t0-beta

Run it

$ pip install pfnstudio
$ pfnstudio run t0-beta --input <your file>

# ex:
$ pfnstudio run t0-beta --input sample

# download it without running · its tasks, inputs, license and digest
$ pfnstudio pull t0-beta
$ pfnstudio show t0-beta

# models loaded now · delete it from this machine
$ pfnstudio ps
$ pfnstudio rm t0-beta

Python 3.10+. The first run downloads the model's adapter, asks before installing PyTorch and the model's own packages (-y installs without asking) and pulls the pretrained weights from Hugging Face. --input sample runs the sample input pfnstudio ships and prints its path: copy it, put your data in, and pass it as <your file>. Later runs reuse the cache.

Serves

Headline numbers

Provenance

Readme

A ready-to-use forecasting model you can point at your own history — it predicts the next weeks of sales, demand or any metric, with a range, without training a model.

t0-beta (The Forecasting Company) is a zero-shot time-series forecasting transformer (~255.6M parameters). It reads a series' history in patches and returns quantile forecasts for the next steps. This listing installs the real pretrained weights as an inference-only base model: the checkpoint is pulled from HuggingFace (theforecastingcompany/t0-beta) at run time and served through the upstream tfc-t0 package.