armandnlp commited on
Commit
2543b08
1 Parent(s): 1cbcabe

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|action|>": 50275,
3
+ "<|belief|>": 50262,
4
+ "<|context|>": 50286,
5
+ "<|endofaction|>": 50277,
6
+ "<|endofbelief|>": 50292,
7
+ "<|endofcontext|>": 50259,
8
+ "<|endofresponse|>": 50285,
9
+ "<|endofuseremotion|>": 50289,
10
+ "<|response|>": 50281,
11
+ "<|system|>": 50280,
12
+ "<|useremotion|>": 50270,
13
+ "<|user|>": 50271,
14
+ "[address]": 50257,
15
+ "[area]": 50272,
16
+ "[arriveby]": 50294,
17
+ "[bookday]": 50267,
18
+ "[bookpeople]": 50291,
19
+ "[bookstay]": 50273,
20
+ "[booktime]": 50284,
21
+ "[choice]": 50290,
22
+ "[day]": 50266,
23
+ "[department]": 50258,
24
+ "[departure]": 50261,
25
+ "[destination]": 50263,
26
+ "[duration]": 50287,
27
+ "[entrancefee]": 50265,
28
+ "[food]": 50274,
29
+ "[leaveat]": 50264,
30
+ "[name]": 50269,
31
+ "[openhours]": 50268,
32
+ "[phone]": 50282,
33
+ "[postcode]": 50283,
34
+ "[price]": 50278,
35
+ "[pricerange]": 50279,
36
+ "[ref]": 50293,
37
+ "[stars]": 50260,
38
+ "[trainid]": 50276,
39
+ "[type]": 50288
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[address]",
4
+ "[department]",
5
+ "<|endofcontext|>",
6
+ "[stars]",
7
+ "[departure]",
8
+ "<|belief|>",
9
+ "[destination]",
10
+ "[leaveat]",
11
+ "[entrancefee]",
12
+ "[day]",
13
+ "[bookday]",
14
+ "[openhours]",
15
+ "[name]",
16
+ "<|useremotion|>",
17
+ "<|user|>",
18
+ "[area]",
19
+ "[bookstay]",
20
+ "[food]",
21
+ "<|action|>",
22
+ "[trainid]",
23
+ "<|endofaction|>",
24
+ "[price]",
25
+ "[pricerange]",
26
+ "<|system|>",
27
+ "<|response|>",
28
+ "[phone]",
29
+ "[postcode]",
30
+ "[booktime]",
31
+ "<|endofresponse|>",
32
+ "<|context|>",
33
+ "[duration]",
34
+ "[type]",
35
+ "<|endofuseremotion|>",
36
+ "[choice]",
37
+ "[bookpeople]",
38
+ "<|endofbelief|>",
39
+ "[ref]",
40
+ "[arriveby]"
41
+ ],
42
+ "bos_token": {
43
+ "content": "<|endoftext|>",
44
+ "lstrip": false,
45
+ "normalized": true,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ },
49
+ "eos_token": {
50
+ "content": "<|endoftext|>",
51
+ "lstrip": false,
52
+ "normalized": true,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "pad_token": {
57
+ "content": "<|endoftext|>",
58
+ "lstrip": false,
59
+ "normalized": true,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ },
63
+ "unk_token": {
64
+ "content": "<|endoftext|>",
65
+ "lstrip": false,
66
+ "normalized": true,
67
+ "rstrip": false,
68
+ "single_word": false
69
+ }
70
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,364 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "[address]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "[department]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|endofcontext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "[stars]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50261": {
45
+ "content": "[departure]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50262": {
53
+ "content": "<|belief|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50263": {
61
+ "content": "[destination]",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50264": {
69
+ "content": "[leaveat]",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "50265": {
77
+ "content": "[entrancefee]",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "50266": {
85
+ "content": "[day]",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "50267": {
93
+ "content": "[bookday]",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "50268": {
101
+ "content": "[openhours]",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "50269": {
109
+ "content": "[name]",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "50270": {
117
+ "content": "<|useremotion|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "50271": {
125
+ "content": "<|user|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "50272": {
133
+ "content": "[area]",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "50273": {
141
+ "content": "[bookstay]",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "50274": {
149
+ "content": "[food]",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "50275": {
157
+ "content": "<|action|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "50276": {
165
+ "content": "[trainid]",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "50277": {
173
+ "content": "<|endofaction|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "50278": {
181
+ "content": "[price]",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "50279": {
189
+ "content": "[pricerange]",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "50280": {
197
+ "content": "<|system|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "50281": {
205
+ "content": "<|response|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "50282": {
213
+ "content": "[phone]",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "50283": {
221
+ "content": "[postcode]",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "50284": {
229
+ "content": "[booktime]",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "50285": {
237
+ "content": "<|endofresponse|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "50286": {
245
+ "content": "<|context|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "50287": {
253
+ "content": "[duration]",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "50288": {
261
+ "content": "[type]",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "50289": {
269
+ "content": "<|endofuseremotion|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "50290": {
277
+ "content": "[choice]",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "50291": {
285
+ "content": "[bookpeople]",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "50292": {
293
+ "content": "<|endofbelief|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "50293": {
301
+ "content": "[ref]",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "50294": {
309
+ "content": "[arriveby]",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ }
316
+ },
317
+ "additional_special_tokens": [
318
+ "[address]",
319
+ "[department]",
320
+ "<|endofcontext|>",
321
+ "[stars]",
322
+ "[departure]",
323
+ "<|belief|>",
324
+ "[destination]",
325
+ "[leaveat]",
326
+ "[entrancefee]",
327
+ "[day]",
328
+ "[bookday]",
329
+ "[openhours]",
330
+ "[name]",
331
+ "<|useremotion|>",
332
+ "<|user|>",
333
+ "[area]",
334
+ "[bookstay]",
335
+ "[food]",
336
+ "<|action|>",
337
+ "[trainid]",
338
+ "<|endofaction|>",
339
+ "[price]",
340
+ "[pricerange]",
341
+ "<|system|>",
342
+ "<|response|>",
343
+ "[phone]",
344
+ "[postcode]",
345
+ "[booktime]",
346
+ "<|endofresponse|>",
347
+ "<|context|>",
348
+ "[duration]",
349
+ "[type]",
350
+ "<|endofuseremotion|>",
351
+ "[choice]",
352
+ "[bookpeople]",
353
+ "<|endofbelief|>",
354
+ "[ref]",
355
+ "[arriveby]"
356
+ ],
357
+ "bos_token": "<|endoftext|>",
358
+ "clean_up_tokenization_spaces": true,
359
+ "eos_token": "<|endoftext|>",
360
+ "model_max_length": 1024,
361
+ "pad_token": "<|endoftext|>",
362
+ "tokenizer_class": "GPT2Tokenizer",
363
+ "unk_token": "<|endoftext|>"
364
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff