micky1625 commited on
Commit
7fa7815
·
verified ·
1 Parent(s): fcb2a84

Add new SentenceTransformer model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
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 +1,427 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:5
8
+ - loss:MultipleNegativesRankingLoss
9
+ base_model: BAAI/bge-m3
10
+ pipeline_tag: sentence-similarity
11
+ library_name: sentence-transformers
12
+ metrics:
13
+ - cosine_accuracy@1
14
+ - cosine_accuracy@3
15
+ - cosine_accuracy@5
16
+ - cosine_accuracy@10
17
+ - cosine_precision@1
18
+ - cosine_precision@3
19
+ - cosine_precision@5
20
+ - cosine_precision@10
21
+ - cosine_recall@1
22
+ - cosine_recall@3
23
+ - cosine_recall@5
24
+ - cosine_recall@10
25
+ - cosine_ndcg@10
26
+ - cosine_mrr@10
27
+ - cosine_map@100
28
+ model-index:
29
+ - name: SentenceTransformer based on BAAI/bge-m3
30
+ results:
31
+ - task:
32
+ type: information-retrieval
33
+ name: Information Retrieval
34
+ dataset:
35
+ name: Unknown
36
+ type: unknown
37
+ metrics:
38
+ - type: cosine_accuracy@1
39
+ value: 0.65
40
+ name: Cosine Accuracy@1
41
+ - type: cosine_accuracy@3
42
+ value: 0.8
43
+ name: Cosine Accuracy@3
44
+ - type: cosine_accuracy@5
45
+ value: 0.85
46
+ name: Cosine Accuracy@5
47
+ - type: cosine_accuracy@10
48
+ value: 0.9
49
+ name: Cosine Accuracy@10
50
+ - type: cosine_precision@1
51
+ value: 0.65
52
+ name: Cosine Precision@1
53
+ - type: cosine_precision@3
54
+ value: 0.2666666666666666
55
+ name: Cosine Precision@3
56
+ - type: cosine_precision@5
57
+ value: 0.17000000000000004
58
+ name: Cosine Precision@5
59
+ - type: cosine_precision@10
60
+ value: 0.09000000000000002
61
+ name: Cosine Precision@10
62
+ - type: cosine_recall@1
63
+ value: 0.65
64
+ name: Cosine Recall@1
65
+ - type: cosine_recall@3
66
+ value: 0.8
67
+ name: Cosine Recall@3
68
+ - type: cosine_recall@5
69
+ value: 0.85
70
+ name: Cosine Recall@5
71
+ - type: cosine_recall@10
72
+ value: 0.9
73
+ name: Cosine Recall@10
74
+ - type: cosine_ndcg@10
75
+ value: 0.7817924627528469
76
+ name: Cosine Ndcg@10
77
+ - type: cosine_mrr@10
78
+ value: 0.7433333333333333
79
+ name: Cosine Mrr@10
80
+ - type: cosine_map@100
81
+ value: 0.7483333333333333
82
+ name: Cosine Map@100
83
+ ---
84
+
85
+ # SentenceTransformer based on BAAI/bge-m3
86
+
87
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
88
+
89
+ ## Model Details
90
+
91
+ ### Model Description
92
+ - **Model Type:** Sentence Transformer
93
+ - **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
94
+ - **Maximum Sequence Length:** 8192 tokens
95
+ - **Output Dimensionality:** 1024 dimensions
96
+ - **Similarity Function:** Cosine Similarity
97
+ <!-- - **Training Dataset:** Unknown -->
98
+ <!-- - **Language:** Unknown -->
99
+ <!-- - **License:** Unknown -->
100
+
101
+ ### Model Sources
102
+
103
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
104
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
105
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
106
+
107
+ ### Full Model Architecture
108
+
109
+ ```
110
+ SentenceTransformer(
111
+ (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
112
+ (1): Pooling({'word_embedding_dimension': 1024, '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})
113
+ (2): Normalize()
114
+ )
115
+ ```
116
+
117
+ ## Usage
118
+
119
+ ### Direct Usage (Sentence Transformers)
120
+
121
+ First install the Sentence Transformers library:
122
+
123
+ ```bash
124
+ pip install -U sentence-transformers
125
+ ```
126
+
127
+ Then you can load this model and run inference.
