Pinned Loading

1. BobVLM BobVLM Public

   BobVLM – A 1.5B multimodal model built from scratch and pre-trained on a single P100 GPU capable of image descriptions and moderate question answering. 🤗🎉

   Python 5 2

2. Decoder-Only-LLM Decoder-Only-LLM Public

   This repository features a custom-built decoder-only language model (LLM) with a total of 37 million parameters 🔥. I train the model to be able to ask question from a given context

   Jupyter Notebook 16 3

3. Deblur-AI Deblur-AI Public

   This project uses AI to fix blur images of faces. This uses a 5-layered UNet architecture which hallucinates facial features to sharpen the image. This be used recreationally or aid in forensic inv…

   Python 17 4

4. ViT-FROM-SCRATCH ViT-FROM-SCRATCH Public

   This is an implementation of a simple Vision Transformer (ViT) for a dummy classification task of predicting whether a person is wearing a hat or not. 🎩🤠🎓

   Jupyter Notebook 1

5. Breast-Cancer-Segmentation Breast-Cancer-Segmentation Public

   An image segmentation Model that uses the U-Net Architecture to segment tumours from CT-Scan images of the breast.

   Jupyter Notebook 6

6. web-sight web-sight Public

   Web-sight is uses RAG (Retrieval Augmented Generation) to retrieve and analyze content from website

   Python 1