In this article, we are deploying the NVIDIA Nemotron 3 Nano Omni model on the Modal Serverless L40S GPU for text, image, and video understanding chat. ...

In this article, we cover an introduction to the latest NVIDIA Nemotron 3 Nano Omni model and create a simple chat application using the NVIDIA API. ...

In this article, we fine-tune the PaliGemma 2 model for object detection. We specifically tune the model for wheat head detection. ...

In this article, we are fine-tuning Gemma 4 for text on a reasoning dataset whose responses have been collected from DeepSeek-V4 Flash model. ...

In this article, we are fine-tuning the Gemma 4 E2B model for vision use cases. We use the VQA RAD dataset to teach the model to learn to answer questions about radiology images. ...