ImportError:无法从“变形金刚”中导入名称“ AutoModelWithLMHead”

时间:2020-07-28 19:14:25

标签: python pytorch huggingface-transformers

这实际上是我要运行的所有代码:

from transformers import AutoModelWithLMHead, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")
model = AutoModelWithLMHead.from_pretrained("microsoft/DialoGPT-small")

我收到此错误:

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-14-aad2e7a08a74> in <module>
----> 1 from transformers import AutoModelWithLMHead, AutoTokenizer
      2 import torch
      3 
      4 tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")
      5 model = AutoModelWithLMHead.from_pretrained("microsoft/DialoGPT-small")

ImportError: cannot import name 'AutoModelWithLMHead' from 'transformers' (c:\python38\lib\site-packages\transformers\__init__.py)

我该怎么办?

1 个答案:

答案 0 :(得分:0)

我解决了!在我的版本中,显然删除了AutoModelWithLMHead。

现在,您需要将AutoModelForCausalLM用于因果语言模型,将AutoModelForMaskedLM用于屏蔽语言模型,将AutoModelForSeq2SeqLM用于编码器/解码器模型。

所以在我的情况下,代码如下所示:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")