Skip to content

[model] support glm-4.5 agent #5305

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 6 commits into
base: main
Choose a base branch
from

Conversation

laocheyujie
Copy link

PR type

  • Bug Fix
  • New Feature
  • Document Updates
  • More Models or Datasets Support

PR information

This PR adds support for GLM-4.5 agent (function call) training in ms-swift.

Key updates:

  1. Added GLM4_5AgentTemplate in plugin/agent_template/glm4.py to support training GLM-4.5 function call agents.
  2. Enhanced suffix appending logic: in the final generation round, check if the output already ends with a stop word, and skip appending the suffix if so to avoid redundancy.

Experiment results

  • Training successfully runs on 8×A100 (80GB) with GLM-4.5 agent configuration.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Summary of Changes

Hello @laocheyujie, 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!

I've implemented support for GLM-4.5 agent training, specifically enabling function call capabilities within the ms-swift project. This involved integrating a new agent template and refining the text generation process to ensure more accurate and efficient output by preventing redundant suffixes. The changes aim to expand the framework's compatibility with advanced large language models and their interactive features.

Highlights

  • GLM-4.5 Agent Support: I've added comprehensive support for GLM-4.5 agent (function call) training within the ms-swift framework. This includes defining a new template and agent-specific logic for GLM-4.5 agents.
  • Suffix Appending Logic Enhancement: I've refined the suffix appending logic during the final generation round. The system now checks if the output already ends with a stop word, preventing redundant suffix additions and improving output quality.
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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request adds support for the GLM-4.5 agent, including a new agent template and updates to the suffix appending logic. The changes are well-structured and address the goal of the PR. I've provided a few suggestions to improve code clarity, style, and performance.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant