Neural Networks to GPT: Zero to Hero · Tapelearn
Neural Networks to GPT: Zero to Hero
9/9
Chapter 9 of 9 · 4 h 1 min left
Theater
T
Loading player…
Previous
8 · Let's build the GPT Tokenizer
Sign in to track progress
Next
1×
Loop
Chapter 9 of 9 · 4 h 1 min left
Let's reproduce GPT-2 (124M)
Andrej Karpathy · 4:01:26
Copy link to this moment
Chapters
· 9 chapters
Backprop and language models
1
The spelled-out intro to neural networks and backpropagation: building micrograd
2:25:52
2
The spelled-out intro to language modeling: building makemore
1:57:45
3
Building makemore Part 2: MLP
1:15:40
Training deep nets properly
4
Building makemore Part 3: Activations & Gradients, BatchNorm
1:55:58
5
Building makemore Part 4: Becoming a Backprop Ninja
1:55:24
6
Building makemore Part 5: Building a WaveNet
56:22
Building GPT
7
Let's build GPT: from scratch, in code, spelled out.
1:56:20
8
Let's build the GPT Tokenizer
2:13:35
9
Let's reproduce GPT-2 (124M)
4:01:26