Expediting generative token production using speculative sampling, added guidance, and language models of different capacities

Abstract

A technique accelerates the generative production of tokens using a target language model that operates in cooperation with a draft language model. The target language model is more capable, but slower, compared to the draft language model. In operation, the draft language model transforms prompt tokens into draft tokens. The target language model edits the draft tokens, e.g., by selecting zero, one, or more of the draft tokens, and by also predicting a next token to follow the draft token(s) (if any) that are selected. Further, the target language model produces guidance vector information. In a subsequent cycle, the draft language model uses the guidance vector information to produce an updated set of set of draft tokens. The guidance vector information informs the draft language model of the embedding space being used by the target language model. This achieves a more effective cooperative relation between the two models.