Hugging Face's logo

relik-ie
/
relik-reader-deberta-v3-small-cie-wikipedia

Feature Extraction
Transformers
Safetensors
relik-reader
custom_code
Model card Files Community
relik-ie commited on
Commit
d1eda7c
•
1 Parent(s): 1366114

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +104 -0
  2. special_tokens_map.json +154 -0
  3. spm.model +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +970 -0
added_tokens.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "--NME--": 128026,
3
+ "[E-0]": 128027,
4
+ "[E-10]": 128037,
5
+ "[E-11]": 128038,
6
+ "[E-12]": 128039,
7
+ "[E-13]": 128040,
8
+ "[E-14]": 128041,
9
+ "[E-15]": 128042,
10
+ "[E-16]": 128043,
11
+ "[E-17]": 128044,
12
+ "[E-18]": 128045,
13
+ "[E-19]": 128046,
14
+ "[E-1]": 128028,
15
+ "[E-20]": 128047,
16
+ "[E-21]": 128048,
17
+ "[E-22]": 128049,
18
+ "[E-23]": 128050,
19
+ "[E-24]": 128051,
20
+ "[E-25]": 128052,
21
+ "[E-26]": 128053,
22
+ "[E-27]": 128054,
23
+ "[E-28]": 128055,
24
+ "[E-29]": 128056,
25
+ "[E-2]": 128029,
26
+ "[E-30]": 128057,
27
+ "[E-31]": 128058,
28
+ "[E-32]": 128059,
29
+ "[E-33]": 128060,
30
+ "[E-34]": 128061,
31
+ "[E-35]": 128062,
32
+ "[E-36]": 128063,
33
+ "[E-37]": 128064,
34
+ "[E-38]": 128065,
35
+ "[E-39]": 128066,
36
+ "[E-3]": 128030,
37
+ "[E-40]": 128067,
38
+ "[E-41]": 128068,
39
+ "[E-42]": 128069,
40
+ "[E-43]": 128070,
41
+ "[E-44]": 128071,
42
+ "[E-45]": 128072,
43
+ "[E-46]": 128073,
44
+ "[E-47]": 128074,
45
+ "[E-48]": 128075,
46
+ "[E-49]": 128076,
47
+ "[E-4]": 128031,
48
+ "[E-50]": 128077,
49
+ "[E-51]": 128078,
50
+ "[E-52]": 128079,
51
+ "[E-53]": 128080,
52
+ "[E-54]": 128081,
53
+ "[E-55]": 128082,
54
+ "[E-56]": 128083,
55
+ "[E-57]": 128084,
56
+ "[E-58]": 128085,
57
+ "[E-59]": 128086,
58
+ "[E-5]": 128032,
59
+ "[E-60]": 128087,
60
+ "[E-61]": 128088,
61
+ "[E-62]": 128089,
62
+ "[E-63]": 128090,
63
+ "[E-64]": 128091,
64
+ "[E-65]": 128092,
65
+ "[E-66]": 128093,
66
+ "[E-67]": 128094,
67
+ "[E-68]": 128095,
68
+ "[E-69]": 128096,
69
+ "[E-6]": 128033,
70
+ "[E-70]": 128097,
71
+ "[E-71]": 128098,
72
+ "[E-72]": 128099,
73
+ "[E-73]": 128100,
74
+ "[E-74]": 128101,
75
+ "[E-7]": 128034,
76
+ "[E-8]": 128035,
77
+ "[E-9]": 128036,
78
+ "[MASK]": 128000,
79
+ "[R-0]": 128001,
80
+ "[R-10]": 128011,
81
+ "[R-11]": 128012,
82
+ "[R-12]": 128013,
83
+ "[R-13]": 128014,
84
+ "[R-14]": 128015,
85
+ "[R-15]": 128016,
86
+ "[R-16]": 128017,
87
+ "[R-17]": 128018,
88
+ "[R-18]": 128019,
89
+ "[R-19]": 128020,
90
+ "[R-1]": 128002,
91
+ "[R-20]": 128021,
92
+ "[R-21]": 128022,
93
+ "[R-22]": 128023,
94
+ "[R-23]": 128024,
95
+ "[R-24]": 128025,
96
+ "[R-2]": 128003,
97
+ "[R-3]": 128004,
98
+ "[R-4]": 128005,
99
+ "[R-5]": 128006,
100
+ "[R-6]": 128007,
101
+ "[R-7]": 128008,
102
+ "[R-8]": 128009,
103
+ "[R-9]": 128010
104
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[R-0]",
4
+ "[R-1]",
5
+ "[R-2]",
6
+ "[R-3]",
7
+ "[R-4]",
8
+ "[R-5]",
9
+ "[R-6]",
10
+ "[R-7]",
11
+ "[R-8]",
12
+ "[R-9]",
13
+ "[R-10]",
14
+ "[R-11]",
15
+ "[R-12]",
16
+ "[R-13]",
17
+ "[R-14]",
18
+ "[R-15]",
19
+ "[R-16]",
20
+ "[R-17]",
21
+ "[R-18]",
22
+ "[R-19]",
23
+ "[R-20]",
24
+ "[R-21]",
25
+ "[R-22]",
26
+ "[R-23]",
27
+ "[R-24]",
28
+ "--NME--",
29
+ "[E-0]",
30
+ "[E-1]",
31
+ "[E-2]",
32
+ "[E-3]",
33
+ "[E-4]",
34
+ "[E-5]",
35
+ "[E-6]",
36
+ "[E-7]",
37
+ "[E-8]",
38
+ "[E-9]",
39
+ "[E-10]",
40
+ "[E-11]",
41
+ "[E-12]",
42
+ "[E-13]",
43
+ "[E-14]",
44
+ "[E-15]",
45
+ "[E-16]",
46
+ "[E-17]",
47
+ "[E-18]",
48
+ "[E-19]",
49
+ "[E-20]",
50
+ "[E-21]",
51
+ "[E-22]",
52
+ "[E-23]",
53
+ "[E-24]",
54
+ "[E-25]",
55
+ "[E-26]",
56
+ "[E-27]",
57
+ "[E-28]",
58
+ "[E-29]",
59
+ "[E-30]",
60
+ "[E-31]",
61
+ "[E-32]",
62
+ "[E-33]",
63
+ "[E-34]",
64
+ "[E-35]",
65
+ "[E-36]",
66
+ "[E-37]",
67
+ "[E-38]",
68
+ "[E-39]",
69
+ "[E-40]",
70
+ "[E-41]",
71
+ "[E-42]",
72
+ "[E-43]",
73
+ "[E-44]",
74
+ "[E-45]",
75
+ "[E-46]",
76
+ "[E-47]",
77
+ "[E-48]",
78
+ "[E-49]",
79
+ "[E-50]",
80
+ "[E-51]",
81
+ "[E-52]",
82
+ "[E-53]",
83
+ "[E-54]",
84
+ "[E-55]",
85
+ "[E-56]",
86
+ "[E-57]",
87
+ "[E-58]",
88
+ "[E-59]",
89
+ "[E-60]",
90
+ "[E-61]",
91
+ "[E-62]",
92
+ "[E-63]",
93
+ "[E-64]",
94
+ "[E-65]",
95
+ "[E-66]",
96
+ "[E-67]",
97
+ "[E-68]",
98
+ "[E-69]",
99
+ "[E-70]",
100
+ "[E-71]",
101
+ "[E-72]",
102
+ "[E-73]",
103
+ "[E-74]"
104
+ ],
105
+ "bos_token": {
106
+ "content": "[CLS]",
107
+ "lstrip": false,
108
+ "normalized": false,
109
+ "rstrip": false,
110
+ "single_word": false
111
+ },
112
+ "cls_token": {
113
+ "content": "[CLS]",
114
+ "lstrip": false,
115
+ "normalized": false,
116
+ "rstrip": false,
117
+ "single_word": false
118
+ },
119
+ "eos_token": {
120
+ "content": "[SEP]",
121
+ "lstrip": false,
122
+ "normalized": false,
123
+ "rstrip": false,
124
+ "single_word": false
125
+ },
126
+ "mask_token": {
127
+ "content": "[MASK]",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false
132
+ },
133
+ "pad_token": {
134
+ "content": "[PAD]",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false
139
+ },
140
+ "sep_token": {
141
+ "content": "[SEP]",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false
146
+ },
147
+ "unk_token": {
148
+ "content": "[UNK]",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false
153
+ }
154
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,970 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128000": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128001": {
45
+ "content": "[R-0]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128002": {
53
+ "content": "[R-1]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128003": {
61
+ "content": "[R-2]",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128004": {
69
+ "content": "[R-3]",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128005": {
77
+ "content": "[R-4]",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128006": {
85
+ "content": "[R-5]",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128007": {
93
+ "content": "[R-6]",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128008": {
101
+ "content": "[R-7]",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128009": {
109
+ "content": "[R-8]",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128010": {
117
+ "content": "[R-9]",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128011": {
125
+ "content": "[R-10]",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128012": {
133
+ "content": "[R-11]",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128013": {
141
+ "content": "[R-12]",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128014": {
149
+ "content": "[R-13]",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128015": {
157
+ "content": "[R-14]",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128016": {
165
+ "content": "[R-15]",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128017": {
173
+ "content": "[R-16]",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128018": {
181
+ "content": "[R-17]",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128019": {
189
+ "content": "[R-18]",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128020": {
197
+ "content": "[R-19]",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128021": {
205
+ "content": "[R-20]",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128022": {
213
+ "content": "[R-21]",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128023": {
221
+ "content": "[R-22]",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128024": {
229
+ "content": "[R-23]",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128025": {
237
+ "content": "[R-24]",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128026": {
245
+ "content": "--NME--",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128027": {
253
+ "content": "[E-0]",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128028": {
261
+ "content": "[E-1]",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128029": {
269
+ "content": "[E-2]",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128030": {
277
+ "content": "[E-3]",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128031": {
285
+ "content": "[E-4]",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128032": {
293
+ "content": "[E-5]",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128033": {
301
