Visualizing Vision-Language Models
A concise deep dive into how Vision-Language Models combine images and text through multimodal reasoning and visualization techniques.
LeNet-5 from Scratch with PyTorch A Beginner’s Guide
A complete walkthrough to build LeNet-5 from scratch using PyTorch. Perfect for beginners exploring deep learning and CNNs.
Next Generation AI Development with the AMD MI300X
In this tutorial, we discuss the effectiveness of AMD GPUs for Deep Learning tasks. In particular, we focus on the powerful MI300X, now available for the cloud provider’s GPU Droplets, examine the specs of these potent machines in depth.
Run BAGEL VLM on a DigtialOcean GPU Droplet
In this Jupyter Notebook based tutorial, we show how to run the incredible new BAGEL Vision Language Model to generate, edit, and describe images on a GPU cloud servers.
A Simple Guide to Building AI Agents Correctly
Learn how to design and build reliable AI agents with the right architecture, tools, memory, and evaluation strategies for real-world applications.
Claude 4 – the latest and greatest LLM family from Anthropic
In this tutorial, we do a deep dive on the impressive, new Imagen 4 model. Afterwards, we compare and contrast the capabilities of Imagen 4 with open-source and commercial competitors.
OpenAI Gym: Creating Custom Gym Environments
This guide walks you through creating a custom environment in OpenAI Gym. As an example, we design an environment where a Chopper (helicopter) navigates through the air while avoiding obstacles.
DeepSeek-OCR: Reducing Token Counts with Optical Context Compression
DeepSeek-OCR uses optical context compression to cut token counts, enabling efficient, open-source vision-language document processing.
Stable Diffusion Tutorial Part 2: Using Textual Inversion Embeddings to gain substantial control over your generated images
Learn how to train textual inversion for Stable Diffusion in a Jupyter Notebook and generate samples that represent the features of the training images.
Fara7B Shows Power of Synthetic Data Scaling for Computer Use Agents
‘New Computer Use Agent Model, Fara7B showcases the effectiveness of scaling data with synthetic data generation engine FaraGen.’
