KoichiYasuoka commited on
Commit
6eb64fd
1 Parent(s): 860838f

initial release

Browse files
README.md CHANGED
@@ -1,3 +1,39 @@
1
- ---
2
- license: cc-by-sa-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - "ru"
4
+ tags:
5
+ - "russian"
6
+ - "token-classification"
7
+ - "pos"
8
+ - "dependency-parsing"
9
+ datasets:
10
+ - "universal_dependencies"
11
+ license: "cc-by-sa-4.0"
12
+ pipeline_tag: "token-classification"
13
+ ---
14
+
15
+ # bert-base-russian-upos
16
+
17
+ ## Model Description
18
+
19
+ This is a BERT model pre-trained with [UD_Russian](https://universaldependencies.org/en/) for POS-tagging and dependency-parsing, derived from [rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
20
+
21
+ ## How to Use
22
+
23
+ ```py
24
+ from transformers import AutoTokenizer,AutoModelForTokenClassification
25
+ tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/bert-base-russian-upos")
26
+ model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/bert-base-russian-upos")
27
+ ```
28
+
29
+ or
30
+
31
+ ```py
32
+ import esupar
33
+ nlp=esupar.load("KoichiYasuoka/bert-base-russian-upos")
34
+ ```
35
+
36
+ ## See Also
37
+
38
+ [esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa models
39
+
config.json ADDED
@@ -0,0 +1,480 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "ADJ",
13
+ "1": "ADJ+NOUN",
14
+ "2": "ADP",
15
+ "3": "ADP+PRON",
16
+ "4": "ADV",
17
+ "5": "AUX",
18
+ "6": "B-ADJ",
19
+ "7": "B-ADJ+ADJ",
20
+ "8": "B-ADJ+NOUN",
21
+ "9": "B-ADJ+SCONJ",
22
+ "10": "B-ADJ+VERB",
23
+ "11": "B-ADP",
24
+ "12": "B-ADP+DET",
25
+ "13": "B-ADV",
26
+ "14": "B-ADV+VERB",
27
+ "15": "B-AUX",
28
+ "16": "B-CCONJ",
29
+ "17": "B-DET",
30
+ "18": "B-INTJ",
31
+ "19": "B-NOUN",
32
+ "20": "B-NUM",
33
+ "21": "B-NUM+ADJ",
34
+ "22": "B-NUM+NOUN",
35
+ "23": "B-PART",
36
+ "24": "B-PART+PRON",
37
+ "25": "B-PRON",
38
+ "26": "B-PRON+PART",
39
+ "27": "B-PROPN",
40
+ "28": "B-PUNCT",
41
+ "29": "B-SCONJ",
42
+ "30": "B-SYM",
43
+ "31": "B-SYM+NUM",
44
+ "32": "B-VERB",
45
+ "33": "B-VERB+ADV",
46
+ "34": "B-VERB+PRON",
47
+ "35": "B-X",
48
+ "36": "B-X+X",
49
+ "37": "CCONJ",
50
+ "38": "DET",
51
+ "39": "I-ADJ",
52
+ "40": "I-ADJ+ADJ",
53
+ "41": "I-ADJ+NOUN",
54
+ "42": "I-ADJ+SCONJ",
55
+ "43": "I-ADJ+VERB",
56
+ "44": "I-ADP",
57
+ "45": "I-ADP+DET",
58
+ "46": "I-ADV",
59
+ "47": "I-ADV+VERB",
60
+ "48": "I-AUX",
61
+ "49": "I-CCONJ",
62
+ "50": "I-DET",
63
+ "51": "I-INTJ",
64
+ "52": "I-NOUN",
