💻 My Projects

PaliGemma
End-to-end reconstruction of PaliGemma in PyTorch, featuring SigLIP ViT, Gemma decoder with RoPE & GQA, KV caching, and autoregressive multimodal inference.
VLM PyTorch Multimodal Transformers
Pragna-1B
Reverse-engineering Pragna-1B. A from-scratch PyTorch runtime with RoPE, GQA, RMSNorm, SwiGLU, and checkpoint parity.
Language-Model PyTorch Reverse-Engineering Transformers Huggingface
Wav2Vec2
End-to-end PyTorch implementation of Wav2Vec2 with convolutional feature encoding, Transformer contextualization, Gumbel vector quantization, and full pipelines for contrastive pre-training and CTC fine-tuning.
LLM Speech PyTorch Transformers
VisionSmith
A clean, from-scratch Vision Transformer (ViT) implementation in PyTorch, trained on MNIST based on the "An Image is Worth 16x16 Words" paper.
Vision PyTorch Transformers
ArXivGPT
A 124M-parameter GPT-2 model trained from scratch on ArXiv abstracts, featuring fully custom Transformer components implemented in PyTorch.
LLM Pre-training Transformers
ScratchSpeakSLM
A tiny GPT-style language model built completely from scratch in PyTorch, inspired by TinyStories, demonstrating how small transformer models can learn to generate coherent text.
SLM PyTorch Transformers
LlamaCare
A LoRA-fine-tuned TinyLlama-1.1B model designed for supportive, empathetic mental-health responses. Trained on a custom 15k-sample dataset with 4-bit quantization, achieving massive perplexity improvements and efficient performance on a single H100 GPU.
LLM Fine-Tuning Healthcare
Conformer
End-to-end Conformer ASR in PyTorch featuring Macaron-style blocks, relative multi-head attention, depthwise convolutions, and an LSTM decoder with CTC loss.
Audio ASR PyTorch Transformers
DeepSpeech2
A from-scratch PyTorch implementation of the DeepSpeech2 architecture for automatic speech recognition (ASR)
ASR PyTorch
Indic-ASR
Hindi Speech Recognition model reducing WER from 30.18% to 20.75%, matching performance of commercial APIs like Sarvam.
Audio LLM Benchmarking
CerinaFoundry
specialized multi-agent AI system designed to assist mental health professionals in drafting Cognitive Behavioral Therapy (CBT) clinical protocols.
AI Agents Healthcare
Agentorithm
A sophisticated, multi-agent AI system designed to solve Data Structures and Algorithms (DSA) problems by breaking them down into simpler steps.
AI Agents Python
ArXivMind
ArXivMind is an intelligent, multi-agent system designed to accelerate academic research. Built with Microsoft's AutoGen framework, it automates the process of finding and summarizing scholarly articles from arXiv.
Research AI Agents Python
CFAspire
CFAspire is an intelligent chatbot designed to help users study for the CFA Level 1 exam.
CFA LLM AI Agents
StockSage
A powerful, multi-agent financial analysis tool built with the phidata library for deep diving into stock market data.
Finance AI Agents