Orion Language Of Thought

Compact Mentalese symbolic format trained via SFT, then refined with SLPO (Shorter Length Preference Optimization) to reward concise correct solutions without over-penalizing necessarily long reasoning. Compress reasoning while maintaining accuracy.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 5f52c5c65b

Frequently asked questions

npx get-skill add adu2021/orion-language-of-thought