[template] support mimo-v2 template

[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 introduces comprehensive support for the MiMo-V2 model template, encompassing both its Flash and Flash-Base versions. The changes involve updating core system constants, registering the new models with their specific architectures and tokenizer functions, and defining a dedicated ChatML template. Additionally, the documentation has been revised to reflect the availability of these new models, ensuring that users can easily discover and utilize them within the framework.

Highlights

• MiMo-V2 Model Support: Added full support for the MiMo-V2 model template, including its Flash and Flash-Base variants, enabling their use within the system.
• Documentation Updates: The Chinese and English documentation for supported models and datasets has been updated to include the newly integrated MiMo-V2 models.
• Model and Template Registration: Integrated MiMo-V2 into the system's model type constants, model registration, template type constants, and template registration, including a default ChatML system prompt.

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 mimo-v2 template and models. The changes include updating constants, registering the new model and template, and adding them to the documentation. My review focuses on ensuring consistency and correctness in the documentation and template definitions. I've found a couple of minor issues in the documentation tables and a potential issue with the response_prefix in the new template.

[gemini-code-assist]

The Tags for HunyuanOCR was changed from vision to -. Since OCR is a vision-related task, it would be more accurate to keep the vision tag for better discoverability and consistency.

Suggested change

	|[Tencent-Hunyuan/HunyuanOCR](https://modelscope.cn/models/Tencent-Hunyuan/HunyuanOCR)|hunyuan_ocr|hunyuan_ocr|transformers>=4.49.0|✘|-|[tencent/HunyuanOCR](https://huggingface.co/tencent/HunyuanOCR)|
	|[Tencent-Hunyuan/HunyuanOCR](https://modelscope.cn/models/Tencent-Hunyuan/HunyuanOCR)|hunyuan_ocr|hunyuan_ocr|transformers>=4.49.0|✘|vision|[tencent/HunyuanOCR](https://huggingface.co/tencent/HunyuanOCR)|

[gemini-code-assist]

The Tags for HunyuanOCR was changed from vision to -. Since OCR is a vision-related task, it would be more accurate to keep the vision tag for better discoverability and consistency.

Suggested change

	|[Tencent-Hunyuan/HunyuanOCR](https://modelscope.cn/models/Tencent-Hunyuan/HunyuanOCR)|hunyuan_ocr|hunyuan_ocr|transformers>=4.49.0|✘|-|[tencent/HunyuanOCR](https://huggingface.co/tencent/HunyuanOCR)|
	|[Tencent-Hunyuan/HunyuanOCR](https://modelscope.cn/models/Tencent-Hunyuan/HunyuanOCR)|hunyuan_ocr|hunyuan_ocr|transformers>=4.49.0|✘|vision|[tencent/HunyuanOCR](https://huggingface.co/tencent/HunyuanOCR)|

[gemini-code-assist]

The response_prefix is set to <think></think>, which is an empty tag pair. This is inconsistent with other "thinking" templates like ring2 and gpt_oss which use <think>\n to allow the model to generate thoughts. An empty tag might not be the intended behavior. If the model is not expected to generate thoughts, it might be better to use <think>\n</think>\n to represent an empty thinking step explicitly. If it is expected to generate thoughts, <think>\n would be more appropriate.

Suggested change

	response_prefix='<think></think>',
	response_prefix='<think>\n</think>\n',