[model] update minicpmv-4.5 video processor

[hjh0119]

reference: https://www.modelscope.cn/models/OpenBMB/MiniCPM-V-4_5

[gemini-code-assist]

Summary of Changes

Hello @hjh0119, 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 significantly enhances the video processing capabilities for the MiniCPM-V 4.5 model. It introduces a specialized video processor that efficiently handles video input by extracting relevant frames and generating temporal identifiers. These changes ensure that the model can effectively interpret and utilize video data, aligning with the specific requirements of the MiniCPM-V 4.5 architecture.

Highlights

• MiniCPM-V 4.5 Video Processor Update: Implemented a dedicated video processing pipeline for the MiniCPM-V 4.5 model, including new methods for handling video input, frame extraction, and temporal ID generation within the MiniCPMV4_5Template.
• New Video Loading Utility: Introduced load_video_minicpmv_4_5 in vision_utils.py to manage video frame sampling, packing, and timestamp mapping, supporting specific requirements for the MiniCPM-V 4.5 model.
• Enhanced Image Processor Integration: Modified the _encode method to pass temporal_ids to the image processor, enabling the model to leverage temporal information from video inputs.

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. 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 updates the video processor for the MiniCPM-V 4.5 model. The changes include adding a new template for MiniCPM-V 4.5, a new video loading utility function, and updates to the encoding logic to handle temporal information. The review identifies a critical issue in the test suite where a hardcoded local path is used, making tests non-portable. Additionally, there are a couple of potential bugs in the new video loading utility regarding frame sampling logic that could lead to incorrect behavior. Suggestions are provided to fix these issues.