Hugging Face's logo

mideind
/
IceBERT-PoS

Feature Extraction
Transformers
Safetensors
Icelandic
icebert-pos
nlp
pos
custom_code
Model card Files
xet
 Community
haukurpj commited on
Commit
d2f797f
·
1 Parent(s): dca38d2

Reformat config file

Browse files
Files changed (1) hide show
  1. config.json +40 -191
config.json CHANGED
@@ -1,7 +1,5 @@
1
  {
2
- "architectures": [
3
- "IceBertPosForTokenClassification"
4
- ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "attr_proj_input_size": 811,
7
  "auto_map": {
@@ -162,196 +160,47 @@
162
  },
163
  "label_schema": {
164
  "category_to_group_names": {
165
- "aa": [
166
- "deg"
167
- ],
168
- "ae": [
169
- "deg"
170
- ],
171
- "af": [
172
- "deg"
173
- ],
174
- "ao": [
175
- "deg"
176
- ],
177
- "as": [
178
- "deg"
179
- ],
180
- "au": [
181
- "deg"
182
- ],
183
- "a\u00fe": [
184
- "deg"
185
- ],
186
- "fa": [
187
- "gender",
188
- "number",
189
- "case"
190
- ],
191
- "fb": [
192
- "gender",
193
- "number",
194
- "case"
195
- ],
196
- "fe": [
197
- "gender",
198
- "number",
199
- "case"
200
- ],
201
- "fo": [
202
- "gender_or_person",
203
- "number",
204
- "case"
205
- ],
206
- "fp": [
207
- "gender_or_person",
208
- "number",
209
- "case"
210
- ],
211
- "fs": [
212
- "gender",
213
- "number",
214
- "case"
215
- ],
216
- "ft": [
217
- "gender",
218
- "number",
219
- "case"
220
- ],
221
- "g": [
222
- "gender",
223
- "number",
224
- "case"
225
- ],
226
- "l": [
227
- "gender",
228
- "number",
229
- "case",
230
- "adj_c",
231
- "deg"
232
- ],
233
- "n": [
234
- "gender",
235
- "number",
236
- "case",
237
- "def",
238
- "proper"
239
- ],
240
- "sb": [
241
- "voice",
242
- "person",
243
- "number",
244
- "tense"
245
- ],
246
- "sf": [
247
- "voice",
248
- "person",
249
- "number",
250
- "tense"
251
- ],
252
- "sl": [
253
- "voice",
254
- "person",
255
- "number",
256
- "tense"
257
- ],
258
- "sn": [
259
- "voice"
260
- ],
261
- "ss": [
262
- "voice"
263
- ],
264
- "sv": [
265
- "voice",
266
- "person",
267
- "number",
268
- "tense"
269
- ],
270
- "s\u00fe": [
271
- "voice",
272
- "gender",
273
- "number",
274
- "case"
275
- ],
276
- "tf": [
277
- "gender",
278
- "number",
279
- "case"
280
- ]
281
  },
282
  "group_name_to_labels": {
283
- "adj_c": [
284
- "strong",
285
- "weak",
286
- "equiinflected"
287
- ],
288
- "case": [
289
- "nom",
290
- "acc",
291
- "dat",
292
- "gen"
293
- ],
294
- "def": [
295
- "definite"
296
- ],
297
- "deg": [
298
- "pos",
299
- "cmp",
300
- "superl"
301
- ],
302
- "gender": [
303
- "masc",
304
- "fem",
305
- "neut",
306
- "gender_x"
307
- ],
308
- "gender_or_person": [
309
- "masc",
310
- "fem",
311
- "neut",
312
- "gender_x",
313
- "1",
314
- "2",
315
- "3"
316
- ],
317
- "number": [
318
- "sing",
319
- "plur"
320
- ],
321
- "person": [
322
- "1",
323
- "2",
324
- "3"
325
- ],
326
- "proper": [
327
- "proper"
328
- ],
329
- "tense": [
330
- "pres",
331
- "past"
332
- ],
333
- "voice": [
334
- "act",
335
- "mid"
336
- ]
337
  },
338
- "group_names": [
339
- "gender",
340
- "gender_or_person",
341
- "number",
342
- "case",
343
- "def",
344
- "proper",
345
- "adj_c",
346
- "deg",
347
- "voice",
348
- "person",
349
- "tense"
350
- ],
351
- "ignore_categories": [
352
- "x",
353
- "e"
354
- ],
355
  "label_categories": [
356
  "n",
357
  "g",
@@ -471,7 +320,7 @@
471
  ],
472
  "separator": "<SEP>"
473
  },
474
- "layer_norm_eps": 1e-05,
475
  "max_position_embeddings": 514,
476
  "model_type": "icebert-pos",
477
  "num_attention_heads": 12,
 
1
  {
2
+ "architectures": ["IceBertPosForTokenClassification"],
 
 
3
  "attention_probs_dropout_prob": 0.1,
4
  "attr_proj_input_size": 811,
5
  "auto_map": {
 
160
  },
161
  "label_schema": {
162
  "category_to_group_names": {
163
+ "aa": ["deg"],
164
+ "ae": ["deg"],
165
+ "af": ["deg"],
166
+ "ao": ["deg"],
167
+ "as": ["deg"],
168
+ "au": ["deg"],
169
+ "a\u00fe": ["deg"],
170
+ "fa": ["gender", "number", "case"],
171
+ "fb": ["gender", "number", "case"],
172
+ "fe": ["gender", "number", "case"],
173
+ "fo": ["gender_or_person", "number", "case"],
174
+ "fp": ["gender_or_person", "number", "case"],
175
+ "fs": ["gender", "number", "case"],
176
+ "ft": ["gender", "number", "case"],
177
+ "g": ["gender", "number", "case"],
178
+ "l": ["gender", "number", "case", "adj_c", "deg"],
179
+ "n": ["gender", "number", "case", "def", "proper"],
180
+ "sb": ["voice", "person", "number", "tense"],
181
+ "sf": ["voice", "person", "number", "tense"],
182
+ "sl": ["voice", "person", "number", "tense"],
183
+ "sn": ["voice"],
184
+ "ss": ["voice"],
185
+ "sv": ["voice", "person", "number", "tense"],
186
+ "s\u00fe": ["voice", "gender", "number", "case"],
187
+ "tf": ["gender", "number", "case"]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
188
  },
189
  "group_name_to_labels": {
190
+ "adj_c": ["strong", "weak", "equiinflected"],
191
+ "case": ["nom", "acc", "dat", "gen"],
192
+ "def": ["definite"],
193
+ "deg": ["pos", "cmp", "superl"],
194
+ "gender": ["masc", "fem", "neut", "gender_x"],
195
+ "gender_or_person": ["masc", "fem", "neut", "gender_x", "1", "2", "3"],
196
+ "number": ["sing", "plur"],
197
+ "person": ["1", "2", "3"],
198
+ "proper": ["proper"],
199
+ "tense": ["pres", "past"],
200
+ "voice": ["act", "mid"]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  },
202
+ "group_names": ["gender", "gender_or_person", "number", "case", "def", "proper", "adj_c", "deg", "voice", "person", "tense"],
203
+ "ignore_categories": ["x", "e"],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
204
  "label_categories": [
205
  "n",
206
  "g",
 
320
  ],
321
  "separator": "<SEP>"
322
  },
323
+ "layer_norm_eps": 1e-5,
324
  "max_position_embeddings": 514,
325
  "model_type": "icebert-pos",
326
  "num_attention_heads": 12,