Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)
-
Updated
Apr 13, 2025 - Python
Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)
An architectural persistence experiment for large language models. Claude’s Home gives an AI time, memory, and place by combining scheduled execution with a durable filesystem, allowing one continuous instance to reflect, create, and evolve across sessions.
The meta-architecture behind a high-leverage Claude Code setup. Installed by the very tool it optimizes.
Production-grade architecture patterns, decision frameworks, and best practices for building reliable AI agents. Framework-agnostic reference for engineers.
Jetta-Reinforcement-Learning-Hybrid-LLM-Architecture
Visualize some important concepts related to LLM architectures.
The Compositional Agentic Architecture (CAA): A blueprint for building reliable, deterministic, and safe industrial AI agents.
Multi-agent, policy-driven AI system for processing sensitive enterprise documents with extraction, analysis, verification, deterministic orchestration, and full audit logging. Designed for regulated environments (banking, finance, insurance).
Educational AI chat client: provider abstraction, token compression & state management in ~600 lines Python. Learn robust AI integration patterns.
The first end-to-end programming language and compiler fully developed by AI.
Hackable PyTorch template for decoder-only transformer architecture experiments. Llama baseline with RoPE, SwiGLU, RMSNorm. Swap components, train, compare
A collection of Small Language Models (SLMs) built from scratch in PyTorch.
A framework for creating portable AI systems you can load like a cartridge, from a single file.
An AI voice interview coach leveraging raw WebSockets for ultra-low-latency, bi-directional audio streaming. Features secure stateful session persistence and user metrics tracking via NextAuth.js to simulate real-time technical assessments.
A distributed, LLM-powered microservices architecture for deterministic marketing orchestration on Google Cloud.
DeepHelix — The DNA-Inspired DeepSeek Architecture
A structured collection of PyTorch notebooks and projects covering machine learning fundamentals, computer vision, and advanced AI, including multi-agent systems, candlestick pattern recognition, and transformer-based language models.
Reference architecture for structured AI memory lifecycle management — from the OPHION Memory OS Protocol.
This repository defines a reproducible Layer-0 functional compliance specification for Large Language Models.
Add a description, image, and links to the llm-architecture topic page so that developers can more easily learn about it.
To associate your repository with the llm-architecture topic, visit your repo's landing page and select "manage topics."