Learn how to translate between text to image and back again with CLIP and vector embeddings — After a few short years of life, children can fathom the concepts behind simple words and connect them to related images. They can identify the connection between shapes and textures of the physical world to the abstract symbols of written language. It’s something we take for granted. Very few (if…

Making diffusers models like DALL-E 2 and Imagen more accessible than ever — Hugging Face, the creators of the transformers library, have just released a whole new library for building diffuser models. If you’re not sure what diffuser models are, think of them as the not-so-secret secret behind some of the most talked about AI models this year. Those insanely beautiful, creative, almost…

Easy guide to Hugging Face and Sentence-Transformers on M1 with GPU-acceleration — Prerequisites MacOS 12.4+ Anaconda distribution for M1 (find at bottom of page here) Python Environment We first setup a new Python environment that uses osx-arm64 and install the latest version(s) of PyTorch. Open terminal Create new environment with conda create -n ml python=3.9 anaconda [Alternative]: If using the non-M1 distribution of Anaconda use…

How do the new M1 chips perform with the new PyTorch update? — The release of M1 Macs in November 2020 marked a significant step up in the processing power of Apple machines [1]. Unfortunately, these new features were not integrated into PyTorch until now. Today’s deep learning models owe a great deal of their exponential performance gains to ever increasing model sizes…

Practical resources and advice from a self-taught NLP engineer — Knowing what to learn is one of the hardest parts about self-learning. Imagine being thrown into the wilderness and being told to find a specific landmark. Without a map you will end up wandering to wilderness with no better option than taking one step after another. I spent a long…

How to build *everything* with Streamlit — Streamlit is well-loved as a pure Python solution to building web apps. It makes building dynamic, data-centric apps incredibly easy. And the learning curve is practically non-existent.

Build production-ready NLP apps without the headache — Streamlit has proven itself as an incredibly popular tool for quickly putting together high-quality ML-oriented web apps. More recently, it has seen wider adoption in production environments by ever-larger organizations. All of this means that there is no better time to pick up some experience with Streamlit. Fortunately, the basics…

Why building NLP tokenizers for languages like Dhivehi ދިވެހި is so hard — I’ve been discussing NLP with Ismail Ashraq from the Maldives. A beautiful archipelago in the Indian Ocean with an incredibly stable average low-to-high of 25.2–31.6°C (for those of you stuck in the 18th century, that’s 77.4–88.9°F). Ashraq introduced me to the language of Dhivehi (or Maldivian), which is fascinating. It…

Deploy your API to Google Cloud Platform — Building that first API is for many of us, a significant step towards creating impactful tools that may one day be used by many developers. But often those APIs don’t make it out of our local machines. Fortunately, it’s incredibly easy to deploy APIs. Assuming you have no idea what…