The-matt commited on
Commit
0747781
1 Parent(s): 5ad42b9

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +16 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +88 -0
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "<|sep|>",
7
+ "<|endoftext|>",
8
+ "<|acc|>",
9
+ "<|rrn|>",
10
+ "<|tel|>"
11
+ ],
12
+ "bos_token": "<s>",
13
+ "eos_token": "</s>",
14
+ "pad_token": "</s>",
15
+ "unk_token": "<unk>"
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "46331": {
28
+ "content": "<|sep|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "46332": {
36
+ "content": "<|endoftext|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "46333": {
44
+ "content": "<|acc|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "46334": {
52
+ "content": "<|rrn|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "46335": {
60
+ "content": "<|tel|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<unk>",
70
+ "<s>",
71
+ "</s>",
72
+ "<|sep|>",
73
+ "<|endoftext|>",
74
+ "<|acc|>",
75
+ "<|rrn|>",
76
+ "<|tel|>"
77
+ ],
78
+ "bos_token": "<s>",
79
+ "clean_up_tokenization_spaces": false,
80
+ "eos_token": "</s>",
81
+ "legacy": false,
82
+ "model_max_length": 1000000000000000019884624838656,
83
+ "pad_token": "</s>",
84
+ "sp_model_kwargs": {},
85
+ "tokenizer_class": "LlamaTokenizer",
86
+ "unk_token": "<unk>",
87
+ "use_default_system_prompt": true
88
+ }