metadata

license: apache-2.0
library_name: timer
pipeline_tag: time-series-forecasting
datasets:
  - thuml/UTSD
  - Salesforce/lotsa_data
metrics:
  - mae
  - mse
tags:
  - time-series
  - forecasting
  - foundation-models
  - pretrained-models
  - time-series-foundation-models
  - large-time-series-models

Time-Series Transformer (Timer)

Large time-series model introduced in this paper and enhanced with our further work.

This version is pre-trained on 260B time points with 84M parameters, a lightweight generative Transformer for zero-shot point forecasting.

We evaluate the model on the following benchmark: TSLib Dataset.

For more information, please see the Github Repo.

There's indeed room for improvement in this small model. We are actively working around it and are glad to see constructive suggestions and noteworthy cases :)

Quickstart

pip install transformers==4.40.1 # Use this version and Python 3.10 for stable compatibility

import torch
from transformers import AutoModelForCausalLM

# load pretrain model
model = AutoModelForCausalLM.from_pretrained('thuml/timer-base-84m', trust_remote_code=True)

# prepare input
batch_size, lookback_length = 1, 2880
seqs = torch.randn(batch_size, lookback_length)

# generate forecast
prediction_length = 96
output = model.generate(seqs, max_new_tokens=prediction_length)

print(output.shape)

A notebook example is also provided here. Try it out!

Specification

Architecture: Causal Transformer (Decoder-only)
Pre-training Scale: 260B time points
Context Length: up to 2880
Parameter Count: 84M
Patch Length: 96
Number of Layers: 8

Acknowledgments

This work was supported by the National Natural Science Foundation of China (62022050 and U2342217), the BNRist Innovation Fund (BNR2024RC01010), and the National Engineering Research Center for Big Data Software. The model is mostly built from the Internet public time series dataset, which comes from different research teams and providers. We sincerely thank all individuals and organizations who have contributed the data. Without their generous sharing, this model would not have existed.

Citation

@inproceedings{liutimer,
  title={Timer: Generative Pre-trained Transformers Are Large Time Series Models},
  author={Liu, Yong and Zhang, Haoran and Li, Chenyu and Huang, Xiangdong and Wang, Jianmin and Long, Mingsheng},
  booktitle={Forty-first International Conference on Machine Learning}
}

@article{liu2024timer,
  title={Timer-XL: Long-Context Transformers for Unified Time Series Forecasting},
  author={Liu, Yong and Qin, Guo and Huang, Xiangdong and Wang, Jianmin and Long, Mingsheng},
  journal={arXiv preprint arXiv:2410.04803},
  year={2024}
}

License

This model is licensed under the Apache-2.0 License.