LLamaSharp/docs/Examples/BatchedExecutorRewind.md

490 B

BatchedExecutor - Rewind

This example demonstrates using the BatchedExecutor to split one sequence into multiple sequences. See the source code here.

A single conversation is prompted and then continued for 24 tokens, after that it is re-wound by 12 tokens and continued from there. Rewinding simply sets the conversation back to an earlier state and requires no extra computation.