Skip to content

learn: how BPE works #2

@clay-arras

Description

@clay-arras

Learning Resource

Watch this video: link

This is the core algorithm for BPE, talks about the motivation behind it and how the general algorithm works.
I recommend following along on a Google Colab. The first part of the video (up until 1:11) is VERY IMPORTANT. The remaining part is up to you if you want to watch.

Next Steps

After this, we'll try to implement this tokenizer in C++ and replicate the result that we got in Python.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    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