TiRex This repository provides the pre trained forecasting model TiRex introduced in the paper TiRex: Zero Shot Forecasting across Long and Short Horizons with Enhanced In Context Learning. TiRex is a 35M parameter pre trained time series forecasting model based on xLSTM. Key Facts: Zero Shot Forecasting : TiRex is a pre trained model that performs time series forecasting without requiring any training on your data. Simply download and use it. Quantile Predictions : TiRex provides both point estimates and quantile estimates. State of the art Performance over Long and Short Horizons : TiRex achieves top scores in various time series forecasting benchmarks, see GiftEval and ChronosZS. These benchmark show that TiRex provides great performance for both long and short term forecasting. Documentation A detailed documentation of TiRex can be found here: https://nx ai.github.io/tirex/ Installation Install with additional input/output adapter: You can also install TiRex with all extras at once using: TiRex is currently only tested on Linux and MacOS. Quick Start We provide an extended quick start example in examples/quick start tirex.ipynb. This notebook also shows how to use the different…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy