from transformers import pipeline
classifier = pipeline("sentiment-analysis")
result = classifier("I hate you")[0]
print(f"label: {result['label']}, with score: {round(result['score'], 4)}")
result = classifier("I love you")[0]
print(f"label: {result['label']}, with score: {round(result['score'], 4)}")

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
tokenizer = AutoTokenizer.from_pretrained("bert-base-cased-finetuned-mrpc")
model = AutoModelForSequenceClassification.from_pretrained("bert-base-cased-finetuned-mrpc")
classes = ["not paraphrase", "is paraphrase"]
sequence_0 = "The company HuggingFace is based in New York City"
sequence_1 = "Apples are especially bad for your health"
sequence_2 = "HuggingFace's headquarters are situated in Manhattan"
# The tokenizer will automatically add any model specific separators (i.e. <CLS> and <SEP>) and tokens to
# the sequence, as well as compute the attention masks.
paraphrase = tokenizer(sequence_0, sequence_2, return_tensors="pt")
not_paraphrase = tokenizer(sequence_0, sequence_1, return_tensors="pt")
paraphrase_classification_logits = model(**paraphrase).logits
not_paraphrase_classification_logits = model(**not_paraphrase).logits
paraphrase_results = torch.softmax(paraphrase_classification_logits, dim=1).tolist()[0]
not_paraphrase_results = torch.softmax(not_paraphrase_classification_logits, dim=1).tolist()[0]
# Should be paraphrase
for i in range(len(classes)):
    print(f"{classes[i]}: {int(round(paraphrase_results[i] * 100))}%")
# Should not be paraphrase
for i in range(len(classes)):
    print(f"{classes[i]}: {int(round(not_paraphrase_results[i] * 100))}%")

from transformers import pipeline
question_answerer = pipeline("question-answering")
context = r"""
Extractive Question Answering is the task of extracting an answer from a text given a question. An example of a
question answering dataset is the SQuAD dataset, which is entirely based on that task. If you would like to fine-tune
a model on a SQuAD task, you may leverage the examples/pytorch/question-answering/run_squad.py script.
"""
result = question_answerer(question="What is extractive question answering?", context=context)
print(
    f"Answer: '{result['answer']}', score: {round(result['score'], 4)}, start: {result['start']}, end: {result['end']}"
)
result = question_answerer(question="What is a good example of a question answering dataset?", context=context)
print(
    f"Answer: '{result['answer']}', score: {round(result['score'], 4)}, start: {result['start']}, end: {result['end']}"
)

from transformers import AutoTokenizer, AutoModelForQuestionAnswering
import torch
tokenizer = AutoTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
model = AutoModelForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
text = r"""
🤗 Transformers (formerly known as pytorch-transformers and pytorch-pretrained-bert) provides general-purpose
architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet…) for Natural Language Understanding (NLU) and Natural
Language Generation (NLG) with over 32+ pretrained models in 100+ languages and deep interoperability between
TensorFlow 2.0 and PyTorch.
"""
questions = [
    "How many pretrained models are available in 🤗 Transformers?",
    "What does 🤗 Transformers provide?",
    "🤗 Transformers provides interoperability between which frameworks?",
]
for question in questions:
    inputs = tokenizer(question, text, add_special_tokens=True, return_tensors="pt")
    input_ids = inputs["input_ids"].tolist()[0]
    outputs = model(**inputs)
    answer_start_scores = outputs.start_logits
    answer_end_scores = outputs.end_logits
    # Get the most likely beginning of answer with the argmax of the score
    answer_start = torch.argmax(answer_start_scores)
    # Get the most likely end of answer with the argmax of the score
    answer_end = torch.argmax(answer_end_scores) + 1
    answer = tokenizer.convert_tokens_to_string(
        tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end])
    )
    print(f"Question: {question}")
    print(f"Answer: {answer}")

from transformers import pipeline
unmasker = pipeline("fill-mask")
from pprint import pprint
pprint(
    unmasker(
        f"HuggingFace is creating a {unmasker.tokenizer.mask_token} that the community uses to solve NLP tasks."
    )
)

[{'score': 0.1793,
  'sequence': 'HuggingFace is creating a tool that the community uses to solve '
              'NLP tasks.',
  'token': 3944,
  'token_str': ' tool'},
 {'score': 0.1135,
  'sequence': 'HuggingFace is creating a framework that the community uses to '
              'solve NLP tasks.',
  'token': 7208,
  'token_str': ' framework'},
 {'score': 0.0524,
  'sequence': 'HuggingFace is creating a library that the community uses to '
              'solve NLP tasks.',
  'token': 5560,
  'token_str': ' library'},
 {'score': 0.0349,
  'sequence': 'HuggingFace is creating a database that the community uses to '
              'solve NLP tasks.',
  'token': 8503,
  'token_str': ' database'},
 {'score': 0.0286,
  'sequence': 'HuggingFace is creating a prototype that the community uses to '
              'solve NLP tasks.',
  'token': 17715,
  'token_str': ' prototype'}]

from transformers import AutoModelForMaskedLM, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-cased")
model = AutoModelForMaskedLM.from_pretrained("distilbert-base-cased")
sequence = (
    "Distilled models are smaller than the models they mimic. Using them instead of the large "
    f"versions would help {tokenizer.mask_token} our carbon footprint."
)
inputs = tokenizer(sequence, return_tensors="pt")
mask_token_index = torch.where(inputs["input_ids"] == tokenizer.mask_token_id)[1]
token_logits = model(**inputs).logits
mask_token_logits = token_logits[0, mask_token_index, :]
top_5_tokens = torch.topk(mask_token_logits, 5, dim=1).indices[0].tolist()
#得到分数最高的5个token的索引
#值得注意的是，topk函数默认是根据value经过sort的。参考其函数文档：https://pytorch.org/docs/stable/generated/torch.topk.html
for token in top_5_tokens:
    print(sequence.replace(tokenizer.mask_token, tokenizer.decode([token])))
    #将该token解码为文本形式，替代原文中的tokenizer.mask_token

Distilled models are smaller than the models they mimic. Using them instead of the large versions would help reduce our carbon footprint.
Distilled models are smaller than the models they mimic. Using them instead of the large versions would help increase our carbon footprint.
Distilled models are smaller than the models they mimic. Using them instead of the large versions would help decrease our carbon footprint.
Distilled models are smaller than the models they mimic. Using them instead of the large versions would help offset our carbon footprint.
Distilled models are smaller than the models they mimic. Using them instead of the large versions would help improve our carbon footprint.

from transformers import AutoModelForCausalLM, AutoTokenizer, top_k_top_p_filtering
import torch
from torch import nn
tokenizer = AutoTokenizer.from_pretrained("gpt2")
model = AutoModelForCausalLM.from_pretrained("gpt2")
sequence = f"Hugging Face is based in DUMBO, New York City, and"
inputs = tokenizer(sequence, return_tensors="pt")
input_ids = inputs["input_ids"]
# get logits of last hidden state
next_token_logits = model(**inputs).logits[:, -1, :]
# filter
filtered_next_token_logits = top_k_top_p_filtering(next_token_logits, top_k=50, top_p=1.0)
# sample
probs = nn.functional.softmax(filtered_next_token_logits, dim=-1)
next_token = torch.multinomial(probs, num_samples=1)
generated = torch.cat([input_ids, next_token], dim=-1)
resulting_string = tokenizer.decode(generated.tolist()[0])
print(resulting_string)

from transformers import pipeline
text_generator = pipeline("text-generation")
print(text_generator("As far as I am concerned, I will", max_length=50, do_sample=False))

[{'generated_text': 'As far as I am concerned, I will be the first to admit that I am not a fan of the idea of a
"free market." I think that the idea of a free market is a bit of a stretch. I think that the idea'}]

