Hugging Face's logo

KoichiYasuoka
/
deberta-base-ainu-upos

Token Classification
Transformers
PyTorch
Ainu (Japan)
deberta-v2
ainu
pos
dependency-parsing
Inference Endpoints
Model card Files Community
5
KoichiYasuoka commited on
Commit
48c1a3e
•
1 Parent(s): d740efd

model improved

Browse files
Files changed (4) hide show
  1. config.json +393 -542
  2. pytorch_model.bin +2 -2
  3. supar.model +2 -2
  4. tokenizer.json +0 -0
config.json CHANGED
@@ -14,214 +14,192 @@
14
  "2": "ADP|\u5f8c\u7f6e\u526f\u8a5e|_",
15
  "3": "ADP|\u683c\u52a9\u8a5e|_",
16
  "4": "ADV|\u526f\u8a5e|_",
17
- "5": "ADV|\u9593\u6295\u8a5e|_",
18
- "6": "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
19
- "7": "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
20
- "8": "AUX|\u52a9\u52a9\u8a5e|_",
21
- "9": "AUX|\u52a9\u52d5\u8a5e|_",
22
- "10": "B-ADP|\u526f\u52a9\u8a5e|_",
23
- "11": "B-ADP|\u526f\u8a5e|_",
24
- "12": "B-ADP|\u5f8c\u7f6e\u526f\u8a5e|_",
25
- "13": "B-ADP|\u683c\u52a9\u8a5e|_",
26
- "14": "B-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
27
- "15": "B-ADV|\u526f\u8a5e|_",
28
- "16": "B-ADV|\u9593\u6295\u8a5e|_",
29
- "17": "B-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
30
- "18": "B-AUX|\u52a9\u52d5\u8a5e|_",
31
- "19": "B-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_",
32
- "20": "B-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
33
- "21": "B-CCONJ|\u63a5\u7d9a\u8a5e|_",
34
- "22": "B-DET|\u526f\u8a5e|_",
35
- "23": "B-DET|\u9023\u4f53\u8a5e|_",
36
- "24": "B-DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_",
37
- "25": "B-INFR.EV|\u5f62\u5f0f\u540d\u8a5e|_",
38
- "26": "B-INTJ|\u9593\u6295\u8a5e|_",
39
- "27": "B-NOUN|\u4eba\u79f0\u63a5\u8f9e|_",
40
- "28": "B-NOUN|\u4ee3\u540d\u8a5e|_",
41
- "29": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
42
- "30": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
43
- "31": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_",
44
- "32": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_",
45
- "33": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
46
- "34": "B-NOUN|\u540d\u8a5e|_",
47
- "35": "B-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
48
- "36": "B-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_",
49
- "37": "B-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
50
- "38": "B-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
51
- "39": "B-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
52
- "40": "B-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
53
- "41": "B-NOUN|\u56fa\u6709\u540d\u8a5e|_",
54
- "42": "B-NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
55
- "43": "B-NUM|\u6570\u8a5e|_",
56
- "44": "B-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_",
57
- "45": "B-NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
58
- "46": "B-PART|[\u7d42\u52a9\u8a5e]|_",
59
- "47": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_",
60
- "48": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
61
- "49": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
62
- "50": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
63
- "51": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
64
- "52": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_",
65
- "53": "B-PART|\u52a9\u52d5\u8a5e|_",
66
- "54": "B-PART|\u63a5\u5c3e\u8f9e|_",
67
- "55": "B-PART|\u63a5\u7d9a\u52a9\u8a5e|_",
68
- "56": "B-PART|\u63a5\u982d\u8f9e|_",
69
- "57": "B-PART|\u7d42\u52a9\u8a5e|_",
70
- "58": "B-PART|\u7d42\u52a9\u8a5e\uff09|_",
71
- "59": "B-PART|\u81ea\u52d5\u8a5e|_",
72
- "60": "B-PART|\uff08\u7d42\u52a9\u8a5e\uff09|_",
73
- "61": "B-PRON|\u4ee3\u540d\u8a5e|_",
74
- "62": "B-PROPN|\u56fa\u6709\u540d\u8a5e|_",
75
- "63": "B-PUNCT|\u8a18\u53f7|_",
76
- "64": "B-SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_",
77
- "65": "B-SCONJ|\u4ed6\u52d5\u8a5e|_",
78
- "66": "B-SCONJ|\u526f\u8a5e|_",
79
- "67": "B-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
80
- "68": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
81
- "69": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_",
82
- "70": "B-SCONJ|\u63a5\u7d9a\u8a5e|_",
83
- "71": "B-SCONJ|\u683c\u52a9\u8a5e|_",
84
- "72": "B-VERB|[\u81ea\u52d5\u8a5e]|_",
85
- "73": "B-VERB|\u4ed6\u52d5\u8a5e|_",
86
- "74": "B-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
87
- "75": "B-VERB|\u4ed6\u52d5\u8a5e\uff1f|_",
88
- "76": "B-VERB|\u5b8c\u5168\u52d5\u8a5e|_",
89
- "77": "B-VERB|\u683c\u52a9\u8a5e|_",
90
- "78": "B-VERB|\u81ea\u52d5\u8a5e|_",
91
- "79": "B-VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_",
92
- "80": "B-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_",
93
- "81": "B-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
94
- "82": "B-VERB|\uff08\u81ea\u52d5\u8a5e|_",
95
- "83": "B-VERT|\u4ed6\u52d5\u8a5e|_",
96
- "84": "B-X|_|_",
97
- "85": "CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
98
- "86": "CCONJ|\u63a5\u7d9a\u8a5e|_",
99
- "87": "DET|\u81ea\u52d5\u8a5e|_",
100
- "88": "DET|\u9023\u4f53\u8a5e|_",
101
- "89": "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_",
102
- "90": "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_",
103
- "91": "I-ADP|\u526f\u52a9\u8a5e|_",
104
- "92": "I-ADP|\u526f\u8a5e|_",
105
- "93": "I-ADP|\u5f8c\u7f6e\u526f\u8a5e|_",
106
- "94": "I-ADP|\u683c\u52a9\u8a5e|_",
107
- "95": "I-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
108
- "96": "I-ADV|\u526f\u8a5e|_",
109
- "97": "I-ADV|\u9593\u6295\u8a5e|_",
110
- "98": "I-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
111
- "99": "I-AUX|\u52a9\u52d5\u8a5e|_",
112
- "100": "I-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_",
113
- "101": "I-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
114
- "102": "I-CCONJ|\u63a5\u7d9a\u8a5e|_",
115
- "103": "I-DET|\u526f\u8a5e|_",
116
- "104": "I-DET|\u9023\u4f53\u8a5e|_",
117
- "105": "I-DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_",
118
- "106": "I-INFR.EV|\u5f62\u5f0f\u540d\u8a5e|_",
119
- "107": "I-INTJ|\u9593\u6295\u8a5e|_",
120
- "108": "I-NOUN|\u4eba\u79f0\u63a5\u8f9e|_",
121
- "109": "I-NOUN|\u4ee3\u540d\u8a5e|_",
122
- "110": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
123
- "111": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
124
- "112": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_",
125
- "113": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_",
126
- "114": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
127
- "115": "I-NOUN|\u540d\u8a5e|_",
128
- "116": "I-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
129
- "117": "I-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_",
130
- "118": "I-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
131
- "119": "I-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
132
- "120": "I-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
133
- "121": "I-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
134
- "122": "I-NOUN|\u56fa\u6709\u540d\u8a5e|_",
135
- "123": "I-NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
136
- "124": "I-NUM|\u6570\u8a5e|_",
137
- "125": "I-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_",
138
- "126": "I-NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
139
- "127": "I-PART|[\u7d42\u52a9\u8a5e]|_",
140
- "128": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_",
141
- "129": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
142
- "130": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
143
- "131": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
144
- "132": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
145
- "133": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_",
146
- "134": "I-PART|\u52a9\u52d5\u8a5e|_",
147
- "135": "I-PART|\u63a5\u5c3e\u8f9e|_",
148
- "136": "I-PART|\u63a5\u7d9a\u52a9\u8a5e|_",
149
- "137": "I-PART|\u63a5\u982d\u8f9e|_",
150
- "138": "I-PART|\u7d42\u52a9\u8a5e|_",
151
- "139": "I-PART|\u7d42\u52a9\u8a5e\uff09|_",
152
- "140": "I-PART|\u81ea\u52d5\u8a5e|_",
153
- "141": "I-PART|\uff08\u7d42\u52a9\u8a5e\uff09|_",
154
- "142": "I-PRON|\u4ee3\u540d\u8a5e|_",
155
- "143": "I-PROPN|\u56fa\u6709\u540d\u8a5e|_",
156
- "144": "I-PUNCT|\u8a18\u53f7|_",
157
- "145": "I-SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_",
158
- "146": "I-SCONJ|\u4ed6\u52d5\u8a5e|_",
159
- "147": "I-SCONJ|\u526f\u8a5e|_",
160
- "148": "I-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
161
- "149": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
162
- "150": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_",
163
- "151": "I-SCONJ|\u63a5\u7d9a\u8a5e|_",
164
- "152": "I-SCONJ|\u683c\u52a9\u8a5e|_",
165
- "153": "I-VERB|[\u81ea\u52d5\u8a5e]|_",
166
- "154": "I-VERB|\u4ed6\u52d5\u8a5e|_",
167
- "155": "I-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
168
- "156": "I-VERB|\u4ed6\u52d5\u8a5e\uff1f|_",
169
- "157": "I-VERB|\u5b8c\u5168\u52d5\u8a5e|_",
170
- "158": "I-VERB|\u683c\u52a9\u8a5e|_",
171
- "159": "I-VERB|\u81ea\u52d5\u8a5e|_",
172
- "160": "I-VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_",
173
- "161": "I-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_",
174
- "162": "I-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
175
- "163": "I-VERB|\uff08\u81ea\u52d5\u8a5e|_",
176
- "164": "I-VERT|\u4ed6\u52d5\u8a5e|_",
177
- "165": "I-X|_|_",
178
- "166": "INTJ|\u9593\u6295\u8a5e|_",
179
- "167": "NOUN|\u4ee3\u540d\u8a5e|_",
180
- "168": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
181
- "169": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
182
- "170": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
183
- "171": "NOUN|\u540d\u8a5e|_",
184
- "172": "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
185
- "173": "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
186
- "174": "NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
187
- "175": "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
188
- "176": "NOUN|\u56fa\u6709\u540d\u8a5e|_",
189
- "177": "NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
190
- "178": "NUM|\u6570\u8a5e|_",
191
- "179": "PART|[\u7d42\u52a9\u8a5e]|_",
192
- "180": "PART|\u4eba\u79f0\u63a5\u8f9e|_",
193
- "181": "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
194
- "182": "PART|\u63a5\u5c3e\u8f9e|_",
195
- "183": "PART|\u63a5\u7d9a\u52a9\u8a5e|_",
196
- "184": "PART|\u63a5\u982d\u8f9e|_",
197
- "185": "PART|\u7d42\u52a9\u8a5e|_",
198
- "186": "PART|\u7d42\u52a9\u8a5e\uff09|_",
199
- "187": "PART|\u81ea\u52d5\u8a5e|_",
200
- "188": "PART|\uff08\u7d42\u52a9\u8a5e\uff09|_",
201
- "189": "PROPN|\u56fa\u6709\u540d\u8a5e|_",
202
- "190": "PUNCT|\u8a18\u53f7|_",
203
- "191": "SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_",
204
- "192": "SCONJ|\u4ed6\u52d5\u8a5e|_",
205
- "193": "SCONJ|\u526f\u8a5e|_",
206
- "194": "SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
207
- "195": "SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
208
- "196": "SCONJ|\u63a5\u7d9a\u8a5e|_",
209
- "197": "SCONJ|\u683c\u52a9\u8a5e|_",
210
- "198": "SCONJ|\u7d42\u52a9\u8a5e|_",
211
- "199": "SYM",
212
- "200": "VERB|[\u81ea\u52d5\u8a5e]|_",
213
- "201": "VERB|\u4ed6\u52d5\u8a5e|_",
214
- "202": "VERB|\u4ed6\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
215
- "203": "VERB|\u4ed6\u52d5\u8a5e|_+PART|\u63a5\u5c3e\u8f9e|_",
216
- "204": "VERB|\u5b8c\u5168\u52d5\u8a5e|_",
217
- "205": "VERB|\u81ea\u52d5\u8a5e|_",
218
- "206": "VERB|\u81ea\u52d5\u8a5e|_+AUX|\u52a9\u52d5\u8a5e|_",
219
- "207": "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_",
220
- "208": "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
221
- "209": "VERB|\u81ea\u52d5\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_",
222
- "210": "VERB|\uff08\u81ea\u52d5\u8a5e|_",
223
- "211": "VERT|\u4ed6\u52d5\u8a5e|_",
224
- "212": "X|_|_"
225
  },
226
  "initializer_range": 0.02,
227
  "intermediate_size": 3072,
@@ -231,214 +209,192 @@
231
  "ADP|\u5f8c\u7f6e\u526f\u8a5e|_": 2,
232
  "ADP|\u683c\u52a9\u8a5e|_": 3,
233
  "ADV|\u526f\u8a5e|_": 4,
234
- "ADV|\u9593\u6295\u8a5e|_": 5,
235
- "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 6,
236
- "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 7,
237
- "AUX|\u52a9\u52a9\u8a5e|_": 8,
238
- "AUX|\u52a9\u52d5\u8a5e|_": 9,
239
- "B-ADP|\u526f\u52a9\u8a5e|_": 10,
240
- "B-ADP|\u526f\u8a5e|_": 11,
241
- "B-ADP|\u5f8c\u7f6e\u526f\u8a5e|_": 12,
242
- "B-ADP|\u683c\u52a9\u8a5e|_": 13,
243
- "B-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 14,
244
- "B-ADV|\u526f\u8a5e|_": 15,
245
- "B-ADV|\u9593\u6295\u8a5e|_": 16,
246
- "B-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 17,
247
- "B-AUX|\u52a9\u52d5\u8a5e|_": 18,
248
- "B-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_": 19,
249
- "B-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 20,
250
- "B-CCONJ|\u63a5\u7d9a\u8a5e|_": 21,
251
- "B-DET|\u526f\u8a5e|_": 22,
252
- "B-DET|\u9023\u4f53\u8a5e|_": 23,
253
- "B-DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_": 24,
254
- "B-INFR.EV|\u5f62\u5f0f\u540d\u8a5e|_": 25,
255
- "B-INTJ|\u9593\u6295\u8a5e|_": 26,
256
- "B-NOUN|\u4eba\u79f0\u63a5\u8f9e|_": 27,
257
- "B-NOUN|\u4ee3\u540d\u8a5e|_": 28,
258
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 29,
259
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 30,
260
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": 31,
261
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 32,
262
- "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 33,
263
- "B-NOUN|\u540d\u8a5e|_": 34,
264
- "B-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 35,
265
- "B-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": 36,
266
- "B-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 37,
267
- "B-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 38,
268
- "B-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 39,
269
- "B-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 40,
270
- "B-NOUN|\u56fa\u6709\u540d\u8a5e|_": 41,
271
- "B-NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 42,
272
- "B-NUM|\u6570\u8a5e|_": 43,
273
- "B-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_": 44,
274
- "B-NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 45,
275
- "B-PART|[\u7d42\u52a9\u8a5e]|_": 46,
276
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_": 47,
277
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 48,
278
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 49,
279
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 50,
280
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 51,
281
- "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_": 52,
282
- "B-PART|\u52a9\u52d5\u8a5e|_": 53,
283
- "B-PART|\u63a5\u5c3e\u8f9e|_": 54,
284
- "B-PART|\u63a5\u7d9a\u52a9\u8a5e|_": 55,
285
- "B-PART|\u63a5\u982d\u8f9e|_": 56,
286
- "B-PART|\u7d42\u52a9\u8a5e|_": 57,
287
- "B-PART|\u7d42\u52a9\u8a5e\uff09|_": 58,
288
- "B-PART|\u81ea\u52d5\u8a5e|_": 59,
289
- "B-PART|\uff08\u7d42\u52a9\u8a5e\uff09|_": 60,
290
- "B-PRON|\u4ee3\u540d\u8a5e|_": 61,
291
- "B-PROPN|\u56fa\u6709\u540d\u8a5e|_": 62,
292
- "B-PUNCT|\u8a18\u53f7|_": 63,
293
- "B-SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_": 64,
294
- "B-SCONJ|\u4ed6\u52d5\u8a5e|_": 65,
295
- "B-SCONJ|\u526f\u8a5e|_": 66,
296
- "B-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 67,
297
- "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 68,
298
- "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_": 69,
299
- "B-SCONJ|\u63a5\u7d9a\u8a5e|_": 70,
300
- "B-SCONJ|\u683c\u52a9\u8a5e|_": 71,
301
- "B-VERB|[\u81ea\u52d5\u8a5e]|_": 72,
302
- "B-VERB|\u4ed6\u52d5\u8a5e|_": 73,
303
- "B-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 74,
304
- "B-VERB|\u4ed6\u52d5\u8a5e\uff1f|_": 75,
305
- "B-VERB|\u5b8c\u5168\u52d5\u8a5e|_": 76,
306
- "B-VERB|\u683c\u52a9\u8a5e|_": 77,
307
- "B-VERB|\u81ea\u52d5\u8a5e|_": 78,
308
- "B-VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_": 79,
309
- "B-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": 80,
310
- "B-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 81,
311
- "B-VERB|\uff08\u81ea\u52d5\u8a5e|_": 82,
312
- "B-VERT|\u4ed6\u52d5\u8a5e|_": 83,
313
- "B-X|_|_": 84,
314
- "CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 85,
315
- "CCONJ|\u63a5\u7d9a\u8a5e|_": 86,
316
- "DET|\u81ea\u52d5\u8a5e|_": 87,
317
- "DET|\u9023\u4f53\u8a5e|_": 88,
318
- "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_": 89,
319
- "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 90,
320
- "I-ADP|\u526f\u52a9\u8a5e|_": 91,
321
- "I-ADP|\u526f\u8a5e|_": 92,
322
- "I-ADP|\u5f8c\u7f6e\u526f\u8a5e|_": 93,
323
- "I-ADP|\u683c\u52a9\u8a5e|_": 94,
324
- "I-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 95,
325
- "I-ADV|\u526f\u8a5e|_": 96,
326
- "I-ADV|\u9593\u6295\u8a5e|_": 97,
327
- "I-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 98,
328
- "I-AUX|\u52a9\u52d5\u8a5e|_": 99,
329
- "I-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_": 100,
330
- "I-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 101,
331
- "I-CCONJ|\u63a5\u7d9a\u8a5e|_": 102,
332
- "I-DET|\u526f\u8a5e|_": 103,
333
- "I-DET|\u9023\u4f53\u8a5e|_": 104,
334
- "I-DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_": 105,
335
- "I-INFR.EV|\u5f62\u5f0f\u540d\u8a5e|_": 106,
336
- "I-INTJ|\u9593\u6295\u8a5e|_": 107,
337
- "I-NOUN|\u4eba\u79f0\u63a5\u8f9e|_": 108,
338
- "I-NOUN|\u4ee3\u540d\u8a5e|_": 109,
339
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 110,
340
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 111,
341
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": 112,
342
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 113,
343
- "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 114,
344
- "I-NOUN|\u540d\u8a5e|_": 115,
345
- "I-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 116,
346
- "I-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": 117,
347
- "I-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 118,
348
- "I-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 119,
349
- "I-NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 120,
350
- "I-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 121,
351
- "I-NOUN|\u56fa\u6709\u540d\u8a5e|_": 122,
352
- "I-NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 123,
353
- "I-NUM|\u6570\u8a5e|_": 124,
354
- "I-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_": 125,
355
- "I-NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 126,
356
- "I-PART|[\u7d42\u52a9\u8a5e]|_": 127,
357
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_": 128,
358
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 129,
359
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 130,
360
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 131,
361
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 132,
362
- "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_": 133,
363
- "I-PART|\u52a9\u52d5\u8a5e|_": 134,
364
- "I-PART|\u63a5\u5c3e\u8f9e|_": 135,
365
- "I-PART|\u63a5\u7d9a\u52a9\u8a5e|_": 136,
366
- "I-PART|\u63a5\u982d\u8f9e|_": 137,
367
- "I-PART|\u7d42\u52a9\u8a5e|_": 138,
368
- "I-PART|\u7d42\u52a9\u8a5e\uff09|_": 139,
369
- "I-PART|\u81ea\u52d5\u8a5e|_": 140,
370
- "I-PART|\uff08\u7d42\u52a9\u8a5e\uff09|_": 141,
371
- "I-PRON|\u4ee3\u540d\u8a5e|_": 142,
372
- "I-PROPN|\u56fa\u6709\u540d\u8a5e|_": 143,
373
- "I-PUNCT|\u8a18\u53f7|_": 144,
374
- "I-SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_": 145,
375
- "I-SCONJ|\u4ed6\u52d5\u8a5e|_": 146,
376
- "I-SCONJ|\u526f\u8a5e|_": 147,
377
- "I-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 148,
378
- "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 149,
379
- "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_": 150,
380
- "I-SCONJ|\u63a5\u7d9a\u8a5e|_": 151,
381
- "I-SCONJ|\u683c\u52a9\u8a5e|_": 152,
382
- "I-VERB|[\u81ea\u52d5\u8a5e]|_": 153,
383
- "I-VERB|\u4ed6\u52d5\u8a5e|_": 154,
384
- "I-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 155,
