Bert Large Uncased Whole Word Masking Squad Int8 0001

🚀 OpenVINO model bert-large-uncased-whole-word-masking-squad-int8-0001

This is a pre - trained BERT - large model for English question - answering tasks. It uses Whole - Word - Masking and is fine - tuned on SQuAD v1.1. The model has been quantized to INT8 precision.

🚀 Quick Start

This is a BERT - large model pre - trained on lower - cased English text using Whole - Word - Masking and fine - tuned on the SQuAD v1.1 training set. The model is designed for English question - answering. It takes a concatenated premise and a question about the premise as input, and outputs the location of the answer to the question within the premise.

For details about the original floating - point model, check out BERT: Pre - training of Deep Bidirectional Transformers for Language Understanding.

The model has been further quantized to INT8 precision using quantization - aware fine - tuning with NNCF.

📚 Documentation

Model Source

The model source can be found at Open Model Zoo.