Hugging Face's logo

BGI-HangzhouAI
/
Genos-10B

Safetensors
mixtral
Model card Files
xet
Community
chenjh356 commited on
Commit
423fc92
·
verified ·
1 Parent(s): 26c691d

Upload tokenizer.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer.json +163 -0
tokenizer.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 10,
8
+ "content": "<CLS>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 11,
17
+ "content": "<SEP>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 12,
26
+ "content": "<EOD>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 13,
35
+ "content": "<MASK>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 14,
44
+ "content": "<PAD>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 15,
53
+ "content": "<s>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 16,
62
+ "content": "</s>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 17,
71
+ "content": "<UNK>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ }
78
+ ],
79
+ "normalizer": null,
80
+ "pre_tokenizer": {
81
+ "type": "ByteLevel",
82
+ "add_prefix_space": false,
83
+ "trim_offsets": true,
84
+ "use_regex": true
85
+ },
86
+ "post_processor": {
87
+ "type": "TemplateProcessing",
88
+ "single": [
89
+ {
90
+ "Sequence": {
91
+ "id": "A",
92
+ "type_id": 0
93
+ }
94
+ }
95
+ ],
96
+ "pair": [
97
+ {
98
+ "Sequence": {
99
+ "id": "A",
100
+ "type_id": 0
101
+ }
102
+ },
103
+ {
104
+ "Sequence": {
105
+ "id": "B",
106
+ "type_id": 0
107
+ }
108
+ }
109
+ ],
110
+ "special_tokens": {
111
+ "<CLS>": {
112
+ "id": "<CLS>",
113
+ "ids": [
114
+ 10
115
+ ],
116
+ "tokens": [
117
+ "<CLS>"
118
+ ]
119
+ },
120
+ "<SEP>": {
121
+ "id": "<SEP>",
122
+ "ids": [
123
+ 11
124
+ ],
125
+ "tokens": [
126
+ "<SEP>"
127
+ ]
128
+ }
129
+ }
130
+ },
131
+ "decoder": null,
132
+ "model": {
133
+ "type": "BPE",
134
+ "dropout": null,
135
+ "unk_token": "<UNK>",
136
+ "continuing_subword_prefix": null,
137
+ "end_of_word_suffix": null,
138
+ "fuse_unk": false,
139
+ "byte_fallback": false,
140
+ "ignore_merges": false,
141
+ "vocab": {
142
+ "[PAD]": 0,
143
+ "[UNK]": 1,
144
+ "[CLS]": 2,
145
+ "[SEP]": 3,
146
+ "[MASK]": 4,
147
+ "C": 5,
148
+ "G": 6,
149
+ "T": 7,
150
+ "A": 8,
151
+ "N": 9,
152
+ "<CLS>": 10,
153
+ "<SEP>": 11,
154
+ "<EOD>": 12,
155
+ "<MASK>": 13,
156
+ "<PAD>": 14,
157
+ "<s>": 15,
158
+ "</s>": 16,
159
+ "<UNK>": 17
160
+ },
161
+ "merges": []
162
+ }
163
+ }