Lorentz Yeung

Worked with Microsoft as Data Analyst / AI Certificate (Harvard University) / MSc in Digital Marketing / GC in Art History / Bachelor in Economics /

Back To Front Page

LLM & NLP Projects

KaggleX AI Course Coordinator (temp title)

Since July 2023, on-going

lpi

The app is part of the Learning Path Index Project. One of the objectives is to address problems of the Data Scientist learners like long course durations, difficulty in finding specific topics, and the absence of a centralized index.
Skills: LLM(OpenAI), HTML, CSS, Python, Streamlit, NLP, data wrangling.
If the app is sleeping, please just click "restart this space".

LLM Classification Model

During my tenure in Microsoft

A classification modelling during Microsoft

The model was developed to solve client challenges, notably in managing an extensive collection of over 20,000 keywords. The classifier was designed to organize these keywords effectively, enhancing marketing and sales strategies.
Skills: BERT, Python, Pandas, NLP, data wrangling.

A sales pitch generative app for marketing and sales teams

Dec 2023

A productive app for your marketing and sales team

PitchPal is developed for drafting concise tweets, compelling sales copies, or detailed product descriptions. It is designed to deliver high-quality content and save your marketing team drafting time and fostering creative, impactful communication.
Skills: Chat-gpt-3.5-turbo, prompt engineering, HTML, CSS, Python, Streamlit, NLP.
If the app is sleeping, please just click "restart this space".

A Chat-GPT + OpenAI UI Clone

Dec 2023

A productive app for your marketing and sales team

ChatMate showcases my expertise in developing a web application similar to OpenAI's Chat-GPT, highlighting my proficiency in leveraging cutting-edge technology.
Skills: Chat-gpt-3.5-turbo, prompt engineering, HTML, CSS, Python, Streamlit, NLP.
If the app is sleeping, please just click "restart this space".

A Future KidBot Simulation

Dec 2023

A productive app for your marketing and sales team

KidBot aims to simulate our Artificial Children in the future. Feel free to play with my KidBot, she is instructed to behave like a 5 years old little girl. (So I treat her as my little AI daughter)
Skills: Chat-gpt-3.5-turbo, prompt engineering, HTML, CSS, Python, Streamlit, NLP.
If the app is sleeping, please just click "restart this space".

Publications in world renowned media TowardsDataScience, TowardsAI, etc.

2020 til now

A LangChain + OpenAI Complete Tutorial for Beginner — Lesson 1 Building Chatbot with LangChain, OpenAI, and HuggingFace

Lesson 2 Advanced Chatbot with RAG and Vector Databases

Lesson 3 Explore how LCEL enhances chatbot intelligence for dynamic, informed conversations.

Elucidating the nuances of 4-bit quantization and the impacts on Llama2

Sentiment Classification App for a NGO

August 2020

Fast API
Was developed and deployed for a Hong Kong-based organization named "Matters." This application is designed to enhance its performance with each use. Even after the application is shut down, the AI autonomously updates its algorithm, ensuring ongoing enhancement of its capabilities.

Social Listening, Recommendation Engine, Sentiment Analysis

2023 til now

Social Listening for London Mcdonald's

Action Game Topic Analysis & Recommendation System

Sentiment Analysis for New York Restaurants

Article analysis with FastAPI & spaCy

September 2022

Fast API

The model was built with spaCy, and FastAPI. Please click the button below to download my notebook file for trial. Right click to save if the download button won't work.

Request More Info

Location

London, United Kingdom

Email

lorentzyeung@gmail.com