SalesforceAIResearch/uni2ts
A PyTorch library for pre-training, fine-tuning, and evaluating universal time series transformer models (Moirai, Moirai-MoE) at scale.
Not currently ranked — collecting fresh signals.
star history
Uni2TS provides a unified framework for large-scale pre-training, fine-tuning, inference, and evaluation of time series forecasting transformers. It implements the Moirai and Moirai-MoE model families and includes the GIFT-Eval benchmark for general time series forecasting evaluation. The library offers model weights on Hugging Face with a leaderboard for comparing forecasting performance.
Frequently asked
- What is SalesforceAIResearch/uni2ts?
- A PyTorch library for pre-training, fine-tuning, and evaluating universal time series transformer models (Moirai, Moirai-MoE) at scale.
- Is uni2ts open source?
- Yes — SalesforceAIResearch/uni2ts is open source, released under the Apache-2.0 license.
- What language is uni2ts written in?
- SalesforceAIResearch/uni2ts is primarily written in Jupyter Notebook.
- How popular is uni2ts?
- SalesforceAIResearch/uni2ts has 1.6k stars on GitHub.
- Where can I find uni2ts?
- SalesforceAIResearch/uni2ts is on GitHub at https://github.com/SalesforceAIResearch/uni2ts.