In this article, we cover an introduction to Qwen3.5 by going through the important aspects of the official article along with image and video inference using vLLM and llama.cpp. ...

In this article, we get started with Molmo2. We start with the discussion of the important aspects from the technical article and report. Then we move to a simple inference pipeline for image VQA, vidoe VQA, and image pointing. ...

In this article, we cover the GLM-4.6V model. Specifically, we cover the technical capabilities of the model along with inference for image description, OCR, and image to HTML code. ...

In this article, we fine-tune the DeepSeek-OCR 2 model using Unsloth for Hindi language OCR. We create a simple Gradio application to run inference and check the diff between the original and the inference result. ...

In this article, we discuss the DeepSeek-OCR 2 paper. We start from the DeepEncoder V2, the architecture, and finally discuss the code from Hugging Face. ...