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-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chronos
How to use amazon/chronos-bolt-base with Chronos:
pip install chronos-forecasting
import pandas as pd from chronos import BaseChronosPipeline pipeline = BaseChronosPipeline.from_pretrained("amazon/chronos-bolt-base", 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 with Chronos-2 paper, code links and `library_name`
#3
by nielsr HF Staff - opened
This PR enhances the model card for amazon/chronos-bolt-base by:
- Adding explicit links to the primary paper (Chronos-2: From Univariate to Universal Forecasting), the GitHub repository (https://github.com/amazon-science/chronos-forecasting), and the project page at the top of the README.
- Setting the
library_nametochronos-forecastingin the metadata, which enables an automated code snippet for direct usage with thechronos-forecastinglibrary. - Updating the "Citation" section to include the BibTeX entry for the Chronos-2 paper, providing comprehensive citation information.
Please review and merge this PR if everything looks good.