Making Sense of Gradient Boosting in Classification: A Clear Guide
Learn how Gradient Boosting works in classification tasks. This guide breaks down the algorithm, making it more interpretable and less of a black box.
Deploy llm-d for Distributed LLM Inference on Kubernetes (DOKS)
Learn how to deploy llm-d on Kubernetes (DOKS) for distributed LLM inference with GPU support. This tutorial covers automated cluster setup, llm-d deployment, and basic testing to get you started with production-ready distributed LLM services.
Deep Learning for Image Dehazing- The What, Why, and How
In this tutorial, we discuss the history of image dehazing, show how to set an image dehazing task up in a notebook, and then examine 7 different techniques for performing image dehazing with deep learning!
Intro to optimization in deep learning: Gradient Descent
An in-depth explanation of Gradient Descent and how to avoid the problems of local minima and saddle points.
Designing Hardware-Aware Algorithms with Kimi Linear: Kimi Delta Attention
Moonshot AI’s Kimi Linear introduces Kimi Delta Attention (KDA), a hardware-aware algorithm. Learn how to run Kimi Linear on the cloud provider.
Getting Started with LLMs for Social Media Analytics with 1-Click Models
This article explains how LLMs can be used for analyzing social media data with prompt engineering and includes a tutorial on setting up a gradio interface for 1-Click Models powered by HuggingFace and run on the cloud provider’s GPU Droplets
Evaluating Object Detection Models Using Mean Average Precision (mAP)
URL: https://www.progressiverobot.com/mean-average-precision/ To evaluate object detection models like R-CNN and YOLO, the mean average precision (mAP) is used. The mAP compares the ground-truth bounding box to the detected box and returns a score. The higher the score, the more accurate the model is in its detections. In my last article we looked in detail at […]
Multi-GPU on raw PyTorch with Hugging Face’s Accelerate library
In this article, we examine HuggingFace’s Accelerate library for multi-GPU deep learning. We apply Accelerate with PyTorch and show how it can be used to simplify transforming raw PyTorch into code that can be run on a distributed machine system.
olmOCR and RolmOCR: The Latest in Open-Source OCR
‘ The article provides an overview and implementation details of olmOCR and RolmOCR, two open-source Optical Character Recognition (OCR) models developed for efficient and scalable document conversion.’
Deep Learning Architectures Explained: ResNet, InceptionV3, SqueezeNet
Understand the basics of ResNet, InceptionV3, and SqueezeNet architecture and how they power deep learning models. Learn their architectures, key features, and how they improve accuracy and efficiency.
