Othink R1 Fast Slow Thinking

Enable reasoning models to adaptively switch between fast direct responses and slow detailed reasoning, reducing token consumption by 15-40% while maintaining accuracy through dual-mode fine-tuning.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 085b37aba6

Frequently asked questions

npx get-skill add adu2021/othink-r1-fast-slow-thinking