Skip to content

Question about train dflash for a large target model #92

@dongyibo

Description

@dongyibo

Hello, I want to train a Dflash draft model as a target model with a relatively large number of parameters. This target model, for example, DeepSeek v2, has 236B parameters and includes multiple dialogue formats such as think/no-think/function tool.

From experience, how much training data is appropriate for a model of this size?

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