support pixels range at prepare_hidden_states stage

[justadogistaken]

Motivation

Pixels settting for offline mode is needed. Which is aligned with online training mode.

Modifications

Copied pixels args from train_eagle3.py.

Related Issues

Accuracy Test

Benchmark & Profiling

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://sgl-fru7574.slack.com/archives/C09784E3EN6 to discuss your PR.

[gemini-code-assist]

Summary of Changes

Hello @justadogistaken, 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 enhances the prepare_hidden_states script by introducing configurable pixel range parameters for Vision-Language Models. It allows users to specify minimum and maximum pixel values, which are then passed to the AutoProcessor during initialization. This provides greater flexibility in handling image inputs for VLMs, enabling better alignment with specific model requirements or optimization strategies.

Highlights

• New VLM-related arguments: Introduced --min-pixels and --max-pixels command-line arguments to scripts/prepare_hidden_states.py under a new vlm argument group, allowing specification of pixel range for Vision-Language Models.
• Dynamic AutoProcessor configuration: Modified the AutoProcessor.from_pretrained function call to accept the new min_pixels and max_pixels arguments when is_vlm is true, enabling dynamic configuration of pixel processing based on user-defined ranges.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 support for specifying a pixel range for Vision Language Models (VLMs) during the hidden states preparation stage. This is done by adding --min-pixels and --max-pixels command-line arguments to the prepare_hidden_states.py script. The changes are logical and well-targeted. My review focuses on improving code style and maintainability by suggesting the addition of help text for the new arguments and correcting the formatting of a function call to align with standard Python conventions.

[gemini-code-assist]

It's good practice to add help strings to command-line arguments to explain their purpose. This improves the script's usability and maintainability. The formatting of these calls can also be improved to be more conventional and readable, similar to what code formatters like black would produce.

Suggested change

	vlm_group.add_argument(
	"--min-pixels", type=int, default=50176
	) # 64*28*28 for qwen2.5-vl
	vlm_group.add_argument(
	"--max-pixels", type=int, default=802816
	) # 1024*28*28 for qwen2.5-vl
	vlm_group.add_argument(
	"--min-pixels",
	type=int,
	default=50176,
	help="The minimum number of pixels for VLM processing.",
	) # 64*28*28 for qwen2.5-vl
	vlm_group.add_argument(
	"--max-pixels",
	type=int,
	default=802816,
	help="The maximum number of pixels for VLM processing.",
	) # 1024*28*28 for qwen2.5-vl