metadata
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.
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()
model.load_checkpoint()
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.