diff --git a/README.md b/README.md index 925b79d..20c9b78 100644 --- a/README.md +++ b/README.md @@ -1,73 +1,77 @@ + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理,属于社区翻译,非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/google-research/timesfm) · [上游 README](https://github.com/google-research/timesfm/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 + # TimesFM -TimesFM (Time Series Foundation Model) is a pretrained time-series foundation -model developed by Google Research for time-series forecasting. +TimesFM(Time Series Foundation Model,时间序列基础模型)是 Google Research 开发的预训练时间序列基础模型,用于时间序列预测。 -* Paper: +* 论文: [A decoder-only foundation model for time-series forecasting](https://arxiv.org/abs/2310.10688), - ICML 2024. -* All checkpoints: + ICML 2024。 +* 全部检查点: [TimesFM Hugging Face Collection](https://huggingface.co/collections/google/timesfm-release-66e4be5fdb56e960c1e482a6). * [Google Research blog](https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting/). -* TimesFM in Google 1P Products: - * [BigQuery ML](https://cloud.google.com/bigquery/docs/timesfm-model): Enterprise level SQL queries for scalability and reliability. - * [Google Sheets](https://workspaceupdates.googleblog.com/2026/02/forecast-data-in-connected-sheets-BigQueryML-TimesFM.html): For your daily spreadsheet. - * [Vertex Model Garden](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/timesfm): Dockerized endpoint for agentic calling. +* TimesFM 在 Google 第一方产品中的应用: + * [BigQuery ML](https://cloud.google.com/bigquery/docs/timesfm-model): 企业级 SQL 查询,兼具可扩展性与可靠性。 + * [Google Sheets](https://workspaceupdates.googleblog.com/2026/02/forecast-data-in-connected-sheets-BigQueryML-TimesFM.html): 适用于日常电子表格场景。 + * [Vertex Model Garden](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/timesfm): 容器化端点,支持 agent 式调用。 -This open version is not an officially supported Google product. +此开源版本并非 Google 官方支持的产品。 -**Latest Model Version:** TimesFM 2.5 +**最新模型版本:** TimesFM 2.5 -**Archived Model Versions:** +**已归档模型版本:** -- 1.0 and 2.0: relevant code archived in the sub directory `v1`. You can `pip - install timesfm==1.3.0` to install an older version of this package to load - them. -## Update - July 2, 2026 +- 1.0 和 2.0:相关代码已归档至子目录 `v1`。你可以 `pip + install timesfm==1.3.0` 安装该软件包的旧版本以加载 + 它们。 +## 更新 - 2026 年 7 月 2 日 -Updated PyPI to `timesfm=2.0.2`. See [Install](https://github.com/google-research/timesfm#from-pypi). +已将 PyPI 更新至 `timesfm=2.0.2`。参见 [Install](https://github.com/google-research/timesfm#from-pypi). -## Update - Apr. 9, 2026 +## 更新 - 2026 年 4 月 9 日 -Added fine-tuning example using HuggingFace Transformers + PEFT (LoRA) — see -[`timesfm-forecasting/examples/finetuning/`](timesfm-forecasting/examples/finetuning/). -Also added unit tests (`tests/`) and incorporated several community fixes. +新增使用 HuggingFace Transformers + PEFT(LoRA)的微调示例 — 参见 +[`timesfm-forecasting/examples/finetuning/`](timesfm-forecasting/examples/finetuning/)。 +同时新增单元测试(`tests/`),并纳入多项社区修复。 -Shoutout to [@kashif](https://github.com/kashif) and [@darkpowerxo](https://github.com/darkpowerxo). +特别鸣谢 [@kashif](https://github.com/kashif) 与 [@darkpowerxo](https://github.com/darkpowerxo). -## Update - Mar. 19, 2026 +## 更新 - 2026 年 3 月 19 日 -Huge shoutout to [@borealBytes](https://github.com/borealBytes) for adding the support for [AGENTS](https://github.com/google-research/timesfm/blob/master/AGENTS.md)! TimesFM [SKILL.md](https://github.com/google-research/timesfm/tree/master/timesfm-forecasting) is out. +大力感谢 [@borealBytes](https://github.com/borealBytes) 添加了对 [AGENTS](https://github.com/google-research/timesfm/blob/master/AGENTS.md)! 的支持;TimesFM [SKILL.md](https://github.com/google-research/timesfm/tree/master/timesfm-forecasting) 已发布。 -## Update - Oct. 29, 2025 +## 更新 - 2025 年 10 月 29 日 -Added back the covariate support through XReg for TimesFM 2.5. +通过 XReg 为 TimesFM 2.5 重新加入协变量(covariate)支持。 -## Update - Sept. 15, 2025 +## 更新 - 2025 年 9 月 15 日 -TimesFM 2.5 is out! +TimesFM 2.5 正式发布! -Comparing to TimesFM 2.0, this new 2.5 model: +与 TimesFM 2.0 相比,全新的 2.5 模型: -- uses 200M parameters, down from 500M. -- supports up to 16k context length, up from 2048. -- supports continuous quantile forecast up to 1k horizon via an optional 30M - quantile head. -- gets rid of the `frequency` indicator. -- has a couple of new forecasting flags. +- 参数量为 200M,较此前的 500M 有所减少。 +- 支持最长 16k 上下文长度,较此前的 2048 大幅提升。 +- 通过可选的 30M quantile head,支持最长 1k 预测步长的连续分位数(quantile)预测。 +- 移除了 `frequency` 指示器。 +- 新增若干预测相关标志位。 -Since the Sept. 2025 launch, the following improvements have been completed: +自 2025 年 9 月发布以来,已完成以下改进: -1. ✅ Flax version of the model for faster inference. -2. ✅ Covariate support via XReg (see Oct. 2025 update). -3. ✅ Documentation, examples, and agent skill (see `timesfm-forecasting/`). -4. ✅ Fine-tuning example with LoRA via HuggingFace Transformers + PEFT (see `timesfm-forecasting/examples/finetuning/`). -5. ✅ Unit tests for core layers, configs, and utilities (see `tests/`). +1. ✅ 提供 Flax 版本模型,推理更快。 +2. ✅ 通过 XReg 支持协变量(参见 2025 年 10 月更新)。 +3. ✅ 文档、示例与 agent skill(参见 `timesfm-forecasting/`)。 +4. ✅ 基于 HuggingFace Transformers + PEFT 的 LoRA 微调示例(参见 `timesfm-forecasting/examples/finetuning/`)。 +5. ✅ 核心层、配置与工具函数的单元测试(参见 `tests/`)。 -### Install +### 安装 -#### From `PyPI` +#### 通过 `PyPI` 安装 ```shell # Install the package with torch @@ -78,15 +82,15 @@ pip install timesfm[flax] pip install timesfm[xreg] ``` -#### Local Install +#### 本地安装 -1. Clone the repository: +1. 克隆仓库: ```shell git clone https://github.com/google-research/timesfm.git cd timesfm ``` -2. Create a virtual environment and install dependencies using `uv`: +2. 使用 `uv` 创建虚拟环境并安装依赖: ```shell # Create a virtual environment uv venv @@ -102,14 +106,13 @@ pip install timesfm[xreg] uv pip install -e .[xreg] ``` -3. [Optional] Install your preferred `torch` / `jax` backend based on your OS and accelerators -(CPU, GPU, TPU or Apple Silicon).: +3. [可选] 根据你的操作系统与加速器(CPU、GPU、TPU 或 Apple Silicon)安装偏好的 `torch` / `jax` 后端: - [Install PyTorch](https://pytorch.org/get-started/locally/). - [Install Jax](https://docs.jax.dev/en/latest/installation.html#installation) - for Flax. + 用于 Flax。 -### Code Example +### 代码示例 ```python import torch