Skip to content

Will the trained DSA version of GLM-4.7-Flash (the 30B DSA model from the paper) be released? #8

Description

@Xnhyacinth

Hi, thanks for the great work on IndexCache!

I'd like to reproduce and deploy the method, but I noticed the repository only provides the SGLang/vLLM patches, and the release list doesn't include the 30B DSA model used for the main experiments (Tables 1–3 in the paper).

In Section 4.1 of the paper, the 30B DSA model is described as initialized from zai-org/GLM-4.7-Flash (30B-A3B MoE, MLA, 47 layers) and trained with a 1,000-step dense warm-up + 4,000-step sparse training phase on SFT data at 200K context. This DSA-finetuned checkpoint is currently not available on Hugging Face.

Thanks in advance!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions