Learn LLM Path / pillar 1 of 10
Deeper track: heavier resources for job-ready depth. Concepts you already checked stay checked.
explain how an LLM works end-to-end without deep math. 3Blue1Brown chapters are the visual gold standard - watch in order
- Sign in to track this item
Big-picture: what an LLM is
LLMs explained briefly - 3Blue1Brown (playlist)videoDEEP8m
- Sign in to track this item
Full forward pass, embeddings, softmax
Ch.5 Transformers, the tech behind LLMs - 3B1B ↗videoDEEP27m
- Sign in to track this item
Attention: Q/K/V, masking, multi-head KEY
Ch.6 Attention, step-by-step - 3B1B ↗videoDEEP26m
- Sign in to track this item
How facts live in MLP layers (often skipped)
Ch.7 How might LLMs store facts - 3B1B ↗videoDEEP23m
- Sign in to track this item
Tokenization/BPE + positional encoding
Let's build GPT from scratch - Karpathy ↗videoDEEP1h56m
Deeper · Extras
- Sign in to track this item
Backprop from scratch (micrograd) [KEY]
Neural Networks: Zero to Hero, Ep.1 - Karpathyvideo2h25m⚠ link unverified
- Sign in to track this item
Building an MLP language model (makemore pt.1-2)
Neural Networks: Zero to Hero, Ep.2-3 - Karpathyvideo~2h30m⚠ link unverified
- Sign in to track this item
Why training breaks: activations, gradients, batchnorm
Neural Networks: Zero to Hero, Ep.4 - Karpathyvideo1h55m⚠ link unverified
- Sign in to track this item
Loss functions & gradient descent, in plain language
But what is a neural network? - 3Blue1Brown Ch.1-2video~40m⚠ link unverified
- Sign in to track this item
CNNs & RNNs - the 1-video version (context only)
CNNs and RNNs explained simply - any solid overviewvideo~20m⚠ link unverified