Using & Mixing Hugging Face Models with Gradio 2.0

Back to Articles Using & Mixing Hugging Face Models with Gradio 2.0 Published May 25, 2021 Update on GitHub Upvote 3 Abubakar Abid abidlabs Follow Cross-posted from the Gradio blog. The Hugging Face Model Hub has more than 10,000 machine learning models submitted by users. You’ll find all kinds of natural language processing models that, for example, translate between Finnish and English or recognize Chinese speech. More recently, the Hub has expanded to even include models for image classification and audio processing. Hugging Face has always worked to make models accessible and easy to use. The transformers library makes it possible to load a model in a few lines of code. After a model is loaded, it can be used to make predictions on new data programmatically. But it’s not just programmers that are using machine learning models! An increasingly common scenario in machine learning is demoing models to interdisciplinary teams or letting non-programmers use models (to help discover biases, failure points, etc.). The Gradio library lets machine learning developers create demos and GUIs from machine learning models very easily, and share them for free with your collaborators as easily as sharing a Google docs link. Now, we’re excited to share that the Gradio 2.0 library lets you load and use almost any Hugging Face model with a GUI in just 1 line of code. Here’s an example: By default, this uses HuggingFace’s hosted Inference API (you can supply your own API key or use the pu...