1. 背景

使用 超算互聯網 的云服務，不能連接外網，只能把模型下載到本地，再上傳上去到云服務。

2. 模型下載

在 模型中 https://huggingface.co/models 找到所需的模型后

點擊下載 config.json pytorch_model.bin vocab.txt

3. 上傳模型文件

打開文件管理 e-file
點擊 上傳，選擇 本地上傳

4. 運行代碼

由原來的代碼：

from transformers import BertTokenizer, BertForSequenceClassificationmodel = BertForSequenceClassification.from_pretrained('bert-base-chinese', num_labels=2)
tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')

改成這樣的：

from transformers import BertTokenizer, BertForSequenceClassificationpath_to_local_model_directory="/public/home/acc5trotmy/jupyter/models/bert-base-chinese"model = BertForSequenceClassification.from_pretrained(path_to_local_model_directory, num_labels=2)
tokenizer = BertTokenizer.from_pretrained(path_to_local_model_directory)

或者：

from transformers import BertTokenizer, BertForSequenceClassification, BertConfigconfig = BertConfig.from_pretrained(path_to_local_model_directory)
model = BertForSequenceClassification.from_pretrained(path_to_local_model_directory, config=config)
tokenizer = BertTokenizer.from_pretrained(path_to_local_model_directory)