Chronos T5 Tiny

🚀 Chronos-T5 (Tiny)

Chronos is a family of pretrained time series forecasting models. It transforms time - series data into tokens, trains a language model on these tokens, and then generates probabilistic forecasts. The models are trained on a large corpus of public time - series data and synthetic data.

🚀 Quick Start

Updates

• Feb 14, 2025: Chronos - Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code.
• Nov 27, 2024: We have released Chronos - Bolt⚡️ models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory - efficient than the original Chronos models of the same size. Check out the new models here.

Chronos transforms a time series into a sequence of tokens via scaling and quantization. A language model is then trained on these tokens using the cross - entropy loss. After training, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. The models are trained on a large corpus of publicly available time series data and synthetic data generated using Gaussian processes.

For details on Chronos models, training data and procedures, and experimental results, please refer to the paper Chronos: Learning the Language of Time Series.

Fig. 1: High - level depiction of Chronos. (Left) The input time series is scaled and quantized to obtain a sequence of tokens. (Center) The tokens are fed into a language model which may either be an encoder - decoder or a decoder - only model. The model is trained using the cross - entropy loss. (Right) During inference, we autoregressively sample tokens from the model and map them back to numerical values. Multiple trajectories are sampled to obtain a predictive distribution.

✨ Features

Chronos models are based on language model architectures. They can transform time series data into tokens, train on these tokens, and generate probabilistic forecasts. They are trained on a large amount of public and synthetic time series data.

📦 Installation

To perform inference with Chronos models, install the package in the GitHub companion repo by running:

pip install git+https://github.com/amazon-science/chronos-forecasting.git

💻 Usage Examples

Basic Usage

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import torch
from chronos import ChronosPipeline

pipeline = ChronosPipeline.from_pretrained(
  "amazon/chronos-t5-tiny",
  device_map="cuda",
  torch_dtype=torch.bfloat16,
)

df = pd.read_csv("https://raw.githubusercontent.com/AileenNielsen/TimeSeriesAnalysisWithPython/master/data/AirPassengers.csv")

# context must be either a 1D tensor, a list of 1D tensors,
# or a left-padded 2D tensor with batch as the first dimension
context = torch.tensor(df["#Passengers"])
prediction_length = 12
forecast = pipeline.predict(context, prediction_length)  # shape [num_series, num_samples, prediction_length]

# visualize the forecast
forecast_index = range(len(df), len(df) + prediction_length)
low, median, high = np.quantile(forecast[0].numpy(), [0.1, 0.5, 0.9], axis=0)

plt.figure(figsize=(8, 4))
plt.plot(df["#Passengers"], color="royalblue", label="historical data")
plt.plot(forecast_index, median, color="tomato", label="median forecast")
plt.fill_between(forecast_index, low, high, color="tomato", alpha=0.3, label="80% prediction interval")
plt.legend()
plt.grid()
plt.show()

📚 Documentation

For details on Chronos models, training data and procedures, and experimental results, please refer to the paper Chronos: Learning the Language of Time Series.

Architecture

The models in this repository are based on the T5 architecture. The only difference is in the vocabulary size: Chronos - T5 models use 4096 different tokens, compared to 32128 of the original T5 models, resulting in fewer parameters.

📄 License

This project is licensed under the Apache - 2.0 License.

📄 Citation

If you find Chronos models useful for your research, please consider citing the associated paper:

@article{ansari2024chronos,
  author  = {Ansari, Abdul Fatir and Stella, Lorenzo and Turkmen, Caner and Zhang, Xiyuan, and Mercado, Pedro and Shen, Huibin and Shchur, Oleksandr and Rangapuram, Syama Syndar and Pineda Arango, Sebastian and Kapoor, Shubham and Zschiegner, Jasper and Maddix, Danielle C. and Mahoney, Michael W. and Torkkola, Kari and Gordon Wilson, Andrew and Bohlke - Schneider, Michael and Wang, Yuyang},
  title   = {Chronos: Learning the Language of Time Series},
  journal = {arXiv preprint arXiv:2403.07815},
  year    = {2024}
}

🔒 Security

See CONTRIBUTING for more information.