John Broadway
john-broadway
AI & ML interests
Independent AI researcher. Sovereign models on bare metal. RYS layer duplication — train-free reasoning-circuit discovery across 21 model variants and 10 architecture families. Retired disabled U.S. veteran building from home. The work speaks for itself.
Recent Activity
updated a model 11 days ago
john-broadway/TinyLlama-1.1B-RYS-10-14-GGUF updated a model 11 days ago
john-broadway/Qwen2.5-0.5B-RYS-3-7-GGUF updated a model 11 days ago
john-broadway/Llama-3.2-1B-RYS-10-13-GGUFOrganizations
None yet
Cross-architecture RYS sweep — Yi-1.5-6B-Chat (rare three-way positive lift across math + EQ + reasoning)
1
#5 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — gemma-2-9b-it (early-layer reasoning circuit L14; highest baseline EQ in corpus)
1
#69 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — Qwen2.5-Coder-1.5B-Instruct (+35.29% reasoning, specialization unlock)
1
#7 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — Granite-3.1-1B-A400M-Instruct, first MoE result (+52.94% reasoning)
1
#2 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — Llama-3.2-3B-Instruct (biggest math lift in corpus +14.32; family spans entire baseline curve)
1
#282 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — Llama-3.1-8B-Instruct (richer multi-circuit than Qwen2.5-7B at same scale; 15 of 66 boosters)
1
#370 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — Llama-3.2-1B-Instruct lifts reasoning 0%→76%
1
#174 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — SmolLM2-1.7B-Instruct (negative result; 135M and 360M siblings respond normally)
#33 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — Qwen2.5-Coder-1.5B-Instruct (+35.29% reasoning, specialization unlock)
1
#7 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — Granite-3.1-1B-A400M-Instruct, first MoE result (+52.94% reasoning)
1
#2 opened about 2 months ago
by john-broadway
Cross-architecture RYS sweep — Llama-3.2-1B-Instruct lifts reasoning 0%→76%
1
#174 opened about 2 months ago
by john-broadway