A curated collection of my machine learning models, AI solutions, and notebooks for various competitions.
Hi, I'm Shourya Varshney. This repository tracks my journey, experiments, and final submissions across different Kaggle competitions and global AI hackathons. Each folder corresponds to a specific challenge and contains the data processing, feature engineering, and model training code used to build the final solution.
| 🏅 Competition / Challenge | 🧠 Domain / Focus | 💻 Tech Stack / Models | 🏆 Status | 🔗 Code |
|---|---|---|---|---|
| CAFA 6 - Protein Function Prediction | Bioinformatics, Multi-label Classification | Python, PyTorch, Deep Learning | Active | 📁 View Code |
| [Nemotron Challenge] | Large Language Models (LLMs), NLP | Nemotron, Python, Prompt Engineering | Active | 📁 View Code |
(Note: Click on the folders to view the specific problem statements, exploratory data analysis (EDA), and the final implementation.)
- Data Processing: Pandas, NumPy
- Machine Learning & Deep Learning: Scikit-Learn, PyTorch, Neural Networks
- Generative AI: Large Language Models (LLMs), RAG Architectures, Prompt Engineering
- Specialized Domains: Bioinformatics, Natural Language Processing
To explore a specific challenge's code:
- Navigate to the respective directory from the table above.
- Read the local
README.mdinside that folder for a deep dive into the architecture and approach. - Open the
.ipynbor.pyfiles to view the step-by-step code.
If you found these approaches or notebooks helpful, consider leaving a ⭐ on the repository!