LLM Eval: Benchmarking Suite for Large Language Models
Published:
Benchmarking and evaluation suite for large language models
Published:
Benchmarking and evaluation suite for large language models
Published:
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems.
Published:
A unified wrapper for various ML frameworks - to have one uniform scikit-learn format for predict and predict_proba functions
Published:
Safe and fair machine learning for researchers, data scientists, and beginners.
Published:
Demo of a chat bot for an e-commerce website built using ChatGPT that can answer questions about products and orders in real time by interacting with the website’s database.
Published:
A web app that uses object detection and Google Street View API to map pet preferences in different geographical regions.
Published:
A personalized news page that summarizes real-time news using the BART model from HuggingFace, using a MongoDB backend and hosted on Google Cloud Platform
Published:
We compare Plug-and-Play ADMM and Total Variation Denoising algorithms for recovering images distorted by Gaussian blur and additive white Gaussian noise.
Published:
We examine three algorithms that work for continuous state and action spaces – REINFORCE with Baseline, One-Step Actor-Critic for episodic tasks, and Episodic Semi-Gradient n-step SARSA.
Published:
Implementing a basic GAN in Tensorflow
Published:
Creating adversarial examples for image classifiers using fast gradient sign method
Published:
Kaggle ‘Getting Started Prediction Competition’ for NLP.
Published:
A simple and basic implementation of Naive Bayes for text classification