File size: 285 Bytes
5fa1a76 |
1 2 3 4 5 6 7 8 |
Preprocess
The next step is to load a DistilGPT2 tokenizer to process the text subfield:
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
You'll notice from the example above, the text field is actually nested inside answers. |