385
- "I-VERB|\u4ed6\u52d5\u8a5e\uff1f|_": 156,
386
- "I-VERB|\u5b8c\u5168\u52d5\u8a5e|_": 157,
387
- "I-VERB|\u683c\u52a9\u8a5e|_": 158,
388
- "I-VERB|\u81ea\u52d5\u8a5e|_": 159,
389
- "I-VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_": 160,
390
- "I-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": 161,
391
- "I-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 162,
392
- "I-VERB|\uff08\u81ea\u52d5\u8a5e|_": 163,
393
- "I-VERT|\u4ed6\u52d5\u8a5e|_": 164,
394
- "I-X|_|_": 165,
395
- "INTJ|\u9593\u6295\u8a5e|_": 166,
396
- "NOUN|\u4ee3\u540d\u8a5e|_": 167,
397
- "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 168,
398
- "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 169,
399
- "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 170,
400
- "NOUN|\u540d\u8a5e|_": 171,
401
- "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 172,
402
- "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 173,
403
- "NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 174,
404
- "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 175,
405
- "NOUN|\u56fa\u6709\u540d\u8a5e|_": 176,
406
- "NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 177,
407
- "NUM|\u6570\u8a5e|_": 178,
408
- "PART|[\u7d42\u52a9\u8a5e]|_": 179,
409
- "PART|\u4eba\u79f0\u63a5\u8f9e|_": 180,
410
- "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 181,
411
- "PART|\u63a5\u5c3e\u8f9e|_": 182,
412
- "PART|\u63a5\u7d9a\u52a9\u8a5e|_": 183,
413
- "PART|\u63a5\u982d\u8f9e|_": 184,
414
- "PART|\u7d42\u52a9\u8a5e|_": 185,
415
- "PART|\u7d42\u52a9\u8a5e\uff09|_": 186,
416
- "PART|\u81ea\u52d5\u8a5e|_": 187,
417
- "PART|\uff08\u7d42\u52a9\u8a5e\uff09|_": 188,
418
- "PROPN|\u56fa\u6709\u540d\u8a5e|_": 189,
419
- "PUNCT|\u8a18\u53f7|_": 190,
420
- "SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_": 191,
421
- "SCONJ|\u4ed6\u52d5\u8a5e|_": 192,
422
- "SCONJ|\u526f\u8a5e|_": 193,
423
- "SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 194,
424
- "SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 195,
425
- "SCONJ|\u63a5\u7d9a\u8a5e|_": 196,
426
- "SCONJ|\u683c\u52a9\u8a5e|_": 197,
427
- "SCONJ|\u7d42\u52a9\u8a5e|_": 198,
428
- "SYM": 199,
429
- "VERB|[\u81ea\u52d5\u8a5e]|_": 200,
430
- "VERB|\u4ed6\u52d5\u8a5e|_": 201,
431
- "VERB|\u4ed6\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 202,
432
- "VERB|\u4ed6\u52d5\u8a5e|_+PART|\u63a5\u5c3e\u8f9e|_": 203,
433
- "VERB|\u5b8c\u5168\u52d5\u8a5e|_": 204,
434
- "VERB|\u81ea\u52d5\u8a5e|_": 205,
435
- "VERB|\u81ea\u52d5\u8a5e|_+AUX|\u52a9\u52d5\u8a5e|_": 206,
436
- "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_": 207,
437
- "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 208,
438
- "VERB|\u81ea\u52d5\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 209,
439
- "VERB|\uff08\u81ea\u52d5\u8a5e|_": 210,
440
- "VERT|\u4ed6\u52d5\u8a5e|_": 211,
441
- "X|_|_": 212
442
  },
443
  "layer_norm_eps": 1e-07,
444
  "max_position_embeddings": 512,
@@ -475,10 +431,6 @@
475
  "nangonna": [
476
  "nangon",
477
  "na"
478
- ],
479
- "nankonna": [
480
- "nankon",
481
- "na"
482
  ]
483
  },
484
  "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_": {
@@ -489,14 +441,6 @@
489
  "Tampa": [
490
  "Tam",
491
  "pa"
492
- ],
493
- "tanpa": [
494
- "tan",
495
- "pa"
496
- ],
497
- "tanto": [
498
- "tan",
499
- "to"
500
  ]
501
  },
502
  "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": {
@@ -504,11 +448,6 @@
504
  "Ne",
505
  "wa",
506
  "an"
507
- ],
508
- "newaan": [
509
- "ne",
510
- "wa",
511
- "an"
512
  ]
513
  },
514
  "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": {
@@ -532,16 +471,16 @@
532
  "Soi",
533
  "ta"
534
  ],
535
- "keseta": [
536
- "kese",
537
- "ta"
538
  ],
539
- "kesta": [
540
- "kes",
541
- "ta"
542
  ],
543
- "neyta": [
544
- "ney",
545
  "ta"
546
  ],
547
  "orota": [
@@ -563,22 +502,6 @@
563
  "otta": [
564
  "ot",
565
  "ta"
566
- ],
567
- "petsamaketa": [
568
- "petsamake",
569
- "ta"
570
- ],
571
- "samaketa": [
572
- "samake",
573
- "ta"
574
- ],
575
- "soyta": [
576
- "soy",
577
- "ta"
578
- ],
579
- "tomta": [
580
- "tom",
581
- "ta"
582
  ]
583
  },
584
  "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": {
@@ -586,18 +509,6 @@
586
  "ror",
587
  "un",
588
  "purai"
589
- ],
590
- "rorunpuray": [
591
- "ror",
592
- "un",
593
- "puray"
594
- ]
595
- },
596
- "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": {
597
- "soytaarpa": [
598
- "soy",
599
- "ta",
600
- "arpa"
601
  ]
602
  },
603
  "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": {
@@ -609,14 +520,6 @@
609
  "Orep",
610
  "un"
611
  ],
612
- "makun": [
613
- "mak",
614
- "un"
615
- ],
616
- "repun": [
617
- "rep",
618
- "un"
619
- ],
620
  "rikunruke": [
621
  "rik",
622
  "unruke"
@@ -624,10 +527,6 @@
624
  "ukakushte": [
625
  "uka",
626
  "kushte"
627
- ],
628
- "ukakuste": [
629
- "uka",
630
- "kuste"
631
  ]
632
  },
633
  "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": {
@@ -638,14 +537,6 @@
638
  "cheppone": [
639
  "cheppo",
640
  "ne"
641
- ],
642
- "kunneywano": [
643
- "kunney",
644
- "wano"
645
- ],
646
- "neyta": [
647
- "ney",
648
- "ta"
649
  ]
650
  },
651
  "NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": {
@@ -666,10 +557,6 @@
666
  "petetok": [
667
  "pet",
668
  "etok"
669
- ],
670
- "petetoko": [
671
- "pet",
672
- "etoko"
673
  ]
674
  },
675
  "NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": {
@@ -689,27 +576,9 @@
689
  "kamui",
690
  "nish"
691
  ],
692
- "kamuynis": [
693
- "kamuy",
694
- "nis"
695
- ],
696
  "konkanipe": [
697
  "konkani",
698
  "pe"
699
- ],
700
- "sirokanipe": [
701
- "sirokani",
702
- "pe"
703
- ]
704
- },
705
- "NOUN|\u540d\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
706
- "inaanpe": [
707
- "inaan",
708
- "pe"
709
- ],
710
- "inanpe": [
711
- "inan",
712
- "pe"
713
  ]
714
  },
715
  "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": {
@@ -721,10 +590,6 @@
721
  "kotan",
722
  "kor"
723
  ],
724
- "siriki": [
725
- "siri",
726
- "ki"
727
- ],
728
  "uraikik": [
729
  "urai",
730
  "kik"
@@ -735,21 +600,11 @@
735
  "Wan",
736
  "to"
737
  ],
738
- "hotnepa": [
739
- "hotne",
740
- "pa"
741
- ],
742
  "wanto": [
743
  "wan",
744
  "to"
745
  ]
746
  },
747
- "NUM|\u6570\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
748
- "wanpe": [
749
- "wan",
750
- "pe"
751
- ]
752
- },
753
  "PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": {
754
  "chine": [
755
  "chi",
@@ -762,10 +617,14 @@
762
  "sam"
763
  ]
764
  },
765
- "PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": {
766
- "=anpe": [
767
- "=an",
768
- "pe"
 
