Time Series Forecasting
Chronos
Safetensors
t5
time series
forecasting
foundation models
pretrained models

Add update for new SageMaker deployment guide

#3
by shchuro - opened
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -21,6 +21,9 @@ library_name: chronos-forecasting
21
  ---
22
 
23
  # Chronos-2
 
 
 
24
  **Chronos-2** is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting.
25
  It supports **univariate**, **multivariate**, and **covariate-informed** tasks within a single architecture.
26
  Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates.
 
21
  ---
22
 
23
  # Chronos-2
24
+
25
+ **Update Dec 30, 2025:** ☁️ Deploy Chronos-2 on Amazon SageMaker. [New guide](https://github.com/amazon-science/chronos-forecasting/blob/main/notebooks/deploy-chronos-to-amazon-sagemaker.ipynb) covers real-time GPU and CPU inference, serverless endpoints (run on demand, no idle costs), and batch transform for large-scale forecasting.
26
+
27
  **Chronos-2** is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting.
28
  It supports **univariate**, **multivariate**, and **covariate-informed** tasks within a single architecture.
29
  Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates.