ChenyuEcho commited on
Commit
64cd842
·
verified ·
1 Parent(s): 78ed07b

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": true,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,975 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:816
9
+ - loss:MultipleNegativesRankingLoss
10
+ base_model: Qwen/Qwen3-Embedding-0.6B
11
+ widget:
12
+ - source_sentence: Search for evidence of regulators requesting clarification on barrel
13
+ aging logs for NOM-006-SCFI-2012 certification for batches 3124-A and 3125-B.
14
+ sentences:
15
+ - 'Subject: Exciting News: New Distribution Agreement Expands Our North American
16
+ Reach
17
+
18
+ Date: 2025-08-06T16:41:00
19
+
20
+ From: Thomas Tom Bradford
21
+
22
+ Participants: Sarah Mitchell; Kevin O''Brien; Patricia Reeves
23
+
24
+
25
+ Body:
26
+
27
+ Dear Executive Team,
28
+
29
+
30
+ I am pleased to announce that Agave Spirits International has finalized a new
31
+ distribution agreement with Pacific Spirits Group, targeting the U.S. West Coast
32
+ and Canadian markets. This partnership is expected to increase our premium product
33
+ presence by at least 35% over the next fiscal year, with flagship brands such
34
+ as Tequila Oro and Sierra Azul leading the portfolio. This strategic move positions
35
+ us for accelerated growth and strengthens our competitive advantage in crucial
36
+ markets.
37
+
38
+
39
+ I will share further details during our leadership call next week. In the meantime,
40
+ please begin preparing your teams to support the anticipated rollout in Q3. Your
41
+ collaboration is vital to ensuring a successful launch.
42
+
43
+
44
+ Thank you for your continued commitment and leadership.
45
+
46
+
47
+ Best regards,
48
+
49
+ Tom'
50
+ - 'Subject: Re: Inventory Discrepancy at Tequila Distillery – Proposal to Resolve
51
+
52
+ Date: 2025-11-21T10:30:00
53
+
54
+ From: Roberto Garza
55
+
56
+ Participants: Carlos Delgado
57
+
58
+
59
+ Body:
60
+
61
+ Hola Carlos,
62
+
63
+
64
+ Thank you for flagging this and for approaching it thoughtfully. I completely
65
+ agree that a recount with Pedro’s team is the right step—showing transparency
66
+ is key. Mañana at 10am works for me. Before we meet, could you or Pedro please
67
+ pull the detailed transfer logs from the last quarter? Having those on hand will
68
+ help clarify if this is a timing or recording issue. As you said, it’s likely
69
+ just a minor oversight, but it''s best we review all angles.
70
+
71
+
72
+ Looking forward to resolving this together with cafecito—appreciate the care you
73
+ both put into these matters.
74
+
75
+
76
+ Saludos,
77
+
78
+ Roberto'
79
+ - 'Subject: Quality Certification Requirements for Recent Batches – Clarification
80
+ Needed
81
+
82
+ Date: 2025-12-01T06:07:00
83
+
84
+ From: Carlos Delgado
85
+
86
+ Participants: Roberto Garza
87
+
88
+
89
+ Body:
90
+
91
+ Hola Roberto,
92
+
93
+
94
+ Hope you''re having a good afternoon. I wanted to touch base regarding the NOM-006-SCFI-2012
95
+ certification process for our most recent lots (especially Batch 3124-A and 3125-B).
96
+ While the initial chromatographic analyses were within threshold, there were minor
97
+ variances in the ester content and methanol limits. Nothing fuera de lo común,
98
+ pero los reguladores have requested clarification on our barrel aging logs for
99
+ these particular batches. You know, in Mexico, relationships matter, and sometimes
100
+ a simple phone call or una pequeña cena can resolve these technicalities. This
101
+ is how business is done here, and I’m confident our local practices meet the spirit
102
+ and letter of the regulations.
103
+
104
+
105
+ Let’s ensure the technical team keeps detailed test result documentation (including
106
+ los controles de temperatura y humedad en la bodega). If you need my support defending
107
+ our methodology, I’m happy to take the lead—nuestro equipo es lo más importante.
108
+ Please advise if you need me to coordinate with external auditors or if a site
109
+ visit would be beneficial.
110
+
111
+
112
+ Un abrazo,
113
+
114
+ Carlos
115
+
116
+
117
+ --
118
+
119
+ Carlos Delgado
120
+
121
+ Country Manager, Mexico Operations
122
+
123
+ Agave Spirits International
124
+
125
+ Tequila, Jalisco'
126
+ - source_sentence: Find the Team Lunch expense report dated June 14, 2024 with attendee
127
+ details and business purpose, including the itemized factura and supporting receipts.
128
+ sentences:
129
+ - 'Subject: Re: Expense Report Submission: Team Lunch – June 14th, 2024
130
+
131
+ Date: 2025-12-19T13:33:00
132
+
133
+ From: Maria Santos
134
+
135
+ Participants: Ana Lucia Vega
136
+
137
+
138
+ Body:
139
+
140
+ Hello Ana Lucia,
141
+
142
+
143
+ Thank you for your timely submission of the expense report and for providing both
144
+ the itemized factura and supporting receipts. I have reviewed the documentation,
145
+ and everything appears to be in order for processing. Please remember that, as
146
+ per policy, any future expense reports should continue to include full details
147
+ on attendees and business purpose, which you have done correctly here. I will
148
+ proceed to send this for approval and notify you if any further information is
149
+ required.
150
+
151
+
152
+ Best regards,
153
+
154
+ Maria'
155
+ - 'Subject: Re: Cork Vendor Evaluation and Procurement Considerations
156
+
157
+ Date: 2025-08-12T09:26:00
158
+
159
+ From: Roberto Garza
160
+
161
+ Participants: Pedro Villanueva
162
+
163
+
164
+ Body:
165
+
166
+ Hi Pedro,
167
+
168
+
169
+ Thanks for putting together the comparison and highlighting the delivery timeline
170
+ differences. I agree that consistent supply is crucial, especially with permit
171
+ uncertainty looming. Please move forward with ProCork SA, but ensure we document
172
+ service guarantees and any penalties for late delivery in the contract. Also,
173
+ confirm there are no recent supply chain disruptions on their end.
174
+
175
+
176
+ Let me know if you encounter any issues during negotiations.
177
+
178
+
179
+ Best,
180
+
181
+ Roberto'
182
+ - 'Subject: Re: Urgent: Water Permit Renewal Delay Threatening Production Levels
183
+
184
+ Date: 2025-08-25T15:02:00
185
+
186
+ From: Carlos Delgado
187
+
188
+ Participants: Roberto Garza
189
+
190
+
191
+ Body:
192
+
193
+ Hola Roberto,
194
+
195
+
196
+ Thank you for raising your concerns. I completely understand the pressure this
197
+ delay puts on the plant, but I want to reassure you that Rick has the situation
198
+ well in hand. We’ve been investing a lot in our relationship with the local authorities—In
199
+ Mexico, relationships matter, ya sabes. The mayor has been very receptive to our
200
+ efforts, and we’ve had several productive meetings (and just a small dinner or
201
+ two) with municipal leadership. This is how business is done here; these things
202
+ take relationship building, and I’m confident we’ll have good news soon. Por favor,
203
+ don’t worry—déjalo en nuestras manos. I’ll keep you posted as soon as I hear anything
204
+ definitive.
205
+
206
+
207
+ Un abrazo,
208
+
209
+ Carlos'
210
+ - source_sentence: ¿Se utilizará la tarjeta corporativa para la cena con el municipio
211
+ (seis comensales)?
