Vision Language Models: Building VLMs with Hugging Face

It doesn’t happen every day that a friend of yours publishes a book (at least not to me!)¹. I’m so happy to have my signed copy of Vision Language Models: Building VLMs with Hugging Face, co-written by Miquel Farré together with Merve Noyan and Andrés Marafioti.

The book is a hands-on guide to models that understand both images and text, built around the Hugging Face ecosystem. It goes from the basics, like image captioning and document understanding, all the way to zero-shot inference and retrieval-augmented generation (RAG) over visual content.

I happened to work with Miquel back at YouTube in Zurich.

• Books
• Hugging Face