Skip to main content

Module infer

Module infer 

Source
Expand description

MOMENT-1-large inference engine.

Architecture: T5 encoder-only transformer with patch embeddings.

  • RevIN normalization → patch embedding (value + position) → 24 T5 encoder blocks (RMSNorm + relative-bias MHA + gated-GELU FFN) → final RMSNorm → per-patch reconstruction head
  • Zero-shot forecasting: iteratively predict 8 steps at a time using the reconstruction head applied to the last patch’s encoder output.

Structs§

MomentModel