Adds customizing quantization with QuantizationConfig guide

[JyotinderSingh]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @JyotinderSingh, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly expands the Keras documentation on model quantization by introducing a comprehensive guide to the QuantizationConfig API. This new guide empowers users with granular control over the quantization process, covering custom INT8 configurations, efficient weight-only INT4 quantization, and the creation of bespoke quantizers. Additionally, it refines the existing quantization overview by adding selective layer quantization capabilities, making the Keras quantization framework even more flexible and user-friendly.

Highlights

• New Quantization Guide: A new guide titled 'Customizing Quantization with QuantizationConfig' has been added, detailing advanced quantization techniques in Keras.
• Custom INT8 Quantization: The new guide demonstrates how to customize INT8 quantization by specifying custom value ranges for weights and activations using Int8QuantizationConfig.
• Weight-Only INT4 Quantization: The guide provides an example of performing weight-only INT4 quantization, a common technique for LLMs, by setting activation_quantizer=None in Int4QuantizationConfig.
• Custom Quantizers: It illustrates how to implement and integrate custom quantizers, such as a PercentileQuantizer, by subclassing keras.quantizers.Quantizer.
• Enhanced Quantization Overview: The existing quantization_overview guide has been updated to include a new section on 'Selective Quantization', demonstrating how to quantize specific layers using regex or callable filters.
• Keras Version Update: The Keras version referenced in scripts/autogen.py has been updated from v3.12.0 to v3.13.0.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a new guide on customizing quantization in Keras using QuantizationConfig. It adds Python, Jupyter Notebook, and Markdown versions of the guide, and updates related files to include it. The guide is well-structured and covers custom INT8 quantization, weight-only INT4 quantization, and implementing a custom PercentileQuantizer. My review focuses on improving the implementation of the custom PercentileQuantizer for better robustness and adherence to Keras API conventions. The other changes, including refactoring in the quantization overview guide and script updates, look good.