Skip to content
View minyang-chen's full-sized avatar
🎯
Focusing
🎯
Focusing
23 followers · 2 following
  • https://github.com/PavAI-Research
  • Ontario, Canada

Achievements

Achievement: StarstruckAchievement: Pull Shark

Achievements

Achievement: StarstruckAchievement: Pull Shark

Block or report minyang-chen

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
minyang-chen/README.md

Engineer in AI,Software,Data,Cloud and Enterprise Architect

Hi there 👋

my name is Minyang, welcome to my github repositories. I am software enginner living in Greater Toronto Area, Canada.

I architected, designed and implemented business critical hub placement, billing and financial solution at world largest commercial insurance broker Marsh Canada (parent: MMC). As tech lead for one of the Canada largest Bank BMO to complete the banking systems modernization with real-time lead management and offering capabilities. At IBM Canada - Watson health tackling big data challenges in Health Care. developing secure privacy first platform, Cloud cognitive services and big data normalization pipelines, data protection and de-identification framework for analytics, data linking and AI training use cases.

I found my passion for AI, big data, cloud and mental model concepts many years ago. Since then I never stopped learning. Currently, I am focusing myself in the area Generative AI/Large Language Model (LLM) fine-tuning and knowledge enrichment with private data integration and how to leverage fine-tuned models to generate business value and assist problem-solving for an enterprise.

🔗 Connect with me

⚡Technologies

I believe that one should not have a fixed technology stack, but should always respond to the needs and problems of the customer and business needs. Below is just an excerpt and my favorite technologies in machine learning, cloud and non-ML frameworks.

🤖 Generative AI/ LLM
OpenAI ChatGPT, LLama2, Alpaca, H2OGPT

🤖 Machine Learning
LangChain,LlamIndex, Huggingface Transformers, Pytorch, Scikit-Learn, Tensorflow, Weights & Bias, Optuna, Pandas, Numpy

☁️ Cloud
AWS, GCP, Azure, Kubernetes, Kubeflow, Docker, Terraform, AWS CDK, Github Actions, Serverless Framework

☁️ Big Data
DuckDB, Apache Spark,Apache Iceberg, Cassandra, Hadoop,Delta Lake and Talend

☁️ Data Privacy
Microsoft presidio, postgresql anonymizer

🏗️ Frameworks
Poetry, Angular, Spring, Rust, React, Svelte, React-Native, LitElement, GraphQL, Gatsby, TailwindCSS

🏗️ Architectures
Clean, Event Driven, SOA, Distributed and decentralized, Polylith

🔭 Other topics

Here are some ideas to write about:

  • 🔭 I’m currently working on ... [AI researches, LLM model Merging, LLM fine-tuning and private knowledge integration]
  • 🌱 I’m currently learning ...
  • 👯 I’m looking to collaborate on ...
  • 🤔 I’m looking for help with ...
  • 💬 Ask me about ...
  • 📫 How to reach me: ...
  • 😄 Pronouns: ...
  • ⚡ Fun fact: ...

Popular repositories Loading

  1. LLM_convert_receipt_image-to-json_or_xml LLM_convert_receipt_image-to-json_or_xml Public

    Finetune LLM to convert an invoice or receipt image to receipt XML or JSON object.

    Jupyter Notebook 37 12

  2. tinyllama_colorist tinyllama_colorist Public

    finetune tinyllama to generate color code

    Jupyter Notebook 5 4

  3. h20_llm h20_llm Public

    Fine-tuning an LLM model with H2O LLM Studio to generate Cypher statements Avoid depending on external and ever changing APIs for your knowledge graph based chatbot

    Jupyter Notebook 2 1

  4. Knowledge_Distillation_Training Knowledge_Distillation_Training Public

    employ knowledge distillation to compress their large deep models into lightweight versions (Teacher and Student Model)

    Jupyter Notebook 2 1

  5. chatgpt_like_experience_locally chatgpt_like_experience_locally Public

    mimic chatgpt like experience locally using latest open source LLM models

    TypeScript 2

  6. chain-of-thoughts-agent chain-of-thoughts-agent Public

    Chain of Thoughts is a MRKL system - a modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning built on top of LLMs.

    Python 1