 
 
 
769
  ]
770
  },
771
  "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": {
@@ -789,6 +648,10 @@
789
  "e",
790
  "ram an"
791
  ],
 
 
 
 
792
  "eramasu": [
793
  "e",
794
  "ramasu"
@@ -839,18 +702,10 @@
839
  "am",
840
  "be"
841
  ],
842
- "anpe": [
843
- "an",
844
- "pe"
845
- ],
846
  "anto": [
847
  "an",
848
  "to"
849
  ],
850
- "h\u00e9sep\u00e1ha": [
851
- "h\u00e9se",
852
- "p\u00e1ha"
853
- ],
854
  "wenpuri": [
855
  "wen",
856
  "puri"
@@ -860,10 +715,6 @@
860
  "ambe": [
861
  "am",
862
  "be"
863
- ],
864
- "anpe": [
865
- "an",
866
- "pe"
867
  ]
868
  },
869
  "VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": {
@@ -900,7 +751,7 @@
900
  },
901
  "tokenizer_class": "DebertaV2TokenizerFast",
902
  "torch_dtype": "float32",
903
- "transformers_version": "4.25.1",
904
  "type_vocab_size": 0,
905
  "vocab_size": 6143
906
  }
 
14
  "2": "ADP|\u5f8c\u7f6e\u526f\u8a5e|_",
15
  "3": "ADP|\u683c\u52a9\u8a5e|_",
16
  "4": "ADV|\u526f\u8a5e|_",
17
+ "5": "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
18
+ "6": "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
19
+ "7": "AUX|\u52a9\u52a9\u8a5e|_",
20
+ "8": "AUX|\u52a9\u52d5\u8a5e|_",
21
+ "9": "B-ADP|\u526f\u52a9\u8a5e|_",
22
+ "10": "B-ADP|\u5f8c\u7f6e\u526f\u8a5e|_",
23
+ "11": "B-ADP|\u683c\u52a9\u8a5e|_",
24
+ "12": "B-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
25
+ "13": "B-ADV|\u526f\u8a5e|_",
26
+ "14": "B-ADV|\u9593\u6295\u8a5e|_",
27
+ "15": "B-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
28
+ "16": "B-AUX|\u52a9\u52d5\u8a5e|_",
29
+ "17": "B-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_",
30
+ "18": "B-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
31
+ "19": "B-CCONJ|\u63a5\u7d9a\u8a5e|_",
32
+ "20": "B-DET|\u526f\u8a5e|_",
33
+ "21": "B-DET|\u9023\u4f53\u8a5e|_",
34
+ "22": "B-INFR.EV|\u5f62\u5f0f\u540d\u8a5e|_",
35
+ "23": "B-INTJ|\u9593\u6295\u8a5e|_",
36
+ "24": "B-NOUN|\u4eba\u79f0\u63a5\u8f9e|_",
37
+ "25": "B-NOUN|\u4ee3\u540d\u8a5e|_",
38
+ "26": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
39
+ "27": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
40
+ "28": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_",
41
+ "29": "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
42
+ "30": "B-NOUN|\u540d\u8a5e|_",
43
+ "31": "B-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
44
+ "32": "B-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_",
45
+ "33": "B-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
46
+ "34": "B-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
47
+ "35": "B-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
48
+ "36": "B-NOUN|\u56fa\u6709\u540d\u8a5e|_",
49
+ "37": "B-NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
50
+ "38": "B-NUM|\u6570\u8a5e|_",
51
+ "39": "B-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_",
52
+ "40": "B-PART|[\u7d42\u52a9\u8a5e]|_",
53
+ "41": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_",
54
+ "42": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
55
+ "43": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
56
+ "44": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
57
+ "45": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
58
+ "46": "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_",
59
+ "47": "B-PART|\u52a9\u52d5\u8a5e|_",
60
+ "48": "B-PART|\u63a5\u5c3e\u8f9e|_",
61
+ "49": "B-PART|\u63a5\u7d9a\u52a9\u8a5e|_",
62
+ "50": "B-PART|\u63a5\u982d\u8f9e|_",
63
+ "51": "B-PART|\u7d42\u52a9\u8a5e|_",
64
+ "52": "B-PART|\u81ea\u52d5\u8a5e|_",
65
+ "53": "B-PART|\uff08\u7d42\u52a9\u8a5e\uff09|_",
66
+ "54": "B-PRON|\u4ee3\u540d\u8a5e|_",
67
+ "55": "B-PROPN|\u56fa\u6709\u540d\u8a5e|_",
68
+ "56": "B-PUNCT|\u8a18\u53f7|_",
69
+ "57": "B-SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_",
70
+ "58": "B-SCONJ|\u4ed6\u52d5\u8a5e|_",
71
+ "59": "B-SCONJ|\u526f\u8a5e|_",
72
+ "60": "B-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
73
+ "61": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
74
+ "62": "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_",
75
+ "63": "B-SCONJ|\u63a5\u7d9a\u8a5e|_",
76
+ "64": "B-SCONJ|\u683c\u52a9\u8a5e|_",
77
+ "65": "B-SCONJ|\u7d42\u52a9\u8a5e|_",
78
+ "66": "B-VERB|[\u81ea\u52d5\u8a5e]|_",
79
+ "67": "B-VERB|\u4ed6\u52d5\u8a5e|_",
80
+ "68": "B-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
81
+ "69": "B-VERB|\u4ed6\u52d5\u8a5e\uff1f|_",
82
+ "70": "B-VERB|\u5b8c\u5168\u52d5\u8a5e|_",
83
+ "71": "B-VERB|\u683c\u52a9\u8a5e|_",
84
+ "72": "B-VERB|\u81ea\u52d5\u8a5e|_",
85
+ "73": "B-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_",
86
+ "74": "B-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
87
+ "75": "B-VERT|\u4ed6\u52d5\u8a5e|_",
88
+ "76": "B-X|_|_",
89
+ "77": "CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
90
+ "78": "CCONJ|\u63a5\u7d9a\u8a5e|_",
91
+ "79": "DET|\u81ea\u52d5\u8a5e|_",
92
+ "80": "DET|\u9023\u4f53\u8a5e|_",
93
+ "81": "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_",
94
+ "82": "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_",
95
+ "83": "I-ADP|\u526f\u52a9\u8a5e|_",
96
+ "84": "I-ADP|\u5f8c\u7f6e\u526f\u8a5e|_",
97
+ "85": "I-ADP|\u683c\u52a9\u8a5e|_",
98
+ "86": "I-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
99
+ "87": "I-ADV|\u526f\u8a5e|_",
100
+ "88": "I-ADV|\u9593\u6295\u8a5e|_",
101
+ "89": "I-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
102
+ "90": "I-AUX|\u52a9\u52d5\u8a5e|_",
103
+ "91": "I-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_",
104
+ "92": "I-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
105
+ "93": "I-CCONJ|\u63a5\u7d9a\u8a5e|_",
106
+ "94": "I-DET|\u526f\u8a5e|_",
107
+ "95": "I-DET|\u9023\u4f53\u8a5e|_",
108
+ "96": "I-INFR.EV|\u5f62\u5f0f\u540d\u8a5e|_",
109
+ "97": "I-INTJ|\u9593\u6295\u8a5e|_",
110
+ "98": "I-NOUN|\u4eba\u79f0\u63a5\u8f9e|_",
111
+ "99": "I-NOUN|\u4ee3\u540d\u8a5e|_",
112
+ "100": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
113
+ "101": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
114
+ "102": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_",
115
+ "103": "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
116
+ "104": "I-NOUN|\u540d\u8a5e|_",
117
+ "105": "I-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
118
+ "106": "I-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_",
119
+ "107": "I-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
120
+ "108": "I-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_",
121
+ "109": "I-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
122
+ "110": "I-NOUN|\u56fa\u6709\u540d\u8a5e|_",
123
+ "111": "I-NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
124
+ "112": "I-NUM|\u6570\u8a5e|_",
125
+ "113": "I-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_",
126
+ "114": "I-PART|[\u7d42\u52a9\u8a5e]|_",
127
+ "115": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_",
128
+ "116": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_",
129
+ "117": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
130
+ "118": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
131
+ "119": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
132
+ "120": "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_",
133
+ "121": "I-PART|\u52a9\u52d5\u8a5e|_",
134
+ "122": "I-PART|\u63a5\u5c3e\u8f9e|_",
135
+ "123": "I-PART|\u63a5\u7d9a\u52a9\u8a5e|_",
136
+ "124": "I-PART|\u63a5\u982d\u8f9e|_",
137
+ "125": "I-PART|\u7d42\u52a9\u8a5e|_",
138
+ "126": "I-PART|\u81ea\u52d5\u8a5e|_",
139
+ "127": "I-PART|\uff08\u7d42\u52a9\u8a5e\uff09|_",
140
+ "128": "I-PRON|\u4ee3\u540d\u8a5e|_",
141
+ "129": "I-PROPN|\u56fa\u6709\u540d\u8a5e|_",
142
+ "130": "I-PUNCT|\u8a18\u53f7|_",
143
+ "131": "I-SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_",
144
+ "132": "I-SCONJ|\u4ed6\u52d5\u8a5e|_",
145
+ "133": "I-SCONJ|\u526f\u8a5e|_",
146
+ "134": "I-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
147
+ "135": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
148
+ "136": "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_",
149
+ "137": "I-SCONJ|\u63a5\u7d9a\u8a5e|_",
150
+ "138": "I-SCONJ|\u683c\u52a9\u8a5e|_",
151
+ "139": "I-SCONJ|\u7d42\u52a9\u8a5e|_",
152
+ "140": "I-VERB|[\u81ea\u52d5\u8a5e]|_",
153
+ "141": "I-VERB|\u4ed6\u52d5\u8a5e|_",
154
+ "142": "I-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
155
+ "143": "I-VERB|\u4ed6\u52d5\u8a5e\uff1f|_",
156
+ "144": "I-VERB|\u5b8c\u5168\u52d5\u8a5e|_",
157
+ "145": "I-VERB|\u683c\u52a9\u8a5e|_",
158
+ "146": "I-VERB|\u81ea\u52d5\u8a5e|_",
159
+ "147": "I-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_",
160
+ "148": "I-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
161
+ "149": "I-VERT|\u4ed6\u52d5\u8a5e|_",
162
+ "150": "I-X|_|_",
163
+ "151": "INTJ|\u9593\u6295\u8a5e|_",
164
+ "152": "NOUN|\u4ee3\u540d\u8a5e|_",
165
+ "153": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
166
+ "154": "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_",
167
+ "155": "NOUN|\u540d\u8a5e|_",
168
+ "156": "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_",
169
+ "157": "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_",
170
+ "158": "NOUN|\u56fa\u6709\u540d\u8a5e|_",
171
+ "159": "NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
172
+ "160": "NUM|\u6570\u8a5e|_",
173
+ "161": "PART|[\u7d42\u52a9\u8a5e]|_",
174
+ "162": "PART|\u4eba\u79f0\u63a5\u8f9e|_",
175
+ "163": "PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
176
+ "164": "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_",
177
+ "165": "PART|\u63a5\u5c3e\u8f9e|_",
178
+ "166": "PART|\u63a5\u7d9a\u52a9\u8a5e|_",
179
+ "167": "PART|\u63a5\u982d\u8f9e|_",
180
+ "168": "PART|\u7d42\u52a9\u8a5e|_",
181
+ "169": "PART|\u81ea\u52d5\u8a5e|_",
182
+ "170": "PROPN|\u56fa\u6709\u540d\u8a5e|_",
183
+ "171": "PUNCT|\u8a18\u53f7|_",
184
+ "172": "SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_",
185
+ "173": "SCONJ|\u4ed6\u52d5\u8a5e|_",
186
+ "174": "SCONJ|\u526f\u8a5e|_",
187
+ "175": "SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_",
188
+ "176": "SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_",
189
+ "177": "SCONJ|\u63a5\u7d9a\u8a5e|_",
190
+ "178": "SCONJ|\u683c\u52a9\u8a5e|_",
191
+ "179": "SCONJ|\u7d42\u52a9\u8a5e|_",
192
+ "180": "SYM",
193
+ "181": "VERB|\u4ed6\u52d5\u8a5e|_",
194
+ "182": "VERB|\u4ed6\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
195
+ "183": "VERB|\u4ed6\u52d5\u8a5e|_+PART|\u63a5\u5c3e\u8f9e|_",
196
+ "184": "VERB|\u5b8c\u5168\u52d5\u8a5e|_",
197
+ "185": "VERB|\u81ea\u52d5\u8a5e|_",
198
+ "186": "VERB|\u81ea\u52d5\u8a5e|_+AUX|\u52a9\u52d5\u8a5e|_",
199
+ "187": "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_",
200
+ "188": "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_",
201
+ "189": "VERB|\u81ea\u52d5\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_",
202
+ "190": "X|_|_"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
203
  },
204
  "initializer_range": 0.02,
205
  "intermediate_size": 3072,
 
