bhavibhatt commited on
Commit
3b53e2f
·
verified ·
1 Parent(s): 61e1b74

Upload 10 files

Browse files
README.md ADDED
@@ -0,0 +1,457 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:92
9
+ - loss:ContrastiveLoss
10
+ base_model: nlpaueb/legal-bert-base-uncased
11
+ widget:
12
+ - source_sentence: Party B may terminate this Agreement for convenience.
13
+ sentences:
14
+ - Company at its sole discretion may at any time alter or cease providing the Customer
15
+ Service which it has agreed to provide to Client relating to Client Website pursuant
16
+ to this Agreement without any liability to Company.
17
+ - Except for claims arising out of Articles 4.3 and 7.0, or as may be set forth
18
+ in a SOW, neither Party will be liable for any consequential damages, lost profits,
19
+ lost savings, loss of anticipated revenue, or any exemplary, punitive, special
20
+ or indirect damages, even if advised of their possibility.
21
+ - This Agreement may only be terminated by mutual written agreement of both Parties,
22
+ with each party providing thirty (30) days' prior written notice to the other,
23
+ or upon material breach by either party, provided that the breaching party fails
24
+ to cure such breach within thirty (30) days of receiving written notice of the
25
+ breach.
26
+ - source_sentence: Party A shall not compete with Party B.
27
+ sentences:
28
+ - Party A's liability for any and all claims arising under this Agreement, including
29
+ claims under Section 10 or failures to pay under Section 6, shall in no event
30
+ exceed the total fees actually paid by Boxlot to The Globe hereunder during the
31
+ twelve (12) month period preceding the claim.
32
+ - Regardless of the term, Licensee can terminate Agreement with at least one hundred
33
+ eighty (180) days written notice with no further obligation.
34
+ - Throughout the Term, XSPA shall have the explicit right to sell, offer for sale,
35
+ market, or promote any digital meditation or digital sleep products (other than
36
+ the Products) exclusively through online channels in the Territory without Calm's
37
+ consent. Additionally, Calm shall be permitted to sell digital meditation or digital
38
+ sleep products in airport retail locations solely within the metropolitan area
39
+ of City A for a limited period of three (3) months following termination of this
40
+ Agreement, without XSPA's collaboration or prior written consent.
41
+ - source_sentence: Party B may terminate this Agreement for convenience.
42
+ sentences:
43
+ - EXCEPT FOR [**EXCLUDED DAMAGES**], IN NO EVENT SHALL PARTY A'S TOTAL LIABILITY
44
+ TO PARTY B UNDER OR IN CONNECTION WITH THIS AGREEMENT EXCEED THE TOTAL FEES PAID
45
+ BY PARTY B TO PARTY A UNDER THIS AGREEMENT IN THE 12 MONTH PERIOD PRECEDING THE
46
+ CLAIM.
47
+ - Party A's liability for breach of this Agreement, including but not limited to
48
+ Channel Partner's payment obligations, liability for early termination fees or
49
+ charges, breaches of confidentiality by either party, misappropriation of intellectual
50
+ property rights of the other party, and the parties' indemnification obligations
51
+ under this Agreement, is in all cases limited to the total fees paid or payable
52
+ under this Agreement during the 12 months preceding the event giving rise to such
53
+ liability.
54
+ - The term of this Agreement shall commence on the Effective Date and shall continue
55
+ indefinitely unless terminated (a) by mutual written agreement of both Parties,
56
+ with at least 30 days' prior notice to the other Party, or (b) by either Party
57
+ upon material breach by the other Party, provided that the breaching Party fails
58
+ to cure such breach within 30 days of receiving written notice specifying the
59
+ breach. In no event shall either Party terminate this Agreement for convenience
60
+ alone.
61
+ - source_sentence: Party B may terminate this Agreement for convenience.
62
+ sentences:
63
+ - Except as agreed by the Parties in writing or as otherwise stated in the Exhibits,
64
+ neither Party may terminate any Transition Service or Reverse Transition Service
65
+ for convenience. Termination of any Service shall only be permitted (i) upon mutual
66
+ written agreement of both Parties, effective upon 30 days' prior written notice,
67
+ or (ii) for material breach by the other Party following cure periods specified
68
+ herein. With respect to the Services described in Section G1 of Exhibit A, unless
69
+ otherwise indicated therein, those Services may not be terminated independently
70
+ except in accordance with an agreed Migration Plan. Any unamortized costs associated
71
+ with Provider's purchase of any license or other costs incurred specifically for
72
+ the purpose of providing the Services hereunder will be passed through to the
73
+ Terminating Party.
74
+ - Following the Initial Term, either Party may terminate this Agreement without
75
+ cause upon written notice to the other Party of at least 3 months.
76
+ - The provisions of Section 9.1 and Section 9.2 shall fully apply to limit the Licensee's
77
+ indemnification obligations under Section 8.2, even in the case of the Licensee's
78
+ gross negligence or wilful misconduct, and such indemnification shall in all circumstances
79
+ be limited to the total fees paid by Licensee under this Agreement during the
80
+ twelve (12) months preceding the claim.
81
+ - source_sentence: Party A shall not compete with Party B.
82
+ sentences:
83
+ - '["NOTWITHSTANDING ANY OTHER PROVISION OF THIS AGREEMENT TO THE CONTRARY, EXCEPT
84
+ FOR DAMAGES OR CLAIMS ARISING OUT OF (I) A BREACH OF SECTION 13 OF THIS AGREEMENT,
85
+ (II) CUSTOMER LIABILITIES PURSUANT TO, AND SUBJECT TO THE LIMITATIONS SET FORTH
86
+ IN, SECTION 2.5(E), (III) A PARTY''S OR ITS PERSONNEL''S GROSS NEGLIGENCE, FRAUD
87
+ OR WILLFUL MISCONDUCT, (IV) A PARTY''S WILLFUL BREACH OF THIS AGREEMENT, OR (V)
88
+ A PARTY''S INDEMNIFICATION OBLIGATION WITH RESPECT TO THIRD PARTY CLAIMS UNDER
89
+ SECTION 10.1 OR SECTION 10.2, IN NO EVENT SHALL EITHER PARTY BE LIABLE TO THE
90
+ OTHER PARTY OR ANY INDEMNIFIED PARTY HEREUNDER FOR ANY CONSEQUENTIAL DAMAGES,
91
+ SPECIAL DAMAGES, INCIDENTAL OR INDIRECT DAMAGES, LOSS OF REVENUE OR PROFITS, DIMINUTION
92
+ IN VALUE, DAMAGES BASED ON MULTIPLE OF REVENUE OR EARNINGS OR OTHER PERFORMANCE
93
+ METRIC, LOSS OF BUSINESS REPUTATION, PUNITIVE AND EXEMPLARY DAMAGES OR ANY SIMILAR
94
+ DAMAGES ARISING OR RESULTING FROM OR RELATING TO THIS AGREEMENT, WHETHER SUCH
95
+ ACTION IS BASED ON WARRANTY, CONTRACT, TORT (INCLUDING NEGLIGENCE OR STRICT LIABILITY)
96
+ OR OTHERWISE.", ''Except in the event of (i) Third Party Claims subject to a Party\''s
97
+ indemnification obligations pursuant to Section 10.1, (ii) Third Party Claims
98
+ subject to a Party\''s indemnification obligations pursuant to Section 10.2, (iii)
99
+ the gross negligence, fraud or willful misconduct of a Party or its Personnel,
100
+ (iv) a Party\''s willful breach of this Agreement, (v) a breach of Section 13
101
+ or (vi) customer liabilities pursuant to, and subject to the limitations set forth
102
+ in, Section 2.5(e), neither Party\''s aggregate liability to the other Party (or
103
+ its Personnel that are indemnitees under Section 10.1 or Section 10.2, as applicable)
104
+ under this Agreement for the initial twelve (12) month period immediately following
105
+ the Effective Date, and for any twelve (12) month period thereafter during the
106
+ Term, shall exceed, on a cumulative basis, the amount that is one and one half
107
+ (11∕2) times the aggregate amounts paid or payable pursuant to this Agreement
108
+ in the preceding twelve (12) month period preceding the loss date by Customer
109
+ to Manufacturer but solely with respect to the supply hereunder of Product (or
110
+ Products) for which such corresponding liability arose (the "Affected Products")
111
+ and not any other Products (or if, as of the time the liability arises, this Agreement
112
+ has not been in effect for twelve (12) months, then the amounts paid or payable
113
+ by Customer to Manufacturer hereunder during the period from the Effective Date
114
+ until such time the liability arises, shall be annualized to a full twelve (12)
115
+ months but solely with respect to the supply hereunder of the Affected Product(s)
116
+ and not any other Products).'']'
117
+ - '["EXCEPT FOR LIABILITY ARISING FROM BREACHES OF A PARTY''S CONFIDENTIALITY OBLIGATIONS
118
+ CONTAINED IN THE NON-DISCLOSURE CLAUSE IN SECTION 12.17 OF THE CHINA JV OPERATING
119
+ AGREEMENT, BREACHES OF LICENSE GRANTS CONTAINED HEREIN, AND EXCEPT FOR AMOUNTS
120
+ PAYABLE TO THIRD PARTIES TO FULFILL INDEMNITY OBLIGATIONS DESCRIBED IN ARTICLE
121
+ 8, (A) IN NO EVENT SHALL ANY PARTY HAVE ANY LIABILITY TO THE OTHERS, OR TO ANY
122
+ PARTY CLAIMING THROUGH OR UNDER THE OTHER, FOR ANY LOST PROFITS, ANY INDIRECT,
123
+ INCIDENTAL, SPECIAL OR CONSEQUENTIAL DAMAGES OF ANY KIND IN ANY WAY ARISING OUT
124
+ OF OR RELATED TO THIS AGREEMENT, HOWEVER CAUSED AND UNDER ANY THEORY OF LIABILITY,
125
+ EVEN IF SUCH PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES; AND (B)
126
+ IN NO EVENT SHALL A PARTY''S CUMULATIVE LIABILITY ARISING OUT OF THIS AGREEMENT
127
+ EXCEED THE AMOUNTS ACTUALLY PAID, PAYABLE, RECEIVED OR RECEIVABLE BY SUCH PARTY
128
+ FOR THE PRODUCTS CONCERNED THEREWITH HEREUNDER PURSUANT TO THIS AGREEMENT DURING
129
+ THE TWELVE (12) MONTHS PRIOR TO THE OCCURRENCE OF THE INITIAL EVENT FOR WHICH
130
+ A PARTY RECOVERS DAMAGES HEREUNDER."]'
131
+ - The Distributor shall not act as the agent or the buying agent, for any person,
132
+ for any goods which are competitive with the Product, **except within the geographic
133
+ area of City Y and for a period not exceeding two years from the effective date
134
+ of this Agreement.**
135
+ pipeline_tag: sentence-similarity
136
+ library_name: sentence-transformers
137
+ ---
138
+
139
+ # SentenceTransformer based on nlpaueb/legal-bert-base-uncased
140
+
141
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nlpaueb/legal-bert-base-uncased](https://huggingface.co/nlpaueb/legal-bert-base-uncased). 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.
142
+
143
+ ## Model Details
144
+
145
+ ### Model Description
146
+ - **Model Type:** Sentence Transformer
147
+ - **Base model:** [nlpaueb/legal-bert-base-uncased](https://huggingface.co/nlpaueb/legal-bert-base-uncased) <!-- at revision 15b570cbf88259610b082a167dacc190124f60f6 -->
148
+ - **Maximum Sequence Length:** 512 tokens
149
+ - **Output Dimensionality:** 768 dimensions
150
+ - **Similarity Function:** Cosine Similarity
151
+ <!-- - **Training Dataset:** Unknown -->
152
+ <!-- - **Language:** Unknown -->
153
+ <!-- - **License:** Unknown -->
154
+
155
+ ### Model Sources
156
+
157
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
158
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
159
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
160
+
161
+ ### Full Model Architecture
162
+
163
+ ```
164
+ SentenceTransformer(
165
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
166
+ (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})
167
+ )
168
+ ```
169
+
170
+ ## Usage
171
+
172
+ ### Direct Usage (Sentence Transformers)
173
+
174
+ First install the Sentence Transformers library:
175
+
176
+ ```bash
177
+ pip install -U sentence-transformers
178
+ ```
179
+
180
+ Then you can load this model and run inference.
181
+ ```python
182
+ from sentence_transformers import SentenceTransformer
183
+
184
+ # Download from the 🤗 Hub
185
+ model = SentenceTransformer("sentence_transformers_model_id")
186
+ # Run inference
187
+ sentences = [
188
+ 'Party A shall not compete with Party B.',
189
+ 'The Distributor shall not act as the agent or the buying agent, for any person, for any goods which are competitive with the Product, **except within the geographic area of City Y and for a period not exceeding two years from the effective date of this Agreement.**',
190
+ '["EXCEPT FOR LIABILITY ARISING FROM BREACHES OF A PARTY\'S CONFIDENTIALITY OBLIGATIONS CONTAINED IN THE NON-DISCLOSURE CLAUSE IN SECTION 12.17 OF THE CHINA JV OPERATING AGREEMENT, BREACHES OF LICENSE GRANTS CONTAINED HEREIN, AND EXCEPT FOR AMOUNTS PAYABLE TO THIRD PARTIES TO FULFILL INDEMNITY OBLIGATIONS DESCRIBED IN ARTICLE 8, (A) IN NO EVENT SHALL ANY PARTY HAVE ANY LIABILITY TO THE OTHERS, OR TO ANY PARTY CLAIMING THROUGH OR UNDER THE OTHER, FOR ANY LOST PROFITS, ANY INDIRECT, INCIDENTAL, SPECIAL OR CONSEQUENTIAL DAMAGES OF ANY KIND IN ANY WAY ARISING OUT OF OR RELATED TO THIS AGREEMENT, HOWEVER CAUSED AND UNDER ANY THEORY OF LIABILITY, EVEN IF SUCH PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES; AND (B) IN NO EVENT SHALL A PARTY\'S CUMULATIVE LIABILITY ARISING OUT OF THIS AGREEMENT EXCEED THE AMOUNTS ACTUALLY PAID, PAYABLE, RECEIVED OR RECEIVABLE BY SUCH PARTY FOR THE PRODUCTS CONCERNED THEREWITH HEREUNDER PURSUANT TO THIS AGREEMENT DURING THE TWELVE (12) MONTHS PRIOR TO THE OCCURRENCE OF THE INITIAL EVENT FOR WHICH A PARTY RECOVERS DAMAGES HEREUNDER."]',
191
+ ]
192
+ embeddings = model.encode(sentences)
193
+ print(embeddings.shape)
194
+ # [3, 768]
195
+
196
+ # Get the similarity scores for the embeddings
197
+ similarities = model.similarity(embeddings, embeddings)
198
+ print(similarities)
199
+ # tensor([[1.0000, 0.7770, 0.7303],
200
+ # [0.7770, 1.0000, 0.9041],
201
+ # [0.7303, 0.9041, 1.0000]])
202
+ ```
203
+
204
+ <!--
205
+ ### Direct Usage (Transformers)
206
+
207
+ <details><summary>Click to see the direct usage in Transformers</summary>
208
+
209
+ </details>
210
+ -->
211
+
212
+ <!--
213
+ ### Downstream Usage (Sentence Transformers)
214
+
215
+ You can finetune this model on your own dataset.
