LLM from Scratch Tutorial - Code and Train Qwen 3

LLM from Scratch Tutorial - Code and Train Qwen 3

freeCodeCamp.org via freeCodeCamp Direct link

⌨ 0:44:28 Feed-Forward & SwiGLU

13 of 19

13 of 19

⌨ 0:44:28 Feed-Forward & SwiGLU

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

LLM from Scratch Tutorial - Code and Train Qwen 3

Automatically move to the next video in the Classroom when playback concludes

  1. 1 ⌨ 0:00:00 Intro & Demo
  2. 2 ⌨ 0:01:46 Qwen 3 Architecture
  3. 3 ⌨ 0:02:36 Prerequisites
  4. 4 ⌨ 0:04:01 Code Setup & Imports
  5. 5 ⌨ 0:05:26 Model Configuration
  6. 6 ⌨ 0:08:26 Qwen 3 Specifics
  7. 7 ⌨ 0:12:24 Training Hyperparameters
  8. 8 ⌨ 0:17:18 Grouped Query Attention Logic
  9. 9 ⌨ 0:18:56 Muon Optimizer Explained
  10. 10 ⌨ 0:29:02 Data Loading & Tokenization
  11. 11 ⌨ 0:32:37 RoPE Positional Embeddings
  12. 12 ⌨ 0:36:56 Self-Attention Code
  13. 13 ⌨ 0:44:28 Feed-Forward & SwiGLU
  14. 14 ⌨ 0:47:36 Building the Final Model
  15. 15 ⌨ 0:52:34 Evaluation & Optimizer Setup
  16. 16 ⌨ 0:54:08 The Training Loop
  17. 17 ⌨ 0:55:43 Running the Training
  18. 18 ⌨ 0:58:38 Inference & Text Generation
  19. 19 ⌨ 1:00:51 Final Results

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.