Skip to content

Build my own model and use DCLM-1B training script and dataset. #95

Description

@windbar778

Hello ! I'm currently building a custom model that is similar to a decoder-only architecture (GPT-2 style not Llama).

I'm wondering if there's the easiest way to train my custom model using the TRI-ML/DCLM-1B dataset and training script!

I appreciate your help.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions