AI drug discovery on Apple Silicon. De novo generation + drug repurposing. 100% local, no cloud, fully auditable.
Structured State Matrix Architecture (SSMA) is a high-performance framework designed for efficient sequence modeling, combining structured state space models with adaptive attention mechanisms.
PERSPECTIVE v2 — A 1.05 trillion parameter sparse Mixture-of-Experts language model that runs on consumer hardware (4 GB VRAM + 32 GB RAM). Features O(1) perspective decay recurrence, 3D torus manifold routing, native ternary {-1,0,+1} weights, holographic distributed memory, and hard geometric safety constraints. Built in Rust.
Research — Mixture-of-Experts efficiency analysis. Benchmarking sparse activation vs dense models on cost-per-token and quality.
Code and data for: Three Phases of Expert Routing — How Load Balance Evolves During MoE Training
Developed a Lasso Regression model applying L1 regularization for housing price prediction. The model achieved an R² score of ~0.64 while performing implicit feature selection and maintaining strong predictive performance.
Run AI-driven drug discovery models locally on Apple Silicon. Protect your data without the need for cloud infrastructure or external GPUs.
LiDAR point cloud completion for unstructured terrain in autonomous earthworks
Add a description, image, and links to the sparse-models topic page so that developers can more easily learn about it.
To associate your repository with the sparse-models topic, visit your repo's landing page and select "manage topics."