Update README.md

1d95242 verified 11 months ago

2.5 kB

license: apache-2.0
library_name: timesfm
pipeline_tag: time-series-forecasting

TimesFM

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

Updates

October 2, 2025: We changed the structure of the model to fuse QKV matrices into one for speed optimization. Please reinstall the latest version of the timesfm package to reflect these changes. Results should be unchanged.

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 checkpoint is not an officially supported Google product. See TimesFM in BigQuery for Google official support.

Checkpoint `timesfm-2.5-200m`

timesfm-2.5-200m is the third open model checkpoint.

Data

timesfm-2.5-200m is pretrained using

GiftEvalPretrain
Wikimedia Pageviews, cutoff Nov 2023 (see paper for details).
Google Trends top queries, cutoff EoY 2022 (see paper for details).
Synthetic and augmented data.

Install

pip install from PyPI coming soon. At this point, please run

git clone https://github.com/google-research/timesfm.git
cd timesfm
pip install -e .

Code Example

import numpy as np
import timesfm
model = timesfm.TimesFM_2p5_200M_torch.from_pretrained("google/timesfm-2.5-200m-pytorch", torch_compile=True)

model.compile(
    timesfm.ForecastConfig(
        max_context=1024,
        max_horizon=256,
        normalize_inputs=True,
        use_continuous_quantile_head=True,
        force_flip_invariance=True,
        infer_is_positive=True,
        fix_quantile_crossing=True,
    )
)
point_forecast, quantile_forecast = model.forecast(
    horizon=12,
    inputs=[
        np.linspace(0, 1, 100),
        np.sin(np.linspace(0, 20, 67)),
    ],  # Two dummy inputs
)
point_forecast.shape  # (2, 12)
quantile_forecast.shape  # (2, 12, 10): mean, then 10th to 90th quantiles.