Granite PatchTST-FM-r2
AssessTools
A pre-trained patched Conformer model for time-series forecasting.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by model releases, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 6Hugging Face Blog·10/22/2026model_releaseIBM Granite time-series ensemble forecasting
Hugging Face highlights a new Granite Timeseries Ensemble recipe from IBM that combines four pre-trained time-series models into one forecasting interface. The approach returns point and quantile forecasts without retraining or fitted ensemble weights, aiming to reduce model-selection guesswork for different series types.