TimesFM 3.0 Forecasting Demo

Tools

• timesfm_3_pytorch_demo__symbols_for_source
• timesfm_3_pytorch_demo_backtest_market Fetch a live FX or Hyperliquid series and walk-forward backtest it.
• timesfm_3_pytorch_demo_backtest_open_to_close Walk-forward 1-day TimesFM forecasts; trade each session open→close. For day t the model sees only prior closes (no today's close). At the morning open it goes long if the forecasted close is above the open, otherwise short, and covers at the session close. Optional overlays (gap, SMA, RSI, shorts-only) use only data available at the open. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
• timesfm_3_pytorch_demo_forecast_multivariate Jointly forecast several related series with TimesFM 3.0. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
• timesfm_3_pytorch_demo_forecast_univariate Forecast a univariate series with TimesFM 3.0. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
• timesfm_3_pytorch_demo_load_univariate_example Fill the input box with a built-in synthetic series.
• timesfm_3_pytorch_demo_load_univariate_example_1 Fill the input box with a built-in synthetic series.
• timesfm_3_pytorch_demo_load_univariate_example_2 Fill the input box with a built-in synthetic series.

No tool matches.

As the server's own listing gives them. We never call a tool.