napatswift commited on
Commit
730f07b
1 Parent(s): bde9841

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</amount>": 31867,
3
+ "</fiscal_year>": 31868,
4
+ "</fiscal_year_end_year>": 31869,
5
+ "</fiscal_year_year>": 31870,
6
+ "</line_item_amount>": 31871,
7
+ "</line_item_bullet>": 31872,
8
+ "</line_item_children>": 31873,
9
+ "</line_item_fiscal_years>": 31874,
10
+ "</line_item_name>": 31875,
11
+ "</line_item_root>": 31876,
12
+ "</root>": 31866,
13
+ "</s>": 1,
14
+ "<amount>": 31877,
15
+ "<begin>": 31878,
16
+ "<begin_indent>": 31879,
17
+ "<big_sep>": 31880,
18
+ "<fiscal_year>": 31881,
19
+ "<fiscal_year_end_year>": 31882,
20
+ "<fiscal_year_year>": 31883,
21
+ "<line_item_amount>": 31884,
22
+ "<line_item_bullet>": 31885,
23
+ "<line_item_children>": 31886,
24
+ "<line_item_fiscal_years>": 31887,
25
+ "<line_item_name>": 31888,
26
+ "<line_item_root>": 31889,
27
+ "<pad>": 0,
28
+ "<root>": 31865,
29
+ "<unk>": 2
30
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<pad>",
4
+ "</s>",
5
+ "<unk>"
6
+ ],
7
+ "eos_token": "</s>",
8
+ "pad_token": "<pad>",
9
+ "unk_token": "<unk>"
10
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:943e54fe3508d321697daaf197abf6d87c7fe305dc5669abe82e26e38cb165f1
3
+ size 813480
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
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": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "31865": {
28
+ "content": "<root>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "31866": {
36
+ "content": "</root>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "31867": {
44
+ "content": "</amount>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "31868": {
52
+ "content": "</fiscal_year>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "31869": {
60
+ "content": "</fiscal_year_end_year>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "31870": {
68
+ "content": "</fiscal_year_year>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "31871": {
76
+ "content": "</line_item_amount>",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "31872": {
84
+ "content": "</line_item_bullet>",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "31873": {
92
+ "content": "</line_item_children>",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "31874": {
100
+ "content": "</line_item_fiscal_years>",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "31875": {
108
+ "content": "</line_item_name>",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "31876": {
116
+ "content": "</line_item_root>",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "31877": {
124
+ "content": "<amount>",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "31878": {
132
+ "content": "<begin>",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "31879": {
140
+ "content": "<begin_indent>",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "31880": {
148
+ "content": "<big_sep>",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "31881": {
156
+ "content": "<fiscal_year>",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "31882": {
164
+ "content": "<fiscal_year_end_year>",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "31883": {
172
+ "content": "<fiscal_year_year>",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "31884": {
180
+ "content": "<line_item_amount>",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "31885": {
188
+ "content": "<line_item_bullet>",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "31886": {
196
+ "content": "<line_item_children>",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "31887": {
204
+ "content": "<line_item_fiscal_years>",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "31888": {
212
+ "content": "<line_item_name>",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "31889": {
220
+ "content": "<line_item_root>",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ }
227
+ },
228
+ "additional_special_tokens": [
229
+ "<pad>",
230
+ "</s>",
231
+ "<unk>"
232
+ ],
233
+ "clean_up_tokenization_spaces": true,
234
+ "eos_token": "</s>",
235
+ "extra_ids": 0,
236
+ "legacy": true,
237
+ "max_length": 1100,
238
+ "model_max_length": 1000000000000000019884624838656,
239
+ "pad_token": "<pad>",
240
+ "sp_model_kwargs": {},
241
+ "stride": 0,
242
+ "tokenizer_class": "T5Tokenizer",
243
+ "truncation_side": "right",
244
+ "truncation_strategy": "longest_first",
245
+ "unk_token": "<unk>"
246
+ }