[model] support glm4_6v flash

[Jintao-Huang]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @Jintao-Huang, 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 integrates the GLM-4.6V-Flash model into the system, enhancing its capabilities by supporting a new large language model. The changes include the necessary code modifications to recognize and configure the model, alongside updates to the user-facing documentation to reflect its availability and associated prerequisites.

Highlights

• New Model Support: Added support for the ZhipuAI/GLM-4.6V-Flash model, expanding the range of available models.
• Documentation Update: Updated both English and Chinese documentation files to include the newly supported GLM-4.6V-Flash model.
• Dependency Specification: Specified 'transformers>=5.0.0.dev' as a minimum requirement for the GLM-4.6V-Flash model.

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 support for the GLM-4.6V-Flash model. The changes include registering the model and updating the documentation. My review focuses on improving the consistency of model type naming for better user experience and on highlighting the risk of depending on a development version of a library.

[gemini-code-assist]

For better clarity and consistency with other GLM-V models like glm4_1v and glm4_5v, it's recommended to introduce a new model type for GLM-4.6V-Flash, such as glm4_6v. This will make the model selection more intuitive for users, who would otherwise have to use --model_type glm4_1v for a 4.6V model, which is confusing.

This can be achieved by:

1. Defining a new MLLMModelType.glm4_6v.
2. Creating a new ModelMeta registration for it. You can likely reuse get_model_tokenizer_glm4_1v and TemplateType.glm4_1v if they are compatible.
3. Updating the documentation in docs/ to use glm4_6v as the model type.

[gemini-code-assist]

The requirement for a development version of transformers (>=5.0.0.dev) introduces a potential risk, as APIs in development versions can change without notice. This might break compatibility in the future. It is strongly recommended to depend on a stable release version if possible.