Time Series Forecasting
Transformers
PyTorch
Safetensors
patchtsmixer
time series
forecasting
pretrained models
foundation models
time series foundation models
time-series
Instructions to use ibm-granite/granite-timeseries-patchtsmixer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-granite/granite-timeseries-patchtsmixer with Transformers:
# Load model directly from transformers import AutoTokenizer, PatchTSMixerForPrediction tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-timeseries-patchtsmixer") model = PatchTSMixerForPrediction.from_pretrained("ibm-granite/granite-timeseries-patchtsmixer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- abeb88018e515ffdbfdd0533629eb380e99afeeb069ec6cd58a6b73dc09907c0
- Size of remote file:
- 797 kB
- SHA256:
- 684fb8f2ee6e38ab430e77a4e8cd86028c34a150d1251f7d2a624f4de0e8c9c8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.