🎓 AI Researcher | 🧠 LLM Expert | 📊 Data Scientist
🔬 Data Science, Deep Learning, LLM, NLP, Cybersecurity, and Real-World Applications

I'm an AI researcher and data scientist passionate about advancing Large Language Models (LLMs) and Data Science for impactful, real-world applications. With a Ph.D. in Computer Science from McGill University, I’ve led and contributed to open-source tools and publications at the intersection of deep learning, NLP, and cybersecurity.

• 🧩 Miles_AI_Collection
  A curated repository of my LLM experiments, including training, and application built with LangChain etc.

• 💬 Virtual Customer Service Representative (RAG)
  Two-page web app (Admin + Chat) with a FastAPI backend using LangChain + LangGraph ReAct agent and FAISS vector store (Ollama embeddings) for retrieval-augmented generation.

  • Admin panel to configure models and upload knowledge files (PDF/TXT) for indexing.
  • Chat interface with persistent sessions and retrieval-augmented responses.
  • Integrates with local OpenAI-compatible LLMs and Ollama embeddings.

• 🦙 DMaS-LLaMa-Lite-Training-Code
  Complete training pipeline for a 1.7B-parameter LLaMa-based model, optimized for data-efficiency.

• 🔁 Incremental-LLM-Training
  Layer-wise incremental LLM training: a novel paradigm to improve compute utilization and training throughput.

• 📁 Miles_Data_Science_Collection
  Exploratory data analysis, modeling, and evaluation on real-world datasets across domains (music, healthcare, finance).

• 🛠️ Kam1n0-Community
  Scalable binary similarity analysis platform for reverse engineering, built with Apache Spark and Cassandra.

• 🧮 iffnn
  Interpretable feedforward neural network architecture for tabular data with intrinsic explanations for its predictions.