Skip to content

Replicate training #1

@ftvalentini

Description

@ftvalentini

I'm trying to replicate tranining for French documents (I didn't find any models published).

I can't find any files I can use for distillation when finetuning with mmarco, in:

https://github.com/hltcoe/BLADE/blob/3e1721b99e2ce09d92134398f7c42c4ab3fabc69/README.md?plain=1#L88C1-L91C1

    --q_distil data/query_vector_distil.json \
    --p_distil data/passage_vector_distil.jsonl \
    --p_offset data/passage_vector_distil.offset

How can I find or produce these files?

Thanks!!

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