Huggingface Transformer教程

pip install transformers

pip install git+https://github.com/huggingface/transformers

git clone https://github.com/huggingface/transformers.git
cd transformers
pip install -e .

~/huggingface-venv/lib/python3.6/site-packages/transformers/

HF_DATASETS_OFFLINE=1 TRANSFORMERS_OFFLINE=1

from transformers import pipeline
classifier = pipeline('sentiment-analysis')

[{'label': 'POSITIVE', 'score': 0.9997795224189758}]

classifier = pipeline('sentiment-analysis', proxies={"http": "http://localhost:1080"})

TypeError: __init__() got an unexpected keyword argument 'proxies'

results = classifier(["We are very happy to show you the 🤗 Transformers library.",
           "We hope you don't hate it."])
for result in results:
    print(f"label: {result['label']}, with score: {round(result['score'], 4)}")

label: POSITIVE, with score: 0.9998
label: NEGATIVE, with score: 0.5309

classifier = pipeline('sentiment-analysis', model="nlptown/bert-base-multilingual-uncased-sentiment")

from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)

from transformers import AutoTokenizer, AutoModelForSequenceClassification
model_name = "distilbert-base-uncased-finetuned-sst-2-english"
pt_model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

inputs = tokenizer("We are very happy to show you the 🤗 Transformers library.")

print(inputs)
{'input_ids': [101, 2057, 2024, 2200, 3407, 2000, 2265, 2017, 1996, 100, 19081, 3075, 1012, 102], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}

pt_batch = tokenizer(
    ["We are very happy to show you the 🤗 Transformers library.", "We hope you don't hate it."],
    padding=True,
    truncation=True,
    max_length=512,
    return_tensors="pt"
)

>>> for key, value in pt_batch.items():
...     print(f"{key}: {value.numpy().tolist()}")
input_ids: [[101, 2057, 2024, 2200, 3407, 2000, 2265, 2017, 1996, 100, 19081, 3075, 1012, 102], [101, 2057, 3246, 2017, 2123, 1005, 1056, 5223, 2009, 1012, 102, 0, 0, 0]]
attention_mask: [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0]]

# PyTorch
pt_outputs = pt_model(**pt_batch)
# TensorFlow
tf_outputs = tf_model(tf_batch)

>>> print(pt_outputs)
(tensor([[-4.0833,  4.3364],
        [ 0.0818, -0.0418]], grad_fn=<AddmmBackward>),)

>>> import torch.nn.functional as F
>>> pt_predictions = F.softmax(pt_outputs[0], dim=-1)

>>> print(pt_predictions)
tensor([[2.2043e-04, 9.9978e-01],
        [5.3086e-01, 4.6914e-01]], grad_fn=<SoftmaxBackward>)

>>> import torch
>>> pt_outputs = pt_model(**pt_batch, labels = torch.tensor([1, 0]))

SequenceClassifierOutput(loss=tensor(0.3167, grad_fn=<NllLossBackward>), logits=tensor([[-4.0833,  4.3364],
        [ 0.0818, -0.0418]], grad_fn=<AddmmBackward>), hidden_states=None, attentions=None)

tokenizer.save_pretrained(save_directory)
model.save_pretrained(save_directory)

tokenizer = AutoTokenizer.from_pretrained(save_directory)
model = TFAutoModel.from_pretrained(save_directory, from_pt=True)

tokenizer = AutoTokenizer.from_pretrained(save_directory)
model = AutoModel.from_pretrained(save_directory, from_tf=True)

pt_outputs = pt_model(**pt_batch, output_hidden_states=True, output_attentions=True)
all_hidden_states, all_attentions = pt_outputs[-2:]

from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
model_name = "distilbert-base-uncased-finetuned-sst-2-english"
model = DistilBertForSequenceClassification.from_pretrained(model_name)
tokenizer = DistilBertTokenizer.from_pretrained(model_name)

from transformers import DistilBertConfig, DistilBertTokenizer, DistilBertForSequenceClassification
config = DistilBertConfig(n_heads=8, dim=512, hidden_dim=4*512)
tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertForSequenceClassification(config)

from transformers import DistilBertConfig, DistilBertTokenizer, DistilBertForSequenceClassification
model_name = "distilbert-base-uncased"
model = DistilBertForSequenceClassification.from_pretrained(model_name, num_labels=10)
tokenizer = DistilBertTokenizer.from_pretrained(model_name)

class DistilBertForSequenceClassification(DistilBertPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels

        self.distilbert = DistilBertModel(config)
        self.pre_classifier = nn.Linear(config.dim, config.dim)
        self.classifier = nn.Linear(config.dim, config.num_labels)
        self.dropout = nn.Dropout(config.seq_classif_dropout)

        self.init_weights()

from transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained("bert-base-cased")
sequence = "A Titan RTX has 24GB of VRAM"

tokenized_sequence = tokenizer.tokenize(sequence)

>>> print(tokenized_sequence)
['A', 'Titan', 'R', '##T', '##X', 'has', '24', '##GB', 'of', 'V', '##RA', '##M']

inputs = tokenizer(sequence)

>>> encoded_sequence = inputs["input_ids"]
>>> print(encoded_sequence)
[101, 138, 18696, 155, 1942, 3190, 1144, 1572, 13745, 1104, 159, 9664, 2107, 102]

decoded_sequence = tokenizer.decode(encoded_sequence)

>>> print(decoded_sequence)
[CLS] A Titan RTX has 24GB of VRAM [SEP]

from transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained("bert-base-cased")
sequence_a = "This is a short sequence."
sequence_b = "This is a rather long sequence. It is at least longer than the sequence A."
encoded_sequence_a = tokenizer(sequence_a)["input_ids"]
encoded_sequence_b = tokenizer(sequence_b)["input_ids"]

>>> len(encoded_sequence_a), len(encoded_sequence_b)
(8, 19)

padded_sequences = tokenizer([sequence_a, sequence_b], padding=True)
print(padded_sequences["input_ids"])
[[101, 1188, 1110, 170, 1603, 4954, 119, 102, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [101, 1188, 1110, 170, 1897, 1263, 4954, 119, 1135, 1110, 1120, 1655, 2039, 1190, 1103, 4954, 138, 119, 102]]

>>> padded_sequences["attention_mask"]
[[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]

from transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained("bert-base-cased")
sequence_a = "HuggingFace is based in NYC"
sequence_b = "Where is HuggingFace based?"
encoded_dict = tokenizer(sequence_a, sequence_b)
decoded = tokenizer.decode(encoded_dict["input_ids"])

>>> print(decoded)
[CLS] HuggingFace is based in NYC [SEP] Where is HuggingFace based? [SEP]

>>> encoded_dict['token_type_ids']
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1]

>>> from transformers import pipeline

>>> nlp = pipeline("sentiment-analysis")

>>> result = nlp("I hate you")[0]
>>> print(f"label: {result['label']}, with score: {round(result['score'], 4)}")
label: NEGATIVE, with score: 0.9991

>>> result = nlp("I love you")[0]
>>> print(f"label: {result['label']}, with score: {round(result['score'], 4)}")
label: POSITIVE, with score: 0.9999

>>> 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"

>>> 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))}%")
not paraphrase: 10%
is paraphrase: 90%

>>> # Should not be paraphrase
>>> for i in range(len(classes)):
...     print(f"{classes[i]}: {int(round(not_paraphrase_results[i] * 100))}%")
not paraphrase: 94%
is paraphrase: 6%

>>> from transformers import pipeline

>>> nlp = 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/question-answering/run_squad.py script.
... """

>>> result = nlp(question="What is extractive question answering?", context=context)
>>> print(f"Answer: '{result['answer']}', score: {round(result['score'], 4)}, start: {result['start']}, end: {result['end']}")
Answer: 'the task of extracting an answer from a text given a question.', score: 0.6226, start: 34, end: 96

>>> result = nlp(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']}")
Answer: 'SQuAD dataset,', score: 0.5053, start: 147, end: 161

>>> 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
...
...     answer_start = torch.argmax(
...         answer_start_scores
...     )  # Get the most likely beginning of answer with the argmax of the score
...     answer_end = torch.argmax(answer_end_scores) + 1  # Get the most likely end of answer with the argmax of the score
...
...     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}")
Question: How many pretrained models are available in 🤗 Transformers?
Answer: over 32 +
Question: What does 🤗 Transformers provide?
Answer: general - purpose architectures
Question: 🤗 Transformers provides interoperability between which frameworks?
Answer: tensorflow 2 . 0 and pytorch

>>> from transformers import pipeline
>>> nlp = pipeline("fill-mask")
>>> from pprint import pprint
>>> pprint(nlp(f"HuggingFace is creating a {nlp.tokenizer.mask_token} that the community uses to solve NLP tasks."))
[{'score': 0.1792745739221573,
  'sequence': '<s>HuggingFace is creating a tool that the community uses to '
              'solve NLP tasks.</s>',
  'token': 3944,
  'token_str': 'Ġtool'},
 {'score': 0.11349421739578247,
  'sequence': '<s>HuggingFace is creating a framework that the community uses '
              'to solve NLP tasks.</s>',
  'token': 7208,
  'token_str': 'Ġframework'},
 {'score': 0.05243554711341858,
  'sequence': '<s>HuggingFace is creating a library that the community uses to '
              'solve NLP tasks.</s>',
  'token': 5560,
  'token_str': 'Ġlibrary'},
 {'score': 0.03493533283472061,
  'sequence': '<s>HuggingFace is creating a database that the community uses '
              'to solve NLP tasks.</s>',
  'token': 8503,
  'token_str': 'Ġdatabase'},
 {'score': 0.02860250137746334,
  'sequence': '<s>HuggingFace is creating a prototype that the community uses '
              'to solve NLP tasks.</s>',
  'token': 17715,
  'token_str': 'Ġprototype'}]

>>> from transformers import AutoModelWithLMHead, AutoTokenizer
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("distilbert-base-cased")
>>> model = AutoModelWithLMHead.from_pretrained("distilbert-base-cased")

>>> sequence = f"Distilled models are smaller than the models they mimic. Using them instead of the large versions would help {tokenizer.mask_token} our carbon footprint."

>>> input = tokenizer.encode(sequence, return_tensors="pt")
>>> mask_token_index = torch.where(input == tokenizer.mask_token_id)[1]

>>> token_logits = model(input).logits
>>> mask_token_logits = token_logits[0, mask_token_index, :]

>>> top_5_tokens = torch.topk(mask_token_logits, 5, dim=1).indices[0].tolist()

>>> for token in top_5_tokens:
...     print(sequence.replace(tokenizer.mask_token, tokenizer.decode([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 AutoModelWithLMHead, AutoTokenizer, top_k_top_p_filtering
>>> import torch
>>> from torch.nn import functional as F

>>> tokenizer = AutoTokenizer.from_pretrained("gpt2")
>>> model = AutoModelWithLMHead.from_pretrained("gpt2")

>>> sequence = f"Hugging Face is based in DUMBO, New York City, and"

>>> input_ids = tokenizer.encode(sequence, return_tensors="pt")

>>> # get logits of last hidden state
>>> next_token_logits = model(input_ids).logits[:, -1, :]

>>> # filter
>>> filtered_next_token_logits = top_k_top_p_filtering(next_token_logits, top_k=50, top_p=1.0)

>>> # sample
>>> probs = F.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)
Hugging Face is based in DUMBO, New York City, and has

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 pipeline
nlp = 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."

>>> print(nlp(sequence))
[
    {'word': 'Hu', 'score': 0.9995632767677307, 'entity': 'I-ORG'},
    {'word': '##gging', 'score': 0.9915938973426819, 'entity': 'I-ORG'},
    {'word': 'Face', 'score': 0.9982671737670898, 'entity': 'I-ORG'},
    {'word': 'Inc', 'score': 0.9994403719902039, 'entity': 'I-ORG'},
    {'word': 'New', 'score': 0.9994346499443054, 'entity': 'I-LOC'},
    {'word': 'York', 'score': 0.9993270635604858, 'entity': 'I-LOC'},
    {'word': 'City', 'score': 0.9993864893913269, 'entity': 'I-LOC'},
    {'word': 'D', 'score': 0.9825621843338013, 'entity': 'I-LOC'},
    {'word': '##UM', 'score': 0.936983048915863, 'entity': 'I-LOC'},
    {'word': '##BO', 'score': 0.8987102508544922, 'entity': 'I-LOC'},
    {'word': 'Manhattan', 'score': 0.9758241176605225, 'entity': 'I-LOC'},
    {'word': 'Bridge', 'score': 0.990249514579773, 'entity': 'I-LOC'}
]

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. She is believed to still be married to four men.'}]

from transformers import AutoModelWithLMHead, AutoTokenizer
model = AutoModelWithLMHead.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.encode("summarize: " + ARTICLE, return_tensors="pt", max_length=512)
outputs = model.generate(inputs, max_length=150, min_length=40, length_penalty=2.0, num_beams=4, 	early_stopping=True)

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 AutoModelWithLMHead, AutoTokenizer
model = AutoModelWithLMHead.from_pretrained("t5-base")
tokenizer = AutoTokenizer.from_pretrained("t5-base")
inputs = tokenizer.encode("translate English to German: Hugging Face is a technology company based in New York and Paris", return_tensors="pt")
outputs = model.generate(inputs, max_length=40, num_beams=4, early_stopping=True)

from transformers import pipeline, AutoModelWithLMHead, AutoTokenizer
model = AutoModelWithLMHead.from_pretrained("Helsinki-NLP/opus-mt-en-zh")
tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-zh")
translation = pipeline("translation_en_to_zh", model=model, tokenizer=tokenizer)

text = "I like to study Data Science and Machine Learning"
translated_text = translation(text, max_length=40)[0]['translation_text']
print(translated_text)

我喜欢学习数据科学和机器学习

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')

>>> encoded_input = tokenizer("Hello, I'm a single sentence!")
>>> print(encoded_input)
{'input_ids': [101, 138, 18696, 155, 1942, 3190, 1144, 1572, 13745, 1104, 159, 9664, 2107, 102],
 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}

>>> tokenizer.decode(encoded_input["input_ids"])
"[CLS] Hello, I'm a single sentence! [SEP]"

>>> batch_sentences = ["Hello I'm a single sentence",
...                    "And another sentence",
...                    "And the very very last one"]
>>> encoded_inputs = tokenizer(batch_sentences)
>>> print(encoded_inputs)
{'input_ids': [[101, 8667, 146, 112, 182, 170, 1423, 5650, 102],
               [101, 1262, 1330, 5650, 102],
               [101, 1262, 1103, 1304, 1304, 1314, 1141, 102]],
 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0],
                    [0, 0, 0, 0, 0],
                    [0, 0, 0, 0, 0, 0, 0, 0]],
 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1],
                    [1, 1, 1, 1, 1],
                    [1, 1, 1, 1, 1, 1, 1, 1]]}

>>> batch = tokenizer(batch_sentences, padding=True, truncation=True, return_tensors="pt")
>>> print(batch)
{'input_ids': tensor([[ 101, 8667,  146,  112,  182,  170, 1423, 5650,  102],
                      [ 101, 1262, 1330, 5650,  102,    0,    0,    0,    0],
                      [ 101, 1262, 1103, 1304, 1304, 1314, 1141,  102,    0]]),
 'token_type_ids': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0],
                           [0, 0, 0, 0, 0, 0, 0, 0, 0],
                           [0, 0, 0, 0, 0, 0, 0, 0, 0]]),
 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1],
                           [1, 1, 1, 1, 1, 0, 0, 0, 0],
                           [1, 1, 1, 1, 1, 1, 1, 1, 0]])}

>>> encoded_input = tokenizer("How old are you?", "I'm 6 years old")
>>> print(encoded_input)
{'input_ids': [101, 1731, 1385, 1132, 1128, 136, 102, 146, 112, 182, 127, 1201, 1385, 102],
 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1],
 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}