65
+ "53": "I-NUM",
66
+ "54": "I-NUM+ADJ",
67
+ "55": "I-NUM+NOUN",
68
+ "56": "I-PART",
69
+ "57": "I-PART+PRON",
70
+ "58": "I-PRON",
71
+ "59": "I-PRON+PART",
72
+ "60": "I-PROPN",
73
+ "61": "I-PUNCT",
74
+ "62": "I-SCONJ",
75
+ "63": "I-SYM",
76
+ "64": "I-SYM+NUM",
77
+ "65": "I-VERB",
78
+ "66": "I-VERB+ADV",
79
+ "67": "I-VERB+PRON",
80
+ "68": "I-X",
81
+ "69": "I-X+X",
82
+ "70": "INTJ",
83
+ "71": "NOUN",
84
+ "72": "NUM",
85
+ "73": "NUM+NOUN",
86
+ "74": "NUM+PROPN",
87
+ "75": "NUM+SYM",
88
+ "76": "PART",
89
+ "77": "PRON",
90
+ "78": "PROPN",
91
+ "79": "PUNCT",
92
+ "80": "SCONJ",
93
+ "81": "SYM",
94
+ "82": "SYM+NOUN",
95
+ "83": "SYM+NUM",
96
+ "84": "SYM+PROPN",
97
+ "85": "VERB",
98
+ "86": "VERB+ADV",
99
+ "87": "VERB+PRON",
100
+ "88": "X"
101
+ },
102
+ "initializer_range": 0.02,
103
+ "intermediate_size": 3072,
104
+ "label2id": {
105
+ "ADJ": 0,
106
+ "ADJ+NOUN": 1,
107
+ "ADP": 2,
108
+ "ADP+PRON": 3,
109
+ "ADV": 4,
110
+ "AUX": 5,
111
+ "B-ADJ": 6,
112
+ "B-ADJ+ADJ": 7,
113
+ "B-ADJ+NOUN": 8,
114
+ "B-ADJ+SCONJ": 9,
115
+ "B-ADJ+VERB": 10,
116
+ "B-ADP": 11,
117
+ "B-ADP+DET": 12,
118
+ "B-ADV": 13,
119
+ "B-ADV+VERB": 14,
120
+ "B-AUX": 15,
121
+ "B-CCONJ": 16,
122
+ "B-DET": 17,
123
+ "B-INTJ": 18,
124
+ "B-NOUN": 19,
125
+ "B-NUM": 20,
126
+ "B-NUM+ADJ": 21,
127
+ "B-NUM+NOUN": 22,
128
+ "B-PART": 23,
129
+ "B-PART+PRON": 24,
130
+ "B-PRON": 25,
131
+ "B-PRON+PART": 26,
132
+ "B-PROPN": 27,
133
+ "B-PUNCT": 28,
134
+ "B-SCONJ": 29,
135
+ "B-SYM": 30,
136
+ "B-SYM+NUM": 31,
137
+ "B-VERB": 32,
138
+ "B-VERB+ADV": 33,
139
+ "B-VERB+PRON": 34,
140
+ "B-X": 35,
141
+ "B-X+X": 36,
142
+ "CCONJ": 37,
143
+ "DET": 38,
144
+ "I-ADJ": 39,
145
+ "I-ADJ+ADJ": 40,
146
+ "I-ADJ+NOUN": 41,
147
+ "I-ADJ+SCONJ": 42,
148
+ "I-ADJ+VERB": 43,
149
+ "I-ADP": 44,
150
+ "I-ADP+DET": 45,
151
+ "I-ADV": 46,
152
+ "I-ADV+VERB": 47,
153
+ "I-AUX": 48,
154
+ "I-CCONJ": 49,
155
+ "I-DET": 50,
156
+ "I-INTJ": 51,
157
+ "I-NOUN": 52,
158
+ "I-NUM": 53,
159
+ "I-NUM+ADJ": 54,
160
+ "I-NUM+NOUN": 55,
161
+ "I-PART": 56,
162
+ "I-PART+PRON": 57,
163
+ "I-PRON": 58,
164
+ "I-PRON+PART": 59,
165
+ "I-PROPN": 60,
166
+ "I-PUNCT": 61,
167
+ "I-SCONJ": 62,
168
+ "I-SYM": 63,
169
+ "I-SYM+NUM": 64,
170
+ "I-VERB": 65,
171
+ "I-VERB+ADV": 66,
172
+ "I-VERB+PRON": 67,
173
+ "I-X": 68,
174
+ "I-X+X": 69,
175
+ "INTJ": 70,
176
+ "NOUN": 71,
177
+ "NUM": 72,
178
+ "NUM+NOUN": 73,
179
+ "NUM+PROPN": 74,
180
+ "NUM+SYM": 75,
181
+ "PART": 76,
182
+ "PRON": 77,
183
+ "PROPN": 78,
184
+ "PUNCT": 79,
185
+ "SCONJ": 80,
186
+ "SYM": 81,
187
+ "SYM+NOUN": 82,
188
+ "SYM+NUM": 83,
189
+ "SYM+PROPN": 84,
190
+ "VERB": 85,
191
+ "VERB+ADV": 86,
192
+ "VERB+PRON": 87,
193
+ "X": 88
194
+ },
195
+ "layer_norm_eps": 1e-12,
196
+ "max_position_embeddings": 512,
197
+ "model_type": "bert",
198
+ "num_attention_heads": 12,
199
+ "num_hidden_layers": 12,
200
+ "output_past": true,
201
+ "pad_token_id": 0,
202
+ "pooler_fc_size": 768,
203
+ "pooler_num_attention_heads": 12,
204
+ "pooler_num_fc_layers": 3,
205
+ "pooler_size_per_head": 128,
206
+ "pooler_type": "first_token_transform",
207
+ "position_embedding_type": "absolute",
208
+ "task_specific_params": {
209
+ "upos_multiword": {
210
+ "ADJ+ADJ": {
211
+ "\u0432\u043e\u0435\u043d\u043d\u043e\u043c\u043e\u0440\u0441\u043a\u0430\u044f": [
212
+ "\u0432\u043e\u0435\u043d\u043d\u043e",
213
+ "\u043c\u043e\u0440\u0441\u043a\u0430\u044f"
214
+ ],
215
+ "\u0432\u043e\u0435\u043d\u043d\u043e\u043c\u043e\u0440\u0441\u043a\u0443\u044e": [
216
+ "\u0432\u043e\u0435\u043d\u043d\u043e",
217
+ "\u043c\u043e\u0440\u0441\u043a\u0443\u044e"
218
+ ],
219
+ "\u0433\u043e\u0440\u043d\u043e\u043c\u0435\u0442\u0430\u043b\u043b\u0443\u0440\u0433\u0438\u0447\u0435\u0441\u043a\u0438\u0439": [
220
+ "\u0433\u043e\u0440\u043d\u043e",
221
+ "\u043c\u0435\u0442\u0430\u043b\u043b\u0443\u0440\u0433\u0438\u0447\u0435\u0441\u043a\u0438\u0439"
222
+ ],
223
+ "\u0434\u043e\u043b\u0433\u043e\u0441\u0440\u043e\u0447\u043d\u044b\u043c": [
224
+ "\u0434\u043e\u043b\u0433\u043e",
225
+ "\u0441\u0440\u043e\u0447\u043d\u044b\u043c"
226
+ ],
227
+ "\u043a\u043e\u0441\u043c\u043e\u0437\u0435\u043c\u043d\u044b\u0445": [
228
+ "\u043a\u043e\u0441\u043c\u043e",
229
+ "\u0437\u0435\u043c\u043d\u044b\u0445"
230
+ ],
231
+ "\u0441\u0443\u0434\u0435\u0431\u043d\u043e\u043c\u0435\u0434\u0438\u0446\u0438\u043d\u0441\u043a\u043e\u0439": [
232
+ "\u0441\u0443\u0434\u0435\u0431\u043d\u043e",
233
+ "\u043c\u0435\u0434\u0438\u0446\u0438\u043d\u0441\u043a\u043e\u0439"
234
+ ]
235
+ },
236
+ "ADJ+NOUN": {
237
+ "\u0420\u043e\u0441\u0433\u043e\u0441\u0441\u0442\u0440\u0430\u0445\u0430": [
238
+ "\u0420\u043e\u0441",
239
+ "\u0433\u043e\u0441\u0441\u0442\u0440\u0430\u0445\u0430"
240
+ ],
241
+ "\u0420\u043e\u0441\u043a\u0443\u043b\u044c\u0442\u0443\u0440\u044b": [
242
+ "\u0420\u043e\u0441",
243
+ "\u043a\u0443\u043b\u044c\u0442\u0443\u0440\u044b"
