Completed Projects

These are only some of my favorite projects;

Llama-3.1-8B-Sarcasm: Human-Like Conversational AI   image

    Natural Language Processing, LLM Fine-tuning 2024

A fine-tuned language model based on Meta’s Llama-3.1-8B-Instruct that generates natural, human-like responses in conversations. The model excels at generating contextually appropriate replies with sarcasm, humor, and casual tones. Trained using AdaLoRA (Adaptive Low-Rank Adaptation) for parameter efficiency and improved generalization, it can process both single-turn exchanges and multi-turn conversations up to 7 turns of context. Available in both full model and quantized GGUF formats for efficient deployment.

Integrated Weights & Biases (W&B) for real-time monitoring of token usage, latency, user interaction flow, and model performance metrics.

                 

Multi-Modal AI Music Assistant   image  

    AI, Machine Learning, Recommendation Systems 2023

A personalized music recommendation system powered by AI that combines facial emotion detection, contextual awareness, and music analysis. The system detects user emotions from facial images, considers environmental factors (weather, time, location), and uses advanced Matern kernel similarity metrics for music matching. It connects with Spotify for seamless playback and adapts recommendations based on user feedback.

                 

Transformers: English-Hindi Translation   image

    Deep Learning, NLP, Transformers 2024

A complete implementation of transformer architecture from scratch for English to Hindi translation. The project features a full encoder-decoder architecture with RoPE (Rotary Position Embedding), multiple optimizer options (SGD, Momentum, RMSProp, Adam, Nadam) with Noam scheduler, and multi-head attention mechanisms with visualization support. The implementation includes batched processing with masking, checkpoint saving, and comprehensive performance metrics tracking.

             

Adaptive Decisioning Platform   image  

    Data Science,MLOPS , Predictive Analytics 2023

An intelligent, real-time decision-making system designed to automate critical business decisions using a combination of rule-based logic and machine learning. The platform adapts its recommendations or actions based on contextual data such as user behavior, time, or feedback history.

  • Built modular data pipelines for ingestion, preprocessing, and feature engineering.
  • Implemented predictive models and decision rules to handle classification and recommendation tasks.
  • Integrated REST APIs (FastAPI) for real-time model serving and feedback collection.
  • Enabled continuous learning through user feedback loops and context-aware adaptations.
  • Deployed containerized services using Docker for scalable and reliable deployment.

Multi-Agent Automated Research Assistant   image image

    AI Agents, LLM Applications 2025

A multi-agent system that automates the creation of structured literature reviews. It uses specialized agents for query analysis, document retrieval (via RAG), summarization, synthesis, and fact validation. The system integrates tools like LangChain, CrewAI, and ChromaDB to generate accurate, well-organized reports with citations, saving researchers significant time.

             

Gauri Tripathi