PatchTST was originally released prior to the interest in creating pre-trained, zero-shot time series foundation models that were capable of state-of-the-art performance on out of sample datasets. PatchTST-FM (patched time-series transformer-based foundation model) essentially has the architectural simplicity of PatchTST, but differs in some crucial ways. Coupled with a revised training strategy and a significantly larger training corpus, we are able to train a model that achieves state-of-the-art results on GiftEval (see below for recommended filters to view this on the leaderboard). The architecture incorporates the following changes: - residual blocks in the input and output projections…
Open weights
apache-2.0
258M parameters
Model · Time series forecasting
Google
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. Please reinstall the latest version of the timesfm package to reflect these changes. Results should be unchanged. This checkpoint is not an officially supported Google product. See TimesFM in BigQuery for Google official support. timesfm-2.5-200m is the third open model checkpoint. timesfm-2.5-200m is pretrained using - Wikimedia Pageviews, cutoff Nov 2023 (see paper for details). - Google Trends top queries, cutoff EoY 2022 (see paper for details). - Synthetic and augmented data. At this point, please run
Open weights
apache-2.0
231M parameters
timesfm
Model · Time series forecasting
Google
TimesFM (Time Series Foundation Model) is a pretrained decoder-only model for time-series forecasting. This repository contains the Transformers port of the official TimesFM 2.5 PyTorch release. This model is converted from the official TimesFM 2.5 PyTorch checkpoint and integrated into transformers as TimesFm25ModelForPrediction. The converted checkpoint preserves the original architecture and forecasting behavior, including: patch-based inputs for time-series contexts decoder-only self-attention stack point and quantile forecasts Weight conversion parity is verified by comparing converted-model forecasts against the official implementation outputs on deterministic inputs.
Open weights
apache-2.0
231M parameters
16,384 tokens
transformers
alt="Aurora Logo" src="https://cdn-uploads.huggingface.co/production/uploads/66276727368ec2a0b933772c/ytpsIAr98keUvNouoOVmb.png" width="30%" The official code repo of our ICLR 2026 paper: Aurora: Towards Universal Generative Multimodal Time Series Forecasting alt="ICLR 2026" src="https://img.shields.io/badge/ICLR%202026-Aurora-orange" alt="Python" src="https://img.shields.io/badge/Python-3.10%2B-blue" alt="PyTorch" src="https://img.shields.io/badge/PyTorch-2.4.1-blue" alt="GitHub Stars" src="https://img.shields.io/github/stars/decisionintelligence/Aurora?logo=github" alt="GitHub" src="https://img.shields.io/badge/GitHub-Aurora-black?logo=github" Aurora is a highly capable multimodal time…
Open weights
mit
211M parameters
10,000 tokens
Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. It chunks the historical time series context into patches of multiple observations, which are then input into the encoder. The decoder then uses these representations to directly generate quantile forecasts across multiple future steps—a method known as…
Open weights
apache-2.0
205M parameters
Model · Time series forecasting
Amazon
Update Feb 14, 2025: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. It chunks the historical time series context into patches of multiple observations, which are then input into the encoder. The decoder then uses these representations to directly generate quantile forecasts across multiple future steps—a method known as…
Open weights
apache-2.0
205M parameters
chronos-forecasting
