Spaces:
Running
Running
| title: Time Series Forecasting with Chronos-2 | |
| emoji: π | |
| colorFrom: blue | |
| colorTo: purple | |
| sdk: streamlit | |
| sdk_version: 1.38.0 | |
| app_file: app.py | |
| pinned: false | |
| # Time Series Forecasting Demo | |
| This demo uses **Chronos-2**, Amazon's state-of-the-art pretrained time series forecasting model, for accurate zero-shot predictions. | |
| ## Features | |
| - π Powered by Chronos-2 (120M parameters) | |
| - π Interactive forecasting with customizable prediction horizons | |
| - π Probabilistic forecasts with confidence intervals | |
| - π» Easy-to-use web interface built with Streamlit | |
| ## Usage | |
| 1. Enter your time series data (comma-separated values) | |
| 2. Select the forecast horizon (1-64 time steps) | |
| 3. View the forecast with 80% prediction intervals | |
| ## About Chronos-2 | |
| Chronos-2 offers zero-shot support for univariate, multivariate, and covariate-informed forecasting tasks, delivering state-of-the-art performance across multiple benchmarks. | |
| Learn more: [Chronos Forecasting Repository](https://github.com/amazon-science/chronos-forecasting) | |