openstef-foundation-models

Foundation model support for OpenSTEF — bringing pre-trained, ONNX-based forecasting models to the OpenSTEF ecosystem.

Installation

Pick exactly one ONNX runtime — [cpu] and [gpu] are mutually exclusive.

CPU (default — the meta-package openstef installs this for you):

pip install "openstef-foundation-models[cpu]"

GPU (CUDA):

pip install "openstef-foundation-models[gpu]"

Note: Do not install both [cpu] and [gpu] in the same environment — onnxruntime and onnxruntime-gpu collide. They're declared as conflicting extras so uv enforces the choice; pip does not, so pick one yourself.

Selecting a checkpoint

OpenSTEF publishes its checkpoints to the HuggingFace Hub. Pick a model size and variant from the catalog instead of hand-writing repo ids and filenames:

from openstef_foundation_models.models import Chronos2, CheckpointVariant
from openstef_foundation_models.presets import ForecastingWorkflowConfig

# Default: the base Chronos-2, dynamic shapes — runs on any provider.
config = ForecastingWorkflowConfig()

# The smaller model, static shapes — enables the CoreML provider on macOS.
config = ForecastingWorkflowConfig(
    checkpoint=Chronos2.SMALL.checkpoint(CheckpointVariant.STATIC),
)

# Let the host decide: static on macOS, dynamic elsewhere.
config = ForecastingWorkflowConfig(
    checkpoint=Chronos2.BASE.checkpoint(CheckpointVariant.recommended()),
)

Available sizes are Chronos2.BASE (chronos-2) and Chronos2.SMALL (chronos-2-small); variants are DYNAMIC (portable) and STATIC (frozen shapes, the macOS/CoreML path in the default provider fallback chain).

Project links

Data verified by PyPI on Aug 14, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (4.3.1)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for ktp from gravatar.com ktp

Credits

Author: Alliander N.V

GitHub Statistics

Data verified by PyPI on Aug 14, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

MPL-2.0
View SPDX License List

Requires

Python <4.0, >=3.12

Provides Extra

cpu gpu

Tags

energy forecasting foundationmodels machinelearning onnx

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

openstef_foundation_models-4.2.3.tar.gz (36.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

openstef_foundation_models-4.2.3-py3-none-any.whl (29.1 kB view details)

Uploaded Python 3

File details

Details for the file openstef_foundation_models-4.2.3.tar.gz.

File metadata

  • Download URL: openstef_foundation_models-4.2.3.tar.gz
  • Upload date:
  • Size: 36.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.12.4 {"installer":{"name":"uv","version":"0.12.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for openstef_foundation_models-4.2.3.tar.gz
Algorithm Hash digest
SHA256 5ba2ee50d6bc8f7ae5456dc28069241498a1be93b22380c1eb525d724f36444a
MD5 0a66553997e9b0c5e79532bfbfc466ff
BLAKE2b-256 3a501cacc8d9e1e636860950a77a91a627fdc960989dae47bd47d036ea9a3560

See more details on using hashes here.

Provenance

The following attestation bundles were made for openstef_foundation_models-4.2.3.tar.gz:

Publisher: release-v4.yaml on OpenSTEF/openstef

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file openstef_foundation_models-4.2.3-py3-none-any.whl.

File metadata

  • Download URL: openstef_foundation_models-4.2.3-py3-none-any.whl
  • Upload date:
  • Size: 29.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.12.4 {"installer":{"name":"uv","version":"0.12.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for openstef_foundation_models-4.2.3-py3-none-any.whl
Algorithm Hash digest
SHA256 c2e07e920cb0300a51f0bbd4e0b530d82d496cdac7f58d1248a8e9b2a28135d4
MD5 e62a513c67135dbdb22f46bc88ca3762
BLAKE2b-256 8b7ac5d1ed3cc28cdee0944272d5d0ce4b885ef30b37746140f8388c4c23e819

See more details on using hashes here.

Provenance

The following attestation bundles were made for openstef_foundation_models-4.2.3-py3-none-any.whl:

Publisher: release-v4.yaml on OpenSTEF/openstef

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page