ZahraZsm89
Follow
Stars
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai
An open-source data logging library for machine learning models and data pipelines. 📚 Provides visibility into data quality & model performance over time. 🛡️ Supports privacy-preserving data collec…
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance m…
Erasing Concepts from Diffusion Models
Self-supervised learning for wearables using the UK-Biobank (>700,000 person-days)
[ECCV 2020] Official code for "Comprehensive Image Captioning via Scene Graph Decomposition"
Deep Learning & Information Bottleneck
Code for paper: Are Large Language Models Post Hoc Explainers?
PyTorch implementation of the paper "Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization" (ICLR 2021)
A system that analyses patient symptoms and provides preliminary diagnoses along with recommended treatments⚕️
Reproduces the paper NIMA: Neural Image Assessment and adapts the model to evaluate designs generated by genetic algorithms.
Explain Bugs with LLMs
This research advances credit card fraud detection by integrating machine learning and deep learning techniques. Key findings include improved model adaptability through hyperparameter tuning.
This project develops an activity recognition model for a mobile fitness app using statistical analysis and machine learning. By processing smartphone sensor data, it extracts features to train mod…
This project uses statistical analysis to detect fraudulent credit card transactions by examining patterns and anomalies in a dataset of 10,000 transactions, calculating averages, medians, frequen…
This project is created to analyze sentiment of comments of banking applications