nanom commited on
Commit
db2dea0
1 Parent(s): f23c57b

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +36 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +115 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|talk|>",
4
+ "<|ax1|>",
5
+ "<|ax2|>",
6
+ "<|ax3|>",
7
+ "<|ax4|>",
8
+ "<|ax5|>",
9
+ "<|ax6|>",
10
+ "<|ax7|>",
11
+ "<|ax8|>",
12
+ "<|ax9|>"
13
+ ],
14
+ "bos_token": {
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "eos_token": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": "<|endoftext|>",
29
+ "unk_token": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|talk|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|ax1|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|ax2|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|ax3|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<|ax4|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<|ax5|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<|ax6|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<|ax7|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|ax8|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<|ax9|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50256": {
86
+ "content": "<|endoftext|>",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ }
93
+ },
94
+ "additional_special_tokens": [
95
+ "<|talk|>",
96
+ "<|ax1|>",
97
+ "<|ax2|>",
98
+ "<|ax3|>",
99
+ "<|ax4|>",
100
+ "<|ax5|>",
101
+ "<|ax6|>",
102
+ "<|ax7|>",
103
+ "<|ax8|>",
104
+ "<|ax9|>"
105
+ ],
106
+ "bos_token": "<|endoftext|>",
107
+ "clean_up_tokenization_spaces": true,
108
+ "eos_token": "<|endoftext|>",
109
+ "errors": "replace",
110
+ "full_tokenizer_file": null,
111
+ "model_max_length": 1000000000000000019884624838656,
112
+ "pad_token": "<|endoftext|>",
113
+ "tokenizer_class": "GPT2Tokenizer",
114
+ "unk_token": "<|endoftext|>"
115
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff