Moirai 2.0 R Small Moirai 2.0 is a decoder only universal time series forecasting transformer model pre trained on: Subset of GIFT Eval Pretrain, and Train datasets (Non leaking historical context). Mixup data generated from non leaking subsets of Chronos Dataset. Synthetic time series produced via KernelSynth introduced in Chronos paper. Internal Salesforce operational data. We make significant improvements over the first version of Moirai (please refer to the paper for previous version): Switched from a distributional loss to a quantile loss formulation. Moved from single token to multi token prediction, improving efficiency and stability. Added a data filtering mechanism to filter out non forecastable, low quality, time series during pretraining. Added a new patch token embedding which includes missing value information. Added patch level random mask to improve robustness of the model during inference. Usage To perform inference with Moirai 2.0, install the uni2ts library from our GitHub repo. 1. Clone repository: 2) Create virtual environment: 3) Build from source: 4) Create a .env file: A simple notebook to get started: github notebook link Citation If you're using any Moirai…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy