File size: 240 Bytes
44c5827
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
import tiktoken
try:
    tokenizer = tiktoken.get_encoding("cl100k_base")
except:
    tokenizer = tiktoken.get_encoding("gpt2")

# get the number of tokens in a text
def count_tokens(text: str) -> int:
    return len(tokenizer.encode(text))