Published March 31, 2020 | Version v1
Other Open

MLPerf Inference BERT Tensorflow Model on SQuAD v1.1 dataset

  • 1. NVIDIA

Description

BERT TensorFlow model trained on SQuAD v1.1 for MLPerf Inference. To re-create the model, train on SQuAD v1.1 dataset according to the instructions here: https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/BERT

Files

vocab.txt

Files (4.0 GB)

Name Size Download all
md5:3089b27c559906a868878741d992ade7
4.0 GB Download
md5:d23d61572d9404da4dac3363b5bc735b
44.4 kB Download
md5:83e11e57eea14c9e9a246af74af40d66
10.6 MB Download
md5:64800d5d8528ce344256daf115d4965e
231.5 kB Preview Download