허깅페이스 auto

an AutoClass automatically infers and loads the correct architecture from a given checkpoint

• The from_pretrained() method lets you quickly load a pretrained model for any architecture so you don’t have to devote time and resources to train a model from scratch

-In this tutorial, learn to:

Load a pretrained tokenizer.
Load a pretrained image processor
Load a pretrained feature extractor.
Load a pretrained processor.
Load a pretrained model.
Load a model as a backbone.

1) load a tokenizer with AutoTokenizer.from_pretrained():

• from transformers import AutoTokenizer
  tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")