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

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions