4-bit Quantization with GPTQ | Towards Data Science

Maxime Labonne

Quantize your own LLMs using AutoGPTQ Image by author Recent advancements in weight quantization allow us to run massive large language models on consumer hardware, like a LLaMA-30B model on an RTX 3090 GPU. This is possible thanks to novel 4-bit quantization techniques with minimal performance degradation, like GPTQ, GGML, and NF4. In the previous … Read more

Generating Synthetic Data with Python | by Iffat Malik Gore | Jul, 2023

Iffat Malik Gore

A Comprehensive Guide to Creating Synthetic Data Image by author We keep hearing time and again about the pivotal role that data plays in driving growth, innovation, and competitiveness. It has become the bedrock for success across all industries. In essence, data has become the foundation of our every endeavour, from crafting technical blogs, educational … Read more

All Large Language Models (LLMs) You Should Know in 2023 | by Terence Shin | Jul, 2023

Terence Shin

Intuitive explanations of the most popular LLMs Image by Freepik In my last article, we dived into the world of machine learning models, understanding their working principles and how they fit into various practical applications. Today, we’ll venture into something that has quite literally taken over the entire tech space, large language models. Specifically, we’re … Read more

Building an interactive ML dashboard in Panel | by Sophia Yang, Ph.D. | Jun, 2023

Sophia Yang

By Andrew Huang, Sophia Yang, Philipp Rudiger Demo of the image classification app. HoloViz Panel is a versatile Python library that empowers developers and data scientists to build interactive visualizations with ease. Whether you’re working on machine learning projects, developing web applications, or designing data dashboards, Panel provides a powerful set of tools and features … Read more

Double Machine Learning Simplified: Part 2 — Targeting & the CATE | by Jacob Pieniazek | Jul, 2023

Jacob Pieniazek

Learn how to utilize DML for estimating individual level treatment effects to enable data-driven targeting This article is the 2nd in a 2 part series on simplifying and democratizing Double Machine Learning. In the 1st part, we covered the fundamentals of Double Machine Learning, along with two basic causal inference applications. Now, in pt. 2, … Read more

Enhancing CSV File Query Performance in ChatGPT | by Shuyang Xiang | Jul, 2023

Shuyang Xiang

with LangChain’s Self-Querying based on a customized CSV Loader The advent of sophisticated language models, like ChatGPT, has brought a novel and promising approach to querying tabular data. However, due to token limitations, directly executing a query becomes challenging without the assistance of APIs like retriever. Consequently, the accuracy of queries heavily relies on the … Read more

How To Become A Prompt Engineer, Skills, Resources to learn

how to become prompt engineer

AI prompt engineering positions command lucrative salaries, ranging from $175,000 to over $300,000 annually, making it an appealing career choice. However, excelling as an AI prompt engineer demands more than just adeptly asking questions. Success in this field requires a fusion of AI, programming, language proficiency, creative problem-solving, and artistic skills to flourish in this … Read more

Practical Prompt Engineering. Tips and tricks for successful… | by Cameron R. Wolfe, Ph.D. | Jul, 2023

Cameron R. Wolfe, Ph.D.

Tips and tricks for successful prompting with LLMs… (Photo by Jan Kahánek on Unsplash) Due to their text-to-text format, large language models (LLMs) are capable of solving a wide variety of tasks with a single model. Such a capability was originally demonstrated via zero and few-shot learning with models like GPT-2 and GPT-3 [5, 6]. … Read more

The Necessity of a Gradient of Explainability in AI | by Kevin Berlemont, PhD | Jul, 2023

Kevin Berlemont, PhD

Too much detail can be overwhelming, yet insufficient detail can be misleading. Photo by No Revisions on Unsplash “Any sufficiently advanced technology is indistinguishable from magic” — Arthur C. Clarke With the advances in self-driving cars, computer vision, and more recently, large language models, science can sometimes feel like magic! Models are becoming more and … Read more