Unfolding the universe of possibilities..

Navigating the waves of the web ocean

Speculative Sampling — Intuitively and Exhaustively Explained

A drop-in strategy for making language models 3x faster Continue reading on Towards Data Science »

Towards AGI: LLMs and Foundational Models’ Roles in the Lifelong Learning Revolution

Integrating Innovations in Continual Learning Advancements Towards Artificial General Intelligence (AGI), Including VOYAGER, DEPS, and AutoGPT. Authors: Elahe Aghapour, Salar Rahili Introduction: In the past decade and especially with the success of deep learning, an ongoing discussion has formed around the possibility

Develop Your First AI Agent: Deep Q-Learning

Dive into the world of artificial intelligence — build a deep reinforcement learning gym from scratch. Construct your own Deep Reinforcement Learning Gym — Image by author Table of Contents If you already have a grasp of Reinforcement and Deep Q-Learning concepts, feel free to jump directly

MLX vs MPS vs CUDA: a Benchmark

A first benchmark of Apple’s new ML framework MLX Continue reading on Towards Data Science »

The Surprising Behavior of Data in Higher Dimensions

A journey into the surprising world of high-dimensional data: the blessings and the challenges Photo by Guillermo Ferla on Unsplash Richard Feynman, the renowned physicist, once said, “I can safely say that nobody understands quantum mechanics.” In his interview titled “Fun

Mixtral-8x7B: Understanding and Running the Sparse Mixture of Experts

How to efficiently outperform GPT-3.5 and Llama 2 70B Continue reading on Towards Data Science »

Be Careful When Using “NOT IN” in SQL

+ 3 simple solutions to make sure you’re not caught out Continue reading on Towards Data Science »

How to efficiently fine-tune your own open-source LLM using novel techniques — code provided

In this article I tune a base LLama2 LLM to output SQL code. I use Parameter Efficient Fine-Tuning Techniques to optimise the process. Continue reading on Towards Data Science »

The Unstructured Data Funnel

Why a funnel is the centre of the war between data’s heaviest hitters Continue reading on Towards Data Science »

Towards LLM explainability: why did my model produce this output ?

The recent release of larger, better LLMs that showcase new capabilities has been paired with growing concerns over AI safety Continue reading on Towards Data Science »