|
--- |
|
license: apache-2.0 |
|
tags: |
|
- time series |
|
- forecasting |
|
- pretrained models |
|
- foundation models |
|
- time series foundation models |
|
- time-series |
|
--- |
|
# Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting |
|
|
|
 |
|
|
|
Lag-Llama is the <b>first open-source foundation model for time series forecasting</b>! |
|
|
|
[[Tweet Thread](https://twitter.com/arjunashok37/status/1755261111233114165)] [[Model Weights](https://huggingface.co/time-series-foundation-models/Lag-Llama)] [[Colab Demo on Zero-Shot Forecasting](https://colab.research.google.com/drive/13HHKYL_HflHBKxDWycXgIUAHSeHRR5eo?usp=sharing)] [[GitHub](https://github.com/time-series-foundation-models/lag-llama)] [[Paper](https://arxiv.org/abs/2310.08278)] |
|
|
|
____ |
|
This HuggingFace model houses the <a href="https://huggingface.co/time-series-foundation-models/Lag-Llama/blob/main/lag-llama.ckpt" target="_blank">pretrained checkpoint</a> of Lag-Llama. |
|
|
|
____ |
|
|
|
* **Coming Next**: Fine-tuning scripts with examples on real-world datasets and best practices in using Lag-Llama!🚀 |
|
|
|
<b>Updates</b>: |
|
|
|
* **17-Feb-2024**: We have released a new updated [Colab Demo](https://colab.research.google.com/drive/1XxrLW9VGPlZDw3efTvUi0hQimgJOwQG6?usp=sharing) 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. |
|
|
|
____ |
|
|
|
<b>Current Features:</b> |
|
|
|
💫 <b>Zero-shot forecasting</b> on a dataset of <b>any frequency</b> for <b>any prediction length</b>, using the <a href="https://colab.research.google.com/drive/13HHKYL_HflHBKxDWycXgIUAHSeHRR5eo?usp=sharing" target="_blank">Colab Demo.</a><br/> |
|
|
|
____ |
|
|
|
Coming Soon: |
|
|
|
⭐ An <b>online gradio demo</b> where you can upload time series and get zero-shot predictions and perform finetuning. |
|
|
|
⭐ Features for <b>finetuning</b> the foundation model |
|
|
|
⭐ Features for <b>pretraining</b> Lag-Llama on your own large-scale data |
|
|
|
⭐ Scripts to <b>reproduce</b> all results in the paper. |
|
|
|
|
|
____ |
|
|
|
Stay Tuned!🦙 |
