Hugging Face's logo

Detomo
/
cl-nagoya-sup-simcse-ja-nss-v_1_0_7_10

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:210384
loss:CategoricalContrastiveLoss
Model card Files
xet
Community
dtm-hoinv commited on
Commit
c78f214
·
verified ·
1 Parent(s): b1de54c

Add new SentenceTransformer model

Browse files
Files changed (10) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +416 -0
  3. config.json +24 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +37 -0
  9. tokenizer_config.json +64 -0
  10. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
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 +1,416 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:210384
8
+ - loss:CategoricalContrastiveLoss
9
+ widget:
10
+ - source_sentence: 科目：コンクリート。名称：基礎部ｺﾝｸﾘｰﾄ打設手間。
11
+ sentences:
12
+ - 科目：コンクリート。名称：ｺﾝｸﾘｰﾄ打設手間･ﾎﾟﾝﾌﾟ圧送。
13
+ - 科目：コンクリート。名称：普通ｺﾝｸﾘｰﾄ。摘要：FC=24 S15粗骨材基礎部。備考：代価表 0059。
14
+ - 科目：コンクリート。名称：基礎部ｺﾝｸﾘｰﾄ。摘要：FC36N/mm2 ｽﾗﾝﾌﾟ18高性能AE減水剤。備考：代価表 0032。
15
+ - source_sentence: 科目：コンクリート。名称：均しｺﾝｸﾘｰﾄ。
16
+ sentences:
17
+ - 科目：コンクリート。名称：多目的ﾎｰﾙ機械式移動座席基礎ｺﾝｸﾘｰﾄ。
18
+ - 科目：コンクリート。名称：普通ｺﾝｸﾘｰﾄ。摘要：JIS A5308 FC21 S15粗骨材20。備考：刊-ｺﾝ 2115嵩上げｺﾝ。
19
+ - 科目：コンクリート。名称：普通ｺﾝｸﾘｰﾄ。摘要：FC=24 S15粗骨材基礎部。備考：代価表 0064。
20
+ - source_sentence: 科目：コンクリート。名称：防振床浮き床ｺﾝｸﾘｰﾄ。
21
+ sentences:
22
+ - 科目：コンクリート。名称：設備基礎ｺﾝｸﾘｰﾄ。摘要：FC21N/mm2 ｽﾗﾝﾌﾟ18。備考：代価表 0036。
23
+ - 科目：コンクリート。名称：免震上部ｺﾝｸﾘｰﾄ。摘要：FC30 S15高性能AE減水剤。備考：代価表 0106。
24
+ - 科目：コンクリート。名称：多目的ﾎｰﾙ間柱基礎ｺﾝｸﾘｰﾄ。摘要：FC21N/mm2 ｽﾗﾝﾌﾟ18。備考：代価表 0041。
25
+ - source_sentence: 科目：コンクリート。名称：EXP_J充填ｺﾝｸﾘｰﾄ。
26
+ sentences:
27
+ - 科目：コンクリート。名称：土間ｺﾝｸﾘｰﾄ。
28
+ - 科目：コンクリート。名称：基礎部ｽﾛｰﾌﾟｺﾝｸﾘｰﾄ。摘要：FC24N/mm2 ｽﾗﾝﾌﾟ15。備考：代価表 0048。
29
+ - 科目：コンクリート。名称：擁壁部ｺﾝｸﾘｰﾄ。摘要：FC36 S15粗骨材20 高性能AE減水剤躯体防水材 ﾍﾞｽﾄﾝA同等品以上。備考：代価表 0105。
30
+ - source_sentence: 科目：コンクリート。名称：浮き床ｺﾝｸﾘｰﾄ。
31
+ sentences:
32
+ - 科目：コンクリート。名称：ｵｲﾙﾀﾝｸ基礎ｺﾝｸﾘｰﾄ。摘要：FC24 S18粗骨材20 高性能AE減水剤。備考：代価表 0108。
33
+ - 科目：コンクリート。名称：ｺﾝｸﾘｰﾄ（個別）。摘要：Ｆ0＝18N/mm2 Ｓ＝１８ 徳島１。備考：B1-111111 H2906BD 個別嵩上げｺﾝｸﾘｰﾄ。
34
+ - 科目：コンクリート。名称：普通ｺﾝｸﾘｰﾄ。摘要：FC=24 S15粗骨材基礎部。備考：代価表 0054。
35
+ pipeline_tag: sentence-similarity
36
+ library_name: sentence-transformers
37
+ ---
38
+
39
+ # SentenceTransformer
40
+
41
+ This is a [sentence-transformers](https://www.SBERT.net) model trained. 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.
42
+
43
+ ## Model Details
44
+
45
+ ### Model Description
46
+ - **Model Type:** Sentence Transformer
47
+ <!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
48
+ - **Maximum Sequence Length:** 512 tokens
49
+ - **Output Dimensionality:** 768 dimensions
50
+ - **Similarity Function:** Cosine Similarity
51
+ <!-- - **Training Dataset:** Unknown -->
52
+ <!-- - **Language:** Unknown -->
53
+ <!-- - **License:** Unknown -->
54
+
55
+ ### Model Sources
56
+
57
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
58
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
59
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
60
+
61
+ ### Full Model Architecture
62
+
63
+ ```
64
+ SentenceTransformer(
65
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
66
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
67
+ )
68
+ ```
69
+
70
+ ## Usage
71
+
72
+ ### Direct Usage (Sentence Transformers)
73
+
74
+ First install the Sentence Transformers library:
75
+
76
+ ```bash
77
+ pip install -U sentence-transformers
78
+ ```
79
+
80
+ Then you can load this model and run inference.
81
+ ```python
82
+ from sentence_transformers import SentenceTransformer
83
+
84
+ # Download from the 🤗 Hub
85
+ model = SentenceTransformer("Detomo/cl-nagoya-sup-simcse-ja-nss-v_1_0_7_10")
86
+ # Run inference
87
+ sentences = [
88
+ '科目：コンクリート。名称：浮き床ｺﾝｸﾘｰﾄ。',
89
+ '科目：コンクリート。名称：ｵｲﾙﾀﾝｸ基礎ｺﾝｸﾘｰﾄ。摘要：FC24 S18粗��材20 高性能AE減水剤。備考：代価表 0108。',
90
+ '科目：コンクリート。名称：普通ｺﾝｸﾘｰﾄ。摘要：FC=24 S15粗骨材基礎部。備考：代価表 0054。',
91
+ ]
92
+ embeddings = model.encode(sentences)
93
+ print(embeddings.shape)
94
+ # [3, 768]
95
+
96
+ # Get the similarity scores for the embeddings
97
+ similarities = model.similarity(embeddings, embeddings)
98
+ print(similarities.shape)
99
+ # [3, 3]
100
+ ```
101
+
102
+ <!--
103
+ ### Direct Usage (Transformers)
104
+
105
+ <details><summary>Click to see the direct usage in Transformers</summary>
106
+
107
+ </details>
108
+ -->
109
+
110
+ <!--
111
+ ### Downstream Usage (Sentence Transformers)
112
+
113
+ You can finetune this model on your own dataset.
114
+
115
+ <details><summary>Click to expand</summary>
116
+
117
+ </details>
118
+ -->
119
+
120
+ <!--
121
+ ### Out-of-Scope Use
122
+
123
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
124
+ -->
125
+
126
+ <!--
127
+ ## Bias, Risks and Limitations
128
+
129
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
130
+ -->
131
+
132
+ <!--
133
+ ### Recommendations
134
+
135
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
136
+ -->
137
+
138
+ ## Training Details
139
+
140
+ ### Training Dataset
141
+
142
+ #### Unnamed Dataset
143
+
144
+ * Size: 210,384 training samples
145
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
146
+ * Approximate statistics based on the first 1000 samples:
147
+ | | sentence1 | sentence2 | label |
148
+ |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------|
149
+ | type | string | string | int |
150
+ | details | <ul><li>min: 11 tokens</li><li>mean: 13.73 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 35.89 tokens</li><li>max: 72 tokens</li></ul> | <ul><li>0: ~71.40%</li><li>1: ~2.90%</li><li>2: ~25.70%</li></ul> |
151
+ * Samples:
152
+ | sentence1 | sentence2 | label |
153
+ |:-----------------------------------------|:---------------------------------------------------------------------------------------------------|:---------------|
154
+ | <code>科目：コンクリート。名称：ｺﾝｸﾘｰﾄﾎﾟﾝﾌﾟ圧送。</code> | <code>科目：コンクリート。名称：ﾎﾟﾝﾌﾟ圧送。</code> | <code>1</code> |
155
+ | <code>科目：コンクリート。名称：ｺﾝｸﾘｰﾄﾎﾟﾝﾌﾟ圧送。</code> | <code>科目：コンクリート。名称：ｺﾝｸﾘｰﾄﾎﾟﾝﾌﾟ圧送。摘要：100m3/回以上基本料金別途加算。備考：B0-434226 No.1 市場免震層下部ｺﾝ。</code> | <code>2</code> |
156
+ | <code>科目：コンクリート。名称：ｺﾝｸﾘｰﾄﾎﾟﾝﾌﾟ圧送。</code> | <code>科目：コンクリート。名称：ｺﾝｸﾘｰﾄﾎﾟﾝﾌﾟ圧送。摘要：100m3/回以上基本料金別途加算。備考：B0-434226 No.1 市場湧水ﾏｯﾄ保護ｺﾝ。</code> | <code>2</code> |
157
+ * Loss: <code>sentence_transformer_lib.categorical_constrastive_loss.CategoricalContrastiveLoss</code>
158
+
159
+ ### Training Hyperparameters
160
+ #### Non-Default Hyperparameters
161
+
162
+ - `per_device_train_batch_size`: 256
163
+ - `per_device_eval_batch_size`: 256
164
+ - `learning_rate`: 1e-05
165
+ - `weight_decay`: 0.01
166
+ - `num_train_epochs`: 10
167
+ - `warmup_ratio`: 0.2
168
+ - `fp16`: True
169
+
170
+ #### All Hyperparameters
171
+ <details><summary>Click to expand</summary>
172
+
173
+ - `overwrite_output_dir`: False
174
+ - `do_predict`: False
175
+ - `eval_strategy`: no
176
+ - `prediction_loss_only`: True
177
+ - `per_device_train_batch_size`: 256
178
+ - `per_device_eval_batch_size`: 256
179
+ - `per_gpu_train_batch_size`: None
180
+ - `per_gpu_eval_batch_size`: None
181
+ - `gradient_accumulation_steps`: 1
182
+ - `eval_accumulation_steps`: None
183
+ - `torch_empty_cache_steps`: None
184
+ - `learning_rate`: 1e-05
185
+ - `weight_decay`: 0.01
186
+ - `adam_beta1`: 0.9
187
+ - `adam_beta2`: 0.999
188
+ - `adam_epsilon`: 1e-08
189
+ - `max_grad_norm`: 1.0
190
+ - `num_train_epochs`: 10
191
+ - `max_steps`: -1
192
+ - `lr_scheduler_type`: linear
193
+ - `lr_scheduler_kwargs`: {}
194
+ - `warmup_ratio`: 0.2
195
+ - `warmup_steps`: 0
196
+ - `log_level`: passive
197
+ - `log_level_replica`: warning
198
+ - `log_on_each_node`: True
199
+ - `logging_nan_inf_filter`: True
200
+ - `save_safetensors`: True
201
+ - `save_on_each_node`: False
202
+ - `save_only_model`: False
203
+ - `restore_callback_states_from_checkpoint`: False
204
+ - `no_cuda`: False
205
+ - `use_cpu`: False
206
+ - `use_mps_device`: False
207
+ - `seed`: 42
208
+ - `data_seed`: None
209
+ - `jit_mode_eval`: False
210
+ - `use_ipex`: False
211
+ - `bf16`: False
212
+ - `fp16`: True
213
+ - `fp16_opt_level`: O1
214
+ - `half_precision_backend`: auto
215
+ - `bf16_full_eval`: False
216
+ - `fp16_full_eval`: False
217
+ - `tf32`: None
218
+ - `local_rank`: 0
219
+ - `ddp_backend`: None
220
+ - `tpu_num_cores`: None
221
+ - `tpu_metrics_debug`: False
222
+ - `debug`: []
223
+ - `dataloader_drop_last`: False
224
+ - `dataloader_num_workers`: 0
225
+ - `dataloader_prefetch_factor`: None
226
+ - `past_index`: -1
227
+ - `disable_tqdm`: False
228
+ - `remove_unused_columns`: True
229
+ - `label_names`: None
230
+ - `load_best_model_at_end`: False
231
+ - `ignore_data_skip`: False
232
+ - `fsdp`: []
233
+ - `fsdp_min_num_params`: 0
234
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
235
+ - `fsdp_transformer_layer_cls_to_wrap`: None
236
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
237
+ - `deepspeed`: None
238
+ - `label_smoothing_factor`: 0.0
239
+ - `optim`: adamw_torch
240
+ - `optim_args`: None
241
+ - `adafactor`: False
242
+ - `group_by_length`: False
243
+ - `length_column_name`: length
244
+ - `ddp_find_unused_parameters`: None
245
+ - `ddp_bucket_cap_mb`: None
246
+ - `ddp_broadcast_buffers`: False
247
+ - `dataloader_pin_memory`: True
248
+ - `dataloader_persistent_workers`: False
249
+ - `skip_memory_metrics`: True
250
+ - `use_legacy_prediction_loop`: False
251
+ - `push_to_hub`: False
252
+ - `resume_from_checkpoint`: None
253
+ - `hub_model_id`: None
254
+ - `hub_strategy`: every_save
255
+ - `hub_private_repo`: None
256
+ - `hub_always_push`: False
257
+ - `gradient_checkpointing`: False
258
+ - `gradient_checkpointing_kwargs`: None
259
+ - `include_inputs_for_metrics`: False
260
+ - `include_for_metrics`: []
261
+ - `eval_do_concat_batches`: True
262
+ - `fp16_backend`: auto
263
+ - `push_to_hub_model_id`: None
264
+ - `push_to_hub_organization`: None
265
+ - `mp_parameters`:
266
+ - `auto_find_batch_size`: False
267
+ - `full_determinism`: False
268
+ - `torchdynamo`: None
269
+ - `ray_scope`: last
270
+ - `ddp_timeout`: 1800
271
+ - `torch_compile`: False
272
+ - `torch_compile_backend`: None
273
+ - `torch_compile_mode`: None
274
+ - `include_tokens_per_second`: False
275
+ - `include_num_input_tokens_seen`: False
276
+ - `neftune_noise_alpha`: None
277
+ - `optim_target_modules`: None
278
+ - `batch_eval_metrics`: False
279
+ - `eval_on_start`: False
280
+ - `use_liger_kernel`: False
281
+ - `eval_use_gather_object`: False
282
+ - `average_tokens_across_devices`: False
283
+ - `prompts`: None
284
+ - `batch_sampler`: batch_sampler
285
+ - `multi_dataset_batch_sampler`: proportional
286
+
287
+ </details>
288
+
289
+ ### Training Logs
290
+ | Epoch | Step | Training Loss |
291
+ |:------:|:----:|:-------------:|
292
+ | 0.0608 | 50 | 0.3009 |
293
+ | 0.1217 | 100 | 0.1359 |
294
+ | 0.1825 | 150 | 0.095 |
295
+ | 0.2433 | 200 | 0.0808 |
296
+ | 0.3041 | 250 | 0.0724 |
297
+ | 0.3650 | 300 | 0.0757 |
298
+ | 0.4258 | 350 | 0.0608 |
299
+ | 0.4866 | 400 | 0.0607 |
300
+ | 0.5474 | 450 | 0.0549 |
301
+ | 0.6083 | 500 | 0.051 |
302
+ | 0.6691 | 550 | 0.0517 |
303
+ | 0.7299 | 600 | 0.0432 |
304
+ | 0.7908 | 650 | 0.0436 |
305
+ | 0.8516 | 700 | 0.0418 |
306
+ | 0.9124 | 750 | 0.04 |
307
+ | 0.9732 | 800 | 0.0391 |
308
+ | 1.0341 | 850 | 0.038 |
309
+ | 1.0949 | 900 | 0.0352 |
310
+ | 1.1557 | 950 | 0.0329 |
311
+ | 1.2165 | 1000 | 0.029 |
312
+ | 1.2774 | 1050 | 0.0283 |
313
+ | 1.3382 | 1100 | 0.03 |
314
+ | 1.3990 | 1150 | 0.029 |
315
+ | 1.4599 | 1200 | 0.0274 |
316
+ | 1.5207 | 1250 | 0.0261 |
317
+ | 1.5815 | 1300 | 0.0248 |
318
+ | 1.6423 | 1350 | 0.0267 |
319
+ | 1.7032 | 1400 | 0.0234 |
320
+ | 1.7640 | 1450 | 0.0218 |
321
+ | 1.8248 | 1500 | 0.0217 |
322
+ | 1.8856 | 1550 | 0.0195 |
323
+ | 1.9465 | 1600 | 0.022 |
324
+ | 2.0073 | 1650 | 0.0195 |
325
+ | 2.0681 | 1700 | 0.0165 |
326
+ | 2.1290 | 1750 | 0.0155 |
327
+ | 2.1898 | 1800 | 0.0156 |
328
+ | 2.2506 | 1850 | 0.0148 |
329
+ | 2.3114 | 1900 | 0.0135 |
330
+ | 2.3723 | 1950 | 0.0122 |
331
+ | 2.4331 | 2000 | 0.0145 |
332
+ | 2.4939 | 2050 | 0.0138 |
333
+ | 2.5547 | 2100 | 0.0133 |
334
+ | 2.6156 | 2150 | 0.0137 |
335
+ | 2.6764 | 2200 | 0.0118 |
336
+ | 2.7372 | 2250 | 0.0132 |
337
+ | 2.7981 | 2300 | 0.0132 |
338
+ | 2.8589 | 2350 | 0.0129 |
339
+ | 2.9197 | 2400 | 0.0109 |
340
+ | 2.9805 | 2450 | 0.0115 |
341
+ | 3.0414 | 2500 | 0.0083 |
342
+ | 3.1022 | 2550 | 0.0082 |
343
+ | 3.1630 | 2600 | 0.0096 |
344
+ | 3.2238 | 2650 | 0.0081 |
345
+ | 3.2847 | 2700 | 0.0081 |
346
+ | 3.3455 | 2750 | 0.0083 |
347
+ | 3.4063 | 2800 | 0.01 |
348
+ | 3.4672 | 2850 | 0.0077 |
349
+ | 3.5280 | 2900 | 0.0081 |
350
+ | 3.5888 | 2950 | 0.0088 |
351
+ | 3.6496 | 3000 | 0.0088 |
352
+ | 3.7105 | 3050 | 0.0079 |
353
+ | 3.7713 | 3100 | 0.0075 |
354
+ | 3.8321 | 3150 | 0.0079 |
355
+ | 3.8929 | 3200 | 0.0066 |
356
+ | 3.9538 | 3250 | 0.0081 |
357
+ | 4.0146 | 3300 | 0.0062 |
358
+ | 4.0754 | 3350 | 0.0058 |
359
+ | 4.1363 | 3400 | 0.0055 |
360
+ | 4.1971 | 3450 | 0.0061 |
361
+ | 4.2579 | 3500 | 0.006 |
362
+ | 4.3187 | 3550 | 0.0057 |
363
+ | 4.3796 | 3600 | 0.0057 |
364
+ | 4.4404 | 3650 | 0.0061 |
365
+ | 4.5012 | 3700 | 0.0056 |
366
+ | 4.5620 | 3750 | 0.005 |
367
+ | 4.6229 | 3800 | 0.005 |
368
+ | 4.6837 | 3850 | 0.0054 |
369
+ | 4.7445 | 3900 | 0.0045 |
370
+ | 4.8054 | 3950 | 0.0062 |
371
+ | 4.8662 | 4000 | 0.0052 |
372
+
373
+
374
+ ### Framework Versions
375
+ - Python: 3.11.12
376
+ - Sentence Transformers: 4.1.0
377
+ - Transformers: 4.52.2
378
+ - PyTorch: 2.6.0+cu124
379
+ - Accelerate: 1.7.0
380
+ - Datasets: 2.14.4
381
+ - Tokenizers: 0.21.1
382
+
383
+ ## Citation
384
+
385
+ ### BibTeX
386
+
387
+ #### Sentence Transformers
388
+ ```bibtex
389
+ @inproceedings{reimers-2019-sentence-bert,
390
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
391
+ author = "Reimers, Nils and Gurevych, Iryna",
392
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
393
+ month = "11",
394
+ year = "2019",
395
+ publisher = "Association for Computational Linguistics",
396
+ url = "https://arxiv.org/abs/1908.10084",
397
+ }
398
+ ```
399
+
400
+ <!--
401
+ ## Glossary
402
+
403
+ *Clearly define terms in order to be accessible across audiences.*
404
+ -->
405
+
406
+ <!--
407
+ ## Model Card Authors
408
+
409
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
410
+ -->
411
+
412
+ <!--
413
+ ## Model Card Contact
414
+
415
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
416
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.52.2",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 32768
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "4.1.0",
4
+ "transformers": "4.52.2",
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:e56a51446c139bff5bb450bc708b1516c9e6d6d6993eead0bd96580d4ea83340
3
+ size 444851048
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_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": false,
47
+ "do_subword_tokenize": true,
48
+ "do_word_tokenize": true,
49
+ "extra_special_tokens": {},
50
+ "jumanpp_kwargs": null,
51
+ "mask_token": "[MASK]",
52
+ "mecab_kwargs": {
53
+ "mecab_dic": "unidic_lite"
54
+ },
55
+ "model_max_length": 512,
56
+ "never_split": null,
57
+ "pad_token": "[PAD]",
58
+ "sep_token": "[SEP]",
59
+ "subword_tokenizer_type": "wordpiece",
60
+ "sudachi_kwargs": null,
61
+ "tokenizer_class": "BertJapaneseTokenizer",
62
+ "unk_token": "[UNK]",
63
+ "word_tokenizer_type": "mecab"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff