从 Hugging Face 模型加载权重时出错

Question

我正在使用变压器，我已经加载了一个模型，它工作正常：

from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer

task='sentiment'
MODEL = "cardiffnlp/twitter-roberta-base-{task}"
tokenizer = AutoTokenizer.from_pretrained(MODEL)

# PT
model = AutoModelForSequenceClassification.from_pretrained(MODEL) 
model.save_pretrained(MODEL)

但如果我尝试加载另一个任务，如“情感”或“仇恨”，我会收到以下错误：

from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer

task='emotion'
MODEL = "cardiffnlp/twitter-roberta-base-{task}"
tokenizer = AutoTokenizer.from_pretrained(MODEL)

# PT
model = AutoModelForSequenceClassification.from_pretrained(MODEL)  ## Here I get the error
model.save_pretrained(MODEL)

这个错误：

OSError: Can't load weights for 'cardiffnlp/twitter-roberta-base-emotion'. Make sure that:

- 'cardiffnlp/twitter-roberta-base-emotion' is a correct model identifier listed on 'https://huggingface.co/models'

- or 'cardiffnlp/twitter-roberta-base-emotion' is the correct path to a directory containing a file named one of pytorch_model.bin, tf_model.h5, model.ckpt.

我已经检查过了，这些模型实际上是 Hugging Face 模型，你可以看到 here，所以我不明白为什么不工作。

编辑：我注意到我第一次运行它时，它适用于所有任务（仇恨、情感、情绪），但如果我再次尝试运行它，则会出现错误。

Answer 1

# PT
model = AutoModelForSequenceClassification.from_pretrained(MODEL) 
model.save_pretrained(MODEL)
tokenizer.save_pretrained(MODEL)

将第三行添加到此部分，重命名或删除您已有的模型文件夹，然后重试。这一次它确实应该不止一次地工作。我希望这能让你继续前进！