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: Using Hugging Face Agents (Your Personal AI Assistant)
This is the cutting-edge of AI, far beyond a simple pipeline. An Agent is an LLM (like ChatGPT) that has been given tools and can…
AI Project: Zero-Shot Classification with Hugging Face
This is one of the most powerful and “magical” tasks in modern AI. In particular, Hugging Face Zero-Shot is a technique that demonstrates impressive versatility…
AI Project: Multi-Label Text Classification with Hugging Face
We’ve done single-label classification (e.g., “POSITIVE” or “NEGATIVE”). But what if a text can be both? A news article could be about “POLITICS” and “FINANCE”….
AI Project: Build an Image Classifier with Hugging Face (Vision)
We’ve used Hugging Face to understand text and generate text. Now, let’s use it to understand images with Hugging Face Image Classification. Image Classification is…
AI Project: Text Classification with Hugging Face (The Manual Way)
The Hugging Face pipeline is great for simple tasks, and it’s particularly well-known for Hugging Face Text Classification. But what if you need the raw…
AI Project: Text Generation with gpt-2 (Hugging Face)
We’ve used the Hugging Face pipeline to understand text (sentiment-analysis) and answer questions (question-answering). Now, let’s use it for its most famous task: Text Generation….
AI Project: Build a Question-Answering Bot with Hugging Face
We’ve used the Hugging Face pipeline to understand emotion and summarize text. Now, let’s use it to find answers. “Question-Answering” models are trained to read…
AI Project: Build a Text Summarizer with Hugging Face
In our last AI project, we taught Python how to understand emotion. Now, let’s teach it how to read and summarize a long article for…
Beyond the Pipeline: Loading Hugging Face Models and Tokenizers
The pipeline() function in our Hugging Face intro is amazing, but it’s a black box. To do advanced work (like fine-tuning or getting raw data),…
