Add new SentenceTransformer model
Browse files- 1_Pooling/config.json +10 -0
- README.md +737 -0
- config.json +26 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- vocab.txt +0 -0
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
|
|