This repository provides a collection of Transformer-based time series models implemented in PyTorch, integrated with the GluonTS API. It aims to offer a centralized resource for researchers and practitioners working with advanced deep learning architectures for time series forecasting tasks.

How It Works

The project leverages the Transformer architecture, known for its ability to capture long-range dependencies, and adapts it for time series data. By integrating with GluonTS, it benefits from a standardized framework for time series modeling, enabling easier experimentation and comparison of different models and techniques.

Quick Start & Requirements

• Install via pip3 install -U -r requirements.txt.
• Requires Python 3.x.
• Note: The project points to a separate repository for the latest version of Lag-Llama: https://github.com/time-series-foundation-models/lag-llama.

Highlighted Details

• Focuses on Transformer architectures for time series.
• Integrates with the GluonTS framework.
• Includes Lag-Llama, a foundation model for time series forecasting.

Maintenance & Community

No specific details on contributors, sponsorships, or community channels are provided in the README.

Licensing & Compatibility

The README does not specify a license.

Limitations & Caveats

The project README explicitly directs users to a different repository for the latest version of Lag-Llama, suggesting this repository may not be actively maintained or may be superseded for that specific model.