#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/P-rZWqcB6CE?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

! pip install datasets transformers[sentencepiece]

from transformers import AutoTokenizer

checkpoint = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
sequences = [
    "I've been waiting for a HuggingFace course my whole life.",
    "This course is amazing!",
]
batch = tokenizer(sequences, padding=True, truncation=True, return_tensors="tf")

from transformers import AutoTokenizer

checkpoint = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
tokenizer("My name is Sylvain.", "I work at Hugging Face.")

from transformers import AutoTokenizer

checkpoint = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
tokenizer(
    ["My name is Sylvain.", "Going to the cinema."],
    ["I work at Hugging Face.", "This movie is great."],
    padding=True
)

from transformers import TFAutoModelForSequenceClassification, AutoTokenizer

checkpoint = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
batch = tokenizer(
    ["My name is Sylvain.", "Going to the cinema."],
    ["I work at Hugging Face.", "This movie is great."],
    padding=True,
    return_tensors="tf",
)

model = TFAutoModelForSequenceClassification.from_pretrained(checkpoint)
outputs = model(**batch)