kperkins411 commited on
Commit
95c6b38
1 Parent(s): 5e5d94c

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
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 +1,552 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets: []
3
+ language: []
4
+ library_name: sentence-transformers
5
+ metrics:
6
+ - cosine_accuracy
7
+ - dot_accuracy
8
+ - manhattan_accuracy
9
+ - euclidean_accuracy
10
+ - max_accuracy
11
+ pipeline_tag: sentence-similarity
12
+ tags:
13
+ - sentence-transformers
14
+ - sentence-similarity
15
+ - feature-extraction
16
+ - generated_from_trainer
17
+ - dataset_size:32621
18
+ - loss:TripletLoss
19
+ widget:
20
+ - source_sentence: 6.2 either party may terminate this agreement for cause if the
21
+ other party fails to perform any material provision of this agreement or commits
22
+ a material breach of this agreement which is not corrected within [***] after
23
+ receiving written notice of the failure or breach. except that if the default
24
+ is by 6 supplier that creates an immediate public food safety risk, pnc may terminate
25
+ this agreement immediately without regard to any period for correction.
26
+ sentences:
27
+ - what constitutes a material violation under the default provision?
28
+ - '8.3 termination for cause. this agreement may be terminated by a party ----------------------
29
+ for cause immediately upon the occurrence of and in accordance with the following:
30
+ (a) insolvency event. either may terminate this agreement by delivering written
31
+ notice to the other party upon the occurrence of any of the following events:
32
+ (i) a receiver is appointed for either party or its property; (ii) either makes
33
+ a general assignment for the benefit of its creditors; (iii) either party commences,
34
+ or has commenced against it, proceedings under any bankruptcy, insolvency or debtor''s
35
+ relief law, which proceedings are not dismissed within sixty (60) days; or (iv)
36
+ either party is liquidated or source: rae systems inc, 10-q, 11/14/2000 dissolved.
37
+ (b) change of control. in the event more that there is a change in ownership representing
38
+ fifty percent (50%) or more of the equity ownership of either party, the other
39
+ party may, at its option, terminate this agreement upon written notice. (c) default.
40
+ either party may terminate this agreement effective upon written notice to the
41
+ other if the other party violates any covenant, agreement, representation or warranty
42
+ contained herein in any material respect or defaults or fails to perform any of
43
+ its obligations or agreements hereunder in any material respect, which violation,
44
+ default or failure is not cured within thirty (30) days after notice thereof from
45
+ the non-defaulting party stating its intention to terminate this agreement by
46
+ reason thereof.'
47
+ - does chinese law supersede international regulations?
48
+ - source_sentence: (a) member specifically acknowledges that, pursuant to the franchise
49
+ agreement, and by virtue of its position with franchisee, member will receive
50
+ valuable specialized training and confidential information, including, without
51
+ limitation, information regarding the operational, sales, promotional, and marketing
52
+ methods and techniques of franchisor and the system.
53
+ sentences:
54
+ - 1. confidential information. member shall not, during the term of the franchise
55
+ agreement or thereafter, communicate, divulge or use, for any purpose other than
56
+ the operation of the franchised business, any confidential information, knowledge,
57
+ trade secrets or know-how which may be communicated to member or which member
58
+ may learn by virtue of member's relationship with franchisee. all information,
59
+ knowledge and know-how relating to franchisor, its business plans, franchised
60
+ businesses, or the system ("confidential information") is deemed confidential,
61
+ except for information that member can demonstrate came to member's attention
62
+ by lawful means prior to disclosure to member; or which, at the time of the disclosure
63
+ to member, had become a part of the public domain.
64
+ - can the member use trade secrets for purposes outside of operating the franchised
65
+ business?
66
+ - is written consent from party a mandatory for party b's assignment?
67
+ - source_sentence: 'ad networks we may feature advertising within our service. the
68
+ advertisers may collect and use information about you, such as your service session
69
+ activity, device identifier, mac address, imei, geo-location information and ip
70
+ address. they may use this information to provide advertisements of interest to
71
+ you. please refer to our list of partners within the services and for more information
72
+ on how to opt out at: http://www.supercell.net/partner-opt-out.'
73
+ sentences:
74
+ - what is the designation for the type of data that pertains to a person's confidential
75
+ and unique identifiers, including their electronic mail details and connections
76
+ within online platforms?
