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. ...

In this article, we explore Qwen2.5-Omni, a multimodal generative AI model that can accept text, image, video, and audio as inputs while outputting both text and audio. ...

In this article, we are fine-tuning the SmolVLM-256M model for receipt OCR on the SROIE v2 dataset after generating the ground truth data using QwenVL-2B model. ...

In this article, we explore Gemma 3. We start with the need for Gemma 3, its architecture and multimodal capabilities, and carry out inference using Hugging Face. ...