mad-lab-ai

- Large Language Models (LLM) - Model Quantization (GGUF, TQ3/TQ4) - Fine-tuning & LoRA (QLoRA, SFTTrainer) - Reinforcement Learning from Human Feedback (RLHF) - Retrieval-Augmented Generation (RAG) - Knowledge Graphs & Agent Memory - Multi-Agent Systems - Mixture of Experts (MoE) - ROCm / AMD GPU ML - Autonomous AI Agents - Text Generation & Inference - On-Device / Consumer Hardware ML