Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 

Repository files navigation

Stanford LLM Mastery (9 Lectures)

A weekly roadmap + prerequisites + practice plan

If you use ChatGPT, Claude, or Gemini every day and you want to understand what is actually happening inside LLMs, this Stanford series is one of the cleanest paths I have found.

This README gives you:

  • All 9 lecture links (working)
  • A simple 9-week plan (1 lecture per week)
  • Prerequisites you should know before you start
  • A practice workflow so you learn by building, not just watching

9-week plan (1 lecture per week)

Rule: don’t binge. One lecture per week + hands-on notes + one small build.

Week 1: Transformers – end to end walkthrough

https://www.youtube.com/watch?v=Ub3GoFaUcds

Week 2: Transformer tricks

https://www.youtube.com/watch?v=yT84Y5zCnaA

Week 3: Large Language Models

https://www.youtube.com/watch?v=Q5baLehv5So

Week 4: LLM training – Pretraining, SFT, LoRA

https://youtu.be/VlA_jt_3Qc4

Week 5: LLM tuning – RLHF, PPO, DPO

https://youtu.be/PmW_TMQ3l0I

Week 6: LLM reasoning – RL scaling with GRPO

https://youtu.be/k5Fh-UgTuCo

Week 7: LLM tuning (advanced)

https://youtu.be/h-7S6HNq0Vg

Week 8: Agentic LLMs – RAG, tool calling, agents

https://youtu.be/8fNP4N46RRo

Week 9: LLM evaluation – LLMs as judge, benchmarks

https://youtu.be/Q86qzJ1K1Ss


How to use this series (the learning workflow)

For each lecture, do this:

  1. Watch the lecture (no multitasking)
  2. Write 7 to 10 bullet notes in your own words
  3. Ask an LLM to quiz you (and explain what you got wrong)
  4. Build one tiny thing (30 to 90 minutes)
  5. Publish something small (optional but powerful)
    • a short LinkedIn post
    • a short note
    • a tiny Kaggle notebook
    • a mini GitHub repo

This is how you go from “I watched it” to “I can apply it”.


Prerequisites (what you should know BEFORE starting)

You do not need to be perfect. You need basic comfort.

1) Python fundamentals

You should be comfortable with:

  • functions, loops, list and dicts
  • reading files, working in notebooks
  • basic debugging (print, exceptions)

Good free resources:

Minimum practice (do this once before Week 1):

  • write a small script that loads text, cleans it, counts words, prints top 20

2) Math essentials

You do not need heavy math. You need the practical pieces.

Linear algebra:

  • vectors and matrices
  • dot product
  • cosine similarity (used in embeddings)
  • matrix multiplication shape logic

Probability:

  • probability basics
  • expectation and variance intuition
  • cross entropy as “how wrong your predicted probabilities are”

Good free resources:

Minimum practice:

  • implement cosine similarity in Python
  • compare 3 vectors and find nearest neighbor

3) Machine learning basics

You should understand:

  • train / validation / test
  • overfitting vs underfitting
  • loss, optimization (basic concept)
  • metrics

Good free resources:

Minimum practice:

  • train a simple model once (even logistic regression) and understand what changed

4) Neural network basics

You should know:

  • what a layer is
  • what backprop means (conceptually)
  • embeddings as learnable vectors
  • attention at a high level (the series will teach it deeper)

Good free resources:

Minimum practice:

  • use PyTorch to fit a tiny model on dummy data (even random points)

Build ideas (one per week, pick small)

Week 1 to 3:

  • build a tiny tokenizer and count token frequency
  • implement attention on a toy example and print attention weights
  • implement cosine similarity and retrieval for embeddings

Week 4 to 7:

  • compare full fine-tuning vs LoRA (read, summarize, count parameters)
  • write a small report: SFT vs RLHF vs DPO in your own words
  • replicate a tiny alignment toy example (conceptual is fine)

Week 8:

  • build a toy RAG:
    • store 5 docs
    • retrieve top 2
    • answer based on retrieved text

Week 9:

  • evaluate outputs:
    • create 20 test prompts
    • score with simple rubric
    • compare two models

Note template (copy for every lecture)

Lecture #: Title
Date:

What I learned (10 bullets):

Key terms (with my own definitions):

Confusions (questions I still have):

Mini build I did:

One post idea (optional):


Suggested pace (realistic)

  • 1 lecture per week
  • 2 short practice sessions in the week (45 minutes each)
  • 1 note writeup session (30 minutes)

You will finish in 9 weeks with real understanding.


Credits

  • Stanford Online / Stanford University for making the content public
  • Afshine Amidi + Shervine Amidi for the curriculum and teaching
  • Credit for the original share that triggered this README goes to Raunak Kumar’s LinkedIn post

About

A weekly roadmap + prerequisites + practice plan

Resources

Stars

4 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors