HuggingFace：pipeline为特定NLP任务直接调用_huggingface pipeline

1. English Sentiment Analysis

默认情况下，pipeline选择一个特定的预训练模型，该模型已为英语情绪分析进行了微调。创建分类器对象时，将下载并缓存模型。如果重新运行该命令，则将使用缓存的模型，无需再次下载该模型。

from transformers import pipeline

classifier = pipeline("sentiment-analysis")
classifier("I've been waiting for a HuggingFace course my whole life.")
1
2
3
4

输出：[{'label': 'POSITIVE', 'score': 0.9598047137260437}]
1

2. zero-shot classification

from transformers import pipeline

classifier = pipeline("zero-shot-classification")
classifier(
    "This is a course about the Transformers library",
    candidate_labels=["education", "politics", "business", "course"],
)
1
2
3
4
5
6
7

输出：
{'sequence': 'This is a course about the Transformers library',
 'labels': ['course', 'education', 'business', 'politics'],
 'scores': [0.9461037516593933,
  0.04552055522799492,
  0.0060350666753947735,
  0.002340571256354451]}
1
2
3
4
5
6
7

3. text generation