Time Series Transformer (trained on monash_tsf/tourism-monthly)

Time Series Transformer model trained on the tourism-monthly dataset for 30 epochs.

Model description

The Time Series Transformer is a vanilla encoder-decoder Transformer for time-series forecasting. The model is trained in the same way as one trains a Transformer for machine translation. At inference time, the model autoregressively generates samples, one time step at a time.

Usage

We refer to the documentation regarding usage.

Downloads last month
3,211
Safetensors
Model size
30.5k params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Dataset used to train huggingface/time-series-transformer-tourism-monthly

Space using huggingface/time-series-transformer-tourism-monthly 1