Time Series Forecasting
Chronos
Safetensors
t5
time series
forecasting
pretrained models
foundation models
time series foundation models
time-series
Instructions to use amazon/chronos-bolt-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chronos
How to use amazon/chronos-bolt-mini with Chronos:
pip install chronos-forecasting
import pandas as pd from chronos import BaseChronosPipeline pipeline = BaseChronosPipeline.from_pretrained("amazon/chronos-bolt-mini", device_map="cuda") # Load historical data context_df = pd.read_csv("https://autogluon.s3.us-west-2.amazonaws.com/datasets/timeseries/misc/AirPassengers.csv") # Generate predictions pred_df = pipeline.predict_df( context_df, prediction_length=36, # Number of steps to forecast quantile_levels=[0.1, 0.5, 0.9], # Quantiles for probabilistic forecast id_column="item_id", # Column identifying different time series timestamp_column="Month", # Column with datetime information target="#Passengers", # Column(s) with time series values to predict ) - Notebooks
- Google Colab
- Kaggle
Improve model card: Add `transformers` library tag and Chronos-2 paper link
#1
by nielsr HF Staff - opened
This PR improves the model card for amazon/chronos-bolt-mini by making the following updates:
- Added
library_name: transformersmetadata: Theconfig.jsonindicates the model is based on a T5 architecture and includestransformers_version, confirming its compatibility with the Hugging Facetransformerslibrary. This addition will enable an automated, predefined code snippet on the Hub, showcasing how to use the model. - Added prominent link to Chronos-2 paper: The model card now explicitly links to the associated paper, "Chronos-2: From Univariate to Universal Forecasting", providing immediate context and discoverability for researchers.
- Updated Citation section: The citation section has been expanded to include the BibTeX entry for the Chronos-2 paper, aligning with the comprehensive citation provided in the official GitHub repository.
These updates enhance the model card's accuracy, utility, and adherence to documentation best practices.