AI Project: Fill-in-the-Blank with Hugging Face (BERT)
This is one of the original tasks that made models like BERT famous. A “Masked Language Model” (MLM) is trained by having words randomly “masked”…
AI Project: How to Edit Images with AI (Inpainting with diffusers)
We’ve used Stable Diffusion to create images. Now, let’s use it to edit them. In this guide, we’ll explore Hugging Face Inpainting and how it…
AI Project: Image Segmentation with Hugging Face
This is the next level of Computer Vision. Hugging Face Image Segmentation is an innovative approach transforming what computers see and understand. This is how…
AI Project: Quantization for Faster Models (Hugging Face optimum)
You’ve built amazing AI models, but they’re huge and slow. A model like gpt-2 can be 500MB+ and slow to run on a CPU. Hugging…
AI Project: Image Generation with Stable Diffusion (Hugging Face)
This is the project you’ve been waiting for. We’re going to write a Python script that generates a unique image from a text prompt (e.g.,…
AI Project: Create Text Embeddings with Hugging Face (Sentence Transformers)
This is one of the most powerful concepts in modern AI. In particular, Hugging Face Text Embeddings are an innovative way to use embeddings today….
AI Project: Build a Web App for Your Hugging Face Model (with Gradio)
You’ve built amazing AI models, but how do you let your friends or colleagues use them without running your script? One solution is to share…
High-Performance NLP: Pre-processing Text with Polars (2026 Guide)
When preparing text data for an AI model, you’re often working with millions of rows. For this reason, many practitioners are interested in Polars NLP…
AI Project: Fine-Tuning a Hugging Face Model (Part 3: Evaluation & Sharing)
This is the final part of our fine-tuning series. In this article, we’ll explore Hugging Face Evaluate and Share to wrap up our journey. Now,…
AI Project: Fine-Tuning a Hugging Face Model (Part 2: The Trainer)
Welcome to Part 2! In Part 1 (The Data), we loaded the “imdb” dataset and prepared it with a tokenizer. Now, we’ll do the exciting…
