Question and Answering Collection

Overview

This page contains the information about the Question and Answering collection with TLT.

The models in this collection can be used to find answer spans for questions inside of a given text. They are trained on generic datasets like Squad and can be used with proprietary user content.

Available Models

For instructions on how to use a model, please see its corresponding model card page:

• Question Answering Bert Base
• Question Answering Bert Large
• Question Answering Megatron

License

License to use these models is covered by the Model EULA. By downloading the model checkpoints, you accept the terms and conditions of these licenses.

Suggested Reading

• More information about the Transfer Learning Toolkit can be found at the NVIDIA Developer Zone: https://developer.nvidia.com/transfer-learning-toolkit
• Read the TLT getting Started guide and release notes.
• More information about the experiment spec files can be found in the TLT User Guide

Ethical AI

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.