thisisHJLee commited on
Commit
a71e6ab
·
1 Parent(s): 76b305e

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "bos_token": "<|startoftext|>",
10
+ "eos_token": "<|endoftext|>",
11
+ "pad_token": "<|pad|>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<|pad|>",
7
+ "special_tokens_map_file": "C:\\Users\\hj.lee/.cache\\huggingface\\hub\\models--EleutherAI--polyglot-ko-1.3b\\snapshots\\711da2957fdae31202de86c51edbc0c7f433b9e5\\special_tokens_map.json",
8
+ "tokenizer_class": "PreTrainedTokenizerFast"
9
+ }