211 free LLM flashcards
A set of 211 free visual flashcards, one concept per card with a diagram and explanation, covering LLM topics from tokenization and attention through RAG, inference and deployment, organised into guided study paths.
This project is a collection of 211 free visual flashcards about large language models, each covering one concept with a diagram and an explanation. Cards are meant for interview preparation, revisiting previously learned material, or understanding a system currently being built.
The cards are organised around the layers of a modern LLM system: representing language (tokenization, embeddings), the transformer architecture (attention, normalization, position encodings), training objectives and scaling laws, adaptation and alignment (SFT, RLHF, DPO), inference (decoding, KV cache, quantization), prompting and context management, retrieval and agents, multimodal models, evaluation, safety behaviour, and shipping concerns such as APIs and rate limits. Guided study paths group related cards for topics like attention, RAG, inference and agents.
The public collection is served from a website built from this repository with a standard install, development-server, build and preview workflow; a larger paid collection of 376 cards adds a printable PDF, individual images and a full Anki deck.