← All tutorials
Skill Zuno · skillzunos.com · AI
LLMs tutorial
Learn LLMs on Skill Zuno. This LLMs tutorial covers New, Easy, Medium, Hard, and Diff levels so you can study practical LLMs problems on skillzunos.com.
Open LLMs on Skill ZunoAlso see the LLMs interview questions.
Large language models are transformer models with billions of parameters trained on vast amounts of text to predict the next token. After pretraining they are tuned with instructions and human feedback to follow requests, and they can write, summarise, reason and use tools. Interviews cover pretraining and alignment, tokens and context windows, sampling, prompting, hallucination and evaluation.
LLMs topics covered
- How LLMs are trained — Pretraining on next-token prediction, then instruction tuning and RLHF or DPO.
- Tokens and context windows — How text becomes tokens, and what limits how much a model can read.
- Sampling and decoding — Temperature, top-p, top-k and greedy decoding.
- Prompt engineering — Clear instructions, examples, structured output and chain-of-thought.
- Hallucination and grounding — Why models make things up, and reducing it with retrieval and verification.
- Evaluating LLMs — Benchmarks, human evaluation and LLM-as-judge.
What you can learn
- LLMs tutorial for beginners and experienced developers
- Level-based practice: New, Easy, Medium, Hard, and Diff
- AI topics alongside LLMs on skillzunos.com