Hugging Face's logo

yahyaabd
/
indosbert-bps-custom-tokenizer

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
text-embeddings-inference
Model card Files Community
yahyaabd commited on
Commit
6f6c413
·
verified ·
1 Parent(s): 90f3a4e

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +14 -0
  3. added_tokens.json +55 -0
  4. config.json +46 -0
  5. config_sentence_transformers.json +10 -0
  6. model.safetensors +3 -0
  7. modules.json +14 -0
  8. sentence_bert_config.json +4 -0
  9. special_tokens_map.json +37 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +489 -0
  12. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Custom BPS SentenceTransformer
2
+
3
+ Model ini berbasis `paraphrase-multilingual-MiniLM-L12-v2` dengan tambahan token khusus untuk konteks statistik Badan Pusat Statistik (BPS) Indonesia. Token baru mencakup istilah seperti `PDRB`, `SP2020`, `SAKERNAS`, dll.
4
+
5
+ ## Cara Penggunaan
6
+ ```python
7
+ from sentence_transformers import SentenceTransformer
8
+
9
+ model = SentenceTransformer('yahyaabd/paraphrase-multilingual-MiniLM-L12-v2-bps-custom-tokenizer')
10
+ embeddings = model.encode(['PDRB meningkat di tahun 2023.', 'BPS merilis ST2023.'])
11
+ ```
12
+
13
+ ## Kontak
14
+ Hubungi [yahyaabd] di Hugging Face untuk pertanyaan atau dukungan.
added_tokens.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "BADAN PUSAT STATISTIK": 30522,
3
+ "BPP": 30551,
4
+ "BPS": 30521,
5
+ "BRS": 30566,
6
+ "CIF": 30556,
7
+ "EKSPOR": 30552,
8
+ "FOB": 30555,
9
+ "HLS": 30543,
10
+ "HS": 30554,
11
+ "IHK": 30525,
12
+ "IHP": 30527,
13
+ "IHPB": 30528,
14
+ "IMK": 30532,
15
+ "IMPOR": 30553,
16
+ "IPH": 30526,
17
+ "IPM": 30537,
18
+ "ITB": 30531,
19
+ "ITK": 30530,
20
+ "KATALOG": 30572,
21
+ "KB": 30542,
22
+ "KCI": 30562,
23
+ "KEGIATAN": 30568,
24
+ "KKI": 30561,
25
+ "KKL": 30560,
26
+ "KRT": 30563,
27
+ "LPE": 30533,
28
+ "LTN": 30549,
29
+ "LTT": 30548,
30
+ "METADATA": 30571,
31
+ "NTP": 30529,
32
+ "NTUP": 30550,
33
+ "PDB": 30524,
34
+ "PDRB": 30523,
35
+ "PKL": 30559,
36
+ "PUBLIKASI": 30567,
37
+ "RLS": 30544,
38
+ "RT": 30564,
39
+ "RW": 30565,
40
+ "SAKERNAS": 30557,
41
+ "SDGI": 30541,
42
+ "SDKI": 30540,
43
+ "SEKTORAL": 30570,
44
+ "SP2020": 30538,
45
+ "ST2013": 30547,
46
+ "ST2023": 30546,
47
+ "STATISTIK": 30569,
48
+ "SUPAS": 30539,
49
+ "SURVEI": 30573,
50
+ "SUTAS": 30545,
51
+ "TPAK": 30558,
52
+ "TPK": 30534,
53
+ "TPT": 30535,
54
+ "UMP": 30536
55
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 5,
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3,
26
+ "LABEL_4": 4
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_position_embeddings": 512,
30
+ "model_type": "bert",
31
+ "num_attention_heads": 16,
32
+ "num_hidden_layers": 24,
33
+ "output_past": true,
34
+ "pad_token_id": 0,
35
+ "pooler_fc_size": 768,
36
+ "pooler_num_attention_heads": 12,
37
+ "pooler_num_fc_layers": 3,
38
+ "pooler_size_per_head": 128,
39
+ "pooler_type": "first_token_transform",
40
+ "position_embedding_type": "absolute",
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.51.3",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 30574
46
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.4.1",
4
+ "transformers": "4.51.3",
5
+ "pytorch": "2.6.0+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e60913acacea8cbbe7e23c51dc87a3861ab07d76a450979f1656e8409e32f6b
3
+ size 1340825424
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,489 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30521": {
44
+ "content": "BPS",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "30522": {
52
+ "content": "BADAN PUSAT STATISTIK",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "30523": {
60
+ "content": "PDRB",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "30524": {
68
+ "content": "PDB",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "30525": {
76
+ "content": "IHK",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "30526": {
84
+ "content": "IPH",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "30527": {
92
+ "content": "IHP",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "30528": {
100
+ "content": "IHPB",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "30529": {
108
+ "content": "NTP",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "30530": {
116
+ "content": "ITK",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "30531": {
124
+ "content": "ITB",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "30532": {
132