244
+ ],
245
+ "\u0433\u043e\u0441\u0437\u0430\u043a\u0443\u043f\u043e\u043a": [
246
+ "\u0433\u043e\u0441",
247
+ "\u0437\u0430\u043a\u0443\u043f\u043e\u043a"
248
+ ],
249
+ "\u0433\u043e\u0441\u043a\u043e\u0440\u043f\u043e\u0440\u0430\u0446\u0438\u044f\u043c": [
250
+ "\u0433\u043e\u0441",
251
+ "\u043a\u043e\u0440\u043f\u043e\u0440\u0430\u0446\u0438\u044f\u043c"
252
+ ],
253
+ "\u0433\u043e\u0441\u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0430": [
254
+ "\u0433\u043e\u0441",
255
+ "\u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0430"
256
+ ],
257
+ "\u0433\u043e\u0441\u0441\u043b\u0443\u0436\u0431\u044b": [
258
+ "\u0433\u043e\u0441",
259
+ "\u0441\u043b\u0443\u0436\u0431\u044b"
260
+ ],
261
+ "\u043c\u0435\u0434\u0443\u0447\u0440\u0435\u0436\u0434\u0435\u043d\u0438\u0438": [
262
+ "\u043c\u0435\u0434",
263
+ "\u0443\u0447\u0440\u0435\u0436\u0434\u0435\u043d\u0438\u0438"
264
+ ],
265
+ "\u0441\u0435\u043b\u044c\u0445\u043e\u0437\u043f\u0440\u043e\u0434\u0443\u043a\u0446\u0438\u0438": [
266
+ "\u0441\u0435\u043b\u044c\u0445\u043e\u0437",
267
+ "\u043f\u0440\u043e\u0434\u0443\u043a\u0446\u0438\u0438"
268
+ ]
269
+ },
270
+ "ADJ+VERB": {
271
+ "\u041b\u0435\u0432\u043e\u043d\u0430\u0441\u0442\u0440\u043e\u0435\u043d\u043d\u044b\u0435": [
272
+ "\u041b\u0435\u0432\u043e",
273
+ "\u043d\u0430\u0441\u0442\u0440\u043e\u0435\u043d\u043d\u044b\u0435"
274
+ ]
275
+ },
276
+ "ADP+DET": {
277
+ "\u0441\u0434\u0440\u0443\u0433\u0438\u043c\u0438": [
278
+ "\u0441",
279
+ "\u0434\u0440\u0443\u0433\u0438\u043c\u0438"
280
+ ],
281
+ "\u0441\u0442\u0435\u0445": [
282
+ "\u0441",
283
+ "\u0442\u0435\u0445"
284
+ ]
285
+ },
286
+ "ADP+PRON": {
287
+ "\u0441\u043d\u0438\u043c": [
288
+ "\u0441",
289
+ "\u043d\u0438\u043c"
290
+ ]
291
+ },
292
+ "ADV+VERB": {
293
+ "\u043d\u0435\u0433\u0434\u0435\u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u0430\u0442\u044c": [
294
+ "\u043d\u0435\u0433\u0434\u0435",
295
+ "\u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u0430\u0442\u044c"
296
+ ]
297
+ },
298
+ "NUM+NOUN": {
299
+ "\u041f\u043e\u043b\u043b\u0438\u0442\u0440\u0430": [
300
+ "\u041f\u043e\u043b",
301
+ "\u043b\u0438\u0442\u0440\u0430"
302
+ ],
303
+ "\u043f\u043e\u043b\u0432\u0435\u043a\u0430": [
304
+ "\u043f\u043e\u043b",
305
+ "\u0432\u0435\u043a\u0430"
306
+ ],
307
+ "\u043f\u043e\u043b\u0433\u043e\u0434\u0430": [
308
+ "\u043f\u043e\u043b",
309
+ "\u0433\u043e\u0434\u0430"
310
+ ],
311
+ "\u043f\u043e\u043b\u0434\u043d\u044f": [
312
+ "\u043f\u043e\u043b",
313
+ "\u0434\u043d\u044f"
314
+ ],
315
+ "\u043f\u043e\u043b\u0434\u044e\u0436\u0438\u043d\u044b": [
316
+ "\u043f\u043e\u043b",
317
+ "\u0434\u044e\u0436\u0438\u043d\u044b"
318
+ ],
319
+ "\u043f\u043e\u043b\u043a\u0438\u043b\u043e": [
320
+ "\u043f\u043e\u043b",
321
+ "\u043a\u0438\u043b\u043e"
322
+ ],
323
+ "\u043f\u043e\u043b\u043a\u0438\u043b\u043e\u0433\u0440\u0430\u043c\u043c\u0430": [
324
+ "\u043f\u043e\u043b",
325
+ "\u043a\u0438\u043b\u043e\u0433\u0440\u0430\u043c\u043c\u0430"
326
+ ],
327
+ "\u043f\u043e\u043b\u043a\u043e\u0442\u043b\u0435\u0442\u044b": [
328
+ "\u043f\u043e\u043b",
329
+ "\u043a\u043e\u0442\u043b\u0435\u0442\u044b"
330
+ ],
331
+ "\u043f\u043e\u043b\u043a\u0443\u0441\u043e\u0447\u043a\u0430": [
332
+ "\u043f\u043e\u043b",
333
+ "\u043a\u0443\u0441\u043e\u0447\u043a\u0430"
334
+ ],
335
+ "\u043f\u043e\u043b\u043c\u0435\u0441\u044f\u0446\u0430": [
336
+ "\u043f\u043e\u043b",
337
+ "\u043c\u0435\u0441\u044f\u0446\u0430"
338
+ ],
339
+ "\u043f\u043e\u043b\u043c\u0435\u0442\u0440\u0430": [
340
+ "\u043f\u043e\u043b",
341
+ "\u043c\u0435\u0442\u0440\u0430"
342
+ ],
343
+ "\u043f\u043e\u043b\u043c\u0435\u0448\u043a\u0430": [
344
+ "\u043f\u043e\u043b",
345
+ "\u043c\u0435\u0448\u043a\u0430"
346
+ ],
347
+ "\u043f\u043e\u043b\u043c\u0438\u043b\u043b\u0438\u0430\u0440\u0434\u0430": [
348
+ "\u043f\u043e\u043b",
349
+ "\u043c\u0438\u043b\u043b\u0438\u0430\u0440\u0434\u0430"
350
+ ],
351
+ "\u043f\u043e\u043b\u043c\u0438\u043b\u043b\u0438\u043e\u043d\u0430": [
352
+ "\u043f\u043e\u043b",
353
+ "\u043c\u0438\u043b\u043b\u0438\u043e\u043d\u0430"
354
+ ],
355
+ "\u043f\u043e\u043b\u043c\u0438\u043d\u0443\u0442\u044b": [
356
+ "\u043f\u043e\u043b",
357
+ "\u043c\u0438\u043d\u0443\u0442\u044b"
358
+ ],
359
+ "\u043f\u043e\u043b\u043c\u044b\u0441\u043b\u0438": [
360
+ "\u043f\u043e\u043b",
361
+ "\u043c\u044b\u0441\u043b\u0438"
362
+ ],
363
+ "\u043f\u043e\u043b\u043f\u0443\u0442\u0438": [
364
+ "\u043f\u043e\u043b",
365
+ "\u043f\u0443\u0442\u0438"
366
+ ],
367
+ "\u043f\u043e\u043b\u0447\u0430\u0441\u0430": [
368
+ "\u043f\u043e\u043b",
369
+ "\u0447\u0430\u0441\u0430"
370
+ ]
371
+ },
372
+ "NUM+SYM": {
373
+ "20\u00b0": [
374
+ "20",
375
+ "\u00b0"
376
+ ],
377
+ "2\u00b0": [
378
+ "2",
379
+ "\u00b0"
380
+ ],
381
+ "90\u00b0": [
382
+ "90",
383
+ "\u00b0"
384
+ ]
385
+ },
386
+ "PART+PRON": {
387
+ "\u0434\u0430\u0442\u043e": [
388
+ "\u0434\u0430",
389
+ "\u0442\u043e"
390
+ ]
391
+ },
392
+ "SYM+NUM": {
393
+ "\u21161": [
394
+ "\u2116",
395
+ "1"
396
+ ],
397
+ "\u2116159": [
398
+ "\u2116",
399
+ "159"
400
+ ],
401
+ "\u211619": [
402
+ "\u2116",
403
+ "19"
404
+ ],
405
+ "\u21162": [
406
+ "\u2116",
407
+ "2"
408
+ ],
409
+ "\u211636": [
410
+ "\u2116",
411
+ "36"
412
+ ],
413
+ "\u21165": [
414
+ "\u2116",
415
+ "5"
416
+ ]
417
+ },
418
+ "VERB+ADV": {
419
+ "\u041d\u0435\u043a\u043e\u0433\u0434\u0430": [
420
+ "\u041d\u0435",
421
+ "\u043a\u043e\u0433\u0434\u0430"
422
+ ],
423
+ "\u043d\u0435\u0437\u0430\u0447\u0435\u043c": [
424
+ "\u043d\u0435",
425
+ "\u0437\u0430\u0447\u0435\u043c"
426
+ ],
427
+ "\u043d\u0435\u043a\u043e\u0433\u0434\u0430": [
428
+ "\u043d\u0435",
429
+ "\u043a\u043e\u0433\u0434\u0430"
430
+ ],
431
+ "\u043d\u0435\u043a\u0443\u0434\u0430": [
432
+ "\u043d\u0435",
433
+ "\u043a\u0443\u0434\u0430"
434
+ ]
435
+ },
436
+ "VERB+PRON": {
437
+ "\u041d\u0435\u043a\u043e\u043c\u0443": [
438
+ "\u041d\u0435",
439
+ "\u043a\u043e\u043c\u0443"
440
+ ],
441
+ "\u043d\u0435\u043a\u043e\u0433\u043e": [
442
+ "\u043d\u0435",
443
+ "\u043a\u043e\u0433\u043e"
444
+ ],
445
+ "\u043d\u0435\u043a\u043e\u043c\u0443": [
446
+ "\u043d\u0435",
447
+ "\u043a\u043e\u043c\u0443"
448
+ ],
449
+ "\u043d\u0435\u0447\u0435\u0433\u043e": [
450
+ "\u043d\u0435",
451
+ "\u0447\u0435\u0433\u043e"
452
+ ],
453
+ "\u043d\u0435\u0447\u0435\u043c": [
454
+ "\u043d\u0435",
455
+ "\u0447\u0435\u043c"
456
+ ],
457
+ "\u043d\u0435\u0447\u0435\u043c\u0443": [
458
+ "\u043d\u0435",
459
+ "\u0447\u0435\u043c\u0443"
460
+ ]
461
+ },
462
+ "X+X": {
463
+ "xxx": [
464
+ "x",
465
+ "xx"
466
+ ],
467
+ "xxxx": [
468
+ "x",
469
+ "xxx"
470
+ ]
471
+ }
472
+ }
473
+ },
474
+ "tokenizer_class": "BertTokenizerFast",
475
+ "torch_dtype": "float32",
476
+ "transformers_version": "4.14.1",
477
+ "type_vocab_size": 2,
478
+ "use_cache": true,
479
+ "vocab_size": 119547
480
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e6ba8490ae024fdb7b312840c7eef31daa7a78fcc1427ed25193d1d7db5627
3
+ size 709408561
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
supar.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67026db7795c9288d1cb9e4fbdb792af061b24e2a8bacbd2dda066e4ed2d98a9
3
+ size 792040869
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "do_basic_tokenize": true, "tokenizer_class": "BertTokenizerFast"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff