TSorchestra

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

(★ 42)

Time Series Orchestra (TSorchestra) is a novel ensemble framework designed for zero-shot time series forecasting. It is built upon a curated collection of time series foundation models. The architecture is designed to leverage the specialized capabilities of its constituent models to deliver SOTA performance and generalization across datasets.

TSorchestra 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# TSorchestra

[Ongoing Project]

Time Series Orchestra (TSorchestra) is a novel ensemble framework designed for zero-shot time series forecasting. It's a curated collection of time series foundation models (TSFMs) that leverages each TSFM's strengths to create something greater than the sum of its parts, yielding SOTA performance.

## Set Up

---

1. Create a new conda environment named `tso` from our .yml file:

```bash
conda env create -f environment.yml
```

2. Download the [GIFT-Eval benchmark](https://huggingface.co/spaces/Salesforce/GIFT-Eval) from Hugging Face:

```bash
mkdir data
huggingface-cli download Salesforce/GiftEval --repo-type=dataset --local-dir data
```

3. Set up the environment variable for loading the datasets:
``bash 
echo "GIFT_EVAL=data" >> .env
``

## Usage

---

Run our evaluation script to reproduce our results:

```bash
chmod +x ./cli/eval.sh
./cli/eval.sh
```

## Cite

```
@article{cao2025conversational,
  title={Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting},
  author={Cao, Defu and Gee, Michael and Liu, Jinbo and Wang, Hengxuan and Yang, Wei and Wang, Rui and Liu, Yan},
  journal={arXiv preprint arXiv:2512.16022},
  year={2025}
}
```

TSorchestra

TSorchestra 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

TSorchestra

TSorchestra 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README