File size: 384 Bytes
751936e
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14

import os
from transformers import LlamaTokenizer

CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
TOKENIZER_DIR = os.path.join(CURRENT_DIR, "tokenizer")

tokenizer = LlamaTokenizer.from_pretrained(TOKENIZER_DIR)

tokenizer.comments = "向原始LLaMA的词汇表中添加2w个中文词汇,针对原版LLaMA模型扩充了中文词表, 提升了中文编解码效率"