概要
TimesFMはGoogle研究チームによって開発されたデコーダーベースの事前学習済み時系列基盤モデルであり、長いコンテキストと連続分位数予測をサポートし、PyTorch版とFlax版を提供しています。
README プレビュー
# TimesFM\n\nTimesFM (Time Series Foundation Model) is a pretrained time-series foundation\nmodel developed by Google Research for time-series forecasting.\n\n* Paper:\n [A decoder-only foundation model for time-series forecasting](https://arxiv.org/abs/2310.10688),\n ICML 2024.\n* All checkpoints:\n [TimesFM Hugging Face Collection](https://huggingface.co/collections/google/timesfm-release-66e4be5fdb56e960c1e482a6).\n* [Google Research blog](https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting/).\n* TimesFM in Google 1P Products:\n * [BigQuery ML](https://cloud.google.com/bigquery/docs/timesfm-model): Enterprise level SQL queries for scalability and reliability.\n * [Google Sheets](https://workspaceupdates.googleblog.com/2026/02/forecast-data-in-connected-sheets-BigQueryML-TimesFM.html): For your daily spreadsheet. \n * [Vertex Model Garden](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/timesfm): Dockerized endpoint for agentic calling.\n\nThis open version is not an officially supported Google product.\n\n**Latest Model Version:** TimesFM 2.5\n\n**Archived Model Versions:**\n\n- 1.0 and 2.0: relevant code archived in the sub directory `v1`. You can `pip\n install timesfm==1.3.0` to install an older version of this package to load\n them.\n## Update - June 5, 2026\n\nUpdated PyPI to `timesfm=2.0.0`. See [Install](https://github.com/google-research/timesfm#from-pypi).\n\n## Update - Apr. 9, 2026\n\nAdded fine-tuning example using HuggingFace Transformers + PEFT (LoRA) — see\n[`timesfm-forecasting/examples/finetuning/`](timesfm-forecasting/examples/finetuning/).\nAlso added unit tests (`tests/`) and incorporated several community fixes.\n\nShoutout to [@kashif](https://github.com/kashif) and [@darkpowerxo](https://github.com/darkpowerxo). \n\n## Update - Mar. 19, 2026\n\nHuge shoutout to [@borealBytes](https://github.com/borealBytes) for adding the support for [AGE