metadata

license: apache-2.0
pipeline_tag: time-series-forecasting
tags:
  - time series
  - forecasting
  - pretrained models
  - foundation models
  - time series foundation models
  - time-series

Chronos⚡️-Tiny

Pre-release of Chronos⚡️ (read: Chronos-Bolt) pretrained time series forecasting models. Chronos⚡️ models are based on the T5 architecture and are available in the following sizes.

Model	Parameters	Based on
chronos-bolt-tiny	9M	t5-efficient-tiny
chronos-bolt-mini	21M	t5-efficient-mini
chronos-bolt-small	48M	t5-efficient-small
chronos-bolt-base	205M	t5-efficient-base

Usage

A minimal example showing how to perform inference using Chronos⚡️ with AutoGluon:

pip install --pre autogluon

from autogluon.timeseries import TimeSeriesPredictor, TimeSeriesDataFrame

df = TimeSeriesDataFrame("https://autogluon.s3.amazonaws.com/datasets/timeseries/m4_hourly/train.csv")

predictions = TimeSeriesPredictor().fit(
    df,
    hyperparameters={
        "Chronos": [
            {"model_path": "autogluon/chronos-bolt-tiny"},
        ]
    },
).predict(
    df
)

Citation

If you find Chronos or Chronos⚡️ models useful for your research, please consider citing the associated paper:

@article{ansari2024chronos,
  author  = {Ansari, Abdul Fatir and Stella, Lorenzo and Turkmen, Caner and Zhang, Xiyuan, and Mercado, Pedro and Shen, Huibin and Shchur, Oleksandr and Rangapuram, Syama Syndar and Pineda Arango, Sebastian and Kapoor, Shubham and Zschiegner, Jasper and Maddix, Danielle C. and Mahoney, Michael W. and Torkkola, Kari and Gordon Wilson, Andrew and Bohlke-Schneider, Michael and Wang, Yuyang},
  title   = {Chronos: Learning the Language of Time Series},
  journal = {arXiv preprint arXiv:2403.07815},
  year    = {2024}
}

License

This project is licensed under the Apache-2.0 License.