[Bugfix] Fix accuracy-test-1-gpu failure caused by builtin_tools

[CatherineSue]

Motivation

Fix accuracy test.

Root cause: Llama3.1-8B-Instruct's chat_template has a field called builtin_tools. It works in conflict with tools. In #9043 , we passed this field as [] to tokenizer.apply_chat_template for gpt-oss. However this field doesn't need to be set for gpt-oss either.

Modifications

Remove builtin_tools=[]. This won't affect gpt-oss models. It checks if builtin_tools is set. As long as we don't set it, it is fine.

Accuracy Tests

test_eval_accuray_large

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.

[gemini-code-assist]

Summary of Changes

Hello @CatherineSue, 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 addresses a bug that was causing accuracy test failures, specifically related to the tokenizer.apply_chat_template function. The issue stemmed from a conflict between the builtin_tools and tools parameters when processing chat templates, particularly affecting models like Llama3.1-8B-Instruct. The core change involves removing an unnecessary builtin_tools=[] argument from the template application calls, thereby resolving the parameter conflict and restoring test accuracy.

Highlights

• Removal of builtin_tools parameter: The builtin_tools=[] argument was explicitly removed from two calls to tokenizer.apply_chat_template within the _apply_jinja_template function. This change directly addresses the conflict identified with the tools parameter, which was causing accuracy test failures.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 correctly addresses an accuracy issue caused by the builtin_tools argument being passed to tokenizer.apply_chat_template. The removal of this hardcoded argument is a good fix that should resolve the conflict with models like Llama3.1-8B-Instruct. I have one suggestion to improve code maintainability by reducing duplication in the _apply_jinja_template function.