timesfm-forecasting
Performs zero-shot time-series forecasting with Google's TimesFM, including regular-grid CSV preparation, quantile forecasts, XReg covariates, and held-out evaluation. Uses the Apache-licensed TimesFM 2.5 checkpoint by default and documents the distinct TimesFM 3.0 multivariate API and weight-license requirements.
- Version
- 3.0
- License
- Apache-2.0 license
- Compatibility
- Requires Python 3.10+ and timesfm 3.0.2 with PyTorch; CSV tooling also needs NumPy and pandas. Network access and cache space are needed for initial Hugging Face checkpoint download. Optional XReg needs JAX and scikit-learn; current JAX requires Python 3.12+.
Pinned to revision 68105dd992f1, so it is the text this page describes rather than whatever the author pushed since.
Pre-approved tools experimental
Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.
- Read
- Write
- Edit
- Bash
Files
- skills/timesfm-forecasting/SKILL.md
- skills/timesfm-forecasting/SKILL_CN.md
- skills/timesfm-forecasting/examples/anomaly-detection/detect_anomalies.py
- skills/timesfm-forecasting/examples/covariates-forecasting/demo_covariates.py
- skills/timesfm-forecasting/examples/global-temperature/README.md
- skills/timesfm-forecasting/examples/global-temperature/generate_animation_data.py
- skills/timesfm-forecasting/examples/global-temperature/generate_gif.py
- skills/timesfm-forecasting/examples/global-temperature/generate_html.py
- skills/timesfm-forecasting/examples/global-temperature/run_example.sh
- skills/timesfm-forecasting/examples/global-temperature/run_forecast.py
- skills/timesfm-forecasting/examples/global-temperature/temperature_anomaly.csv
- skills/timesfm-forecasting/examples/global-temperature/visualize_forecast.py
- skills/timesfm-forecasting/references/api_reference.md
- skills/timesfm-forecasting/references/data_preparation.md
- skills/timesfm-forecasting/references/examples_and_validation.md
- skills/timesfm-forecasting/references/output_and_config.md
- skills/timesfm-forecasting/references/performance_tuning.md
- skills/timesfm-forecasting/references/system_requirements.md
- skills/timesfm-forecasting/references/timesfm3.md
- skills/timesfm-forecasting/references/workflows.md
- skills/timesfm-forecasting/scripts/check_system.py
- skills/timesfm-forecasting/scripts/forecast_csv.py
Every link opens the file at its source, pinned to the revision this page describes.