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 Jul 21, 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 Jul 21, 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-4.2.1.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-4.2.1-py3-none-any.whl (29.1 kB view details)

Uploaded Python 3

File details

Details for the file openstef_foundation_models-4.2.1.tar.gz.

File metadata

  • Download URL: openstef_foundation_models-4.2.1.tar.gz
  • Upload date:
  • Size: 36.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.30 {"installer":{"name":"uv","version":"0.11.30","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-4.2.1.tar.gz
Algorithm Hash digest
SHA256 369425d0ccf43326c8cbcc6004d671fd4f5715270c494af77126871767f73df2
MD5 d0ef5627fec554a3dcd7a8354fd78427
BLAKE2b-256 502dec6944869ac6541a539b08a51a7a8f930a8287dc87e27981a638254fa791

See more details on using hashes here.

Provenance

The following attestation bundles were made for openstef_foundation_models-4.2.1.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-4.2.1-py3-none-any.whl.

File metadata

  • Download URL: openstef_foundation_models-4.2.1-py3-none-any.whl
  • Upload date:
  • Size: 29.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.30 {"installer":{"name":"uv","version":"0.11.30","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-4.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 249baaebaf519a2cad7f6937f1c957b270455f5187309b8d947b0cdeb4538da5
MD5 8fce24ad3bac5b790844824d53793c0f
BLAKE2b-256 4d20cacec82630bc73ec0f8c077abd9c6d748dd84833a0dae3c249463e94b4f3

See more details on using hashes here.

Provenance

The following attestation bundles were made for openstef_foundation_models-4.2.1-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