File size: 291 Bytes
f4973d4
 
 
 
d27a756
 
 
 
 
 
 
 
f4973d4
1
2
3
4
5
6
7
8
9
10
11
12
13

from vocab.gpt_35_turbo import tokenizer


text = "你好,请告诉我聚乙烯是什么"
encoding = tokenizer.encode(text)


print(tokenizer.decode([6744]))
print(tokenizer.convert_ids_to_tokens([6744]))

print(tokenizer.decode([100256]))
print(tokenizer.convert_ids_to_tokens([100256]))