MOMENT-Large

MOMENT-Large is the large checkpoint in AutonLab's general-purpose time-series foundation-model family, the highest-capacity member of the line. Official sources frame MOMENT as a multi-task representation model that transfers across forecasting, classification, anomaly detection, imputation, reconstruction, and embedding extraction rather than optimizing purely for one forecasting benchmark, and the Large variant offers the most capacity for that transfer.

Architecturally it is the same design as its siblings: a patch-based encoder-only transformer trained with masked time-series modeling, where masked spans are reconstructed during pretraining and the encoder yields representations reusable across downstream tasks. It is trained on Timeseries-PILE, built from public forecasting, classification, and anomaly-detection corpora including Informer datasets, Monash, UCR/UEA, and TSB-UAD. The upstream momentfm package warns that only the reconstruction head is pretrained and that forecasting heads must be fine-tuned, so it is best used as a shared backbone across downstream tasks rather than assumed to be the strongest default zero-shot forecaster.