Mohamad Hussein's Projects
Made a convenient LCD circuit for easy plug and play. Images of the solidworks drawing and of the circuit itself
Android app that sends prompts and receives response from ChatGPT3.5 using the OpenAI API.
This is an attempt to configure a chatbot using the falcon-7b-instruct parameter model to run locally on a machine with <8Gb VRAM. Using 4 bit quantization to reduce memory load.
Used both logistic regression and random forest models to predict the survived feature. Got 0.758 and 0.772 accuracy respectively.
Just a quick program to use stable diffusion XL to generate images with minimal GPU memory, using the Streamlit library
This is my first set up of a knn machine learning model and the chosen dataset is made up.
Config files for my GitHub profile.
Learning more on machine learning and statistics by making a naive bayes classifier through this video: https://www.youtube.com/watch?v=3I8oX3OUL6I&ab_channel=NormalizedNerd
Making a neural network that predicts the type of crimes depending on various factors.
This is a website that generates obituaries using the power of ChatGPT prompting. All you have to do is input a name, a picture, and its date to get a formatted graphical obituary on the topic!
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Desktop application for Linux and Windows that utilizes distil-whisper models from HuggingFace, to enable real-time offline speech-to-text dictation.
Final Portfolio Project in ENDG 233 of the 2021-2022 school year.