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-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chronos
How to use amazon/chronos-bolt-tiny with Chronos:
pip install chronos-forecasting
import pandas as pd from chronos import BaseChronosPipeline pipeline = BaseChronosPipeline.from_pretrained("amazon/chronos-bolt-tiny", 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
Update model card with Chronos-2 paper link, GitHub repo, `transformers` tag, and full citation
#2
by nielsr HF Staff - opened
This PR updates the model card for chronos-bolt-tiny to reflect the latest information and improve its discoverability and utility on the Hugging Face Hub.
Specifically, it:
- Adds
library_name: transformersto the metadata, enabling the automated "Load with Transformers" usage widget, as the model is based on the T5 architecture and uses the Transformers library. - Adds a prominent link to the Chronos-2: From Univariate to Universal Forecasting paper at the top of the model card, as this is the paper in which the model was presented.
- Adds a direct link to the Chronos Forecasting GitHub repository for easy access to the code.
- Updates the
Citationsection to include both the original Chronos paper and the Chronos-2 paper, aligning with the comprehensive citation provided in the GitHub repository's README.
These changes enhance the model card's completeness and help users better understand and utilize the model.