Skip to content
View BlackJack-14's full-sized avatar
♾️
Getting real
♾️
Getting real
4 followers · 5 following

Achievements

Achievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: Pull Sharkx2Achievement: Quickdraw

Highlights

  • Pro

Block or report BlackJack-14

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
BlackJack-14/README.md

Typing SVG


Stack


Python
PyTorch
React
Node.js
Express
FastAPI
MongoDB

PostgreSQL
Docker
AWS EC2
Nginx
Git
Linux
JavaScript

AI / ML / NLP

HuggingFace FAISS LoRA RAG Sentence Transformers OpenCV YOLO MediaPipe

Projects

Edu-SLM  ·  Domain-Specific Educational LLM

Python PyTorch LLaMA Qwen LoRA/PEFT RAG FAISS

Fine-tuned LLaMA & Qwen on OS curriculum using LoRA + RAG-assisted knowledge distillation. FAISS vector retrieval with semantic embeddings and synthetic dataset generation for curriculum-based QA.

95.3% accuracy · 655-MCQ benchmark
Reduced hallucinations
Low-cost · privacy-first · institution-grade

UPESCSA.in  ·  Official UPES-CSA Platform

MongoDB Express React Node.js Docker Nginx AWS EC2

Full MERN stack platform for event registrations and technical operations. Containerized with Docker, reverse-proxied via Nginx, hosted on AWS EC2.

Production · AWS EC2
Docker + Nginx deployment
Scalable REST API

TheGeetaWay  ·  AI Guidance Portal

Python FastAPI Streamlit FAISS Sentence Transformers Llama 3

Semantic search + RAG over Bhagavad Gita verses. Llama 3 generates verse-grounded, context-aware responses via FAISS retrieval pipeline.

FAISS vector retrieval
Llama 3 + Sentence Transformers
Verse-grounded RAG

ASL Recognition  ·  Real-Time Sign Language

Python OpenCV MediaPipe YOLO Deep Learning

Real-time ASL alphabet detection via YOLO + MediaPipe hand tracking for low-latency gesture recognition.

0.99+ precision
0.90 mAP
High-accuracy · low-latency

Stats

Currently Learning

Topic Progress
Advanced LLM Architectures ████████████░░░ 75%
RAG Optimization & Evaluation █████████████░░ 80%
Multi-Agent AI Systems ██████████░░░░░ 62%
Distributed Backend Systems ██████████░░░░░ 63%
AI Infrastructure & Serving ████████░░░░░░░ 50%

Popular repositories Loading

  1. Python-Calculator Python-Calculator Public

    Calculator made using python :)

    Python

  2. anime anime Public

    JavaScript

  3. covid_dashboard covid_dashboard Public

    JavaScript

  4. BlackJack-14 BlackJack-14 Public

    Config files for my GitHub profile.

  5. UPESCSA-Website-Backend UPESCSA-Website-Backend Public

    Forked from UPESCSA/UPESCSA-Website-Backend

    JavaScript

  6. UPESCSA-Website-Frontend UPESCSA-Website-Frontend Public

    Forked from UPESCSA/UPESCSA-Website-Frontend

    JavaScript