damand2061 commited on
Commit
6d3c198
1 Parent(s): 98d145d

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
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 +1,489 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: indobenchmark/indobert-base-p1
3
+ datasets: []
4
+ language: []
5
+ library_name: sentence-transformers
6
+ metrics:
7
+ - pearson_cosine
8
+ - spearman_cosine
9
+ - pearson_manhattan
10
+ - spearman_manhattan
11
+ - pearson_euclidean
12
+ - spearman_euclidean
13
+ - pearson_dot
14
+ - spearman_dot
15
+ - pearson_max
16
+ - spearman_max
17
+ pipeline_tag: sentence-similarity
18
+ tags:
19
+ - sentence-transformers
20
+ - sentence-similarity
21
+ - feature-extraction
22
+ - generated_from_trainer
23
+ - dataset_size:12000
24
+ - loss:MegaBatchMarginLoss
25
+ widget:
26
+ - source_sentence: Awalnya merupakan singkatan dari John's Macintosh Project.
27
+ sentences:
28
+ - Sebuah formasi yang terdiri dari sekitar 50 petugas Polisi Baltimore akhirnya
29
+ menempatkan diri mereka di antara para perusuh dan milisi, memungkinkan Massachusetts
30
+ ke-6 untuk melanjutkan ke Stasiun Camden.
31
+ - Mengecat luka dapat melindungi dari jamur dan hama.
32
+ - Dulunya merupakan singkatan dari John's Macintosh Project.
33
+ - source_sentence: Boueiz berprofesi sebagai pengacara.
34
+ sentences:
35
+ - Mereka juga gagal mengembangkan Water Cooperation Quotient yang baru.
36
+ - Pada Pemilu 1970, ia ikut serta dari Partai Persatuan Nasional namun dikalahkan.
37
+ - Seorang pengacara berprofesi sebagai Boueiz.
38
+ - source_sentence: Fakultas Studi Oriental memiliki seorang profesor.
39
+ sentences:
40
+ - Di tempat lain di New Mexico, LAHS terkadang dianggap sebagai sekolah untuk orang
41
+ kaya.
42
+ - Laporan lain juga menunjukkan kandungannya lebih rendah dari 0,1% di Australia.
43
+ - Profesor tersebut merupakan bagian dari Fakultas Studi Oriental.
44
+ - source_sentence: Hal ini terjadi di sejumlah negara, termasuk Ethiopia, Republik
45
+ Demokratik Kongo, dan Afrika Selatan.
46
+ sentences:
47
+ - Hal ini diketahui terjadi di Eritrea, Ethiopia, Kongo, Tanzania, Namibia dan Afrika
48
+ Selatan.
49
+ - Gugus amil digantikan oleh gugus pentil.
50
+ - Dan saya beritahu Anda sesuatu, itu tidak adil.
51
+ - source_sentence: Ini adalah wilayah sosial-ekonomi yang lebih rendah.
52
+ sentences:
53
+ - Ini adalah bengkel perbaikan mobil terbaru yang masih beroperasi di kota.
54
+ - Zelinsky hanya berteori bahwa tidak ada tiga bilangan bulat berurutan yang semuanya
55
+ dapat difaktorkan ulang.
56
+ - Ini adalah wilayah sosial-ekonomi yang lebih tinggi.
57
+ model-index:
58
+ - name: SentenceTransformer based on indobenchmark/indobert-base-p1
59
+ results:
60
+ - task:
61
+ type: semantic-similarity
62
+ name: Semantic Similarity
63
+ dataset:
64
+ name: str dev
65
+ type: str-dev
66
+ metrics:
67
+ - type: pearson_cosine
68
+ value: 0.45499177580198114
69
+ name: Pearson Cosine
70
+ - type: spearman_cosine
71
+ value: 0.47824954773877343
72
+ name: Spearman Cosine
73
+ - type: pearson_manhattan
74
+ value: 0.5063760846250573
75
+ name: Pearson Manhattan
76
+ - type: spearman_manhattan
77
+ value: 0.49835693711719375
78
+ name: Spearman Manhattan
79
+ - type: pearson_euclidean
80
+ value: 0.5062153453050553
81
+ name: Pearson Euclidean
82
+ - type: spearman_euclidean
83
+ value: 0.4982327535492364
84
+ name: Spearman Euclidean
85
+ - type: pearson_dot
86
+ value: 0.27097056415300647
87
+ name: Pearson Dot
88
+ - type: spearman_dot
89
+ value: 0.25179460239023077
90
+ name: Spearman Dot
91
+ - type: pearson_max
92
+ value: 0.5063760846250573
93
+ name: Pearson Max
94
+ - type: spearman_max
95
+ value: 0.49835693711719375
96
+ name: Spearman Max
97
+ - task:
98
+ type: semantic-similarity
99
+ name: Semantic Similarity
100
+ dataset:
101
+ name: str test
102
+ type: str-test
103
+ metrics:
104
+ - type: pearson_cosine
105
+ value: 0.47495139518851825
106
+ name: Pearson Cosine
107
+ - type: spearman_cosine
108
+ value: 0.5059515739122313
109
+ name: Spearman Cosine
110
+ - type: pearson_manhattan
111
+ value: 0.50154011084872
112
+ name: Pearson Manhattan
113
+ - type: spearman_manhattan
114
+ value: 0.5058071904463332
115
+ name: Spearman Manhattan
116
+ - type: pearson_euclidean
117
+ value: 0.5028237271275693
118
+ name: Pearson Euclidean
119
+ - type: spearman_euclidean
120
+ value: 0.5061159996491946
121
+ name: Spearman Euclidean
122
+ - type: pearson_dot
123
+ value: 0.3250041946830172
124
+ name: Pearson Dot
125
+ - type: spearman_dot
126
+ value: 0.31627719040314917
127
+ name: Spearman Dot
128
+ - type: pearson_max
129
+ value: 0.5028237271275693
130
+ name: Pearson Max
131
+ - type: spearman_max
132
+ value: 0.5061159996491946
133
+ name: Spearman Max
134
+ ---
135
+
136
+ # SentenceTransformer based on indobenchmark/indobert-base-p1
137
+
138
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [indobenchmark/indobert-base-p1](https://huggingface.co/indobenchmark/indobert-base-p1). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
139
+
140
+ ## Model Details
141
+
142
+ ### Model Description
143
+ - **Model Type:** Sentence Transformer
144
+ - **Base model:** [indobenchmark/indobert-base-p1](https://huggingface.co/indobenchmark/indobert-base-p1) <!-- at revision c2cd0b51ddce6580eb35263b39b0a1e5fb0a39e2 -->
145
+ - **Maximum Sequence Length:** 32 tokens
146
+ - **Output Dimensionality:** 768 tokens
147
+ - **Similarity Function:** Cosine Similarity
148
+ <!-- - **Training Dataset:** Unknown -->
149
+ <!-- - **Language:** Unknown -->
150
+ <!-- - **License:** Unknown -->
151
+
152
+ ### Model Sources
153
+
154
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
155
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
156
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
157
+
158
+ ### Full Model Architecture
159
+
160
+ ```
161
+ SentenceTransformer(
162
+ (0): Transformer({'max_seq_length': 32, 'do_lower_case': False}) with Transformer model: BertModel
163
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
164
+ )
165
+ ```
166
+
167
+ ## Usage
168
+
169
+ ### Direct Usage (Sentence Transformers)
170
+
171
+ First install the Sentence Transformers library:
172
+
173
+ ```bash
174
+ pip install -U sentence-transformers
175
+ ```
176
+
177
+ Then you can load this model and run inference.
178
+ ```python
179
+ from sentence_transformers import SentenceTransformer
180
+
181
+ # Download from the 🤗 Hub
182
+ model = SentenceTransformer("damand2061/negasibert-mbm")
183
+ # Run inference
184
+ sentences = [
185
+ 'Ini adalah wilayah sosial-ekonomi yang lebih rendah.',
186
+ 'Ini adalah wilayah sosial-ekonomi yang lebih tinggi.',
187
+ 'Zelinsky hanya berteori bahwa tidak ada tiga bilangan bulat berurutan yang semuanya dapat difaktorkan ulang.',
188
+ ]
189
+ embeddings = model.encode(sentences)
190
+ print(embeddings.shape)
191
+ # [3, 768]
192
+
193
+ # Get the similarity scores for the embeddings
194
+ similarities = model.similarity(embeddings, embeddings)
195
+ print(similarities.shape)
196
+ # [3, 3]
197
+ ```
198
+
199
+ <!--
200
+ ### Direct Usage (Transformers)
201
+
202
+ <details><summary>Click to see the direct usage in Transformers</summary>
203
+
204
+ </details>
205
+ -->
206
+
207
+ <!--
208
+ ### Downstream Usage (Sentence Transformers)
209
+
210
+ You can finetune this model on your own dataset.
211
+
212
+ <details><summary>Click to expand</summary>
213
+
214
+ </details>
215
+ -->
216
+
217
+ <!--
218
+ ### Out-of-Scope Use
219
+
220
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
221
+ -->
222
+
223
+ ## Evaluation
224
+
225
+ ### Metrics
226
+
227
+ #### Semantic Similarity
228
+ * Dataset: `str-dev`
229
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
230
+
231
+ | Metric | Value |
232
+ |:-------------------|:-----------|
233
+ | pearson_cosine | 0.455 |
234
+ | spearman_cosine | 0.4782 |
235
+ | pearson_manhattan | 0.5064 |
236
+ | spearman_manhattan | 0.4984 |
237
+ | pearson_euclidean | 0.5062 |
238
+ | spearman_euclidean | 0.4982 |
239
+ | pearson_dot | 0.271 |
240
+ | spearman_dot | 0.2518 |
241
+ | pearson_max | 0.5064 |
242
+ | **spearman_max** | **0.4984** |
243
+
244
+ #### Semantic Similarity
245
+ * Dataset: `str-test`
246
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
247
+
248
+ | Metric | Value |
249
+ |:-------------------|:-----------|
250
+ | pearson_cosine | 0.475 |
251
+ | spearman_cosine | 0.506 |
252
+ | pearson_manhattan | 0.5015 |
253
+ | spearman_manhattan | 0.5058 |
254
+ | pearson_euclidean | 0.5028 |
255
+ | spearman_euclidean | 0.5061 |
256
+ | pearson_dot | 0.325 |
257
+ | spearman_dot | 0.3163 |
258
+ | pearson_max | 0.5028 |
259
+ | **spearman_max** | **0.5061** |
260
+
261
+ <!--
262
+ ## Bias, Risks and Limitations
263
+
264
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
265
+ -->
266
+
267
+ <!--
268
+ ### Recommendations
269
+
270
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
271
+ -->
272
+
273
+ ## Training Details
274
+
275
+ ### Training Dataset
276
+
277
+ #### Unnamed Dataset
278
+
279
+
280
+ * Size: 12,000 training samples
281
+ * Columns: <code>sentence_0</code> and <code>sentence_1</code>
282
+ * Approximate statistics based on the first 1000 samples:
283
+ | | sentence_0 | sentence_1 |
284
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
285
+ | type | string | string |
286
+ | details | <ul><li>min: 5 tokens</li><li>mean: 14.84 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.83 tokens</li><li>max: 32 tokens</li></ul> |
287
+ * Samples:
288
+ | sentence_0 | sentence_1 |
289
+ |:-------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------|
290
+ | <code>Pusat Peringatan Topan Gabungan (JTWC) juga mengeluarkan peringatan dalam kapasitas tidak resmi.</code> | <code>Pusat Peringatan Topan Gabungan (JTWC) hanya mengeluarkan peringatan dalam kapasitas yang tidak resmi.</code> |
291
+ | <code>DNP komersial digunakan sebagai antiseptik dan pestisida bioakumulasi non-selektif.</code> | <code>DNP komersial tidak dapat digunakan sebagai antiseptik atau pestisida bioakumulasi non-selektif.</code> |
292
+ | <code>Kuncian tulang belakang dan kuncian serviks diperbolehkan dan wajib dalam kompetisi jiu-jitsu Brasil IBJJF.</code> | <code>Kuncian tulang belakang dan kuncian serviks dilarang dalam kompetisi jiu-jitsu Brasil IBJJF.</code> |
293
+ * Loss: [<code>MegaBatchMarginLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#megabatchmarginloss)
294
+
295
+ ### Training Hyperparameters
296
+ #### Non-Default Hyperparameters
297
+
298
+ - `per_device_train_batch_size`: 500
299
+ - `per_device_eval_batch_size`: 500
300
+ - `num_train_epochs`: 5
301
+ - `multi_dataset_batch_sampler`: round_robin
302
+
303
+ #### All Hyperparameters
304
