dongim04 commited on
Commit
6114e40
·
verified ·
1 Parent(s): 9924a8e

Upload tokenizer

Browse files
Files changed (1) hide show
  1. vocab.json +53 -53
vocab.json CHANGED
@@ -15,14 +15,14 @@
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,
24
  "些": 317,
25
- "享": 87,
26
  "人": 288,
27
  "什": 283,
28
  "今": 282,
@@ -44,7 +44,7 @@
44
  "佛": 197,
45
  "作": 134,
46
  "你": 34,
47
- "信": 261,
48
  "候": 281,
49
  "做": 157,
50
  "停": 299,
@@ -52,7 +52,7 @@
52
  "傅": 73,
53
  "催": 305,
54
  "像": 235,
55
- "充": 43,
56
  "先": 248,
57
  "光": 136,
58
  "关": 324,
@@ -61,7 +61,7 @@
61
  "内": 364,
62
  "再": 120,
63
  "冲": 149,
64
- "决": 69,
65
  "准": 169,
66
  "减": 256,
67
  "几": 61,
@@ -71,21 +71,21 @@
71
  "别": 322,
72
  "到": 331,
73
  "前": 217,
74
- "剑": 332,
75
  "剧": 121,
76
  "力": 179,
77
  "功": 38,
78
  "务": 204,
79
  "动": 32,
80
  "努": 238,
81
- "勤": 333,
82
  "区": 36,
83
- "单": 266,
84
  "卡": 291,
85
  "印": 263,
86
  "原": 124,
87
  "去": 28,
88
- "又": 105,
89
  "反": 30,
90
  "发": 83,
91
  "受": 268,
@@ -93,7 +93,7 @@
93
  "另": 158,
94
  "只": 29,
95
  "叫": 189,
96
- "可": 273,
97
  "号": 147,
98
  "吃": 370,
99
  "各": 227,
@@ -101,19 +101,19 @@
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,
@@ -125,12 +125,12 @@
125
  "够": 193,
126
  "大": 355,
127
  "天": 302,
128
- "太": 192,
129
  "奇": 90,
130
  "奋": 100,
131
  "女": 229,
132
  "她": 258,
133
- "好": 272,
134
  "如": 7,
135
  "始": 357,
136
  "姓": 127,
@@ -162,7 +162,7 @@
162
  "己": 111,
163
  "已": 129,
164
  "巴": 328,
165
- "师": 297,
166
  "希": 141,
167
  "带": 319,
168
  "常": 339,
@@ -174,7 +174,7 @@
174
  "强": 33,
175
  "归": 162,
176
  "彩": 22,
177
- "影": 117,
178
  "往": 369,
179
  "很": 114,
180
  "得": 347,
@@ -187,7 +187,7 @@
187
  "总": 374,
188
  "悉": 251,
189
  "患": 289,
190
- "悲": 53,
191
  "情": 168,
192
  "惨": 39,
193
  "想": 175,
@@ -197,7 +197,7 @@
197
  "我": 338,
198
  "或": 11,
199
  "所": 70,
200
- "才": 182,
201
  "打": 207,
202
  "执": 344,
203
  "找": 41,
@@ -206,25 +206,25 @@
206
  "抢": 94,
207
  "抱": 27,
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,
218
- "敬": 109,
219
  "文": 293,
220
  "斗": 279,
221
  "断": 212,
222
  "新": 45,
223
  "方": 151,
224
  "无": 49,
225
- "旧": 96,
226
  "时": 287,
227
- "明": 164,
228
  "星": 63,
229
  "映": 155,
230
  "是": 5,
@@ -234,7 +234,7 @@
234
  "有": 304,
235
  "望": 102,
236
  "杀": 2,
237
- "来": 95,
238
  "林": 260,
239
  "果": 354,
240
  "柔": 51,
@@ -250,18 +250,18 @@
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,
261
  "熟": 181,
262
  "爱": 14,
263
- "物": 239,
264
- "特": 108,
265
  "狼": 290,
266
  "环": 156,
267
  "现": 170,
@@ -269,7 +269,7 @@
269
  "生": 13,
270
  "电": 329,
271
  "男": 371,
272
- "画": 237,
273
  "留": 276,
274
  "病": 18,
275
  "痕": 373,
@@ -283,50 +283,50 @@
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,
308
  "节": 26,
309
  "苦": 224,
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,
328
  "说": 230,
329
- "读": 267,
330
  "课": 208,
331
  "谢": 194,
332
  "象": 177,
@@ -334,13 +334,13 @@
334
  "资": 234,
335
  "超": 186,
336
  "趣": 37,
337
- "足": 198,
338
  "跟": 349,
339
  "路": 123,
340
  "较": 85,
341
  "输": 252,
342
  "辛": 280,
343
- "过": 236,
344
  "近": 125,
345
  "还": 74,
346
  "这": 249,
@@ -351,15 +351,15 @@
351
  "邵": 1,
352
  "郝": 78,
353
  "部": 180,
354
- "都": 244,
355
  "释": 42,
356
  "里": 56,
357
  "重": 0,
358
- "钟": 165,
359
  "长": 211,
360
  "门": 213,
361
  "问": 348,
362
- "间": 296,
363
  "院": 31,
364
  "随": 361,
365
  "隐": 358,
 
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,
24
  "些": 317,
25
+ "享": 88,
26
  "人": 288,
27
  "什": 283,
28
  "今": 282,
 
44
  "佛": 197,
45
  "作": 134,
46
  "你": 34,
47
+ "信": 262,
48
  "候": 281,
49
  "做": 157,
50
  "停": 299,
 
52
  "傅": 73,
53
  "催": 305,
54
  "像": 235,
55
+ "充": 44,
56
  "先": 248,
57
  "光": 136,
58
  "关": 324,
 
61
  "内": 364,
62
  "再": 120,
63
  "冲": 149,
64
+ "决": 68,
65
  "准": 169,
66
  "减": 256,
67
  "几": 61,
 
71
  "别": 322,
72
  "到": 331,
73
  "前": 217,
74
+ "剑": 333,
75
  "剧": 121,
76
  "力": 179,
77
  "功": 38,
78
  "务": 204,
79
  "动": 32,
80
  "努": 238,
81
+ "勤": 332,
82
  "区": 36,
83
+ "单": 267,
84
  "卡": 291,
85
  "印": 263,
86
  "原": 124,
87
  "去": 28,
88
+ "又": 106,
89
  "反": 30,
90
  "发": 83,
91
  "受": 268,
 
93
  "另": 158,
94
  "只": 29,
95
  "叫": 189,
96
+ "可": 272,
97
  "号": 147,
98
  "吃": 370,
99
  "各": 227,
 
101
  "名": 115,
102
  "后": 368,
103
  "吧": 139,
104
+ "听": 53,
105
  "吼": 163,
106
+ "呃": 109,
107
  "呢": 145,
108
  "周": 265,
109
  "和": 184,
110
  "哎": 327,
111
+ "哦": 96,
112
  "啊": 23,
113
  "啥": 367,
114
+ "喜": 244,
115
  "嗯": 3,
116
+ "嘛": 43,
117
  "回": 20,
118
  "因": 84,
119
  "园": 55,
 
125
  "够": 193,
126
  "大": 355,
127
  "天": 302,
128
+ "太": 191,
129
  "奇": 90,
130
  "奋": 100,
131
  "女": 229,
132
  "她": 258,
133
+ "好": 273,
134
  "如": 7,
135
  "始": 357,
136
  "姓": 127,
 
162
  "己": 111,
163
  "已": 129,
164
  "巴": 328,
165
+ "师": 296,
166
  "希": 141,
167
  "带": 319,
168
  "常": 339,
 
174
  "强": 33,
175
  "归": 162,
176
  "彩": 22,
177
+ "影": 118,
178
  "往": 369,
179
  "很": 114,
180
  "得": 347,
 
187
  "总": 374,
188
  "悉": 251,
189
  "患": 289,
190
+ "悲": 52,
191
  "情": 168,
192
  "惨": 39,
193
  "想": 175,
 
197
  "我": 338,
198
  "或": 11,
199
  "所": 70,
200
+ "才": 183,
201
  "打": 207,
202
  "执": 344,
203
  "找": 41,
 
206
  "抢": 94,
207
  "抱": 27,
208
  "担": 323,
209
+ "拍": 199,
210
+ "拿": 105,
211
+ "挂": 261,
212
  "挺": 142,
213
  "探": 119,
214
+ "接": 196,
215
  "放": 309,
216
  "故": 122,
217
  "教": 295,
218
+ "敬": 108,
219
  "文": 293,
220
  "斗": 279,
221
  "断": 212,
222
  "新": 45,
223
  "方": 151,
224
  "无": 49,
225
+ "旧": 95,
226
  "时": 287,
227
+ "明": 165,
228
  "星": 63,
229
  "映": 155,
230
  "是": 5,
 
234
  "有": 304,
235
  "望": 102,
236
  "杀": 2,
237
+ "来": 97,
238
  "林": 260,
239
  "果": 354,
240
  "柔": 51,
 
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,
261
  "熟": 181,
262
  "爱": 14,
263
+ "物": 240,
264
+ "特": 107,
265
  "狼": 290,
266
  "环": 156,
267
  "现": 170,
 
269
  "生": 13,
270
  "电": 329,
271
  "男": 371,
272
+ "画": 236,
273
  "留": 276,
274
  "病": 18,
275
  "痕": 373,
 
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": 200,
297
  "经": 116,
298
  "结": 241,
299
  "给": 216,
300
  "老": 303,
301
+ "者": 69,
302
  "肯": 320,
303
  "背": 274,
304
+ "能": 243,
305
  "脑": 330,
306
  "自": 40,
307
  "致": 223,
308
  "节": 26,
309
  "苦": 224,
310
  "虽": 12,
311
+ "行": 117,
312
  "被": 140,
313
+ "要": 198,
314
+ "见": 239,
315
  "视": 372,
316
  "觉": 202,
317
  "角": 79,
318
  "解": 66,
319
+ "认": 132,
320
+ "讲": 87,
321
  "许": 228,
322
  "论": 166,
323
  "评": 98,
324
+ "识": 182,
325
  "词": 62,
326
  "话": 346,
327
  "语": 75,
328
  "说": 230,
329
+ "读": 266,
330
  "课": 208,
331
  "谢": 194,
332
  "象": 177,
 
334
  "资": 234,
335
  "超": 186,
336
  "趣": 37,
337
+ "足": 201,
338
  "跟": 349,
339
  "路": 123,
340
  "较": 85,
341
  "输": 252,
342
  "辛": 280,
343
+ "过": 237,
344
  "近": 125,
345
  "还": 74,
346
  "这": 249,
 
351
  "邵": 1,
352
  "郝": 78,
353
  "部": 180,
354
+ "都": 245,
355
  "释": 42,
356
  "里": 56,
357
  "重": 0,
358
+ "钟": 164,
359
  "长": 211,
360
  "门": 213,
361
  "问": 348,
362
+ "间": 297,
363
  "院": 31,
364
  "随": 361,
365
  "隐": 358,