dnth commited on
Commit
2de8e72
·
verified ·
1 Parent(s): 58d4592

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 +1,633 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:6032
9
+ - loss:MultipleNegativesRankingLoss
10
+ base_model: nomic-ai/modernbert-embed-base
11
+ widget:
12
+ - source_sentence: A Principal Physiotherapy Researcher is responsible for planning
13
+ research projects related to physiotherapy and healthcare. S/He identifies potential
14
+ research areas and designs research projects. S/He leads grant application processes
15
+ to secure research resources and partners with external organisations for research
16
+ projects. S/He serves as the principal investigator in research projects of her/his
17
+ specialisation, assists in the publication of findings in peer reviewed journals
18
+ and presents research at local and international conferences. S/He may work in
19
+ various settings such as but not limited to public and private institutions, sports
20
+ teams, acute hospitals, community hospitals, rehabilitation centres, voluntary
21
+ welfare organisations, schools, integrated and long-term care facilities and clients
22
+ homes and work environments. S/He may also work as part of a collaborative, interdisciplinary
23
+ team which may include teachers, nurses, doctors, audiologists, psychologists,
24
+ social workers, occupational therapists and speech therapists. S/He may collaborate
25
+ with research institutions to advance her/his research. S/He should be analytical,
26
+ inquisitive and innovative. S/He should possess time and project management skills.
27
+ sentences:
28
+ - The Principal Physiotherapy Researcher specializes in managing clinical physiotherapy
29
+ operations within acute care hospitals. This role focuses primarily on supervising
30
+ physiotherapy staff, coordinating patient treatment schedules, and ensuring adherence
31
+ to clinical protocols. Responsibilities include overseeing daily therapy sessions,
32
+ facilitating communication between therapists and medical teams, and maintaining
33
+ compliance with healthcare regulations. The researcher does not engage in grant
34
+ writing or research publication activities but instead emphasizes clinical service
35
+ delivery, staff training, and quality assurance. Strong leadership, organizational,
36
+ and interpersonal skills are required to optimize therapeutic outcomes and support
37
+ hospital administration.
38
+ - The Principal Physiotherapy Researcher leads the development and execution of
39
+ physiotherapy and healthcare research initiatives. This role involves identifying
40
+ key research opportunities, designing comprehensive studies, and spearheading
41
+ grant applications to secure necessary funding. The researcher acts as the chief
42
+ investigator on projects within their area of expertise, contributing to academic
43
+ publications and disseminating findings at both national and international forums.
44
+ Operating across diverse environments—including hospitals, rehabilitation centers,
45
+ sports organizations, educational institutions, and community settings—the researcher
46
+ collaborates with multidisciplinary teams comprising healthcare and social service
47
+ professionals. Proficiency in analytical thinking, innovation, and effective project
48
+ management is essential to successfully advance research objectives and foster
49
+ partnerships with external research bodies.
50
+ - The Engineer/Engineering Manager/Maintenance Manager utilises engineering expertise
51
+ to oversee the operation and upkeep of machinery within food manufacturing processes.
52
+ This role involves designing and implementing production lines for both new product
53
+ launches and improvements to existing food production capacity. The incumbent
54
+ stays current with technological advancements relevant to food processing and
55
+ maintains strong relationships with equipment suppliers to support the organisation’s
56
+ technical needs. Responsibilities include controlling production processes, ensuring
57
+ the reliability and sustainability of plant equipment through capacity planning,
58
+ resource management for maintenance activities, and making informed decisions
59
+ on equipment upgrades or retirements. The role demands a strong command of high-speed
60
+ production machinery, effective communication skills for team leadership, and
61
+ an analytical approach to promptly address equipment issues while adhering strictly
62
+ to food safety standards and Workplace Safety and Health regulations.
63
+ - source_sentence: The Senior Laboratory Chemist develops and validates new and improved
64
+ test methods and establishes improved analytical techniques for the purpose of
65
+ product testing and quality control. He/She liaises with government agencies,
66
+ testing laboratories and external suppliers on matters relating to regulatory
67
+ requirements, international standards and product specifications. He supports
68
+ laboratory operations by validating the technical specifications of new laboratory
69
+ equipment and providing guidance for the conduct of laboratory special projects.
70
+ The Senior Laboratory Chemist ensures the compliance of laboratory activities
71
+ with Workplace Safety and Health (WSH) and Environmental Management System (EMS)
72
+ requirements, by reviewing laboratory safe work practices and Standard Operating
73
+ Procedures (SOPs). He manages non-conformance by highlighting standard deviation
74
+ and product failure data to the quality assurance team. He validates continuous
75
+ improvement initiatives and activities for the laboratory, and provides coaching
76
+ and mentoring to the laboratory team. The Senior Laboratory Chemist leads a team
77
+ of chemists in the laboratory. He is able to multi-task, and possesses excellent
78
+ analytical, communication and interpersonal skills.
79
+ sentences:
80
+ - The Gas Systems Operations Principal Engineer is responsible for overseeing the
81
+ operational procedures of the system control center, gas transportation network,
82
+ and gas market to ensure uninterrupted gas supply in compliance with applicable
83
+ standards and protocols. This role leads comprehensive network analyses to assess
84
+ natural gas capacities across various networks and determines bookable capacities
85
+ for shippers. The engineer provides technical guidance on project requirements
86
+ related to gas system operations and evaluates response strategies for resolving
87
+ network abnormalities. Additionally, they supervise the technical accuracy of
88
+ management reports concerning market operations, injection tolerances, and nomination
89
+ variances, while defining load profiling methods for capacity certificates. They
90
+ develop and implement technical training programs to enhance team capabilities
91
+ and lead staff development initiatives. The role involves proposing emergency
92
+ technical responses and recovery actions aligned with the crisis management framework,
93
+ as well as assessing cyber incident severity to guide appropriate response measures,
94
+ including vulnerability assessments and penetration testing. Operating within
95
+ the control room environment, the engineer utilizes control panels, consoles,
96
+ and computer systems to manage gas operations, occasionally performing rotating
97
+ shifts to support 24/7 operations. Strong leadership and stakeholder engagement
98
+ skills are essential, alongside a systematic and approachable demeanor for mentoring
99
+ junior staff and ensuring effective emergency response and operational fault management.
100
+ - The Senior Laboratory Chemist is responsible for developing and refining analytical
101
+ methodologies to enhance product testing and quality assurance. This role involves
102
+ coordinating with regulatory bodies, external labs, and vendors to ensure alignment
103
+ with international standards and compliance requirements. The Senior Laboratory
104
+ Chemist oversees the validation of new laboratory instruments and guides special
105
+ technical projects within the lab. Ensuring adherence to Workplace Safety and
106
+ Health (WSH) and Environmental Management System (EMS) policies, this professional
107
+ reviews laboratory safety protocols and standard operating procedures. They monitor
108
+ deviations and product failures, collaborating closely with the quality assurance
109
+ team to address non-conformances. Additionally, the Senior Laboratory Chemist
110
+ drives continuous improvement efforts, while mentoring and leading a team of chemists.
111
+ Strong multitasking capabilities, along with excellent analytical, communication,
112
+ and interpersonal skills, are essential for success in this position.
113
+ - The Senior Quality Assurance Manager oversees the overall quality management system
114
+ for manufacturing operations, focusing on compliance with industry regulations
115
+ and customer requirements. This role directs cross-functional teams to implement
116
+ quality improvement initiatives, manages supplier quality programs, and ensures
117
+ that production processes meet established standards. The Senior Quality Assurance
118
+ Manager is responsible for developing company-wide quality policies, conducting
119
+ audits, and liaising with external certification bodies. Strong leadership, strategic
120
+ planning, and risk management skills are required to maintain high-quality standards
121
+ and support business objectives.
122
+ - source_sentence: The Producer - Broadcast leads the production of broadcast content
123
+ by managing the production operations and budgets, providing creative direction
124
+ to the production cast as well as overseeing post-production processes to lead
125
+ the content to completion. He/She is responsible for ensuring the script readiness
126
+ for production by collaborating with scriptwriters to develop the script in episodic
127
+ series. He oversees the filming of the content and provides creative direction
128
+ during filming. He manages the overall production operations, resolving issues
129
+ and recommending solutions to improve the operations. He performs creative as
130
+ well as management responsibilities and leads a team of roles responsible for
131
+ the creative coordination and logistical management of production. In some instances,
132
+ he is also responsible for hiring of the right cast for the production to enable
133
+ the achievement of the creative vision of the production. The work involves leading
134
+ projects or teams and provision of guidance to the production department in identifying
135
+ projects with high customer and/or audience appeal and monetisation potential.
136
+ He is expected to liaise with external and internal stakeholders. He should have
137
+ a flair for translating an idea or story into the desired end product. He needs
138
+ to have a pulse of the audience to understand the type of content would succeed
139
+ and should therefore be produced. He also needs to be an expert project manager
140
+ to deliver a project on time and within budget.
141
+ sentences:
142
+ - The Producer - Radio hosts live radio shows by engaging with listeners, curating
143
+ music playlists, and coordinating on-air content schedules. This role requires
144
+ excellent verbal communication skills and the ability to interact spontaneously
145
+ with callers and guests. The Producer manages show timings, ensures compliance
146
+ with broadcasting regulations specific to radio, and works closely with sound
147
+ engineers to maintain audio quality. Unlike television broadcast production, this
148
+ position focuses on audio-only content creation, requiring expertise in voice
149
+ modulation and live audience engagement rather than visual storytelling or filming.
150
+ The Producer also collaborates with marketing teams to promote radio programs
151
+ and reaches out to sponsors for advertising partnerships. Strong organizational
152
+ skills and adaptability are necessary to handle the dynamic nature of live radio
153
+ broadcasting.
154
+ - The Producer - Broadcast is responsible for overseeing the entire lifecycle of
155
+ broadcast content production, including managing budgets, directing creative efforts
156
+ with the cast, and supervising post-production activities to ensure the final
157
+ product meets quality standards. This role involves close collaboration with scriptwriters
158
+ to finalize scripts for episodic series and providing artistic guidance throughout
159
+ filming. The Producer manages production operations, troubleshoots challenges,
160
+ and implements improvements to streamline workflows. Leading a team that handles
161
+ both creative coordination and logistical tasks, the Producer may also participate
162
+ in casting decisions to align with the creative vision. Additionally, this position
163
+ requires strong project leadership skills to identify content with high audience
164
+ engagement and commercial potential, while maintaining effective communication
165
+ with both internal teams and external partners. A keen understanding of audience
166
+ preferences, coupled with expert project management abilities, is essential to
167
+ deliver successful productions on schedule and within allocated budgets.
