Tiny Llama – a Performance Review and Discussion
Learn how you can utilize a tiny large language model, fine-tune it, and achieve high performance- 20847Murphy2025-03-22
Bayesian Data Science: The What, Why, and How
Choosing between frequentist and Bayesian approaches is the great debate of the last century, with a recent surge in Bayesian adoption in...- 20439Murphy2025-03-22
Merging tokens to accelerate LLM inference with SLERP
We can significantly accelerate LLMs next token generation by merging consecutive pairs of tokens using SLERP, reducing the computing power...- 25169Murphy2025-03-22
3 Best Practices for Bridging the Gap Between Engineers and Analysts
Assigning code owners, hiring analytics engineers, and creating flywheels- 25054Murphy2025-03-22
The Math Behind "The Curse of Dimensionality"
Dive into the "Curse of Dimensionality" concept and understand the math behind all the surprising phenomena that arise in high dimensions.- 25162Murphy2025-03-22
The Elusive Challenge of Data Reconciliation in Large Organizations
How can we use clustering techniques to combine and refactor a large number of disparate dashboards?- 28856Murphy2025-03-22
Visualizing My Data Science Job Search
Reflections from a humbling journey trying to find a job in 2023- 29354Murphy2025-03-22
Quantization, Linear Regression, and Hardware for AI: Our Best Recent Deep Dives
Our weekly selection of must-read Editors' Picks and original features- 27291Murphy2025-03-22
Combining Storytelling and Design for Unforgettable Presentations
How to craft slide decks that stand out- 23729Murphy2025-03-22
Fine-tune Llama 3 with ORPO
A cheaper and faster unified fine-tuning technique- 21786Murphy2025-03-22
Complex List Comprehensions Can Be Readable!
Even quite complicated Python comprehensions can be more readable than the corresponding for loops.- 20279Murphy2025-03-22
Don't Crash Your App: Load Records from the Database in Batches for Better Performance
Save your Python app's performance by efficiently loading query- 27697Murphy2025-03-22
Designing the relationship between LLMs and user experience
How to make your LLM do the right things, and do them right- 23258Murphy2025-03-22
How to Read and Analyze GDAT Files Using Python
A quick tutorial on how to work with these computer-modelled binary files.- 21743Murphy2025-03-22
Label Studio Customized Backend for Semiautomatic Image Segmentation Labeling
Customized backend; GCP Deployment; Data Versioning with GCS Integration- 27524Murphy2025-03-22
Meta Llama 3 Optimized CPU Inference with Hugging Face and PyTorch
Learn how to reduce model latency when deploying Meta* Llama 3 on CPUs- 28562Murphy2025-03-22
Exploring Hierarchical Blending in Target Encoding
When can code hierarchies improve target encoding for high-cardinality categorical features?- 28790Murphy2025-03-22
Introduction to Multi-Stage Image Build for Python
This post introduces the Multi-Stage build approach for setting up a lightweight dockerized Python development environment.- 23550Murphy2025-03-22
Calculating the previous value in Power BI
Calculating the consumption based on meter data looks easy. However, complex situations can be challenging. Let's see how we can solve...- 22410Murphy2025-03-22
Evaluate anything you want | Creating advanced evaluators with LLMs
Discover how to build custom LLM evaluators for specific real-world needs.- 29972Murphy2025-03-22
Genius Cliques: Mapping out the Nobel Network
Combining Network Science, Data Visualization, and Wikipedia to uncover hidden connections between all the Nobel laureates.
Data Science Expertise Comes in Many Shapes and Forms
Our weekly selection of must-read Editors' Picks and original features