Views
No views yet
1from tokenizers import Tokenizer
2from perovskite_tokenizer import PerovskiteTokenizer
3
4# Load tokenizer
5tokenizer = Tokenizer.from_file("tokenizer.json")
6
7# Tokenize a formula
8result = tokenizer.encode("CsPbI3")
9print(result.tokens) # ['[CLS]', 'Cs', 'Pb', 'I', '3', '[SEP]']