Skip to content
View bauwenst's full-sized avatar
:octocat:
#SigmaMaleGrindset
:octocat:
#SigmaMaleGrindset
3 followers · 1 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Organizations

@LAGoM-NLP

Block or report bauwenst

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
bauwenst/README.md

I'm Thomas. This is my ✨professional✨ GitHub account, which I use to host my website plus repos I want associated with my name. If this account shows days without any commits, it's likely because I'm cooking up gruesome code in private repos on my original account @GitMew.

  • PhD student in natural language processing at the KU Leuven in Belgium. I work in the LAGoM • NLP research group, which is part of the Human-Computer Interaction (HCI) division at our department of Computer Science.
  • I tokenise stuff, and if you're not careful, I will tokenise you next 💀
  • Contact me using the information on this page.

If we are lucky, my GitHub streak is shown below.

Pinned Loading

  1. TkTkT TkTkT Public

    A collection of Pythonic subword tokenisers and text preprocessing tools.

    Python 12 1

  2. LaMoTO LaMoTO Public

    Language Modelling Tasks as Objects (LaMoTO) treats the pretraining and finetuning of causal and masked language models as classes themselves, not just the models.

    Python 2

  3. MoDeST MoDeST Public

    Morphological Decomposition & Segmentation Trove

    Python 2

  4. ArchIt ArchIt Public

    Implement a PyTorch head and loss once, reuse it with any language model. An actual attempt at object-oriented design, unlike `transformers`.

    Python

  5. fiject fiject Public

    Object-oriented, two-stage PDF figure generation library for Python.

    Python 3 1

  6. ReleaseMe ReleaseMe Public

    Tool for releasing Python packages automatically.

    Python