Fix llama3.2 VL vision in "Supported Modals" documents

[blankanswer]

Motivation

fix document: llama3.2 multimodal vision 8B(×) -> 11B(√)

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported
4. versions of downstream projects.
5. The documentation has been modified accordingly, like docstring or example tutorials.