Skip to content
View nickaqmal02's full-sized avatar
🎯
Focusing
🎯
Focusing
  • 03:37 (UTC -12:00)

Sponsoring

@neovim

Block or report nickaqmal02

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

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

Report abuse
nickaqmal02/README.md
Nik Abdul Aqmal — Computer Science @ UPNM. NeoFetch-style card with the Neovim logo, live GitHub stats, and current work: Sentiri (NLP for autism therapy centres), ApexAgent (macOS voice agent in Swift), and an XLM-R vs mBERT evaluation.

Fine-tuned XLM-R on 2,000 self-labelled Malay messages · Benchmarked 4 transformers and published the losses · Shipped a RAG + agent platform for real therapy centres · Built a local-first macOS voice agent in pure Swift

Final-year Computer Science @ UPNM · applied NLP & ML · backend engineering

I build models that survive evaluation and backends that people actually use. Email: nikabdulaqmal@gmail.com · 📄 Résumé (PDF)

0.933
negative recall
2,000
hand-labelled msgs
4
models benchmarked
1,400+
journal lines
3.79
CGPA · Dean's List
Résumé preview (pages loop every 6s)

Résumé preview — pages loop every 6s


⚙️ How I work

  • Measure before believing. Every model choice gets a held-out benchmark — including the ones that prove me wrong (mBERT beat my pick).
  • The LLM proposes, code verifies. Agents never commit an action (a booking, a tool call) until deterministic Python has checked it.
  • Privacy is a pipeline stage, not a policy. PII is stripped before any text reaches a model.
  • Online and offline paths. Every stage of my voice agent has a local fallback, so it degrades instead of dying.
  • Automate the boring parts. This profile card rebuilds itself nightly from the GitHub API via Actions.

🛠 Stack

Python, PyTorch, Django, FastAPI, PostgreSQL, Redis, Swift, JavaScript, React, Tailwind, Laravel, Rust, Linux, Neovim, Git, MATLAB

plus Hugging Face Transformers · LangChain · ChromaDB · BERTopic · Celery · Ollama · Quarto


koi

📌 Portfolio

🧠 Sentiri — Autism therapy chat analyzer

Python · Django 6 · PyTorch · PostgreSQL · ChromaDB · LangChain · Celery

Clinical platform for autism therapy centres: imports WhatsApp exports, links messages to clients, and turns them into sentiment, topics, and grounded answers.

  • Sentiment — XLM-RoBERTa fine-tuned on 2,000 self-labelled Malay / code-switched therapy messages.
  • Topics — BERTopic (UMAP → HDBSCAN → c-TF-IDF) with Sastrawi stemming, resolving to 5 supervisor-confirmed themes across 266 analysed messages.
  • RAG assistant — multilingual MiniLM → ChromaDB → cross-encoder rerank (retrieve 20, answer from 5) over clinic treatment documents.
  • Booking agent — LangChain + GLM-5.3 with Redis memory; the LLM proposes, Python verifies availability, only then is it confirmed.
  • Privacy — a PII wall strips 54 client/therapist name tokens before any text reaches a model.
  • Ops — Celery Beat reminders, role-based dashboards (admin / therapist / doctor / client), DSM-5 specifier approval workflow.

Repository →


📊 Model evaluation — XLM-R vs mBERT vs IndoBERT vs DistilBERT

PyTorch · Hugging Face · Quarto · Jupyter

My project shipped XLM-R because "it handles Malay natively." That is a hypothesis, so I tested it on the same 432-message held-out split.

Model Accuracy Macro-F1 Negative recall Params
mBERT 0.882 0.881 0.919 178M
XLM-R 0.863 0.862 0.933 278M
IndoBERT 0.509 0.046 0.899 124M
DistilBERT 0.345 0.171 1.000 135M
  • The hypothesis lost: mBERT also won on rojak (0.951 vs 0.926) and pure Malay (0.923 vs 0.863).
  • The decision held anyway: in a therapy context the expensive error is missing distress, so XLM-R's negative recall won the requirement — documented as a trade-off, not hidden.
  • Two baselines collapsed and are reported as-is.
  • Topic modelling defended architecturally (no labels): 42% multi-topic rate, NPMI c_v coherence −0.753, honestly interpreted for 3-token documents.

Repository →


🎙 ApexAgent — macOS voice agent in pure Swift

Swift · Ollama · Deepgram · Accessibility API

Jarvis, but local. Voice in → intent → tool execution → voice out, with an online and offline path at every stage: Deepgram Flux / Apple Speech, GLM API / local Qwen3 8B, Aura-2 / AVSpeechSynthesizer. No Xcode project — Swift Package Manager from the terminal.

Repository → · Demo video →


🔎 PersonalRAG — a second brain in the terminal

Python · Textual · Groq · vector search

Personal retrieval-augmented agent with a real TUI: ingest PDFs, semantic search, cited answers with source tracking, persistent local embeddings. Where I learned retrieval quality — not prompt wording — decides whether RAG works.

Repository →


🧰 Also on GitHub

12 more projects — e-commerce, data analysis, image processing, learning tracks
Project What it is Stack
django_ecommerce_stripe E-commerce with payments and order state Django, Stripe
studentperformanceanalysis Exploratory analysis + modelling notebook Python, pandas
diet-optimizer Constraint-based meal planning Laravel, Blade
fuzzylogicvisualization Interactive fuzzy-inference explainer HTML, JS
DIGITALIMAGEPROCESSING Coursework: filters, transforms, feature work Python
notesprojectcli CLI notes app Python
learningdjangoblog · fullstackapplication · javascriptlearningjourney · first_rust_program Learning tracks kept public on purpose Django · JS · Rust
RAGLearning · RAGPersonalAcademy RAG bootcamp notes and experiments Python

🎓 Education & awards

B.Sc. Computer Science (Honours) National Defence University of Malaysia (UPNM) · CGPA 3.79
STPM Science stream · 3.92
Awards Dean's List · First Class Award, UPNM
Certifications MATLAB Fundamentals & Machine Learning · Django & REST APIs · Full-stack (Tailwind, JS, PostgreSQL)
Currently learning FastAPI + Poetry, vector databases, Swift beyond the terminal

📈 Consistency

GitHub contribution streak for nickaqmal02


I'd rather understand a pipeline than copy one. The engineering journal for Sentiri is 1,400+ lines of bugs, wrong hypotheses, and the reasoning that fixed them.

Pinned Loading

  1. ApexAgent ApexAgent Public

    Swift 1

  2. finalyearenginefulleffort finalyearenginefulleffort Public

    This project are fully enterprise level project

    Python 1

  3. PersonalRAG PersonalRAG Public

    this is personal RAG application for study and building my own agent as a second mind

    Python 1

  4. MatrixEvaluationModel MatrixEvaluationModel Public

    HTML

  5. studentperformanceanalysis studentperformanceanalysis Public

    Jupyter Notebook

  6. django_ecommerce_stripe django_ecommerce_stripe Public

    HTML 1