Cola Test Time Depth Adaptation LLM

Dynamically adapt LLM depth per input at test time by skipping, repeating, or reordering layers using MCTS search, correcting 60% of initially wrong predictions and processing 75% of correct predictions with shorter architectures without retraining.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 98629d3767

Frequently asked questions

npx get-skill add adu2021/cola-test-time-depth-adaptation-llm