In this article we are fine-tuning the Phi-3.5 Vision Instruct model on a receipt OCR dataset. We are using Hugging Face libraries and training a LoRA. ...

In this article, we explore the DEIMv2 object detection model based on the DINOv3 and HGNetv2 backbones, along with carrying inference on images and videos. ...

In this article, we cover Moondream3, the latest iteration in Moondream VLM family. We cover the model architecture and carry out inference using the different tasks that it supports. ...

In this article, we modify the DINOv3 backbone with RetinaNet head for object detection. We train the model on the Pascal VOC dataset and carry out inference. ...

In this article, we modify the DINOv3 model for object detection and train in on the Pascal VOC detection dataset. We discuss the model creation, training, and inference in detail. ...