Articles for category: AI Tools

March 30, 2025

ikayaniaamirshahzad@gmail.com

Deploy LLMs with Hugging Face Inference Endpoints

Open-source LLMs like Falcon, (Open-)LLaMA, X-Gen, StarCoder or RedPajama, have come a long way in recent months and can compete with closed-source models like ChatGPT or GPT4 for certain use cases. However, deploying these models in an efficient and optimized way still presents a challenge. In this blog post, we will show you how to deploy open-source LLMs to Hugging Face Inference Endpoints, our managed SaaS solution that makes it easy to deploy models. Additionally, we will teach you how to stream responses and test the performance of our endpoints. So let’s get started! How to deploy Falcon 40B instruct

March 30, 2025

ikayaniaamirshahzad@gmail.com

We struggled at $1k MRR for a year… then hit $1k MRR in 2 weeks (and here’s why)

Hey Dev Community 👋 Wanted to share a transparent story about our SaaS journey—because I know many developers here are building side projects, and this might resonate. 🛠️ The backstory In February 2024, we launched LanderMagic while still working our full-time jobs.At first, it was a tool to dynamically personalize your own landing pages (on Webflow, WordPress, etc.).You could tweak headlines, CTAs, and content automatically based on UTM parameters, ad keywords, or geolocation. It was useful… but, to be honest, it was a “Nice to have.” For a whole year, we grinded and struggled around $1k MRR.No real growth. Just

March 30, 2025

ikayaniaamirshahzad@gmail.com

Changelog · Prodigy · An annotation tool for AI, Machine Learning & NLP

Select page…Get Started › Prodigy 101Get Started › Installation & SetupGet Started › ChangelogUsage › Named Entity RecognitionUsage › Span CategorizationUsage › Text ClassificationUsage › Dependencies & RelationsUsage › Computer VisionUsage › Audio & VideoUsage › Task RoutingUsage › Large Language ModelsUsage › ReviewUsage › Custom RecipesUsage › Custom InterfacesUsage › MetricsUsage › DeploymentAPI › RecipesAPI › Annotation InterfacesAPI › Web ApplicationAPI › Loaders & Input DataAPI › Components & FunctionsAPI › DatabasePlugins › Open Source PluginsPlugins › Single Sign-onPlugins › Modal This page lists the history of changes to Prodigy. Whenever a new update is available, you’ll receive an

March 30, 2025

ikayaniaamirshahzad@gmail.com

Making ML-powered web games with Transformers.js

In this blog post, I’ll show you how I made Doodle Dash, a real-time ML-powered web game that runs completely in your browser (thanks to Transformers.js). The goal of this tutorial is to show you how easy it is to make your own ML-powered web game… just in time for the upcoming Open Source AI Game Jam (7-9 July 2023). Join the game jam if you haven’t already! Video: Doodle Dash demo video Quick links Overview Before we start, let’s talk about what we’ll be creating. The game is inspired by Google’s Quick, Draw! game, where you’re given a word

March 30, 2025

ikayaniaamirshahzad@gmail.com

Converting arbitrarily large CSVs to Parquet with R

In this recent post, we have used Polars and DuckDB to convert a large CSV file to Parquet in steaming mode – and Python. Different people have contacted me and asked: “and in R?” Simple answer: We have DuckDB, and we have different Polars bindings. Here, we are using {polars} which is currently being overhauled into {neopandas}. So let’s not wait any longer! Run times are on a Windows system with an Intel i7-13700H CPU. Generate 2.2 GB csv file We use {data.table} to dump a randomly generated dataset with 100 Mio rows into a csv file. library(data.table) set.seed(1) n

March 30, 2025

ikayaniaamirshahzad@gmail.com

Comprehensive Guide to Building a CI/CD Pipeline in AWS with GitHub

Introduction CI/CD (Continuous Integration/Continuous Delivery) pipelines are foundational to modern software development, enabling teams to automate building, testing, and deploying code. Benefits include: Faster Delivery: Automate repetitive tasks to release updates rapidly. Improved Quality: Catch bugs early with automated testing. Reduced Errors: Minimize manual intervention in deployments. Scalability: Easily adapt pipelines to handle growing workloads. Step 1: Prepare Sample Code Create a Simple Web Application Step 2 Push Code to GitHub Create a new repository on GitHub. Commit and push your code: git init git add README.md git commit -m "first commit" git branch -M main git remote add origin

March 30, 2025

ikayaniaamirshahzad@gmail.com

Fine-tuning Stable Diffusion models on Intel CPUs

Diffusion models helped popularize generative AI thanks to their uncanny ability to generate photorealistic images from text prompts. These models have now found their way into enterprise use cases like synthetic data generation or content creation. The Hugging Face hub includes over 5,000 pre-trained text-to-image models. Combining them with the Diffusers library, it’s never been easier to start experimenting and building image generation workflows. Like Transformer models, you can fine-tune Diffusion models to help them generate content that matches your business needs. Initially, fine-tuning was only possible on GPU infrastructure, but things are changing! A few months ago, Intel launched

March 30, 2025

ikayaniaamirshahzad@gmail.com

Terraform for DevOps: Managing State & Remote Backends (Part 3)

Hey DevOps friends! 🚀 Welcome back to our Terraform tutorial series. In our previous posts, we explored the power of Infrastructure as Code and got hands-on with setting up and deploying Terraform. Now, in Part 3, we’re diving deep into Terraform Backends & State Management. We’ll explore everything from local backends to remote setups, and learn how to securely manage and collaborate on your infrastructure’s state. Ready to unlock the secrets behind robust state management? Let’s dive in! 1. Backends Backends in Terraform dictate where your state file—the beating heart of your deployed infrastructure—lives. Picking the right backend isn’t just