Google Colab 无法拥抱脸部模型

Question

我喜欢使用 BERT 模型来标记词性。为此，我使用了 Hugging Face 库。

当我在 Hugging Face API 上运行模型时，我得到了输出

但是，当我在 Google Colab 上运行代码时，出现错误。

我的代码

from transformers import AutoModelWithHeads
from transformers import pipeline
from transformers import AutoTokenizer

model = AutoModelWithHeads.from_pretrained("bert-base-uncased")
adapter_name = model.load_adapter("AdapterHub/bert-base-uncased-pf-ud_pos", source="hf")
model.active_adapters = adapter_name

tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
token_classification = pipeline("token-classification", model=model, tokenizer=tokenizer, aggregation_strategy="NONE")
res = token_classification("Take out the trash bag from the bin and replace it.")
print(res)

错误是

 The model 'BertModelWithHeads' is not supported for token-classification. Supported models are ['AlbertForTokenClassification', 'BertForTokenClassification', 'BigBirdForTokenClassification', 'BloomForTokenClassification', 'CamembertForTokenClassification', 'CanineForTokenClassification', 'ConvBertForTokenClassification', 'Data2VecTextForTokenClassification', 'DebertaForTokenClassification', 'DebertaV2ForTokenClassification', 'DistilBertForTokenClassification', 'ElectraForTokenClassification', 'ErnieForTokenClassification', 'EsmForTokenClassification', 'FlaubertForTokenClassification', 'FNetForTokenClassification', 'FunnelForTokenClassification', 'GPT2ForTokenClassification', 'GPT2ForTokenClassification', 'IBertForTokenClassification', 'LayoutLMForTokenClassification', 'LayoutLMv2ForTokenClassification', 'LayoutLMv3ForTokenClassification', 'LiltForTokenClassification', 'LongformerForTokenClassification', 'LukeForTokenClassification', 'MarkupLMForTokenClassification', 'MegatronBertForTokenClassification', 'MobileBertForTokenClassification', 'MPNetForTokenClassification', 'NezhaForTokenClassification', 'NystromformerForTokenClassification', 'QDQBertForTokenClassification', 'RemBertForTokenClassification', 'RobertaForTokenClassification', 'RobertaPreLayerNormForTokenClassification', 'RoCBertForTokenClassification', 'RoFormerForTokenClassification', 'SqueezeBertForTokenClassification', 'XLMForTokenClassification', 'XLMRobertaForTokenClassification', 'XLMRobertaXLForTokenClassification', 'XLNetForTokenClassification', 'YosoForTokenClassification', 'XLMRobertaAdapterModel', 'RobertaAdapterModel', 'AlbertAdapterModel', 'BeitAdapterModel', 'BertAdapterModel', 'BertGenerationAdapterModel', 'DistilBertAdapterModel', 'DebertaV2AdapterModel', 'DebertaAdapterModel', 'BartAdapterModel', 'MBartAdapterModel', 'GPT2AdapterModel', 'GPTJAdapterModel', 'T5AdapterModel', 'ViTAdapterModel'].
---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-18-79b43720402e> in <cell line: 12>()
     10 tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
     11 token_classification = pipeline("token-classification", model=model, tokenizer=tokenizer, aggregation_strategy="NONE")
---> 12 res = token_classification("Take out the trash bag from the bin and replace it.")
     13 print(res)

4 frames
/usr/local/lib/python3.10/dist-packages/transformers/pipelines/token_classification.py in aggregate(self, pre_entities, aggregation_strategy)
    346                 score = pre_entity["scores"][entity_idx]
    347                 entity = {
--> 348                     "entity": self.model.config.id2label[entity_idx],
    349                     "score": score,
    350                     "index": pre_entity["index"],

密钥错误：16

我不明白模型在 Hugging Face API 中运行正常，为什么无法在 Google Colab 上运行？

提前谢谢您。

Answer 1

您可以这样做：

from transformers import AutoModelWithHeads, AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
model = AutoModelWithHeads.from_pretrained("bert-base-uncased")
model.load_adapter(
    "AdapterHub/bert-base-uncased-pf-ud_pos",
    source="hf",
    set_active=True,
)
token_classification = pipeline(
    "token-classification",
    model=model,
    tokenizer=tokenizer,
)

此管道创建部分将显示警告，即

The model 'BertModelWithHeads' is not supported for token-classification. Supported models are ['AlbertForTokenClassification', 'BertForTokenClassification', 'BigBirdForTokenClassification', 'BloomForTokenClassification', 'CamembertForTokenClassification', 'CanineForTokenClassification', 'ConvBertForTokenClassification', 'Data2VecTextForTokenClassification', 'DebertaForTokenClassification', 'DebertaV2ForTokenClassification', 'DistilBertForTokenClassification', 'ElectraForTokenClassification', 'ErnieForTokenClassification', 'EsmForTokenClassification', 'FlaubertForTokenClassification', 'FNetForTokenClassification', 'FunnelForTokenClassification', 'GPT2ForTokenClassification', 'GPT2ForTokenClassification', 'IBertForTokenClassification', 'LayoutLMForTokenClassification', 'LayoutLMv2ForTokenClassification', 'LayoutLMv3ForTokenClassification', 'LiltForTokenClassification', 'LongformerForTokenClassification', 'LukeForTokenClassification', 'MarkupLMForTokenClassification', 'MegatronBertForTokenClassification', 'MobileBertForTokenClassification', 'MPNetForTokenClassification', 'NezhaForTokenClassification', 'NystromformerForTokenClassification', 'QDQBertForTokenClassification', 'RemBertForTokenClassification', 'RobertaForTokenClassification', 'RobertaPreLayerNormForTokenClassification', 'RoCBertForTokenClassification', 'RoFormerForTokenClassification', 'SqueezeBertForTokenClassification', 'XLMForTokenClassification', 'XLMRobertaForTokenClassification', 'XLMRobertaXLForTokenClassification', 'XLNetForTokenClassification', 'YosoForTokenClassification', 'XLMRobertaAdapterModel', 'RobertaAdapterModel', 'AlbertAdapterModel', 'BeitAdapterModel', 'BertAdapterModel', 'BertGenerationAdapterModel', 'DistilBertAdapterModel', 'DebertaV2AdapterModel', 'DebertaAdapterModel', 'BartAdapterModel', 'MBartAdapterModel', 'GPT2AdapterModel', 'GPTJAdapterModel', 'T5AdapterModel', 'ViTAdapterModel'].

你可以忽略它，管道仍然可以工作。这是一个例子：

>>> token_classification("Take out the trash bag from the bin and replace it")
[{'entity': 'VERB','score': 0.99986637, 'index': 1, 'word': 'take', 'start': 0, 'end': 4},
 {'entity': 'ADP', 'score': 0.9829973, 'index': 2, 'word': 'out', 'start': 5, 'end': 8},
 {'entity': 'DET', 'score': 0.9998791, 'index': 3, 'word': 'the', 'start': 9, 'end': 12},
 {'entity': 'NOUN', 'score': 0.9958676, 'index': 4, 'word': 'trash', 'start': 13, 'end': 18},
 {'entity': 'NOUN', 'score': 0.99657273, 'index': 5, 'word': 'bag', 'start': 19, 'end': 22},
 {'entity': 'ADP', 'score': 0.99989176, 'index': 6, 'word': 'from', 'start': 23, 'end': 27},
 {'entity': 'DET', 'score': 0.99982834, 'index': 7, 'word': 'the', 'start': 28, 'end': 31},
 {'entity': 'NOUN', 'score': 0.99584526, 'index': 8, 'word': 'bin', 'start': 32, 'end': 35},
 {'entity': 'CCONJ', 'score': 0.99962616, 'index': 9, 'word': 'and', 'start': 36, 'end': 39},
 {'entity': 'VERB', 'score': 0.99976975, 'index': 10, 'word': 'replace', 'start': 40, 'end': 47},
 {'entity': 'PRON', 'score': 0.9989698, 'index': 11, 'word': 'it', 'start': 48, 'end': 50}]

Answer 2

adapter-transformers

软件包已弃用，并由

adapters

取代（有关更多信息，请参阅介绍适配器）。

这里是基于 Riccardo 答案的更新代码和来自 适配器文档 的示例：

from transformers import BertTokenizer, pipeline, BertForTokenClassification
from adapters import BertAdapterModel

# Load pre-trained BERT tokenizer from Hugging Face
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

# Load pre-trained BERT model from Hugging Face Hub
# The `BertAdapterModel` class is specifically designed for working with adapters
# It can be used with different prediction heads
model = BertAdapterModel.from_pretrained('bert-base-uncased')

# Load pre-trained task adapter from Adapter Hub
adapter_name = model.load_adapter("AdapterHub/bert-base-uncased-pf-ud_pos", source="hf", set_active=True)

# Activate the adapter we just loaded, so that it is used in every forward pass
model.set_active_adapters(adapter_name)

token_classification = pipeline("token-classification", model=model, tokenizer=tokenizer)
token_classification("Take out the trash bag from the bin and replace it.")

这是输出：

[{'entity': 'VERB',
  'score': 0.9998685,
  'index': 1,
  'word': 'take',
  'start': None,
  'end': None},
 {'entity': 'ADP',
  'score': 0.9836626,
  'index': 2,
  'word': 'out',
  'start': None,
  'end': None},
 {'entity': 'DET',
  'score': 0.9998733,
  'index': 3,
  'word': 'the',
  'start': None,
  'end': None},
 {'entity': 'NOUN',
  'score': 0.9964223,
  'index': 4,
  'word': 'trash',
  'start': None,
  'end': None},
 {'entity': 'NOUN',
  'score': 0.9971655,
  'index': 5,
  'word': 'bag',
  'start': None,
  'end': None},
 {'entity': 'ADP',
  'score': 0.99989533,
  'index': 6,
  'word': 'from',
  'start': None,
  'end': None},
 {'entity': 'DET',
  'score': 0.9998233,
  'index': 7,
  'word': 'the',
  'start': None,
  'end': None},
 {'entity': 'NOUN',
  'score': 0.9966047,
  'index': 8,
  'word': 'bin',
  'start': None,
  'end': None},
 {'entity': 'CCONJ',
  'score': 0.9996582,
  'index': 9,
  'word': 'and',
  'start': None,
  'end': None},
 {'entity': 'VERB',
  'score': 0.9997621,
  'index': 10,
  'word': 'replace',
  'start': None,
  'end': None},
 {'entity': 'PRON',
  'score': 0.9989335,
  'index': 11,
  'word': 'it',
  'start': None,
  'end': None},
 {'entity': 'PUNCT',
  'score': 0.99996936,
  'index': 12,
  'word': '.',
  'start': None,
  'end': None}]