mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-06-03 21:34:52 -05:00
8afe207ce5
✅ Rename all module directories: 00_setup → 01_setup, etc. ✅ Update convert_modules.py mappings for new directory names ✅ Update _toc.yml file paths and titles (1-14 instead of 0-13) ✅ Regenerate all overview pages with new numbering ✅ Fix all broken references in usage-paths and intro ✅ Update chapter references to use natural numbering Benefits: - More intuitive course progression starting from 1 - Matches academic course numbering conventions - Eliminates confusion about 'Module 0' concept - Cleaner mental model for students and instructors - All references and links properly updated Complete transformation: 14 modules now numbered 01-14
1.9 KiB
1.9 KiB
Compression & Optimization - Making AI Models Efficient
Welcome to the Compression module! This is where you'll learn to make neural networks smaller, faster, and more efficient for real-world deployment.
:class: tip
- Understand how model size affects deployment and why compression matters
- Implement magnitude-based pruning to remove unimportant weights
- Master quantization to reduce memory usage by 75%
- Build knowledge distillation for training compact models
- Create structured pruning to optimize network architectures
- Compare compression techniques and their trade-offs
Build → Use → Optimize
- Build: Four compression techniques from scratch
- Use: Apply compression to real neural networks
- Optimize: Combine techniques for maximum efficiency gains
🚀 Interactive Learning
Choose your preferred way to engage with this module:
```{grid-item-card} 🚀 Launch Binder
:link: https://mybinder.org/v2/gh/mlsysbook/TinyTorch/main?filepath=modules/source/11_compression/compression_dev.ipynb
:class-header: bg-light
Run this module interactively in your browser. No installation required!
```
```{grid-item-card} ⚡ Open in Colab
:link: https://colab.research.google.com/github/mlsysbook/TinyTorch/blob/main/modules/source/11_compression/compression_dev.ipynb
:class-header: bg-light
Use Google Colab for GPU access and cloud compute power.
```
```{grid-item-card} 📖 View Source
:link: https://github.com/mlsysbook/TinyTorch/blob/main/modules/source/11_compression/compression_dev.py
:class-header: bg-light
Browse the Python source code and understand the implementation.
```
:class: tip
**Binder sessions are temporary!** Download your completed notebook when done, or switch to local development for persistent work.
Ready for serious development? → [🏗️ Local Setup Guide](../usage-paths/serious-development.md)