Instructions to use google/timesfm-1.0-200m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TimesFM
How to use google/timesfm-1.0-200m with TimesFM:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Forecasting multivariate time series?
#13
by nikhilarundesai - opened
If I am understanding the model card correctly, the uploaded checkpoint / forecasting API can only forecast univariate time series (each value is a scalar/single-dimensional). Is this correct, or does the forecasting API also support multivariate time series (eg the trajectory of a particle moving in 3-space)?
Will support be added in the future for multivariate forecasting, or does no version of the model support this?
Hey, any updates on this? We now have Times FM 2.5, which is really advanced compared to previous models. Please let us know. Thanks.