Overview of self-supervised learning of tiny models, including distillation-based methods (aks. self-supervised distillation) and non-distillation methods.

⚡ A talking desktop Pikachu that runs 100% on-device — MiniCPM5-1B brain + VoxCPM voice + Nemotron ears, every model ≤1B params. No cloud, works with the Wi-Fi off.

🔍 Explore recursive reasoning with TinyRecursiveModels, a compact 7M parameter neural network achieving high scores on tough tasks without massive resources.

🚀 Streamline parallel development with Ralph MCP: run multiple PRDs in isolated workspaces, ensuring quality and efficient merging.

Phi-3-Vision model test - running locally

First 1-bit (BitNet b1.58) recursive reasoner for Sudoku-Extreme - distilled from a 7M-param FP TRM teacher into a 1.4 MB ternary student

Local, project-scoped memory system for LLMs with evidence-based truth validation. Provides reliable long-term context via OpenAI-compatible Proxy and MCP, using Chain-of-Verification (CoVe) to eliminate hallucinations and the Ralph Loop for autonomous codebase repair.

Testing the Moondream tiny vision model

Train the smallest LM you can that fits in 16MB. Best model wins!

🚀 Implement the Tiny Recursive Model (TRM) for improved performance in recursive tasks, building on the HRM framework by Sapient AI.