TPSTokens Per Second

Granite Time Series PatchTST-FM-r2

Ibm🇺🇸 United States
active
Compare with other models →
Context window8K tokens

Version History

r2major

PatchTST-FM-r2 upgrades the architecture from standard transformer layers to conformer blocks combining attention with temporal convolution, expands from 20 to 30 blocks, and adds overlapping patches with Hamming-window smoothing, improving zero-shot forecasting accuracy over predecessor PatchTST-FM-r1.

Coverage

model releaseIbm

IBM's Granite PatchTST-FM-r2 Tops Permissively Licensed Time Series Forecasting Models on GIFT-Eval

IBM has released Granite Time Series PatchTST-FM-r2, a 385M-parameter forecasting model that ranks #2 overall among replicable zero-shot models on the GIFT-Eval benchmark and first among those with permissive, commercial-friendly licensing. The model uses conformer-based architecture and supports probabilistic forecasts across up to 8,192-step contexts.

3 min read
IBMGranitetime series