CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutSign UpSign In
huggingface

Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place. Commercial Alternative to JupyterHub.

GitHub Repository: huggingface/notebooks
Path: blob/main/course/videos/offset_mapping.ipynb
Views: 2542
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/3umI3tm27Vw?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 AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("bert-base-cased") print(tokenizer("Let's talk about tokenizers superpowers.")["input_ids"]) print(tokenizer("Let's talk about tokenizers superpowers.")["input_ids"])
encoding = tokenizer("Let's talk about tokenizers superpowers.") print(encoding.tokens()) print(encoding.word_ids())
encoding = tokenizer( "Let's talk about tokenizers superpowers.", return_offsets_mapping=True ) print(encoding.tokens()) print(encoding["offset_mapping"])