Hugging Face's logo

KoichiYasuoka
/
deberta-base-japanese-aozora-ud-head

Question Answering
Transformers
PyTorch
Japanese
deberta-v2
japanese
dependency-parsing
Inference Endpoints
Model card Files Community
2
KoichiYasuoka commited on
Commit
a746cb4
•
1 Parent(s): 76fee45

initial release

Browse files
Files changed (6) hide show
  1. tagger/config.json +374 -0
  2. tagger/pytorch_model.bin +3 -0
  3. tagger/special_tokens_map.json +1 -0
  4. tagger/spm.model +3 -0
  5. tagger/tokenizer.json +0 -0
  6. tagger/tokenizer_config.json +1 -0
tagger/config.json ADDED
@@ -0,0 +1,374 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "pos",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B-ADJ|_|acl",
14
+ "1": "B-ADJ|_|advcl",
15
+ "2": "B-ADJ|_|amod",
16
+ "3": "B-ADJ|_|ccomp",
17
+ "4": "B-ADJ|_|csubj",
18
+ "5": "B-ADJ|_|dep",
19
+ "6": "B-ADJ|_|dislocated",
20
+ "7": "B-ADJ|_|nmod",
21
+ "8": "B-ADJ|_|nsubj",
22
+ "9": "B-ADJ|_|obj",
23
+ "10": "B-ADJ|_|obl",
24
+ "11": "B-ADJ|_|root",
25
+ "12": "B-ADP|_|case",
26
+ "13": "B-ADP|_|fixed",
27
+ "14": "B-ADV|_|advcl",
28
+ "15": "B-ADV|_|advmod",
29
+ "16": "B-ADV|_|dep",
30
+ "17": "B-ADV|_|obj",
31
+ "18": "B-ADV|_|root",
32
+ "19": "B-AUX|Polarity=Neg|aux",
33
+ "20": "B-AUX|_|aux",
34
+ "21": "B-AUX|_|cop",
35
+ "22": "B-AUX|_|fixed",
36
+ "23": "B-AUX|_|root",
37
+ "24": "B-CCONJ|_|cc",
38
+ "25": "B-DET|_|det",
39
+ "26": "B-INTJ|_|discourse",
40
+ "27": "B-INTJ|_|root",
41
+ "28": "B-NOUN|Polarity=Neg|obl",
42
+ "29": "B-NOUN|Polarity=Neg|root",
43
+ "30": "B-NOUN|_|acl",
44
+ "31": "B-NOUN|_|advcl",
45
+ "32": "B-NOUN|_|ccomp",
46
+ "33": "B-NOUN|_|compound",
47
+ "34": "B-NOUN|_|csubj",
48
+ "35": "B-NOUN|_|dislocated",
49
+ "36": "B-NOUN|_|nmod",
50
+ "37": "B-NOUN|_|nsubj",
51
+ "38": "B-NOUN|_|obj",
52
+ "39": "B-NOUN|_|obl",
53
+ "40": "B-NOUN|_|root",
54
+ "41": "B-NUM|_|advcl",
55
+ "42": "B-NUM|_|compound",
56
+ "43": "B-NUM|_|dislocated",
57
+ "44": "B-NUM|_|nmod",
58
+ "45": "B-NUM|_|nsubj",
59
+ "46": "B-NUM|_|nummod",
60
+ "47": "B-NUM|_|obj",
61
+ "48": "B-NUM|_|obl",
62
+ "49": "B-NUM|_|root",
63
+ "50": "B-PART|_|mark",
64
+ "51": "B-PRON|_|acl",
65
+ "52": "B-PRON|_|advcl",
66
+ "53": "B-PRON|_|dislocated",
67
+ "54": "B-PRON|_|nmod",
68
+ "55": "B-PRON|_|nsubj",
69
+ "56": "B-PRON|_|obj",
70
+ "57": "B-PRON|_|obl",