168
+ - The Game Director leads the creative direction and overall vision of the game,
169
+ encompassing gameplay mechanics, narrative, audio design, cinematics, and promotional
170
+ content. Collaborating closely with senior team members, they help define the
171
+ game concept and transform the client’s brief into a cohesive creative strategy.
172
+ They oversee the integration of story, art, design, sound, and cinematic elements
173
+ to ensure consistent quality and vision throughout production. Acting as the key
174
+ creative decision-maker, the Game Director coordinates cross-departmental tasks
175
+ and manages approvals during development phases. Their role requires strong leadership,
176
+ excellent communication skills, and the ability to influence both internal teams
177
+ and external partners to achieve a unified, impactful game experience.
178
+ - source_sentence: The Principal Engineer/Engineering Manager (Engineering Train)
179
+ leads cross-functional teams in maintenance work involving engineering trains.
180
+ He/She also applies technical expertise to improve maintenance regime, provide
181
+ advice on engineering studies and new engineering initiatives, as well as the
182
+ engagement and management of external contractors. He is required to carry out
183
+ his duties at various train depots and workshops. He has excellent problem solving
184
+ and analytical skills, and applies his managerial skills to lead his team to fulfil
185
+ the responsibilities of operational and maintenance activities. He also facilitates
186
+ the implementation of organisational maintenance regimes and continuous improvement
187
+ initiatives.
188
+ sentences:
189
+ - The Senior Assistant Engineer/Assistant Engineer (Engineering Train) leads a team
190
+ responsible for conducting both preventive and corrective maintenance on engineering
191
+ trains. Proficient in operating calibration and diagnostic tools, this role also
192
+ involves enhancing maintenance procedures and overseeing team performance to meet
193
+ predefined Key Performance Indicators (KPIs). The position requires working on
194
+ rotating shifts across multiple train depots and workshops. Demonstrating strong
195
+ leadership and attention to detail, the engineer ensures strict adherence to workplace
196
+ safety protocols and maintains an organized environment during maintenance operations.
197
+ - The Principal Engineer/Project Manager (Rail Infrastructure) directs projects
198
+ focused on the development and expansion of rail infrastructure systems. This
199
+ position involves planning, budgeting, and supervising construction activities
200
+ rather than maintenance operations. The role requires expertise in civil engineering
201
+ design, contract negotiations, and stakeholder engagement with government agencies
202
+ and contractors. The incumbent primarily works at construction sites and corporate
203
+ offices, emphasizing project delivery timelines and regulatory compliance, without
204
+ direct involvement in train maintenance or operational management.
205
+ - The Principal Engineer/Engineering Manager (Engineering Train) oversees multidisciplinary
206
+ teams responsible for the upkeep and servicing of engineering trains. This role
207
+ demands the application of specialized technical knowledge to enhance maintenance
208
+ procedures, offer guidance on engineering research and innovative projects, and
209
+ coordinate with external contractors. The incumbent operates across multiple train
210
+ depots and workshops, demonstrating strong analytical and problem-solving capabilities.
211
+ Leadership acumen is essential to manage the team effectively in executing operational
212
+ and maintenance tasks, while also driving the adoption of organizational maintenance
213
+ standards and ongoing improvement programs.
214
+ - source_sentence: The Workshop Supervisor/Senior Foreman supervises multiple maintenance
215
+ teams in performing scheduled as well as routine preventive and corrective maintenance
216
+ of bus fleets. His/Her duties include planning and assigning maintenance teams
217
+ according to schedule, allocating prioritised maintenance and redirecting resources
218
+ to meet service requirements. He is also responsible for the deployment and coordination
219
+ of bus breakdown recovery teams. He coordinates the implementation of maintenance,
220
+ operations and safety audits across multiple maintenance teams, review maintenance
221
+ performances as well as recommends improvement initiatives to achieve established
222
+ Key Performance Indicators (KPIs). He is required to work in the bus workshop
223
+ and/or depot environment based on rotating shifts. He possesses excellent supervision
224
+ skills, takes a systematic approach to coordinate work activities across multiple
225
+ maintenance teams, and is resourceful to achieve maintenance targets and requirements.
226
+ sentences:
227
+ - The Harbour Pilot is responsible for guiding vessels safely into and out of the
228
+ port, coordinating berthing operations, and ensuring compliance with all maritime
229
+ safety regulations and emergency procedures. This role requires a valid Harbour
230
+ Pilot Licence from the Flag State authority and passing a colour vision assessment.
231
+ The Harbour Pilot must demonstrate strong analytical skills, excellent organisational
232
+ abilities, and effectively liaise with various port personnel to maintain smooth
233
+ and secure vessel navigation.
234
+ - The Workshop Planner coordinates the procurement and inventory management of spare
235
+ parts for bus maintenance but does not supervise maintenance teams. This role
236
+ focuses on forecasting parts requirements, liaising with suppliers, and managing
237
+ stock levels to prevent service disruptions. Unlike supervisory positions, the
238
+ planner operates primarily in an office environment, supporting workshop operations
239
+ through logistical and administrative tasks rather than direct team management
240
+ or on-site maintenance activities.
241
+ - The Workshop Supervisor/Senior Foreman oversees several maintenance crews responsible
242
+ for both planned and reactive upkeep of bus fleets. This role involves organizing
243
+ and dispatching teams following maintenance schedules, prioritizing tasks, and
244
+ reallocating resources to ensure service continuity. Additionally, the supervisor
245
+ manages breakdown recovery operations and facilitates maintenance, operational,
246
+ and safety audits across various teams. They evaluate maintenance outcomes and
247
+ suggest improvements to meet defined Key Performance Indicators (KPIs). The position
248
+ requires presence in bus workshops or depots, often on rotating shifts, and demands
249
+ strong leadership abilities, methodical coordination skills, and resourcefulness
250
+ to fulfill maintenance objectives.
251
+ datasets:
252
+ - dnth/ssf-train-valid-v4.1
253
+ pipeline_tag: sentence-similarity
254
+ library_name: sentence-transformers
255
+ ---
256
+
257
+ # SentenceTransformer based on nomic-ai/modernbert-embed-base
258
+
259
+ 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-v4.1](https://huggingface.co/datasets/dnth/ssf-train-valid-v4.1) 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.
260
+
261
+ ## Model Details
262
+
263
+ ### Model Description
264
+ - **Model Type:** Sentence Transformer
265
+ - **Base model:** [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) <!-- at revision d556a88e332558790b210f7bdbe87da2fa94a8d8 -->
266
+ - **Maximum Sequence Length:** 8192 tokens
267
+ - **Output Dimensionality:** 768 dimensions
268
+ - **Similarity Function:** Cosine Similarity
269
+ - **Training Dataset:**
270
+ - [ssf-train-valid-v4.1](https://huggingface.co/datasets/dnth/ssf-train-valid-v4.1)
271
+ <!-- - **Language:** Unknown -->
272
+ <!-- - **License:** Unknown -->
273
+
274
+ ### Model Sources
275
+
276
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
277
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
278
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
279
+
280
+ ### Full Model Architecture
281
+
282
+ ```
283
+ SentenceTransformer(
284
+ (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
285
+ (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})
286
+ (2): Normalize()
287
+ )
288
+ ```
289
+
290
+ ## Usage
291
+
292
+ ### Direct Usage (Sentence Transformers)
293
+
294
+ First install the Sentence Transformers library:
295
+
296
+ ```bash
297
+ pip install -U sentence-transformers
298
+ ```
299
+
300
+ Then you can load this model and run inference.
301
+ ```python
302
+ from sentence_transformers import SentenceTransformer
303
+
304
+ # Download from the 🤗 Hub
305
+ model = SentenceTransformer("dnth/ssf-retriever-modernbert-embed-base-v4.1")
306
+ # Run inference
307
+ sentences = [
308
+ 'The Workshop Supervisor/Senior Foreman supervises multiple maintenance teams in performing scheduled as well as routine preventive and corrective maintenance of bus fleets. His/Her duties include planning and assigning maintenance teams according to schedule, allocating prioritised maintenance and redirecting resources to meet service requirements. He is also responsible for the deployment and coordination of bus breakdown recovery teams. He coordinates the implementation of maintenance, operations and safety audits across multiple maintenance teams, review maintenance performances as well as recommends improvement initiatives to achieve established Key Performance Indicators (KPIs). He is required to work in the bus workshop and/or depot environment based on rotating shifts. He possesses excellent supervision skills, takes a systematic approach to coordinate work activities across multiple maintenance teams, and is resourceful to achieve maintenance targets and requirements.',
309
+ 'The Workshop Supervisor/Senior Foreman oversees several maintenance crews responsible for both planned and reactive upkeep of bus fleets. This role involves organizing and dispatching teams following maintenance schedules, prioritizing tasks, and reallocating resources to ensure service continuity. Additionally, the supervisor manages breakdown recovery operations and facilitates maintenance, operational, and safety audits across various teams. They evaluate maintenance outcomes and suggest improvements to meet defined Key Performance Indicators (KPIs). The position requires presence in bus workshops or depots, often on rotating shifts, and demands strong leadership abilities, methodical coordination skills, and resourcefulness to fulfill maintenance objectives.',
310
+ 'The Workshop Planner coordinates the procurement and inventory management of spare parts for bus maintenance but does not supervise maintenance teams. This role focuses on forecasting parts requirements, liaising with suppliers, and managing stock levels to prevent service disruptions. Unlike supervisory positions, the planner operates primarily in an office environment, supporting workshop operations through logistical and administrative tasks rather than direct team management or on-site maintenance activities.',
311
+ ]
312
+ embeddings = model.encode(sentences)
313
+ print(embeddings.shape)
314
+ # [3, 768]
315
+
316
+ # Get the similarity scores for the embeddings
317
+ similarities = model.similarity(embeddings, embeddings)
318
+ print(similarities)
319
+ # tensor([[1.0000, 0.8839, 0.4636],
320
+ # [0.8839, 1.0000, 0.4686],
321
+ # [0.4636, 0.4686, 1.0000]])
322
+ ```
323
+
324
+ <!--
325
+ ### Direct Usage (Transformers)
326
+
327
+ <details><summary>Click to see the direct usage in Transformers</summary>
328
+
329
+ </details>
330
+ -->
331
+
332
+ <!--
333
+ ### Downstream Usage (Sentence Transformers)
334
+
335
+ You can finetune this model on your own dataset.
336
+
337
+ <details><summary>Click to expand</summary>
338
+
339
+ </details>
340
+ -->
341
+
342
+ <!--
343
+ ### Out-of-Scope Use
344
+
345
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
346
+ -->
347
+
348
+ <!--
349
+ ## Bias, Risks and Limitations
350
+
351
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
352
+ -->
353
+
354
+ <!--
355
+ ### Recommendations
356
+
357
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
358
+ -->
359
+
360
+ ## Training Details
361
+
362
+ ### Training Dataset
363
+
364
+ #### ssf-train-valid-v4.1
365
+
366
+ * Dataset: [ssf-train-valid-v4.1](https://huggingface.co/datasets/dnth/ssf-train-valid-v4.1) at [b41efb0](https://huggingface.co/datasets/dnth/ssf-train-valid-v4.1/tree/b41efb0d379535244276178e5ef476e350858e03)
367
+ * Size: 6,032 training samples
368
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
369
+ * Approximate statistics based on the first 1000 samples:
370
+ | | anchor | positive | negative |
371
+ |:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
372
+ | type | string | string | string |
373
+ | details | <ul><li>min: 57 tokens</li><li>mean: 169.25 tokens</li><li>max: 403 tokens</li></ul> | <ul><li>min: 55 tokens</li><li>mean: 138.16 tokens</li><li>max: 267 tokens</li></ul> | <ul><li>min: 46 tokens</li><li>mean: 108.1 tokens</li><li>max: 205 tokens</li></ul> |
374
+ * Samples:
375
+ | anchor | positive | negative |
376
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
377
+ | <code>The Business Development Manager is responsible for managing business development strategy implementation. He/she implements market expansion and new market plans for business growth. By engaging key internal stakeholders, he supports cross-functional collaboration for business development activities. He also performs data analysis on partnerships, Joint Ventures (JV) and Mergers and Acquisitions (M&A) to expand the market share of the organisation. Independent and insightful, he possesses strong business acumen and is able to source for growth opportunities. He supports the proactive pursuit of growth opportunities by being aware of market trends, industry events, competitors' actions and clients' needs. He is also able to adapt strategies and plans to ensure success in a competitive and global market. He travels frequently, maintains rapport with potential and existing clients, and networks extensively outside of the office to develop business relationships.</code> | <code>The Business Development Manager leads the execution of strategies aimed at driving business expansion and entering new markets. Collaborating closely with key internal teams, this role fosters cross-departmental initiatives to support growth objectives. The manager conducts detailed analyses of partnerships, joint ventures, and mergers and acquisitions to enhance the company’s market presence. Demonstrating strong commercial insight and independent judgment, the incumbent identifies and capitalizes on new business opportunities. By staying informed of industry trends, competitor activities, and client requirements, the manager continuously refines strategies to maintain competitive advantage in a global marketplace. This position involves regular travel and active networking to build and sustain relationships with both prospective and current clients.</code> | <code>The Business Development Manager oversees the recruitment and onboarding processes within the human resources function of the company. He/she coordinates talent acquisition campaigns, manages employee relations, and ensures compliance with employment laws. The manager collaborates with department heads to assess staffing needs and develops training programs to enhance workforce capabilities. Responsible for maintaining HR records and administering benefits, the role requires strong interpersonal and organizational skills. Unlike a market-facing role, this position focuses primarily on internal employee management and does not involve external client engagement or market expansion activities.</code> |
378
+ | <code>The Head of Product defines the organisations product development vision and strategy, and ensures alignment of the product roadmap with the strategy and vision. He/She anticipates the impacts of internal and external business challenges and market conditions on the organisation's product development roadmap. He oversees the organisations product development process, and enhancements to product portfolios to improve their commercial performance. He guides development teams on issues related to the product design, development and deployment for the product portfolio, and development of differentiated strategies across the lines of business. He distils insights and competitive intelligence with various market analyses to grow the organisations business. He works with various teams across the organisation. He is knowledgeable of product development and management practices and tools, as well as product branding and pricing methodologies. He is also knowledgeable of new and emerging consum...</code> | <code>The Head of Product leads the company’s product vision and strategic direction, ensuring that the product roadmap aligns closely with overarching business objectives. This role involves anticipating how internal dynamics and market trends may affect product development plans. The Head of Product manages the full product lifecycle, driving enhancements that boost portfolio profitability and competitive positioning. They provide guidance to cross-functional teams on product design, development, and launch, fostering innovative strategies tailored to different business units. By synthesizing market intelligence and competitive analysis, they identify growth opportunities and shape the company’s product strategy. Collaborating extensively across departments, the Head of Product leverages expertise in product management methodologies, branding, and pricing strategies. They stay abreast of emerging consumer behaviors and industry trends, adopting a global perspective to shape a visionary pro...</code> | <code>The Head of Product manages the company’s internal communications and public relations strategy, ensuring all messaging aligns with the corporate brand and reputation goals. They monitor both internal and external communication channels to anticipate potential challenges and opportunities impacting the organization’s image. The Head of Product oversees the development of corporate messaging frameworks and media relations initiatives, guiding teams on content creation, media engagement, and crisis communication strategies. They analyze public sentiment and competitive communication tactics to enhance the company’s visibility. Working closely with marketing, legal, and executive teams, the Head of Product applies expertise in communication technologies and branding consistency. They stay informed about emerging communication trends and digital platforms, integrating global best practices to craft compelling narratives. As a persuasive and charismatic leader, they inspire communication te...</code> |
379
+ | <code>The Production Manager oversees all operations of the food production plant, with a focus on simplifying work processes, reducing costs and increasing production process efficiency. He/She is responsible for setting key performance indicators (KPI) for the production plant, and formulating new food production standards and standard operating procedures (SOPs). The Production Manager monitors quality assurance on an overall level, investigates production and/or quality issues and recommends solutions. He is required to go through training in internal food safety audits and serves on the organisation's food safety internal audit committee. He operates in a food production environment and may be required to work shifts. He should be comfortable with exposure to physically demanding work conditions (i.e. long standing hours, hot or cold temperatures).</code> | <code>The Production Manager is responsible for managing the entire food manufacturing facility, focusing on optimizing workflows, cutting operational costs, and enhancing production efficiency. This role involves establishing key performance metrics for the plant, developing updated standards and standard operating procedures for food production, and overseeing overall quality assurance. The Production Manager addresses production and quality concerns through thorough investigation and proposes effective corrective actions. Participation in internal food safety audit training and membership on the company’s food safety audit committee are essential. The role requires working in a food processing environment, which may include shift work and handling physically demanding conditions such as prolonged standing and exposure to varying temperatures.</code> | <code>The Production Supervisor directs daily operations within a pharmaceutical packaging facility, prioritizing compliance with drug safety regulations and maintaining equipment calibration. This position involves setting production targets, enforcing cleanroom protocols, and overseeing product labeling accuracy. The Production Supervisor conducts routine equipment inspections and coordinates with quality control teams to resolve packaging discrepancies. Training in pharmaceutical Good Manufacturing Practices (GMP) and participation in regulatory audit preparations are required. The role demands working in a controlled, sterile environment with adherence to strict hygiene standards and occasional shift work.</code> |
380
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
381
+ ```json
382
+ {
383
+ "scale": 20.0,
384
+ "similarity_fct": "cos_sim",
385
+ "gather_across_devices": false
386
+ }
387
+ ```
388
+
389
+ ### Evaluation Dataset
390
+
391
+ #### ssf-train-valid-v4.1
392
+
393
+ * Dataset: [ssf-train-valid-v4.1](https://huggingface.co/datasets/dnth/ssf-train-valid-v4.1) at [b41efb0](https://huggingface.co/datasets/dnth/ssf-train-valid-v4.1/tree/b41efb0d379535244276178e5ef476e350858e03)
394
+ * Size: 1,508 evaluation samples
395
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
396
+ * Approximate statistics based on the first 1000 samples:
397
+ | | anchor | positive | negative |
398
+ |:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
399
+ | type | string | string | string |
400
+ | details | <ul><li>min: 57 tokens</li><li>mean: 170.2 tokens</li><li>max: 403 tokens</li></ul> | <ul><li>min: 56 tokens</li><li>mean: 138.34 tokens</li><li>max: 266 tokens</li></ul> | <ul><li>min: 51 tokens</li><li>mean: 108.37 tokens</li><li>max: 236 tokens</li></ul> |
401
+ * Samples:
402
+ | anchor | positive | negative |
403
+ |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
404