+ "content": "IMK",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "30533": {
140
+ "content": "LPE",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "30534": {
148
+ "content": "TPK",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "30535": {
156
+ "content": "TPT",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "30536": {
164
+ "content": "UMP",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "30537": {
172
+ "content": "IPM",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "30538": {
180
+ "content": "SP2020",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "30539": {
188
+ "content": "SUPAS",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "30540": {
196
+ "content": "SDKI",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "30541": {
204
+ "content": "SDGI",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "30542": {
212
+ "content": "KB",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "30543": {
220
+ "content": "HLS",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "30544": {
228
+ "content": "RLS",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "30545": {
236
+ "content": "SUTAS",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "30546": {
244
+ "content": "ST2023",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "30547": {
252
+ "content": "ST2013",
253
+ "lstrip": false,
254
+ "normalized": true,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "30548": {
260
+ "content": "LTT",
261
+ "lstrip": false,
262
+ "normalized": true,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "30549": {
268
+ "content": "LTN",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "30550": {
276
+ "content": "NTUP",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "30551": {
284
+ "content": "BPP",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "30552": {
292
+ "content": "EKSPOR",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "30553": {
300
+ "content": "IMPOR",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "30554": {
308
+ "content": "HS",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "30555": {
316
+ "content": "FOB",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "30556": {
324
+ "content": "CIF",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "30557": {
332
+ "content": "SAKERNAS",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "30558": {
340
+ "content": "TPAK",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "30559": {
348
+ "content": "PKL",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "30560": {
356
+ "content": "KKL",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "30561": {
364
+ "content": "KKI",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "30562": {
372
+ "content": "KCI",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "30563": {
380
+ "content": "KRT",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "30564": {
388
+ "content": "RT",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "30565": {
396
+ "content": "RW",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "30566": {
404
+ "content": "BRS",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "30567": {
412
+ "content": "PUBLIKASI",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "30568": {
420
+ "content": "KEGIATAN",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "30569": {
428
+ "content": "STATISTIK",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "30570": {
436
+ "content": "SEKTORAL",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "30571": {
444
+ "content": "METADATA",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "30572": {
452
+ "content": "KATALOG",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "30573": {
460
+ "content": "SURVEI",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ }
467
+ },
468
+ "clean_up_tokenization_spaces": true,
469
+ "cls_token": "[CLS]",
470
+ "do_basic_tokenize": true,
471
+ "do_lower_case": true,
472
+ "extra_special_tokens": {},
473
+ "mask_token": "[MASK]",
474
+ "max_length": 256,
475
+ "model_max_length": 1000000000000000019884624838656,
476
+ "never_split": null,
477
+ "pad_to_multiple_of": null,
478
+ "pad_token": "[PAD]",
479
+ "pad_token_type_id": 0,
480
+ "padding_side": "right",
481
+ "sep_token": "[SEP]",
482
+ "stride": 0,
483
+ "strip_accents": null,
484
+ "tokenize_chinese_chars": true,
485
+ "tokenizer_class": "BertTokenizer",
486
+ "truncation_side": "right",
487
+ "truncation_strategy": "longest_first",
488
+ "unk_token": "[UNK]"
489
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff