Daxtra commited on
Commit
0dc49b0
1 Parent(s): 84d93dc

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 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sentence-transformers/all-MiniLM-L6-v2
3
+ library_name: sentence-transformers
4
+ metrics:
5
+ - cosine_accuracy@10
6
+ - cosine_precision@10
7
+ - cosine_recall@10
8
+ - cosine_ndcg@10
9
+ - cosine_mrr@10
10
+ - cosine_map@10
11
+ pipeline_tag: sentence-similarity
12
+ tags:
13
+ - sentence-transformers
14
+ - sentence-similarity
15
+ - feature-extraction
16
+ - generated_from_trainer
17
+ - dataset_size:149352
18
+ - loss:MultipleNegativesRankingLoss
19
+ widget:
20
+ - source_sentence: '- Digital PR Specialist, requiring 2-4 years of experience in
21
+ digital PR, preferably from an agency or startup environment.
22
+
23
+ - Craft and execute digital PR campaigns aligned with SEO goals and brand messaging.
24
+
25
+ - Develop and pitch newsworthy content to media outlets.
26
+
27
+ - Lead client calls and utilize digital marketing analytics tools for campaign
28
+ optimization.
29
+
30
+ - Maintain up-to-date knowledge of industry trends and competitive landscape.
31
+
32
+ - Proficient in SEO, digital marketing analytics (e.g., Google Analytics, Ahrefs,
33
+ SEMrush).
34
+
35
+ - Expertise with media databases and PR tools, confident in client interactions.
36
+
37
+ - Remote work experience essential.
38
+
39
+ - Ability to engage with large brand clients in Europe and the US.
40
+
41
+ - Valid work permit to operate in the UK.'
42
+ sentences:
43
+ - '- Digital Marketing and Social Media Specialist with 8+ years of experience managing
44
+ digital marketing campaigns and social media accounts for the automotive industry.
45
+
46
+ - Successfully increased online visibility and customer engagement for VW, Ford,
47
+ Fiat, and ISUZU franchises through SEO, content creation, and social media strategy.
48
+
49
+ - Developed and executed digital marketing plans, enhanced online reputation,
50
+ and managed multiple online platforms for customer engagement.
51
+
52
+ - Expertise in Google Analytics, SEMrush, Moz, Canva Content Planner, and Zoho
53
+ CRM for targeted campaigns and customer relationship management.
54
+
55
+ - Strong skills in content production, email marketing, website optimization,
56
+ and digital campaign analysis.'
57
+ - '- Data and Business Analyst with expertise in SQL, Python, and Excel, seeking
58
+ a Graduate Finance Analyst role.
59
+
60
+ - Developed data querying, manipulation, and database management skills using
61
+ SQL; enhanced analysis with Python and Power BI.
62
+
63
+ - Achieved 20% improvement in event safety and addressed safety concerns proactively.
64
+
65
+ - Strong problem-solving, time management, and team collaboration skills.
66
+
67
+ - Holds a Bachelor of Science in Finance with Mathematics, demonstrating analytical
68
+ and financial expertise.
69
+
70
+ - Proficient in data analysis, financial modelling, and business operations; seeks
71
+ to apply skills in finance.'
72
+ - '- Digital Marketing Executive with extensive experience in rebranding social
73
+ media and websites for clients to enhance online presence.
74
+
75
+ - Successfully created content calendars and blogs for client websites, and managed
76
+ social media campaigns on platforms like TikTok and Instagram.
77
+
78
+ - Bachelor of Arts in Business and Management with a focus on ethics, finance,
79
+ and sociology.
80
+
81
+ - Strong skills in verbal communication, teamwork, and problem-solving under pressure.
82
+
83
+ - Experience in COVID testing site operations, including health and hazard training,
84
+ and maintaining a high standard of detail and initiative.
85
+
86
+ - Proficient in Microsoft Excel, PowerPoint, and Word; skilled in analytics, market
87
+ research, and communication.'
88
+ - source_sentence: '- Residential and Commercial Roofers needed for tear-off, roofing
89
+ installation, and debris removal.
90
+
91
+ - Responsibilities include installation of underlayment and roofing systems, loading
92
+ and unloading materials, and cleanup.
93
+
94
+ - Preferred: Valid Driver''s License; Preferred experience in roofing, entry-level
95
+ with construction experience.
96
+
97
+ - Basic knowledge of tools required; ability to read tape measures.
98
+
99
+ - Must meet at the shop and drive in company trucks to job sites.'
100
+ sentences:
101
+ - '- Experienced Registered Nurse with a strong background in both inpatient and
102
+ outpatient settings.
103
+
104
+ - Currently providing comprehensive care at Water Gap Wellness Treatment Center,
105
+ focusing on patients with psychiatric conditions.
106
+
107
+ - Skills include monitoring patient wellbeing, medication administration, treatment
108
+ planning, and collaborating with healthcare professionals.
109
+
110
+ - Proficient in patient behavior management, team collaboration, and creating
111
+ high-quality care plans.
112
+
113
+ - Equipped with Basic Life Support Certification, CPR Certification, and Immunization
114
+ Certification.
115
+
116
+ - Holds a High School Diploma and Registered Nurse certification, specializing
117
+ in RN roles.
118
+
119
+ - Capable of driving, managing schedules, and delivering emotional support.
120
+
121
+ - Team player with excellent attention to detail, capable of multi-tasking, and
122
+ working independently.'
123
+ - '- Senior Software Engineer with over 10 years of experience in full-stack development
124
+ and a passion for ReactJS and cutting-edge technologies.
125
+
126
+ - Currently a Senior Backend Engineer specializing in AWS and Azure environments,
127
+ using tools like AWS Fargate, CloudWatch, and Cloud Formation.
128
+
129
+ - Experienced in managing web applications, configuration, and databases (e.g.,
130
+ MongoDB, MySQL, PostgreSQL).
131
+
132
+ - Skilled in automation, performance improvement, and scalability, achieving a
133
+ 30% reduction in infrastructure costs.
134
+
135
+ - Proficient in Python, JavaScript, ReactJS, React Native, HTML5, CSS, Python
136
+ Programming, and AWS services.
137
+
138
+ - Notable expertise in containerization, Docker, and cloud infrastructure management.
139
+
140
+ - Holds Bachelor''s degrees in Computer Science and Computer Engineering.'
141
+ - '- Caregiver with extensive experience in patient care, including Alzheimer''s
142
+ disease and autism, and experience in various industries.
143
+
144
+ - Certified Home Health Aide, Registered Dental Assistant, and trained in First
145
+ Aid, CPR, and Basic Life Support.
146
+
147
+ - Proficient in handling EMR, Foodservice, and Hospitality Industry, along with
148
+ janitorial and patient monitoring.
149
+
150
+ - Skilled in communication, quick learning, and handling vital signs; experience
151
+ with dental and dietary departments.
152
+
153
+ - Possesses forklift, safety, and other certifications relevant to caregiving
154
+ and healthcare environments.'
155
+ - source_sentence: '- Legal Assistant role for candidates with legal experience or
156
+ schooling, ideal for growth opportunities.
157
+
158
+ - Act as primary contact for clients and manage a busy phone system.
159
+
160
+ - Organize client documents, data entry, and handle courier packages.
161
+
162
+ - Requires Criminal Justice degree or paralegal degree; Criminal Justice or Legal
163
+ Schooling preferred.
164
+
165
+ - Must be computer savvy, open to learning new programs for the legal industry.
166
+
167
+ - Preferred bilingual (Spanish).
168
+
169
+ - Reception or Office Assistant experience is a plus.'
170
+ sentences:
171
+ - '- UI / Frontend Developer with a strong background in creating digital frontends
172
+ and web-based user interfaces for pharmaceutical companies.
173
+
174
+ - Successfully developed company websites, custom HTML emails, and web-based learning
175
+ modules with WCAG Level A compliance.
176
+
177
+ - Led web accessibility testing and QA, ensuring usability and functionality.
178
+
179
+ - Collaborated with designers to convert designs into digital frontends and conducted
180
+ development review processes (Alpha, Beta).
181
+
182
+ - Enhanced website SEO and user retention by 30% and managed client-facing projects,
183
+ meeting deadlines.
184
+
185
+ - Holds a Bachelor of Science in Information Technology and a UI Developer certification.
186
+
187
+ - Proficient in HTML, CSS, JavaScript, and MJML; experienced with CSS3, TypeScript,
188
+ React, and Git.'
189
+ - '- Service Project Manager with experience in mechanical engineering and project
190
+ management roles.
191
+
192
+ - Currently a Project Engineer, specializing in project coordination and management.
193
+
194
+ - Proficient in Microsoft Excel, PowerPoint, and Office Suite tools.
195
+
196
+ - Holds Bachelor of Science in Mechanical Engineering.
197
+
198
+ - Previous roles include Service Sales Engineer, Mechanical Design Engineer, and
199
+ Project Engineer Intern.
200
+
201
+ - Strong project management skills and experience in team coordination.'
202
+ - '- Experienced Sales Representative specializing in inside and outside sales,
203
+ including cold calling and field visits.
204
+
205
+ - Currently assisting in construction as a Creative Homeworks contractor, handling
206
+ site preparation, equipment maintenance, problem management, and basic plumbing
207
+ and electrical work.
208
+
209
+ - Skilled in project management and handling specifications.
210
+
211
+ - Previous experience includes contractor assistance and inside/outside sales
212
+ roles.
213
+
214
+ - Proficient in sales techniques and customer relationship management.
215
+
216
+ - Holds certifications in various construction and sales-related areas.'
217
+ - source_sentence: '- Program Manager (Senior) for CMS Star Ratings, with 5+ years
218
+ of relevant professional experience in healthcare, preferred with a degree in
219
+ business, nursing, or public health.
220
+
221
+ - Lead design, development, implementation, and evaluation of CMS Star Ratings
222
+ programs to meet organizational and market requirements.
223
+
224
+ - Collaborate with cross-functional teams to advance strategic priorities and
225
+ manage programs with tight deadlines.
226
+
227
+ - Responsible for resolving complex business issues, managing change, and liaising
228
+ between departments.
229
+
230
+ - Requires strong knowledge of CMS Star Ratings measures and experience with the
231
+ Medicare population.
232
+
233
+ - Essential skills: organizational relationship management, critical thinking,
234
+ problem-solving, and effective communication.
235
+
236
+ - Must be adaptable, self-motivated, and capable of working under pressure in
237
+ a dynamic environment.'
238
+ sentences:
239
+ - '- Project Coordinator with strong business management and military background,
240
+ skilled in data analytics, scheduling, and leadership.
241
+
242
+ - Currently coordinating projects for operational and capital projects at Seattle
243
+ Children''s Hospital, managing stakeholders and ensuring timely execution.
244
+
245
+ - Expertise in Microsoft Office and various other systems like GTIMS and Smartsheet;
246
+ proficient in vendor management and scheduling.
247
+
248
+ - Previous roles include operations scheduling manager and vendor manager, with
249
+ experience in large-scale military exercises and international projects.
250
+
251
+ - Skilled in communication, critical thinking, multi-tasking, and negotiation,
252
+ with a keen eye for detail and strong analytical abilities.'
253
+ - '- Legal Nurse Consultant with experience in medical analysis and consultation
254
+ for legal teams, specializing in healthcare-related legal strategies.
255
+
256
+ - Led Legal Nurse roles at Kaiser Permanente and Kaiser Permanente, managing quality
257
+ improvement initiatives and educating families.
258
+
259
+ - Served as a Clinical Nurse II, providing direct care in Neonatal Intensive Care
260
+ and Urgent Care, and maintaining medical records.
261
+
262
+ - Holds a Master of Science in Health Care Administration and a Bachelor of Science
263
+ in Nursing from San Diego State University.
264
+
265
+ - Certified Six Sigma Green Belt, skilled in clinical data analysis and patient
266
+ care planning.
267
+
268
+ - Proficient in electronic medical records and patient safety, with expertise
269
+ in critical care nursing and legal consultation.'
270
+ - '- SEO Manager with 7 years of experience, specializing in traffic growth and
271
+ content strategy.
272
+
273
+ - Achieved a 45% increase in web traffic through dynamic keyword insertion and
274
+ SEO management.
275
+
276
+ - Managed freelancers for technical blog content, creating and overseeing a content
277
+ marketing strategy.
278
+
279
+ - Efficiently managed social media accounts, increasing engagement by 200% over
280
+ three months.
281
+
282
+ - Skilled in database management, A/B testing, analytics, and SEO tools like Google
283
+ Analytics, Google AdWords, and Google Ads.
284
+
285
+ - Holds a Bachelor''s Degree in Classical Archaeology; strong in team management
286
+ and content development.
287
+
288
+ - Proficient in Microsoft Excel, Word, Outlook, and PowerPoint.
289
+
290
+ - Strong analytical, communication, and multichannel marketing skills.'
291
+ - source_sentence: '- Data Management Specialist (Junior/Intermediate), requiring
292
+ a Bachelor''s degree in computer science, information systems, or related field.
293
+
294
+ - Must have a solid understanding of web- and app-based platforms.
295
+
296
+ - Required experience with SQL, Data warehousing, and Tableau.
297
+
298
+ - Ability to analyze, interpret, and organize large data sets.
299
+
300
+ - Proficiency in Microsoft Suite, G-Suite, Slack, Zoom, ZenDesk, and Monday.com
301
+ is essential.'
302
+ sentences:
303
+ - '- Experienced Technical Project Manager with 12 years in IT infrastructure and
304
+ project management.
305
+
306
+ - Expertise in IT project planning, budgeting, resource allocation, and stakeholder
307
+ engagement.
308
+
309
+ - Led successful IT infrastructure upgrades, including EFT and Manta application
310
+ migrations to AWS.
311
+
312
+ - Managed cloud and on-premise infrastructure projects, ensuring compliance and
313
+ minimal disruption.
314
+
315
+ - Holds PMP certification and proficiency in Agile and Waterfall methodologies.
316
+
317
+ - Master''s in Business Administration with a focus on Marketing and User Experience.
318
+
319
+ - Strong analytical skills, stakeholder management, and continuous improvement
320
+ practices.
321
+
322
+ - Proficient in Microsoft Office, Windows Server, and Azure, with experience in
323
+ networking, security, and VMware.'
324
+ - '- Leadership roles in healthcare and pharmaceuticals with extensive experience
325
+ in contract negotiation and site management.
326
+
327
+ - Parexel Site Contract Leader: Lead global CSA strategy development, budget creation,
328
+ and legal drafting, ensuring compliance with ICH-GCP and local regulations.
329
+
330
+ - Drafts, reviews, and finalizes contracts with study sites, managing budgets
331
+ and negotiations, and maintaining quality standards.
332
+
333
+ - Expertise in financial risk assessment, budgeting, and regulatory compliance
334
+ with a Bachelor''s in Criminal Justice.
335
+
336
+ - Proficient in Microsoft Excel, PowerPoint, and Salesforce.com, with a background
337
+ in biotechnology, clinical trials, and patient safety.'
338
+ - '- Financial professional with extensive experience in member service and trading,
339
+ currently a Member Representative focusing on customer service and banking transactions.
340
+
341
+ - Expertise in handling ATMs, deposit envelopes, and savings accounts; ensures
342
+ member data security and efficient payment processing.
343
+
344
+ - Proficient in making outbound calls for sales and inquiry, building relationships
345
+ with customers and banking managers.
346
+
347
+ - Experienced in trading major currencies and assets with a strong foundation
348
+ in technical and fundamental analysis.
349
+
350
+ - Holds a Masters in Business Administration and proficient in Microsoft Excel,
351
+ Python, and social media platforms.
352
+
353
+ - Fluent in English and French, with skills in communication, content writing,
354
+ and project planning.'
355
+ model-index:
356
+ - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
357
+ results:
358
+ - task:
359
+ type: information-retrieval
360
+ name: Information Retrieval
361
+ dataset:
362
+ name: vac res matcher
363
+ type: vac-res-matcher
364
+ metrics:
365
+ - type: cosine_accuracy@10
366
+ value: 0.3696705426356589
367
+ name: Cosine Accuracy@10
368
+ - type: cosine_precision@10
369
+ value: 0.07374031007751937
370
+ name: Cosine Precision@10
371
+ - type: cosine_recall@10
372
+ value: 0.10916001476122919
373
+ name: Cosine Recall@10
374
+ - type: cosine_ndcg@10
375
+ value: 0.1177083437550142
376
+ name: Cosine Ndcg@10
377
+ - type: cosine_mrr@10
378
+ value: 0.19530038759689897
379
+ name: Cosine Mrr@10
380
+ - type: cosine_map@10
381
+ value: 0.07133683851447556
382
+ name: Cosine Map@10
383
+ ---
384
+
385
+ # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
386
+
387
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). 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.
388
+
389
+ ## Model Details
390
+
391
+ ### Model Description
392
+ - **Model Type:** Sentence Transformer
393
+ - **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision ea78891063587eb050ed4166b20062eaf978037c -->
394
+ - **Maximum Sequence Length:** 128 tokens
395
+ - **Output Dimensionality:** 384 tokens
396
+ - **Similarity Function:** Cosine Similarity
397
+ <!-- - **Training Dataset:** Unknown -->
398
+ <!-- - **Language:** Unknown -->
399
+ <!-- - **License:** Unknown -->
400
+
401
+ ### Model Sources
402
+
403
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
404
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
405
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
406
+
407
+ ### Full Model Architecture
408
+
409
+ ```
410
+ SentenceTransformer(
411
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
412
+ (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})
413
+ )
414
+ ```
415
+
416
+ ## Usage
417
+
418
+ ### Direct Usage (Sentence Transformers)
419
+
420
+ First install the Sentence Transformers library:
421
+
422
+ ```bash
423
+ pip install -U sentence-transformers
424
+ ```
425
+
426
+ Then you can load this model and run inference.
427
+ ```python
428
+ from sentence_transformers import SentenceTransformer
429
+
430
+ # Download from the 🤗 Hub
431
+ model = SentenceTransformer("Daxtra/sbert-summaries-minilm-24-batch")
432
+ # Run inference
433
+ sentences = [
434
+ "- Data Management Specialist (Junior/Intermediate), requiring a Bachelor's degree in computer science, information systems, or related field.\n- Must have a solid understanding of web- and app-based platforms.\n- Required experience with SQL, Data warehousing, and Tableau.\n- Ability to analyze, interpret, and organize large data sets.\n- Proficiency in Microsoft Suite, G-Suite, Slack, Zoom, ZenDesk, and Monday.com is essential.",
435
+ "- Leadership roles in healthcare and pharmaceuticals with extensive experience in contract negotiation and site management.\n- Parexel Site Contract Leader: Lead global CSA strategy development, budget creation, and legal drafting, ensuring compliance with ICH-GCP and local regulations.\n- Drafts, reviews, and finalizes contracts with study sites, managing budgets and negotiations, and maintaining quality standards.\n- Expertise in financial risk assessment, budgeting, and regulatory compliance with a Bachelor's in Criminal Justice.\n- Proficient in Microsoft Excel, PowerPoint, and Salesforce.com, with a background in biotechnology, clinical trials, and patient safety.",
436
+ "- Experienced Technical Project Manager with 12 years in IT infrastructure and project management.\n- Expertise in IT project planning, budgeting, resource allocation, and stakeholder engagement.\n- Led successful IT infrastructure upgrades, including EFT and Manta application migrations to AWS.\n- Managed cloud and on-premise infrastructure projects, ensuring compliance and minimal disruption.\n- Holds PMP certification and proficiency in Agile and Waterfall methodologies.\n- Master's in Business Administration with a focus on Marketing and User Experience.\n- Strong analytical skills, stakeholder management, and continuous improvement practices.\n- Proficient in Microsoft Office, Windows Server, and Azure, with experience in networking, security, and VMware.",
437
+ ]
438
+ embeddings = model.encode(sentences)
439
+ print(embeddings.shape)
440
+ # [3, 384]
441
+
442
+ # Get the similarity scores for the embeddings
443
+ similarities = model.similarity(embeddings, embeddings)
444
+ print(similarities.shape)
445
+ # [3, 3]
446
+ ```
447
+
448
+ <!--
449
+ ### Direct Usage (Transformers)
450
+
451
+ <details><summary>Click to see the direct usage in Transformers</summary>
452
+
453
+ </details>
454
+ -->
455
+
456
+ <!--
457
+ ### Downstream Usage (Sentence Transformers)
458
+
459
+ You can finetune this model on your own dataset.
460
+
461
+ <details><summary>Click to expand</summary>
462
+
463
+ </details>
464
+ -->
465
+
466
+ <!--
467
+ ### Out-of-Scope Use
468
+
469
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
470
+ -->
471
+
472
+ ## Evaluation
473
+
474
+ ### Metrics
475
+
476
+ #### Information Retrieval
477
+ * Dataset: `vac-res-matcher`
478
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
479
+
480
+ | Metric | Value |
481
+ |:--------------------|:-----------|
482
+ | cosine_accuracy@10 | 0.3697 |
483
+ | cosine_precision@10 | 0.0737 |
484
+ | cosine_recall@10 | 0.1092 |
485
+ | cosine_ndcg@10 | 0.1177 |
486
+ | cosine_mrr@10 | 0.1953 |
487
+ | **cosine_map@10** | **0.0713** |
488
+
489
+ <!--
490
+ ## Bias, Risks and Limitations
491
+
492
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
493
+ -->
494
+
495
+ <!--
496
+ ### Recommendations
497
+
498
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
499
+ -->
500
+
501
+ ## Training Details
502
+
503
+ ### Training Dataset
504
+
505
+ #### Unnamed Dataset
506
+
507
+
508
+ * Size: 149,352 training samples
509
+ * Columns: <code>sentence_0</code> and <code>sentence_1</code>
510
+ * Approximate statistics based on the first 1000 samples:
511
+ | | sentence_0 | sentence_1 |
512
+ |:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
513
+ | type | string | string |
514
+ | details | <ul><li>min: 53 tokens</li><li>mean: 115.57 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 51 tokens</li><li>mean: 119.82 tokens</li><li>max: 128 tokens</li></ul> |
515
+ * Samples:
516
+ | sentence_0 | sentence_1 |
517
+ |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
518
+ | <code>- Solutions Architect/Snowflake position requiring 8+ years of experience in data management and implementation of Snowflake solutions.<br>- Responsibilities include developing data models, optimizing data pipelines, and integrating with AWS/Azure PBAS.<br>- Must possess deep knowledge of relational and NoSQL databases, SQL, and Unix Shell/Python Scripting.<br>- Experience with data security, database optimization, and Snowflake's Resource Monitors.<br>- Required: Bachelor's or Master's degree in Computer Science or related field.<br>- Preferred: Management consulting experience, expertise in AI use cases, and experience with Cloud technologies.<br>- Skills: Strong leadership, team management, and experience with globally distributed teams.</code> | <code>- Senior IT Consultant with 30 years of experience, specializing in enterprise architecture and solution architecture.<br>- Currently a Senior Consultant, with significant experience in architecture roles and delivering solutions for mission-critical projects.<br>- Expertise in Enterprise Architecture, Enterprise Consortium management, and IT Governance.<br>- Leads projects ranging from $100M to $900M, focusing on architecture for business, data, and applications.<br>- Designed enterprise-wide architecture models and created strategies for product development based on product architecture.<br>- Skilled in modern technologies like Spring Framework, Kafka, Spring Cloud, and Docker, and in containerization with Kubernetes.<br>- Holds Masters Degrees in Computer Science and Law, with a Bachelor's in Computer Sciences.</code> |
519
+ | <code>- Global Head of Business Development - Financial Education, with a focus on rapid adaptation and leadership in Hong Kong.<br>- Responsible for identifying leads, building pipelines, and converting prospects into clients, and managing international teams.<br>- Implement relationship-based sales practices, nurture industry relationships, and lead global expansion efforts.<br>- Requires a proven track record in financial services business development and experience in sales with tech, media, or administration.<br>- Strong networking and relationship-building skills, leadership abilities across cultures, and excellent communication and negotiation skills.<br>- Must have the right to work in the United Kingdom.</code> | <code>- Management Accountant with extensive experience in financial planning and analysis, specializing in the banking sector.<br>- Leads financial planning and analysis roles, overseeing budget processes, regulatory reporting, and financial performance analysis.<br>- Streamlined processes to reduce payment processing time by 15% and minimize penalties.<br>- Led quarterly and year-end audits, ensuring accurate financial audits and implementing improvement suggestions.<br>- Proficient in financial reporting, budgeting, forecasting, and variance analysis; adept at using Microsoft Excel and QuickBooks.<br>- Strong communication and team management skills, with expertise in process improvement and strategic initiatives.</code> |
520
+ | <code>- Customer Service Administrator position requiring experience in customer service or administration.<br>- Key responsibilities include managing customer feedback, coordinating deliveries, processing refunds, and general office support.<br>- Must possess strong communication, problem-solving, and attention to detail skills.<br>- Proficiency in MS Office and CRM software required.<br>- Ability to multitask and prioritize workload effectively.<br>- Must have the right to work in the United Kingdom.</code> | <code>- Experienced Technical Services Coordinator with a strong background in administration and team collaboration, seeking to advance in London.<br>- Manages UK technical services, handling device delivery, fault reporting, and resource planning.<br>- Expert in Microsoft Office, maintaining databases and customer service through communication and negotiation.<br>- Holds NVQ Level 2 and 3, with skills in GDPR compliance and financial transactions.<br>- Proven experience in collecting evidence for claims, negotiating settlements, and managing key performance indicators.<br>- Strong communication, organizational, and interpersonal skills, with proficiency in using initiative and effective negotiation.<br>- Holds GCSE qualifications and relevant experience in customer service roles.</code> |
521
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
522
+ ```json
523
+ {
524
+ "scale": 20.0,
525
+ "similarity_fct": "cos_sim"
526
+ }
527
+ ```
528
+
529
+ ### Training Hyperparameters
530
+ #### Non-Default Hyperparameters
531
+
532
+ - `eval_strategy`: steps
533
+ - `per_device_train_batch_size`: 24
534
+ - `per_device_eval_batch_size`: 24
535
+ - `num_train_epochs`: 1
536
+ - `multi_dataset_batch_sampler`: round_robin
537
+
538
+ #### All Hyperparameters
539
+ <details><summary>Click to expand</summary>
540
+
541
+ - `overwrite_output_dir`: False
542
+ - `do_predict`: False
543
+ - `eval_strategy`: steps
544
+ - `prediction_loss_only`: True
545
+ - `per_device_train_batch_size`: 24
546
+ - `per_device_eval_batch_size`: 24
547
+ - `per_gpu_train_batch_size`: None
548
+ - `per_gpu_eval_batch_size`: None
549
+ - `gradient_accumulation_steps`: 1
550
+ - `eval_accumulation_steps`: None
551
+ - `torch_empty_cache_steps`: None
552
+ - `learning_rate`: 5e-05
553
+ - `weight_decay`: 0.0
554
+ - `adam_beta1`: 0.9
555
+ - `adam_beta2`: 0.999
556
+ - `adam_epsilon`: 1e-08
557
+ - `max_grad_norm`: 1
558
+ - `num_train_epochs`: 1
559
+ - `max_steps`: -1
560
+ - `lr_scheduler_type`: linear
561
+ - `lr_scheduler_kwargs`: {}
562
+ - `warmup_ratio`: 0.0
563
+ - `warmup_steps`: 0
564
+ - `log_level`: passive
565
+ - `log_level_replica`: warning
566
+ - `log_on_each_node`: True
567
+ - `logging_nan_inf_filter`: True
568
+ - `save_safetensors`: True
569
+ - `save_on_each_node`: False
570
+ - `save_only_model`: False
571
+ - `restore_callback_states_from_checkpoint`: False
572
+ - `no_cuda`: False
573
+ - `use_cpu`: False
574
+ - `use_mps_device`: False
575
+ - `seed`: 42
576
+ - `data_seed`: None
577
+ - `jit_mode_eval`: False
578
+ - `use_ipex`: False
579
+ - `bf16`: False
580
+ - `fp16`: False
581
+ - `fp16_opt_level`: O1
582
+ - `half_precision_backend`: auto
583
+ - `bf16_full_eval`: False
584
+ - `fp16_full_eval`: False
585
+ - `tf32`: None
586
+ - `local_rank`: 0
587
+ - `ddp_backend`: None
588
+ - `tpu_num_cores`: None
589
+ - `tpu_metrics_debug`: False
590
+ - `debug`: []
591
+ - `dataloader_drop_last`: False
592
+ - `dataloader_num_workers`: 0
593
+ - `dataloader_prefetch_factor`: None
594
+ - `past_index`: -1
595
+ - `disable_tqdm`: False
596
+ - `remove_unused_columns`: True
597
+ - `label_names`: None
598
+ - `load_best_model_at_end`: False
599
+ - `ignore_data_skip`: False
600
+ - `fsdp`: []
601
+ - `fsdp_min_num_params`: 0
602
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
603
+ - `fsdp_transformer_layer_cls_to_wrap`: None
604
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
605
+ - `deepspeed`: None
606
+ - `label_smoothing_factor`: 0.0
607
+ - `optim`: adamw_torch
608
+ - `optim_args`: None
609
+ - `adafactor`: False
610
+ - `group_by_length`: False
611
+ - `length_column_name`: length
612
+ - `ddp_find_unused_parameters`: None
613
+ - `ddp_bucket_cap_mb`: None
614
+ - `ddp_broadcast_buffers`: False
615
+ - `dataloader_pin_memory`: True
616
+ - `dataloader_persistent_workers`: False
617
+ - `skip_memory_metrics`: True
618
+ - `use_legacy_prediction_loop`: False
619
+ - `push_to_hub`: False
620
+ - `resume_from_checkpoint`: None
621
+ - `hub_model_id`: None
622
+ - `hub_strategy`: every_save
623
+ - `hub_private_repo`: False
624
+ - `hub_always_push`: False
625
+ - `gradient_checkpointing`: False
626
+ - `gradient_checkpointing_kwargs`: None
627
+ - `include_inputs_for_metrics`: False
628
+ - `eval_do_concat_batches`: True
629
+ - `fp16_backend`: auto
630
+ - `push_to_hub_model_id`: None
631
+ - `push_to_hub_organization`: None
632
+ - `mp_parameters`:
633
+ - `auto_find_batch_size`: False
634
+ - `full_determinism`: False
635
+ - `torchdynamo`: None
636
+ - `ray_scope`: last
637
+ - `ddp_timeout`: 1800
638
+ - `torch_compile`: False
639
+ - `torch_compile_backend`: None
640
+ - `torch_compile_mode`: None
641
+ - `dispatch_batches`: None
642
+ - `split_batches`: None
643
+ - `include_tokens_per_second`: False
644
+ - `include_num_input_tokens_seen`: False
645
+ - `neftune_noise_alpha`: None
646
+ - `optim_target_modules`: None
647
+ - `batch_eval_metrics`: False
648
+ - `eval_on_start`: False
649
+ - `eval_use_gather_object`: False
650
+ - `batch_sampler`: batch_sampler
651
+ - `multi_dataset_batch_sampler`: round_robin
652
+
653
+ </details>
654
+
655
+ ### Training Logs
656
+ | Epoch | Step | Training Loss | vac-res-matcher_cosine_map@10 |
657
+ |:------:|:----:|:-------------:|:-----------------------------:|
658
+ | 0.0803 | 500 | 1.5369 | - |
659
+ | 0.1000 | 622 | - | 0.0697 |
660
+ | 0.1607 | 1000 | 1.2768 | - |
661
+ | 0.1999 | 1244 | - | 0.0692 |
662
+ | 0.2410 | 1500 | 1.2 | - |
663
+ | 0.2999 | 1866 | - | 0.0673 |
664
+ | 0.3214 | 2000 | 1.1463 | - |
665
+ | 0.3998 | 2488 | - | 0.0705 |
666
+ | 0.4017 | 2500 | 1.1206 | - |
667
+ | 0.4821 | 3000 | 1.1043 | - |
668
+ | 0.4998 | 3110 | - | 0.0683 |
669
+ | 0.5624 | 3500 | 1.0768 | - |
670
+ | 0.5997 | 3732 | - | 0.0700 |
671
+ | 0.6428 | 4000 | 1.0905 | - |
672
+ | 0.6997 | 4354 | - | 0.0705 |
673
+ | 0.7231 | 4500 | 1.0804 | - |
674
+ | 0.7996 | 4976 | - | 0.0699 |
675
+ | 0.8035 | 5000 | 1.0536 | - |
676
+ | 0.8838 | 5500 | 1.0352 | - |
677
+ | 0.8996 | 5598 | - | 0.0715 |
678
+ | 0.9642 | 6000 | 1.0292 | - |
679
+ | 0.9995 | 6220 | - | 0.0713 |
680
+ | 1.0 | 6223 | - | 0.0713 |
681
+
682
+
683
+ ### Framework Versions
684
+ - Python: 3.10.12
685
+ - Sentence Transformers: 3.2.1
686
+ - Transformers: 4.44.2
687
+ - PyTorch: 2.4.1+cu121
688
+ - Accelerate: 0.34.2
689
+ - Datasets: 3.0.1
690
+ - Tokenizers: 0.19.1
691
+
692
+ ## Citation
693
+
694
+ ### BibTeX
695
+
696
+ #### Sentence Transformers
697
+ ```bibtex
698
+ @inproceedings{reimers-2019-sentence-bert,
699
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
700
+ author = "Reimers, Nils and Gurevych, Iryna",
701
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
702
+ month = "11",
703
+ year = "2019",
704
+ publisher = "Association for Computational Linguistics",
705
+ url = "https://arxiv.org/abs/1908.10084",
706
+ }
707
+ ```
708
+
709
+ #### MultipleNegativesRankingLoss
710
+ ```bibtex
711
+ @misc{henderson2017efficient,
712
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
713
+ 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},
714
+ year={2017},
715
+ eprint={1705.00652},
716
+ archivePrefix={arXiv},
717
+ primaryClass={cs.CL}
718
+ }
719
+ ```
720
+
721
+ <!--
722
+ ## Glossary
723
+
724
+ *Clearly define terms in order to be accessible across audiences.*
725
+ -->
726
+
727
+ <!--
728
+ ## Model Card Authors
729
+
730
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
731
+ -->
732
+
733
+ <!--
734
+ ## Model Card Contact
735
+
736
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
737
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
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": "4.44.2",
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": "3.2.1",
4
+ "transformers": "4.44.2",
5
+ "pytorch": "2.4.1+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 sha256:15ae6442843664c54539e5a808f3d712af40f3fd602d32f89e38bdc3ae714451
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": 128,
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": 128,
50
+ "model_max_length": 128,
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