+ | <code>The Capacity Manager oversee daily operations and review capacity forecasts and develops process improvements to maximise voyage yields. He/She develops cargo mixture strategies, based on profit maximisation and customer demand, and manages all vessel operations planning to optimise capacity utilisation, terminal operations, vessel utilisation, vessel movement and route adjustment strategies. He has a strong understanding of commercial and financial drivers in the shipping industry. He has strong leadership skills to manage multiple internal and external stakeholders and demonstrates commitment to exceptional customer service.</code> | <code>The Capacity Manager is responsible for managing daily operational activities and evaluating capacity projections to enhance voyage profitability. This role involves formulating cargo allocation plans aimed at maximizing profits and meeting customer needs, alongside coordinating vessel operation schedules to improve capacity use, terminal efficiency, vessel deployment, navigation, and routing strategies. The Capacity Manager possesses deep commercial and financial insight within the maritime sector and exhibits strong leadership abilities to coordinate diverse stakeholder groups while maintaining a high standard of customer service excellence.</code> | <code>The Capacity Planner coordinates warehouse inventory levels and supervises stock replenishment to meet retail demand forecasts. They focus on optimizing storage space usage, managing supplier schedules, and streamlining logistics processes for efficient product flow. The role requires proficiency in supply chain software and collaboration with procurement and distribution teams but does not involve vessel operations or maritime commercial analysis. Strong organizational skills and attention to detail are essential for ensuring timely delivery and inventory accuracy.</code> |
405
+ | <code>The Research Analyst is responsible for conducting research based on requirements and requests from various internal business units. He/She also facilitates investment processes by providing assumptions necessary for forecasting and investment recommendations based on the research conducted. The Research Analyst is self-motivated, driven and passionate about learning. He takes the initiative to share research outcomes that are useful to other business units. The role also requires him to be able to analyse and interpret information quickly and to condense and bring across complex research ideas and concepts in easily understandable terms.</code> | <code>The Research Analyst supports multiple internal departments by performing targeted research aligned with their specific needs. This role involves contributing to investment decision-making by supplying key assumptions that inform forecasting and asset allocation suggestions. The Research Analyst must be proactive, eager to expand their knowledge, and willing to disseminate valuable insights across teams. Strong analytical skills are essential for swiftly interpreting data and simplifying intricate research findings into clear, accessible language.</code> | <code>The Business Development Analyst focuses on identifying new market opportunities and building client relationships to drive revenue growth across various sectors. This role requires expertise in sales strategies, negotiation, and customer engagement rather than conducting in-depth research or investment analysis. The Business Development Analyst must be persuasive, target-driven, and skilled at presenting compelling business proposals to potential partners and stakeholders.</code> |
406
+ | <code>The Head of Chartering manages the chartering function and oversees a ship chartering team in the execution of the organisation's chartering business. He/She negotiates and/or evaluates potential business development opportunities and is able to synthesise complex concepts and information to distil them into actionable propositions. He is a self-motivated individual who works independently to lead a team and support their efforts in accomplishing goals, and provides guidance where necessary.</code> | <code>The Head of Chartering leads the ship chartering department, supervising a team responsible for executing the company’s chartering operations. This role involves assessing and negotiating new business ventures, translating intricate market data and insights into strategic actions. The individual is a proactive leader who independently drives team performance, offers direction to ensure objectives are met, and fosters a collaborative environment to achieve business targets.</code> | <code>The Head of Operations directs the vessel maintenance division, coordinating technical teams to ensure fleet readiness and compliance with maritime safety standards. This role focuses on overseeing repair schedules, managing maintenance budgets, and liaising with regulatory bodies to uphold operational excellence. The individual works closely with engineering staff to optimize vessel uptime and supports continuous improvement initiatives across the maintenance function.</code> |
407
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
408
+ ```json
409
+ {
410
+ "scale": 20.0,
411
+ "similarity_fct": "cos_sim",
412
+ "gather_across_devices": false
413
+ }
414
+ ```
415
+
416
+ ### Training Hyperparameters
417
+ #### Non-Default Hyperparameters
418
+
419
+ - `eval_strategy`: epoch
420
+ - `per_device_train_batch_size`: 16
421
+ - `per_device_eval_batch_size`: 32
422
+ - `gradient_accumulation_steps`: 32
423
+ - `learning_rate`: 2e-05
424
+ - `weight_decay`: 0.01
425
+ - `num_train_epochs`: 5
426
+ - `lr_scheduler_type`: cosine
427
+ - `warmup_ratio`: 0.1
428
+ - `bf16`: True
429
+ - `tf32`: True
430
+ - `load_best_model_at_end`: True
431
+ - `gradient_checkpointing`: True
432
+ - `batch_sampler`: no_duplicates
433
+
434
+ #### All Hyperparameters
435
+ <details><summary>Click to expand</summary>
436
+
437
+ - `overwrite_output_dir`: False
438
+ - `do_predict`: False
439
+ - `eval_strategy`: epoch
440
+ - `prediction_loss_only`: True
441
+ - `per_device_train_batch_size`: 16
442
+ - `per_device_eval_batch_size`: 32
443
+ - `per_gpu_train_batch_size`: None
444
+ - `per_gpu_eval_batch_size`: None
445
+ - `gradient_accumulation_steps`: 32
446
+ - `eval_accumulation_steps`: None
447
+ - `torch_empty_cache_steps`: None
448
+ - `learning_rate`: 2e-05
449
+ - `weight_decay`: 0.01
450
+ - `adam_beta1`: 0.9
451
+ - `adam_beta2`: 0.999
452
+ - `adam_epsilon`: 1e-08
453
+ - `max_grad_norm`: 1.0
454
+ - `num_train_epochs`: 5
455
+ - `max_steps`: -1
456
+ - `lr_scheduler_type`: cosine
457
+ - `lr_scheduler_kwargs`: {}
458
+ - `warmup_ratio`: 0.1
459
+ - `warmup_steps`: 0
460
+ - `log_level`: passive
461
+ - `log_level_replica`: warning
462
+ - `log_on_each_node`: True
463
+ - `logging_nan_inf_filter`: True
464
+ - `save_safetensors`: True
465
+ - `save_on_each_node`: False
466
+ - `save_only_model`: False
467
+ - `restore_callback_states_from_checkpoint`: False
468
+ - `no_cuda`: False
469
+ - `use_cpu`: False
470
+ - `use_mps_device`: False
471
+ - `seed`: 42
472
+ - `data_seed`: None
473
+ - `jit_mode_eval`: False
474
+ - `use_ipex`: False
475
+ - `bf16`: True
476
+ - `fp16`: False
477
+ - `fp16_opt_level`: O1
478
+ - `half_precision_backend`: auto
479
+ - `bf16_full_eval`: False
480
+ - `fp16_full_eval`: False
481
+ - `tf32`: True
482
+ - `local_rank`: 0
483
+ - `ddp_backend`: None
484
+ - `tpu_num_cores`: None
485
+ - `tpu_metrics_debug`: False
486
+ - `debug`: []
487
+ - `dataloader_drop_last`: False
488
+ - `dataloader_num_workers`: 0
489
+ - `dataloader_prefetch_factor`: None
490
+ - `past_index`: -1
491
+ - `disable_tqdm`: False
492
+ - `remove_unused_columns`: True
493
+ - `label_names`: None
494
+ - `load_best_model_at_end`: True
495
+ - `ignore_data_skip`: False
496
+ - `fsdp`: []
497
+ - `fsdp_min_num_params`: 0
498
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
499
+ - `fsdp_transformer_layer_cls_to_wrap`: None
500
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
501
+ - `deepspeed`: None
502
+ - `label_smoothing_factor`: 0.0
503
+ - `optim`: adamw_torch_fused
504
+ - `optim_args`: None
505
+ - `adafactor`: False
506
+ - `group_by_length`: False
507
+ - `length_column_name`: length
508
+ - `ddp_find_unused_parameters`: None
509
+ - `ddp_bucket_cap_mb`: None
510
+ - `ddp_broadcast_buffers`: False
511
+ - `dataloader_pin_memory`: True
512
+ - `dataloader_persistent_workers`: False
513
+ - `skip_memory_metrics`: True
514
+ - `use_legacy_prediction_loop`: False
515
+ - `push_to_hub`: False
516
+ - `resume_from_checkpoint`: None
517
+ - `hub_model_id`: None
518
+ - `hub_strategy`: every_save
519
+ - `hub_private_repo`: None
520
+ - `hub_always_push`: False
521
+ - `hub_revision`: None
522
+ - `gradient_checkpointing`: True
523
+ - `gradient_checkpointing_kwargs`: None
524
+ - `include_inputs_for_metrics`: False
525
+ - `include_for_metrics`: []
526
+ - `eval_do_concat_batches`: True
527
+ - `fp16_backend`: auto
528
+ - `push_to_hub_model_id`: None
529
+ - `push_to_hub_organization`: None
530
+ - `mp_parameters`:
531
+ - `auto_find_batch_size`: False
532
+ - `full_determinism`: False
533
+ - `torchdynamo`: None
534
+ - `ray_scope`: last
535
+ - `ddp_timeout`: 1800
536
+ - `torch_compile`: False
537
+ - `torch_compile_backend`: None
538
+ - `torch_compile_mode`: None
539
+ - `include_tokens_per_second`: False
540
+ - `include_num_input_tokens_seen`: False
541
+ - `neftune_noise_alpha`: None
542
+ - `optim_target_modules`: None
543
+ - `batch_eval_metrics`: False
544
+ - `eval_on_start`: False
545
+ - `use_liger_kernel`: False
546
+ - `liger_kernel_config`: None
547
+ - `eval_use_gather_object`: False
548
+ - `average_tokens_across_devices`: False
549
+ - `prompts`: None
550
+ - `batch_sampler`: no_duplicates
551
+ - `multi_dataset_batch_sampler`: proportional
552
+ - `router_mapping`: {}
553
+ - `learning_rate_mapping`: {}
554
+
555
+ </details>
556
+
557
+ ### Training Logs
558
+ | Epoch | Step | Training Loss | Validation Loss |
559
+ |:-------:|:------:|:-------------:|:---------------:|
560
+ | 0.4244 | 5 | 0.1542 | - |
561
+ | 0.8488 | 10 | 0.0158 | - |
562
+ | 1.0 | 12 | - | 0.0059 |
563
+ | 1.2546 | 15 | 0.0039 | - |
564
+ | 1.6790 | 20 | 0.0038 | - |
565
+ | 2.0 | 24 | - | 0.0033 |
566
+ | 2.0849 | 25 | 0.0033 | - |
567
+ | 2.5093 | 30 | 0.0017 | - |
568
+ | 2.9337 | 35 | 0.0012 | - |
569
+ | 3.0 | 36 | - | 0.0022 |
570
+ | 3.3395 | 40 | 0.0014 | - |
571
+ | 3.7639 | 45 | 0.0012 | - |
572
+ | 4.0 | 48 | - | 0.0020 |
573
+ | 4.1698 | 50 | 0.0011 | - |
574
+ | 4.5942 | 55 | 0.0022 | - |
575
+ | **5.0** | **60** | **0.0014** | **0.002** |
576
+
577
+ * The bold row denotes the saved checkpoint.
578
+
579
+ ### Framework Versions
580
+ - Python: 3.12.8
581
+ - Sentence Transformers: 5.1.0
582
+ - Transformers: 4.55.0
583
+ - PyTorch: 2.8.0+cu128
584
+ - Accelerate: 1.10.0
585
+ - Datasets: 4.0.0
586
+ - Tokenizers: 0.21.4
587
+
588
+ ## Citation
589
+
590
+ ### BibTeX
591
+
592
+ #### Sentence Transformers
593
+ ```bibtex
594
+ @inproceedings{reimers-2019-sentence-bert,
595
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
596
+ author = "Reimers, Nils and Gurevych, Iryna",
597
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
598
+ month = "11",
599
+ year = "2019",
600
+ publisher = "Association for Computational Linguistics",
601
+ url = "https://arxiv.org/abs/1908.10084",
602
+ }
603
+ ```
604
+
605
+ #### MultipleNegativesRankingLoss
606
+ ```bibtex
607
+ @misc{henderson2017efficient,
608
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
609
+ 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},
610
+ year={2017},
611
+ eprint={1705.00652},
612
+ archivePrefix={arXiv},
613
+ primaryClass={cs.CL}
614
+ }
615
+ ```
616
+
617
+ <!--
618
+ ## Glossary
619
+
620
+ *Clearly define terms in order to be accessible across audiences.*
621
+ -->
622
+
623
+ <!--
624
+ ## Model Card Authors
625
+
626
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
627
+ -->
628
+
629
+ <!--
630
+ ## Model Card Contact
631
+
632
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
633
+ -->
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:fb676baa217a7033c3bf41a1369163676e6e01a98fb55cbf2cc4054a3d3286e8
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
+ }