Hugging Face's logo

kperkins411
/
multi-qa-mpnet-base-cos-v1_MultipleNegativesRankingLoss

Sentence Similarity
sentence-transformers
Safetensors
mpnet
feature-extraction
Generated from Trainer
dataset_size:491850
loss:MultipleNegativesRankingLoss
Eval Results
Inference Endpoints
Model card Files Community
kperkins411 commited on
Commit
227684e
•
1 Parent(s): 94d9f47

Add new SentenceTransformer model.

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +1011 -0
  3. config.json +24 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +20 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +72 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,1011 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sentence-transformers/multi-qa-mpnet-base-cos-v1
3
+ datasets: []
4
+ language: []
5
+ library_name: sentence-transformers
6
+ metrics:
7
+ - cosine_accuracy@1
8
+ - cosine_accuracy@3
9
+ - cosine_accuracy@5
10
+ - cosine_accuracy@10
11
+ - cosine_precision@1
12
+ - cosine_precision@3
13
+ - cosine_precision@5
14
+ - cosine_precision@10
15
+ - cosine_recall@1
16
+ - cosine_recall@3
17
+ - cosine_recall@5
18
+ - cosine_recall@10
19
+ - cosine_ndcg@10
20
+ - cosine_mrr@10
21
+ - cosine_map@100
22
+ - dot_accuracy@1
23
+ - dot_accuracy@3
24
+ - dot_accuracy@5
25
+ - dot_accuracy@10
26
+ - dot_precision@1
27
+ - dot_precision@3
28
+ - dot_precision@5
29
+ - dot_precision@10
30
+ - dot_recall@1
31
+ - dot_recall@3
32
+ - dot_recall@5
33
+ - dot_recall@10
34
+ - dot_ndcg@10
35
+ - dot_mrr@10
36
+ - dot_map@100
37
+ pipeline_tag: sentence-similarity
38
+ tags:
39
+ - sentence-transformers
40
+ - sentence-similarity
41
+ - feature-extraction
42
+ - generated_from_trainer
43
+ - dataset_size:491850
44
+ - loss:MultipleNegativesRankingLoss
45
+ widget:
46
+ - source_sentence: Is Auriemma able to affect the choices made by the educational
47
+ institution in Connecticut regarding deals with rivals of the company located
48
+ in Berkshire?
49
+ sentences:
50
+ - "13. EXPENSES ASSOCIATED WITH THIS AGREEMENT. Marv shall be reimbursed in\
51
+ \ full for the cost(s) of all legal expenses associated with this agreement by\
52
+ \ THI. [remainder of page intentionally left blank; signature page to follow]\n\
53
+ \n5\n\n\n\n\n\n IN WITNESS WHEREOF, the Parties hereto, agreeing\
54
+ \ to be bound hereby, execute this Agreement upon the date first set forth above.\
55
+ \ Premier Biomedical, Inc.: /s/ William Hartman Date__________ By:\
56
+ \ William Hartman, CEO Technology Health, Inc.: /s/ James Christopher\
57
+ \ LeDoux Date___________ By: CEO Marv Enterprises, LLC: \
58
+ \ /s/ Mitchell Felder Date__________ By: Mitchell Felder\n\n6"
59
+ - Notwithstanding the foregoing, either party shall have the right to assign this
60
+ Agreement in connection with the merger or acquisition of such party or the sale
61
+ of all or substantially all of its assets related to this Agreement without such
62
+ consent, except in the case where such transaction involves a direct competitor
63
+ of the other party where consent of the other party will be required.
64
+ - Notwithstanding the foregoing, it is understood that Auriemma has no control or
65
+ influence over any decisions by the University of Connecticut to enter into any
66
+ arrangement or agreement with any Berkshire Competitor.
67
+ - source_sentence: Can this location information be shared with third-party entities?
68
+ sentences:
69
+ - Information Collected by Third Parties Third Parties' Services Our Services may
70
+ contain third party tracking tools from third party service providers. Such third
71
+ parties may use cookies, APIs, and SDKs in our Services to enable them to collect
72
+ and analyze your information on our behalf. The third parties may have access
73
+ to information such as your device identifier, MAC address, IMEI, locale (specific
74
+ location where a given language is spoken), geo-location information, and IP address
75
+ for the purpose of providing their services under their respective privacy policies.
76
+ The Policy does not cover the use of tracking tools from third parties. We do
77
+ not have access or control over these third parties. If you would like to know
78
+ the information of the corresponding third parties, please contact us at support@meitu.com
79
+ or legal@meitu.com
80
+ - We may collect your location based information for the purpose of providing you
81
+ with a correct version of the application and our better Services. Except otherwise
82
+ provided in the Policy, we will not share this information with any third party.
83
+ If you no longer wish to allow us to track or use such information, you may turn
84
+ the internet access and/or GPS off at the device level or disable the relevant
85
+ permission to our application.
86
+ - Notwithstanding the foregoing, it is understood that Auriemma has no control or
87
+ influence over any decisions by the University of Connecticut to enter into any
88
+ arrangement or agreement with any Berkshire Competitor.
89
+ - source_sentence: 'Hashing: Is it applied to ANDROID_ID?'
90
+ sentences:
91
+ - Information associated with users is collected from cookies and similar technologies
92
+ such as digital identifiers, log files, web beacons, and plugins ("Cookies"),
93
+ which store certain information from user devices, allowing us to understand and
94
+ save preferences for future visits and to compile aggregate data about site traffic
95
+ and site interaction. If a user provides Received Information to us, then this
96
+ Received Information may be linked to data stored in Cookies.
97
+ - To the extent that the Parties have jointly developed any New Amorphous Alloy
98
+ Technology and they have agreed that such New Amorphous Alloy Technology will
99
+ be jointly owned, as set forth in Section 8.2 above, each Party hereby assigns
100
+ to the other, and will cause its employees, contractors, representatives, successors,
101
+ assigns, Affiliates, parents, subsidiaries, officers and directors to assign to
102
+ the other, a co-equal right, title and interest in and to any such jointly developed
103
+ New Amorphous Alloy Technology. T
104
+ - 'The analytics software may provide information about how you use your mobile
105
+ applications as well as how applications are performing across different handsets.
106
+ The third parties obtain this information as a result of data being sent to their
107
+ servers from our software "agent" if embedded in your mobile application. The
108
+ data collected by the agent may include: agent version, platform, SDK version,
109
+ timestamp, API key (identifier for application), application version, device identifier,
110
+ iOS Identifier for Advertising, iOS Identifier for Vendors, Media Access Control
111
+ (MAC) address, International Mobile Equipment Identity (IMEI), Model, manufacture
112
+ and OS version of device, session start/stop time, locale (specific location where
113
+ a given language is spoken), time zone, and network status (WiFi, etc.). It hashes
114
+ iOS device identifiers, MAC address and IMEI; however, we do not hash platform
115
+ device identifiers such as the iOS Identifier for Advertising, ANDROID_ID and
116
+ the BB_PIN. Hashing involves the transformation of these identifiers into a value
117
+ or key that represents the original identifier. The device identifiers (if applicable),
118
+ IMEI (if applicable), MAC address (if applicable), and platform are hashed to
119
+ a third party ID.'
120
+ - source_sentence: f"What constitutes 'Received Information' as defined in this contract?"
121
+ sentences:
122
+ - '"Effective Date" means the date as of which the last signature of a Party is
123
+ affixed hereto.'
124
+ - '"Received Information" means a user''s private, personal or personally identifying
125
+ or identifiable data or information, including content and contact information
126
+ such as name, email address, or social network identifier.'
127
+ - 'B. HOW WE USE COLLECTED INFORMATION a. Any of the information (Personal and Non-personal)
128
+ we collect from you may be used in one of the following ways: To personalize user
129
+ experience- We may use Information to understand demographics, customer interest,
130
+ and other trends among our Users;'
131
+ - source_sentence: What steps must precede mediation?
132
+ sentences:
133
+ - In case OntoChem finds a novel and unexpected antiviral use of those Rejected
134
+ Hit Compounds during this 2-years period, it will notify Anixa about these findings
135
+ and Anixa has the right of first negotiation during a period of 6 months after
136
+ this notification.
137
+ - '11. Dispute Resolution. a. Negotiation. If a Party believes that the other Party
138
+ has breached this Agreement or if there is a dispute between the Parties over
139
+ the interpretation of this Agreement (a "Dispute"), the Parties will endeavor
140
+ to resolve the Dispute through good faith negotiation for a period of thirty (30)
141
+ days after a Party notifies the other Party of the Dispute and before either Party
142
+ requests mediation or files litigation to resolve the Dispute. b. Mediation. If
143
+ the Parties have been unable to resolve a Dispute through good faith negotiation
144
+ as provided in the prior Subsection, a Party may request that the Parties attempt
145
+ to resolve the Dispute through mediation by notifying the other Party with a copy
146
+ to JAMS. The Parties will attempt to select a mutually acceptable JAMS mediator
147
+ within ten (10) days of the notice requesting mediation. The mediation will be
148
+ held in Lake County or Cook County, Illinois within thirty (30) days of the notice
149
+ requesting mediation before a JAMS mediator and in compliance with JAMS mediation
150
+ guidelines. Each party will bear its own costs in preparing for and participating
151
+ in the mediation and one-half of the fees and expenses charged by JAMS for conducting
152
+ the mediation. c. Litigation. If the Parties have been unable to resolve a Dispute
153
+ through mediation as provided in the prior Subsection, a Party may file litigation
154
+ against the other Party in a court of competent jurisdiction in the United States
155
+ of America. With respect to litigation involving only the Parties or their Affiliates,
156
+ the Parties irrevocably consent to the exclusive personal jurisdiction and venue
157
+ of the U.S. federal and Illinois state courts of competent subject matter jurisdiction
158
+ located in Lake County, Illinois or Cook County, Illinois and their respective
159
+ higher courts of appeal for the limited purpose of resolving a Dispute, and the
160
+ Parties waive, to the fullest extent permitted by law, any defense of inconvenient
161
+ forum. The Parties waive any right to trial by jury as to any Disputes resolved
162
+ through litigation. Notwithstanding the foregoing, a Party may file litigation
163
+ to resolve a Dispute without undergoing either negotiation or mediation as provided
164
+ in the prior Subsections for any Dispute involving: (i) infringement on intellectual
165
+ property; (ii) the unauthorized use or disclosure of Confidential Information;
166
+ or (iii) a request for a temporary restraining order, a preliminary or permanent
167
+ injunction or any other type of equitable relief. d. Remedies. Except as expressly
168
+ limited in the preceding Subsections and the other provisions in this Agreement,
169
+ a Party may immediately exercise any rights and remedies available to the Party
170
+ under Applicable Law upon a breach of this Agreement by the other Party. A Party
171
+ will not suspend performance under or terminate this Agreement or any accepted
172
+ purchase order for a product being purchased and sold under this Agreement unless:
173
+ (1) the other Party is in material breach of this Agreement and has either refused
174
+ to cure the material breach or has failed to cure the material breach within thirty
175
+ (30) day of its receipt of written notice of the failure; and (2) the Parties
176
+ have been unable to resolve the Dispute related to the material breach through
177
+ negotiation or mediation, or the breaching Party has refused or failed to attempt
178
+ to resolve the Dispute through negotiation or mediation, as provided in this Section.
179
+ Notwithstanding the foregoing, a Party may suspend performance or terminate this
180
+ Agreement or any accepted purchase order for a product being purchase and sold
181
+ under this Agreement immediately on written notice to the other Party, and without
182
+ providing the other Party an opportunity to cure the material breach or attempting
183
+ to resolve a Dispute over the material breach by negotiation or mediation as provided
184
+ in this Section, for a material breach by the other Party involving substantial
185
+ harm to the reputation, goodwill and business of the non-breaching Party that
186
+ cannot reasonably be avoided or fully redressed by providing the other Party an
187
+ opportunity to cure the material breach. e. Late Fees and Collection Costs. If
188
+ Buyer fails to pay Seller an amount owed under this Agreement by the invoice due
189
+ date, then Buyer will owe Seller: (i) the delinquent amount; and (ii) a late payment
190
+ fee equal to two percent (2%) of the delinquent amount for each full or partial
191
+ calendar month past the invoice due date that the delinquent amount remains unpaid.
192
+ In addition, if Seller has to file
193
+
194
+
195
+ Source: REYNOLDS CONSUMER PRODUCTS INC., S-1, 11/15/2019
196
+
197
+
198
+
199
+
200
+
201
+
202
+ litigation to collect the amount owed and Seller prevails in the litigation, Buyer
203
+ will reimburse Seller for actual, reasonable, substantiated out-of-pocket expenses
204
+ incurred by Seller in collecting the delinquent amount and accrued late payment
205
+ fees on the delinquent amount. Under no circumstance will the late payment fee
206
+ payable to Seller exceed the amount that a creditor may lawfully impose on a debtor
207
+ on a delinquent amount under Applicable Law.'
208
+ - Third Party, Services, Ads and Analytics Ad companies may use and collect anonymous
209
+ data about your interests to customize content and advertising here and in other
210
+ sites and applications. Interest and location data may be linked to your device,
211
+ but is not linked to your identity. Analytics companies may access anonymous data
212
+ (such as your IP address or device ID) to help us understand how our services
213
+ are used. They use this data solely on our behalf. They do not share it except
214
+ in aggregate form; no data is shared as to any individual user.
215
+ model-index:
216
+ - name: SentenceTransformer based on sentence-transformers/multi-qa-mpnet-base-cos-v1
217
+ results:
218
+ - task:
219
+ type: information-retrieval
220
+ name: Information Retrieval
221
+ dataset:
222
+ name: multi qa mpnet base cos v1
223
+ type: multi-qa-mpnet-base-cos-v1
224
+ metrics:
225
+ - type: cosine_accuracy@1
226
+ value: 0.5675880348352896
227
+ name: Cosine Accuracy@1
228
+ - type: cosine_accuracy@3
229
+ value: 0.7251041272245362
230
+ name: Cosine Accuracy@3
231
+ - type: cosine_accuracy@5
232
+ value: 0.7890950397576676
233
+ name: Cosine Accuracy@5
234
+ - type: cosine_accuracy@10
235
+ value: 0.8458917076864824
236
+ name: Cosine Accuracy@10
237
+ - type: cosine_precision@1
238
+ value: 0.5675880348352896
239
+ name: Cosine Precision@1
240
+ - type: cosine_precision@3
241
+ value: 0.24170137574151201
242
+ name: Cosine Precision@3
243
+ - type: cosine_precision@5
244
+ value: 0.1578190079515335
245
+ name: Cosine Precision@5
246
+ - type: cosine_precision@10
247
+ value: 0.08458917076864823
248
+ name: Cosine Precision@10
249
+ - type: cosine_recall@1
250
+ value: 0.5675880348352896
251
+ name: Cosine Recall@1
252
+ - type: cosine_recall@3
253
+ value: 0.7251041272245362
254
+ name: Cosine Recall@3
255
+ - type: cosine_recall@5
256
+ value: 0.7890950397576676
257
+ name: Cosine Recall@5
258
+ - type: cosine_recall@10
259
+ value: 0.8458917076864824
260
+ name: Cosine Recall@10
261
+ - type: cosine_ndcg@10
262
+ value: 0.7056724990427845
263
+ name: Cosine Ndcg@10
264
+ - type: cosine_mrr@10
265
+ value: 0.6608194647289684
266
+ name: Cosine Mrr@10
267
+ - type: cosine_map@100
268
+ value: 0.6658281637529629
269
+ name: Cosine Map@100
270
+ - type: dot_accuracy@1
271
+ value: 0.5675880348352896
272
+ name: Dot Accuracy@1
273
+ - type: dot_accuracy@3
274
+ value: 0.7251041272245362
275
+ name: Dot Accuracy@3
276
+ - type: dot_accuracy@5
277
+ value: 0.7890950397576676
278
+ name: Dot Accuracy@5
279
+ - type: dot_accuracy@10
280
+ value: 0.8458917076864824
281
+ name: Dot Accuracy@10
282
+ - type: dot_precision@1
283
+ value: 0.5675880348352896
284
+ name: Dot Precision@1
285
+ - type: dot_precision@3
286
+ value: 0.24170137574151201
287
+ name: Dot Precision@3
288
+ - type: dot_precision@5
289
+ value: 0.1578190079515335
290
+ name: Dot Precision@5
291
+ - type: dot_precision@10
292
+ value: 0.08458917076864823
293
+ name: Dot Precision@10
294
+ - type: dot_recall@1
295
+ value: 0.5675880348352896
296
+ name: Dot Recall@1
297
+ - type: dot_recall@3
298
+ value: 0.7251041272245362
299
+ name: Dot Recall@3
300
+ - type: dot_recall@5
301
+ value: 0.7890950397576676
302
+ name: Dot Recall@5
303
+ - type: dot_recall@10
304
+ value: 0.8458917076864824
305
+ name: Dot Recall@10
306
+ - type: dot_ndcg@10
307
+ value: 0.7056724990427845
308
+ name: Dot Ndcg@10
309
+ - type: dot_mrr@10
310
+ value: 0.6608194647289684
311
+ name: Dot Mrr@10
312
+ - type: dot_map@100
313
+ value: 0.6658281637529629
314
+ name: Dot Map@100
315
+ ---
316
+
317
+ # SentenceTransformer based on sentence-transformers/multi-qa-mpnet-base-cos-v1
318
+
319
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/multi-qa-mpnet-base-cos-v1](https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-cos-v1). 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.
320
+
321
+ ## Model Details
322
+
323
+ ### Model Description
324
+ - **Model Type:** Sentence Transformer
325
+ - **Base model:** [sentence-transformers/multi-qa-mpnet-base-cos-v1](https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-cos-v1) <!-- at revision 892b36c151c41db91e84d97d9274bf8cf1227dc0 -->
326
+ - **Maximum Sequence Length:** 512 tokens
327
+ - **Output Dimensionality:** 768 tokens
328
+ - **Similarity Function:** Cosine Similarity
329
+ <!-- - **Training Dataset:** Unknown -->
330
+ <!-- - **Language:** Unknown -->
331
+ <!-- - **License:** Unknown -->
332
+
333
+ ### Model Sources
334
+
335
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
336
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
337
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
338
+
339
+ ### Full Model Architecture
340
+
341
+ ```
342
+ SentenceTransformer(
343
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
344
+ (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})
345
+ (2): Normalize()
346
+ )
347
+ ```
348
+
349
+ ## Usage
350
+
351
+ ### Direct Usage (Sentence Transformers)
352
+
353
+ First install the Sentence Transformers library:
354
+
355
+ ```bash
356
+ pip install -U sentence-transformers
357
+ ```
358
+
359
+ Then you can load this model and run inference.
360
+ ```python
361
+ from sentence_transformers import SentenceTransformer
362
+
363
+ # Download from the 🤗 Hub
364
+ model = SentenceTransformer("kperkins411/multi-qa-mpnet-base-cos-v1_MultipleNegativesRankingLoss")
365
+ # Run inference
366
+ sentences = [
367
+ 'What steps must precede mediation?',
368
+ '11. Dispute Resolution. a. Negotiation. If a Party believes that the other Party has breached this Agreement or if there is a dispute between the Parties over the interpretation of this Agreement (a "Dispute"), the Parties will endeavor to resolve the Dispute through good faith negotiation for a period of thirty (30) days after a Party notifies the other Party of the Dispute and before either Party requests mediation or files litigation to resolve the Dispute. b. Mediation. If the Parties have been unable to resolve a Dispute through good faith negotiation as provided in the prior Subsection, a Party may request that the Parties attempt to resolve the Dispute through mediation by notifying the other Party with a copy to JAMS. The Parties will attempt to select a mutually acceptable JAMS mediator within ten (10) days of the notice requesting mediation. The mediation will be held in Lake County or Cook County, Illinois within thirty (30) days of the notice requesting mediation before a JAMS mediator and in compliance with JAMS mediation guidelines. Each party will bear its own costs in preparing for and participating in the mediation and one-half of the fees and expenses charged by JAMS for conducting the mediation. c. Litigation. If the Parties have been unable to resolve a Dispute through mediation as provided in the prior Subsection, a Party may file litigation against the other Party in a court of competent jurisdiction in the United States of America. With respect to litigation involving only the Parties or their Affiliates, the Parties irrevocably consent to the exclusive personal jurisdiction and venue of the U.S. federal and Illinois state courts of competent subject matter jurisdiction located in Lake County, Illinois or Cook County, Illinois and their respective higher courts of appeal for the limited purpose of resolving a Dispute, and the Parties waive, to the fullest extent permitted by law, any defense of inconvenient forum. The Parties waive any right to trial by jury as to any Disputes resolved through litigation. Notwithstanding the foregoing, a Party may file litigation to resolve a Dispute without undergoing either negotiation or mediation as provided in the prior Subsections for any Dispute involving: (i) infringement on intellectual property; (ii) the unauthorized use or disclosure of Confidential Information; or (iii) a request for a temporary restraining order, a preliminary or permanent injunction or any other type of equitable relief. d. Remedies. Except as expressly limited in the preceding Subsections and the other provisions in this Agreement, a Party may immediately exercise any rights and remedies available to the Party under Applicable Law upon a breach of this Agreement by the other Party. A Party will not suspend performance under or terminate this Agreement or any accepted purchase order for a product being purchased and sold under this Agreement unless: (1) the other Party is in material breach of this Agreement and has either refused to cure the material breach or has failed to cure the material breach within thirty (30) day of its receipt of written notice of the failure; and (2) the Parties have been unable to resolve the Dispute related to the material breach through negotiation or mediation, or the breaching Party has refused or failed to attempt to resolve the Dispute through negotiation or mediation, as provided in this Section. Notwithstanding the foregoing, a Party may suspend performance or terminate this Agreement or any accepted purchase order for a product being purchase and sold under this Agreement immediately on written notice to the other Party, and without providing the other Party an opportunity to cure the material breach or attempting to resolve a Dispute over the material breach by negotiation or mediation as provided in this Section, for a material breach by the other Party involving substantial harm to the reputation, goodwill and business of the non-breaching Party that cannot reasonably be avoided or fully redressed by providing the other Party an opportunity to cure the material breach. e. Late Fees and Collection Costs. If Buyer fails to pay Seller an amount owed under this Agreement by the invoice due date, then Buyer will owe Seller: (i) the delinquent amount; and (ii) a late payment fee equal to two percent (2%) of the delinquent amount for each full or partial calendar month past the invoice due date that the delinquent amount remains unpaid. In addition, if Seller has to file\n\nSource: REYNOLDS CONSUMER PRODUCTS INC., S-1, 11/15/2019\n\n\n\n\n\nlitigation to collect the amount owed and Seller prevails in the litigation, Buyer will reimburse Seller for actual, reasonable, substantiated out-of-pocket expenses incurred by Seller in collecting the delinquent amount and accrued late payment fees on the delinquent amount. Under no circumstance will the late payment fee payable to Seller exceed the amount that a creditor may lawfully impose on a debtor on a delinquent amount under Applicable Law.',
369
+ 'In case OntoChem finds a novel and unexpected antiviral use of those Rejected Hit Compounds during this 2-years period, it will notify Anixa about these findings and Anixa has the right of first negotiation during a period of 6 months after this notification.',
370
+ ]
371
+ embeddings = model.encode(sentences)
372
+ print(embeddings.shape)
373
+ # [3, 768]
374
+
375
+ # Get the similarity scores for the embeddings
376
+ similarities = model.similarity(embeddings, embeddings)
377
+ print(similarities.shape)
378
+ # [3, 3]
379
+ ```
380
+
381
+ <!--
382
+ ### Direct Usage (Transformers)
383
+
384
+ <details><summary>Click to see the direct usage in Transformers</summary>
385
+
386
+ </details>
387
+ -->
388
+
389
+ <!--
390
+ ### Downstream Usage (Sentence Transformers)
391
+
392
+ You can finetune this model on your own dataset.
393
+
394
+ <details><summary>Click to expand</summary>
395
+
396
+ </details>
397
+ -->
398
+
399
+ <!--
400
+ ### Out-of-Scope Use
401
+
402
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
403
+ -->
404
+
405
+ ## Evaluation
406
+
407
+ ### Metrics
408
+
409
+ #### Information Retrieval
410
+ * Dataset: `multi-qa-mpnet-base-cos-v1`
411
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
412
+
413
+ | Metric | Value |
414
+ |:--------------------|:-----------|
415
+ | cosine_accuracy@1 | 0.5676 |
416
+ | cosine_accuracy@3 | 0.7251 |
417
+ | cosine_accuracy@5 | 0.7891 |
418
+ | cosine_accuracy@10 | 0.8459 |
419
+ | cosine_precision@1 | 0.5676 |
420
+ | cosine_precision@3 | 0.2417 |
421
+ | cosine_precision@5 | 0.1578 |
422
+ | cosine_precision@10 | 0.0846 |
423
+ | cosine_recall@1 | 0.5676 |
424
+ | cosine_recall@3 | 0.7251 |
425
+ | cosine_recall@5 | 0.7891 |
426
+ | cosine_recall@10 | 0.8459 |
427
+ | cosine_ndcg@10 | 0.7057 |
428
+ | cosine_mrr@10 | 0.6608 |
429
+ | **cosine_map@100** | **0.6658** |
430
+ | dot_accuracy@1 | 0.5676 |
431
+ | dot_accuracy@3 | 0.7251 |
432
+ | dot_accuracy@5 | 0.7891 |
433
+ | dot_accuracy@10 | 0.8459 |
434
+ | dot_precision@1 | 0.5676 |
435
+ | dot_precision@3 | 0.2417 |
436
+ | dot_precision@5 | 0.1578 |
437
+ | dot_precision@10 | 0.0846 |
438
+ | dot_recall@1 | 0.5676 |
439
+ | dot_recall@3 | 0.7251 |
440
+ | dot_recall@5 | 0.7891 |
441
+ | dot_recall@10 | 0.8459 |
442
+ | dot_ndcg@10 | 0.7057 |
443
+ | dot_mrr@10 | 0.6608 |
444
+ | dot_map@100 | 0.6658 |
445
+
446
+ <!--
447
+ ## Bias, Risks and Limitations
448
+
449
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
450
+ -->
451
+
452
+ <!--
453
+ ### Recommendations
454
+
455
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
456
+ -->
457
+
458
+ ## Training Details
459
+
460
+ ### Training Dataset
461
+
462
+ #### Unnamed Dataset
463
+
464
+
465
+ * Size: 491,850 training samples
466
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
467
+ * Approximate statistics based on the first 1000 samples:
468
+ | | anchor | positive | negative |
469
+ |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
470
+ | type | string | string | string |
471
+ | details | <ul><li>min: 7 tokens</li><li>mean: 17.09 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 102.69 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 103.91 tokens</li><li>max: 512 tokens</li></ul> |
472
+ * Samples:
473
+ | anchor | positive | negative |
474
+ |:--------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
475
+ | <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> | <code>Use of cookies and other technology to collect information.</code> |
476
+ | <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> | <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> |
477
+ | <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> | <code>You also may be able to link an account from a social networking service (e.g., Facebook, Google+, Yahoo!) to an account through our Services. This may allow you to use your credentials from the other site or service to sign in to certain features on our Services. If you link your account from a third-party site or service, we may collect information from those third-party accounts, and any information that we collect will be governed by this Privacy Policy.</code> |
478
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
479
+ ```json
480
+ {
481
+ "scale": 20.0,
482
+ "similarity_fct": "cos_sim"
483
+ }
484
+ ```
485
+
486
+ ### Evaluation Dataset
487
+
488
+ #### Unnamed Dataset
489
+
490
+
491
+ * Size: 6,000 evaluation samples
492
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
493
+ * Approximate statistics based on the first 1000 samples:
494
+ | | anchor | positive | negative |
495
+ |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
496
+ | type | string | string | string |
497
+ | details | <ul><li>min: 8 tokens</li><li>mean: 23.16 tokens</li><li>max: 124 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 96.66 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 102.41 tokens</li><li>max: 512 tokens</li></ul> |
498
+ * Samples:
499
+ | anchor | positive | negative |
500
+ |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
501
+ | <code>What term is used to describe sensitive materials unique to the involved entities and not accessible by the general populace, regardless of its physical state or the manner of its revelation?</code> | <code>For purposes of this Agreement, "Confidential Information" means any data or information that is proprietary to the Parties and not generally known to the public, whether in tangible or intangible form, whenever and however disclosed, including but not limited to:</code> | <code>6.1 In this Agreement, "Confidential Information" means information disclosed by (or on behalf of) one party to the other party under this Agreement that is marked as confidential or, from its nature, content or the circumstances in which it is disclosed, might reasonably be supposed to be confidential, including the terms and conditions (including the Exhibits) of this Agreement. It does not include information that the recipient already knew, that becomes public through no fault of the recipient, that was independently developed by the recipient or that was lawfully given to the recipient by a third party.</code> |
502
+ | <code>What term is used to describe sensitive materials unique to the involved entities and not accessible by the general populace, regardless of its physical state or the manner of its revelation?</code> | <code>For purposes of this Agreement, "Confidential Information" means any data or information that is proprietary to the Parties and not generally known to the public, whether in tangible or intangible form, whenever and however disclosed, including but not limited to:</code> | <code>1. “Confidential Information” shall mean the Purpose (including the contemplated transaction), identity of, and any discussions or negotiations between, the Parties, existence of this Agreement, and any and all information whether in oral, written, graphic or electronic form, including but not limited to, data, know-how and any and all subject matter (whether patentable or not, including without limitation any derivatives thereof) pertaining to Verenium’s research, financial data, sales information, inventions, development, materials, technology, trade secrets, work in process, marketing, business plans, regulatory information and strategies, scientific, engineering and/or manufacturing processes or equipment, protocols, assays, strains, compounds, genes, gene pathways, enzymes, peptides, the commercial applications of genes, gene pathways, enzymes, peptides, accessing microbial diversity, manipulating and modifying genes and gene pathways, identifying bioactive compounds through recombinant techniques and any other elements of Verenium’s business which Verenium considers to be of value, including its present or future products, projections, sales, pricing, customers, employees, investors and contractual relationships.</code> |
503
+ | <code>What term is used to describe sensitive materials unique to the involved entities and not accessible by the general populace, regardless of its physical state or the manner of its revelation?</code> | <code>For purposes of this Agreement, "Confidential Information" means any data or information that is proprietary to the Parties and not generally known to the public, whether in tangible or intangible form, whenever and however disclosed, including but not limited to:</code> | <code>Confidential Information means any information disclosed by one party (the ‘Discloser’) to the other (the ‘Recipient’) relating directly or indirectly to Name of Technology/Project, file # which is identified by the Discloser, either orally or in writing, as confidential, either at the time of disclosure or, if disclosed orally, confirmed in writing within thirty (30) days following the original disclosure.</code> |
504
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
505
+ ```json
506
+ {
507
+ "scale": 20.0,
508
+ "similarity_fct": "cos_sim"
509
+ }
510
+ ```
511
+
512
+ ### Training Hyperparameters
513
+ #### Non-Default Hyperparameters
514
+
515
+ - `eval_strategy`: epoch
516
+ - `per_device_train_batch_size`: 32
517
+ - `per_device_eval_batch_size`: 32
518
+ - `learning_rate`: 2e-05
519
+ - `num_train_epochs`: 2
520
+ - `warmup_ratio`: 0.1
521
+ - `fp16`: True
522
+ - `load_best_model_at_end`: True
523
+
524
+ #### All Hyperparameters
525
+ <details><summary>Click to expand</summary>
526
+
527
+ - `overwrite_output_dir`: False
528
+ - `do_predict`: False
529
+ - `eval_strategy`: epoch
530
+ - `prediction_loss_only`: True
531
+ - `per_device_train_batch_size`: 32
532
+ - `per_device_eval_batch_size`: 32
533
+ - `per_gpu_train_batch_size`: None
534
+ - `per_gpu_eval_batch_size`: None
535
+ - `gradient_accumulation_steps`: 1
536
+ - `eval_accumulation_steps`: None
537
+ - `learning_rate`: 2e-05
538
+ - `weight_decay`: 0.0
539
+ - `adam_beta1`: 0.9
540
+ - `adam_beta2`: 0.999
541
+ - `adam_epsilon`: 1e-08
542
+ - `max_grad_norm`: 1.0
543
+ - `num_train_epochs`: 2
544
+ - `max_steps`: -1
545
+ - `lr_scheduler_type`: linear
546
+ - `lr_scheduler_kwargs`: {}
547
+ - `warmup_ratio`: 0.1
548
+ - `warmup_steps`: 0
549
+ - `log_level`: passive
550
+ - `log_level_replica`: warning
551
+ - `log_on_each_node`: True
552
+ - `logging_nan_inf_filter`: True
553
+ - `save_safetensors`: True
554
+ - `save_on_each_node`: False
555
+ - `save_only_model`: False
556
+ - `restore_callback_states_from_checkpoint`: False
557
+ - `no_cuda`: False
558
+ - `use_cpu`: False
559
+ - `use_mps_device`: False
560
+ - `seed`: 42
561
+ - `data_seed`: None
562
+ - `jit_mode_eval`: False
563
+ - `use_ipex`: False
564
+ - `bf16`: False
565
+ - `fp16`: True
566
+ - `fp16_opt_level`: O1
567
+ - `half_precision_backend`: auto
568
+ - `bf16_full_eval`: False
569
+ - `fp16_full_eval`: False
570
+ - `tf32`: None
571
+ - `local_rank`: 0
572
+ - `ddp_backend`: None
573
+ - `tpu_num_cores`: None
574
+ - `tpu_metrics_debug`: False
575
+ - `debug`: []
576
+ - `dataloader_drop_last`: False
577
+ - `dataloader_num_workers`: 0
578
+ - `dataloader_prefetch_factor`: None
579
+ - `past_index`: -1
580
+ - `disable_tqdm`: False
581
+ - `remove_unused_columns`: True
582
+ - `label_names`: None
583
+ - `load_best_model_at_end`: True
584
+ - `ignore_data_skip`: False
585
+ - `fsdp`: []
586
+ - `fsdp_min_num_params`: 0
587
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
588
+ - `fsdp_transformer_layer_cls_to_wrap`: None
589
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
590
+ - `deepspeed`: None
591
+ - `label_smoothing_factor`: 0.0
592
+ - `optim`: adamw_torch
593
+ - `optim_args`: None
594
+ - `adafactor`: False
595
+ - `group_by_length`: False
596
+ - `length_column_name`: length
597
+ - `ddp_find_unused_parameters`: None
598
+ - `ddp_bucket_cap_mb`: None
599
+ - `ddp_broadcast_buffers`: False
600
+ - `dataloader_pin_memory`: True
601
+ - `dataloader_persistent_workers`: False
602
+ - `skip_memory_metrics`: True
603
+ - `use_legacy_prediction_loop`: False
604
+ - `push_to_hub`: False
605
+ - `resume_from_checkpoint`: None
606
+ - `hub_model_id`: None
607
+ - `hub_strategy`: every_save
608
+ - `hub_private_repo`: False
609
+ - `hub_always_push`: False
610
+ - `gradient_checkpointing`: False
611
+ - `gradient_checkpointing_kwargs`: None
612
+ - `include_inputs_for_metrics`: False
613
+ - `eval_do_concat_batches`: True
614
+ - `fp16_backend`: auto
615
+ - `push_to_hub_model_id`: None
616
+ - `push_to_hub_organization`: None
617
+ - `mp_parameters`:
618
+ - `auto_find_batch_size`: False
619
+ - `full_determinism`: False
620
+ - `torchdynamo`: None
621
+ - `ray_scope`: last
622
+ - `ddp_timeout`: 1800
623
+ - `torch_compile`: False
624
+ - `torch_compile_backend`: None
625
+ - `torch_compile_mode`: None
626
+ - `dispatch_batches`: None
627
+ - `split_batches`: None
628
+ - `include_tokens_per_second`: False
629
+ - `include_num_input_tokens_seen`: False
630
+ - `neftune_noise_alpha`: None
631
+ - `optim_target_modules`: None
632
+ - `batch_eval_metrics`: False
633
+ - `batch_sampler`: batch_sampler
634
+ - `multi_dataset_batch_sampler`: proportional
635
+
636
+ </details>
637
+
638
+ ### Training Logs
639
+ <details><summary>Click to expand</summary>
640
+
641
+ | Epoch | Step | Training Loss | loss | multi-qa-mpnet-base-cos-v1_cosine_map@100 |
642
+ |:-------:|:---------:|:-------------:|:---------:|:-----------------------------------------:|
643
+ | 0 | 0 | - | - | 0.4784 |
644
+ | 0.0065 | 100 | 0.9364 | - | - |
645
+ | 0.0130 | 200 | 0.8395 | - | - |
646
+ | 0.0195 | 300 | 0.7295 | - | - |
647
+ | 0.0260 | 400 | 0.7025 | - | - |
648
+ | 0.0325 | 500 | 0.6212 | - | - |
649
+ | 0.0390 | 600 | 0.6038 | - | - |
650
+ | 0.0455 | 700 | 0.5723 | - | - |
651
+ | 0.0520 | 800 | 0.552 | - | - |
652
+ | 0.0586 | 900 | 0.5407 | - | - |
653
+ | 0.0651 | 1000 | 0.5332 | - | - |
654
+ | 0.0716 | 1100 | 0.4981 | - | - |
655
+ | 0.0781 | 1200 | 0.4671 | - | - |
656
+ | 0.0846 | 1300 | 0.4756 | - | - |
657
+ | 0.0911 | 1400 | 0.4461 | - | - |
658
+ | 0.0976 | 1500 | 0.4425 | - | - |
659
+ | 0.1041 | 1600 | 0.4329 | - | - |
660
+ | 0.1106 | 1700 | 0.4412 | - | - |
661
+ | 0.1171 | 1800 | 0.3952 | - | - |
662
+ | 0.1236 | 1900 | 0.4179 | - | - |
663
+ | 0.1301 | 2000 | 0.4157 | - | - |
664
+ | 0.1366 | 2100 | 0.4014 | - | - |
665
+ | 0.1431 | 2200 | 0.3747 | - | - |
666
+ | 0.1496 | 2300 | 0.3596 | - | - |
667
+ | 0.1561 | 2400 | 0.3571 | - | - |
668
+ | 0.1626 | 2500 | 0.3717 | - | - |
669
+ | 0.1691 | 2600 | 0.3369 | - | - |
670
+ | 0.1757 | 2700 | 0.3508 | - | - |
671
+ | 0.1822 | 2800 | 0.3281 | - | - |
672
+ | 0.1887 | 2900 | 0.3285 | - | - |
673
+ | 0.1952 | 3000 | 0.3423 | - | - |
674
+ | 0.2017 | 3100 | 0.2967 | - | - |
675
+ | 0.2082 | 3200 | 0.3076 | - | - |
676
+ | 0.2147 | 3300 | 0.3223 | - | - |
677
+ | 0.2212 | 3400 | 0.3097 | - | - |
678
+ | 0.2277 | 3500 | 0.2964 | - | - |
679
+ | 0.2342 | 3600 | 0.2836 | - | - |
680
+ | 0.2407 | 3700 | 0.3007 | - | - |
681
+ | 0.2472 | 3800 | 0.2882 | - | - |
682
+ | 0.2537 | 3900 | 0.2852 | - | - |
683
+ | 0.2602 | 4000 | 0.2923 | - | - |
684
+ | 0.2667 | 4100 | 0.2938 | - | - |
685
+ | 0.2732 | 4200 | 0.2597 | - | - |
686
+ | 0.2797 | 4300 | 0.2423 | - | - |
687
+ | 0.2863 | 4400 | 0.2719 | - | - |
688
+ | 0.2928 | 4500 | 0.2546 | - | - |
689
+ | 0.2993 | 4600 | 0.2545 | - | - |
690
+ | 0.3058 | 4700 | 0.2538 | - | - |
691
+ | 0.3123 | 4800 | 0.249 | - | - |
692
+ | 0.3188 | 4900 | 0.2473 | - | - |
693
+ | 0.3253 | 5000 | 0.2398 | - | - |
694
+ | 0.3318 | 5100 | 0.254 | - | - |
695
+ | 0.3383 | 5200 | 0.2399 | - | - |
696
+ | 0.3448 | 5300 | 0.2367 | - | - |
697
+ | 0.3513 | 5400 | 0.2208 | - | - |
698
+ | 0.3578 | 5500 | 0.2201 | - | - |
699
+ | 0.3643 | 5600 | 0.2384 | - | - |
700
+ | 0.3708 | 5700 | 0.2166 | - | - |
701
+ | 0.3773 | 5800 | 0.1949 | - | - |
702
+ | 0.3838 | 5900 | 0.2127 | - | - |
703
+ | 0.3903 | 6000 | 0.2032 | - | - |
704
+ | 0.3969 | 6100 | 0.2073 | - | - |
705
+ | 0.4034 | 6200 | 0.2124 | - | - |
706
+ | 0.4099 | 6300 | 0.1963 | - | - |
707
+ | 0.4164 | 6400 | 0.1965 | - | - |
708
+ | 0.4229 | 6500 | 0.2088 | - | - |
709
+ | 0.4294 | 6600 | 0.2079 | - | - |
710
+ | 0.4359 | 6700 | 0.1902 | - | - |
711
+ | 0.4424 | 6800 | 0.1785 | - | - |
712
+ | 0.4489 | 6900 | 0.2063 | - | - |
713
+ | 0.4554 | 7000 | 0.1781 | - | - |
714
+ | 0.4619 | 7100 | 0.172 | - | - |
715
+ | 0.4684 | 7200 | 0.1733 | - | - |
716
+ | 0.4749 | 7300 | 0.192 | - | - |
717
+ | 0.4814 | 7400 | 0.195 | - | - |
718
+ | 0.4879 | 7500 | 0.1926 | - | - |
719
+ | 0.4944 | 7600 | 0.1754 | - | - |
720
+ | 0.5009 | 7700 | 0.1859 | - | - |
721
+ | 0.5074 | 7800 | 0.1779 | - | - |
722
+ | 0.5140 | 7900 | 0.1714 | - | - |
723
+ | 0.5205 | 8000 | 0.1639 | - | - |
724
+ | 0.5270 | 8100 | 0.1527 | - | - |
725
+ | 0.5335 | 8200 | 0.1695 | - | - |
726
+ | 0.5400 | 8300 | 0.1501 | - | - |
727
+ | 0.5465 | 8400 | 0.1636 | - | - |
728
+ | 0.5530 | 8500 | 0.166 | - | - |
729
+ | 0.5595 | 8600 | 0.1554 | - | - |
730
+ | 0.5660 | 8700 | 0.1571 | - | - |
731
+ | 0.5725 | 8800 | 0.1506 | - | - |
732
+ | 0.5790 | 8900 | 0.1504 | - | - |
733
+ | 0.5855 | 9000 | 0.1601 | - | - |
734
+ | 0.5920 | 9100 | 0.1413 | - | - |
735
+ | 0.5985 | 9200 | 0.15 | - | - |
736
+ | 0.6050 | 9300 | 0.1473 | - | - |
737
+ | 0.6115 | 9400 | 0.1509 | - | - |
738
+ | 0.6180 | 9500 | 0.1555 | - | - |
739
+ | 0.6246 | 9600 | 0.1477 | - | - |
740
+ | 0.6311 | 9700 | 0.1399 | - | - |
741
+ | 0.6376 | 9800 | 0.1422 | - | - |
742
+ | 0.6441 | 9900 | 0.1383 | - | - |
743
+ | 0.6506 | 10000 | 0.1299 | - | - |
744
+ | 0.6571 | 10100 | 0.1328 | - | - |
745
+ | 0.6636 | 10200 | 0.147 | - | - |
746
+ | 0.6701 | 10300 | 0.152 | - | - |
747
+ | 0.6766 | 10400 | 0.136 | - | - |
748
+ | 0.6831 | 10500 | 0.1409 | - | - |
749
+ | 0.6896 | 10600 | 0.1298 | - | - |
750
+ | 0.6961 | 10700 | 0.1359 | - | - |
751
+ | 0.7026 | 10800 | 0.137 | - | - |
752
+ | 0.7091 | 10900 | 0.1245 | - | - |
753
+ | 0.7156 | 11000 | 0.1303 | - | - |
754
+ | 0.7221 | 11100 | 0.1307 | - | - |
755
+ | 0.7286 | 11200 | 0.1171 | - | - |
756
+ | 0.7352 | 11300 | 0.1319 | - | - |
757
+ | 0.7417 | 11400 | 0.1296 | - | - |
758
+ | 0.7482 | 11500 | 0.1344 | - | - |
759
+ | 0.7547 | 11600 | 0.1195 | - | - |
760
+ | 0.7612 | 11700 | 0.1048 | - | - |
761
+ | 0.7677 | 11800 | 0.1242 | - | - |
762
+ | 0.7742 | 11900 | 0.1163 | - | - |
763
+ | 0.7807 | 12000 | 0.1253 | - | - |
764
+ | 0.7872 | 12100 | 0.1215 | - | - |
765
+ | 0.7937 | 12200 | 0.1092 | - | - |
766
+ | 0.8002 | 12300 | 0.1131 | - | - |
767
+ | 0.8067 | 12400 | 0.1155 | - | - |
768
+ | 0.8132 | 12500 | 0.1211 | - | - |
769
+ | 0.8197 | 12600 | 0.1235 | - | - |
770
+ | 0.8262 | 12700 | 0.1242 | - | - |
771
+ | 0.8327 | 12800 | 0.1068 | - | - |
772
+ | 0.8392 | 12900 | 0.1352 | - | - |
773
+ | 0.8457 | 13000 | 0.1156 | - | - |
774
+ | 0.8523 | 13100 | 0.129 | - | - |
775
+ | 0.8588 | 13200 | 0.1113 | - | - |
776
+ | 0.8653 | 13300 | 0.1165 | - | - |
777
+ | 0.8718 | 13400 | 0.1083 | - | - |
778
+ | 0.8783 | 13500 | 0.1081 | - | - |
779
+ | 0.8848 | 13600 | 0.105 | - | - |
780
+ | 0.8913 | 13700 | 0.1088 | - | - |
781
+ | 0.8978 | 13800 | 0.1067 | - | - |
782
+ | 0.9043 | 13900 | 0.1032 | - | - |
783
+ | 0.9108 | 14000 | 0.0989 | - | - |
784
+ | 0.9173 | 14100 | 0.1044 | - | - |
785
+ | 0.9238 | 14200 | 0.1032 | - | - |
786
+ | 0.9303 | 14300 | 0.108 | - | - |
787
+ | 0.9368 | 14400 | 0.0905 | - | - |
788
+ | 0.9433 | 14500 | 0.098 | - | - |
789
+ | 0.9498 | 14600 | 0.12 | - | - |
790
+ | 0.9563 | 14700 | 0.122 | - | - |
791
+ | 0.9629 | 14800 | 0.1011 | - | - |
792
+ | 0.9694 | 14900 | 0.0943 | - | - |
793
+ | 0.9759 | 15000 | 0.1031 | - | - |
794
+ | 0.9824 | 15100 | 0.1099 | - | - |
795
+ | 0.9889 | 15200 | 0.1034 | - | - |
796
+ | 0.9954 | 15300 | 0.0896 | - | - |
797
+ | **1.0** | **15371** | **-** | **0.441** | **-** |
798
+ | 1.0019 | 15400 | 0.0887 | - | - |
799
+ | 1.0084 | 15500 | 0.0958 | - | - |
800
+ | 1.0149 | 15600 | 0.0929 | - | - |
801
+ | 1.0214 | 15700 | 0.083 | - | - |
802
+ | 1.0279 | 15800 | 0.0897 | - | - |
803
+ | 1.0344 | 15900 | 0.0924 | - | - |
804
+ | 1.0409 | 16000 | 0.0897 | - | - |
805
+ | 1.0474 | 16100 | 0.0912 | - | - |
806
+ | 1.0539 | 16200 | 0.0912 | - | - |
807
+ | 1.0604 | 16300 | 0.0851 | - | - |
808
+ | 1.0669 | 16400 | 0.0779 | - | - |
809
+ | 1.0735 | 16500 | 0.0886 | - | - |
810
+ | 1.0800 | 16600 | 0.0876 | - | - |
811
+ | 1.0865 | 16700 | 0.0831 | - | - |
812
+ | 1.0930 | 16800 | 0.0858 | - | - |
813
+ | 1.0995 | 16900 | 0.0821 | - | - |
814
+ | 1.1060 | 17000 | 0.0835 | - | - |
815
+ | 1.1125 | 17100 | 0.0907 | - | - |
816
+ | 1.1190 | 17200 | 0.0764 | - | - |
817
+ | 1.1255 | 17300 | 0.0853 | - | - |
818
+ | 1.1320 | 17400 | 0.1002 | - | - |
819
+ | 1.1385 | 17500 | 0.0717 | - | - |
820
+ | 1.1450 | 17600 | 0.0926 | - | - |
821
+ | 1.1515 | 17700 | 0.0864 | - | - |
822
+ | 1.1580 | 17800 | 0.0758 | - | - |
823
+ | 1.1645 | 17900 | 0.0806 | - | - |
824
+ | 1.1710 | 18000 | 0.0866 | - | - |
825
+ | 1.1775 | 18100 | 0.0876 | - | - |
826
+ | 1.1840 | 18200 | 0.0905 | - | - |
827
+ | 1.1906 | 18300 | 0.0747 | - | - |
828
+ | 1.1971 | 18400 | 0.0731 | - | - |
829
+ | 1.2036 | 18500 | 0.0724 | - | - |
830
+ | 1.2101 | 18600 | 0.0835 | - | - |
831
+ | 1.2166 | 18700 | 0.0809 | - | - |
832
+ | 1.2231 | 18800 | 0.0722 | - | - |
833
+ | 1.2296 | 18900 | 0.0799 | - | - |
834
+ | 1.2361 | 19000 | 0.0675 | - | - |
835
+ | 1.2426 | 19100 | 0.0704 | - | - |
836
+ | 1.2491 | 19200 | 0.0749 | - | - |
837
+ | 1.2556 | 19300 | 0.0743 | - | - |
838
+ | 1.2621 | 19400 | 0.0798 | - | - |
839
+ | 1.2686 | 19500 | 0.0691 | - | - |
840
+ | 1.2751 | 19600 | 0.0782 | - | - |
841
+ | 1.2816 | 19700 | 0.0776 | - | - |
842
+ | 1.2881 | 19800 | 0.0807 | - | - |
843
+ | 1.2946 | 19900 | 0.0881 | - | - |
844
+ | 1.3012 | 20000 | 0.081 | - | - |
845
+ | 1.3077 | 20100 | 0.073 | - | - |
846
+ | 1.3142 | 20200 | 0.0758 | - | - |
847
+ | 1.3207 | 20300 | 0.0752 | - | - |
848
+ | 1.3272 | 20400 | 0.082 | - | - |
849
+ | 1.3337 | 20500 | 0.0763 | - | - |
850
+ | 1.3402 | 20600 | 0.0727 | - | - |
851
+ | 1.3467 | 20700 | 0.0793 | - | - |
852
+ | 1.3532 | 20800 | 0.0759 | - | - |
853
+ | 1.3597 | 20900 | 0.0666 | - | - |
854
+ | 1.3662 | 21000 | 0.0714 | - | - |
855
+ | 1.3727 | 21100 | 0.0636 | - | - |
856
+ | 1.3792 | 21200 | 0.0724 | - | - |
857
+ | 1.3857 | 21300 | 0.0703 | - | - |
858
+ | 1.3922 | 21400 | 0.0687 | - | - |
859
+ | 1.3987 | 21500 | 0.0748 | - | - |
860
+ | 1.4052 | 21600 | 0.0761 | - | - |
861
+ | 1.4117 | 21700 | 0.059 | - | - |
862
+ | 1.4183 | 21800 | 0.0717 | - | - |
863
+ | 1.4248 | 21900 | 0.0631 | - | - |
864
+ | 1.4313 | 22000 | 0.0591 | - | - |
865
+ | 1.4378 | 22100 | 0.0729 | - | - |
866
+ | 1.4443 | 22200 | 0.0825 | - | - |
867
+ | 1.4508 | 22300 | 0.0761 | - | - |
868
+ | 1.4573 | 22400 | 0.0734 | - | - |
869
+ | 1.4638 | 22500 | 0.0678 | - | - |
870
+ | 1.4703 | 22600 | 0.0674 | - | - |
871
+ | 1.4768 | 22700 | 0.0638 | - | - |
872
+ | 1.4833 | 22800 | 0.0763 | - | - |
873
+ | 1.4898 | 22900 | 0.0686 | - | - |
874
+ | 1.4963 | 23000 | 0.0743 | - | - |
875
+ | 1.5028 | 23100 | 0.0685 | - | - |
876
+ | 1.5093 | 23200 | 0.0645 | - | - |
877
+ | 1.5158 | 23300 | 0.0611 | - | - |
878
+ | 1.5223 | 23400 | 0.0678 | - | - |
879
+ | 1.5289 | 23500 | 0.0693 | - | - |
880
+ | 1.5354 | 23600 | 0.0694 | - | - |
881
+ | 1.5419 | 23700 | 0.0594 | - | - |
882
+ | 1.5484 | 23800 | 0.0635 | - | - |
883
+ | 1.5549 | 23900 | 0.069 | - | - |
884
+ | 1.5614 | 24000 | 0.0609 | - | - |
885
+ | 1.5679 | 24100 | 0.0673 | - | - |
886
+ | 1.5744 | 24200 | 0.062 | - | - |
887
+ | 1.5809 | 24300 | 0.0652 | - | - |
888
+ | 1.5874 | 24400 | 0.0685 | - | - |
889
+ | 1.5939 | 24500 | 0.0648 | - | - |
890
+ | 1.6004 | 24600 | 0.0612 | - | - |
891
+ | 1.6069 | 24700 | 0.0624 | - | - |
892
+ | 1.6134 | 24800 | 0.0635 | - | - |
893
+ | 1.6199 | 24900 | 0.0585 | - | - |
894
+ | 1.6264 | 25000 | 0.066 | - | - |
895
+ | 1.6329 | 25100 | 0.0678 | - | - |
896
+ | 1.6395 | 25200 | 0.0619 | - | - |
897
+ | 1.6460 | 25300 | 0.066 | - | - |
898
+ | 1.6525 | 25400 | 0.058 | - | - |
899
+ | 1.6590 | 25500 | 0.0649 | - | - |
900
+ | 1.6655 | 25600 | 0.0626 | - | - |
901
+ | 1.6720 | 25700 | 0.0687 | - | - |
902
+ | 1.6785 | 25800 | 0.0593 | - | - |
903
+ | 1.6850 | 25900 | 0.0632 | - | - |
904
+ | 1.6915 | 26000 | 0.0705 | - | - |
905
+ | 1.6980 | 26100 | 0.0598 | - | - |
906
+ | 1.7045 | 26200 | 0.0667 | - | - |
907
+ | 1.7110 | 26300 | 0.0595 | - | - |
908
+ | 1.7175 | 26400 | 0.0635 | - | - |
909
+ | 1.7240 | 26500 | 0.065 | - | - |
910
+ | 1.7305 | 26600 | 0.0556 | - | - |
911
+ | 1.7370 | 26700 | 0.0559 | - | - |
912
+ | 1.7435 | 26800 | 0.0552 | - | - |
913
+ | 1.7500 | 26900 | 0.0577 | - | - |
914
+ | 1.7566 | 27000 | 0.0666 | - | - |
915
+ | 1.7631 | 27100 | 0.06 | - | - |
916
+ | 1.7696 | 27200 | 0.0465 | - | - |
917
+ | 1.7761 | 27300 | 0.0621 | - | - |
918
+ | 1.7826 | 27400 | 0.056 | - | - |
919
+ | 1.7891 | 27500 | 0.062 | - | - |
920
+ | 1.7956 | 27600 | 0.0554 | - | - |
921
+ | 1.8021 | 27700 | 0.0656 | - | - |
922
+ | 1.8086 | 27800 | 0.0573 | - | - |
923
+ | 1.8151 | 27900 | 0.0555 | - | - |
924
+ | 1.8216 | 28000 | 0.0611 | - | - |
925
+ | 1.8281 | 28100 | 0.0538 | - | - |
926
+ | 1.8346 | 28200 | 0.0573 | - | - |
927
+ | 1.8411 | 28300 | 0.051 | - | - |
928
+ | 1.8476 | 28400 | 0.0599 | - | - |
929
+ | 1.8541 | 28500 | 0.0592 | - | - |
930
+ | 1.8606 | 28600 | 0.0568 | - | - |
931
+ | 1.8672 | 28700 | 0.0549 | - | - |
932
+ | 1.8737 | 28800 | 0.0558 | - | - |
933
+ | 1.8802 | 28900 | 0.0545 | - | - |
934
+ | 1.8867 | 29000 | 0.048 | - | - |
935
+ | 1.8932 | 29100 | 0.056 | - | - |
936
+ | 1.8997 | 29200 | 0.054 | - | - |
937
+ | 1.9062 | 29300 | 0.06 | - | - |
938
+ | 1.9127 | 29400 | 0.0586 | - | - |
939
+ | 1.9192 | 29500 | 0.0606 | - | - |
940
+ | 1.9257 | 29600 | 0.0648 | - | - |
941
+ | 1.9322 | 29700 | 0.0601 | - | - |
942
+ | 1.9387 | 29800 | 0.0582 | - | - |
943
+ | 1.9452 | 29900 | 0.0551 | - | - |
944
+ | 1.9517 | 30000 | 0.0575 | - | - |
945
+ | 1.9582 | 30100 | 0.0547 | - | - |
946
+ | 1.9647 | 30200 | 0.0612 | - | - |
947
+ | 1.9712 | 30300 | 0.0601 | - | - |
948
+ | 1.9778 | 30400 | 0.0516 | - | - |
949
+ | 1.9843 | 30500 | 0.0503 | - | - |
950
+ | 1.9908 | 30600 | 0.0561 | - | - |
951
+ | 1.9973 | 30700 | 0.0558 | - | - |
952
+ | 2.0 | 30742 | - | 0.4783 | 0.6658 |
953
+
954
+ * The bold row denotes the saved checkpoint.
955
+ </details>
956
+
957
+ ### Framework Versions
958
+ - Python: 3.11.9
959
+ - Sentence Transformers: 3.1.0.dev0
960
+ - Transformers: 4.41.2
961
+ - PyTorch: 2.4.0+cu121
962
+ - Accelerate: 0.31.0
963
+ - Datasets: 2.19.1
964
+ - Tokenizers: 0.19.1
965
+
966
+ ## Citation
967
+
968
+ ### BibTeX
969
+
970
+ #### Sentence Transformers
971
+ ```bibtex
972
+ @inproceedings{reimers-2019-sentence-bert,
973
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
974
+ author = "Reimers, Nils and Gurevych, Iryna",
975
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
976
+ month = "11",
977
+ year = "2019",
978
+ publisher = "Association for Computational Linguistics",
979
+ url = "https://arxiv.org/abs/1908.10084",
980
+ }
981
+ ```
982
+
983
+ #### MultipleNegativesRankingLoss
984
+ ```bibtex
985
+ @misc{henderson2017efficient,
986
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
987
+ 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},
988
+ year={2017},
989
+ eprint={1705.00652},
990
+ archivePrefix={arXiv},
991
+ primaryClass={cs.CL}
992
+ }
993
+ ```
994
+
995
+ <!--
996
+ ## Glossary
997
+
998
+ *Clearly define terms in order to be accessible across audiences.*
999
+ -->
1000
+
1001
+ <!--
1002
+ ## Model Card Authors
1003
+
1004
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
1005
+ -->
1006
+
1007
+ <!--
1008
+ ## Model Card Contact
1009
+
1010
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
1011
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/multi-qa-mpnet-base-cos-v1/MultipleNegativesRankingLoss/final",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.41.2",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.1.0.dev0",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.5.0+cu124"
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 sha256:1d237b195a73c93b3e5583e52ca70ed7347e7f6513cd8dae79d2093360d61b62
3
+ size 437967672
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": 512,
3
+ "do_lower_case": false
4
+ }
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": true,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "mask_token": "<mask>",
58
+ "max_length": 250,
59
+ "model_max_length": 512,
60
+ "pad_to_multiple_of": null,
61
+ "pad_token": "<pad>",
62
+ "pad_token_type_id": 0,
63
+ "padding_side": "right",
64
+ "sep_token": "</s>",
65
+ "stride": 0,
66
+ "strip_accents": null,
67
+ "tokenize_chinese_chars": true,
68
+ "tokenizer_class": "MPNetTokenizer",
69
+ "truncation_side": "right",
70
+ "truncation_strategy": "longest_first",
71
+ "unk_token": "[UNK]"
72
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff