Unfolding the universe of possibilities..

Every load time is a step closer to discovery.

Add your own data to an LLM using Retrieval-Augmented Generation (RAG)

Add Your Own Data to an LLM Using Retrieval-Augmented Generation (RAG) Learn how to add your own proprietary data to a pre-trained LLM using a prompt-based technique called Retrieval-Augmented Generation Photo by Joshua Sortino on Unsplash Introduction Large Language Models (LLMs)

Change Point Detection — A Bayesian Approach

Change Point Detection — A Bayesian Approach Identifying a change point in time series analysis could provide you much more information about the series than you previously though Change point analysis has become a field of interest in many areas of study. This

Exploring GEMBA: A New LLM-Based Metric for Translation Quality Assessment

Using LLMs for evaluating translation quality Continue reading on Towards Data Science »

‘Talk’ to Your SQL Database Using LangChain and Azure OpenAI

Explore the power of natural language processing using LLMs for your database queries Langchain is an open source framework for developing applications which can process natural language using LLMs (Large Language Models). The Agent component of LangChain is a wrapper around LLM,

Regulating AI: The Case for a Mechanisms-Based Approach

Targeting specific mechanisms mitigates AI risks more effectively, is easier to get consensus on, and avoids unintended consequences of brute force approaches Photo by Growtika on Unsplash This is the second of three articles in Unpacked’s “Tech Policy September” series. Disclaimer:

Prompt Engineering Evolution: Defining the New Program Simulation Prompt Framework

A roadmap for crafting different types of program simulation prompts Source: Image by Author and generated with MidJourney Introduction In my recent article, New ChatGPT Prompt Engineering Technique: Program Simulation, I explored a new category of prompt engineering techniques that

Conversations as Directed Graphs with LangChain

Building a chatbot designed to understand key information about new prospective customers. Image by Daniel Warfield using MidJourney. All images by the author unless otherwise specified. In this post we’ll use LangChain to do lead qualification in a real-estate context.

XGBoost: Intro, Step-by-Step Implementation, and Performance Comparison

Extreme Gradient Boosting: A quick and reliable classifier Continue reading on Towards Data Science »

Run Llama 2 70B on Your GPU with ExLlamaV2

Finding the optimal mixed-precision quantization for your hardware Continue reading on Towards Data Science »

The Multi-Task Optimization Controversy

Do we need special algorithms to train models on multiple tasks at the same time? Continue reading on Towards Data Science »