January 2025 - Present
Everyday coding challenge to develop CUDA kernels from scratch.
January 2025
Code for my library to create simple LLMs for research purposes.
December 2024
A modular library focused on generative AI experimentation and development.
October 2024 - Present
Workflow and methodology for YOLO models.
September 2024
Project mostly for learning experience.I implement different RWKV architectures
September 2024
Energy Based Models that I implemented based on various papers and courses/talks by different researchers
July 2024
Developed several RNNs in PyTorch as a learning project, focusing on implementing mathematical formulas into models.
July 2024
Built several ConvNets as foundational components, providing a great learning experience on various architectures.
May 2024
Developed an image2latex model for extracting LaTeX formulas from images and an LLM for explaining mathematical concepts.
April 2024
Constructed the LLama 2 architecture entirely from the ground up. Throughout this project, I gained knowledge about KV-caching and ROPE
April 2024
GPT-2 based model trained on selected books from open libraries, leveraging existing GPT-2 weights for better language understanding and improved output quality.
March 2024
The Stable Diffusion architecture, implemented in PyTorch, was used for inference with version 1.5 weights from Hugging Face, providing key insights into building complex models.
January-February 2024
Implemented various GAN architectures including: WGAN, DCGAN, Linear GAN, C-GAN, CycleGAN, VAE Model, Pix2Pix Model for different image generation tasks.
March 2024
Text-to-Image pipeline based on CLIP architecture and used pretrained weights.
March 2024
Created Transformer architecture for English-German text translation, fine-tuning with HuggingFace's open weights.
December 2024
Created a simple MLP neural network using numpy
November 2023
Using VGG-16 pretrained feature maps for creating artworks through styletransfer.
November 2023
Fine-tuned YOLOv8 and crafted custom multi-object detection model for specialized tasks.
October 2023
PyTorch CNN with ResNet50 backbone for accurate multi-class classification.
October 2023
Developed FR-CNN model for robust object detection between busses and trucks.
October 2023
Implemented U-NET with VGG-16 backbone for precise street semantic segmentation.
September 2023
Achieved exceptional accuracy in tumor detection using diverse backbone architectures(VGG-16, ResNet50, MobileNetV3, Inception).