codys12 commited on
Commit
49b28d6
β€’
1 Parent(s): 3673822

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +15 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +108 -0
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ ">>>>>>>",
8
+ "=======",
9
+ "<<<<<<<"
10
+ ],
11
+ "bos_token": "<s>",
12
+ "eos_token": "</s>",
13
+ "pad_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32007": {
28
+ "content": "▁<PRE>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32008": {
36
+ "content": "▁<SUF>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32009": {
44
+ "content": "▁<MID>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32010": {
52
+ "content": "▁<EOT>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32016": {
60
+ "content": ">>>>>>>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32017": {
68
+ "content": "=======",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32018": {
76
+ "content": "<<<<<<<",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ }
83
+ },
84
+ "additional_special_tokens": [
85
+ "▁<PRE>",
86
+ "▁<MID>",
87
+ "▁<SUF>",
88
+ "▁<EOT>",
89
+ ">>>>>>>",
90
+ "=======",
91
+ "<<<<<<<"
92
+ ],
93
+ "bos_token": "<s>",
94
+ "clean_up_tokenization_spaces": false,
95
+ "eos_token": "</s>",
96
+ "eot_token": "▁<EOT>",
97
+ "fill_token": "<FILL_ME>",
98
+ "legacy": null,
99
+ "middle_token": "▁<MID>",
100
+ "model_max_length": 1000000000000000019884624838656,
101
+ "pad_token": "</s>",
102
+ "prefix_token": "▁<PRE>",
103
+ "sp_model_kwargs": {},
104
+ "suffix_token": "▁<SUF>",
105
+ "tokenizer_class": "CodeLlamaTokenizer",
106
+ "unk_token": "<unk>",
107
+ "use_default_system_prompt": false
108
+ }