A simple collection of important AI and LLM concepts explained in beginner-friendly language.
- LLM — Predicts the next token based on the context before it.
- Tokenization — Breaks text into smaller pieces called tokens.
- Context Window — The amount of information a model can process at one time.
- Embeddings — Converts text into numerical representations that capture meaning.
- Vector Database — Stores embeddings and finds similar information based on meaning.
- Cosine Similarity — Measures how similar two embeddings are.
- RAG — Retrieves relevant external information and gives it to the model with the user's question.
- MCP — A standard way for AI models to connect with tools and external services.
- Fine-Tuning — Further trains a general model for a specific task or behavior.
- Overfitting — When a model learns training data too closely and performs poorly on new data.
- Knowledge Distillation — A smaller model learns to imitate a larger model.
This repository is a quick reference for understanding common AI and LLM terminology in a simple way.
LLMs Tokenization Embeddings RAG MCP Fine-Tuning Vector Databases AI
Learning resource — continuously improving as I learn more about AI engineering.
Wahaj Ahmed
GitHub: Wahaj-Developer