Skip to content
View kenhktsui's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report kenhktsui

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
kenhktsui/README.md

Follow me on X • 🤗 Hugging Face • 💻 Medium

Hi there 👋 I am Ken Tsui

I am a product-minded machine learning engineer lead, a open source small language model/ LLM researcher, and a blogger.

Product

I lead ML R&D, and prototypes in following products.

  • Arbor, which tailors a daily update of your professional topics with AI
  • SuperAcc, a banking grade document intelligence SaaS for FIs

Research

I mostly work on LLM data curation/ filtering for pretraining data, small language model training and synthetic data generation.

Handles

Huggingface: kenhktsui
Medium: kentsui
Twitter: kenhktsui
Linkedin: Ken Tsui
Gitlab (commits in my job): kenhktsui

Popular repositories Loading

  1. anyclassifier anyclassifier Public

    One Line To Build Zero-Data Classifiers in Minutes

    Python 30 6

  2. open-information-retrieval open-information-retrieval Public

    Implementation of Production Ready Information Retrieval System

    Python 11 2

  3. Visualizing-Logistic-Regression Visualizing-Logistic-Regression Public

    Python 2 1

  4. adversarial_examples adversarial_examples Public

    Python 2 5

  5. bert bert Public

    Forked from google-research/bert

    TensorFlow code and pre-trained models for BERT

    Python 2

  6. Open-Assistant Open-Assistant Public

    Forked from LAION-AI/Open-Assistant

    OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

    Python 2