以t5-base为例：
储存模型：
from transformers import AutoModelForSeq2SeqLM
if __name__ == '__main__':
model_name = 't5-base'
prefix = 'your_path'
save_path = prefix+model_name
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
model.save_pretrained(save_path)
加载模型：
model = AutoModelForSeq2SeqLM.from_pretrained(save_path)
标签：__,name,本地化,huggingface,AutoModelForSeq2SeqLM,path,model,save From： https://www.cnblogs.com/huangshiyu13/p/17177037.html