在 Huggingface 变压器管道中使用非默认模型时出现 KeyError

Question

我在情感分析管道中使用默认模型没有任何问题。

# Allocate a pipeline for sentiment-analysis
nlp = pipeline('sentiment-analysis')

nlp('I am a black man.')

>>>[{'label': 'NEGATIVE', 'score': 0.5723695158958435}]

但是，当我尝试通过添加特定模型来稍微自定义管道时。它抛出一个KeyError。

nlp = pipeline('sentiment-analysis',
               tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/bert-base-cased-conversational"),
               model = AutoModelWithLMHead.from_pretrained("DeepPavlov/bert-base-cased-conversational"))

nlp('I am a black man.')



>>>---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-55-af7e46d6c6c9> in <module>
      3                tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/bert-base-cased-conversational"),
      4             model = AutoModelWithLMHead.from_pretrained("DeepPavlov/bert-base-cased-conversational"))
----> 5 nlp('I am a black man.')
      6 
      7 

~/opt/anaconda3/lib/python3.7/site-packages/transformers/pipelines.py in __call__(self, *args, **kwargs)
    721         outputs = super().__call__(*args, **kwargs)
    722         scores = np.exp(outputs) / np.exp(outputs).sum(-1, keepdims=True)
--> 723         return [{"label": self.model.config.id2label[item.argmax()], "score": item.max().item()} for item in scores]
    724 
    725 

~/opt/anaconda3/lib/python3.7/site-packages/transformers/pipelines.py in <listcomp>(.0)
    721         outputs = super().__call__(*args, **kwargs)
    722         scores = np.exp(outputs) / np.exp(outputs).sum(-1, keepdims=True)
--> 723         return [{"label": self.model.config.id2label[item.argmax()], "score": item.max().item()} for item in scores]
    724 
    725 

KeyError: 58129

Answer 1

我面临着同样的问题。我正在使用 XML-R 中的一个模型，该模型使用 teamv2 数据集（“a-ware/xlmroberta-squadv2”）进行微调。在我的例子中，KeyError 是 16。

关联

在寻找有关该问题的帮助时，我发现了以下信息：链接希望您发现它有帮助。

答案（来自链接）

当模型预测不属于文档一部分的标记（例如最终特殊标记 [SEP]）时，管道会引发异常

我的问题：

from transformers import XLMRobertaTokenizer, XLMRobertaForQuestionAnswering
from transformers import pipeline

nlp = pipeline('question-answering', 
                model =  XLMRobertaForQuestionAnswering.from_pretrained('a-ware/xlmroberta-squadv2'),
                tokenizer= XLMRobertaTokenizer.from_pretrained('a-ware/xlmroberta-squadv2'))

nlp(question = "Who was Jim Henson?", context ="Jim Henson was a nice puppet")

---------------------------------------------------------------------------

KeyError                                  Traceback (most recent call last)

<ipython-input-15-b5a8ece5e525> in <module>()
      1 context = "Jim Henson was a nice puppet"
      2 # --------------- CON INTERROGACIONES
----> 3 nlp(question = "Who was Jim Henson?", context =context)

1 frames

/usr/local/lib/python3.6/dist-packages/transformers/pipelines.py in <listcomp>(.0)
   1745                         ),
   1746                     }
-> 1747                     for s, e, score in zip(starts, ends, scores)
   1748                 ]
   1749 

KeyError: 16

解决方案 1：在上下文末尾添加标点符号

为了避免尝试提取最终标记（可能是特殊的 [SEP]）的错误，我在上下文末尾添加了一个元素（在本例中为标点符号）：

nlp(question = "Who was Jim Henson?", context ="Jim Henson was a nice puppet.")

[OUT]
{'answer': 'nice puppet.', 'end': 28, 'score': 0.5742837190628052, 'start': 17}

解决方案 2：不要使用 pipeline()

原始模型可以自行处理以检索正确的令牌索引。

from transformers import XLMRobertaTokenizer, XLMRobertaForQuestionAnswering
import torch

tokenizer = XLMRobertaTokenizer.from_pretrained('a-ware/xlmroberta-squadv2')
model = XLMRobertaForQuestionAnswering.from_pretrained('a-ware/xlmroberta-squadv2')

question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
encoding = tokenizer(question, text, return_tensors='pt')
input_ids = encoding['input_ids']
attention_mask = encoding['attention_mask']

start_scores, end_scores = model(input_ids, attention_mask=attention_mask, output_attentions=False)[:2]

all_tokens = tokenizer.convert_ids_to_tokens(input_ids[0])
answer = ' '.join(all_tokens[torch.argmax(start_scores) : torch.argmax(end_scores)+1])
answer = tokenizer.convert_tokens_to_ids(answer.split())
answer = tokenizer.decode(answer)

更新

更详细地查看您的案例，我发现管道中会话任务的默认模型是distilbert-base-cased（源代码）。

我发布的第一个解决方案确实不是一个好的解决方案。尝试其他问题我得到了同样的错误。然而，管道之外的模型本身工作得很好（正如我在解决方案 2 中所示）。因此，我相信并非所有模型都可以引入管道中。如果有人有更多相关信息，请帮助我们。谢谢。