ERNIE-text-classification-pytorch

ERNIE-text-classification-pytorch copied to clipboard

I am so disappointed

DaveZLB

全球每分钟砍伐森林面积相当于36个足球场中新网10月25日电据新加坡 3 全球每分钟砍伐森林面积相当于36个足球场中新网10月25日电据新加坡 2 全球每分钟砍伐森林面积相当于36个足球场中新网10月25日电据新加坡 1 是这样的格式吗？

stubbornwdb

RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got CUDAType instead (while checking arguments for embedding)

2

运行python fine_tune_ernie.py.py出错： RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got CUDAType instead (while checking arguments for embedding)

ghost

请问fine-tuning数据集是没有上传吗？

17

大佬，哪里可以找的你fine-tuning时候的数据集？

Duanexiao

bert_config.json里的vocb_size和vocab.txt里的词汇不一致

1

您好，在转成pytorch后的模型文件中，bert_config.json里的vocb_size为18000，但是vocab.txt里只有17964个词汇，解码时生成的17964之后的id没法对应到词表，请问这个差异怎么处理？

linjianz

you may miss something the model needed

1

when i download the ernie_base from panbaidu,and run fine_tune_ernie.py , it raise error as follows: File "/Users/yuanjun/Downloads/ERNIE-text-classification-pytorch-master/fine_tune_ernie.py", line 8, in from pyernie.io.dataset import CreateDataset File "/Users/yuanjun/Downloads/ERNIE-text-classification-pytorch-master/pyernie/io/dataset.py", line 5, in from...

yuanjun1991

# Patching CVE-2007-4559 Hi, we are security researchers from the Advanced Research Center at [Trellix](https://www.trellix.com). We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a...

TrellixVulnTeam