Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training

Keyword: Fine-tuning

Publisher: Github.com

Published: Mar 18, 2026

I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B improves logical deduction from 0.220.76 … [+7245 chars]

Read Full Story ↗