Kasabian92 commited on
Commit
db66f70
1 Parent(s): 26c1466

Add Tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +53 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "46080": {
28
+ "content": "<|im_end|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [
37
+ "<unk>",
38
+ "<s>",
39
+ "</s>"
40
+ ],
41
+ "bos_token": "<s>",
42
+ "clean_up_tokenization_spaces": false,
43
+ "eos_token": "<|im_end|>",
44
+ "legacy": true,
45
+ "model_max_length": 1000000000000000019884624838656,
46
+ "pad_token": "</s>",
47
+ "sp_model_kwargs": {},
48
+ "spaces_between_special_tokens": false,
49
+ "tokenizer_class": "LlamaTokenizer",
50
+ "truncation_side": "left",
51
+ "unk_token": "<unk>",
52
+ "use_default_system_prompt": true
53
+ }