+ <details><summary>Click to expand</summary>
305
+
306
+ - `overwrite_output_dir`: False
307
+ - `do_predict`: False
308
+ - `eval_strategy`: no
309
+ - `prediction_loss_only`: True
310
+ - `per_device_train_batch_size`: 500
311
+ - `per_device_eval_batch_size`: 500
312
+ - `per_gpu_train_batch_size`: None
313
+ - `per_gpu_eval_batch_size`: None
314
+ - `gradient_accumulation_steps`: 1
315
+ - `eval_accumulation_steps`: None
316
+ - `torch_empty_cache_steps`: None
317
+ - `learning_rate`: 5e-05
318
+ - `weight_decay`: 0.0
319
+ - `adam_beta1`: 0.9
320
+ - `adam_beta2`: 0.999
321
+ - `adam_epsilon`: 1e-08
322
+ - `max_grad_norm`: 1
323
+ - `num_train_epochs`: 5
324
+ - `max_steps`: -1
325
+ - `lr_scheduler_type`: linear
326
+ - `lr_scheduler_kwargs`: {}
327
+ - `warmup_ratio`: 0.0
328
+ - `warmup_steps`: 0
329
+ - `log_level`: passive
330
+ - `log_level_replica`: warning
331
+ - `log_on_each_node`: True
332
+ - `logging_nan_inf_filter`: True
333
+ - `save_safetensors`: True
334
+ - `save_on_each_node`: False
335
+ - `save_only_model`: False
336
+ - `restore_callback_states_from_checkpoint`: False
337
+ - `no_cuda`: False
338
+ - `use_cpu`: False
339
+ - `use_mps_device`: False
340
+ - `seed`: 42
341
+ - `data_seed`: None
342
+ - `jit_mode_eval`: False
343
+ - `use_ipex`: False
344
+ - `bf16`: False
345
+ - `fp16`: False
346
+ - `fp16_opt_level`: O1
347
+ - `half_precision_backend`: auto
348
+ - `bf16_full_eval`: False
349
+ - `fp16_full_eval`: False
350
+ - `tf32`: None
351
+ - `local_rank`: 0
352
+ - `ddp_backend`: None
353
+ - `tpu_num_cores`: None
354
+ - `tpu_metrics_debug`: False
355
+ - `debug`: []
356
+ - `dataloader_drop_last`: False
357
+ - `dataloader_num_workers`: 0
358
+ - `dataloader_prefetch_factor`: None
359
+ - `past_index`: -1
360
+ - `disable_tqdm`: False
361
+ - `remove_unused_columns`: True
362
+ - `label_names`: None
363
+ - `load_best_model_at_end`: False
364
+ - `ignore_data_skip`: False
365
+ - `fsdp`: []
366
+ - `fsdp_min_num_params`: 0
367
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
368
+ - `fsdp_transformer_layer_cls_to_wrap`: None
369
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
370
+ - `deepspeed`: None
371
+ - `label_smoothing_factor`: 0.0
372
+ - `optim`: adamw_torch
373
+ - `optim_args`: None
374
+ - `adafactor`: False
375
+ - `group_by_length`: False
376
+ - `length_column_name`: length
377
+ - `ddp_find_unused_parameters`: None
378
+ - `ddp_bucket_cap_mb`: None
379
+ - `ddp_broadcast_buffers`: False
380
+ - `dataloader_pin_memory`: True
381
+ - `dataloader_persistent_workers`: False
382
+ - `skip_memory_metrics`: True
383
+ - `use_legacy_prediction_loop`: False
384
+ - `push_to_hub`: False
385
+ - `resume_from_checkpoint`: None
386
+ - `hub_model_id`: None
387
+ - `hub_strategy`: every_save
388
+ - `hub_private_repo`: False
389
+ - `hub_always_push`: False
390
+ - `gradient_checkpointing`: False
391
+ - `gradient_checkpointing_kwargs`: None
392
+ - `include_inputs_for_metrics`: False
393
+ - `eval_do_concat_batches`: True
394
+ - `fp16_backend`: auto
395
+ - `push_to_hub_model_id`: None
396
+ - `push_to_hub_organization`: None
397
+ - `mp_parameters`:
398
+ - `auto_find_batch_size`: False
399
+ - `full_determinism`: False
400
+ - `torchdynamo`: None
401
+ - `ray_scope`: last
402
+ - `ddp_timeout`: 1800
403
+ - `torch_compile`: False
404
+ - `torch_compile_backend`: None
405
+ - `torch_compile_mode`: None
406
