In this article, we discuss the latest iteration in the Qwen family of models, Qwen3. We discuss the need for Qwen3, the architecture, and the training strategy. ...

In this article, we are modifying the Web-DINO 300M architecture for semantic segmentation. We will add a simple segmentation decoder head and train the model for person segmentation. ...

In this article we use the Web-DINO model for image classification. We modify the Web-DINO 300M model, adding a classification head on top, freezing the backbone, and training on cotton disease classification task. ...

In this article, we explore the Web-DINO models trained via Web-SSL 2.0 methodology on the MC-2B (MetaCLIP-2B) dataset. ...

In this article, we cover inference code for SmolVLM2. We carry out image and video inference experiments using SmolVLM2-2.2B-Instruct and SmolVLM2-256M-Instruct. ...