Distilbert Base Uncased Agnews Student

🚀 distilbert-base-uncased-agnews-student

This model is distilled from a zero - shot classification pipeline on the AG's News dataset, serving as a demo of distilling an NLI - based zero - shot model to a more efficient student.

🚀 Quick Start

This model can be used in the same way as other models trained on AG's News. You can refer to the general usage methods of text - classification models in Hugging Face's ecosystem.

✨ Features

• Distilled from the zero - shot classification pipeline on the unlabeled AG's News dataset.
• Demonstrates how to distill an expensive NLI - based zero - shot model to a more efficient student.

📚 Documentation

Model Description

This model is distilled from the zero - shot classification pipeline on the unlabeled AG's News dataset using [this script](https://github.com/huggingface/transformers/tree/master/examples/research_projects/zero - shot - distillation). It is the result of the demo notebook here, where more details about the model can be found.

• Teacher model: [roberta - large - mnli](https://huggingface.co/roberta - large - mnli)
• Teacher hypothesis template: "This text is about {}."

Intended Usage

The model can be used like any other model trained on AG's News, but will likely not perform as well as a model trained with full supervision. It is primarily intended as a demo of how an expensive NLI - based zero - shot model can be distilled to a more efficient student.

📄 License

This model is released under the MIT license.

Information Table

Widget Examples

The following are some example texts for the widget:

• "Armed conflict has been a near - constant policial and economic burden."
• "Tom Brady won his seventh Super Bowl last night."
• "Dow falls more than 100 points after disappointing jobs data"
• "A new moon has been discovered in Jupter's orbit."