jiangix

Yeah, Thank for your reply.

Thanks for your reply. I don't have a good knowledge of tensorflow. And I want to know how does the model run out of the memory of gpu. In fact...

Very thanks for your reply. I do not turn on the coverage loss. However, according to the figure 2 in the readme, the result without coverage loss is also high....

> 我用这行命令 > python pytorch_transformers/convert_xlnet_checkpoint_to_pytorch.py --tf_checkpoint_path XLNet_zh_Large_L-24_H-1024_A-16/xlnet_model.ckpt --xlnet_config_file XLNet_zh_Large_L-24_H-1024_A-16/xlnet_config.json --pytorch_dump_folder_path XLNet_zh_Large_L-24_H-1024_A-16 > 而且，把xlnet_model.ckpt改名为xlnet_model.ckpt.data-00000-of-00001，就可以顺利转换了 谢谢谢谢，我这边还是会报错，看了一下可能是pytorch_transformers已经更新了，所以这条命令会报错，如果您方便的话可以麻烦将您用于转化的pytorch_transformers文件夹发给我一下吗？真的非常感谢~我的邮箱是[email protected]

Hi，Sorry for bothering you. Can you run the code without error? I have an error "Don't know how to create ISeq from: clojure.lang.Keyword". How can i deal with it. Thanks...