Danielwei0214 commited on
Commit
04a7a4a
1 Parent(s): 33a3524

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +302 -0
  2. special_tokens_map.json +7 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +15 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,302 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ethanyt/guwenbert-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-人生-出生",
16
+ "2": "I-人生-出生",
17
+ "3": "B-人生-结婚",
18
+ "4": "I-人生-结婚",
19
+ "5": "B-人生-生病",
20
+ "6": "I-人生-生病",
21
+ "7": "B-人生-受伤",
22
+ "8": "I-人生-受伤",
23
+ "9": "B-人生-死亡",
24
+ "10": "I-人生-死亡",
25
+ "11": "B-人生-安葬",
26
+ "12": "I-人生-安葬",
27
+ "13": "B-人生-分封",
28
+ "14": "I-人生-分封",
29
+ "15": "B-人生-立谥",
30
+ "16": "I-人生-立谥",
31
+ "17": "B-职位-帝位-确立",
32
+ "18": "I-职位-帝位-确立",
33
+ "19": "B-职位-帝位-即位",
34
+ "20": "I-职位-帝位-即位",
35
+ "21": "B-职位-帝位-继位",
36
+ "22": "I-职位-帝位-继位",
37
+ "23": "B-职位-官位-任职",
38
+ "24": "I-职位-官位-任职",
39
+ "25": "B-职位-官位-免职",
40
+ "26": "I-职位-官位-免职",
41
+ "27": "B-职位-官位-升职",
42
+ "28": "I-职位-官位-升职",
43
+ "29": "B-职位-官位-降职",
44
+ "30": "I-职位-官位-降职",
45
+ "31": "B-职位-官位-赏赐",
46
+ "32": "I-职位-官位-赏赐",
47
+ "33": "B-交流-国家交流-出使",
48
+ "34": "I-交流-国家交流-出使",
49
+ "35": "B-交流-国家交流-盟约",
50
+ "36": "I-交流-国家交流-盟约",
51
+ "37": "B-交流-国家交流-朝贡",
52
+ "38": "I-交流-国家交流-朝贡",
53
+ "39": "B-交流-个人交流-见面",
54
+ "40": "I-交流-个人交流-见面",
55
+ "41": "B-交流-个人交流-商议",
56
+ "42": "I-交流-个人交流-商议",
57
+ "43": "B-交流-个人交流-询问",
58
+ "44": "I-交流-个人交流-询问",
59
+ "45": "B-交流-个人交流-诏令-命令",
60
+ "46": "I-交流-个人交流-诏令-命令",
61
+ "47": "B-交流-个人交流-诏令-下诏",
62
+ "48": "I-交流-个人交流-诏令-下诏",
63
+ "49": "B-交流-个人交流-进言",
64
+ "50": "I-交流-个人交流-进言",
65
+ "51": "B-交流-个人交流-派遣",
66
+ "52": "I-交流-个人交流-派遣",
67
+ "53": "B-祭祀-祭天神",
68
+ "54": "I-祭祀-祭天神",
69
+ "55": "B-祭祀-祭地祇",
70
+ "56": "I-祭祀-祭地祇",
71
+ "57": "B-祭祀-祭人鬼",
72
+ "58": "I-祭祀-祭人鬼",
73
+ "59": "B-移动-到达",
74
+ "60": "I-移动-到达",
75
+ "61": "B-移动-停留",
76
+ "62": "I-移动-停留",
77
+ "63": "B-移动-离开",
78
+ "64": "I-移动-离开",
79
+ "65": "B-军事-备战-出兵",
80
+ "66": "I-军事-备战-出兵",
81
+ "67": "B-军事-备战-驻扎",
82
+ "68": "I-军事-备战-驻扎",
83
+ "69": "B-军事-作战-攻击-征伐",
84
+ "70": "I-军事-作战-攻击-征伐",
85
+ "71": "B-军事-作战-攻击-侵袭",
86
+ "72": "I-军事-作战-攻击-侵袭",
87
+ "73": "B-军事-作战-防守",
88
+ "74": "I-军事-作战-防守",
89
+ "75": "B-军事-作战-谋反",
90
+ "76": "I-军事-作战-谋反",
91
+ "77": "B-军事-作战-杀害",
92
+ "78": "I-军事-作战-杀害",
93
+ "79": "B-军事-作战-救援",
94
+ "80": "I-军事-作战-救援",
95
+ "81": "B-军事-作战-撤退",
96
+ "82": "I-军事-作战-撤退",
97
+ "83": "B-军事-作战-俘虏",
98
+ "84": "I-军事-作战-俘虏",
99
+ "85": "B-军事-停战-战胜",
100
+ "86": "I-军事-停战-战胜",
101
+ "87": "B-军事-停战-战败",
102
+ "88": "I-军事-停战-战败",
103
+ "89": "B-军事-停战-投降",
104
+ "90": "I-军事-停战-投降",
105
+ "91": "B-经济-赋税-征税",
106
+ "92": "I-经济-赋税-征税",
107
+ "93": "B-经济-赋税-减税",
108
+ "94": "I-经济-赋税-减税",
109
+ "95": "B-经济-赋税-免税",
110
+ "96": "I-经济-赋税-免税",
111
+ "97": "B-经济-买卖-买入",
112
+ "98": "I-经济-买卖-买入",
113
+ "99": "B-经济-买卖-卖出",
114
+ "100": "I-经济-买卖-卖出",
115
+ "101": "B-经济-生产-耕种",
116
+ "102": "I-经济-生产-耕种",
117
+ "103": "B-经济-生产-打猎",
118
+ "104": "I-经济-生产-打猎",
119
+ "105": "B-经济-生产-建造",
120
+ "106": "I-经济-生产-建造",
121
+ "107": "B-法律-制法",
122
+ "108": "I-法律-制法",
123
+ "109": "B-法律-废法",
124
+ "110": "I-法律-废法",
125
+ "111": "B-法律-犯罪",
126
+ "112": "I-法律-犯罪",
127
+ "113": "B-法律-逮捕",
128
+ "114": "I-法律-逮捕",
129
+ "115": "B-法律-赦免",
130
+ "116": "I-法律-赦免",
131
+ "117": "B-法律-处死",
132
+ "118": "I-法律-处死",
133
+ "119": "B-法律-流放",
134
+ "120": "I-法律-流放",
135
+ "121": "B-自然-灾害-饥荒",
136
+ "122": "I-自然-灾害-饥荒",
137
+ "123": "B-自然-灾害-地震",
138
+ "124": "I-自然-灾害-地震",
139
+ "125": "B-自然-灾害-水灾",
140
+ "126": "I-自然-灾害-水灾",
141
+ "127": "B-自然-灾害-蝗灾",
142
+ "128": "I-自然-灾害-蝗灾",
143
+ "129": "B-自然-天象-日食",
144
+ "130": "I-自然-天象-日食",
145
+ "131": "B-自然-天象-���星",
146
+ "132": "I-自然-天象-流星",
147
+ "133": "B-自然-天气",
148
+ "134": "I-自然-天气"
149
+ },
150
+ "initializer_range": 0.02,
151
+ "intermediate_size": 3072,
152
+ "label2id": {
153
+ "O": 0,
154
+ "B-人生-出生": 1,
155
+ "I-人生-死亡": 10,
156
+ "I-经济-买卖-卖出": 100,
157
+ "B-经济-生产-耕种": 101,
158
+ "I-经济-生产-耕种": 102,
159
+ "B-经济-生产-打猎": 103,
160
+ "I-经济-生产-打猎": 104,
161
+ "B-经济-生产-建造": 105,
162
+ "I-经济-生产-建造": 106,
163
+ "B-法律-制法": 107,
164
+ "I-法律-制法": 108,
165
+ "B-法律-废法": 109,
166
+ "B-人生-安葬": 11,
167
+ "I-法律-废法": 110,
168
+ "B-法律-犯罪": 111,
169
+ "I-法律-犯罪": 112,
170
+ "B-法律-逮捕": 113,
171
+ "I-法律-逮捕": 114,
172
+ "B-法律-赦免": 115,
173
+ "I-法律-赦免": 116,
174
+ "B-法律-处死": 117,
175
+ "I-法律-处死": 118,
176
+ "B-法律-流放": 119,
177
+ "I-人生-安葬": 12,
178
+ "I-法律-流放": 120,
179
+ "B-自然-灾害-饥荒": 121,
180
+ "I-自然-灾害-饥荒": 122,
181
+ "B-自然-灾害-地震": 123,
182
+ "I-自然-灾害-地震": 124,
183
+ "B-自然-灾害-水灾": 125,
184
+ "I-自然-灾害-水灾": 126,
185
+ "B-自然-灾害-蝗灾": 127,
186
+ "I-自然-灾害-蝗灾": 128,
187
+ "B-自然-天象-日食": 129,
188
+ "B-人生-分封": 13,
189
+ "I-自然-天象-日食": 130,
190
+ "B-自然-天象-流星": 131,
191
+ "I-自然-天象-流星": 132,
192
+ "B-自然-天气": 133,
193
+ "I-自然-天气": 134,
194
+ "I-人生-分封": 14,
195
+ "B-人生-立谥": 15,
196
+ "I-人生-立谥": 16,
197
+ "B-职位-帝位-确立": 17,
198
+ "I-职位-帝位-确立": 18,
199
+ "B-职位-帝位-即位": 19,
200
+ "I-人生-出生": 2,
201
+ "I-职位-帝位-即位": 20,
202
+ "B-职位-帝位-继位": 21,
203
+ "I-职位-帝位-继位": 22,
204
+ "B-职位-官位-任职": 23,
205
+ "I-职位-官位-任职": 24,
206
+ "B-职位-官位-免职": 25,
207
+ "I-职位-官位-免职": 26,
208
+ "B-职位-官位-升职": 27,
209
+ "I-职位-官位-升职": 28,
210
+ "B-职位-官位-降职": 29,
211
+ "B-人生-结婚": 3,
212
+ "I-职位-官位-降职": 30,
213
+ "B-职位-官位-赏赐": 31,
214
+ "I-职位-官位-赏赐": 32,
215
+ "B-交流-国家交流-出使": 33,
216
+ "I-交流-国家交流-出使": 34,
217
+ "B-交流-国家交流-盟约": 35,
218
+ "I-交流-国家交流-盟约": 36,
219
+ "B-交流-国家交流-朝贡": 37,
220
+ "I-交流-国家交流-朝贡": 38,
221
+ "B-交流-个人交流-见面": 39,
222
+ "I-人生-结婚": 4,
223
+ "I-交流-个人交流-见面": 40,
224
+ "B-交流-个人交流-商议": 41,
225
+ "I-交流-个人交流-商议": 42,
226
+ "B-交流-个人交流-询问": 43,
227
+ "I-交流-个人交流-询问": 44,
228
+ "B-交流-个人交流-诏令-命令": 45,
229
+ "I-交流-个人交流-诏令-命令": 46,
230
+ "B-交流-个人交流-诏令-下诏": 47,
231
+ "I-交流-个人交流-诏令-下诏": 48,
232
+ "B-交流-个人交流-进言": 49,
233
+ "B-人生-生病": 5,
234
+ "I-交流-个人交流-进言": 50,
235
+ "B-交流-个人交流-派遣": 51,
236
+ "I-交流-个人交流-派遣": 52,
237
+ "B-祭祀-祭天神": 53,
238
+ "I-祭祀-祭天神": 54,
239
+ "B-祭祀-祭地祇": 55,
240
+ "I-祭祀-祭地祇": 56,
241
+ "B-祭祀-祭人鬼": 57,
242
+ "I-祭祀-祭人鬼": 58,
243
+ "B-移动-到达": 59,
244
+ "I-人生-生病": 6,
245
+ "I-移动-到达": 60,
246
+ "B-移动-停留": 61,
247
+ "I-移动-停留": 62,
248
+ "B-移动-离开": 63,
249
+ "I-移动-离开": 64,
250
+ "B-军事-备战-出兵": 65,
251
+ "I-军事-备战-出兵": 66,
252
+ "B-军事-备战-驻扎": 67,
253
+ "I-军事-备战-驻扎": 68,
254
+ "B-军事-作战-攻击-征伐": 69,
255
+ "B-人生-受伤": 7,
256
+ "I-军事-作战-攻击-征伐": 70,
257
+ "B-军事-作战-攻击-侵袭": 71,
258
+ "I-军事-作战-攻击-侵袭": 72,
259
+ "B-军事-作战-防守": 73,
260
+ "I-军事-作战-防守": 74,
261
+ "B-军事-作战-谋反": 75,
262
+ "I-军事-作战-谋反": 76,
263
+ "B-军事-作战-杀害": 77,
264
+ "I-军事-作战-杀害": 78,
265
+ "B-军事-作战-救援": 79,
266
+ "I-人生-受伤": 8,
267
+ "I-军事-作战-救援": 80,
268
+ "B-军事-作战-撤退": 81,
269
+ "I-军事-作战-撤退": 82,
270
+ "B-军事-作战-俘虏": 83,
271
+ "I-军事-作战-俘虏": 84,
272
+ "B-军事-停战-战胜": 85,
273
+ "I-军事-停战-战胜": 86,
274
+ "B-军事-停战-战败": 87,
275
+ "I-军事-停战-战败": 88,
276
+ "B-军事-停战-投降": 89,
277
+ "B-人生-死亡": 9,
278
+ "I-军事-停战-投降": 90,
279
+ "B-经济-赋税-征税": 91,
280
+ "I-经济-赋税-征税": 92,
281
+ "B-经济-赋税-减税": 93,
282
+ "I-经济-赋税-减税": 94,
283
+ "B-经济-赋税-免税": 95,
284
+ "I-经济-赋税-免税": 96,
285
+ "B-经济-买卖-买入": 97,
286
+ "I-经济-买卖-买入": 98,
287
+ "B-经济-买卖-卖出": 99
288
+ },
289
+ "layer_norm_eps": 1e-05,
290
+ "max_position_embeddings": 514,
291
+ "model_type": "roberta",
292
+ "num_attention_heads": 12,
293
+ "num_hidden_layers": 12,
294
+ "pad_token_id": 1,
295
+ "position_embedding_type": "absolute",
296
+ "tokenizer_class": "BertTokenizer",
297
+ "torch_dtype": "float32",
298
+ "transformers_version": "4.31.0",
299
+ "type_vocab_size": 1,
300
+ "use_cache": true,
301
+ "vocab_size": 23292
302
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff