Add workflow and example for toolcall training using ToolAce dataset

[garyzhang99]

Description

As the title says. Referenced from https://github.com/NVlabs/Tool-N1.

Checklist

Please check the following items before code is ready to be reviewed.

• Code has passed all tests
• Docstrings have been added/updated in Google Style
• Documentation has been updated
• Code is ready for review

[gemini-code-assist]

Summary of Changes

Hello @garyzhang99, 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 a complete pipeline for training models on tool-calling tasks, specifically leveraging the ToolAce dataset. It encompasses a new workflow that handles prompt formatting and reward computation, a dedicated script for data preparation, and example configurations to facilitate the setup and execution of GRPO-based training runs. The changes aim to expand the framework's capabilities for advanced model training scenarios involving external tools.

Highlights

• New Tool-Calling Workflow: I've added a ToolCallWorkflow to enable training models on tool-calling tasks. This workflow integrates prompt construction and reward calculation logic adapted from the NVlabs/Tool-N1 project.
• ToolAce Dataset Support: This PR introduces full support for the ToolAce dataset, including a dedicated data preprocessing script (scripts/data_prepare/get_toolace_data.py) to prepare the data for the new workflow.
• Example Configuration: I've provided comprehensive example configuration files (examples/grpo_toolcall/toolace.yaml and examples/grpo_toolcall/train_toolace.yaml) for running GRPO (Generative Reinforcement Learning with Policy Optimization) training on the ToolAce dataset.
• Documentation: A new README.md file (examples/grpo_toolcall/README.md) has been added to guide users on how to set up and run the tool-calling training example.

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 or fill out our survey to provide feedback.

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 workflow and example for tool-call training using the ToolAce dataset. The changes include data preparation scripts, workflow implementation, and configuration files. The code is generally well-structured and follows the project's patterns. I've provided some suggestions to improve robustness, clarity, and adherence to best practices, including fixing a potential IndexError, improving exception handling, and cleaning up some redundant code. Overall, this is a solid contribution.