microsoft/prophetnet-large-uncased-squad-qg

ProphetNet is a new pre-trained language model for sequence-to-sequence learning with a novel self-supervised objective called future n-gram prediction . ProphetNet is able to predict more future tokens with a n-stream decoder . The original implementation is Fairseq version at GitHub repo . Fine-tuned weights(converted from original fairseq version repo) for ProphetNet on question generation                SQuAD 1.1.1: Fine-tensors, weights, and n-Stream decoder. Proving it's possible to predict tokens more with a pre-training model . Proving that the model can predict future tokens more easily with n-,