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("xlnet-base-cased")
tokenizer = AutoTokenizer.from_pretrained("xlnet-base-cased")
# Padding text helps XLNet with short prompts - proposed by Aman Rusia in https://github.com/rusiaaman/XLNet-gen#methodology
PADDING_TEXT = """In 1991, the remains of Russian Tsar Nicholas II and his family
(except for Alexei and Maria) are discovered.
The voice of Nicholas's young son, Tsarevich Alexei Nikolaevich, narrates the
remainder of the story. 1883 Western Siberia,
a young Grigori Rasputin is asked by his father and a group of men to perform magic.
Rasputin has a vision and denounces one of the men as a horse thief. Although his
father initially slaps him for making such an accusation, Rasputin watches as the
man is chased outside and beaten. Twenty years later, Rasputin sees a vision of
the Virgin Mary, prompting him to become a priest. Rasputin quickly becomes famous,
with people, even a bishop, begging for his blessing. <eod> </s> <eos>"""
prompt = "Today the weather is really nice and I am planning on "
inputs = tokenizer(PADDING_TEXT + prompt, add_special_tokens=False, return_tensors="pt")["input_ids"]
prompt_length = len(tokenizer.decode(inputs[0]))
outputs = model.generate(inputs, max_length=250, do_sample=True, top_p=0.95, top_k=60)
generated = prompt + tokenizer.decode(outputs[0])[prompt_length + 1 :]
print(generated)

Today the weather is really nice and I am planning on going for a walk in the park with my mom (she can walk and play golf) to explore and see something I didn't know. The park is actually a giant green, with lots of shade in the first two thirds of the way (it is en route to a major golf course, which is really neat). I decided to walk

Today the weather is really nice and I am planning on going on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on going on on on on on on on on on on on on going on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on and on on on on on on on and on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on on and on on on on on on on on on on on on on on and on on on on on on and on on on on on on on on on on on on on on on on and on on on and on on on on on on on on on on on on on on on on on on and on and on on on

from transformers import pipeline
ner_pipe = pipeline("ner")
sequence = """Hugging Face Inc. is a company based in New York City. Its headquarters are in DUMBO,
therefore very close to the Manhattan Bridge which is visible from the window."""

for entity in ner_pipe(sequence):
    print(entity)

{'entity': 'I-ORG', 'score': 0.9996, 'index': 1, 'word': 'Hu', 'start': 0, 'end': 2}
{'entity': 'I-ORG', 'score': 0.9910, 'index': 2, 'word': '##gging', 'start': 2, 'end': 7}
{'entity': 'I-ORG', 'score': 0.9982, 'index': 3, 'word': 'Face', 'start': 8, 'end': 12}
{'entity': 'I-ORG', 'score': 0.9995, 'index': 4, 'word': 'Inc', 'start': 13, 'end': 16}
{'entity': 'I-LOC', 'score': 0.9994, 'index': 11, 'word': 'New', 'start': 40, 'end': 43}
{'entity': 'I-LOC', 'score': 0.9993, 'index': 12, 'word': 'York', 'start': 44, 'end': 48}
{'entity': 'I-LOC', 'score': 0.9994, 'index': 13, 'word': 'City', 'start': 49, 'end': 53}
{'entity': 'I-LOC', 'score': 0.9863, 'index': 19, 'word': 'D', 'start': 79, 'end': 80}
{'entity': 'I-LOC', 'score': 0.9514, 'index': 20, 'word': '##UM', 'start': 80, 'end': 82}
{'entity': 'I-LOC', 'score': 0.9337, 'index': 21, 'word': '##BO', 'start': 82, 'end': 84}
{'entity': 'I-LOC', 'score': 0.9762, 'index': 28, 'word': 'Manhattan', 'start': 114, 'end': 123}
{'entity': 'I-LOC', 'score': 0.9915, 'index': 29, 'word': 'Bridge', 'start': 124, 'end': 130}

from transformers import AutoModelForTokenClassification, AutoTokenizer
import torch
model = AutoModelForTokenClassification.from_pretrained("dbmdz/bert-large-cased-finetuned-conll03-english")
tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
sequence = (
    "Hugging Face Inc. is a company based in New York City. Its headquarters are in DUMBO, "
    "therefore very close to the Manhattan Bridge."
)
inputs = tokenizer(sequence, return_tensors="pt")
tokens = inputs.tokens()
outputs = model(**inputs).logits
predictions = torch.argmax(outputs, dim=2)

for token, prediction in zip(tokens, predictions[0].numpy()):
    print((token, model.config.id2label[prediction]))

('[CLS]', 'O')
('Hu', 'I-ORG')
('##gging', 'I-ORG')
('Face', 'I-ORG')
('Inc', 'I-ORG')
('.', 'O')
('is', 'O')
('a', 'O')
('company', 'O')
('based', 'O')
('in', 'O')
('New', 'I-LOC')
('York', 'I-LOC')
('City', 'I-LOC')
('.', 'O')
('Its', 'O')
('headquarters', 'O')
('are', 'O')
('in', 'O')
('D', 'I-LOC')
('##UM', 'I-LOC')
('##BO', 'I-LOC')
(',', 'O')
('therefore', 'O')
('very', 'O')
('close', 'O')
('to', 'O')
('the', 'O')
('Manhattan', 'I-LOC')
('Bridge', 'I-LOC')
('.', 'O')
('[SEP]', 'O')

from transformers import pipeline
summarizer = pipeline("summarization")
ARTICLE = """ New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York.
A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband.
Only 18 days after that marriage, she got hitched yet again. Then, Barrientos declared "I do" five more times, sometimes only within two weeks of each other.
In 2010, she married once more, this time in the Bronx. In an application for a marriage license, she stated it was her "first and only" marriage.
Barrientos, now 39, is facing two criminal counts of "offering a false instrument for filing in the first degree," referring to her false statements on the
2010 marriage license application, according to court documents.
Prosecutors said the marriages were part of an immigration scam.
On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further.
After leaving court, Barrientos was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New York subway through an emergency exit, said Detective
Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002.
All occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be married to four men, and at one time, she was married to eight men at once, prosecutors say.
Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages.
Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted.
The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s
Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali.
Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force.
If convicted, Barrientos faces up to four years in prison.  Her next court appearance is scheduled for May 18.
"""
print(summarizer(ARTICLE, max_length=130, min_length=30, do_sample=False))

[{'summary_text': ' Liana Barrientos, 39, is charged with two counts of "offering a false instrument for filing in
the first degree" In total, she has been married 10 times, with nine of her marriages occurring between 1999 and
2002 . At one time, she was married to eight men at once, prosecutors say .'}]

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
tokenizer = AutoTokenizer.from_pretrained("t5-base")
# T5 uses a max_length of 512 so we cut the article to 512 tokens.
inputs = tokenizer("summarize: " + ARTICLE, return_tensors="pt", max_length=512, truncation=True)
outputs = model.generate(
    inputs["input_ids"], max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True
)
print(tokenizer.decode(outputs[0]))

<pad> prosecutors say the marriages were part of an immigration scam. if convicted, barrientos faces two criminal
counts of "offering a false instrument for filing in the first degree" she has been married 10 times, nine of them
between 1999 and 2002.</s>

from transformers import pipeline
translator = pipeline("translation_en_to_de")
print(translator("Hugging Face is a technology company based in New York and Paris", max_length=40))

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
tokenizer = AutoTokenizer.from_pretrained("t5-base")
inputs = tokenizer(
    "translate English to German: Hugging Face is a technology company based in New York and Paris",
    return_tensors="pt",
)
outputs = model.generate(inputs["input_ids"], max_length=40, num_beams=4, early_stopping=True)
print(tokenizer.decode(outputs[0]))