Are the pre-trained model and pre-training dataset available?

[lanzhuzhu]

Thanks for your open sourcing. It is really good work. According to your paper, the pre-trained model could achieve promising performance on both the few-shot relation extraction task (FewRel1.0) and the supervised relation extraction task (semeval 2010 task 8). I am working on these two datasets recently and met some problems about fine-tuning the pre-trained model. Would you make the pre-trained model or pre-training dataset public? In this way, we could make a better understanding of your approach. Thanks again!