Skip to content

Role assistant vs user in format_dpo_sample? #82

Open
@tmoroder

Description

@tmoroder

Wondering if the role must be assistant rather than user in the format_dpo_sample function of the training script run_dpo.py in chosen and rejected messages, e.g., line 124?

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