feat: add Llama 3.2 chat template with Cutting Knowledge Date

[gururajkosuru]

Add a new llama-3_2 conversation template that includes the 'Cutting Knowledge Date' and 'Today Date' preamble lines in the system template, matching the official HuggingFace chat template.

Also adds unit tests for the new template verifying:

• Date preamble in system template
• Tool/ipython role support
• Correct stop token IDs
• Also fixed the date to be templated
• unrelated jenkins UT 404 failure

Fixes #3002

[gemini-code-assist]

Summary of Changes

Hello, 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 introduces the llama-3_2 conversation template, aligning MLC LLM with the official HuggingFace chat template by incorporating specific date-related preamble lines into the system template. Comprehensive unit tests have been added to validate the new template's structure and functionality, ensuring accurate system message formatting, tool role support, and correct stop token identification.

Highlights

• New Conversation Template: Added a new llama-3_2 conversation template to align with the official HuggingFace chat template.
• System Template Preamble: Included 'Cutting Knowledge Date' and 'Today Date' preamble lines within the llama-3_2 system template.
• Unit Tests: Introduced unit tests to verify the new template's date preamble, tool/ipython role support, and correct stop token IDs.

🧠 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.

Changelog

• python/mlc_llm/conversation_template/llama.py
  • Registered a new llama-3_2 conversation template.
  • Configured the llama-3_2 system template to include 'Cutting Knowledge Date' and 'Today Date' preambles.
  • Defined roles, separators, and stop token IDs for the llama-3_2 template.
• tests/python/conversation_template/test_llama_template.py
  • Added test_llama3_2_prompt to verify the system template's date preamble.
  • Added test_llama3_2_has_tool_role to confirm tool/ipython role support.
  • Added test_llama3_2_stop_tokens to check for correct stop token IDs.

Activity

• No human activity has been recorded on this pull request yet.

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 adds a new conversation template for Llama 3.2, along with corresponding unit tests. The implementation is generally good, but there is a significant issue with the Today Date being hardcoded in the template. This will cause the template to generate incorrect prompts for any conversation not occurring on that specific date. I've added comments highlighting this issue and suggesting a more robust, dynamic approach.