212
+ sentences:
213
+ - 'Subject: Re: Reservación especial en La Tequila para cena con el municipio
214
+
215
+ Date: 2025-09-11T12:29:00
216
+
217
+ From: Elena Fuentes
218
+
219
+ Participants: Ricardo Mendez
220
+
221
+
222
+ Body:
223
+
224
+ Hola Ricardo,
225
+
226
+
227
+ La reservación para seis personas está confirmada en el salón privado de Hueso
228
+ para el viernes solicitado. El costo aproximado es de 3,500 MXN por persona. ¿Prefieres
229
+ que cubra el pago con la tarjeta corporativa o gestiono la facturación con el
230
+ proveedor habitual? El restaurante está al tanto de todos los detalles, incluyendo
231
+ las restricciones alimentarias de la Sra. Sofia Reyes, y nos apoyarán con un menú
232
+ especial y un brindis de bienvenida.
233
+
234
+
235
+ Te mantengo informando cualquier ajuste adicional que propongan y confirmo los
236
+ detalles finales en cuanto los tenga.
237
+
238
+
239
+ Saludos,
240
+
241
+ Elena'
242
+ - 'Subject: Planning for the Annual Distributor Conference – Maximizing Q4 Impact
243
+
244
+ Date: 2025-12-03T16:29:00
245
+
246
+ From: Kevin O''Brien
247
+
248
+ Participants: Daniel Wright; Patricia Reeves; Sarah Mitchell
249
+
250
+
251
+ Body:
252
+
253
+ Hi Team,
254
+
255
+
256
+ As we move into the final stretch of the year, I want to discuss our participation
257
+ and objectives for the upcoming Distributor Conference. This event is critical
258
+ for driving Q4 numbers and reinforcing our market share, especially as our competitors
259
+ ramp up their own outreach. My recommendation is that we prioritize high-value
260
+ partner meetings and fast-track any compliance reviews that might hold up potential
261
+ deals. Let''s ensure our competitive positioning is front and center throughout
262
+ the conference. Please come prepared with actionable strategies and an update
263
+ on how we can expedite pipeline conversions without unnecessary delay.
264
+
265
+
266
+ Looking forward to everyone''s input so we can hit the ground running and close
267
+ the year strong.
268
+
269
+
270
+ Best,
271
+
272
+ Kevin'
273
+ - 'Subject: Reminder: Performance Review Deadlines and Upcoming Calibration Meetings
274
+
275
+ Date: 2025-08-29T16:46:00
276
+
277
+ From: Elena Fuentes
278
+
279
+ Participants: Patricia Reeves
280
+
281
+
282
+ Body:
283
+
284
+ Hello Managers,
285
+
286
+
287
+ Carlos asked me to remind you that the deadline for submitting team performance
288
+ reviews is next Friday, June 14. Please use the forms circulated last week and
289
+ ensure they are returned to HR by noon on the deadline. Calibration meetings are
290
+ scheduled for June 17 and 18. Invitations were sent separately—let me know if
291
+ you did not receive yours. Contact me if you need replacement forms or have questions
292
+ about the process.
293
+
294
+
295
+ Thank you,
296
+
297
+ Elena
298
+
299
+
300
+ --
301
+
302
+ Elena Fuentes
303
+
304
+ Executive Assistant
305
+
306
+ ASI Mexico'
307
+ - source_sentence: What is the attendance confirmation deadline by Tuesday for the
308
+ retirement farewell dinner for José Morales at Casa Agave?
309
+ sentences:
310
+ - 'Subject: Regulatory Fee Payment – Strategic Approach
311
+
312
+ Date: 2025-09-15T08:35:00
313
+
314
+ From: Carlos Delgado
315
+
316
+ Participants: Maria Santos
317
+
318
+
319
+ Body:
320
+
321
+ Hola Maria,
322
+
323
+
324
+ I hope this message finds you well. Regarding the upcoming regulatory fee payment,
325
+ I want to remind you that in Mexico, relationships matter as much as paperwork.
326
+ These cuotas are not just formalities; they reflect our respect for the local
327
+ authorities, and a small gesture—a coffee, una cenita sencilla—can go a long way
328
+ to help facilitate smoother approvals. This is how business is done here, and
329
+ I always defend our approach. Please coordinate with our tax advisors so everything
330
+ is handled with full transparency, but also with the personal touch that sets
331
+ us apart.
