FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines

TL;DR

FMTK is an open-source toolkit that simplifies the construction and fine-tuning of time-series foundation model pipelines, promoting modularity, reproducibility, and ease of use in machine learning applications.

Contribution

It introduces a standardized, extensible framework for assembling TSFM pipelines, reducing implementation complexity and enhancing flexibility.

Findings

Achieves correct and high-performance pipelines with minimal code

Enables flexible composition across models and tasks

Open-source and easy to extend

Abstract

Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-series foundation models (TSFMs) -- FMs trained on time-series data -- have shown strong performance on classification, regression, and imputation tasks. Recent pipelines combine TSFMs with task-specific encoders, decoders, and adapters to improve performance; however, assembling such pipelines typically requires ad hoc, model-specific implementations that hinder modularity and reproducibility. We introduce FMTK, an open-source, lightweight and extensible toolkit for constructing and fine-tuning TSFM pipelines via standardized backbone and component abstractions. FMTK enables flexible composition across models and tasks, achieving correctness and performance with an average of seven lines of code. https://github.com/umassos/FMTK