huggingface | how to get the params‘ number of a model

Posted CSU迦叶

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了huggingface | how to get the params‘ number of a model相关的知识,希望对你有一定的参考价值。

主要实现在下列的how_big(model)函数中

# 探究plbart和codegpt的参数量
from transformers import PLBartModel,GPT2Model


def how_big(model):
    total_num = sum(p.numel() for p in model.parameters())
    trainable_num = sum(p.numel() for p in model.parameters() if p.requires_grad)
    print("Total: ,Trainable: ".format(total_num,trainable_num))


def main():
    bart = PLBartModel.from_pretrained("uclanlp/plbart-java-cs")
    how_big(bart)
    codegpt = GPT2Model.from_pretrained("pytorch.bin所在的文件夹路径")
    how_big(codegpt)

if __name__ == "__main__":
    main()

输出结果为

Total: 139220736,Trainable: 139220736
Total: 124442112,Trainable: 124442112

以上是关于huggingface | how to get the params‘ number of a model的主要内容,如果未能解决你的问题,请参考以下文章

How to get service execuable path

How to get date from OAMessageDateFieldBean

how-to-get-a-job-in-deep-learning

csuoj-1720-How to Get 2^n

How to GET a Cup of Coffee

[特征选择] DIscover Feature Engineering, How to Engineer Features and How to Get Good at It 翻译