values in time series data using foundation models. Chronos T5 Mini is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
Autogluon builds and maintains Chronos T5 Mini, and the product first shipped in 2024. The project is developed in the open on GitHub with 5.6k stars and 10 commits in the last 90 days. Among its 3 catalogued features are Time Series Forecasting, T5 Architecture, and Pretrained Foundation Model.
Latest indexed changes and source events
autogluon/chronos-t5-mini verified by the PulseGate indexer
Other apps tracked under the same category.
