mistralai/Timestral

preview.redd.it/zyoo32u7hnvh1.png from Mistral: Timestral is a family of time series foundation models for zero-shot forecasting, available in 5M , 28M , 123M , and 209M parameter versions. This repository contains the 209M checkpoint. Timestral supports univariate and multivariate forecasting, past-only and known-future covariates, and probabilistic predictions across 21 quantiles. It accepts up to 32,768 historical time steps and forecasts up to 1,024 steps in a single forward pass. We’re releasing the source code in our GitHub repository to make it easy to run Timestral and reproduce our benchmark results. Model Details Size: 209M parameters. Architecture: patch-based transformer with time attention and variate attention, 24 layers, embedding dimension 768. Patching: 32 time steps per patch. Each patch is embedded from its values together with their missing-value indicators. Context length: up to 32,768 time steps (1,024 patches). Forecast horizon : Up to 1,024 time steps (32 patches) in a single forward pass. Longer horizons are forecast block by block, with each block's median forecast appended to the context. Outputs: 21 quantiles (0.01, 0.05, 0.1, 0.15, …, 0.85, 0.9, 0.95, 0.99). Inputs: univariate or multivariate target variates, plus past-only and known-future covariates, numeric or categorical (categorical covariates are target-encoded). Missing values are marked as NaN. Inference: PyTorch on CPU or GPU. huggingface.co/mistralai/Timestral-209M huggingface.co/mistralai/Timestral-123M huggingface.co/mistralai/Timestral-28M huggingface.co/mistralai/Timestral-5M