This screencast walks through how to predict which #TidyTuesday NYT bestsellers will be on the list for a long time vs. a short time, based on author names. We walk through how to use wordpiece tokenization for these names, and how to deploy your model as a REST API. Check out the code on my blog: juliasilge.com...
NOTE: I misspoke about how the wordpiece tokenization is implemented; it uses the pre-trained vocabulary from BERT.
Негізгі бет Predict NYT bestsellers with wordpiece tokenization
Пікірлер: 10