Skip to content

Regarding the "clean" issue of running three datasets on the Voxtral model #1

Description

@sunyulin0421

I found that when performing "clean" reasoning on Voxtral, since Voxtral is a native multimodal model, its tokenizer must include audio tokens in order to function properly. Voxtral cannot handle pure text input (task_type=text_bench), which ultimately results in completely garbled output.

Could you please explain how this issue should be addressed during the experimental part of the thesis?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions