Chronos-2: From Univariate to Universal Forecasting
Paper • 2510.15821 • Published • 26
Time Series Forecasting
Chronos
Safetensors
t5
time series
forecasting
foundation models
pretrained models
import pandas as pd
from chronos import BaseChronosPipeline
pipeline = BaseChronosPipeline.from_pretrained("autogluon/chronos-2-synth", 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
)Chronos-2-Synth
This is a variant of the Chronos-2 model which has only been trained on synthetic univariate and multivariate data. For usage and details on the Chronos-2 model, please refer to https://huggingface.co/autogluon/chronos-2.
Citation
If you find Chronos-2 useful for your research, please consider citing the associated paper:
@article{ansari2025chronos2,
title = {Chronos-2: From Univariate to Universal Forecasting},
author = {Abdul Fatir Ansari and Oleksandr Shchur and Jaris Küken and Andreas Auer and Boran Han and Pedro Mercado and Syama Sundar Rangapuram and Huibin Shen and Lorenzo Stella and Xiyuan Zhang and Mononito Goswami and Shubham Kapoor and Danielle C. Maddix and Pablo Guerron and Tony Hu and Junming Yin and Nick Erickson and Prateek Mutalik Desai and Hao Wang and Huzefa Rangwala and George Karypis and Yuyang Wang and Michael Bohlke-Schneider},
year = {2025},
url = {https://arxiv.org/abs/2510.15821}
}
- Downloads last month
- 242,954
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support