Solaris
Solaris
> 上面这个版本问题解决了，但是遇到了新的问题，请问我在预处理之后获得的mergerd_data为啥为空呢，我也没有找到对应的vocab.bpe.600；以至于预处理的数据不对，调用fairseq generate导致后面字典和数据维度对不上 vocab.bpe可能是在README中dataset小节中下载的，可是现在链接用不了
Check the newest version of transformers document and you can easily solve the problem [https://huggingface.co/transformers/serialization.html#from-pretrained-method](url) and if you want to use other embeddings, you may use a package called genism...
You could try to adapt ```cache_dir``` and ```wordVecPath``` in ```LSBert1.py```