timesfm 1.0 200m pytorch EU AI Act Compliance Profile

TimesFM

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Resources and Technical Documentation:

• Paper: A decoder-only foundation model for time-series forecasting, to appear in ICML 2024.
• Google Research blog
• GitHub repo

Authors: Google Research

This is not an officially supported Google product.

Checkpoint timesfm-1.0-200m

timesfm-1.0-200m is the first open model checkpoint:

• It performs univariate time series forecasting for context lengths up to 512 time points and any horizon lengths, with an optional frequency indicator.
• It focuses on point forecasts and does not support probabilistic forecasts. We experimentally offer quantile heads but they have not been calibrated after pretraining.
• It requires the context to be contiguous (i.e. no "holes"), and the context and the horizon to be of the same frequency.

Benchmarks

Please refer to our result tables on the extended benchmarks and the long horizon benchmarks.

Please look into the README files in the respective benchmark directories within experiments/ for instructions for running TimesFM on the respective benchmarks.

Installation

This HuggingFace repo hosts TimesFm checkpoints. Please visit our GitHub repo and follow the instructions there to install the timesfm library for model inference.

In particular, the dependency lingvo does not support ARM architectures and the inference code is not working for machines with Apple silicon. We are

Your obligations as a timesfm 1.0 200m pytorch deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library