Time Series Forecasting
Transformers
Safetensors
kairos
time-series
forecasting
foundation-model
zero-shot
Instructions to use mldi-lab/Kairos_10m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mldi-lab/Kairos_10m with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mldi-lab/Kairos_10m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Multivariate forecasting
#3
by lorenzolaudato - opened
Hello,
is it possible to use model in multivariate way to predict more than a single target ?
Thanks,
Hi @lorenzolaudato ,
Thank you for your question.
Similar to most time series foundation models, Kairos currently only supports channel-independent forecasting (like PatchTST). This means that each variable in a multivariate time series is forecasted independently.
We are actively considering the modeling of inter-variable relationships in our future work.
Best regards.