afshinea/stanford-cme-295-transformers-large-language-models

VIP cheatsheet for Stanford's CME 295 Transformers and Large Language Models

What it solves

This project provides a centralized, concise reference for the complex concepts taught in Stanford's CME 295 course on Transformers and Large Language Models (LLMs), helping students and practitioners consolidate their understanding of the field.

How it works

The repository offers a comprehensive "VIP Cheatsheet" that summarizes core technical topics into a single, accessible format. It serves as a companion to the "Super Study Guide" book, which provides in-depth explanations and visual aids for the same curriculum.

Who it’s for

It is designed for students enrolled in the Stanford CME 295 course and any learners or professionals seeking a structured overview of modern AI architecture and training techniques.

Highlights

  • Covers foundational Transformer architecture, including self-attention and variants.
  • Details LLM training methods like fine-tuning (SFT, LoRA) and preference tuning (RLHF, DPO).
  • Explains technical optimizations such as distributed training, KV caching, and speculative decoding.
  • Includes information on advanced applications like AI agents and evaluation.
  • Available in 15 different languages to support a global audience.

Related

  • Project
    changyeyu/LLM-RL-Visualized

    LLM-RL-Visualized is a bilingual, diagram-heavy educational repository with 100+ original architecture diagrams explaining large language models, reinforcement learning, and related training techniques — organized into 11 topic sections with high-res SVG/PNG images and bonus PDFs.

  • Project
    alvinreal/awesome-opensource-ai

    The project is a curated list of open-source AI tools, models, and resources, organized into 14 categories. It prioritizes usefulness over popularity, includes projects regardless of star count, and invites contributions.

  • Project
    openTrinity/mycontext

    MyContext is a desktop app that continuously ingests a user’s work data (chat, docs, meetings, etc.) into a private, locally stored knowledge graph. The graph can be queried by LLMs, local agents, or authorized AI apps, providing them with a personal context layer for more informed responses. Features include a digital‑self assistant, natural‑language search with source citations, and strict human‑in‑the‑loop controls. The project is actively developed and released under the Elastic License 2.0.

  • Project
    WeThinkIn/AIGC-Interview-Book

    WeThinkIn/AIGC-Interview-Book is a free, open-source Chinese-language platform for AI job seekers — covering interview prep, technical knowledge (AIGC, LLMs, AI agents, deep learning, etc.), study routes, career planning, and a community contribution system. It emphasizes learning only technologies with proven long-term value, and is maintained by a lead editor plus six co-editors, all with industry experience.