timesfm 2.0 500m 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, ICML 2024.
• Google Research blog
• GitHub repo

Authors: Google Research

This is not an officially supported Google product.

Checkpoint timesfm-2.0-500m

timesfm-2.0-500m is the second open model checkpoint:

• It performs univariate time series forecasting for context lengths up to 2048 time points and any horizon lengths, with an optional frequency indicator. Note that it can go even beyond 2048 context even though it was trained with that as the maximum context.
• It focuses on point forecasts. We experimentally offer 10 quantile heads but they have not been calibrated after pretraining.
• It ideally requires the context to be contiguous (i.e. no "holes"), and the context and the horizon to be of the same frequency. In case there are nans we fill in the missing values with linear interpolation before calling the model.

Installation

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

Usage

Initialize the model and load a checkpoint.

Then the base class can be loaded as,

import timesfm

# For PyTorch
tfm = timesfm.TimesFm(
      hparams=timesfm.TimesFmHparams(
          backend=<backend>,
          per_core_batch_size=32,
          horizon_len=128,
          input_patch_len=32,
          output_patch_len=128,
          num_layers=50,
          model_dims=1280,
          use_positional_embedding=False,
      ),
      ch

Your obligations as a timesfm 2.0 500m pytorch deployer

Track your progress

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

Tags

Library