A Deep Dive into Autoencoders and Their Relationship to PCA and SVD
An in-depth exploration of autoencoders and dimensionality reduction
my_library
The fear of being duped is ubiquitous, but excessive scepticism makes it ha
The fear of being duped is ubiquitous, but excessive scepticism makes it harder to trust one another and cooperate
Rails 7.0: Fulfilling a vision
This version of Rails has been years in the conceptual making. It’s the fulfillment of a vision to present a truly full-stack approach to web development that tackles both the front- and back-end challenges with equal vigor. An omakase menu that includes everything from the…
Free Full Stack LLM Bootcamp
Want to learn more about LLMs and build cool LLM-powered applications? This free Full Stack LLM Bootcamp is all you need!
The Instant Pot Failed Because It Was a Good Product
A one-hit wonder is never enough.
A Story of Pepper, the World’s Most Important and Underappreciated Spice
How Arabs, Malabarians and Portuguese shaped the world in search of the 'black gold'
Edge 300: Meet Falcon LLM: The Most Powerful Open Source LLM Released to Da
The model quickly top the Open LLM Leaderboard that ranks the performance of open source LLMs.
From “Heavy Purchasers” of Pregnancy Tests to the Depression-Prone: We Foun
A spreadsheet on ad platform Xandr’s website revealed a massive collection of “audience segments” used to target consumers based on highly specific, sometimes intimate information and inferences
How Can Platforms Deal with Toxic Content? Look to Wall Street
Social media has a content problem. It's not the content itself, although the list of toxic material is long. The problem is the sheer volume of content. Instead of trusting in self-regulation, the United States could use its regulation of Wall Street after 2008 as a roadmap for…
How to crawl a quarter billion webpages in 40 hours
How GPT works: A Metaphoric Explanation of Key, Value, Query in Attention,
GPT, explained simply, in a metaphor of potion.
Why You Need To Know About Autonomous AI Agents
A beginner's guide to understanding autonomous AI agents and their importance.
Machine Learning in a Non-Euclidean space
Chapter I. Why you should learn about non-Euclidean ML
Use Systemctl Status Command to Check Service Status
Learn how to check and understand the status of a systemd service using the systemctl command.
Extract Images from PDF: Download processed file(s)
The Secret Sauce behind 100K context window in LLMs: all tricks in one plac
tldr; techniques to speed up training and inference of LLMs to use large context window up to 100K input tokens during training and…
All You Need to Know to Build Your First LLM App
A step-by-step tutorial to document loaders, embeddings, vector stores and prompt templates
Creating Incredible Decision Tree Visualizations with dtreeviz
How to visualize decision tree models with this useful library
Observe.ai unveils 30-billion-parameter contact center LLM and a generative
The Observe.AI contact center LLM showed a 35% increase in accuracy compared to GPT-3.5 when automatically summarizing conversations.
Unsupervised Learning Series — Exploring Hierarchical Clustering
Let’s explore how hierarchical clustering works and how it builds clusters based on pairwise distances.
Plex
Training LLMs with AMD MI250 GPUs and MosaicML
With the release of PyTorch 2.0 and ROCm 5.4, we are excited to announce that LLM training works out of the box on AMD MI250 accelerators with zero code changes and at high performance!
KDnuggets News, June 28: 10 ChatGPT Plugins for Data Science Cheat Sheet •
10 ChatGPT Plugins for Data Science Cheat Sheet • Noteable Plugin: The ChatGPT Plugin That Automates Data Analysis • 3 Ways to Access Claude AI for Free • What are Vector Databases and Why Are They Important for LLMs? • A Data Scientist’s Essential Guide to Exploratory Data…
Joins 13 Ways
Optimizing Memory Usage for Training LLMs and Vision Transformers in PyTorc
This article provides a series of techniques that can lower memory consumption in PyTorch (when training vision transformers and LLMs) by approximately 20x without sacrificing modeling performance and prediction accuracy.
Top 5 Gems for Implementing a Search Engine in a Rails App
Thanks to gems, it is easy to implement a search engine into Rails applications. Of course, you have to choose which gem to use. While there are countless options, four stand out as the best. You will be happy with any of these options.
Deploying Falcon-7B Into Production
Running Falcon-7B in the cloud as a microservice
How to Train Generative AI Using Your Company’s Data
Leveraging a company’s proprietary knowledge is critical to its ability to compete and innovate, especially in today’s volatile environment. Organizational innovation is fueled through effective and agile creation, management, application, recombination, and deployment of…
Shell Built-in Commands
In Linux, there are shell built-in commands which you are already using but never paid attention to. Learn more about them in this tutorial.
I Used ChatGPT (Every Day) for 5 Months. Here Are Some Hidden Gems That Wil
Transform your life with these ChatGPT’s hidden gems.
Anthropic releases Claude 2, its second-gen AI chatbot
Anthropic, the AI startup founded by ex-OpenAI execs, has released its newest chatbot, Claude 2. It's ostensibly improved in several ways.
A Gentle Introduction to Support Vector Machines
A guide to understanding support vector machines for classification: from theory to scikit-learn implementation.
Feature Transformations: A Tutorial on PCA and LDA
Reducing the dimension of a dataset using methods such as PCA
Google Launches AI-Powered Notes App Called NotebookLM
Google is launching its AI-backed note-taking tool to "a small group of users in the US," the company said in a blog post. Formerly referred to as Project Tailwind at Google I/O earlier this year, the new app is now known as NotebookLM (the LM stands for Language Model). The…
Uplift Modeling — A Data Scientist’s Guide to Optimizing a Credit Card Rene
Applying causal machine learning to trim the campaign target audience
An Introduction to Devise for Ruby on Rails
In part one of this series on Devise, we'll cover the basics of the Devise gem.
Meet LMQL: An Open Source Query Language for LLMs
Developed by ETH Zürich, the language explores new paradigms for LLM programming.
Ecosystem Graphs for Foundation Models
Chapter 16: Reusing Previous Computations
Chapter 16, Reusing Previous Computations, is now finished!
Meta reveals new AI image generation model CM3leon, touting greater efficie
Looking at the sample sets of generated images that Meta has shared in its blog post about CM3leon, the results are impressive.
CUDA Quick Start Guide
Minimal first-steps instructions to get CUDA running on a standard system.
Leandro von Werra’s Post
It crazy how far the ML field has come when it comes to fine-tuning LLMs. A year ago: it was challenging to fine-tune GPT-2 (1.5B) on a single GPU without… | 76 comments on LinkedIn
Why America’s Largest Tool Company Couldn’t Make a Wrench in America …
archived 22 Jul 2023 03:08:13 UTC
LLaMA 2: How to access and use Meta’s versatile open-source chatbot right n
A comprehensive guide on how to use Meta's LLaMA 2, the new open-source AI model challenging OpenAI's ChatGPT and Google's Bard.
The Balancing Act Of Training Generative AI
We learn a lot of lessons from the hyperscalers and HPC centers of the world, and one of them is that those who control their own software control their
How We Determine What to Believe as True
Psychologists have been studying a very basic cognitive function that appears to be of increasing importance - how do we choose what to believe as true or false? We live in a world awash in information, and access to essentially the world's store of knowledge is now a trivial…
Design of complex tables
How Mathematical Curves Enable Advanced Communication
A simple geometric idea has been used to power advances in information theory, cryptography and even blockchain technology.
Beyond LLaMA: The Power of Open LLMs
How LLaMA is making open-source cool again
Edge 309: What is Active Prompting?
Understanding one of the most effective techniques to improve the effectiveness of prompts in LLM applications.