209
  "ADP|\u5f8c\u7f6e\u526f\u8a5e|_": 2,
210
  "ADP|\u683c\u52a9\u8a5e|_": 3,
211
  "ADV|\u526f\u8a5e|_": 4,
212
+ "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 5,
213
+ "AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 6,
214
+ "AUX|\u52a9\u52a9\u8a5e|_": 7,
215
+ "AUX|\u52a9\u52d5\u8a5e|_": 8,
216
+ "B-ADP|\u526f\u52a9\u8a5e|_": 9,
217
+ "B-ADP|\u5f8c\u7f6e\u526f\u8a5e|_": 10,
218
+ "B-ADP|\u683c\u52a9\u8a5e|_": 11,
219
+ "B-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 12,
220
+ "B-ADV|\u526f\u8a5e|_": 13,
221
+ "B-ADV|\u9593\u6295\u8a5e|_": 14,
222
+ "B-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 15,
223
+ "B-AUX|\u52a9\u52d5\u8a5e|_": 16,
224
+ "B-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_": 17,
225
+ "B-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 18,
226
+ "B-CCONJ|\u63a5\u7d9a\u8a5e|_": 19,
227
+ "B-DET|\u526f\u8a5e|_": 20,
228
+ "B-DET|\u9023\u4f53\u8a5e|_": 21,
229
+ "B-INFR.EV|\u5f62\u5f0f\u540d\u8a5e|_": 22,
230
+ "B-INTJ|\u9593\u6295\u8a5e|_": 23,
231
+ "B-NOUN|\u4eba\u79f0\u63a5\u8f9e|_": 24,
232
+ "B-NOUN|\u4ee3\u540d\u8a5e|_": 25,
233
+ "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 26,
234
+ "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 27,
235
+ "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": 28,
236
+ "B-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 29,
237
+ "B-NOUN|\u540d\u8a5e|_": 30,
238
+ "B-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 31,
239
+ "B-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": 32,
240
+ "B-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 33,
241
+ "B-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 34,
242
+ "B-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 35,
243
+ "B-NOUN|\u56fa\u6709\u540d\u8a5e|_": 36,
244
+ "B-NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 37,
245
+ "B-NUM|\u6570\u8a5e|_": 38,
246
+ "B-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_": 39,
247
+ "B-PART|[\u7d42\u52a9\u8a5e]|_": 40,
248
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_": 41,
249
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 42,
250
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 43,
251
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 44,
252
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 45,
253
+ "B-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_": 46,
254
+ "B-PART|\u52a9\u52d5\u8a5e|_": 47,
255
+ "B-PART|\u63a5\u5c3e\u8f9e|_": 48,
256
+ "B-PART|\u63a5\u7d9a\u52a9\u8a5e|_": 49,
257
+ "B-PART|\u63a5\u982d\u8f9e|_": 50,
258
+ "B-PART|\u7d42\u52a9\u8a5e|_": 51,
259
+ "B-PART|\u81ea\u52d5\u8a5e|_": 52,
260
+ "B-PART|\uff08\u7d42\u52a9\u8a5e\uff09|_": 53,
261
+ "B-PRON|\u4ee3\u540d\u8a5e|_": 54,
262
+ "B-PROPN|\u56fa\u6709\u540d\u8a5e|_": 55,
263
+ "B-PUNCT|\u8a18\u53f7|_": 56,
264
+ "B-SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_": 57,
265
+ "B-SCONJ|\u4ed6\u52d5\u8a5e|_": 58,
266
+ "B-SCONJ|\u526f\u8a5e|_": 59,
267
+ "B-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 60,
268
+ "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 61,
269
+ "B-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_": 62,
270
+ "B-SCONJ|\u63a5\u7d9a\u8a5e|_": 63,
271
+ "B-SCONJ|\u683c\u52a9\u8a5e|_": 64,
272
+ "B-SCONJ|\u7d42\u52a9\u8a5e|_": 65,
273
+ "B-VERB|[\u81ea\u52d5\u8a5e]|_": 66,
274
+ "B-VERB|\u4ed6\u52d5\u8a5e|_": 67,
275
+ "B-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 68,
276
+ "B-VERB|\u4ed6\u52d5\u8a5e\uff1f|_": 69,
277
+ "B-VERB|\u5b8c\u5168\u52d5\u8a5e|_": 70,
278
+ "B-VERB|\u683c\u52a9\u8a5e|_": 71,
279
+ "B-VERB|\u81ea\u52d5\u8a5e|_": 72,
280
+ "B-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": 73,
281
+ "B-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 74,
282
+ "B-VERT|\u4ed6\u52d5\u8a5e|_": 75,
283
+ "B-X|_|_": 76,
284
+ "CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 77,
285
+ "CCONJ|\u63a5\u7d9a\u8a5e|_": 78,
286
+ "DET|\u81ea\u52d5\u8a5e|_": 79,
287
+ "DET|\u9023\u4f53\u8a5e|_": 80,
288
+ "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_": 81,
289
+ "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 82,
290
+ "I-ADP|\u526f\u52a9\u8a5e|_": 83,
291
+ "I-ADP|\u5f8c\u7f6e\u526f\u8a5e|_": 84,
292
+ "I-ADP|\u683c\u52a9\u8a5e|_": 85,
293
+ "I-ADP|\u683c\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 86,
294
+ "I-ADV|\u526f\u8a5e|_": 87,
295
+ "I-ADV|\u9593\u6295\u8a5e|_": 88,
296
+ "I-AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 89,
297
+ "I-AUX|\u52a9\u52d5\u8a5e|_": 90,
298
+ "I-AUX|\u52a9\u52d5\u8a5e|_+PART|\u7d42\u52a9\u8a5e|_": 91,
299
+ "I-CCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 92,
300
+ "I-CCONJ|\u63a5\u7d9a\u8a5e|_": 93,
301
+ "I-DET|\u526f\u8a5e|_": 94,
302
+ "I-DET|\u9023\u4f53\u8a5e|_": 95,
303
+ "I-INFR.EV|\u5f62\u5f0f\u540d\u8a5e|_": 96,
304
+ "I-INTJ|\u9593\u6295\u8a5e|_": 97,
305
+ "I-NOUN|\u4eba\u79f0\u63a5\u8f9e|_": 98,
306
+ "I-NOUN|\u4ee3\u540d\u8a5e|_": 99,
307
+ "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 100,
308
+ "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 101,
309
+ "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": 102,
310
+ "I-NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 103,
311
+ "I-NOUN|\u540d\u8a5e|_": 104,
312
+ "I-NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 105,
313
+ "I-NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": 106,
314
+ "I-NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 107,
315
+ "I-NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": 108,
316
+ "I-NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 109,
317
+ "I-NOUN|\u56fa\u6709\u540d\u8a5e|_": 110,
318
+ "I-NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 111,
319
+ "I-NUM|\u6570\u8a5e|_": 112,
320
+ "I-NUM|\u6570\u8a5e|_+NOUN|\u540d\u8a5e|_": 113,
321
+ "I-PART|[\u7d42\u52a9\u8a5e]|_": 114,
322
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_": 115,
323
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": 116,
324
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 117,
325
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 118,
326
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 119,
327
+ "I-PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u81ea\u52d5\u8a5e|_": 120,
328
+ "I-PART|\u52a9\u52d5\u8a5e|_": 121,
329
+ "I-PART|\u63a5\u5c3e\u8f9e|_": 122,
330
+ "I-PART|\u63a5\u7d9a\u52a9\u8a5e|_": 123,
331
+ "I-PART|\u63a5\u982d\u8f9e|_": 124,
332
+ "I-PART|\u7d42\u52a9\u8a5e|_": 125,
333
+ "I-PART|\u81ea\u52d5\u8a5e|_": 126,
334
+ "I-PART|\uff08\u7d42\u52a9\u8a5e\uff09|_": 127,
335
+ "I-PRON|\u4ee3\u540d\u8a5e|_": 128,
336
+ "I-PROPN|\u56fa\u6709\u540d\u8a5e|_": 129,
337
+ "I-PUNCT|\u8a18\u53f7|_": 130,
338
+ "I-SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_": 131,
339
+ "I-SCONJ|\u4ed6\u52d5\u8a5e|_": 132,
340
+ "I-SCONJ|\u526f\u8a5e|_": 133,
341
+ "I-SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 134,
342
+ "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 135,
343
+ "I-SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+ADV|\u526f\u8a5e|_": 136,
344
+ "I-SCONJ|\u63a5\u7d9a\u8a5e|_": 137,
345
+ "I-SCONJ|\u683c\u52a9\u8a5e|_": 138,
346
+ "I-SCONJ|\u7d42\u52a9\u8a5e|_": 139,
347
+ "I-VERB|[\u81ea\u52d5\u8a5e]|_": 140,
348
+ "I-VERB|\u4ed6\u52d5\u8a5e|_": 141,
349
+ "I-VERB|\u4ed6\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 142,
350
+ "I-VERB|\u4ed6\u52d5\u8a5e\uff1f|_": 143,
351
+ "I-VERB|\u5b8c\u5168\u52d5\u8a5e|_": 144,
352
+ "I-VERB|\u683c\u52a9\u8a5e|_": 145,
353
+ "I-VERB|\u81ea\u52d5\u8a5e|_": 146,
354
+ "I-VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": 147,
355
+ "I-VERB|\u81ea\u52d5\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 148,
356
+ "I-VERT|\u4ed6\u52d5\u8a5e|_": 149,
357
+ "I-X|_|_": 150,
358
+ "INTJ|\u9593\u6295\u8a5e|_": 151,
359
+ "NOUN|\u4ee3\u540d\u8a5e|_": 152,
360
+ "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 153,
361
+ "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": 154,
362
+ "NOUN|\u540d\u8a5e|_": 155,
363
+ "NOUN|\u540d\u8a5e|_+NOUN|\u4f4d\u7f6e\u540d\u8a5e|_": 156,
364
+ "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": 157,
365
+ "NOUN|\u56fa\u6709\u540d\u8a5e|_": 158,
366
+ "NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 159,
367
+ "NUM|\u6570\u8a5e|_": 160,
368
+ "PART|[\u7d42\u52a9\u8a5e]|_": 161,
369
+ "PART|\u4eba\u79f0\u63a5\u8f9e|_": 162,
370
+ "PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 163,
371
+ "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": 164,
372
+ "PART|\u63a5\u5c3e\u8f9e|_": 165,
373
+ "PART|\u63a5\u7d9a\u52a9\u8a5e|_": 166,
374
+ "PART|\u63a5\u982d\u8f9e|_": 167,
375
+ "PART|\u7d42\u52a9\u8a5e|_": 168,
376
+ "PART|\u81ea\u52d5\u8a5e|_": 169,
377
+ "PROPN|\u56fa\u6709\u540d\u8a5e|_": 170,
378
+ "PUNCT|\u8a18\u53f7|_": 171,
379
+ "SCONJ|[\u63a5\u7d9a\u52a9\u8a5e]|_": 172,
380
+ "SCONJ|\u4ed6\u52d5\u8a5e|_": 173,
381
+ "SCONJ|\u526f\u8a5e|_": 174,
382
+ "SCONJ|\u5f8c\u7f6e\u526f\u8a5e|_": 175,
383
+ "SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": 176,
384
+ "SCONJ|\u63a5\u7d9a\u8a5e|_": 177,
385
+ "SCONJ|\u683c\u52a9\u8a5e|_": 178,
386
+ "SCONJ|\u7d42\u52a9\u8a5e|_": 179,
387
+ "SYM": 180,
388
+ "VERB|\u4ed6\u52d5\u8a5e|_": 181,
389
+ "VERB|\u4ed6\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 182,
390
+ "VERB|\u4ed6\u52d5\u8a5e|_+PART|\u63a5\u5c3e\u8f9e|_": 183,
391
+ "VERB|\u5b8c\u5168\u52d5\u8a5e|_": 184,
392
+ "VERB|\u81ea\u52d5\u8a5e|_": 185,
393
+ "VERB|\u81ea\u52d5\u8a5e|_+AUX|\u52a9\u52d5\u8a5e|_": 186,
394
+ "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u540d\u8a5e|_": 187,
395
+ "VERB|\u81ea\u52d5\u8a5e|_+NOUN|\u5f62\u5f0f\u540d\u8a5e|_": 188,
396
+ "VERB|\u81ea\u52d5\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": 189,
397
+ "X|_|_": 190
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
398
  },
399
  "layer_norm_eps": 1e-07,
400
  "max_position_embeddings": 512,
 
431
  "nangonna": [
432
  "nangon",
433
  "na"
 
 
 
 
434
  ]
435
  },
436
  "DET|\u9023\u4f53\u8a5e|_+NOUN|\u540d\u8a5e|_": {
 
441
  "Tampa": [
442
  "Tam",
443
  "pa"
 
 
 
 
 
 
 
 
444
  ]
445
  },
446
  "DET|\u9023\u4f53\u8a5e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_+VERB|\u81ea\u52d5\u8a5e|_": {
 
448
  "Ne",
449
  "wa",
450
  "an"
 
 
 
 
 
451
  ]
452
  },
453
  "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": {
 
471
  "Soi",
472
  "ta"
473
  ],
474
+ "Urorun": [
475
+ "Uror",
476
+ "un"
477
  ],
478
+ "asama": [
479
+ "asam",
480
+ "a"
481
  ],
482
+ "keseta": [
483
+ "kese",
484
  "ta"
485
  ],
486
  "orota": [
 
502
  "otta": [
503
  "ot",
504
  "ta"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
505
  ]
506
  },
507
  "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_+NOUN|\u540d\u8a5e|_": {
 
509
  "ror",
510
  "un",
511
  "purai"
 
 
 
 
 
 
 
 
 
 
 
 
512
  ]
513
  },
514
  "NOUN|\u4f4d\u7f6e\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": {
 
520
  "Orep",
521
  "un"
522
  ],
 
 
 
 
 
 
 
 
523
  "rikunruke": [
524
  "rik",
525
  "unruke"
 
527
  "ukakushte": [
528
  "uka",
529
  "kushte"
 
 
 
 
530
  ]
531
  },
532
  "NOUN|\u540d\u8a5e|_+ADP|\u683c\u52a9\u8a5e|_": {
 
537
  "cheppone": [
538
  "cheppo",
539
  "ne"
 
 
 
 
 
 
 
 
540
  ]
541
  },
542
  "NOUN|\u540d\u8a5e|_+ADV|\u526f\u8a5e|_": {
 
557
  "petetok": [
558
  "pet",
559
  "etok"
 
 
 
 
560
  ]
561
  },
562
  "NOUN|\u540d\u8a5e|_+NOUN|\u540d\u8a5e|_": {
 
576
  "kamui",
577
  "nish"
578
  ],
 
 
 
 
579
  "konkanipe": [
580
  "konkani",
581
  "pe"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
582
  ]
583
  },
584
  "NOUN|\u540d\u8a5e|_+VERB|\u4ed6\u52d5\u8a5e|_": {
 
590
  "kotan",
591
  "kor"
592
  ],
 
 
 
 
593
  "uraikik": [
594
  "urai",
595
  "kik"
 
600
  "Wan",
601
  "to"
602
  ],
 
 
 
 
603
  "wanto": [
604
  "wan",
605
  "to"
606
  ]
607
  },
 
 
 
 
 
 
608
  "PART|\u4eba\u79f0\u63a5\u8f9e|_+AUX|\u30c7\u30a2\u30eb\u52d5\u8a5e|_": {
609
  "chine": [
610
  "chi",
 
617
  "sam"
618
  ]
619
  },
620
+ "PART|\u4eba\u79f0\u63a5\u8f9e|_+SCONJ|\u63a5\u7d9a\u52a9\u8a5e|_": {
621
+ "anak": [
622
+ "an",
623
+ "ak"
624
+ ],
625
+ "anak ka": [
626
+ "an",
627
+ "ak ka"
628
  ]
629
  },
630
  "PART|\u4eba\u79f0\u63a5\u8f9e|_+VERB|\u4ed6\u52d5\u8a5e|_": {
 
648
  "e",
649
  "ram an"
650
  ],
651
+ "eraman": [
652
+ "e",
653
+ "raman"
654
+ ],
655
  "eramasu": [
656
  "e",
657
  "ramasu"
 
702
  "am",
703
  "be"
704
  ],
 
 
 
 
705
  "anto": [
706
  "an",
707
  "to"
708
  ],
 
 
 
 
709
  "wenpuri": [
710
  "wen",
711
  "puri"
 
715
  "ambe": [
716
  "am",
717
  "be"
 
 
 
 
718
  ]
719
  },
720
  "VERB|\u81ea\u52d5\u8a5e|_+PART|\u4eba\u79f0\u63a5\u8f9e|_": {
 
751
  },
752
  "tokenizer_class": "DebertaV2TokenizerFast",
753
  "torch_dtype": "float32",
754
+ "transformers_version": "4.22.1",
755
  "type_vocab_size": 0,
756
  "vocab_size": 6143
757
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d8170f1dc079c571024819ed51da72737802f5496aa91ea9b9e897cd057cdc3
3
- size 419684622
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:badc5f6bd055ae321f11ed18a0c6128d664f205bbda8e2fc87c95e02344f5680
3
+ size 419613139
supar.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a3be76abfe33d66cddc9cd8cabef468bc0b862dff5d10ff8994bd65f7fe30fd
3
- size 464325982
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1252472f31fc0650b080bb5ecd069b75ba707d55ccf43560fb69066e0e590984
3
+ size 464340235
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff