frankwong2001 commited on
Commit
b820f10
·
verified ·
1 Parent(s): 202324f

Add new SentenceTransformer model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,625 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:3016
9
+ - loss:MultipleNegativesRankingLoss
10
+ base_model: nomic-ai/modernbert-embed-base
11
+ widget:
12
+ - source_sentence: The Technician (Automatic Fare Collection) works in a team to perform
13
+ preventive and corrective maintenance of Automatic Fare Collection (AFC) Line
14
+ Replacement Units (LRUs). He/She is responsible for the preparation of materials,
15
+ tools, equipment and checklists required. He also assists in the conduct of fault
16
+ analysis and testing to improve the reliability of the AFC systems as well as
17
+ supervises the work of contractors and external stakeholders in ensuring compliance
18
+ to safety requirements and operating standards. He is required to carry out his
19
+ duties in the depot, workshop and/or at various train stations during train operating
20
+ hours. He is a team player and a well-organised individual who is able to work
21
+ under pressure and carry out his duties professionally in public access areas.
22
+ sentences:
23
+ - The Technician/Coordinator (Operations and Maintenance) plays a crucial role in
24
+ guaranteeing that all engineering systems and equipment operate smoothly and efficiently.
25
+ This position involves conducting maintenance activities on various equipment
26
+ according to established Standard Operating Procedures (SOPs). The individual
27
+ adheres to corporate policies and best practices, ensuring that all tasks are
28
+ performed safely and meet regulatory standards. Additionally, he/she follows emergency
29
+ protocols and complies with workplace safety and health (WSH) regulations. This
30
+ role typically involves working under guidance and requires strong collaboration
31
+ skills to effectively communicate with both internal and external stakeholders.
32
+ The Technician/Coordinator is also expected to be present on-site, work in shifts,
33
+ and may need to be available for on-call duties.
34
+ - The Technician (Automatic Fare Collection) leads a team to conduct routine and
35
+ emergency repairs of Public Transport Systems (PTS) Line Maintenance Units (LMUs).
36
+ He/She is tasked with sourcing materials, tools, and equipment while also preparing
37
+ reports required for compliance checks. He further manages the evaluation of system
38
+ performance and oversees the training of junior staff and external vendors to
39
+ guarantee adherence to operational metrics and quality standards. This role is
40
+ conducted exclusively in corporate offices and training facilities during non-operational
41
+ hours. The candidate must be a self-motivated and meticulous individual who can
42
+ work independently and handle complex projects in restricted areas.
43
+ - The Technician (Automatic Fare Collection) collaborates with a team to execute
44
+ both preventive and corrective maintenance on Automatic Fare Collection (AFC)
45
+ Line Replacement Units (LRUs). This role involves preparing the necessary materials,
46
+ tools, and equipment, as well as creating checklists for efficient task execution.
47
+ Additionally, the technician aids in fault analysis and testing to enhance the
48
+ reliability of AFC systems and oversees the work of contractors and external partners
49
+ to ensure adherence to safety standards and operational protocols. Duties are
50
+ performed in various settings, including depots, workshops, and train stations
51
+ during operational hours. The ideal candidate is a team-oriented and organized
52
+ professional who thrives under pressure and maintains a high level of professionalism
53
+ in public environments.
54
+ - source_sentence: The Head - Content Acquisition drives the organisation's content
55
+ acquisition strategy by developing and implementing plans to acquire content which
56
+ is aligned to the creative vision of the organisation. He/She leads the development
57
+ of the content acquisition strategy in accordance with the overall content strategy
58
+ for the organisation. He also oversees the execution of content acquisition plans
59
+ by leading negotiations for acquiring content. The work involves providing creative
60
+ and business leadership to his team and liaising with several internal and external
61
+ stakeholders. He spends his time in planning as well as meetings to acquire content.
62
+ He may also be required to travel as part of his work. He is an expert in industry
63
+ trends with proficiency in business acumen. He should be comfortable with numbers
64
+ and analysis. He is an able communicator and planner. He ought to be proficient
65
+ in decision making and stakeholder management.
66
+ sentences:
67
+ - The Head of Content Acquisition spearheads the organization’s strategy for sourcing
68
+ new content by crafting and executing initiatives that resonate with the creative
69
+ goals of the company. This role involves leading the formulation of the content
70
+ acquisition plan in line with the overarching content strategy. The Head also
71
+ manages the implementation of these plans by negotiating effectively for content
72
+ procurement. This position requires providing both creative direction and business
73
+ insight to the team while collaborating with various internal and external partners.
74
+ The role demands a significant amount of time spent on strategic planning and
75
+ meetings focused on content acquisition, with occasional travel expected. The
76
+ ideal candidate is well-versed in industry trends and possesses strong business
77
+ acumen, alongside a comfort with data analysis. Excellent communication, planning,
78
+ decision-making, and stakeholder management skills are essential.
79
+ - The Head of Marketing oversees the organization’s promotional strategy by developing
80
+ and executing plans to enhance brand visibility that aligns with the overall marketing
81
+ vision. This role involves leading the marketing strategy development to ensure
82
+ consistency with the corporate branding objectives. The Head also supervises the
83
+ execution of marketing campaigns by managing partnerships for promotional activities.
84
+ The work involves providing strategic guidance to the marketing team and coordinating
85
+ with various internal departments. Frequent meetings and planning sessions are
86
+ conducted to discuss promotional initiatives, and travel may be necessary. The
87
+ candidate should have a strong grasp of consumer behavior and marketing analytics,
88
+ with a focus on creativity and innovation. Proficiency in project management and
89
+ team leadership is critical.
90
+ - The Counselling Educator designs and implements training programs in counselling
91
+ while collaborating with practitioners and external partners within the social
92
+ services sector to create effective training materials and methodologies. This
93
+ role also involves enhancing sector-wide capabilities, mentoring aspiring counsellors,
94
+ and guiding community members and para-counsellors. Furthermore, the educator
95
+ engages with professionals in practice and research to develop and execute education-focused
96
+ studies. An individual with extensive experience, the Counselling Educator exhibits
97
+ exceptional facilitation and communication skills, fostering a cooperative atmosphere
98
+ and operating in diverse environments, including government bodies, private organizations,
99
+ and social service agencies.
100
+ - source_sentence: The Relationship Manager - Financial Institutions and Non-Bank
101
+ Financial Institutions is responsible for acquiring and managing a portfolio of
102
+ Financial Institutions (FI) and Non-Bank Financial Institutions (NBFI) clients.
103
+ He/She actively acquires clients through targeted relationship building, networking
104
+ and referrals. He will provide advice on customised products, services and solutions
105
+ as well as cross-sell the full suite of bank products. He is involved with credit
106
+ analysis and collaborates with other business units to mitigate credit issues.
107
+ He serves key accounts in specialised industries. He applies his deep FI and NBFI
108
+ industry knowledge to deliver specific solutions to this client segment. The Relationship
109
+ Manager - Financial Institutions and Non-Bank Financial Institutions possess decorum
110
+ and business acumen to interact with various stakeholders. He is resourceful in
111
+ acquiring clients. He is a team player and leverages on knowledge from other business
112
+ units to continually provide enhanced services to his clients. He has a proven
113
+ track record of working with FIs and NBFIs. He is organised and has good time
114
+ management skills. He is an effective communicator, able to influence others and
115
+ negotiate.
116
+ sentences:
117
+ - The Relationship Manager - Tax Compliance is responsible for overseeing a portfolio
118
+ of clients in the tax advisory sector. He/She primarily focuses on managing regulatory
119
+ compliance and ensuring that clients adhere to tax requirements. This position
120
+ requires collaborating with legal teams to interpret tax laws and regulations
121
+ while advising clients on complex tax issues. The manager is expected to conduct
122
+ in-depth audits and prepare reports for governmental agencies. He/She works independently
123
+ without direct supervision and is required to have extensive experience in tax
124
+ law, with minimal engagement in client relationship management. The role necessitates
125
+ strong analytical skills but does not involve direct communication with stakeholders,
126
+ as most interactions are handled through formal channels.
127
+ - 'Description
128
+
129
+ The Branch Manager is tasked with driving the financial performance of the branch.
130
+ This role encompasses all operational aspects, including recruiting staff, executing
131
+ service improvement strategies, supervising loan approvals and credit lines, promoting
132
+ services, and enhancing customer engagement. The Branch Manager adeptly leads
133
+ team members, focusing on their development and motivation to meet sales objectives.
134
+ Occasionally, this position may require weekend and after-hours work. Strong organizational
135
+ skills, diligence, and exceptional people management abilities are essential.
136
+ A customer-centric mindset, sharp problem-solving skills, and the capability to
137
+ handle diverse internal and external stakeholders are crucial for success.'
138
+ - The Relationship Manager - Financial Institutions and Non-Bank Financial Institutions
139
+ is tasked with developing and overseeing a diverse portfolio of clients in the
140
+ Financial Institutions (FI) and Non-Bank Financial Institutions (NBFI) sectors.
141
+ This role involves proactively building relationships through strategic networking
142
+ and referrals. The manager provides expert advice on tailored products, services,
143
+ and solutions while effectively cross-selling the comprehensive range of bank
144
+ offerings. He/She conducts credit assessments and works closely with other departments
145
+ to address any credit challenges. Serving key accounts within specialized sectors,
146
+ the Relationship Manager applies extensive industry knowledge to deliver targeted
147
+ solutions. Possessing professionalism and business insight, he/she engages confidently
148
+ with various stakeholders. Resourceful in client acquisition, this team-oriented
149
+ individual draws on insights from different business units to enhance client service
150
+ delivery. With a solid history of collaboration with FIs and NBFIs, he/she demonstrates
151
+ strong organizational skills and effective time management. As a persuasive communicator,
152
+ he/she excels in influencing and negotiating outcomes.
153
+ - source_sentence: The Infrastructure Engineering Manager drives the implementation
154
+ of strategy for infrastructure operations and maintenance to ensure availability
155
+ of stable and secure systems and networks. He/She manages project resource allocation
156
+ and develops infrastructure implementation, operations and maintenance engineers;
157
+ scopes out policies and sets performance expectations. He identifies problems
158
+ and presents new methodologies/solutions to key stakeholders to enhance and improve
159
+ the delivery of infrastructure operations and maintenance services. He has expertise
160
+ in the planning, implementation and maintenance of infrastructure systems across
161
+ cloud, on-premise, server and network infrastructure. He is familiar with the
162
+ infrastructure deployment and IT service management processes, tools and methodologies.
163
+ He is knowledgeable in both technical and business aspects of the organisations
164
+ IT infrastructure to bridge gaps and enhance collaboration between IT and functional
165
+ teams. The Infrastructure Engineering Manager is able to address multi-faceted
166
+ issues effectively to ensure systems are stable and secure. He adopts a methodical
167
+ approach to managing project resources and communicates well to his team and key
168
+ stakeholders on the solutions developed.
169
+ sentences:
170
+ - The Infrastructure Engineering Manager oversees the coordination of marketing
171
+ campaigns and manages the allocation of creative resources to ensure brand visibility
172
+ and engagement. He/She develops strategies for promotional activities and evaluates
173
+ marketing performance metrics; creates policies and sets expectations for campaign
174
+ execution. The manager identifies market trends and presents new advertising methodologies
175
+ to stakeholders to enhance the effectiveness of marketing initiatives. He has
176
+ expertise in the planning, execution, and analysis of marketing strategies across
177
+ digital, print, and social media platforms. He is familiar with the marketing
178
+ deployment processes, tools, and methodologies. He is knowledgeable in both creative
179
+ and analytical aspects of the organization’s marketing strategies to bridge gaps
180
+ and enhance collaboration between marketing and sales teams. The Infrastructure
181
+ Engineering Manager is able to address multifaceted marketing challenges effectively
182
+ to ensure brand consistency and engagement. He adopts a methodical approach to
183
+ managing creative resources and communicates well with his team and stakeholders
184
+ on the campaigns developed.
185
+ - The Business Valuation Executive plays a crucial role in delivering high-quality
186
+ valuation analyses. This position requires hands-on engagement with valuation
187
+ projects, ensuring adherence to ethical standards and quality assurance protocols.
188
+ The Business Valuation Executive is also involved in fostering business development
189
+ and maintaining strong relationships with stakeholders. While the candidate may
190
+ have limited experience, they are anticipated to navigate a challenging learning
191
+ journey to enhance their skills and knowledge in business valuation, particularly
192
+ in assessing intangible assets. Strong time management and effective communication
193
+ abilities are essential for success in this role.
194
+ - The Infrastructure Engineering Manager leads the execution of strategic initiatives
195
+ for infrastructure operations and maintenance, ensuring the reliability and security
196
+ of systems and networks. This role involves overseeing the allocation of project
197
+ resources and mentoring engineers focused on infrastructure implementation, operations,
198
+ and maintenance. The manager outlines policies, establishes performance standards,
199
+ and identifies challenges while proposing innovative methodologies and solutions
200
+ to key stakeholders to enhance the efficiency of infrastructure services. With
201
+ expertise in planning, implementing, and maintaining infrastructure systems across
202
+ various environments—cloud, on-premise, servers, and networks—the manager is well-versed
203
+ in deployment and IT service management processes, tools, and methodologies. This
204
+ individual possesses a strong understanding of both the technical and business
205
+ dimensions of the organization’s IT infrastructure, fostering collaboration between
206
+ IT and other functional teams. The Infrastructure Engineering Manager effectively
207
+ resolves complex issues to maintain system stability and security, employing a
208
+ systematic approach to resource management while ensuring clear communication
209
+ with team members and stakeholders regarding developed solutions.
210
+ - source_sentence: The Network Planning and Strategy Senior Technical Officer supervises
211
+ site suitability and pipe and equipment accessibility assessments to facilitate
212
+ network planning. He/She reviews the layouts, schematics and long-term development
213
+ plans for network projects, and performs simulation modelling of gas networks
214
+ to analyse performance. He carries out project activities that champion process
215
+ improvement and innovation. To build capabilities, he conducts on-the-job training
216
+ and identifies appropriate training and development courses for staff. He works
217
+ in a collaborative and intellectually-stimulating environment and occasionally
218
+ goes outdoors along pipelines for site surveys. He is a good team player and demonstrates
219
+ good planning and problem-solving skills in preparing network plans and strategies.
220
+ He possesses good interpersonal and communication skills to engage with key stakeholders.
221
+ sentences:
222
+ - The Assistant Engineer/Senior Technician (Operations and Maintenance) plays a
223
+ crucial role in facilitating the scheduling of corrective, preventive, and predictive
224
+ maintenance tasks to ensure that all equipment and systems operate efficiently
225
+ and effectively. This role adheres to corporate standards and industry best practices,
226
+ promoting a safe working environment while ensuring adherence to regulatory and
227
+ compliance mandates. The individual is responsible for implementing emergency
228
+ response strategies and complying with workplace safety and health (WSH) regulations.
229
+ A collaborative team player, he/she is skilled at engaging with both internal
230
+ and external stakeholders and demonstrates strong analytical and problem-solving
231
+ abilities. The position requires on-site work, which may include rotating shifts
232
+ or on-call duties.
233
+ - The Network Planning and Strategy Senior Technical Officer oversees the evaluation
234
+ of site suitability and accessibility for pipes and equipment to enhance network
235
+ planning. This role involves reviewing designs, schematics, and long-term development
236
+ strategies for network initiatives, as well as executing simulation modeling of
237
+ gas networks to assess their efficiency. He/She undertakes project activities
238
+ that promote process enhancements and innovative solutions. To foster development,
239
+ he/she provides on-the-job training and identifies suitable training programs
240
+ for staff. The position is set within a collaborative and intellectually stimulating
241
+ atmosphere, occasionally requiring site visits along pipelines for surveys. Strong
242
+ teamwork, planning, and problem-solving skills are essential for creating effective
243
+ network plans and strategies. Excellent interpersonal and communication skills
244
+ are necessary to effectively engage with key stakeholders.
245
+ - The Network Planning and Strategy Senior Technical Officer directs the evaluation
246
+ of site compliance and equipment installation assessments to ensure network efficiency.
247
+ He/She audits the designs, schematics, and immediate operational plans for network
248
+ tasks, and performs simulation testing of electrical circuits to assess functionality.
249
+ He carries out project activities that focus on compliance and regulatory adherence.
250
+ To enhance operational standards, he conducts online training and recommends unrelated
251
+ workshops for personnel. He operates in a solitary and technically rigid environment
252
+ and frequently remains indoors for office-based assessments. He is expected to
253
+ work independently and demonstrate limited planning and analytical skills in executing
254
+ network audits. He possesses minimal engagement skills to interact with external
255
+ stakeholders.
256
+ datasets:
257
+ - frankwong2001/ssf-train-valid-full-synthetic-v2
258
+ pipeline_tag: sentence-similarity
259
+ library_name: sentence-transformers
260
+ ---
261
+
262
+ # SentenceTransformer based on nomic-ai/modernbert-embed-base
263
+
264
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) on the [ssf-train-valid-full-synthetic-v2](https://huggingface.co/datasets/frankwong2001/ssf-train-valid-full-synthetic-v2) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
265
+
266
+ ## Model Details
267
+
268
+ ### Model Description
269
+ - **Model Type:** Sentence Transformer
270
+ - **Base model:** [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) <!-- at revision d556a88e332558790b210f7bdbe87da2fa94a8d8 -->
271
+ - **Maximum Sequence Length:** 8192 tokens
272
+ - **Output Dimensionality:** 768 dimensions
273
+ - **Similarity Function:** Cosine Similarity
274
+ - **Training Dataset:**
275
+ - [ssf-train-valid-full-synthetic-v2](https://huggingface.co/datasets/frankwong2001/ssf-train-valid-full-synthetic-v2)
276
+ <!-- - **Language:** Unknown -->
277
+ <!-- - **License:** Unknown -->
278
+
279
+ ### Model Sources
280
+
281
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
282
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
283
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
284
+
285
+ ### Full Model Architecture
286
+
287
+ ```
288
+ SentenceTransformer(
289
+ (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
290
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
291
+ (2): Normalize()
292
+ )
293
+ ```
294
+
295
+ ## Usage
296
+
297
+ ### Direct Usage (Sentence Transformers)
298
+
299
+ First install the Sentence Transformers library:
300
+
301
+ ```bash
302
+ pip install -U sentence-transformers
303
+ ```
304
+
305
+ Then you can load this model and run inference.
306
+ ```python
307
+ from sentence_transformers import SentenceTransformer
308
+
309
+ # Download from the 🤗 Hub
310
+ model = SentenceTransformer("frankwong2001/2_modernbert-embed-base")
311
+ # Run inference
312
+ sentences = [
313
+ 'The Network Planning and Strategy Senior Technical Officer supervises site suitability and pipe and equipment accessibility assessments to facilitate network planning. He/She reviews the layouts, schematics and long-term development plans for network projects, and performs simulation modelling of gas networks to analyse performance. He carries out project activities that champion process improvement and innovation. To build capabilities, he conducts on-the-job training and identifies appropriate training and development courses for staff. He works in a collaborative and intellectually-stimulating environment and occasionally goes outdoors along pipelines for site surveys. He is a good team player and demonstrates good planning and problem-solving skills in preparing network plans and strategies. He possesses good interpersonal and communication skills to engage with key stakeholders.',
314
+ 'The Network Planning and Strategy Senior Technical Officer oversees the evaluation of site suitability and accessibility for pipes and equipment to enhance network planning. This role involves reviewing designs, schematics, and long-term development strategies for network initiatives, as well as executing simulation modeling of gas networks to assess their efficiency. He/She undertakes project activities that promote process enhancements and innovative solutions. To foster development, he/she provides on-the-job training and identifies suitable training programs for staff. The position is set within a collaborative and intellectually stimulating atmosphere, occasionally requiring site visits along pipelines for surveys. Strong teamwork, planning, and problem-solving skills are essential for creating effective network plans and strategies. Excellent interpersonal and communication skills are necessary to effectively engage with key stakeholders.',
315
+ 'The Network Planning and Strategy Senior Technical Officer directs the evaluation of site compliance and equipment installation assessments to ensure network efficiency. He/She audits the designs, schematics, and immediate operational plans for network tasks, and performs simulation testing of electrical circuits to assess functionality. He carries out project activities that focus on compliance and regulatory adherence. To enhance operational standards, he conducts online training and recommends unrelated workshops for personnel. He operates in a solitary and technically rigid environment and frequently remains indoors for office-based assessments. He is expected to work independently and demonstrate limited planning and analytical skills in executing network audits. He possesses minimal engagement skills to interact with external stakeholders.',
316
+ ]
317
+ embeddings = model.encode(sentences)
318
+ print(embeddings.shape)
319
+ # [3, 768]
320
+
321
+ # Get the similarity scores for the embeddings
322
+ similarities = model.similarity(embeddings, embeddings)
323
+ print(similarities)
324
+ # tensor([[1.0000, 0.9498, 0.5232],
325
+ # [0.9498, 1.0000, 0.5047],
326
+ # [0.5232, 0.5047, 1.0000]])
327
+ ```
328
+
329
+ <!--
330
+ ### Direct Usage (Transformers)
331
+
332
+ <details><summary>Click to see the direct usage in Transformers</summary>
333
+
334
+ </details>
335
+ -->
336
+
337
+ <!--
338
+ ### Downstream Usage (Sentence Transformers)
339
+
340
+ You can finetune this model on your own dataset.
341
+
342
+ <details><summary>Click to expand</summary>
343
+
344
+ </details>
345
+ -->
346
+
347
+ <!--
348
+ ### Out-of-Scope Use
349
+
350
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
351
+ -->
352
+
353
+ <!--
354
+ ## Bias, Risks and Limitations
355
+
356
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
357
+ -->
358
+
359
+ <!--
360
+ ### Recommendations
361
+
362
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
363
+ -->
364
+
365
+ ## Training Details
366
+
367
+ ### Training Dataset
368
+
369
+ #### ssf-train-valid-full-synthetic-v2
370
+
371
+ * Dataset: [ssf-train-valid-full-synthetic-v2](https://huggingface.co/datasets/frankwong2001/ssf-train-valid-full-synthetic-v2) at [dc8851d](https://huggingface.co/datasets/frankwong2001/ssf-train-valid-full-synthetic-v2/tree/dc8851d3b29c0127f1c2d521e73a8d34a91aa520)
372
+ * Size: 3,016 training samples
373
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
374
+ * Approximate statistics based on the first 1000 samples:
375
+ | | anchor | positive | negative |
376
+ |:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
377
+ | type | string | string | string |
378
+ | details | <ul><li>min: 57 tokens</li><li>mean: 167.95 tokens</li><li>max: 403 tokens</li></ul> | <ul><li>min: 51 tokens</li><li>mean: 161.03 tokens</li><li>max: 369 tokens</li></ul> | <ul><li>min: 55 tokens</li><li>mean: 132.91 tokens</li><li>max: 354 tokens</li></ul> |
379
+ * Samples:
380
+ | anchor | positive | negative |
381
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
382
+ | <code>The Operations Manager (Fleet Management) develops aircraft lifecycle management programmes including planning for aviation asset management and strategising improvements to aircraft fleet services. He/She develops reliable maintenance programme strategy for aircraft fleet and optimises maintenance plans to fulfil customer and business requirements. He manages conformance of aircraft maintenance to original equipment manufacturer (OEM), customer and regulatory requirements to ensure continuous airworthiness management for the aircraft fleet. He is responsible for establishing work instructions, quality control and workflow improvements to enhance the organisation's productivity. He supervises all maintenance personnel in optimising utilisation of available manpower and other resources to meet functional, business, and organisational objectives. He drives team performance to achieve business key performance indicators (KPIs) and leads talent recruitment and development plans. He drives ...</code> | <code>The Operations Manager (Fleet Management) is responsible for creating and overseeing aircraft lifecycle management initiatives, which include strategic planning for aviation asset management and enhancing aircraft fleet services. This role requires the development of effective maintenance programme strategies for the aircraft fleet, ensuring that maintenance plans align with both customer needs and business objectives. The manager ensures that aircraft maintenance adheres to the standards set by the original equipment manufacturer (OEM), as well as customer and regulatory guidelines, to maintain continuous airworthiness. Additionally, the Operations Manager establishes clear work instructions, implements quality control measures, and drives workflow improvements to boost the organisation's productivity. Supervision of maintenance staff is crucial to optimize the use of manpower and resources in achieving functional and business goals. The manager fosters team performance to meet key pe...</code> | <code>The Operations Manager (Fleet Management) is tasked with developing customer service strategies for aircraft passenger handling operations, focusing on enhancing the passenger experience through service improvements and relationship management. This role involves creating innovative marketing plans to attract new customers while ensuring compliance with hospitality standards and regulations. The manager oversees a team of customer service agents to optimize guest engagement and satisfaction, ensuring that all interactions meet the organization's service quality benchmarks. He/She is responsible for training personnel in customer interaction techniques and establishing service protocols to maintain high standards of customer care. The Operations Manager also analyzes customer feedback to identify service gaps and implement corrective actions, driving performance to achieve satisfaction metrics. Collaboration with sales and marketing teams is essential to align efforts in promoting the o...</code> |
383
+ | <code>The Family Office Advisor - Private Banking is responsible for advising and providing support to the operations of a family office. A family office may assume wide-ranging responsibilities, including managing or overseeing family governance and succession planning, corporate finance and investment management, providing tax planning, concierge services, philanthropy, trust and corporate services, as well as managing operational aspects such as compliance and risk management. The Family Office Advisor - Private Banking should thus possess broad-based knowledge and skills sets, including relevant soft skills, across these diverse areas, to be able to work with family office professionals and other solution providers to address the family's needs.</code> | <code>The Family Office Consultant - Wealth Management is tasked with guiding and assisting the operations of a family office. This role encompasses a variety of responsibilities, including overseeing family governance and succession strategies, managing corporate finance and investment portfolios, offering tax advisory services, and facilitating philanthropy initiatives. The Family Office Consultant - Wealth Management should have extensive knowledge and a diverse skill set, including essential interpersonal abilities, to collaborate effectively with family office teams and other service providers to meet the family's requirements.</code> | <code>The Family Office Analyst - Investment Banking is responsible for analyzing and reporting on the financial performance of a family office. This role primarily focuses on evaluating investment opportunities, managing compliance with regulatory standards, and preparing detailed financial models. The Family Office Analyst - Investment Banking should possess strong quantitative skills and analytical expertise, with an emphasis on technical proficiency in financial software, to support the family office's strategic investment decisions and operational efficiencies.</code> |
384
+ | <code>A Director of Nursing in the Clinical sub-track works with the Chief Nurse to enable nurses to practice to the full extent of their education and training in an evolving healthcare landscape. S/He constantly scans the environment for new models of care or expansion of the scope of practice for all nursing professional groups. S/He works with relevant authorities on the barriers to practices. S/He has oversight of nursing clinical developments and promotes evidence-based care. S/He oversees systemic and local interventions for value and safe patient care. S/He leads nursing alignment to national priority of Beyond Hospital to Community. S/He operates in a wide variety of settings such as acute care, primary care, and community care. S/He practises evidence-based care, demonstrates clinical leadership; is an effective communicator, and a role model of care values and beliefs to nurses aspiring to clinical developments. S/He is conversant with acute and long-term models of care.</code> | <code>Description<br>The Director of Nursing collaborates closely with the Chief Nurse to empower nursing professionals to fully utilize their educational background and skills in a dynamic healthcare environment. They consistently monitor the landscape for innovative care models and opportunities to broaden the practice scope for various nursing groups. The Director engages with pertinent authorities to address practice barriers and ensures comprehensive oversight of clinical nursing advancements while advocating for evidence-based care. They implement systemic and localized strategies to enhance patient safety and value in care delivery. Additionally, they lead nursing initiatives aligned with the national vision of transitioning from hospital to community care. This role encompasses a diverse range of settings, including acute care, primary care, and community health. They exemplify evidence-based practices, exhibit strong clinical leadership, and serve as a communicator and role model for c...</code> | <code>Description<br>The Director of Nursing oversees the Chief Medical Officer to restrict nurses from utilizing their full educational qualifications in a stagnant healthcare environment. They frequently ignore emerging care models and limit the scope of practice for nursing professionals. The Director avoids interaction with authorities regarding practice barriers and neglects the oversight of nursing clinical advancements, promoting outdated care practices instead. They concentrate solely on individual interventions rather than systemic changes for patient care. Furthermore, they resist alignment with national health priorities, focusing exclusively on hospital settings without consideration for community care. The role lacks emphasis on evidence-based practices and clinical leadership, failing to inspire nurses and disregarding essential care values. Familiarity with only acute care models is prioritized, with no regard for long-term care practices.</code> |
385
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
386
+ ```json
387
+ {
388
+ "scale": 20.0,
389
+ "similarity_fct": "cos_sim",
390
+ "gather_across_devices": false
391
+ }
392
+ ```
393
+
394
+ ### Evaluation Dataset
395
+
396
+ #### ssf-train-valid-full-synthetic-v2
397
+
398
+ * Dataset: [ssf-train-valid-full-synthetic-v2](https://huggingface.co/datasets/frankwong2001/ssf-train-valid-full-synthetic-v2) at [dc8851d](https://huggingface.co/datasets/frankwong2001/ssf-train-valid-full-synthetic-v2/tree/dc8851d3b29c0127f1c2d521e73a8d34a91aa520)
399
+ * Size: 754 evaluation samples
400
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
401
+ * Approximate statistics based on the first 754 samples:
402
+ | | anchor | positive | negative |
403
+ |:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
404
+ | type | string | string | string |
405
+ | details | <ul><li>min: 73 tokens</li><li>mean: 168.6 tokens</li><li>max: 380 tokens</li></ul> | <ul><li>min: 73 tokens</li><li>mean: 161.25 tokens</li><li>max: 323 tokens</li></ul> | <ul><li>min: 62 tokens</li><li>mean: 133.1 tokens</li><li>max: 289 tokens</li></ul> |
406
+ * Samples:
407
+ | anchor | positive | negative |
408
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
409
+ | <code>The Director works in the field of social work management. He/She should have expertise and experience in domains under social work management in to supervise strategic initiatives, corporate governance, resource management, organisation and capability development. He develops and reviews framework for the organisations operating guidelines and standards, directs the implementation of corporate policies in accordance with governance regulations and drives improvements to the service delivery and operational efficiency. He is responsible for developing resource allocation and human resource management systems as well as fostering collaborations with external agencies. A highly experienced management staff who possesses excellent management and leadership skills, the Director works in institutional settings, communities, Voluntary Welfare Organisations and hospitals. He also works in collaboration with other agencies and ministries in the course of his work.</code> | <code>The Director oversees the management of social work initiatives. This role requires extensive knowledge and background in social work management to guide strategic projects, ensure corporate governance, manage resources, and enhance organizational capabilities. The Director formulates and assesses frameworks for operational guidelines and standards, leads the execution of corporate policies in alignment with governance standards, and promotes enhancements in service delivery and operational effectiveness. Additionally, this position is accountable for developing systems for resource allocation and human resource management, while also building partnerships with external organizations. A seasoned management professional with exceptional leadership and management abilities, the Director operates within institutional environments, community settings, Voluntary Welfare Organizations, and healthcare facilities, collaborating with various agencies and ministries throughout their responsibili...</code> | <code>The Director manages corporate training initiatives in the field of educational administration. He/She should possess knowledge and experience in training development to oversee strategic programs, compliance regulations, resource allocation, and organizational effectiveness. He creates and evaluates policies for educational standards and guidelines, directs the execution of training procedures in line with industry regulations, and drives enhancements to program delivery and operational effectiveness. He is responsible for developing training frameworks and staff management systems as well as fostering partnerships with educational institutions. A highly skilled professional with excellent training and development skills, the Director works in academic settings, corporate training environments, Non-Profit Organizations, and educational institutions, collaborating with different stakeholders and regulatory bodies throughout his work.</code> |
410
+ | <code>The Associate User Experience Designer assists in the design of user journeys and development of wireframes, ensuring design work is consistent with design and brand standards, analytics insights and customer feedback. He/She coordinates consultation sessions with stakeholders to gather requirements and needs, conducts research on user needs and behaviours, market and industry trends, as well as comparable experiences to support development of user experience (UX). He assists in usability assessments and tests, and analyses the pros and cons of refinements and iterations. He works under supervision to effectively deal with unfamiliar issues. He is knowledgeable of user experience design methodologies and familiar with relevant design tools and software. The Associate UX Designer is analytical in the evaluation of user feedback and offers new and fresh perspectives and suggestions to optimise the user experience. He is articulate and comfortable with brainstorming and putting forth his ...</code> | <code>The Associate User Experience Designer plays a crucial role in crafting user journeys and creating wireframes, ensuring that all design outputs align with brand guidelines, analytical data, and user feedback. This position involves coordinating with stakeholders to gather essential requirements, conducting thorough research on user needs and behaviors, as well as exploring market trends and analogous experiences to enhance user experience (UX) development. The designer aids in usability testing and evaluations, assessing the strengths and weaknesses of various iterations. Working under guidance, they adeptly navigate unfamiliar challenges. Proficient in user experience design methodologies and proficient with relevant design tools, the Associate UX Designer applies analytical skills to interpret user feedback, providing innovative ideas and recommendations to enhance the overall user experience. They effectively communicate and collaborate with team members and stakeholders, fostering ...</code> | <code>The Associate User Experience Designer manages the compliance of user data and oversees the implementation of security measures to ensure the protection of sensitive information. This role involves organizing training sessions for staff on data privacy protocols and conducting audits to assess adherence to regulatory standards. The designer evaluates the effectiveness of various compliance strategies and reports findings to senior management. They work independently to resolve complex regulatory issues and are well-versed in compliance frameworks and legal requirements. The Associate Compliance Designer is methodical in their approach to auditing processes and provides detailed recommendations for policy improvements. They are skilled in documentation and present findings to internal teams and external regulators to ensure a thorough understanding of compliance obligations.</code> |
411
+ | <code>The Engineering Head (Mechanical and Electrical) is a technical subject matter expert in mechanical and electrical systems within the organisation. He/She represents the organisation in interfacing with internal and/or external stakeholders to implement mechanical and electrical systems-related strategies. His duties also include translating and aligning established industry standards into department Key Performance Indicators (KPIs). He has a strong understanding of the leading engineering practices, operational best practices, industry developments and regulatory requirements, and he translates it to organisation practices and performance requirements. He possesses strong leadership skills, is able to cultivate a culture of continuous improvement and demonstrates excellent management skills to achieve the departments operational and functional objectives.</code> | <code>The Engineering Head (Mechanical and Electrical) serves as a vital technical expert in the realm of mechanical and electrical systems for the organization. This role involves engaging with both internal and external stakeholders to execute strategies related to mechanical and electrical systems. Key responsibilities include translating established industry standards into departmental Key Performance Indicators (KPIs) and ensuring alignment with operational best practices. A deep understanding of leading engineering methodologies, industry advancements, and regulatory frameworks is essential, as the individual will adapt these insights to enhance organizational practices and performance metrics. Strong leadership capabilities, a commitment to fostering a culture of continuous improvement, and exemplary management skills are crucial for achieving the department's operational and functional goals.</code> | <code>The Engineering Head (Mechanical and Electrical) acts as a project manager for software development initiatives within the organization. He/She collaborates with various teams to drive software-related strategies and oversee the integration of new technologies. Responsibilities include setting performance metrics that align with software development cycles and adapting industry trends to improve project outcomes. A solid grasp of software engineering concepts, agile methodologies, and compliance standards is important, as the role requires implementing these into the organization's software practices. Excellent communication skills, the ability to promote a culture of innovation, and proficient project management abilities are necessary to meet the software team's objectives.</code> |
412
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
413
+ ```json
414
+ {
415
+ "scale": 20.0,
416
+ "similarity_fct": "cos_sim",
417
+ "gather_across_devices": false
418
+ }
419
+ ```
420
+
421
+ ### Training Hyperparameters
422
+ #### Non-Default Hyperparameters
423
+
424
+ - `eval_strategy`: epoch
425
+ - `per_device_train_batch_size`: 32
426
+ - `per_device_eval_batch_size`: 16
427
+ - `gradient_accumulation_steps`: 16
428
+ - `learning_rate`: 2e-05
429
+ - `num_train_epochs`: 5
430
+ - `lr_scheduler_type`: cosine
431
+ - `warmup_ratio`: 0.1
432
+ - `bf16`: True
433
+ - `tf32`: False
434
+ - `load_best_model_at_end`: True
435
+ - `batch_sampler`: no_duplicates
436
+
437
+ #### All Hyperparameters
438
+ <details><summary>Click to expand</summary>
439
+
440
+ - `overwrite_output_dir`: False
441
+ - `do_predict`: False
442
+ - `eval_strategy`: epoch
443
+ - `prediction_loss_only`: True
444
+ - `per_device_train_batch_size`: 32
445
+ - `per_device_eval_batch_size`: 16
446
+ - `per_gpu_train_batch_size`: None
447
+ - `per_gpu_eval_batch_size`: None
448
+ - `gradient_accumulation_steps`: 16
449
+ - `eval_accumulation_steps`: None
450
+ - `torch_empty_cache_steps`: None
451
+ - `learning_rate`: 2e-05
452
+ - `weight_decay`: 0.0
453
+ - `adam_beta1`: 0.9
454
+ - `adam_beta2`: 0.999
455
+ - `adam_epsilon`: 1e-08
456
+ - `max_grad_norm`: 1.0
457
+ - `num_train_epochs`: 5
458
+ - `max_steps`: -1
459
+ - `lr_scheduler_type`: cosine
460
+ - `lr_scheduler_kwargs`: {}
461
+ - `warmup_ratio`: 0.1
462
+ - `warmup_steps`: 0
463
+ - `log_level`: passive
464
+ - `log_level_replica`: warning
465
+ - `log_on_each_node`: True
466
+ - `logging_nan_inf_filter`: True
467
+ - `save_safetensors`: True
468
+ - `save_on_each_node`: False
469
+ - `save_only_model`: False
470
+ - `restore_callback_states_from_checkpoint`: False
471
+ - `no_cuda`: False
472
+ - `use_cpu`: False
473
+ - `use_mps_device`: False
474
+ - `seed`: 42
475
+ - `data_seed`: None
476
+ - `jit_mode_eval`: False
477
+ - `use_ipex`: False
478
+ - `bf16`: True
479
+ - `fp16`: False
480
+ - `fp16_opt_level`: O1
481
+ - `half_precision_backend`: auto
482
+ - `bf16_full_eval`: False
483
+ - `fp16_full_eval`: False
484
+ - `tf32`: False
485
+ - `local_rank`: 0
486
+ - `ddp_backend`: None
487
+ - `tpu_num_cores`: None
488
+ - `tpu_metrics_debug`: False
489
+ - `debug`: []
490
+ - `dataloader_drop_last`: False
491
+ - `dataloader_num_workers`: 0
492
+ - `dataloader_prefetch_factor`: None
493
+ - `past_index`: -1
494
+ - `disable_tqdm`: False
495
+ - `remove_unused_columns`: True
496
+ - `label_names`: None
497
+ - `load_best_model_at_end`: True
498
+ - `ignore_data_skip`: False
499
+ - `fsdp`: []
500
+ - `fsdp_min_num_params`: 0
501
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
502
+ - `fsdp_transformer_layer_cls_to_wrap`: None
503
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
504
+ - `deepspeed`: None
505
+ - `label_smoothing_factor`: 0.0
506
+ - `optim`: adamw_torch_fused
507
+ - `optim_args`: None
508
+ - `adafactor`: False
509
+ - `group_by_length`: False
510
+ - `length_column_name`: length
511
+ - `ddp_find_unused_parameters`: None
512
+ - `ddp_bucket_cap_mb`: None
513
+ - `ddp_broadcast_buffers`: False
514
+ - `dataloader_pin_memory`: True
515
+ - `dataloader_persistent_workers`: False
516
+ - `skip_memory_metrics`: True
517
+ - `use_legacy_prediction_loop`: False
518
+ - `push_to_hub`: False
519
+ - `resume_from_checkpoint`: None
520
+ - `hub_model_id`: None
521
+ - `hub_strategy`: every_save
522
+ - `hub_private_repo`: None
523
+ - `hub_always_push`: False
524
+ - `hub_revision`: None
525
+ - `gradient_checkpointing`: False
526
+ - `gradient_checkpointing_kwargs`: None
527
+ - `include_inputs_for_metrics`: False
528
+ - `include_for_metrics`: []
529
+ - `eval_do_concat_batches`: True
530
+ - `fp16_backend`: auto
531
+ - `push_to_hub_model_id`: None
532
+ - `push_to_hub_organization`: None
533
+ - `mp_parameters`:
534
+ - `auto_find_batch_size`: False
535
+ - `full_determinism`: False
536
+ - `torchdynamo`: None
537
+ - `ray_scope`: last
538
+ - `ddp_timeout`: 1800
539
+ - `torch_compile`: False
540
+ - `torch_compile_backend`: None
541
+ - `torch_compile_mode`: None
542
+ - `include_tokens_per_second`: False
543
+ - `include_num_input_tokens_seen`: False
544
+ - `neftune_noise_alpha`: None
545
+ - `optim_target_modules`: None
546
+ - `batch_eval_metrics`: False
547
+ - `eval_on_start`: False
548
+ - `use_liger_kernel`: False
549
+ - `liger_kernel_config`: None
550
+ - `eval_use_gather_object`: False
551
+ - `average_tokens_across_devices`: False
552
+ - `prompts`: None
553
+ - `batch_sampler`: no_duplicates
554
+ - `multi_dataset_batch_sampler`: proportional
555
+ - `router_mapping`: {}
556
+ - `learning_rate_mapping`: {}
557
+
558
+ </details>
559
+
560
+ ### Training Logs
561
+ | Epoch | Step | Training Loss | Validation Loss |
562
+ |:-------:|:------:|:-------------:|:---------------:|
563
+ | 1.0 | 6 | 0.234 | 0.0275 |
564
+ | 2.0 | 12 | 0.0171 | 0.0059 |
565
+ | 3.0 | 18 | 0.0064 | 0.0039 |
566
+ | 4.0 | 24 | 0.0057 | 0.0033 |
567
+ | **5.0** | **30** | **0.0049** | **0.0033** |
568
+
569
+ * The bold row denotes the saved checkpoint.
570
+
571
+ ### Framework Versions
572
+ - Python: 3.12.11
573
+ - Sentence Transformers: 5.1.0
574
+ - Transformers: 4.55.0
575
+ - PyTorch: 2.8.0+cu128
576
+ - Accelerate: 1.10.0
577
+ - Datasets: 4.0.0
578
+ - Tokenizers: 0.21.4
579
+
580
+ ## Citation
581
+
582
+ ### BibTeX
583
+
584
+ #### Sentence Transformers
585
+ ```bibtex
586
+ @inproceedings{reimers-2019-sentence-bert,
587
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
588
+ author = "Reimers, Nils and Gurevych, Iryna",
589
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
590
+ month = "11",
591
+ year = "2019",
592
+ publisher = "Association for Computational Linguistics",
593
+ url = "https://arxiv.org/abs/1908.10084",
594
+ }
595
+ ```
596
+
597
+ #### MultipleNegativesRankingLoss
598
+ ```bibtex
599
+ @misc{henderson2017efficient,
600
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
601
+ 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},
602
+ year={2017},
603
+ eprint={1705.00652},
604
+ archivePrefix={arXiv},
605
+ primaryClass={cs.CL}
606
+ }
607
+ ```
608
+
609
+ <!--
610
+ ## Glossary
611
+
612
+ *Clearly define terms in order to be accessible across audiences.*
613
+ -->
614
+
615
+ <!--
616
+ ## Model Card Authors
617
+
618
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
619
+ -->
620
+
621
+ <!--
622
+ ## Model Card Contact
623
+
624
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
625
+ -->
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 50282,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1152,
25
+ "layer_norm_eps": 1e-05,
26
+ "local_attention": 128,
27
+ "local_rope_theta": 10000.0,
28
+ "max_position_embeddings": 8192,
29
+ "mlp_bias": false,
30
+ "mlp_dropout": 0.0,
31
+ "model_type": "modernbert",
32
+ "norm_bias": false,
33
+ "norm_eps": 1e-05,
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 22,
36
+ "pad_token_id": 50283,
37
+ "position_embedding_type": "absolute",
38
+ "repad_logits_with_grad": false,
39
+ "sep_token_id": 50282,
40
+ "sparse_pred_ignore_index": -100,
41
+ "sparse_prediction": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.55.0",
44
+ "vocab_size": 50368
45
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "5.1.0",
4
+ "transformers": "4.55.0",
5
+ "pytorch": "2.8.0+cu128"
6
+ },
7
+ "prompts": {
8
+ "query": "",
9
+ "document": ""
10
+ },
11
+ "default_prompt_name": null,
12
+ "similarity_fn_name": "cosine",
13
+ "model_type": "SentenceTransformer"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2cf49af4abaec4b56eef0fb8e15c58846a9a30a3b662471c2337ff65343a399
3
+ size 596070136
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
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": true,
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 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 8192,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizerFast",
944
+ "unk_token": "[UNK]"
945
+ }