IBM 发布 Granite Time Series PatchTST-FM-r2 模型

AI 摘要

IBM 发布 Granite Time Series PatchTST-FM-r2 时间序列基础模型，采用约 3.85 亿参数、Conformer 架构，支持零样本预测、概率预测和缺失值填补。截至 2026 年 9 月 8 日，该模型在 GIFT-Eval 基准的可复现零样本模型中排名第二，并且是同类中唯一采用 Apache 2.0 与 OpenMDW 1.0 宽松商业友好许可的领先模型。模型权重、架构、推理流程和复现基准的代码均已开放。

正文节选

Time-series foundation models are changing the way forecasting systems are built. Instead of training and maintaining a separate model for every dataset, users can use a pretrained model and generate forecasts zero-shot. IBM has released Granite Time Series PatchTST-FM-r2, the latest model in the Granite TSFM family (github, blog). PatchTST-FM-r2, a new version of its predecessor PatchTST-FM-r1, combines an updated architecture, a larger pretraining corpus, probabilistic forecasting, support for

发布时间：—

抓取时间：2026-09-16 00:13

来源机构：Hugging Face