+ - `dispatch_batches`: None
407
+ - `split_batches`: None
408
+ - `include_tokens_per_second`: False
409
+ - `include_num_input_tokens_seen`: False
410
+ - `neftune_noise_alpha`: None
411
+ - `optim_target_modules`: None
412
+ - `batch_eval_metrics`: False
413
+ - `eval_on_start`: False
414
+ - `eval_use_gather_object`: False
415
+ - `batch_sampler`: batch_sampler
416
+ - `multi_dataset_batch_sampler`: round_robin
417
+
418
+ </details>
419
+
420
+ ### Training Logs
421
+ | Epoch | Step | str-dev_spearman_max | str-test_spearman_max |
422
+ |:-----:|:----:|:--------------------:|:---------------------:|
423
+ | 1.0 | 24 | 0.4904 | 0.5030 |
424
+ | 2.0 | 48 | 0.4905 | 0.5036 |
425
+ | 3.0 | 72 | 0.4947 | 0.5041 |
426
+ | 4.0 | 96 | 0.4963 | 0.5061 |
427
+ | 5.0 | 120 | 0.4984 | 0.5061 |
428
+
429
+
430
+ ### Framework Versions
431
+ - Python: 3.10.14
432
+ - Sentence Transformers: 3.0.1
433
+ - Transformers: 4.44.0
434
+ - PyTorch: 2.4.0
435
+ - Accelerate: 0.33.0
436
+ - Datasets: 2.21.0
437
+ - Tokenizers: 0.19.1
438
+
439
+ ## Citation
440
+
441
+ ### BibTeX
442
+
443
+ #### Sentence Transformers
444
+ ```bibtex
445
+ @inproceedings{reimers-2019-sentence-bert,
446
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
447
+ author = "Reimers, Nils and Gurevych, Iryna",
448
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
449
+ month = "11",
450
+ year = "2019",
451
+ publisher = "Association for Computational Linguistics",
452
+ url = "https://arxiv.org/abs/1908.10084",
453
+ }
454
+ ```
455
+
456
+ #### MegaBatchMarginLoss
457
+ ```bibtex
458
+ @inproceedings{wieting-gimpel-2018-paranmt,
459
+ title = "{P}ara{NMT}-50{M}: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations",
460
+ author = "Wieting, John and Gimpel, Kevin",
461
+ editor = "Gurevych, Iryna and Miyao, Yusuke",
462
+ booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
463
+ month = jul,
464
+ year = "2018",
465
+ address = "Melbourne, Australia",
466
+ publisher = "Association for Computational Linguistics",
467
+ url = "https://aclanthology.org/P18-1042",
468
+ doi = "10.18653/v1/P18-1042",
469
+ pages = "451--462",
470
+ }
471
+ ```
472
+
473
+ <!--
474
+ ## Glossary
475
+
476
+ *Clearly define terms in order to be accessible across audiences.*
477
+ -->
478
+
479
+ <!--
480
+ ## Model Card Authors
481
+
482
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
483
+ -->
484
+
485
+ <!--
486
+ ## Model Card Contact
487
+
488
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
489
+ -->
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "indobenchmark/indobert-base-p1",
3
+ "_num_labels": 5,
4
+ "architectures": [
5
+ "BertModel"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 0,
36
+ "pooler_fc_size": 768,
37
+ "pooler_num_attention_heads": 12,
38
+ "pooler_num_fc_layers": 3,
39
+ "pooler_size_per_head": 128,
40
+ "pooler_type": "first_token_transform",
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.44.0",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 50000
47
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.44.0",
5
+ "pytorch": "2.4.0"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa729fcde96bb8c9e32ddbcee5365d47f4db3eb09812f0e824a3640b42431807
3
+ size 497787752
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": 32,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 32,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff