找了个hf的镜像站,把config.json和pytorch_model.bin两个文件进行下载下来,模型文件uncased_L-12_H-768_A-12.zip下载下来先。
解压模型文件压缩包,把前面下载的两个文件也放进去,总共6个文件。这个文件夹就是代码
tokenizer = BertTokenizer.from_pretrained(BERT_PATH)
BERT_PATH这里对应的文件路径。
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']
pip install tensorflow
from transformers import BertModel, BertTokenizer
model_name = 'bert-base-uncased'
tokenizer = BertTokenizer.from_pretrained(model_name)
model = BertModel.from_pretrained(model_name, from_tf=True)