Nirman
Melady

Melady/TEMPO

No description available.

Model Documentation

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting



preprint

TEMPO_logo|50%



The official code for ["TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 2024)"]. TEMPO is one of the very first open source Time Series Foundation Models for forecasting task v1.0 version.

TEMPO-architecture

💡 Demos



1. Reproducing zero-shot experiments on ETTh2:



Please try to reproduc the zero-shot experiments on ETTh2 [here on Colab].

2. Zero-shot experiments on customer dataset:



We use the following Colab page to show the demo of building the customer dataset and directly do the inference via our pre-trained foundation model: [Colab]



🔧 Hands-on: Using Foundation Model



1. Download the repo




git clone git@github.com:DC-research/TEMPO.git


2. [Optional] Download the model and config file via commands


huggingface-cli download Melady/TEMPO config.json --local-dir ./TEMPO/TEMPO_checkpoints


huggingface-cli download Melady/TEMPO TEMPO-80M_v1.pth --local-dir ./TEMPO/TEMPO_checkpoints




huggingface-cli download Melady/TEMPO TEMPO-80M_v2.pth --local-dir ./TEMPO/TEMPO_checkpoints


3. Build the environment




conda create -n tempo python=3.8


conda activate tempo


cd TEMPO


pip install -r requirements.txt


4. Script Demo



A streamlining example showing how to perform forecasting using TEMPO:

python

Third-party library imports

import numpy as np
import torch
from numpy.random import choice

Local imports

from models.TEMPO import TEMPO


model = TEMPO.load_pretrained_model(
        device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu'),
        repo_id = "Melady/TEMPO",
        filename = "TEMPO-80M_v1.pth",
        cache_dir = "./checkpoints/TEMPO_checkpoints"  
)

input_data = np.random.rand(336)    
Random input data

with torch.no_grad():
        predicted_values = model.predict(input_data, pred_length=96)
print("Predicted values:")
print(predicted_values)



5. Online demo



Please try our foundation model demo [here].

TEMPO_demo.jpg

🔨 Advanced Practice: Full Training Workflow!



We also updated our models on HuggingFace: [Melady/TEMPO].



1. Get Data



Download the data from [Google Drive] or [Baidu Drive], and place the downloaded data in the folder./dataset. You can also download the STL results from [Google Drive], and place the downloaded data in the folder./stl.

2. Run Scripts



2.1 Pre-Training Stage


bash [ecl, etth1, etth2, ettm1, ettm2, traffic, weather].sh


2.2 Test/ Inference Stage



After training, we can test TEMPO model under the zero-shot setting:


bash [ecl, etth1, etth2, ettm1, ettm2, traffic, weather]_test.sh


TEMPO-results

Pre-trained Models



You can download the pre-trained model from [Google Drive] and then run the test script for fun.

TETS dataset



Here is the prompts use to generate the coresponding textual informaton of time series via [OPENAI ChatGPT-3.5 API]

TEMPO-prompt

The time series data are come from [S&P 500]. Here is the EBITDA case for one company from the dataset:

Company1_ebitda_summary

Example of generated contextual information for the Company marked above:

Company1_ebitda_summary_words.jpg



You can download the processed data with text embedding from GPT2 from: [[TETS]](https://drive.google.com/file/d/1Hu2KFj0kp4kIIpjbss2ciLCV_KiBreoJ/view?usp=drive_link ).

🚀 News



  • Oct 2024: 🚀 We've streamlined our code structure, enabling users to download the pre-trained model and perform zero-shot inference with a single line of code! Check out our demo for more details. Our model's download count on HuggingFace is now trackable!


  • Jun 2024: 🚀 We added demos for reproducing zero-shot experiments in Colab. We also added the demo of building the customer dataset and directly do the inference via our pre-trained foundation model: Colab
  • May 2024: 🚀 TEMPO has launched a GUI-based online demo, allowing users to directly interact with our foundation model!
  • May 2024: 🚀 TEMPO published the 80M pretrained foundation model in HuggingFace!
  • May 2024: 🧪 We added the code for pretraining and inference TEMPO models. You can find a pre-training script demo in this folder. We also added a script for the inference demo.


  • Mar 2024: 📈 Released TETS dataset from S&P 500 used in multimodal experiments in TEMPO.
  • Mar 2024: 🧪 TEMPO published the project code and the pre-trained checkpoint online!
  • Jan 2024: 🚀 TEMPO paper get accepted by ICLR!
  • Oct 2023: 🚀 TEMPO paper released on Arxiv!




    • ⏳ Upcoming Features



  • [✅] Parallel pre-training pipeline
  • [] Probabilistic forecasting
  • [] Multimodal dataset
  • [] Multimodal pre-training script


    • Contact

    Feel free to connect DefuCao@USC.EDU / YanLiu.CS@USC.EDU if you’re interested in applying TEMPO to your real-world application.

    Cite our work

    
@inproceedings{
cao2024tempo,
title={{TEMPO}: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting},
author={Defu Cao and Furong Jia and Sercan O Arik and Tomas Pfister and Yixiang Zheng and Wen Ye and Yan Liu},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=YH5w12OUuU}
}



    
@article{
   Jia_Wang_Zheng_Cao_Liu_2024, 
   title={GPT4MTS: Prompt-based Large Language Model for Multimodal Time-series Forecasting}, 
   volume={38}, 
   url={https://ojs.aaai.org/index.php/AAAI/article/view/30383}, 
   DOI={10.1609/aaai.v38i21.30383}, 
   number={21}, 
   journal={Proceedings of the AAAI Conference on Artificial Intelligence}, 
   author={Jia, Furong and Wang, Kevin and Zheng, Yixiang and Cao, Defu and Liu, Yan}, 
   year={2024}, month={Mar.}, pages={23343-23351} 
   }

    Files & Weights

    FilenameSizeAction
    TEMPO-80M_v1.pth 0.27 GB
    TEMPO-80M_v2.pth 0.27 GB