Pytorch_pretrained_model

[zysNLP]

when I exectute

python run_bert_triple_classifier.py --task_name kg --do_train
--do_eval --do_predict --data_dir ./data/WN11 --bert_model bert-base-uncased --max_seq_length 20 --train_batch_size 32 --learning_rate 5e-5 --num_train_epochs 3.0 --output_dir ./output_WN11/
--gradient_accumulation_steps 1 --eval_batch_size 512

it turned out that a pytorch_pretrained_file is downloading. I found it too slow to download. so I copy: https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased.tar.gz to download alone.

[zysNLP]

I want to ask where should I put this "bert-base-uncased.tar.gz"? Thank you!

[yao8839836]

@zysNLP

In Linux or Mac OS, the temporary vocab file is under "/Users/myname/.pytorch_pretrained_bert/" and the model file is under "/Users/myname/.pytorch_pretrainedbert/distributed-1/" (no distributed training). I didn't try Windows, but it should be under some similar user folders.

[zysNLP]

@yao8839836 您好，我没有在linux下找到这个文件路径，/Users/看起来更像是windows下的那个文件夹，linux的文件好像不能以"."开头。。

[yao8839836]

@zysNLP

您好，我是在我的MAC下找的，您可以看下pytorch-pretrained-bert这个库的源码，我是直接安装然后调用的，下载模型的代码应该可以定位到。

[zysNLP]

@yao8839836 好的，多谢！