Hugging Face Text Classification

Overview

This app contains great models and workflows built by Hugging Face that you can use in your apps to carry out text classification. You can use the models to assign one or more predefined categories or classes to open-ended text and process them accordingly.

Feel free to explore all the different models! Here are the workflow highlights the app contains:

• Insecure Code Detection
• Natural Language Inference

Insecure Code Detection

Use this model to identify whether a text is insecure code that may attack software systems. It can help you detect whether a source code contains vulnerabilites that may cause various types of attacks, such as resource leaks, use-after-free vulnerabilities, and DoS attack.

The model returns a binary classification (0/1) result, where 1 stands for insecure code and 0 for secure code.

Natural Language Inference

Use this model to make inferences from the provided English text. Essentially, the model takes a premise and a hypothesis and outputs three classes of scores that can be:

• entailment—meaning the hypothesis is true
• contraction—meaning the hypothesis is false
• neutral—meaning there's no relation between the hypothesis and the premise