A Systematic Guide to Large Language Models

From core concepts to practical applications, building your AI knowledge base

Start Exploring

Foundations

Core concepts behind LLMs: Transformers, Tokenization, Embeddings and more

Local Models

Deploy and run open-source models locally: Ollama, llama.cpp, quantization

Prompt Engineering

Effective prompting techniques: prompt design, few-shot, chain of thought

RAG

Retrieval-Augmented Generation: vector databases, embedding search, knowledge bases

Fine-tuning

Model fine-tuning: LoRA, dataset preparation, training pipelines and evaluation

Agents

AI agents: tool use, ReAct pattern, multi-step reasoning and autonomous execution