Using & Mixing Hugging Face Models with Gradio 2.0

Summary

The Hugging Face Model Hub hosts more than 10,000 user-submitted machine learning models spanning natural language processing, image classification, and audio processing. Machine learning developers increasingly need to demo models to interdisciplinary collaborators or non-programmers to uncover biases and failure points. The Gradio 2.0 library enables users to create graphical user interfaces and load almost any Hugging Face model using a single line of code. By default, these interfaces query Hugging Face's hosted Inference API without requiring an API key, though users can also run computations locally via the transformers library. Gradio interfaces can be customized through the Interface class and composed to load multiple models in parallel or chain them in series.

Takeaways

1. 1

   Gradio 2.0 allows loading almost any model from the Hugging Face Model Hub into a shareable GUI with a single line of code.

2. 2

   Inference runs by default through Hugging Face's hosted Inference API without requiring an API key, or locally by installing the transformers library.

3. 3

   Developers can compose models within Gradio by executing them in parallel for side-by-side comparison or chaining them in series for multi-step tasks.