realaer commited on
Commit
c8dc454
·
verified ·
1 Parent(s): 849c7ce

Upload folder using huggingface_hub

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 +1,467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: klue/roberta-base
3
+ library_name: sentence-transformers
4
+ metrics:
5
+ - pearson_cosine
6
+ - spearman_cosine
7
+ - pearson_manhattan
8
+ - spearman_manhattan
9
+ - pearson_euclidean
10
+ - spearman_euclidean
11
+ - pearson_dot
12
+ - spearman_dot
13
+ - pearson_max
14
+ - spearman_max
15
+ pipeline_tag: sentence-similarity
16
+ tags:
17
+ - sentence-transformers
18
+ - sentence-similarity
19
+ - feature-extraction
20
+ - generated_from_trainer
21
+ - dataset_size:7654
22
+ - loss:CosineSimilarityLoss
23
+ widget:
24
+ - source_sentence: 밥을 먹고 나서 운동하시겠어요, 먹기 전에 하시겠어요?
25
+ sentences:
26
+ - 제습기 조정하는 방법을 알려줘
27
+ - 금요일에 놀러 가고 싶은지 토요일에 가고 싶은지 말해보겠니?
28
+ - 이번에 임원들도 오시니 거래처 사람들과 만날 때 늦지 마세요.
29
+ - source_sentence: 올해 지원 대상에 선정된 42개사는 사업화 자금부터 사업화 촉진 진단, 민간투자 유치 등 기업 규모를 키울 수 있는
30
+ 각종 지원을 최대 15개월까지 받을 수 있다.
31
+ sentences:
32
+ - 체크인 아웃 할 때 소통이나 협조도도 매우 좋습니다
33
+ - 작년 용평 지역 강설량은?
34
+ - 긴급 사태가 선언된 7개 도부현의 지사는 법적인 근거 아래 외출자제와 휴교 등을 요청할 수 있다.
35
+ - source_sentence: 언제 할머니 칠순 잔치가 잡혀 있나요, 이번달입니까 다음달입니까?
36
+ sentences:
37
+ - 그리고 세탁세제와 식용유가 없으니 준비 하세요
38
+ - 삼월에 태어난 친구 이름이 어떻게 됩니까?
39
+ - 비 올 때는 다른 신발 말고 장화를 신었으면 합니다.
40
+ - source_sentence: 한메일 서비스를 사용할 수 있는 기한이 언제일까요?
41
+ sentences:
42
+ - 우리는 코로나19와의 투쟁에서 개발도상국들을 지원해야 할 필요성을 인정한다.
43
+ - 비 올 때는 높은지대에 텐트 치도록 해. 낮은 지대는 별로야.
44
+ - 한메일은 언제 서비스를 종료해?
45
+ - source_sentence: 오늘 제가 해야할 일이 무엇인가요!
46
+ sentences:
47
+ - 시내 중심에 위치한 깔끔하고 머무르기 좋은 숙소 입니다.
48
+ - 가게로 들어가는 문 바로 옆에 오른쪽으로 올라가는 입구가 있어요.
49
+ - 언제쯤 친구가 여행 갈 수 있겠니?
50
+ model-index:
51
+ - name: SentenceTransformer based on klue/roberta-base
52
+ results:
53
+ - task:
54
+ type: semantic-similarity
55
+ name: Semantic Similarity
56
+ dataset:
57
+ name: Unknown
58
+ type: unknown
59
+ metrics:
60
+ - type: pearson_cosine
61
+ value: 0.3477070578392738
62
+ name: Pearson Cosine
63
+ - type: spearman_cosine
64
+ value: 0.35560473197486514
65
+ name: Spearman Cosine
66
+ - type: pearson_manhattan
67
+ value: 0.36738467673522557
68
+ name: Pearson Manhattan
69
+ - type: spearman_manhattan
70
+ value: 0.36460670798564826
71
+ name: Spearman Manhattan
72
+ - type: pearson_euclidean
73
+ value: 0.36074511612166327
74
+ name: Pearson Euclidean
75
+ - type: spearman_euclidean
76
+ value: 0.35482778401649034
77
+ name: Spearman Euclidean
78
+ - type: pearson_dot
79
+ value: 0.21251170218646828
80
+ name: Pearson Dot
81
+ - type: spearman_dot
82
+ value: 0.20063256899469895
83
+ name: Spearman Dot
84
+ - type: pearson_max
85
+ value: 0.36738467673522557
86
+ name: Pearson Max
87
+ - type: spearman_max
88
+ value: 0.36460670798564826
89
+ name: Spearman Max
90
+ - type: pearson_cosine
91
+ value: 0.9611295434382598
92
+ name: Pearson Cosine
93
+ - type: spearman_cosine
94
+ value: 0.922281644313147
95
+ name: Spearman Cosine
96
+ - type: pearson_manhattan
97
+ value: 0.95182850390749
98
+ name: Pearson Manhattan
99
+ - type: spearman_manhattan
100
+ value: 0.9211213430736883
101
+ name: Spearman Manhattan
102
+ - type: pearson_euclidean
103
+ value: 0.9519510086799272
104
+ name: Pearson Euclidean
105
+ - type: spearman_euclidean
106
+ value: 0.9217056450919558
107
+ name: Spearman Euclidean
108
+ - type: pearson_dot
109
+ value: 0.9503136478175895
110
+ name: Pearson Dot
111
+ - type: spearman_dot
112
+ value: 0.9045157489205089
113
+ name: Spearman Dot
114
+ - type: pearson_max
115
+ value: 0.9611295434382598
116
+ name: Pearson Max
117
+ - type: spearman_max
118
+ value: 0.922281644313147
119
+ name: Spearman Max
120
+ ---
121
+
122
+ # SentenceTransformer based on klue/roberta-base
123
+
124
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [klue/roberta-base](https://huggingface.co/klue/roberta-base). 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.
125
+
126
+ ## Model Details
127
+
128
+ ### Model Description
129
+ - **Model Type:** Sentence Transformer
130
+ - **Base model:** [klue/roberta-base](https://huggingface.co/klue/roberta-base) <!-- at revision 02f94ba5e3fcb7e2a58a390b8639b0fac974a8da -->
131
+ - **Maximum Sequence Length:** 512 tokens
132
+ - **Output Dimensionality:** 768 tokens
133
+ - **Similarity Function:** Cosine Similarity
134
+ <!-- - **Training Dataset:** Unknown -->
135
+ <!-- - **Language:** Unknown -->
136
+ <!-- - **License:** Unknown -->
137
+
138
+ ### Model Sources
139
+
140
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
141
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
142
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
143
+
144
+ ### Full Model Architecture
145
+
146
+ ```
147
+ SentenceTransformer(
148
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
149
+ (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})
150
+ )
151
+ ```
152
+
153
+ ## Usage
154
+
155
+ ### Direct Usage (Sentence Transformers)
156
+
157
+ First install the Sentence Transformers library:
158
+
159
+ ```bash
160
+ pip install -U sentence-transformers
161
+ ```
162
+
163
+ Then you can load this model and run inference.
164
+ ```python
165
+ from sentence_transformers import SentenceTransformer
166
+
167
+ # Download from the 🤗 Hub
168
+ model = SentenceTransformer("sentence_transformers_model_id")
169
+ # Run inference
170
+ sentences = [
171
+ '오늘 제가 해야할 일이 무엇인가요!',
172
+ '언제쯤 친구가 여행 갈 수 있겠니?',
173
+ '시내 중심에 위치한 깔끔하고 머무르기 좋은 숙소 입니다.',
174
+ ]
175
+ embeddings = model.encode(sentences)
176
+ print(embeddings.shape)
177
+ # [3, 768]
178
+
179
+ # Get the similarity scores for the embeddings
180
+ similarities = model.similarity(embeddings, embeddings)
181
+ print(similarities.shape)
182
+ # [3, 3]
183
+ ```
184
+
185
+ <!--
186
+ ### Direct Usage (Transformers)
187
+
188
+ <details><summary>Click to see the direct usage in Transformers</summary>
189
+
190
+ </details>
191
+ -->
192
+
193
+ <!--
194
+ ### Downstream Usage (Sentence Transformers)
195
+
196
+ You can finetune this model on your own dataset.
197
+
198
+ <details><summary>Click to expand</summary>
199
+
200
+ </details>
201
+ -->
202
+
203
+ <!--
204
+ ### Out-of-Scope Use
205
+
206
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
207
+ -->
208
+
209
+ ## Evaluation
210
+
211
+ ### Metrics
212
+
213
+ #### Semantic Similarity
214
+
215
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
216
+
217
+ | Metric | Value |
218
+ |:-------------------|:-----------|
219
+ | pearson_cosine | 0.3477 |
220
+ | spearman_cosine | 0.3556 |
221
+ | pearson_manhattan | 0.3674 |
222
+ | spearman_manhattan | 0.3646 |
223
+ | pearson_euclidean | 0.3607 |
224
+ | spearman_euclidean | 0.3548 |
225
+ | pearson_dot | 0.2125 |
226
+ | spearman_dot | 0.2006 |
227
+ | pearson_max | 0.3674 |
228
+ | **spearman_max** | **0.3646** |
229
+
230
+ #### Semantic Similarity
231
+
232
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
233
+
234
+ | Metric | Value |
235
+ |:-------------------|:-----------|
236
+ | pearson_cosine | 0.9611 |
237
+ | spearman_cosine | 0.9223 |
238
+ | pearson_manhattan | 0.9518 |
239
+ | spearman_manhattan | 0.9211 |
240
+ | pearson_euclidean | 0.952 |
241
+ | spearman_euclidean | 0.9217 |
242
+ | pearson_dot | 0.9503 |
243
+ | spearman_dot | 0.9045 |
244
+ | pearson_max | 0.9611 |
245
+ | **spearman_max** | **0.9223** |
246
+
247
+ <!--
248
+ ## Bias, Risks and Limitations
249
+
250
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
251
+ -->
252
+
253
+ <!--
254
+ ### Recommendations
255
+
256
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
257
+ -->
258
+
259
+ ## Training Details
260
+
261
+ ### Training Dataset
262
+
263
+ #### Unnamed Dataset
264
+
265
+
266
+ * Size: 7,654 training samples
267
+ * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
268
+ * Approximate statistics based on the first 1000 samples:
269
+ | | sentence_0 | sentence_1 | label |
270
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
271
+ | type | string | string | float |
272
+ | details | <ul><li>min: 7 tokens</li><li>mean: 19.59 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.37 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.44</li><li>max: 1.0</li></ul> |
273
+ * Samples:
274
+ | sentence_0 | sentence_1 | label |
275
+ |:--------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|:------------------|
276
+ | <code>‘인공지능 반도체 산업 발전전략’의 차질 없는 이행 및 성과점검을 위해 정부와 산·학·연이 참여하는 ‘인공지능 반도체 산업 전략회의’를 구성·운영한다.</code> | <code>정부, 산업계, 학계, 연구기관이 참여하는 '인공지능 반도체산업전략회의'를 구성하여 '인공지능 반도체산업 발전전략'의 성과를 점검할 예정입니다.</code> | <code>0.6</code> |
277
+ | <code>예상했던대로 가성비 대비 최고의 위치였어요.</code> | <code>처음에 예상했던것보다 위치가 훨씬 좋았어요</code> | <code>0.54</code> |
278
+ | <code>올해 처음 개최되는 투자유치설명회는 전문투자기관에 홍보할 기회를 얻기 힘든 1인 미디어 스타트업들의 민간 투자유치를 지원할 목적으로 마련됐다.</code> | <code>이번 발사는 저궤도위성에 이어 정지궤도위성에서 실시간으로 환경 감시 업무를 수행하는 세계 최초의 위성으로 기록됐다.</code> | <code>0.04</code> |
279
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
280
+ ```json
281
+ {
282
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
283
+ }
284
+ ```
285
+
286
+ ### Training Hyperparameters
287
+ #### Non-Default Hyperparameters
288
+
289
+ - `eval_strategy`: steps
290
+ - `per_device_train_batch_size`: 16
291
+ - `per_device_eval_batch_size`: 16
292
+ - `num_train_epochs`: 4
293
+ - `multi_dataset_batch_sampler`: round_robin
294
+
295
+ #### All Hyperparameters
296
+ <details><summary>Click to expand</summary>
297
+
298
+ - `overwrite_output_dir`: False
299
+ - `do_predict`: False
300
+ - `eval_strategy`: steps
301
+ - `prediction_loss_only`: True
302
+ - `per_device_train_batch_size`: 16
303
+ - `per_device_eval_batch_size`: 16
304
+ - `per_gpu_train_batch_size`: None
305
+ - `per_gpu_eval_batch_size`: None
306
+ - `gradient_accumulation_steps`: 1
307
+ - `eval_accumulation_steps`: None
308
+ - `torch_empty_cache_steps`: None
309
+ - `learning_rate`: 5e-05
310
+ - `weight_decay`: 0.0
311
+ - `adam_beta1`: 0.9
312
+ - `adam_beta2`: 0.999
313
+ - `adam_epsilon`: 1e-08
314
+ - `max_grad_norm`: 1
315
+ - `num_train_epochs`: 4
316
+ - `max_steps`: -1
317
+ - `lr_scheduler_type`: linear
318
+ - `lr_scheduler_kwargs`: {}
319
+ - `warmup_ratio`: 0.0
320
+ - `warmup_steps`: 0
321
+ - `log_level`: passive
322
+ - `log_level_replica`: warning
323
+ - `log_on_each_node`: True
324
+ - `logging_nan_inf_filter`: True
325
+ - `save_safetensors`: True
326
+ - `save_on_each_node`: False
327
+ - `save_only_model`: False
328
+ - `restore_callback_states_from_checkpoint`: False
329
+ - `no_cuda`: False
330
+ - `use_cpu`: False
331
+ - `use_mps_device`: False
332
+ - `seed`: 42
333
+ - `data_seed`: None
334
+ - `jit_mode_eval`: False
335
+ - `use_ipex`: False
336
+ - `bf16`: False
337
+ - `fp16`: False
338
+ - `fp16_opt_level`: O1
339
+ - `half_precision_backend`: auto
340
+ - `bf16_full_eval`: False
341
+ - `fp16_full_eval`: False
342
+ - `tf32`: None
343
+ - `local_rank`: 0
344
+ - `ddp_backend`: None
345
+ - `tpu_num_cores`: None
346
+ - `tpu_metrics_debug`: False
347
+ - `debug`: []
348
+ - `dataloader_drop_last`: False
349
+ - `dataloader_num_workers`: 0
350
+ - `dataloader_prefetch_factor`: None
351
+ - `past_index`: -1
352
+ - `disable_tqdm`: False
353
+ - `remove_unused_columns`: True
354
+ - `label_names`: None
355
+ - `load_best_model_at_end`: False
356
+ - `ignore_data_skip`: False
357
+ - `fsdp`: []
358
+ - `fsdp_min_num_params`: 0
359
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
360
+ - `fsdp_transformer_layer_cls_to_wrap`: None
361
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
362
+ - `deepspeed`: None
363
+ - `label_smoothing_factor`: 0.0
364
+ - `optim`: adamw_torch
365
+ - `optim_args`: None
366
+ - `adafactor`: False
367
+ - `group_by_length`: False
368
+ - `length_column_name`: length
369
+ - `ddp_find_unused_parameters`: None
370
+ - `ddp_bucket_cap_mb`: None
371
+ - `ddp_broadcast_buffers`: False
372
+ - `dataloader_pin_memory`: True
373
+ - `dataloader_persistent_workers`: False
374
+ - `skip_memory_metrics`: True
375
+ - `use_legacy_prediction_loop`: False
376
+ - `push_to_hub`: False
377
+ - `resume_from_checkpoint`: None
378
+ - `hub_model_id`: None
379
+ - `hub_strategy`: every_save
380
+ - `hub_private_repo`: False
381
+ - `hub_always_push`: False
382
+ - `gradient_checkpointing`: False
383
+ - `gradient_checkpointing_kwargs`: None
384
+ - `include_inputs_for_metrics`: False
385
+ - `eval_do_concat_batches`: True
386
+ - `fp16_backend`: auto
387
+ - `push_to_hub_model_id`: None
388
+ - `push_to_hub_organization`: None
389
+ - `mp_parameters`:
390
+ - `auto_find_batch_size`: False
391
+ - `full_determinism`: False
392
+ - `torchdynamo`: None
393
+ - `ray_scope`: last
394
+ - `ddp_timeout`: 1800
395
+ - `torch_compile`: False
396
+ - `torch_compile_backend`: None
397
+ - `torch_compile_mode`: None
398
+ - `dispatch_batches`: None
399
+ - `split_batches`: None
400
+ - `include_tokens_per_second`: False
401
+ - `include_num_input_tokens_seen`: False
402
+ - `neftune_noise_alpha`: None
403
+ - `optim_target_modules`: None
404
+ - `batch_eval_metrics`: False
405
+ - `eval_on_start`: False
406
+ - `eval_use_gather_object`: False
407
+ - `batch_sampler`: batch_sampler
408
+ - `multi_dataset_batch_sampler`: round_robin
409
+
410
+ </details>
411
+
412
+ ### Training Logs
413
+ | Epoch | Step | Training Loss | spearman_max |
414
+ |:------:|:----:|:-------------:|:------------:|
415
+ | 0 | 0 | - | 0.3646 |
416
+ | 1.0 | 479 | - | 0.9133 |
417
+ | 1.0438 | 500 | 0.0281 | - |
418
+ | 2.0 | 958 | - | 0.9181 |
419
+ | 2.0877 | 1000 | 0.006 | 0.9217 |
420
+ | 3.0 | 1437 | - | 0.9191 |
421
+ | 3.1315 | 1500 | 0.0036 | - |
422
+ | 4.0 | 1916 | - | 0.9223 |
423
+
424
+
425
+ ### Framework Versions
426
+ - Python: 3.10.12
427
+ - Sentence Transformers: 3.1.1
428
+ - Transformers: 4.44.2
429
+ - PyTorch: 2.4.1+cu121
430
+ - Accelerate: 0.34.2
431
+ - Datasets: 3.0.1
432
+ - Tokenizers: 0.19.1
433
+
434
+ ## Citation
435
+
436
+ ### BibTeX
437
+
438
+ #### Sentence Transformers
439
+ ```bibtex
440
+ @inproceedings{reimers-2019-sentence-bert,
441
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
442
+ author = "Reimers, Nils and Gurevych, Iryna",
443
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
444
+ month = "11",
445
+ year = "2019",
446
+ publisher = "Association for Computational Linguistics",
447
+ url = "https://arxiv.org/abs/1908.10084",
448
+ }
449
+ ```
450
+
451
+ <!--
452
+ ## Glossary
453
+
454
+ *Clearly define terms in order to be accessible across audiences.*
455
+ -->
456
+
457
+ <!--
458
+ ## Model Card Authors
459
+
460
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
461
+ -->
462
+
463
+ <!--
464
+ ## Model Card Contact
465
+
466
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
467
+ -->
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/roberta-base",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "tokenizer_class": "BertTokenizer",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.44.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.1.1",
4
+ "transformers": "4.44.2",
5
+ "pytorch": "2.4.1+cu121"
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 sha256:9ebbcf49e98f8965195d9108b88388113dc20897396861e1a355f63372d6d020
3
+ size 442494816
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
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
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff