flowmatic-astana-patchtst-density-forecaster

Forecast smart-city sensor values for core processing-unit routing and prediction.

Model summary

Field Value
Architecture patchtst_forecast
Dataset astana
Source checkpoint q1_astana_patchtst_density_forecaster
Test metrics {"test_loss": 0.3425562016270305, "test_mae": 0.3431200683116913, "test_rmse": 0.5852830410003662}

Files

  • model.safetensors โ€” primary weights
  • model.torchscript.pt โ€” TorchScript export (when present)
  • metadata.json โ€” schema, scaler, metrics
  • model_card.md โ€” training card

Usage in Flowmatic

Deploy in the Core Unit with model ID flowmatic-astana-patchtst-density-forecaster (prefixed by your Hugging Face username in the UI).

Inference is routed through Flowmatic's model-inference service using your organization Hugging Face token.

Downloads last month
6
Safetensors
Model size
101k params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support