Category: Transformer

In this article, we cover the architecture of ViTPose and ViTPose++ and run inference on images & videos using ViTPose. ...

In this article, we walk through the Molmo and PixMo technical reports and carry out Molmo image description and pointing demos using the Hugging Face checkpoints. ...

In this article, we create a custom Phi-3 Gradio chat interface with the ability to upload and query files.s ...

In this article, we discuss Phi 1.5 which is a 1.3 billion parameters language model from Microsoft. ...

In this article, we create an instruction following Jupyter Notebook interface to prompt a fine-tuned Phi 1.5 model. ...