pipeline_function.ipynb

Kernel: Unknown Kernel

This notebook regroups the code sample of the video below, which is a part of the Hugging Face course.

#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/tiZFewofSLM?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

Install the Transformers and Datasets libraries to run this notebook.

! pip install datasets transformers[sentencepiece]

from transformers import pipeline

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

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

from transformers import pipeline

classifier = pipeline("sentiment-analysis")
classifier([
    "I've been waiting for a HuggingFace course my whole life.", 
    "I hate this so much!"
])

[{'label': 'POSITIVE', 'score': 0.9598047137260437},
 {'label': 'NEGATIVE', 'score': 0.9994558095932007}]

from transformers import pipeline

classifier = pipeline("zero-shot-classification")
classifier(
    "This is a course about the Transformers library",
    candidate_labels=["education", "politics", "business"],
)

{'sequence': 'This is a course about the Transformers library',
 'labels': ['education', 'business', 'politics'],
 'scores': [0.8445963859558105, 0.1119762435555458, 0.043427448719739914]}

from transformers import pipeline

generator = pipeline("text-generation")
generator("In this course, we will teach you how to")

Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.

[{'generated_text': 'In this course, we will teach you how to apply a real-time flow strategy of a distributed system called "n-to-5th dimension" in real-world situations. The techniques we will demonstrate are as follows:\n\nCreate your'}]

from transformers import pipeline

generator = pipeline("text-generation")
generator(
    "In this course, we will teach you how to",
    max_length=30,
    num_return_sequences=2,
)

Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.

[{'generated_text': 'In this course, we will teach you how to design your software and help you get the most out of it.\n\nStep 10: Start coding'},
 {'generated_text': "In this course, we will teach you how to handle errors in the program. From scratch, you'll learn the basic operations that can be performed as"}]

from transformers import pipeline

unmasker = pipeline("fill-mask")
unmasker("This course will teach you all about <mask> models.", top_k=2)

[{'sequence': 'This course will teach you all about mathematical models.',
  'score': 0.19619831442832947,
  'token': 30412,
  'token_str': ' mathematical'},
 {'sequence': 'This course will teach you all about computational models.',
  'score': 0.04052725434303284,
  'token': 38163,
  'token_str': ' computational'}]

from transformers import pipeline

ner = pipeline("ner", grouped_entities=True)
ner("My name is Sylvain and I work at Hugging Face in Brooklyn.")

/home/sgugger/git/transformers/src/transformers/pipelines/token_classification.py:155: UserWarning: `grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="AggregationStrategy.SIMPLE"` instead.
  f'`grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="{aggregation_strategy}"` instead.'

[{'entity_group': 'PER',
  'score': 0.9981694,
  'word': 'Sylvain',
  'start': 11,
  'end': 18},
 {'entity_group': 'ORG',
  'score': 0.97960204,
  'word': 'Hugging Face',
  'start': 33,
  'end': 45},
 {'entity_group': 'LOC',
  'score': 0.99321055,
  'word': 'Brooklyn',
  'start': 49,
  'end': 57}]

from transformers import pipeline

question_answerer = pipeline("question-answering")
question_answerer(
    question="Where do I work?",
    context="My name is Sylvain and I work at Hugging Face in Brooklyn.",
)

{'score': 0.6385916471481323, 'start': 33, 'end': 45, 'answer': 'Hugging Face'}

from transformers import pipeline

summarizer = pipeline("summarization")
summarizer("""
    America has changed dramatically during recent years. Not only has the number of 
    graduates in traditional engineering disciplines such as mechanical, civil, 
    electrical, chemical, and aeronautical engineering declined, but in most of 
    the premier American universities engineering curricula now concentrate on 
    and encourage largely the study of engineering science.  As a result, there 
    are declining offerings in engineering subjects dealing with infrastructure, 
    the environment, and related issues, and greater concentration on high 
    technology subjects, largely supporting increasingly complex scientific 
    developments. While the latter is important, it should not be at the expense 
    of more traditional engineering.

    Rapidly developing economies such as China and India, as well as other 
    industrial countries in Europe and Asia, continue to encourage and advance 
    the teaching of engineering. Both China and India, respectively, graduate 
    six and eight times as many traditional engineers as does the United States. 
    Other industrial countries at minimum maintain their output, while America 
    suffers an increasingly serious decline in the number of engineering graduates 
    and a lack of well-educated engineers.
""")

[{'summary_text': ' America has changed dramatically during recent years . The number of engineering graduates in the U.S. has declined in traditional engineering disciplines such as mechanical, civil, electrical, chemical, and aeronautical engineering . Rapidly developing economies such as China and India, as well as other industrial countries in Europe and Asia, continue to encourage and advance engineering .'}]

from transformers import pipeline

translator = pipeline("translation", model="Helsinki-NLP/opus-mt-fr-en")
translator("Ce cours est produit par Hugging Face.")

[{'translation_text': 'This course is produced by Hugging Face.'}]