Chronos - T5 - mini Open-source Time Series Forecasting Model, Free for Probabilistic Forecasting

Chronos T5 Mini

Developed by amazon

Chronos-T5 is a pretrained time series forecasting model based on a language model architecture, achieving probabilistic forecasting by converting time series into token sequences and training the language model using cross-entropy loss.

Climate Model

Transformers

Open Source License:Apache-2.0 #Time Series Forecasting #Probabilistic Forecasting #Language Model Architecture

Downloads 61.15k

Release Time : 2/21/2024

Model Overview

Chronos-T5 is a family of pretrained time series forecasting models that adopt the T5 architecture, converting time series into token sequences through scaling and quantization, and training the language model using cross-entropy loss. After training, probabilistic forecasts are obtained by sampling multiple future trajectories given historical context.

Model Features

Pretrained Model

Pretrained on a large amount of public time series data and synthetic data generated by Gaussian processes, demonstrating strong generalization capabilities.

Probabilistic Forecasting

Provides probabilistic forecast distributions by autoregressively sampling multiple future trajectories, rather than single-point predictions.

Efficient Inference

Adopts the T5 architecture with fewer parameters, ensuring high inference efficiency.

Multi-Domain Applicability

Suitable for various time series forecasting tasks, such as finance, meteorology, sales forecasting, etc.

Model Capabilities

Time Series Forecasting

Probabilistic Forecasting

Multi-Trajectory Sampling

Use Cases

Finance

Stock Price Prediction

Predicts future stock price trends and volatility ranges.

Provides probabilistic forecast distributions to help investors assess risks.

Meteorology

Temperature Prediction

Predicts future temperature changes over a period.

Provides probabilistic forecast intervals to help meteorological departments issue warnings.

Sales

Sales Forecasting

Predicts future product sales volumes.

Helps businesses optimize inventory management and production planning.

🚀 Chronos-T5 (Mini)

Chronos-T5 (Mini) is a pre - trained time - series forecasting model. It transforms time - series data into tokens and uses a language - model architecture for training. With large - scale public time - series data and synthetic data, it can generate probabilistic forecasts.

🚀 Quick Start

Update Information

🚀 Update 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.
🚀 Update 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.

Model Introduction

Chronos is a family of pretrained time series forecasting models based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross - entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as 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, trained on large - scale time - series data. They can generate probabilistic forecasts by sampling multiple future trajectories, and have high accuracy, speed, and memory efficiency.

📦 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-mini",
  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

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.

Property	Details
Model Type	The models in this repository are based on the T5 architecture.
Training Data	Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.

Model	Parameters	Based on
chronos-t5-tiny	8M	t5-efficient-tiny
chronos-t5-mini	20M	t5-efficient-mini
chronos-t5-small	46M	t5-efficient-small
chronos-t5-base	200M	t5-efficient-base
chronos-t5-large	710M	t5-efficient-large

📄 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,
    title={Chronos: Learning the Language of Time Series},
    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},
    journal={Transactions on Machine Learning Research},
    issn={2835 - 8856},
    year={2024},
    url={https://openreview.net/forum?id=gerNCVqqtR}
}

🔧 Technical Details

See CONTRIBUTING for more information.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご