Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

Lag-Llama is the first open-source foundation model for time series forecasting!

[Tweet Thread] [Model Weights] [Colab Demo on Zero-Shot Forecasting] [GitHub] [Paper]

This repository houses the Lag-Llama architecture.

• Coming Next: Fine-tuning scripts with examples on real-world datasets and best practices in using Lag-Llama!🚀

Updates:

• 17-Feb-2024: We have released a new updated Colab Demo for zero-shot forecasting that shows how one can load time series of different formats.
• 7-Feb-2024: We released Lag-Llama, with open-source model checkpoints and a Colab Demo for zero-shot forecasting.

Current Features:

💫 Zero-shot forecasting on a dataset of any frequency for any prediction length, using the Colab Demo.

Coming Soon:

⭐ An online gradio demo where you can upload time series and get zero-shot predictions and perform finetuning.

⭐ Features for finetuning the foundation model

⭐ Features for pretraining Lag-Llama on your own large-scale data

⭐ Scripts to reproduce all results in the paper.

Stay Tuned!🦙