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

In [ ]:

#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/NURcDHhYe98?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

Out[ ]:

Install the Transformers and Datasets libraries to run this notebook.

In [ ]:

! pip install datasets transformers[sentencepiece]

In [ ]:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("gpt2")
tokenizer = AutoTokenizer.from_pretrained("gpt2")

inputs = tokenizer("Hugging Face is a startup based in New York City and Paris",
                   return_tensors="pt")

loss = model(input_ids=inputs["input_ids"],
             labels=inputs["input_ids"]).loss

ppl = torch.exp(loss)

print(f"Perplexity: {ppl.item():.2f}")

In [ ]: