Anas Ahouzi's Projects
Anas Ahouzi profile description
This project focuses on fundamental steps to set up an A/B test experiment, alongside some statistical analysis in Python.
Generates high resolution face images from low resolution ones using SRGANs.
:zap: Dynamically generated stats for your github readmes
Scrape Instagram content and stories, using a new technique based on the har file (No Token + No public API).
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
Port of Facebook's LLaMA model in C/C++
A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.
Multilabel classification of skill sets based on a job description, and deployment in a web app using Flask and pythonanywhere.
Provide unified APIs for SOTA model compression techniques, such as low precision (INT8/INT4/FP4/NF4) quantization, sparsity, pruning, and knowledge distillation on mainstream AI frameworks such as TensorFlow, PyTorch, and ONNX Runtime.
An innovation library for efficient LLM inference via low-bit quantization and sparsity
Implementation of 11 variants of Gradient Descent algorithm from scratch, applied to the Boston Housing Dataset.
Simple Document Classification using Multi Class Logistic Regression & SVM Soft Margin from scratch
An overview of various quantitative techniques and trading strategies for predicting stock prices, based on historical data from YahooFinance.