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 11 3

2. reasoning-and-alignment reasoning-and-alignment Public

   Fine-tuning small language models to reason, align, and use tools (from scratch and on free hardware)

   Jupyter Notebook

3. 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 4

4. 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 23 3

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

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

   Jupyter Notebook 6