128
+ ```python
129
+ from sentence_transformers import SentenceTransformer
130
+
131
+ # Download from the 🤗 Hub
132
+ model = SentenceTransformer("micky1625/finetuned2")
133
+ # Run inference
134
+ sentences = [
135
+ 'The weather is lovely today.',
136
+ "It's so sunny outside!",
137
+ 'He drove to the stadium.',
138
+ ]
139
+ embeddings = model.encode(sentences)
140
+ print(embeddings.shape)
141
+ # [3, 1024]
142
+
143
+ # Get the similarity scores for the embeddings
144
+ similarities = model.similarity(embeddings, embeddings)
145
+ print(similarities.shape)
146
+ # [3, 3]
147
+ ```
148
+
149
+ <!--
150
+ ### Direct Usage (Transformers)
151
+
152
+ <details><summary>Click to see the direct usage in Transformers</summary>
153
+
154
+ </details>
155
+ -->
156
+
157
+ <!--
158
+ ### Downstream Usage (Sentence Transformers)
159
+
160
+ You can finetune this model on your own dataset.
161
+
162
+ <details><summary>Click to expand</summary>
163
+
164
+ </details>
165
+ -->
166
+
167
+ <!--
168
+ ### Out-of-Scope Use
169
+
170
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
171
+ -->
172
+
173
+ ## Evaluation
174
+
175
+ ### Metrics
176
+
177
+ #### Information Retrieval
178
+
179
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
180
+
181
+ | Metric | Value |
182
+ |:--------------------|:-----------|
183
+ | cosine_accuracy@1 | 0.65 |
184
+ | cosine_accuracy@3 | 0.8 |
185
+ | cosine_accuracy@5 | 0.85 |
186
+ | cosine_accuracy@10 | 0.9 |
187
+ | cosine_precision@1 | 0.65 |
188
+ | cosine_precision@3 | 0.2667 |
189
+ | cosine_precision@5 | 0.17 |
190
+ | cosine_precision@10 | 0.09 |
191
+ | cosine_recall@1 | 0.65 |
192
+ | cosine_recall@3 | 0.8 |
193
+ | cosine_recall@5 | 0.85 |
194
+ | cosine_recall@10 | 0.9 |
195
+ | **cosine_ndcg@10** | **0.7818** |
196
+ | cosine_mrr@10 | 0.7433 |
197
+ | cosine_map@100 | 0.7483 |
198
+
199
+ <!--
200
+ ## Bias, Risks and Limitations
201
+
202
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
203
+ -->
204
+
205
+ <!--
206
+ ### Recommendations
207
+
208
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
209
+ -->
210
+
211
+ ## Training Details
212
+
213
+ ### Training Dataset
214
+
215
+ #### Unnamed Dataset
216
+
217
+ * Size: 5 training samples
218
+ * Columns: <code>sentence_0</code> and <code>sentence_1</code>
219
+ * Approximate statistics based on the first 5 samples:
220
+ | | sentence_0 | sentence_1 |
221
+ |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
222
+ | type | string | string |
223
+ | details | <ul><li>min: 16 tokens</li><li>mean: 37.4 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>min: 406 tokens</li><li>mean: 406.0 tokens</li><li>max: 406 tokens</li></ul> |
224
+ * Samples:
225
+ | sentence_0 | sentence_1 |
226
+ |:----------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
227
+ | <code>인체 수곡대사에 있어 액해(液海)의 탁재(濁滓)가 보익하는 장부에서 생성되는 것은?</code> | <code>[1-1] 천기(天機)에 넷이 있는데 첫째는 지방(地方)이고 둘째는 인륜(人倫)이고 셋째는 세회(世會)이<br>고 넷째는 천시(天時)이다.<br>[1-2] 인사(人事)에 넷이 있는데 첫째는 거처(居處)이고 둘째는 당여(黨與)이고 셋째는 교우(交遇)이<br>고 넷째는 사무(事務)이다.<br>[1-3] 귀로 천시를 들으며 눈으로 세회를 보며 코로 인륜을 냄새 맡고 입으로 지방을 맛본다.<br>[1-4] 천시는 지극히 탕(蕩)한 것이고 세회는 극히 큰 것이고 인륜은 극히 넓은 것이고 지방은 극히 <br>먼 것이다.<br>[1-5] 폐는 사무를 수행하며 비는 교우를 맺게 하며 간은 당여를 형성하며 신은 거처를 정한다.<br>[1-6] 사무는 잘 닦여져야 하고 교우는 잘 이루어져야 하고 당여는 잘 정돈되어야 하고, 거처는 잘 <br>다스려져야 한다.<br>[1-7] 턱에는 주책(籌策)이 있고 가슴에는 경륜(經綸)이 있고 배꼽에는 행검(行檢)이 있고 배에는 도<br>량(度量)이 있다.<br>[1-8] 주책은 교만하지 말아야 할 것이고 경륜은 뻐기지 말아야 할 것이고 행검은 함부로 하지 말아<br>야 할 것이고 도량은 과장하지 말아야 할 것이다.<br>[1-9] 머리에는 식견(識見)이 있고 어깨에는 위의(���儀)가 있고 허리에는 재간(材幹)이 있고 엉덩이<br>에는 방략(方略)이 있다.</code> |
228
+ | <code>소음인 여성이 병원에 왔다. 배가 아프고 설사를 하다가 며칠 후에 갑자기 의식을 잃고 넘어지며, 손발이 시리고 열이 나면서 땀이 났다. 치방은?</code> | <code>[1-1] 천기(天機)에 넷이 있는데 첫째는 지방(地方)이고 둘째는 인륜(人倫)이고 셋째는 세회(世會)이<br>고 넷째는 천시(天時)이다.<br>[1-2] 인사(人事)에 넷이 있는데 첫째는 거처(居處)이고 둘째는 당여(黨與)이고 셋째는 교우(交遇)이<br>고 넷째는 사무(事務)이다.<br>[1-3] 귀로 천시를 들으며 눈으로 세회를 보며 코로 인륜을 냄새 맡고 입으로 지방을 맛본다.<br>[1-4] 천시는 지극히 탕(蕩)한 것이고 세회는 극히 큰 것이고 인륜은 극히 넓은 것이고 지방은 극히 <br>먼 것이다.<br>[1-5] 폐는 사무를 수행하며 비는 교우를 맺게 하며 간은 당여를 형성하며 신은 거처를 정한다.<br>[1-6] 사무는 잘 닦여져야 하고 교우는 잘 이루어져야 하고 당여는 잘 정돈되어야 하고, 거처는 잘 <br>다스려져야 한다.<br>[1-7] 턱에는 주책(籌策)이 있고 가슴에는 경륜(經綸)이 있고 배꼽에는 행검(行檢)이 있고 배에는 도<br>량(度量)이 있다.<br>[1-8] 주책은 교만하지 말아야 할 것이고 경륜은 뻐기지 말아야 할 것이고 행검은 함부로 하지 말아<br>야 할 것이고 도량은 과장하지 말아야 할 것이다.<br>[1-9] 머리에는 식견(識見)이 있고 어깨에는 위의(威儀)가 있고 허리에는 재간(材幹)이 있고 엉덩이<br>에는 방략(方略)이 있다.</code> |
229
+ | <code>나아가려고만 하고 물러나려 하지 않는 체질은?</code> | <code>[1-1] 천기(天機)에 넷이 있는데 첫째는 지방(地方)이고 둘째는 인륜(人倫)이고 셋째는 세회(世會)이<br>고 넷째는 천시(天時)이다.<br>[1-2] 인사(人事)에 넷이 있는데 첫째는 거처(居處)이고 둘째는 당여(黨與)이고 셋째는 교우(交遇)이<br>고 넷째는 사무(事務)이다.<br>[1-3] 귀로 천시를 들으며 눈으로 세회를 보며 코로 인륜을 냄새 맡고 입으로 지방을 맛본다.<br>[1-4] 천시는 지극히 탕(蕩)한 것이고 세회는 극히 큰 것이고 인륜은 극히 넓은 것이고 지방은 극히 <br>먼 것이다.<br>[1-5] 폐는 사무를 수행하며 비는 교우를 맺게 하며 간은 당여를 형성하며 신은 거처를 정한다.<br>[1-6] 사무는 잘 닦여져야 하고 교우는 잘 이루어져야 하고 당여는 잘 정돈되어야 하고, 거처는 잘 <br>다스려져야 한다.<br>[1-7] 턱에는 주책(籌策)이 있고 가슴에는 경륜(經綸)이 있고 배꼽에는 행검(行檢)이 있고 배에는 도<br>량(度量)이 있다.<br>[1-8] 주책은 교만하지 말아야 할 것이고 경륜은 뻐기지 말아야 할 것이고 행검은 함부로 하지 말아<br>야 할 것이고 도량은 과장하지 말아야 할 것이다.<br>[1-9] 머리에는 식견(識見)이 있고 어깨에는 위의(威儀)가 있고 허리에는 재간(材幹)이 있고 엉덩이<br>에는 방략(方略)이 있다.</code> |
230
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
231
+ ```json
232
+ {
233
+ "scale": 20.0,
234
+ "similarity_fct": "cos_sim"
235
+ }
236
+ ```
237
+
238
+ ### Training Hyperparameters
239
+ #### Non-Default Hyperparameters
240
+
241
+ - `eval_strategy`: steps
242
+ - `per_device_train_batch_size`: 5
243
+ - `per_device_eval_batch_size`: 5
244
+ - `num_train_epochs`: 2
245
+ - `multi_dataset_batch_sampler`: round_robin
246
+
247
+ #### All Hyperparameters
248
+ <details><summary>Click to expand</summary>
249
+
250
+ - `overwrite_output_dir`: False
251
+ - `do_predict`: False
252
+ - `eval_strategy`: steps
253
+ - `prediction_loss_only`: True
254
+ - `per_device_train_batch_size`: 5
255
+ - `per_device_eval_batch_size`: 5
256
+ - `per_gpu_train_batch_size`: None
257
+ - `per_gpu_eval_batch_size`: None
258
+ - `gradient_accumulation_steps`: 1
259
+ - `eval_accumulation_steps`: None
260
+ - `torch_empty_cache_steps`: None
261
+ - `learning_rate`: 5e-05
262
+ - `weight_decay`: 0.0
263
+ - `adam_beta1`: 0.9
264
+ - `adam_beta2`: 0.999
265
+ - `adam_epsilon`: 1e-08
266
+ - `max_grad_norm`: 1
267
+ - `num_train_epochs`: 2
268
+ - `max_steps`: -1
269
+ - `lr_scheduler_type`: linear
270
+ - `lr_scheduler_kwargs`: {}
271
+ - `warmup_ratio`: 0.0
272
+ - `warmup_steps`: 0
273
+ - `log_level`: passive
274
+ - `log_level_replica`: warning
275
+ - `log_on_each_node`: True
276
+ - `logging_nan_inf_filter`: True
277
+ - `save_safetensors`: True
278
+ - `save_on_each_node`: False
279
+ - `save_only_model`: False
280
+ - `restore_callback_states_from_checkpoint`: False
281
+ - `no_cuda`: False
282
+ - `use_cpu`: False
283
+ - `use_mps_device`: False
284
+ - `seed`: 42
285
+ - `data_seed`: None
286
+ - `jit_mode_eval`: False
287
+ - `use_ipex`: False
288
+ - `bf16`: False
289
+ - `fp16`: False
290
+ - `fp16_opt_level`: O1
291
+ - `half_precision_backend`: auto
292
+ - `bf16_full_eval`: False
293
+ - `fp16_full_eval`: False
294
+ - `tf32`: None
295
+ - `local_rank`: 0
296
+ - `ddp_backend`: None
297
+ - `tpu_num_cores`: None
298
+ - `tpu_metrics_debug`: False
299
+ - `debug`: []
300
+ - `dataloader_drop_last`: False
301
+ - `dataloader_num_workers`: 0
302
+ - `dataloader_prefetch_factor`: None
303
+ - `past_index`: -1
304
+ - `disable_tqdm`: False
305
+ - `remove_unused_columns`: True
306
+ - `label_names`: None
307
+ - `load_best_model_at_end`: False
308
+ - `ignore_data_skip`: False
309
+ - `fsdp`: []
310
+ - `fsdp_min_num_params`: 0
311
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
312
+ - `tp_size`: 0
313
+ - `fsdp_transformer_layer_cls_to_wrap`: None
314
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
315
+ - `deepspeed`: None
316
+ - `label_smoothing_factor`: 0.0
317
+ - `optim`: adamw_torch
318
+ - `optim_args`: None
319
+ - `adafactor`: False
320
+ - `group_by_length`: False
321
+ - `length_column_name`: length
322
+ - `ddp_find_unused_parameters`: None
323
+ - `ddp_bucket_cap_mb`: None
324
+ - `ddp_broadcast_buffers`: False
325
+ - `dataloader_pin_memory`: True
326
+ - `dataloader_persistent_workers`: False
327
+ - `skip_memory_metrics`: True
328
+ - `use_legacy_prediction_loop`: False
329
+ - `push_to_hub`: False
330
+ - `resume_from_checkpoint`: None
331
+ - `hub_model_id`: None
332
+ - `hub_strategy`: every_save
333
+ - `hub_private_repo`: None
334
+ - `hub_always_push`: False
335
+ - `gradient_checkpointing`: False
336
+ - `gradient_checkpointing_kwargs`: None
337
+ - `include_inputs_for_metrics`: False
338
+ - `include_for_metrics`: []
339
+ - `eval_do_concat_batches`: True
340
+ - `fp16_backend`: auto
341
+ - `push_to_hub_model_id`: None
342
+ - `push_to_hub_organization`: None
343
+ - `mp_parameters`:
344
+ - `auto_find_batch_size`: False
345
+ - `full_determinism`: False
346
+ - `torchdynamo`: None
347
+ - `ray_scope`: last
348
+ - `ddp_timeout`: 1800
349
+ - `torch_compile`: False
350
+ - `torch_compile_backend`: None
351
+ - `torch_compile_mode`: None
352
+ - `include_tokens_per_second`: False
353
+ - `include_num_input_tokens_seen`: False
354
+ - `neftune_noise_alpha`: None
355
+ - `optim_target_modules`: None
356
+ - `batch_eval_metrics`: False
357
+ - `eval_on_start`: False
358
+ - `use_liger_kernel`: False
359
+ - `eval_use_gather_object`: False
360
+ - `average_tokens_across_devices`: False
361
+ - `prompts`: None
362
+ - `batch_sampler`: batch_sampler
363
+ - `multi_dataset_batch_sampler`: round_robin
364
+
365
+ </details>
366
+
367
+ ### Training Logs
368
+ | Epoch | Step | cosine_ndcg@10 |
369
+ |:-----:|:----:|:--------------:|
370
+ | 1.0 | 1 | 0.7818 |
371
+
372
+
373
+ ### Framework Versions
374
+ - Python: 3.11.12
375
+ - Sentence Transformers: 4.1.0
376
+ - Transformers: 4.51.3
377
+ - PyTorch: 2.6.0+cu124
378
+ - Accelerate: 1.5.2
379
+ - Datasets: 3.5.0
380
+ - Tokenizers: 0.21.1
381
+
382
+ ## Citation
383
+
384
+ ### BibTeX
385
+
386
+ #### Sentence Transformers
387
+ ```bibtex
388
+ @inproceedings{reimers-2019-sentence-bert,
389
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
390
+ author = "Reimers, Nils and Gurevych, Iryna",
391
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
392
+ month = "11",
393
+ year = "2019",
394
+ publisher = "Association for Computational Linguistics",
395
+ url = "https://arxiv.org/abs/1908.10084",
396
+ }
397
+ ```
398
+
399
+ #### MultipleNegativesRankingLoss
400
+ ```bibtex
401
+ @misc{henderson2017efficient,
402
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
403
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
404
+ year={2017},
405
+ eprint={1705.00652},
406
+ archivePrefix={arXiv},
407
+ primaryClass={cs.CL}
408
+ }
409
+ ```
410
+
411
+ <!--
412
+ ## Glossary
413
+
414
+ *Clearly define terms in order to be accessible across audiences.*
415
+ -->
416
+
417
+ <!--
418
+ ## Model Card Authors
419
+
420
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
421
+ -->
422
+
423
+ <!--
424
+ ## Model Card Contact
425
+
426
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
427
+ -->
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 8194,
16
+ "model_type": "xlm-roberta",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.51.3",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 250002
27
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "4.1.0",
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 sha256:26184a92460a9913cdd11a16cdab549c28a424f54efcf6e5d299dc750a3bb639
3
+ size 2271064456
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
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": "</s>",
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
3
+ size 17083053
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
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": "</s>",
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
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "max_length": 8192,
51
+ "model_max_length": 8192,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "<pad>",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "</s>",
57
+ "sp_model_kwargs": {},
58
+ "stride": 0,
59
+ "tokenizer_class": "XLMRobertaTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "<unk>"
63
+ }