77
+ - which entities constitute 'ad partners' as mentioned in the clause?
78
+ - how we use data collection tools and online advertising under armour uses cookies
79
+ and other data collection tools like web beacons to collect data that help us
80
+ personalize your use of our websites and mobile applications. we also work with
81
+ a variety of advertisers, advertising networks, advertising servers, and analytics
82
+ companies ("ad partners") that use various technologies including cookies to collect
83
+ data about your use of the services (such as pages visited, ads viewed or clicked
84
+ on) so that we and our ad partners deliver ads to you based on your interests
85
+ and online activities.
86
+ - source_sentence: third-party vendors, including google, use cookies to serve ads
87
+ based on a user's prior visits to our website and other websites. google's use
88
+ of advertising cookies enables it and its partners to serve ads based on visits
89
+ to our site or other sites on the internet. you can opt out of personalized advertising
90
+ by visiting google's ads settings. alternately, you can opt out of other third-party
91
+ vendors' uses of cookies by visiting the digital advertising alliance's (daa)
92
+ opt out page at http://www.aboutads.info/choices or http://www.aboutads.info/appchoices.
93
+ to find out more about how google uses data it collects please visit google privacy
94
+ & principals.
95
+ sentences:
96
+ - google, as a third party vendor, uses cookies to serve ads on our site. google's
97
+ use of the dart cookie enables it to serve ads to our users based on their visit
98
+ to our site and other sites on the internet. users may opt out of the use of the
99
+ dart cookie by visiting the google ad and content network privacy policy.
100
+ - is google considered a third-party vendor in this context?
101
+ - what are the obligations of the henry film and entertainment corporation under
102
+ this agreement?
103
+ - source_sentence: sponsor acknowledges and agrees that, notwithstanding the grant
104
+ of exclusivity set forth in this section 4, team shall have the right to solicit
105
+ and enter into sponsorships with other parties that are not known primarily or
106
+ exclusively as suppliers or providers of any product or service within the product
107
+ and services category.
108
+ sentences:
109
+ - what constitutes a 'purchase' under the revenue-sharing agreement?
110
+ - for the avoidance of doubt, the parties acknowledge that the foregoing restriction
111
+ applies only to persistent sponsorship placement as judged by sponsor at its discretion,
112
+ and not to run-of-site banner advertisements or other rotating promotional placements.
113
+ - what does 'foregoing restriction' refer to specifically within the context of
114
+ sponsorships?
115
+ model-index:
116
+ - name: SentenceTransformer
117
+ results:
118
+ - task:
119
+ type: triplet
120
+ name: Triplet
121
+ dataset:
122
+ name: all nli dev
123
+ type: all-nli-dev
124
+ metrics:
125
+ - type: cosine_accuracy
126
+ value: 0.5286745157614888
127
+ name: Cosine Accuracy
128
+ - type: dot_accuracy
129
+ value: 0.47322445879225217
130
+ name: Dot Accuracy
131
+ - type: manhattan_accuracy
132
+ value: 0.5104443600455754
133
+ name: Manhattan Accuracy
134
+ - type: euclidean_accuracy
135
+ value: 0.5142423091530574
136
+ name: Euclidean Accuracy
137
+ - type: max_accuracy
138
+ value: 0.5286745157614888
139
+ name: Max Accuracy
140
+ - task:
141
+ type: triplet
142
+ name: Triplet
143
+ dataset:
144
+ name: all nli test
145
+ type: all-nli-test
146
+ metrics:
147
+ - type: cosine_accuracy
148
+ value: 0.529054310672237
149
+ name: Cosine Accuracy
150
+ - type: dot_accuracy
151
+ value: 0.470945689327763
152
+ name: Dot Accuracy
153
+ - type: manhattan_accuracy
154
+ value: 0.5100645651348272
155
+ name: Manhattan Accuracy
156
+ - type: euclidean_accuracy
157
+ value: 0.515381693885302
158
+ name: Euclidean Accuracy
159
+ - type: max_accuracy
160
+ value: 0.529054310672237
161
+ name: Max Accuracy
162
+ ---
163
+
164
+ # SentenceTransformer
165
+
166
+ This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
167
+
168
+ ## Model Details
169
+
170
+ ### Model Description
171
+ - **Model Type:** Sentence Transformer
172
+ <!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
173
+ - **Maximum Sequence Length:** 512 tokens
174
+ - **Output Dimensionality:** 384 tokens
175
+ - **Similarity Function:** Cosine Similarity
176
+ <!-- - **Training Dataset:** Unknown -->
177
+ <!-- - **Language:** Unknown -->
178
+ <!-- - **License:** Unknown -->
179
+
180
+ ### Model Sources
181
+
182
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
183
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
184
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
185
+
186
+ ### Full Model Architecture
187
+
188
+ ```
189
+ SentenceTransformer(
190
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
191
+ (1): Pooling({'word_embedding_dimension': 384, '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})
192
+ )
193
+ ```
194
+
195
+ ## Usage
196
+
197
+ ### Direct Usage (Sentence Transformers)
198
+
199
+ First install the Sentence Transformers library:
200
+
201
+ ```bash
202
+ pip install -U sentence-transformers
203
+ ```
204
+
205
+ Then you can load this model and run inference.
206
+ ```python
207
+ from sentence_transformers import SentenceTransformer
208
+
209
+ # Download from the 🤗 Hub
210
+ model = SentenceTransformer("kperkins411/multi-qa-MiniLM-L6-cos-v1_triplet")
211
+ # Run inference
212
+ sentences = [
213
+ 'sponsor acknowledges and agrees that, notwithstanding the grant of exclusivity set forth in this section 4, team shall have the right to solicit and enter into sponsorships with other parties that are not known primarily or exclusively as suppliers or providers of any product or service within the product and services category.',
214
+ "what does 'foregoing restriction' refer to specifically within the context of sponsorships?",
215
+ 'for the avoidance of doubt, the parties acknowledge that the foregoing restriction applies only to persistent sponsorship placement as judged by sponsor at its discretion, and not to run-of-site banner advertisements or other rotating promotional placements.',
216
+ ]
217
+ embeddings = model.encode(sentences)
218
+ print(embeddings.shape)
219
+ # [3, 384]
220
+
221
+ # Get the similarity scores for the embeddings
222
+ similarities = model.similarity(embeddings, embeddings)
223
+ print(similarities.shape)
224
+ # [3, 3]
225
+ ```
226
+
227
+ <!--
228
+ ### Direct Usage (Transformers)
229
+
230
+ <details><summary>Click to see the direct usage in Transformers</summary>
231
+
232
+ </details>
233
+ -->
234
+
235
+ <!--
236
+ ### Downstream Usage (Sentence Transformers)
237
+
238
+ You can finetune this model on your own dataset.
239
+
240
+ <details><summary>Click to expand</summary>
241
+
242
+ </details>
243
+ -->
244
+
245
+ <!--
246
+ ### Out-of-Scope Use
247
+
248
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
249
+ -->
250
+
251
+ ## Evaluation
252
+
253
+ ### Metrics
254
+
255
+ #### Triplet
256
+ * Dataset: `all-nli-dev`
257
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
258
+
259
+ | Metric | Value |
260
+ |:-------------------|:-----------|
261
+ | cosine_accuracy | 0.5287 |
262
+ | dot_accuracy | 0.4732 |
263
+ | manhattan_accuracy | 0.5104 |
264
+ | euclidean_accuracy | 0.5142 |
265
+ | **max_accuracy** | **0.5287** |
266
+
267
+ #### Triplet
268
+ * Dataset: `all-nli-test`
269
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
270
+
271
+ | Metric | Value |
272
+ |:-------------------|:-----------|
273
+ | cosine_accuracy | 0.5291 |
274
+ | dot_accuracy | 0.4709 |
275
+ | manhattan_accuracy | 0.5101 |
276
+ | euclidean_accuracy | 0.5154 |
277
+ | **max_accuracy** | **0.5291** |
278
+
279
+ <!--
280
+ ## Bias, Risks and Limitations
281
+
282
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
283
+ -->
284
+
285
+ <!--
286
+ ### Recommendations
287
+
288
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
289
+ -->
290
+
291
+ ## Training Details
292
+
293
+ ### Training Dataset
294
+
295
+ #### Unnamed Dataset
296
+
297
+
298
+ * Size: 32,621 training samples
299
+ * Columns: <code>negative</code>, <code>anchor</code>, and <code>positive</code>
300
+ * Approximate statistics based on the first 1000 samples:
301
+ | | negative | anchor | positive |
302
+ |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
303
+ | type | string | string | string |
304
+ | details | <ul><li>min: 6 tokens</li><li>mean: 80.74 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 17.19 tokens</li><li>max: 167 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 101.64 tokens</li><li>max: 512 tokens</li></ul> |
305
+ * Samples:
306
+ | negative | anchor | positive |
307
+ |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
308
+ | <code>c. the obligations specified in this article shall not apply to information for which the receiving party can reasonably demonstrate that such information: iii. becomes known to the receiving party through disclosure by sources other than the disclosing party, having a right to disclose such information,</code> | <code>what safeguards are in place to protect the information obtained from third-party sources?</code> | <code>information we collect from other sources we may also receive information from other sources and combine that with information we collect through our services. for example: if you choose to link, create, or log in to your uber account with a payment provider (e.g., google wallet) or social media service (e.g., facebook), or if you engage with a separate app or website that uses our api (or whose api we use), we may receive information about you or your connections from that site or app.</code> |
309
+ | <code>3.2 manufacturing standards the manufacturer covenants that it is and will remain for the term of this agreement in compliance with all international standards in production and manufacturing.</code> | <code>is there a guarantee from the manufacturers regarding the conformity of the items to the mutually approved written standards for a certain duration?</code> | <code>each of the suppliers warrants that the products shall comply with the specifications and documentation agreed by the relevant supplier and the company in writing that is applicable to such products for the warranty period.</code> |
310
+ | <code>planetcad hereby grants to dassault systemes a fully-paid, non-exclusive, worldwide, revocable limited license to the server software and infrastructure for the sole purpose of (i) hosting the co-branded service and (ii) fulfilling its<omitted>obligations under this agreement.</code> | <code>what type of authorization has the video conferencing service provided to the british virgin islands-based entity and its associated organization regarding their intellectual property, with respect to the customized software and web platform, including the conditions for customer access to enhanced functionalities that incur additional charges?</code> | <code>skype hereby grants to online bvi and the company a limited, non-exclusive, non-sublicensable (except as set forth herein), non-transferable, non-assignable (except as provided in section 14.4), royalty-free (but subject to the provisions of section 5), license during the term to use, market, provide access to, promote, reproduce and display the skype intellectual property solely (i) as incorporated in the company-skype branded application and/or the company-skype toolbar, and (ii) as incorporated in, for the development of, and for transmission pursuant to this agreement of, the company-skype branded content and the company-skype branded web site, in each case for the sole purposes (unless otherwise mutually agreed by the parties) of promoting and distributing, pursuant to this agreement, the company-skype branded application, the company-skype toolbar, the company-skype branded content and the company-skype branded web site in the territory; (a) provided, that it is understood that the company-skype branded customers will have the right under the eula to use the company- skype branded application and the company-skype toolbar and will have the right to access the company-skype branded content, the company-skype branded web site and the online bvi web site through the internet and to otherwise receive support from the company anywhere in the world, and that the company shall be permitted to provide access to and reproduce and display the skype intellectual property through the internet anywhere in the world, and (b) provided further, that online bvi and the company shall ensure that no company-skype branded customer (or potential company-skype branded customer) shall be permitted to access, using the company-skype branded application or the company-skype toolbar or through the company-skype branded web site, any skype premium features requiring payment by the company-skype branded customer (or potential company-skype branded customer), including, but not limited to, skypein, skypeout, or skype plus, unless such company-skype branded customer (or potential company-skype branded customer) uses the payment methods made available by the company pursuant to section 2.5 for the purchase of such premium features.</code> |
311
+ * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
312
+ ```json
313
+ {
314
+ "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
315
+ "triplet_margin": 5
316
+ }
317
+ ```
318
+
319
+ ### Evaluation Dataset
320
+
321
+ #### Unnamed Dataset
322
+
323
+
324
+ * Size: 2,641 evaluation samples
325
+ * Columns: <code>negative</code>, <code>anchor</code>, and <code>positive</code>
326
+ * Approximate statistics based on the first 1000 samples:
327
+ | | negative | anchor | positive |
328
+ |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
329
+ | type | string | string | string |
330
+ | details | <ul><li>min: 6 tokens</li><li>mean: 83.63 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 18.61 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 98.17 tokens</li><li>max: 512 tokens</li></ul> |
331
+ * Samples:
332
+ | negative | anchor | positive |
333
+ |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
334
+ | <code>this agreement shall be governed by, and construed in accordance with the law of the state of new york.</code> | <code>are there any exceptions to the governing law stated?</code> | <code>this agreement shall be governed by the laws of the state of california, without regard to the conflicts of law provisions of any jurisdiction.</code> |
335
+ | <code>you consent to the third party use, sharing and transfer of your personal information (both inside and outside of your jurisdiction) as described in this section. these third parties will use personal information to provide services to us and for their own internal use, including analytics use. we allow third parties such as analytics providers and advertising partners to collect your personal information over time and across different websites or online services when you use our services.</code> | <code>collection of personal data legal basis?</code> | <code>15. notice for malaysia residents close in view of the implementation of the personal data protection act 2010 ("act"), sony mobile recognises the need to process all personal data obtained in a lawful and appropriate manner. the legal responsibility for compliance with the act lies with sony mobile, which is the "data user" under the act. compliance with this privacy policy and the act is the responsibility of all employees of sony mobile. as and when sony mobile is required to collect personal data, sony mobile and its employees must abide by the requirements of this privacy policy and the act. in the context of the act, "processing" is defined as including the collection, recording, holding or storing of personal data which includes, inter alia, nric numbers, home address and contact details.</code> |
336
+ | <code>you can prevent peel from showing you targeted ads by sending an email to privacy@peel.com and asking to opt-out of targeted advertising. opting-out will only prevent targeted ads from being displayed so you may continue to see generic (non-targeted) ads from peel after you opt-out. for more information on interest-based ads or to stop use of tracking technologies for these purposes, go to www.aboutads.info or www.networkadvertising.org.</code> | <code>how does one opt out from third-party analytics providers?</code> | <code>when you use our services, we collect the following information: information about your device (including device model, os version and operator's name), time and date of the connection to the game and/or service, ip or mac address, international mobile equipment id (imei), android id, device mac address, cookie information. we also from time-to-time use services provided by third party companies that might collect information from you, and you can opt-out from this. follow the directions provided by our other third party analytics provider located at http://www.flurry.com/user-opt-out.html, https://help.chartboost.com/legal/privacy, http://privacy.adcolony.com/, http://info.tapjoy.com/about-tapjoy/privacy-policy/, http://sponsorpay.com/. if you "opt out" with our third party analytics providers, that action is specific to the information we collect specifically for that provider, and does not limit our ability to collect information from you, under the terms of this privacy policy, for other third parties.</code> |
337
+ * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
338
+ ```json
339
+ {
340
+ "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
341
+ "triplet_margin": 5
342
+ }
343
+ ```
344
+
345
+ ### Training Hyperparameters
346
+ #### Non-Default Hyperparameters
347
+
348
+ - `eval_strategy`: steps
349
+ - `per_device_train_batch_size`: 64
350
+ - `per_device_eval_batch_size`: 64
351
+ - `learning_rate`: 2e-05
352
+ - `num_train_epochs`: 4
353
+ - `warmup_ratio`: 0.1
354
+ - `fp16`: True
355
+ - `batch_sampler`: no_duplicates
356
+
357
+ #### All Hyperparameters
358
+ <details><summary>Click to expand</summary>
359
+
360
+ - `overwrite_output_dir`: False
361
+ - `do_predict`: False
362
+ - `eval_strategy`: steps
363
+ - `prediction_loss_only`: True
364
+ - `per_device_train_batch_size`: 64
365
+ - `per_device_eval_batch_size`: 64
366
+ - `per_gpu_train_batch_size`: None
367
+ - `per_gpu_eval_batch_size`: None
368
+ - `gradient_accumulation_steps`: 1
369
+ - `eval_accumulation_steps`: None
370
+ - `learning_rate`: 2e-05
371
+ - `weight_decay`: 0.0
372
+ - `adam_beta1`: 0.9
373
+ - `adam_beta2`: 0.999
374
+ - `adam_epsilon`: 1e-08
375
+ - `max_grad_norm`: 1.0
376
+ - `num_train_epochs`: 4
377
+ - `max_steps`: -1
378
+ - `lr_scheduler_type`: linear
379
+ - `lr_scheduler_kwargs`: {}
380
+ - `warmup_ratio`: 0.1
381
+ - `warmup_steps`: 0
382
+ - `log_level`: passive
383
+ - `log_level_replica`: warning
384
+ - `log_on_each_node`: True
385
+ - `logging_nan_inf_filter`: True
386
+ - `save_safetensors`: True
387
+ - `save_on_each_node`: False
388
+ - `save_only_model`: False
389
+ - `restore_callback_states_from_checkpoint`: False
390
+ - `no_cuda`: False
391
+ - `use_cpu`: False
392
+ - `use_mps_device`: False
393
+ - `seed`: 42
394
+ - `data_seed`: None
395
+ - `jit_mode_eval`: False
396
+ - `use_ipex`: False
397
+ - `bf16`: False
398
+ - `fp16`: True
399
+ - `fp16_opt_level`: O1
400
+ - `half_precision_backend`: auto
401
+ - `bf16_full_eval`: False
402
+ - `fp16_full_eval`: False
403
+ - `tf32`: None
404
+ - `local_rank`: 0
405
+ - `ddp_backend`: None
406
+ - `tpu_num_cores`: None
407
+ - `tpu_metrics_debug`: False
408
+ - `debug`: []
409
+ - `dataloader_drop_last`: False
410
+ - `dataloader_num_workers`: 0
411
+ - `dataloader_prefetch_factor`: None
412
+ - `past_index`: -1
413
+ - `disable_tqdm`: False
414
+ - `remove_unused_columns`: True
415
+ - `label_names`: None
416
+ - `load_best_model_at_end`: False
417
+ - `ignore_data_skip`: False
418
+ - `fsdp`: []
419
+ - `fsdp_min_num_params`: 0
420
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
421
+ - `fsdp_transformer_layer_cls_to_wrap`: None
422
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
423
+ - `deepspeed`: None
424
+ - `label_smoothing_factor`: 0.0
425
+ - `optim`: adamw_torch
426
+ - `optim_args`: None
427
+ - `adafactor`: False
428
+ - `group_by_length`: False
429
+ - `length_column_name`: length
430
+ - `ddp_find_unused_parameters`: None
431
+ - `ddp_bucket_cap_mb`: None
432
+ - `ddp_broadcast_buffers`: False
433
+ - `dataloader_pin_memory`: True
434
+ - `dataloader_persistent_workers`: False
435
+ - `skip_memory_metrics`: True
436
+ - `use_legacy_prediction_loop`: False
437
+ - `push_to_hub`: False
438
+ - `resume_from_checkpoint`: None
439
+ - `hub_model_id`: None
440
+ - `hub_strategy`: every_save
441
+ - `hub_private_repo`: False
442
+ - `hub_always_push`: False
443
+ - `gradient_checkpointing`: False
444
+ - `gradient_checkpointing_kwargs`: None
445
+ - `include_inputs_for_metrics`: False
446
+ - `eval_do_concat_batches`: True
447
+ - `fp16_backend`: auto
448
+ - `push_to_hub_model_id`: None
449
+ - `push_to_hub_organization`: None
450
+ - `mp_parameters`:
451
+ - `auto_find_batch_size`: False
452
+ - `full_determinism`: False
453
+ - `torchdynamo`: None
454
+ - `ray_scope`: last
455
+ - `ddp_timeout`: 1800
456
+ - `torch_compile`: False
457
+ - `torch_compile_backend`: None
458
+ - `torch_compile_mode`: None
459
+ - `dispatch_batches`: None
460
+ - `split_batches`: None
461
+ - `include_tokens_per_second`: False
462
+ - `include_num_input_tokens_seen`: False
463
+ - `neftune_noise_alpha`: None
464
+ - `optim_target_modules`: None
465
+ - `batch_eval_metrics`: False
466
+ - `batch_sampler`: no_duplicates
467
+ - `multi_dataset_batch_sampler`: proportional
468
+
469
+ </details>
470
+
471
+ ### Training Logs
472
+ | Epoch | Step | Training Loss | loss | all-nli-dev_max_accuracy | all-nli-test_max_accuracy |
473
+ |:------:|:----:|:-------------:|:------:|:------------------------:|:-------------------------:|
474
+ | 0 | 0 | - | - | 0.7235 | - |
475
+ | 0.1961 | 100 | 4.9029 | 3.1938 | 0.6058 | - |
476
+ | 0.3922 | 200 | 2.4204 | 1.5424 | 0.5507 | - |
477
+ | 0.5882 | 300 | 1.6076 | 1.0643 | 0.5344 | - |
478
+ | 0.7843 | 400 | 1.3142 | 0.8831 | 0.5351 | - |
479
+ | 0.9804 | 500 | 1.1919 | 0.7455 | 0.5435 | - |
480
+ | 1.1745 | 600 | 1.0824 | 0.6599 | 0.5427 | - |
481
+ | 1.3706 | 700 | 0.963 | 0.6360 | 0.5518 | - |
482
+ | 1.5667 | 800 | 0.8922 | 0.6131 | 0.5397 | - |
483
+ | 1.7627 | 900 | 0.8417 | 0.5900 | 0.5302 | - |
484
+ | 1.9588 | 1000 | 0.8165 | 0.5662 | 0.5253 | - |
485
+ | 2.1529 | 1100 | 0.7774 | 0.5192 | 0.5177 | - |
486
+ | 2.3490 | 1200 | 0.7394 | 0.5158 | 0.5363 | - |
487
+ | 2.5451 | 1300 | 0.7003 | 0.5185 | 0.5363 | - |
488
+ | 2.7412 | 1400 | 0.6636 | 0.5004 | 0.5310 | - |
489
+ | 2.9373 | 1500 | 0.6586 | 0.4872 | 0.5302 | - |
490
+ | 3.1314 | 1600 | 0.6831 | 0.4687 | 0.5306 | - |
491
+ | 3.3275 | 1700 | 0.6494 | 0.4667 | 0.5268 | - |
492
+ | 3.5235 | 1800 | 0.624 | 0.4750 | 0.5321 | - |
493
+ | 3.7196 | 1900 | 0.6035 | 0.4735 | 0.5264 | - |
494
+ | 3.9157 | 2000 | 0.6136 | 0.4679 | 0.5287 | - |
495
+ | 3.9941 | 2040 | - | - | - | 0.5291 |
496
+
497
+
498
+ ### Framework Versions
499
+ - Python: 3.11.9
500
+ - Sentence Transformers: 3.0.1
501
+ - Transformers: 4.41.2
502
+ - PyTorch: 2.1.2+cu121
503
+ - Accelerate: 0.31.0
504
+ - Datasets: 2.19.1
505
+ - Tokenizers: 0.19.1
506
+
507
+ ## Citation
508
+
509
+ ### BibTeX
510
+
511
+ #### Sentence Transformers
512
+ ```bibtex
513
+ @inproceedings{reimers-2019-sentence-bert,
514
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
515
+ author = "Reimers, Nils and Gurevych, Iryna",
516
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
517
+ month = "11",
518
+ year = "2019",
519
+ publisher = "Association for Computational Linguistics",
520
+ url = "https://arxiv.org/abs/1908.10084",
521
+ }
522
+ ```
523
+
524
+ #### TripletLoss
525
+ ```bibtex
526
+ @misc{hermans2017defense,
527
+ title={In Defense of the Triplet Loss for Person Re-Identification},
528
+ author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
529
+ year={2017},
530
+ eprint={1703.07737},
531
+ archivePrefix={arXiv},
532
+ primaryClass={cs.CV}
533
+ }
534
+ ```
535
+
536
+ <!--
537
+ ## Glossary
538
+
539
+ *Clearly define terms in order to be accessible across audiences.*
540
+ -->
541
+
542
+ <!--
543
+ ## Model Card Authors
544
+
545
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
546
+ -->
547
+
548
+ <!--
549
+ ## Model Card Contact
550
+
551
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
552
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/multi-qa-MiniLM-L6-cos-v1",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.41.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.1.2+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:c729929d68afa140f1f2dc93b788384f2e8a9a4f95cc09856a02616acfc0c7d8
3
+ size 90864192
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.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ "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
+ "mask_token": "[MASK]",
49
+ "max_length": 250,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff