Add generation args to ModelConfig

[chenyushuo]

Description

As the title says.

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 @chenyushuo, 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 aims to streamline the management and application of model generation parameters across the system. By introducing generation arguments directly into ModelConfig and ensuring their consistent propagation through various configuration and model wrapper classes, it enhances the configurability and maintainability of how models generate responses. This change provides a unified approach to setting parameters like temperature, top-p, top-k, and log probabilities, making it easier to control model behavior during rollout tasks and API interactions.

Highlights

• Centralized Generation Arguments: Introduced temperature, top_p, top_k, and logprobs as 'rollout args' directly into ModelConfig to centralize generation parameters.
• Flexible Configuration: Modified GenerationConfig fields (temperature, top_p, top_k, logprobs) to be Optional with None as default, allowing for more flexible overriding or inheritance of these values.
• Propagation of Arguments: Updated configuration checking logic to propagate these new generation arguments from ModelConfig to taskset.rollout_args and dataset.rollout_args within the explorer input, and to explorer.rollout_model and auxiliary_models.
• Model Wrapper Integration: Added an abstract get_default_rollout_args method to InferenceModel and implemented it in VLLMModel. ModelWrapper now uses these default rollout arguments, ensuring they are consistently applied when making OpenAI API calls, and explicitly sets logprobs=True for history recording.
• Workflow Updates: The AgentscopeWorkflow now explicitly includes top_p, top_k, and logprobs=True in its generate_kwargs when initializing the agentscope client.

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 generation arguments to ModelConfig for hierarchical configuration, propagating them throughout the system. The refactoring in config.py to dynamically set model attributes is a good improvement for maintainability. However, I've identified a critical bug involving a missing await for an asynchronous call, which will cause runtime errors. Additionally, there are several instances of commented-out code and debug statements that should be removed to improve code clarity.