71
+ "58": "B-PRON|_|root",
72
+ "59": "B-PROPN|_|acl",
73
+ "60": "B-PROPN|_|advcl",
74
+ "61": "B-PROPN|_|compound",
75
+ "62": "B-PROPN|_|dislocated",
76
+ "63": "B-PROPN|_|nmod",
77
+ "64": "B-PROPN|_|nsubj",
78
+ "65": "B-PROPN|_|obj",
79
+ "66": "B-PROPN|_|obl",
80
+ "67": "B-PROPN|_|root",
81
+ "68": "B-PUNCT|_|punct",
82
+ "69": "B-SCONJ|_|mark",
83
+ "70": "B-SYM|_|compound",
84
+ "71": "B-SYM|_|dep",
85
+ "72": "B-SYM|_|nmod",
86
+ "73": "B-SYM|_|obl",
87
+ "74": "B-VERB|_|acl",
88
+ "75": "B-VERB|_|advcl",
89
+ "76": "B-VERB|_|ccomp",
90
+ "77": "B-VERB|_|compound",
91
+ "78": "B-VERB|_|csubj",
92
+ "79": "B-VERB|_|dislocated",
93
+ "80": "B-VERB|_|nmod",
94
+ "81": "B-VERB|_|obj",
95
+ "82": "B-VERB|_|obl",
96
+ "83": "B-VERB|_|root",
97
+ "84": "B-X|_|dep",
98
+ "85": "B-X|_|nmod",
99
+ "86": "I-ADJ|_|acl",
100
+ "87": "I-ADJ|_|advcl",
101
+ "88": "I-ADJ|_|amod",
102
+ "89": "I-ADJ|_|ccomp",
103
+ "90": "I-ADJ|_|csubj",
104
+ "91": "I-ADJ|_|dep",
105
+ "92": "I-ADJ|_|dislocated",
106
+ "93": "I-ADJ|_|nmod",
107
+ "94": "I-ADJ|_|nsubj",
108
+ "95": "I-ADJ|_|obj",
109
+ "96": "I-ADJ|_|obl",
110
+ "97": "I-ADJ|_|root",
111
+ "98": "I-ADP|_|case",
112
+ "99": "I-ADP|_|fixed",
113
+ "100": "I-ADV|_|advcl",
114
+ "101": "I-ADV|_|advmod",
115
+ "102": "I-ADV|_|dep",
116
+ "103": "I-ADV|_|obj",
117
+ "104": "I-ADV|_|root",
118
+ "105": "I-AUX|Polarity=Neg|aux",
119
+ "106": "I-AUX|_|aux",
120
+ "107": "I-AUX|_|cop",
121
+ "108": "I-AUX|_|fixed",
122
+ "109": "I-AUX|_|root",
123
+ "110": "I-CCONJ|_|cc",
124
+ "111": "I-DET|_|det",
125
+ "112": "I-INTJ|_|discourse",
126
+ "113": "I-INTJ|_|root",
127
+ "114": "I-NOUN|Polarity=Neg|obl",
128
+ "115": "I-NOUN|Polarity=Neg|root",
129
+ "116": "I-NOUN|_|acl",
130
+ "117": "I-NOUN|_|advcl",
131
+ "118": "I-NOUN|_|ccomp",
132
+ "119": "I-NOUN|_|compound",
133
+ "120": "I-NOUN|_|csubj",
134
+ "121": "I-NOUN|_|dislocated",
135
+ "122": "I-NOUN|_|nmod",
136
+ "123": "I-NOUN|_|nsubj",
137
+ "124": "I-NOUN|_|obj",
138
+ "125": "I-NOUN|_|obl",
139
+ "126": "I-NOUN|_|root",
140
+ "127": "I-NUM|_|advcl",
141
+ "128": "I-NUM|_|compound",
142
+ "129": "I-NUM|_|dislocated",
143
+ "130": "I-NUM|_|nmod",
144
+ "131": "I-NUM|_|nsubj",
145
+ "132": "I-NUM|_|nummod",
146
+ "133": "I-NUM|_|obj",
147
+ "134": "I-NUM|_|obl",
148
+ "135": "I-NUM|_|root",
149
+ "136": "I-PART|_|mark",
150
+ "137": "I-PRON|_|acl",
151
+ "138": "I-PRON|_|advcl",
152
+ "139": "I-PRON|_|dislocated",
153
+ "140": "I-PRON|_|nmod",
154
+ "141": "I-PRON|_|nsubj",
155
+ "142": "I-PRON|_|obj",
156
+ "143": "I-PRON|_|obl",
157
+ "144": "I-PRON|_|root",
158
+ "145": "I-PROPN|_|acl",
159
+ "146": "I-PROPN|_|advcl",
160
+ "147": "I-PROPN|_|compound",
161
+ "148": "I-PROPN|_|dislocated",
162
+ "149": "I-PROPN|_|nmod",
163
+ "150": "I-PROPN|_|nsubj",
164
+ "151": "I-PROPN|_|obj",
165
+ "152": "I-PROPN|_|obl",
166
+ "153": "I-PROPN|_|root",
167
+ "154": "I-PUNCT|_|punct",
168
+ "155": "I-SCONJ|_|mark",
169
+ "156": "I-SYM|_|dep",
170
+ "157": "I-SYM|_|nmod",
171
+ "158": "I-VERB|_|acl",
172
+ "159": "I-VERB|_|advcl",
173
+ "160": "I-VERB|_|ccomp",
174
+ "161": "I-VERB|_|compound",
175
+ "162": "I-VERB|_|csubj",
176
+ "163": "I-VERB|_|dislocated",
177
+ "164": "I-VERB|_|nmod",
178
+ "165": "I-VERB|_|obj",
179
+ "166": "I-VERB|_|obl",
180
+ "167": "I-VERB|_|root",
181
+ "168": "I-X|_|nmod"
182
+ },
183
+ "initializer_range": 0.02,
184
+ "intermediate_size": 3072,
185
+ "label2id": {
186
+ "B-ADJ|_|acl": 0,
187
+ "B-ADJ|_|advcl": 1,
188
+ "B-ADJ|_|amod": 2,
189
+ "B-ADJ|_|ccomp": 3,
190
+ "B-ADJ|_|csubj": 4,
191
+ "B-ADJ|_|dep": 5,
192
+ "B-ADJ|_|dislocated": 6,
193
+ "B-ADJ|_|nmod": 7,
194
+ "B-ADJ|_|nsubj": 8,
195
+ "B-ADJ|_|obj": 9,
196
+ "B-ADJ|_|obl": 10,
197
+ "B-ADJ|_|root": 11,
198
+ "B-ADP|_|case": 12,
199
+ "B-ADP|_|fixed": 13,
200
+ "B-ADV|_|advcl": 14,
201
+ "B-ADV|_|advmod": 15,
202
+ "B-ADV|_|dep": 16,
203
+ "B-ADV|_|obj": 17,
204
+ "B-ADV|_|root": 18,
205
+ "B-AUX|Polarity=Neg|aux": 19,
206
+ "B-AUX|_|aux": 20,
207
+ "B-AUX|_|cop": 21,
208
+ "B-AUX|_|fixed": 22,
209
+ "B-AUX|_|root": 23,
210
+ "B-CCONJ|_|cc": 24,
211
+ "B-DET|_|det": 25,
212
+ "B-INTJ|_|discourse": 26,
213
+ "B-INTJ|_|root": 27,
214
+ "B-NOUN|Polarity=Neg|obl": 28,
215
+ "B-NOUN|Polarity=Neg|root": 29,
216
+ "B-NOUN|_|acl": 30,
217
+ "B-NOUN|_|advcl": 31,
218
+ "B-NOUN|_|ccomp": 32,
219
+ "B-NOUN|_|compound": 33,
220
+ "B-NOUN|_|csubj": 34,
221
+ "B-NOUN|_|dislocated": 35,
222
+ "B-NOUN|_|nmod": 36,
223
+ "B-NOUN|_|nsubj": 37,
224
+ "B-NOUN|_|obj": 38,
225
+ "B-NOUN|_|obl": 39,
226
+ "B-NOUN|_|root": 40,
227
+ "B-NUM|_|advcl": 41,
228
+ "B-NUM|_|compound": 42,
229
+ "B-NUM|_|dislocated": 43,
230
+ "B-NUM|_|nmod": 44,
231
+ "B-NUM|_|nsubj": 45,
232
+ "B-NUM|_|nummod": 46,
233
+ "B-NUM|_|obj": 47,
234
+ "B-NUM|_|obl": 48,
235
+ "B-NUM|_|root": 49,
236
+ "B-PART|_|mark": 50,
237
+ "B-PRON|_|acl": 51,
238
+ "B-PRON|_|advcl": 52,
239
+ "B-PRON|_|dislocated": 53,
240
+ "B-PRON|_|nmod": 54,
241
+ "B-PRON|_|nsubj": 55,
242
+ "B-PRON|_|obj": 56,
243
+ "B-PRON|_|obl": 57,
244
+ "B-PRON|_|root": 58,
245
+ "B-PROPN|_|acl": 59,
246
+ "B-PROPN|_|advcl": 60,
247
+ "B-PROPN|_|compound": 61,
248
+ "B-PROPN|_|dislocated": 62,
249
+ "B-PROPN|_|nmod": 63,
250
+ "B-PROPN|_|nsubj": 64,
251
+ "B-PROPN|_|obj": 65,
252
+ "B-PROPN|_|obl": 66,
253
+ "B-PROPN|_|root": 67,
254
+ "B-PUNCT|_|punct": 68,
255
+ "B-SCONJ|_|mark": 69,
256
+ "B-SYM|_|compound": 70,
257
+ "B-SYM|_|dep": 71,
258
+ "B-SYM|_|nmod": 72,
259
+ "B-SYM|_|obl": 73,
260
+ "B-VERB|_|acl": 74,
261
+ "B-VERB|_|advcl": 75,
262
+ "B-VERB|_|ccomp": 76,
263
+ "B-VERB|_|compound": 77,
264
+ "B-VERB|_|csubj": 78,
265
+ "B-VERB|_|dislocated": 79,
266
+ "B-VERB|_|nmod": 80,
267
+ "B-VERB|_|obj": 81,
268
+ "B-VERB|_|obl": 82,
269
+ "B-VERB|_|root": 83,
270
+ "B-X|_|dep": 84,
271
+ "B-X|_|nmod": 85,
272
+ "I-ADJ|_|acl": 86,
273
+ "I-ADJ|_|advcl": 87,
274
+ "I-ADJ|_|amod": 88,
275
+ "I-ADJ|_|ccomp": 89,
276
+ "I-ADJ|_|csubj": 90,
277
+ "I-ADJ|_|dep": 91,
278
+ "I-ADJ|_|dislocated": 92,
279
+ "I-ADJ|_|nmod": 93,
280
+ "I-ADJ|_|nsubj": 94,
281
+ "I-ADJ|_|obj": 95,
282
+ "I-ADJ|_|obl": 96,
283
+ "I-ADJ|_|root": 97,
284
+ "I-ADP|_|case": 98,
285
+ "I-ADP|_|fixed": 99,
286
+ "I-ADV|_|advcl": 100,
287
+ "I-ADV|_|advmod": 101,
288
+ "I-ADV|_|dep": 102,
289
+ "I-ADV|_|obj": 103,
290
+ "I-ADV|_|root": 104,
291
+ "I-AUX|Polarity=Neg|aux": 105,
292
+ "I-AUX|_|aux": 106,
293
+ "I-AUX|_|cop": 107,
294
+ "I-AUX|_|fixed": 108,
295
+ "I-AUX|_|root": 109,
296
+ "I-CCONJ|_|cc": 110,
297
+ "I-DET|_|det": 111,
298
+ "I-INTJ|_|discourse": 112,
299
+ "I-INTJ|_|root": 113,
300
+ "I-NOUN|Polarity=Neg|obl": 114,
301
+ "I-NOUN|Polarity=Neg|root": 115,
302
+ "I-NOUN|_|acl": 116,
303
+ "I-NOUN|_|advcl": 117,
304
+ "I-NOUN|_|ccomp": 118,
305
+ "I-NOUN|_|compound": 119,
306
+ "I-NOUN|_|csubj": 120,
307
+ "I-NOUN|_|dislocated": 121,
308
+ "I-NOUN|_|nmod": 122,
309
+ "I-NOUN|_|nsubj": 123,
310
+ "I-NOUN|_|obj": 124,
311
+ "I-NOUN|_|obl": 125,
312
+ "I-NOUN|_|root": 126,
313
+ "I-NUM|_|advcl": 127,
314
+ "I-NUM|_|compound": 128,
315
+ "I-NUM|_|dislocated": 129,
316
+ "I-NUM|_|nmod": 130,
317
+ "I-NUM|_|nsubj": 131,
318
+ "I-NUM|_|nummod": 132,
319
+ "I-NUM|_|obj": 133,
320
+ "I-NUM|_|obl": 134,
321
+ "I-NUM|_|root": 135,
322
+ "I-PART|_|mark": 136,
323
+ "I-PRON|_|acl": 137,
324
+ "I-PRON|_|advcl": 138,
325
+ "I-PRON|_|dislocated": 139,
326
+ "I-PRON|_|nmod": 140,
327
+ "I-PRON|_|nsubj": 141,
328
+ "I-PRON|_|obj": 142,
329
+ "I-PRON|_|obl": 143,
330
+ "I-PRON|_|root": 144,
331
+ "I-PROPN|_|acl": 145,
332
+ "I-PROPN|_|advcl": 146,
333
+ "I-PROPN|_|compound": 147,
334
+ "I-PROPN|_|dislocated": 148,
335
+ "I-PROPN|_|nmod": 149,
336
+ "I-PROPN|_|nsubj": 150,
337
+ "I-PROPN|_|obj": 151,
338
+ "I-PROPN|_|obl": 152,
339
+ "I-PROPN|_|root": 153,
340
+ "I-PUNCT|_|punct": 154,
341
+ "I-SCONJ|_|mark": 155,
342
+ "I-SYM|_|dep": 156,
343
+ "I-SYM|_|nmod": 157,
344
+ "I-VERB|_|acl": 158,
345
+ "I-VERB|_|advcl": 159,
346
+ "I-VERB|_|ccomp": 160,
347
+ "I-VERB|_|compound": 161,
348
+ "I-VERB|_|csubj": 162,
349
+ "I-VERB|_|dislocated": 163,
350
+ "I-VERB|_|nmod": 164,
351
+ "I-VERB|_|obj": 165,
352
+ "I-VERB|_|obl": 166,
353
+ "I-VERB|_|root": 167,
354
+ "I-X|_|nmod": 168
355
+ },
356
+ "layer_norm_eps": 1e-07,
357
+ "max_position_embeddings": 512,
358
+ "max_relative_positions": -1,
359
+ "model_type": "deberta-v2",
360
+ "num_attention_heads": 12,
361
+ "num_hidden_layers": 12,
362
+ "pad_token_id": 1,
363
+ "pooler_dropout": 0,
364
+ "pooler_hidden_act": "gelu",
365
+ "pooler_hidden_size": 768,
366
+ "pos_att_type": null,
367
+ "position_biased_input": true,
368
+ "relative_attention": false,
369
+ "tokenizer_class": "DebertaV2TokenizerFast",
370
+ "torch_dtype": "float32",
371
+ "transformers_version": "4.19.4",
372
+ "type_vocab_size": 0,
373
+ "vocab_size": 32000
374
+ }
tagger/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c261f7caed9b512d349d60b7def09f3eb26ef1075432140ca3d00dfa73ef9389
3
+ size 440691763
tagger/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tagger/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b
3
+ size 1
tagger/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tagger/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": true, "keep_accents": true, "model_max_length": 512, "tokenizer_class": "DebertaV2TokenizerFast"}