https://github.com/ksm26/quantization-in-depth
https://github.com/ksm26/quantization-in-depth
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ksm26/quantization-in-depth
- Owner: ksm26
- Created: 2024-05-14T13:24:17.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-05-22T16:46:11.000Z (over 1 year ago)
- Last Synced: 2024-05-23T05:45:18.952Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 5.79 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🔍 [Quantization in Depth](https://www.deeplearning.ai/short-courses/quantization-in-depth/)
💡 Welcome to the "Quantization in Depth" course! This course delves into advanced quantization techniques to compress and optimize models, making them more accessible and efficient.
## Course Summary
In this course, you'll explore in-depth quantization methods to reduce model weights and maintain performance. Here's what you can expect to learn and experience:
1. ⚙️ **Linear Quantization**: Build and customize linear quantization functions, exploring modes (asymmetric and symmetric) and granularities (per-tensor, per-channel, and per-group).
2. 📏 **Quantization Error Measurement**: Measure the quantization error of different options, balancing performance and space trade-offs.
3. 🛠️ **PyTorch Quantizer**: Implement a general-purpose quantizer in PyTorch to compress model weights from 32 bits to 8 bits.
4. 🧩 **Advanced Techniques**: Pack four 2-bit weights into one 8-bit integer, going beyond standard 8-bit quantization.
## Key Points
- 🔄 Explore different variants of Linear Quantization, including symmetric vs. asymmetric modes and various granularities.
- 🧠 Build a general-purpose quantizer in PyTorch for up to 4x compression on dense layers of any open-source model.
- 📦 Implement weight packing to compress four 2-bit weights into a single 8-bit integer.
## About the Instructors
🌟 **Marc Sun** and **Younes Belkada** are Machine Learning Engineers at Hugging Face, bringing extensive expertise in model compression and optimization to guide you through this advanced course.
🔗 To enroll in the course or for further information, visit [deeplearning.ai](https://www.deeplearning.ai/short-courses/).