Skip to content

Hardware specification #9

@paulcx

Description

@paulcx

Hi @jondurbin Thanks for sharing the bagel model. What kind of hardware specification for DPO trainning? Your DPO training is based on Lora but not full parameters, am I right?

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