>>> tokenizer.decode(encoded_input["input_ids"])
"[CLS] How old are you? [SEP] I'm 6 years old [SEP]"

>>> batch_sentences = ["Hello I'm a single sentence",
...                    "And another sentence",
...                    "And the very very last one"]
>>> batch_of_second_sentences = ["I'm a sentence that goes with the first sentence",
...                              "And I should be encoded with the second sentence",
...                              "And I go with the very last one"]
>>> encoded_inputs = tokenizer(batch_sentences, batch_of_second_sentences)
>>> print(encoded_inputs)
{'input_ids': [[101, 8667, 146, 112, 182, 170, 1423, 5650, 102, 146, 112, 182, 170, 5650, 1115, 2947, 1114, 1103, 1148, 5650, 102],
               [101, 1262, 1330, 5650, 102, 1262, 146, 1431, 1129, 12544, 1114, 1103, 1248, 5650, 102],
               [101, 1262, 1103, 1304, 1304, 1314, 1141, 102, 1262, 146, 1301, 1114, 1103, 1304, 1314, 1141, 102]],
'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                   [0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                   [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1]],
'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                   [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                   [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]}

>>> for ids in encoded_inputs["input_ids"]:
>>>     print(tokenizer.decode(ids))
[CLS] Hello I'm a single sentence [SEP] I'm a sentence that goes with the first sentence [SEP]
[CLS] And another sentence [SEP] And I should be encoded with the second sentence [SEP]
[CLS] And the very very last one [SEP] And I go with the very last one [SEP]

batch = tokenizer(batch_sentences, batch_of_second_sentences, padding=True, truncation=True, return_tensors="pt")

>>> encoded_input = tokenizer(["Hello", "I'm", "a", "single", "sentence"], is_split_into_words=True)
>>> print(encoded_input)
{'input_ids': [101, 8667, 146, 112, 182, 170, 1423, 5650, 102],
 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0],
 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1]}

batch_sentences = [["Hello", "I'm", "a", "single", "sentence"],
                   ["And", "another", "sentence"],
                   ["And", "the", "very", "very", "last", "one"]]
encoded_inputs = tokenizer(batch_sentences, is_split_into_words=True)

batch_of_second_sentences = [["I'm", "a", "sentence", "that", "goes", "with", "the", "first", "sentence"],
                             ["And", "I", "should", "be", "encoded", "with", "the", "second", "sentence"],
                             ["And", "I", "go", "with", "the", "very", "last", "one"]]
encoded_inputs = tokenizer(batch_sentences, batch_of_second_sentences, is_split_into_words=True)

batch = tokenizer(batch_sentences,
                  batch_of_second_sentences,
                  is_split_into_words=True,
                  padding=True,
                  truncation=True,
                  return_tensors="pt")

BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)

from transformers import BertForSequenceClassification
model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
model.train()

no_decay = ['bias', 'LayerNorm.weight']
optimizer_grouped_parameters = [
    {'params': [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01},
    {'params': [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}
]
optimizer = AdamW(optimizer_grouped_parameters, lr=1e-5)

from transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
text_batch = ["I love Pixar.", "I don't care for Pixar."]
encoding = tokenizer(text_batch, return_tensors='pt', padding=True, truncation=True)
input_ids = encoding['input_ids']
attention_mask = encoding['attention_mask']

labels = torch.tensor([1,0]).unsqueeze(0)
outputs = model(input_ids, attention_mask=attention_mask, labels=labels)
loss = outputs.loss
loss.backward()
optimizer.step()

from torch.nn import functional as F
labels = torch.tensor([1,0])
outputs = model(input_ids, attention_mask=attention_mask)
loss = F.cross_entropy(outputs.logits, labels)
loss.backward()
optimizer.step()

from transformers import get_linear_schedule_with_warmup
scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps, num_train_steps)

loss.backward()
optimizer.step()
scheduler.step()

for param in model.base_model.parameters():
    param.requires_grad = False