Fine-tuning LLMs with RAFT, dataset curation, and multi-hardware inference. Focused on specialist models, agentic workflows, and accessible AI applications.
-
neotoi-coder
A Rust / Dioxus 0.7 specialist fine-tuned via RAFT on Qwen3 (3 sizes), optimized for Tailwind v4 + WCAG 2.2 AAA accessibility and dioxus-primitives discipline. Built with CRAFT on a homelab RTX 3090 Ti. No cloud GPUs.
4b 8b 15b57 Pulls 5 Tags Updated 1 month ago
-
svelte-coder
A Svelte 5 / SvelteKit 2 specialist coding model in three sizes. Free to use under MIT. Built on a homelab RTX 3090 Ti using cretrieval-augmented fine-tuning (RAFT).
4b 8b 14b51 Pulls 7 Tags Updated 1 month ago
-
public-a11y-coder
Open-source accessibility coding assistant for the public sector. WCAG 2.2 Level AA conformance, Drupal 11, PHP 8.3, Drush 12, Python 3.12, and Playwright (TypeScript) with both axe-core and Siteimprove Alfa.
4b 14b14 Pulls 2 Tags Updated 1 month ago
-
a11yequitas-gr
A11y Equitas Granite line — fine-tuned accessibility assistant for content editors, developers, and QA teams working on WCAG 2.2 AA compliance. Updated models for RHEL9 and RHEL10.
3b5 Tags Updated 2 weeks ago