⬢github Jupyter Notebook · 55 ★ +8 since we first saw it · pushed 1 d ago · Apache-2.0
theforecastingcompany/tfc-t0
An open-weights time-series forecasting foundation model from The Forecasting Company.
t0 is an open-weights, 256M-parameter foundation model for time-series forecasting from The Forecasting Company. It produces probabilistic forecasts and can incorporate historical and known-future covariates (e.g., weather, holidays). The repo ships a Python/PyPI package, Colab quickstart notebooks, an MLX runtime for Apple silicon, and models hosted on Hugging Face.
Why now: It was shown on Hacker News as a claim of a SOTA open-weights time-series forecasting model, alongside an arXiv report and Hugging Face release.
Who it is for: Data scientists and ML engineers who need ready-to-run forecasting models for demand, prices, or other time series.
forecastingforecasting-modelsfoundation-modelstime-seriestime-series-forecasting
Stars over our 106 snapshots: 47 to 55, since 1 d ago.
Where people talked about it
API: https://socialmediatrends-api.osmike.com/v1/repos/theforecastingcompany/tfc-t0