karpathy/LLM101n resource

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

37505 stars · 2078 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

LLM101n is a planned course by Andrej Karpathy and Eureka Labs that teaches building a Storyteller AI large language model end-to-end, from basics to a ChatGPT-like web app, in Python, C, and CUDA. The repository currently only contains a syllabus and is archived while the course is under development.

Use cases

• learn how large language models work from scratch
• build a GPT-style transformer step by step
• understand backpropagation and training optimization
• learn tokenization, kv-cache, and quantization
• study finetuning techniques like SFT, LoRA, RLHF, and DPO
• learn to deploy an LLM as a web app

When to choose

• you want a structured, fundamentals-first path to understanding LLMs and deep learning
• you prefer building everything from scratch rather than using high-level frameworks
• you want to follow Karpathy's teaching style after enjoying nanoGPT or Zero To Hero

When to avoid

• you need a ready-to-use course today - it does not yet exist and the repo is archived
• you want production LLM tooling rather than educational material
• you need a license-cleared codebase to reuse - no license is specified

Facets

learning-resource · maturity experimental

machine-learning deep-learning llm-training llm-inference large-language-models deep-learning machine-learning education tutorials python cpp cross-platform course llm-from-scratch storyteller transformers archived eureka-labs syllabus education gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="karpathy/LLM101n")