+ "content": "[E-6]",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128034": {
309
+ "content": "[E-7]",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128035": {
317
+ "content": "[E-8]",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128036": {
325
+ "content": "[E-9]",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128037": {
333
+ "content": "[E-10]",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128038": {
341
+ "content": "[E-11]",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128039": {
349
+ "content": "[E-12]",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128040": {
357
+ "content": "[E-13]",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128041": {
365
+ "content": "[E-14]",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128042": {
373
+ "content": "[E-15]",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128043": {
381
+ "content": "[E-16]",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128044": {
389
+ "content": "[E-17]",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128045": {
397
+ "content": "[E-18]",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128046": {
405
+ "content": "[E-19]",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128047": {
413
+ "content": "[E-20]",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128048": {
421
+ "content": "[E-21]",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128049": {
429
+ "content": "[E-22]",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128050": {
437
+ "content": "[E-23]",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128051": {
445
+ "content": "[E-24]",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128052": {
453
+ "content": "[E-25]",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128053": {
461
+ "content": "[E-26]",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128054": {
469
+ "content": "[E-27]",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128055": {
477
+ "content": "[E-28]",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128056": {
485
+ "content": "[E-29]",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128057": {
493
+ "content": "[E-30]",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128058": {
501
+ "content": "[E-31]",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128059": {
509
+ "content": "[E-32]",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128060": {
517
+ "content": "[E-33]",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128061": {
525
+ "content": "[E-34]",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128062": {
533
+ "content": "[E-35]",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128063": {
541
+ "content": "[E-36]",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128064": {
549
+ "content": "[E-37]",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128065": {
557
+ "content": "[E-38]",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128066": {
565
+ "content": "[E-39]",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128067": {
573
+ "content": "[E-40]",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128068": {
581
+ "content": "[E-41]",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128069": {
589
+ "content": "[E-42]",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128070": {
597
+ "content": "[E-43]",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128071": {
605
+ "content": "[E-44]",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128072": {
613
+ "content": "[E-45]",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128073": {
621
+ "content": "[E-46]",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128074": {
629
+ "content": "[E-47]",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128075": {
637
+ "content": "[E-48]",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128076": {
645
+ "content": "[E-49]",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128077": {
653
+ "content": "[E-50]",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128078": {
661
+ "content": "[E-51]",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128079": {
669
+ "content": "[E-52]",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128080": {
677
+ "content": "[E-53]",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128081": {
685
+ "content": "[E-54]",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128082": {
693
+ "content": "[E-55]",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128083": {
701
+ "content": "[E-56]",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128084": {
709
+ "content": "[E-57]",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128085": {
717
+ "content": "[E-58]",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128086": {
725
+ "content": "[E-59]",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128087": {
733
+ "content": "[E-60]",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128088": {
741
+ "content": "[E-61]",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128089": {
749
+ "content": "[E-62]",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128090": {
757
+ "content": "[E-63]",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128091": {
765
+ "content": "[E-64]",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128092": {
773
+ "content": "[E-65]",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128093": {
781
+ "content": "[E-66]",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128094": {
789
+ "content": "[E-67]",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128095": {
797
+ "content": "[E-68]",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128096": {
805
+ "content": "[E-69]",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128097": {
813
+ "content": "[E-70]",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128098": {
821
+ "content": "[E-71]",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128099": {
829
+ "content": "[E-72]",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128100": {
837
+ "content": "[E-73]",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128101": {
845
+ "content": "[E-74]",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ }
852
+ },
853
+ "additional_special_tokens": [
854
+ "[R-0]",
855
+ "[R-1]",
856
+ "[R-2]",
857
+ "[R-3]",
858
+ "[R-4]",
859
+ "[R-5]",
860
+ "[R-6]",
861
+ "[R-7]",
862
+ "[R-8]",
863
+ "[R-9]",
864
+ "[R-10]",
865
+ "[R-11]",
866
+ "[R-12]",
867
+ "[R-13]",
868
+ "[R-14]",
869
+ "[R-15]",
870
+ "[R-16]",
871
+ "[R-17]",
872
+ "[R-18]",
873
+ "[R-19]",
874
+ "[R-20]",
875
+ "[R-21]",
876
+ "[R-22]",
877
+ "[R-23]",
878
+ "[R-24]",
879
+ "--NME--",
880
+ "[E-0]",
881
+ "[E-1]",
882
+ "[E-2]",
883
+ "[E-3]",
884
+ "[E-4]",
885
+ "[E-5]",
886
+ "[E-6]",
887
+ "[E-7]",
888
+ "[E-8]",
889
+ "[E-9]",
890
+ "[E-10]",
891
+ "[E-11]",
892
+ "[E-12]",
893
+ "[E-13]",
894
+ "[E-14]",
895
+ "[E-15]",
896
+ "[E-16]",
897
+ "[E-17]",
898
+ "[E-18]",
899
+ "[E-19]",
900
+ "[E-20]",
901
+ "[E-21]",
902
+ "[E-22]",
903
+ "[E-23]",
904
+ "[E-24]",
905
+ "[E-25]",
906
+ "[E-26]",
907
+ "[E-27]",
908
+ "[E-28]",
909
+ "[E-29]",
910
+ "[E-30]",
911
+ "[E-31]",
912
+ "[E-32]",
913
+ "[E-33]",
914
+ "[E-34]",
915
+ "[E-35]",
916
+ "[E-36]",
917
+ "[E-37]",
918
+ "[E-38]",
919
+ "[E-39]",
920
+ "[E-40]",
921
+ "[E-41]",
922
+ "[E-42]",
923
+ "[E-43]",
924
+ "[E-44]",
925
+ "[E-45]",
926
+ "[E-46]",
927
+ "[E-47]",
928
+ "[E-48]",
929
+ "[E-49]",
930
+ "[E-50]",
931
+ "[E-51]",
932
+ "[E-52]",
933
+ "[E-53]",
934
+ "[E-54]",
935
+ "[E-55]",
936
+ "[E-56]",
937
+ "[E-57]",
938
+ "[E-58]",
939
+ "[E-59]",
940
+ "[E-60]",
941
+ "[E-61]",
942
+ "[E-62]",
943
+ "[E-63]",
944
+ "[E-64]",
945
+ "[E-65]",
946
+ "[E-66]",
947
+ "[E-67]",
948
+ "[E-68]",
949
+ "[E-69]",
950
+ "[E-70]",
951
+ "[E-71]",
952
+ "[E-72]",
953
+ "[E-73]",
954
+ "[E-74]"
955
+ ],
956
+ "bos_token": "[CLS]",
957
+ "clean_up_tokenization_spaces": true,
958
+ "cls_token": "[CLS]",
959
+ "do_lower_case": false,
960
+ "eos_token": "[SEP]",
961
+ "mask_token": "[MASK]",
962
+ "model_max_length": 1000000000000000019884624838656,
963
+ "pad_token": "[PAD]",
964
+ "sep_token": "[SEP]",
965
+ "sp_model_kwargs": {},
966
+ "split_by_punct": false,
967
+ "tokenizer_class": "DebertaV2Tokenizer",
968
+ "unk_token": "[UNK]",
969
+ "vocab_type": "spm"
970
+ }