What's the Difference Between AWS vs. Azure vs. Google Cloud?
October 1, 2024
Article
Recommended experience
Intermediate level
Deepen your understanding of linear quantization methods. If you’re looking to go further into quantization, this course is the perfect next step.
Recommended experience
Intermediate level
Deepen your understanding of linear quantization methods. If you’re looking to go further into quantization, this course is the perfect next step.
Try variants of Linear Quantization and granularities like per tensor, per channel, and per group quantization.
Build a general-purpose quantizer in Pytorch that can quantize the dense layers of any open source model for up to 4x compression on dense layers.
Implement weights packing to pack four 2-bit weights into a single 8-bit integer.
Only available on desktop
In Quantization in Depth you will build model quantization methods to shrink model weights to ¼ their original size, and apply methods to maintain the compressed model’s performance. Your ability to quantize your models can make them more accessible, and also faster at inference time.
Implement and customize linear quantization from scratch so that you can study the tradeoff between space and performance, and then build a general-purpose quantizer in PyTorch that can quantize any open source model. You’ll implement techniques to compress model weights from 32 bits to 8 bits and even 2 bits. Join this course to: 1. Build and customize linear quantization functions, choosing between two “modes”: asymmetric and symmetric; and three granularities: per-tensor, per-channel, and per-group quantization. 2. Measure the quantization error of each of these options as you balance the performance and space tradeoffs for each option. 3. Build your own quantizer in PyTorch, to quantize any open source model’s dense layers from 32 bits to 8 bits. 4. Go beyond 8 bits, and pack four 2-bit weights into one 8-bit integer. Quantization in Depth lets you build and customize your own linear quantizer from scratch, going beyond standard open source libraries such as PyTorch and Quanto, which are covered in the short course Quantization Fundamentals, also by Hugging Face. This course gives you the foundation to study more advanced quantization methods, some of which are recommended at the end of the course.
DeepLearning.AI is an education technology company that develops a global community of AI talent. DeepLearning.AI's expert-led educational experiences provide AI practitioners and non-technical professionals with the necessary tools to go all the way from foundational basics to advanced application, empowering them to build an AI-powered future.
Hands-on, project-based learning
Practice new skills by completing job-related tasks with step-by-step instructions.
No downloads or installation required
Access the tools and resources you need in a cloud environment.
Available only on desktop
This project is designed for laptops or desktop computers with a reliable Internet connection, not mobile devices.
DeepLearning.AI
Course
DeepLearning.AI
Course
Johns Hopkins University
Course
Course
Unlimited access to 10,000+ world-class courses, hands-on projects, and job-ready certificate programs - all included in your subscription
Earn a degree from world-class universities - 100% online
Upskill your employees to excel in the digital economy
In Projects, you'll complete an activity or scenario by following a set of instructions in an interactive hands-on environment. Projects are completed in a real cloud environment and within real instances of various products as opposed to a simulation or demo environment.
By purchasing a Project, you'll get everything you need to complete the Project including temporary access to any product required to complete the Project.
Even though Projects are technically available on mobile devices, we highly recommend that you complete Projects on a laptop or desktop only.
Yes, you can download and keep any of your created files from the Project. To do so, please make sure you save any files and work to your device before exiting the product environment.
Projects are not eligible for refunds. See our full refund policy.
Financial aid is not available for Projects.
In rare instances, Projects may be taken down for maintenance or other reasons. If you are experiencing any issues, please contact us.
Auditing is not available for Projects.
At the top of the page, you can view the experience level recommended for this Project.
Yes, everything you need to complete your Project will be available in your browser.