Home / Topics
01
LLM Fundamentals
How large language models actually work, from tokens to fine-tuning.
Guides
01
Tokens and embeddings
What a model really sees, why token counts matter for cost and latency, and how text becomes vectors.
8 min 02Transformers and attention
Self-attention step by step, multi-head attention, the decoder-only architecture and the KV cache.
12 min 03Training, fine-tuning and alignment
Pre-training, supervised fine-tuning, RLHF and DPO, LoRA, and how to choose between prompting, RAG and fine-tuning.
10 minInterview questions
All 13 with answers →- What is a token, and why do LLMs use subword tokenization instead of words or characters?
- Explain scaled dot-product attention. Why divide by √d_k?
- What is the KV cache and what problem does it solve?
- Why is attention O(n²), and what are common ways to handle long context?
- What's the difference between MHA, MQA and GQA?