Qualization library based on 1R

Pytorch Model Quantization, Layer Fusion and Optimization

Project assignment for course Introduction to Telecommunications at ECE NTUA

Uniform quantizer that uses mexCallMATLAB to call different MATLAB commands and plot the results

Quantizing LLMs using GPTQ

Implementation of MedQ: Lossless ultra-low-bit neural network quantization for medical image segmentation

OnnxRT based Inference Optimization of Roberta model trained for Sentiment Analysis On Twitter Dataset

Regularized Classification-Aware Quantization

A compilation of various ML and DL models and ways to optimize the their inferences.

quantization for images

Optimized CPU Implementation of Llama2-LLM

Try to get some insights about Quantization

Efficient Inference techniques implemented in PyTorch for computer vision.

A library to help with the development of AI models with Keras, with a focus on edge / IoT applications. Based originally on https://github.com/yingkaisha/keras-unet-collection

Telecommunications notes, IST 2022/2023

Ask About Symptoms is an LLM that has an in-depth understanding of health. The creator of the original version known as DoctorGPT, Siraj Raval, says it works offline, it's cross-platform, & the health data is said to be kept private. We are learning how to build this in our community.

Pneumo.ai is a Streamlit web app for detecting pneumonia from X-rays, leveraging CNN variants like AlexNet, VGG, and ResNet18, with ResNet18 leading with an accuracy of 0.89. It employs early stopping callbacks for efficient model training, visualizes training using TensorBoard, and optimizes inference time with pruning and quantization techniques.