Reading Time: 21 minutesTL;DR: A vibe coded Next.js 15 app (https://visualneurons.com/) that lets you create images, edit them with precision masks, and generate… Read More »Building Visual Neurons: image + video generation with Next.js, Replicate, and Amazon Bedrock

Reading Time: 15 minutes👉 Useful links: Youtube lecture, minbpe GitHub repo, Colab notebook What is a tokenizer and why do we need one… Read More »Byte Pair Encoding: building the GPT tokenizer with Karpathy

Reading Time: 18 minutesIntroduction In this post, I go through the content covered by Jeremy Howard in his lecture CUDA for Python programmers.… Read More »CUDA for Python Programmers

Reading Time: 9 minutesContext In this post, Lucas and I describe the end2end cloud solution we built to deploy LogoNet. That’s the name… Read More »LogoNet: the journey to an AWS-powered cloud application running ControlNet on SageMaker async endpoints

Reading Time: 5 minutesUseful links The what and the why If you haven’t yet watched Karpathy’s lecture “Let’s build GPT: from scratch, in… Read More »A visual deep dive into the Transformer’s architecture: turning Karpathy’s masterclass into pictures

Reading Time: 9 minutesContext In October 2022 I started attending the new version of part 2 of the fastai course. In this one,… Read More »Fastai Course Part 2 2022: Understanding CallBacks

Reading Time: 6 minutesNote: you can follow along with the post in this Jupyter notebook Context The ML announcement I liked the most… Read More »Amazon SageMaker Shadow Deployment: Semantic Segmentation from the HuggingFace Hub

Reading Time: 9 minutesDisclaimers TLDR All scenarios running on NVIDIA GPU: Context This post is a continuation of the experiments I conducted and… Read More »Benchmarking TorchVision ResNet18 on EC2 NVIDIA GPU with TensorRT and Amazon SageMaker Neo

Reading Time: 8 minutesCode and disclaimer: you can find the notebook with the relevant code here. Most of it was copied from the… Read More »Benchmarking TorchVision ResNet18 on Amazon SageMaker CPU, GPU, and Inferentia instances (with a Neo twist)

Reading Time: 9 minutesNote: You can find the Jupyter notebook with all the steps I followed here, and the folder with the relevant… Read More »Neural Magic: Training YoloV5 with Sparse Transfer Learning and deploying to Amazon SageMaker with a custom Docker container