dongim04 commited on
Commit
9924a8e
·
verified ·
1 Parent(s): 8fe2390

Upload tokenizer

Browse files
Files changed (1) hide show
  1. vocab.json +42 -42
vocab.json CHANGED
@@ -15,9 +15,9 @@
15
  "主": 255,
16
  "么": 58,
17
  "之": 226,
18
- "乌": 192,
19
  "也": 76,
20
- "了": 133,
21
  "事": 19,
22
  "二": 130,
23
  "于": 356,
@@ -44,7 +44,7 @@
44
  "佛": 197,
45
  "作": 134,
46
  "你": 34,
47
- "信": 262,
48
  "候": 281,
49
  "做": 157,
50
  "停": 299,
@@ -61,13 +61,13 @@
61
  "内": 364,
62
  "再": 120,
63
  "冲": 149,
64
- "决": 67,
65
  "准": 169,
66
  "减": 256,
67
  "几": 61,
68
- "出": 351,
69
  "分": 360,
70
- "刚": 353,
71
  "别": 322,
72
  "到": 331,
73
  "前": 217,
@@ -101,31 +101,31 @@
101
  "名": 115,
102
  "后": 368,
103
  "吧": 139,
104
- "听": 53,
105
  "吼": 163,
106
  "呃": 107,
107
  "呢": 145,
108
  "周": 265,
109
  "和": 184,
110
  "哎": 327,
111
- "哦": 96,
112
  "啊": 23,
113
  "啥": 367,
114
- "喜": 245,
115
  "嗯": 3,
116
  "嘛": 44,
117
  "回": 20,
118
  "因": 84,
119
  "园": 55,
120
  "在": 232,
121
- "地": 315,
122
  "壳": 113,
123
  "备": 363,
124
  "多": 99,
125
  "够": 193,
126
  "大": 355,
127
  "天": 302,
128
- "太": 191,
129
  "奇": 90,
130
  "奋": 100,
131
  "女": 229,
@@ -136,7 +136,7 @@
136
  "姓": 127,
137
  "威": 215,
138
  "子": 231,
139
- "字": 111,
140
  "存": 93,
141
  "学": 350,
142
  "孩": 89,
@@ -155,21 +155,21 @@
155
  "尽": 278,
156
  "局": 172,
157
  "居": 6,
158
- "屏": 336,
159
  "山": 135,
160
  "岁": 203,
161
  "工": 35,
162
- "己": 112,
163
  "已": 129,
164
  "巴": 328,
165
- "师": 296,
166
  "希": 141,
167
  "带": 319,
168
  "常": 339,
169
  "幕": 159,
170
  "平": 25,
171
  "年": 225,
172
- "度": 68,
173
  "开": 321,
174
  "强": 33,
175
  "归": 162,
@@ -187,7 +187,7 @@
187
  "总": 374,
188
  "悉": 251,
189
  "患": 289,
190
- "悲": 52,
191
  "情": 168,
192
  "惨": 39,
193
  "想": 175,
@@ -197,7 +197,7 @@
197
  "我": 338,
198
  "或": 11,
199
  "所": 70,
200
- "才": 183,
201
  "打": 207,
202
  "执": 344,
203
  "找": 41,
@@ -208,10 +208,10 @@
208
  "担": 323,
209
  "拍": 200,
210
  "拿": 106,
211
- "挂": 261,
212
  "挺": 142,
213
  "探": 119,
214
- "接": 196,
215
  "放": 309,
216
  "故": 122,
217
  "教": 295,
@@ -222,7 +222,7 @@
222
  "新": 45,
223
  "方": 151,
224
  "无": 49,
225
- "旧": 98,
226
  "时": 287,
227
  "明": 164,
228
  "星": 63,
@@ -230,17 +230,17 @@
230
  "是": 5,
231
  "显": 161,
232
  "暂": 174,
233
- "最": 352,
234
  "有": 304,
235
  "望": 102,
236
  "杀": 2,
237
  "来": 95,
238
  "林": 260,
239
  "果": 354,
240
- "柔": 50,
241
  "标": 220,
242
  "棋": 313,
243
- "模": 51,
244
  "欢": 77,
245
  "正": 341,
246
  "武": 366,
@@ -250,11 +250,11 @@
250
  "汇": 286,
251
  "没": 103,
252
  "注": 277,
253
- "派": 195,
254
  "海": 345,
255
- "深": 259,
256
  "温": 301,
257
- "灰": 131,
258
  "点": 110,
259
  "然": 150,
260
  "熔": 92,
@@ -283,25 +283,25 @@
283
  "种": 148,
284
  "秒": 292,
285
  "称": 167,
286
- "突": 71,
287
  "童": 178,
288
  "等": 154,
289
  "策": 246,
290
  "精": 298,
291
- "级": 72,
292
  "练": 59,
293
  "组": 185,
294
  "细": 264,
295
  "终": 340,
296
  "绍": 201,
297
  "经": 116,
298
- "结": 242,
299
  "给": 216,
300
  "老": 303,
301
- "者": 69,
302
  "肯": 320,
303
  "背": 274,
304
- "能": 244,
305
  "脑": 330,
306
  "自": 40,
307
  "致": 223,
@@ -310,18 +310,18 @@
310
  "虽": 12,
311
  "行": 118,
312
  "被": 140,
313
- "要": 198,
314
  "见": 240,
315
  "视": 372,
316
  "觉": 202,
317
  "角": 79,
318
  "解": 66,
319
- "认": 132,
320
  "讲": 88,
321
  "许": 228,
322
  "论": 166,
323
- "评": 97,
324
- "识": 182,
325
  "词": 62,
326
  "话": 346,
327
  "语": 75,
@@ -334,7 +334,7 @@
334
  "资": 234,
335
  "超": 186,
336
  "趣": 37,
337
- "足": 199,
338
  "跟": 349,
339
  "路": 123,
340
  "较": 85,
@@ -351,7 +351,7 @@
351
  "邵": 1,
352
  "郝": 78,
353
  "部": 180,
354
- "都": 243,
355
  "释": 42,
356
  "里": 56,
357
  "重": 0,
@@ -359,20 +359,20 @@
359
  "长": 211,
360
  "门": 213,
361
  "问": 348,
362
- "间": 297,
363
  "院": 31,
364
  "随": 361,
365
  "隐": 358,
366
- "隔": 241,
367
  "难": 254,
368
  "需": 64,
369
  "霸": 146,
370
  "面": 138,
371
  "音": 300,
372
  "顾": 128,
373
- "题": 316,
374
  "驰": 48,
375
- "高": 337,
376
  "魔": 285,
377
  "默": 91,
378
  "龄": 218,
 
15
  "主": 255,
16
  "么": 58,
17
  "之": 226,
18
+ "乌": 191,
19
  "也": 76,
20
+ "了": 132,
21
  "事": 19,
22
  "二": 130,
23
  "于": 356,
 
44
  "佛": 197,
45
  "作": 134,
46
  "你": 34,
47
+ "信": 261,
48
  "候": 281,
49
  "做": 157,
50
  "停": 299,
 
61
  "内": 364,
62
  "再": 120,
63
  "冲": 149,
64
+ "决": 69,
65
  "准": 169,
66
  "减": 256,
67
  "几": 61,
68
+ "出": 352,
69
  "分": 360,
70
+ "刚": 351,
71
  "别": 322,
72
  "到": 331,
73
  "前": 217,
 
101
  "名": 115,
102
  "后": 368,
103
  "吧": 139,
104
+ "听": 52,
105
  "吼": 163,
106
  "呃": 107,
107
  "呢": 145,
108
  "周": 265,
109
  "和": 184,
110
  "哎": 327,
111
+ "哦": 97,
112
  "啊": 23,
113
  "啥": 367,
114
+ "喜": 243,
115
  "嗯": 3,
116
  "嘛": 44,
117
  "回": 20,
118
  "因": 84,
119
  "园": 55,
120
  "在": 232,
121
+ "地": 316,
122
  "壳": 113,
123
  "备": 363,
124
  "多": 99,
125
  "够": 193,
126
  "大": 355,
127
  "天": 302,
128
+ "太": 192,
129
  "奇": 90,
130
  "奋": 100,
131
  "女": 229,
 
136
  "姓": 127,
137
  "威": 215,
138
  "子": 231,
139
+ "字": 112,
140
  "存": 93,
141
  "学": 350,
142
  "孩": 89,
 
155
  "尽": 278,
156
  "局": 172,
157
  "居": 6,
158
+ "屏": 337,
159
  "山": 135,
160
  "岁": 203,
161
  "工": 35,
162
+ "己": 111,
163
  "已": 129,
164
  "巴": 328,
165
+ "师": 297,
166
  "希": 141,
167
  "带": 319,
168
  "常": 339,
169
  "幕": 159,
170
  "平": 25,
171
  "年": 225,
172
+ "度": 67,
173
  "开": 321,
174
  "强": 33,
175
  "归": 162,
 
187
  "总": 374,
188
  "悉": 251,
189
  "患": 289,
190
+ "悲": 53,
191
  "情": 168,
192
  "惨": 39,
193
  "想": 175,
 
197
  "我": 338,
198
  "或": 11,
199
  "所": 70,
200
+ "才": 182,
201
  "打": 207,
202
  "执": 344,
203
  "找": 41,
 
208
  "担": 323,
209
  "拍": 200,
210
  "拿": 106,
211
+ "挂": 259,
212
  "挺": 142,
213
  "探": 119,
214
+ "接": 195,
215
  "放": 309,
216
  "故": 122,
217
  "教": 295,
 
222
  "新": 45,
223
  "方": 151,
224
  "无": 49,
225
+ "旧": 96,
226
  "时": 287,
227
  "明": 164,
228
  "星": 63,
 
230
  "是": 5,
231
  "显": 161,
232
  "暂": 174,
233
+ "最": 353,
234
  "有": 304,
235
  "望": 102,
236
  "杀": 2,
237
  "来": 95,
238
  "林": 260,
239
  "果": 354,
240
+ "柔": 51,
241
  "标": 220,
242
  "棋": 313,
243
+ "模": 50,
244
  "欢": 77,
245
  "正": 341,
246
  "武": 366,
 
250
  "汇": 286,
251
  "没": 103,
252
  "注": 277,
253
+ "派": 196,
254
  "海": 345,
255
+ "深": 262,
256
  "温": 301,
257
+ "灰": 133,
258
  "点": 110,
259
  "然": 150,
260
  "熔": 92,
 
283
  "种": 148,
284
  "秒": 292,
285
  "称": 167,
286
+ "突": 72,
287
  "童": 178,
288
  "等": 154,
289
  "策": 246,
290
  "精": 298,
291
+ "级": 71,
292
  "练": 59,
293
  "组": 185,
294
  "细": 264,
295
  "终": 340,
296
  "绍": 201,
297
  "经": 116,
298
+ "结": 241,
299
  "给": 216,
300
  "老": 303,
301
+ "者": 68,
302
  "肯": 320,
303
  "背": 274,
304
+ "能": 245,
305
  "脑": 330,
306
  "自": 40,
307
  "致": 223,
 
310
  "虽": 12,
311
  "行": 118,
312
  "被": 140,
313
+ "要": 199,
314
  "见": 240,
315
  "视": 372,
316
  "觉": 202,
317
  "角": 79,
318
  "解": 66,
319
+ "认": 131,
320
  "讲": 88,
321
  "许": 228,
322
  "论": 166,
323
+ "评": 98,
324
+ "识": 183,
325
  "词": 62,
326
  "话": 346,
327
  "语": 75,
 
334
  "资": 234,
335
  "超": 186,
336
  "趣": 37,
337
+ "足": 198,
338
  "跟": 349,
339
  "路": 123,
340
  "较": 85,
 
351
  "邵": 1,
352
  "郝": 78,
353
  "部": 180,
354
+ "都": 244,
355
  "释": 42,
356
  "里": 56,
357
  "重": 0,
 
359
  "长": 211,
360
  "门": 213,
361
  "问": 348,
362
+ "间": 296,
363
  "院": 31,
364
  "随": 361,
365
  "隐": 358,
366
+ "隔": 242,
367
  "难": 254,
368
  "需": 64,
369
  "霸": 146,
370
  "面": 138,
371
  "音": 300,
372
  "顾": 128,
373
+ "题": 315,
374
  "驰": 48,
375
+ "高": 336,
376
  "魔": 285,
377
  "默": 91,
378
  "龄": 218,