Skip to content
View KwokHing's full-sized avatar
Block or Report

Block or report KwokHing

Report abuse

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

Report abuse
KwokHing/README.md

Hi there! I'm Kwok Hing, a passionate Data Scientist using Machine Learning, in particular, Natural Language Processing (NLP) and Generative AI (GenAI) to obtain insights, predict outcomes, and improve productivity by automating / optimising processes

=================================

📄 Skills:

📊 Data Science Languages: Python, R, SQL
🤖 Machine Learning: scikit-learn, TensorFlow, PyTorch
🧪 Reinforcement Learning: Stable-Baselines3
📚 Natural Language Processing: NLTK, Gensim, spaCy, Transformers, BERT, S-BERT, HuggingFace
🧮 Generative AI: Prompt Engineering, Retrieval-Augmented Generation (RAG), LangChain, Azure OpenAI
📈 Data Visualization: Tableau, Power BI
🛠️ Web Applications: Gradio, Streamlit, Flask, Bootstrap, CSS

=================================

📫 Connect with Me:

Linkedin Badge Gmail Badge

Pinned Loading

  1. AI-Planet-LLM-Bootcamp-Challenge AI-Planet-LLM-Bootcamp-Challenge Public

    An LLM challenge to (i) fine-tune pre-trained HuggingFace transformer model to build a Code Generation language model, and (ii) build a retrieval-augmented generation (RAG) application using LangChain

    Jupyter Notebook 2

  2. Uplimit-Project-Podcast-Frontend Uplimit-Project-Podcast-Frontend Public

    An LLM app to summarize a podcast episode, identifies podcast guests and attempts to retrieve the guest's public information from wikipedia, and identifies key highlights using OpenAI ChatGPT with …

    Jupyter Notebook

  3. Demo-on-automated-fact-checking-using-S-BERT Demo-on-automated-fact-checking-using-S-BERT Public

    In this demo, we illustrate the the possibility of using Semantic Search + Recognising Textual Entailment with Gradio to build an automated fact checking tool

    Jupyter Notebook

  4. SentimentAnalysis-Python-Demo SentimentAnalysis-Python-Demo Public

    Submission of an in-class NLP sentiment analysis competition held at Microsoft AI Singapore group. This submission entry explores the performance of both lexicon & machine-learning based models

    Jupyter Notebook 15 10

  5. YandexCatBoost-Python-Demo YandexCatBoost-Python-Demo Public

    Demo on the capability of Yandex CatBoost gradient boosting classifier on a fictitious IBM HR dataset obtained from Kaggle. Data exploration, cleaning, preprocessing and model tuning are performed …

    Jupyter Notebook 30 16

  6. Regression-with-a-Crab-Age-Dataset Regression-with-a-Crab-Age-Dataset Public

    A light-weight Kaggle challenge to predict crabs' age

    Jupyter Notebook