aychang/bert-large-cased-whole-word-masking-finetuned-squad

A serialized torchscript model of bert-large-cased-whole-word-masking-finetuned-squad is serialized with a config.pbtxt for deployment using NVIDIA Triton Inference Server . The model is used to deploy a large-scale version of the Bert-Large-Cased-Whole-Word-Masked-Squad . The Bert Large-Cases Squad has been deployed to a large number of times in the past . The TorchScript model is a serialized version of a text-based version of this article. The Torch Script is based on the BERT-Large Cased-Wide-,