216
+
217
+ <details><summary>Click to expand</summary>
218
+
219
+ </details>
220
+ -->
221
+
222
+ <!--
223
+ ### Out-of-Scope Use
224
+
225
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
226
+ -->
227
+
228
+ <!--
229
+ ## Bias, Risks and Limitations
230
+
231
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
232
+ -->
233
+
234
+ <!--
235
+ ### Recommendations
236
+
237
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
238
+ -->
239
+
240
+ ## Training Details
241
+
242
+ ### Training Dataset
243
+
244
+ #### Unnamed Dataset
245
+
246
+ * Size: 92 training samples
247
+ * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
248
+ * Approximate statistics based on the first 92 samples:
249
+ | | sentence_0 | sentence_1 | label |
250
+ |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------|
251
+ | type | string | string | float |
252
+ | details | <ul><li>min: 11 tokens</li><li>mean: 13.09 tokens</li><li>max: 17 tokens</li></ul> | <ul><li>min: 22 tokens</li><li>mean: 99.57 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> |
253
+ * Samples:
254
+ | sentence_0 | sentence_1 | label |
255
+ |:---------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
256
+ | <code>Party A's liability for breach of this Agreement is uncapped.</code> | <code>["NOTWITHSTANDING ANY OTHER PROVISION OF THIS AGREEMENT TO THE CONTRARY, EXCEPT FOR DAMAGES OR CLAIMS ARISING OUT OF (I) A BREACH OF SECTION 13 OF THIS AGREEMENT, (II) CUSTOMER LIABILITIES PURSUANT TO, AND SUBJECT TO THE LIMITATIONS SET FORTH IN, SECTION 2.5(E), (III) A PARTY'S OR ITS PERSONNEL'S GROSS NEGLIGENCE, FRAUD OR WILLFUL MISCONDUCT, (IV) A PARTY'S WILLFUL BREACH OF THIS AGREEMENT, OR (V) A PARTY'S INDEMNIFICATION OBLIGATION WITH RESPECT TO THIRD PARTY CLAIMS UNDER SECTION 10.1 OR SECTION 10.2, IN NO EVENT SHALL EITHER PARTY BE LIABLE TO THE OTHER PARTY OR ANY INDEMNIFIED PARTY HEREUNDER FOR ANY CONSEQUENTIAL DAMAGES, SPECIAL DAMAGES, INCIDENTAL OR INDIRECT DAMAGES, LOSS OF REVENUE OR PROFITS, DIMINUTION IN VALUE, DAMAGES BASED ON MULTIPLE OF REVENUE OR EARNINGS OR OTHER PERFORMANCE METRIC, LOSS OF BUSINESS REPUTATION, PUNITIVE AND EXEMPLARY DAMAGES OR ANY SIMILAR DAMAGES ARISING OR RESULTING FROM OR RELATING TO THIS AGREEMENT, WHETHER SUCH ACTION IS BASED ON WARRANTY, CONTRAC...</code> | <code>1.0</code> |
257
+ | <code>Party B may terminate this Agreement for convenience.</code> | <code>Party B may terminate this Agreement only upon thirty (30) days’ prior written notice to Party A and with valid cause, or by mutual written agreement of both parties. In all events, any termination shall be no earlier than six (6) months after the Effective Date of this Agreement.</code> | <code>0.0</code> |
258
+ | <code>Party B may terminate this Agreement for convenience.</code> | <code>["Either Party may terminate this Agreement by giving the other Party thirty (30) days' prior written notice."]</code> | <code>1.0</code> |
259
+ * Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
260
+ ```json
261
+ {
262
+ "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
263
+ "margin": 0.5,
264
+ "size_average": true
265
+ }
266
+ ```
267
+
268
+ ### Training Hyperparameters
269
+ #### Non-Default Hyperparameters
270
+
271
+ - `per_device_train_batch_size`: 16
272
+ - `per_device_eval_batch_size`: 16
273
+ - `num_train_epochs`: 4
274
+ - `multi_dataset_batch_sampler`: round_robin
275
+
276
+ #### All Hyperparameters
277
+ <details><summary>Click to expand</summary>
278
+
279
+ - `overwrite_output_dir`: False
280
+ - `do_predict`: False
281
+ - `eval_strategy`: no
282
+ - `prediction_loss_only`: True
283
+ - `per_device_train_batch_size`: 16
284
+ - `per_device_eval_batch_size`: 16
285
+ - `per_gpu_train_batch_size`: None
286
+ - `per_gpu_eval_batch_size`: None
287
+ - `gradient_accumulation_steps`: 1
288
+ - `eval_accumulation_steps`: None
289
+ - `torch_empty_cache_steps`: None
290
+ - `learning_rate`: 5e-05
291
+ - `weight_decay`: 0.0
292
+ - `adam_beta1`: 0.9
293
+ - `adam_beta2`: 0.999
294
+ - `adam_epsilon`: 1e-08
295
+ - `max_grad_norm`: 1
296
+ - `num_train_epochs`: 4
297
+ - `max_steps`: -1
298
+ - `lr_scheduler_type`: linear
299
+ - `lr_scheduler_kwargs`: {}
300
+ - `warmup_ratio`: 0.0
301
+ - `warmup_steps`: 0
302
+ - `log_level`: passive
303
+ - `log_level_replica`: warning
304
+ - `log_on_each_node`: True
305
+ - `logging_nan_inf_filter`: True
306
+ - `save_safetensors`: True
307
+ - `save_on_each_node`: False
308
+ - `save_only_model`: False
309
+ - `restore_callback_states_from_checkpoint`: False
310
+ - `no_cuda`: False
311
+ - `use_cpu`: False
312
+ - `use_mps_device`: False
313
+ - `seed`: 42
314
+ - `data_seed`: None
315
+ - `jit_mode_eval`: False
316
+ - `bf16`: False
317
+ - `fp16`: False
318
+ - `fp16_opt_level`: O1
319
+ - `half_precision_backend`: auto
320
+ - `bf16_full_eval`: False
321
+ - `fp16_full_eval`: False
322
+ - `tf32`: None
323
+ - `local_rank`: 0
324
+ - `ddp_backend`: None
325
+ - `tpu_num_cores`: None
326
+ - `tpu_metrics_debug`: False
327
+ - `debug`: []
328
+ - `dataloader_drop_last`: False
329
+ - `dataloader_num_workers`: 0
330
+ - `dataloader_prefetch_factor`: None
331
+ - `past_index`: -1
332
+ - `disable_tqdm`: False
333
+ - `remove_unused_columns`: True
334
+ - `label_names`: None
335
+ - `load_best_model_at_end`: False
336
+ - `ignore_data_skip`: False
337
+ - `fsdp`: []
338
+ - `fsdp_min_num_params`: 0
339
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
340
+ - `fsdp_transformer_layer_cls_to_wrap`: None
341
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
342
+ - `parallelism_config`: None
343
+ - `deepspeed`: None
344
+ - `label_smoothing_factor`: 0.0
345
+ - `optim`: adamw_torch_fused
346
+ - `optim_args`: None
347
+ - `adafactor`: False
348
+ - `group_by_length`: False
349
+ - `length_column_name`: length
350
+ - `project`: huggingface
351
+ - `trackio_space_id`: trackio
352
+ - `ddp_find_unused_parameters`: None
353
+ - `ddp_bucket_cap_mb`: None
354
+ - `ddp_broadcast_buffers`: False
355
+ - `dataloader_pin_memory`: True
356
+ - `dataloader_persistent_workers`: False
357
+ - `skip_memory_metrics`: True
358
+ - `use_legacy_prediction_loop`: False
359
+ - `push_to_hub`: False
360
+ - `resume_from_checkpoint`: None
361
+ - `hub_model_id`: None
362
+ - `hub_strategy`: every_save
363
+ - `hub_private_repo`: None
364
+ - `hub_always_push`: False
365
+ - `hub_revision`: None
366
+ - `gradient_checkpointing`: False
367
+ - `gradient_checkpointing_kwargs`: None
368
+ - `include_inputs_for_metrics`: False
369
+ - `include_for_metrics`: []
370
+ - `eval_do_concat_batches`: True
371
+ - `fp16_backend`: auto
372
+ - `push_to_hub_model_id`: None
373
+ - `push_to_hub_organization`: None
374
+ - `mp_parameters`:
375
+ - `auto_find_batch_size`: False
376
+ - `full_determinism`: False
377
+ - `torchdynamo`: None
378
+ - `ray_scope`: last
379
+ - `ddp_timeout`: 1800
380
+ - `torch_compile`: False
381
+ - `torch_compile_backend`: None
382
+ - `torch_compile_mode`: None
383
+ - `include_tokens_per_second`: False
384
+ - `include_num_input_tokens_seen`: no
385
+ - `neftune_noise_alpha`: None
386
+ - `optim_target_modules`: None
387
+ - `batch_eval_metrics`: False
388
+ - `eval_on_start`: False
389
+ - `use_liger_kernel`: False
390
+ - `liger_kernel_config`: None
391
+ - `eval_use_gather_object`: False
392
+ - `average_tokens_across_devices`: True
393
+ - `prompts`: None
394
+ - `batch_sampler`: batch_sampler
395
+ - `multi_dataset_batch_sampler`: round_robin
396
+ - `router_mapping`: {}
397
+ - `learning_rate_mapping`: {}
398
+
399
+ </details>
400
+
401
+ ### Framework Versions
402
+ - Python: 3.12.12
403
+ - Sentence Transformers: 5.1.2
404
+ - Transformers: 4.57.3
405
+ - PyTorch: 2.9.0+cu126
406
+ - Accelerate: 1.12.0
407
+ - Datasets: 4.0.0
408
+ - Tokenizers: 0.22.1
409
+
410
+ ## Citation
411
+
412
+ ### BibTeX
413
+
414
+ #### Sentence Transformers
415
+ ```bibtex
416
+ @inproceedings{reimers-2019-sentence-bert,
417
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
418
+ author = "Reimers, Nils and Gurevych, Iryna",
419
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
420
+ month = "11",
421
+ year = "2019",
422
+ publisher = "Association for Computational Linguistics",
423
+ url = "https://arxiv.org/abs/1908.10084",
424
+ }
425
+ ```
426
+
427
+ #### ContrastiveLoss
428
+ ```bibtex
429
+ @inproceedings{hadsell2006dimensionality,
430
+ author={Hadsell, R. and Chopra, S. and LeCun, Y.},
431
+ booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
432
+ title={Dimensionality Reduction by Learning an Invariant Mapping},
433
+ year={2006},
434
+ volume={2},
435
+ number={},
436
+ pages={1735-1742},
437
+ doi={10.1109/CVPR.2006.100}
438
+ }
439
+ ```
440
+
441
+ <!--
442
+ ## Glossary
443
+
444
+ *Clearly define terms in order to be accessible across audiences.*
445
+ -->
446
+
447
+ <!--
448
+ ## Model Card Authors
449
+
450
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
451
+ -->
452
+
453
+ <!--
454
+ ## Model Card Contact
455
+
456
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
457
+ -->
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_ids": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "position_embedding_type": "absolute",
23
+ "transformers_version": "4.57.3",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "SentenceTransformer",
3
+ "__version__": {
4
+ "sentence_transformers": "5.1.2",
5
+ "transformers": "4.57.3",
6
+ "pytorch": "2.9.0+cu126"
7
+ },
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2057f247e5f9d7952a7f9e81d149018ad20e37c5cc902ddb88a623567ba5a21f
3
+ size 437951328
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 +1,7 @@
 
 
 
 
 
 
 
 
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff