Open Models Almanac
Methodsmodel architectureprediction head

single mention · model architecture

Multi-Token Prediction module for residual codebooks

Uses MTP to model residual speech-codebook tokens for fine-grained acoustic modeling and control.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See prediction head for the methods filed beside it.

Also called multi-token prediction (MTP) module.

Filed under model architecture › prediction head