geekdom commited on
Commit
25808cf
1 Parent(s): 882853e

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<CLS>": 32000,
3
+ "<EOD>": 32002,
4
+ "<MASK>": 32003,
5
+ "<PAD>": 32004,
6
+ "<SEP>": 32001,
7
+ "[/bib]": 32010,
8
+ "[/bib_ref]": 32006,
9
+ "[/fig]": 32012,
10
+ "[/fig_ref]": 32008,
11
+ "[/formula]": 32016,
12
+ "[/table]": 32014,
13
+ "[bib]": 32009,
14
+ "[bib_ref]": 32005,
15
+ "[fig]": 32011,
16
+ "[fig_ref]": 32007,
17
+ "[formula]": 32015,
18
+ "[table]": 32013
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[bib_ref]",
4
+ "[/bib_ref]",
5
+ "[fig_ref]",
6
+ "[/fig_ref]",
7
+ "[bib]",
8
+ "[/bib]",
9
+ "[fig]",
10
+ "[/fig]",
11
+ "[table]",
12
+ "[/table]",
13
+ "[formula]",
14
+ "[/formula]"
15
+ ],
16
+ "bos_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "cls_token": "<CLS>",
24
+ "eos_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "mask_token": "<MASK>",
32
+ "pad_token": "</s>",
33
+ "sep_token": "<SEP>",
34
+ "unk_token": {
35
+ "content": "<unk>",
36
+ "lstrip": false,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
28
+ "content": "<CLS>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<SEP>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<EOD>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "<MASK>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<PAD>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "[bib_ref]",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "[/bib_ref]",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "[fig_ref]",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "[/fig_ref]",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "[bib]",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "[/bib]",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "[fig]",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "[/fig]",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "[table]",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "[/table]",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "[formula]",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32016": {
156
+ "content": "[/formula]",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ }
163
+ },
164
+ "additional_special_tokens": [
165
+ "[bib_ref]",
166
+ "[/bib_ref]",
167
+ "[fig_ref]",
168
+ "[/fig_ref]",
169
+ "[bib]",
170
+ "[/bib]",
171
+ "[fig]",
172
+ "[/fig]",
173
+ "[table]",
174
+ "[/table]",
175
+ "[formula]",
176
+ "[/formula]"
177
+ ],
178
+ "bos_token": "<s>",
179
+ "clean_up_tokenization_spaces": false,
180
+ "cls_token": "<CLS>",
181
+ "eos_token": "</s>",
182
+ "legacy": true,
183
+ "mask_token": "<MASK>",
184
+ "model_max_length": 1000000000000000019884624838656,
185
+ "pad_token": "<PAD>",
186
+ "sep_token": "<SEP>",
187
+ "sp_model_kwargs": {},
188
+ "tokenizer_class": "LlamaTokenizer",
189
+ "unk_token": "<unk>",
190
+ "use_default_system_prompt": false
191
+ }