The stories that resonated the most with our community in the past month- 24527Murphy2025-03-23
Beginner-friendly Python code walkthrough (ft. MLX)- 28382Murphy2025-03-23
Which features carry the most weight? How do original features contribute to principal components? These 5 visualization types have the...- 25399Murphy2025-03-23
The story behind BeatBuddy, a web app that analyzes what you're listening to on Spotify- 26311Murphy2025-03-23
What is interpretable clustering and why is it important.- 21290Murphy2025-03-23
The ability to turn ideas into software products is a great skill to learn. In this blog, I will describe what it takes, and how to put the...- 20581Murphy2025-03-23
A step-by-step tutorial for fine-tuning SAM2 for custom segmentation tasks.- 26376Murphy2025-03-23
How integrating Batch Normalization in an encoder-only Transformer architecture can lead to reduced training time and inference time.- 29941Murphy2025-03-23
An intuitive guide to text vectorization- 22351Murphy2025-03-23
Learn how to use the building blocks of Delta Lakes.- 24471Murphy2025-03-23
When we have a large amount of data, we might ask: Do I really need all this data in my reporting? If no, read this piece to learn more.- 29252Murphy2025-03-23
Lessons from 30+ years in data engineering: The overlooked value of keeping it simple- 30046Murphy2025-03-23
A comprehensive walkthrough on how one can utilize AWS Lambda, Bedrock, and S3 to create a workflow that will summarize a meeting...- 21253Murphy2025-03-23
Foundation + Promptable + Interactive + Video. How?- 29822Murphy2025-03-23
Using LLM prompting for tagging metadata on humanitarian datasets- 28463Murphy2025-03-23
Two New Graphs That Compare Runners on the Same Event- 21203Murphy2025-03-23
A Comparative Study of Small-Scale Language Models: Evaluating Gemma, Llama 3, and Mistral in Reading Comprehension Tasks- 25190Murphy2025-03-23
Using the giant Llama 3.1 405B and Nvidia Nemotron 4 reward model to create a synthetic dataset for instruction fine-tuning.- 23052Murphy2025-03-23
Adding evaluation, automated data pulling, and other improvements.- 29641Murphy2025-03-23
Batching your inputs together can lead to substantial savings without compromising on performance- 27227Murphy2025-03-23
Why is ChatGPT only trained up until 2021?
Learn how to rearrange your code to achieve significant speed improvements.