332
+
333
+
334
+ Let me know if you need support with any introductions or if questions arise—protecting
335
+ our equipo comes first.
336
+
337
+
338
+ Saludos,
339
+
340
+ Carlos
341
+
342
+
343
+ --
344
+
345
+ Carlos Delgado
346
+
347
+ Country Manager, Mexico Operations
348
+
349
+ Agave Spirits International
350
+
351
+ Tequila, Jalisco'
352
+ - 'Subject: Inquiry Regarding Vendor Onboarding: Consultoria Verde de Jalisco
353
+
354
+ Date: 2025-08-13T11:27:00
355
+
356
+ From: Jennifer Walsh
357
+
358
+ Participants: Miguel Torres
359
+
360
+
361
+ Body:
362
+
363
+ Hi Miguel,
364
+
365
+
366
+ I am conducting a review of our vendor onboarding process as it pertains to Consultoria
367
+ Verde de Jalisco. For the record, I need to confirm several specific details to
368
+ ensure full compliance with ASI’s Third-Party Due Diligence Policy. Please provide
369
+ documentation or direct responses to the following:
370
+
371
+
372
+ 1. Was a background check conducted on Consultoria Verde de Jalisco prior to onboarding?
373
+ If so, please forward the results or indicate where they are archived.
374
+
375
+ 2. Do we have up-to-date beneficial ownership documentation for this vendor? If
376
+ yes, please attach or specify the location of these records.
377
+
378
+ 3. Who provided final approval for onboarding this vendor? Please include the
379
+ name, title, and date of approval.
380
+
381
+ 4. Was the standard third-party due diligence questionnaire completed in full?
382
+ If so, please provide a copy for our files.
383
+
384
+
385
+ As you are aware, all vendors providing government-related services require enhanced
386
+ screening, and it is critical that we document everything to mitigate potential
387
+ red flags. Please respond by close of business this Friday so we may ensure our
388
+ files are complete and in accordance with policy.
389
+
390
+
391
+ Thank you for your prompt attention to this matter.
392
+
393
+
394
+ Regards,
395
+
396
+ Jennifer
397
+
398
+
399
+ --
400
+
401
+ Jennifer Walsh
402
+
403
+ Vice President, Global Compliance & Ethics
404
+
405
+ Agave Spirits International
406
+
407
+ CONFIDENTIAL - Attorney Work Product'
408
+ - 'Subject: Announcement: Retirement Farewell Dinner for José Morales
409
+
410
+ Date: 2025-09-08T18:17:00
411
+
412
+ From: Carlos Delgado
413
+
414
+ Participants: Elena Fuentes; Team Mexico Office
415
+
416
+
417
+ Body:
418
+
419
+ Dear team,
420
+
421
+
422
+ It is both with pride and a touch of nostalgia that I announce that our esteemed
423
+ colleague, José Morales, will be retiring at the end of this month after more
424
+ than 25 years of dedicated service. En México, relationships matter—y por eso,
425
+ we are organizing just a small dinner, una cenita sencilla, to celebrate his remarkable
426
+ career and to say ‘gracias’ for his invaluable contributions.
427
+
428
+
429
+ Please join us on Thursday, 7:00 PM at Casa Agave. It will be an opportunity to
430
+ honor José’s legacy, share stories, and reinforce what we do best—support one
431
+ another. In this business, así se hacen las cosas: juntos, con corazón. Your presence
432
+ would mean a lot to José and to our team.
433
+
434
+
435
+ Por favor, confirm your attendance by Tuesday so we can finalize everything. Any
436
+ questions, let me know—my door is always open for my equipo.
437
+
438
+
439
+ Warm regards,
440
+
441
+ Carlos
442
+
443
+
444
+ --
445
+
446
+ Carlos Delgado
447
+
448
+ Country Manager, Mexico Operations
449
+
450
+ Agave Spirits International
451
+
452
+ Tequila, Jalisco'
453
+ - source_sentence: Impresiones Jalisco anti-corruption questionnaire completed and
454
+ signed
455
+ sentences:
456
+ - 'Subject: Fwd: Request for Supporting Documentation – Journal Entry Approval Required
457
+
458
+ Date: 2025-11-17T09:45:00
459
+
460
+ From: David Chen
461
+
462
+ Participants: Maria Santos
463
+
464
+
465
+ Body:
466
+
467
+ Hi Maria,
468
+
469
+
470
+ I''ve reviewed the recent journal entries submitted for month-end and noticed
471
+ that several expense items lack detailed descriptions and corresponding documentation.
472
+ From a financial perspective, I need to stress the importance of transparency
473
+ and traceability. The data shows that ambiguous expense lines can lead to compliance
474
+ risks during audit. Please provide receipts or explanatory memos for all entries
475
+ over $5,000. Once the supporting docs are received, I will proceed with approval.
476
+
477
+
478
+ Thanks,
479
+
480
+ David
481
+
482
+
483
+ --
484
+
485
+ David Chen
486
+
487
+ Chief Financial Officer
488
+
489
+ Agave Spirits International'
490
+ - 'Subject: Quality Test Results for Lot MX-2024-156
491
+
492
+ Date: 2025-09-11T17:36:00
493
+
494
+ From: Ana Lucia Vega
495
+
496
+ Participants: Javier Moreno
497
+
498
+
499
+ Body:
500
+
501
+ Hi Javier,
502
+
503
+
504
+ I''m sending over the routine quality test results for lot MX-2024-156 as requested.
505
+ The alcohol content measured at 38.5%, which is within our standard parameters.
506
+ pH levels were recorded at 4.1, also within acceptable range. Taste panel notes
507
+ mentioned the flavor profile was clean, with no off-notes or irregularities. Carlos
508
+ approved the data and Rick said to process it as normal.
509
+
510
+
511
+ Let me know if you need anything else or have questions.
512
+
513
+
514
+ Best,
515
+
516
+ Ana Lucia
517
+
518
+
519
+ --
520
+
521
+ Ana Lucia Vega
522
+
523
+ Accounts Payable
524
+
525
+ ASI Mexico'
526
+ - 'Subject: Submission of Completed Due Diligence Package: Impresiones Jalisco Vendor
527
+ Onboarding
528
+
529
+ Date: 2025-08-16T12:30:00
530
+
531
+ From: Miguel Torres
532
+
533
+ Participants: Jennifer Walsh
534
+
535
+
536
+ Body:
537
+
538
+ Hi Jennifer,
539
+
540
+
541
+ I’m pleased to submit the completed third-party due diligence package for Impresiones
542
+ Jalisco, our prospective label printer vendor. We’ve finalized all items on the
543
+ vendor onboarding checklist, including a thorough background check (result: clean),
544
+ full beneficial ownership verification (all documentation attached), verified
545
+ business references, as well as a completed and signed anti-corruption questionnaire.
546
+ Additionally, their valid tax registration (RFC) is on file.
547
+
548
+
549
+ Impresiones Jalisco was selected through our competitive bidding process, with
550
+ three bidders considered and evaluated for pricing, quality, and reliability.
551
+ I believe this robust process supports our selection. Please find the full package
552
+ attached for your compliance review. Once you approve, I’ll proceed with finalizing
553
+ the contract so we can move forward with our labeling project timeline.
554
+
555
+
556
+ Let me know if you need anything further or require additional documentation.
557
+
558
+
559
+ Thanks,
560
+
561
+ Miguel
562
+
563
+
564
+ --
565
+
566
+ Miguel Torres
567
+
568
+ Procurement Manager
569
+
570
+ ASI Mexico'
571
+ pipeline_tag: sentence-similarity
572
+ library_name: sentence-transformers
573
+ metrics:
574
+ - cosine_accuracy@1
575
+ - cosine_accuracy@3
576
+ - cosine_accuracy@5
577
+ - cosine_accuracy@10
578
+ - cosine_precision@1
579
+ - cosine_precision@3
580
+ - cosine_precision@5
581
+ - cosine_precision@10
582
+ - cosine_recall@1
583
+ - cosine_recall@3
584
+ - cosine_recall@5
585
+ - cosine_recall@10
586
+ - cosine_ndcg@10
587
+ - cosine_mrr@10
588
+ - cosine_map@100
589
+ model-index:
590
+ - name: SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B
591
+ results:
592
+ - task:
593
+ type: information-retrieval
594
+ name: Information Retrieval
595
+ dataset:
596
+ name: val full corpus
597
+ type: val_full_corpus
598
+ metrics:
599
+ - type: cosine_accuracy@1
600
+ value: 0.9029126213592233
601
+ name: Cosine Accuracy@1
602
+ - type: cosine_accuracy@3
603
+ value: 0.9854368932038835
604
+ name: Cosine Accuracy@3
605
+ - type: cosine_accuracy@5
606
+ value: 0.9902912621359223
607
+ name: Cosine Accuracy@5
608
+ - type: cosine_accuracy@10
609
+ value: 0.9951456310679612
610
+ name: Cosine Accuracy@10
611
+ - type: cosine_precision@1
612
+ value: 0.9029126213592233
613
+ name: Cosine Precision@1
614
+ - type: cosine_precision@3
615
+ value: 0.3284789644012946
616
+ name: Cosine Precision@3
617
+ - type: cosine_precision@5
618
+ value: 0.19805825242718444
619
+ name: Cosine Precision@5
620
+ - type: cosine_precision@10
621
+ value: 0.09951456310679611
622
+ name: Cosine Precision@10
623
+ - type: cosine_recall@1
624
+ value: 0.9029126213592233
625
+ name: Cosine Recall@1
626
+ - type: cosine_recall@3
627
+ value: 0.9854368932038835
628
+ name: Cosine Recall@3
629
+ - type: cosine_recall@5
630
+ value: 0.9902912621359223
631
+ name: Cosine Recall@5
632
+ - type: cosine_recall@10
633
+ value: 0.9951456310679612
634
+ name: Cosine Recall@10
635
+ - type: cosine_ndcg@10
636
+ value: 0.9546600421052297
637
+ name: Cosine Ndcg@10
638
+ - type: cosine_mrr@10
639
+ value: 0.9410194174757281
640
+ name: Cosine Mrr@10
641
+ - type: cosine_map@100
642
+ value: 0.9410877888691372
643
+ name: Cosine Map@100
644
+ ---
645
+
646
+ # SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B
647
+
648
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
649
+
650
+ ## Model Details
651
+
652
+ ### Model Description
653
+ - **Model Type:** Sentence Transformer
654
+ - **Base model:** [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) <!-- at revision c54f2e6e80b2d7b7de06f51cec4959f6b3e03418 -->
655
+ - **Maximum Sequence Length:** 32768 tokens
656
+ - **Output Dimensionality:** 1024 dimensions
657
+ - **Similarity Function:** Cosine Similarity
658
+ <!-- - **Training Dataset:** Unknown -->
659
+ <!-- - **Language:** Unknown -->
660
+ <!-- - **License:** Unknown -->
661
+
662
+ ### Model Sources
663
+
664
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
665
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
666
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
667
+
668
+ ### Full Model Architecture
669
+
670
+ ```
671
+ SentenceTransformer(
672
+ (0): Transformer({'max_seq_length': 32768, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
673
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
674
+ (2): Normalize()
675
+ )
676
+ ```
677
+
678
+ ## Usage
679
+
680
+ ### Direct Usage (Sentence Transformers)
681
+
682
+ First install the Sentence Transformers library:
683
+
684
+ ```bash
685
+ pip install -U sentence-transformers
686
+ ```
687
+
688
+ Then you can load this model and run inference.
689
+ ```python
690
+ from sentence_transformers import SentenceTransformer
691
+
692
+ # Download from the 🤗 Hub
693
+ model = SentenceTransformer("sentence_transformers_model_id")
694
+ # Run inference
695
+ queries = [
696
+ "Impresiones Jalisco anti-corruption questionnaire completed and signed",
697
+ ]
698
+ documents = [
699
+ 'Subject: Submission of Completed Due Diligence Package: Impresiones Jalisco Vendor Onboarding\nDate: 2025-08-16T12:30:00\nFrom: Miguel Torres\nParticipants: Jennifer Walsh\n\nBody:\nHi Jennifer,\n\nI’m pleased to submit the completed third-party due diligence package for Impresiones Jalisco, our prospective label printer vendor. We’ve finalized all items on the vendor onboarding checklist, including a thorough background check (result: clean), full beneficial ownership verification (all documentation attached), verified business references, as well as a completed and signed anti-corruption questionnaire. Additionally, their valid tax registration (RFC) is on file.\n\nImpresiones Jalisco was selected through our competitive bidding process, with three bidders considered and evaluated for pricing, quality, and reliability. I believe this robust process supports our selection. Please find the full package attached for your compliance review. Once you approve, I’ll proceed with finalizing the contract so we can move forward with our labeling project timeline.\n\nLet me know if you need anything further or require additional documentation.\n\nThanks,\nMiguel\n\n--\nMiguel Torres\nProcurement Manager\nASI Mexico',
700
+ "Subject: Quality Test Results for Lot MX-2024-156\nDate: 2025-09-11T17:36:00\nFrom: Ana Lucia Vega\nParticipants: Javier Moreno\n\nBody:\nHi Javier,\n\nI'm sending over the routine quality test results for lot MX-2024-156 as requested. The alcohol content measured at 38.5%, which is within our standard parameters. pH levels were recorded at 4.1, also within acceptable range. Taste panel notes mentioned the flavor profile was clean, with no off-notes or irregularities. Carlos approved the data and Rick said to process it as normal.\n\nLet me know if you need anything else or have questions.\n\nBest,\nAna Lucia\n\n--\nAna Lucia Vega\nAccounts Payable\nASI Mexico",
701
+ "Subject: Fwd: Request for Supporting Documentation – Journal Entry Approval Required\nDate: 2025-11-17T09:45:00\nFrom: David Chen\nParticipants: Maria Santos\n\nBody:\nHi Maria,\n\nI've reviewed the recent journal entries submitted for month-end and noticed that several expense items lack detailed descriptions and corresponding documentation. From a financial perspective, I need to stress the importance of transparency and traceability. The data shows that ambiguous expense lines can lead to compliance risks during audit. Please provide receipts or explanatory memos for all entries over $5,000. Once the supporting docs are received, I will proceed with approval.\n\nThanks,\nDavid\n\n--\nDavid Chen\nChief Financial Officer\nAgave Spirits International",
702
+ ]
703
+ query_embeddings = model.encode_query(queries)
704
+ document_embeddings = model.encode_document(documents)
705
+ print(query_embeddings.shape, document_embeddings.shape)
706
+ # [1, 1024] [3, 1024]
707
+
708
+ # Get the similarity scores for the embeddings
709
+ similarities = model.similarity(query_embeddings, document_embeddings)
710
+ print(similarities)
711
+ # tensor([[0.4883, 0.1104, 0.0481]], dtype=torch.bfloat16)
712
+ ```
713
+
714
+ <!--
715
+ ### Direct Usage (Transformers)
716
+
717
+ <details><summary>Click to see the direct usage in Transformers</summary>
718
+
719
+ </details>
720
+ -->
721
+
722
+ <!--
723
+ ### Downstream Usage (Sentence Transformers)
724
+
725
+ You can finetune this model on your own dataset.
726
+
727
+ <details><summary>Click to expand</summary>
728
+
729
+ </details>
730
+ -->
731
+
732
+ <!--
733
+ ### Out-of-Scope Use
734
+
735
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
736
+ -->
737
+
738
+ ## Evaluation
739
+
740
+ ### Metrics
741
+
742
+ #### Information Retrieval
743
+
744
+ * Dataset: `val_full_corpus`
745
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
746
+
747
+ | Metric | Value |
748
+ |:--------------------|:-----------|
749
+ | cosine_accuracy@1 | 0.9029 |
750
+ | cosine_accuracy@3 | 0.9854 |
751
+ | cosine_accuracy@5 | 0.9903 |
752
+ | cosine_accuracy@10 | 0.9951 |
753
+ | cosine_precision@1 | 0.9029 |
754
+ | cosine_precision@3 | 0.3285 |
755
+ | cosine_precision@5 | 0.1981 |
756
+ | cosine_precision@10 | 0.0995 |
757
+ | cosine_recall@1 | 0.9029 |
758
+ | cosine_recall@3 | 0.9854 |
759
+ | cosine_recall@5 | 0.9903 |
760
+ | cosine_recall@10 | 0.9951 |
761
+ | **cosine_ndcg@10** | **0.9547** |
762
+ | cosine_mrr@10 | 0.941 |
763
+ | cosine_map@100 | 0.9411 |
764
+
765
+ <!--
766
+ ## Bias, Risks and Limitations
767
+
768
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
769
+ -->
770
+
771
+ <!--
772
+ ### Recommendations
773
+
774
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
775
+ -->
776
+
777
+ ## Training Details
778
+
779
+ ### Training Dataset
780
+
781
+ #### Unnamed Dataset
782
+
783
+ * Size: 816 training samples
784
+ * Columns: <code>sentence_0</code> and <code>sentence_1</code>
785
+ * Approximate statistics based on the first 816 samples:
786
+ | | sentence_0 | sentence_1 |
787
+ |:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
788
+ | type | string | string |
789
+ | details | <ul><li>min: 6 tokens</li><li>mean: 32.63 tokens</li><li>max: 98 tokens</li></ul> | <ul><li>min: 118 tokens</li><li>mean: 208.72 tokens</li><li>max: 511 tokens</li></ul> |
790
+ * Samples:
791
+ | sentence_0 | sentence_1 |
792
+ |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
793
+ | <code>Search for impairment assessment documents for Tequila production assets as of May 31, 2024 (Ref: IMP-240531-2) and any reconciliations to the Q2 Finance Statement dated June 3, 2024 showing a MXN 1.2M discrepancy in carrying value, including supporting calculations and any post-finalization adjustments.</code> | <code>Subject: Impairment Assessment: Noted Discrepancies in Asset Valuation<br>Date: 2025-12-15T17:18:00<br>From: Lisa Park<br>Participants: Maria Santos<br><br>Body:<br>Hi Maria,<br><br>I am reviewing the impairment assessment documentation for the Tequila production assets as of May 31, 2024, and have noticed an anomaly in the valuation report (Ref: IMP-240531-2). The carrying value listed in your schedule does not reconcile with the figure reported in the Q2 Finance Statement submitted to HQ on June 3. The difference is approximately MXN 1.2M. Can you clarify which source is correct, and provide any supporting documentation used for your calculation? For completeness, could you also confirm if any subsequent adjustments were made after the finalization date referenced above?<br><br>Thank you for your attention to these details. Please let me know if you need further clarification on the items I flagged.<br><br>Best regards,<br>Lisa<br><br>--<br>Lisa Park<br>Director, Internal Audit<br>Agave Spirits International</code> |
794
+ | <code>Identify Q2 expense journal entries flagged as unclear, particularly those categorized as 'miscellaneous services' or 'external consulting', and locate the associated receipts and service contracts.</code> | <code>Subject: Re: Approval Required: Journal Entry Review and Documentation<br>Date: 2025-09-30T08:40:00<br>From: Maria Santos<br>Participants: David Chen<br><br>Body:<br>Hi David,<br><br>Thank you for your detailed review and careful attention to our Q2 expense entries. I appreciate your diligence regarding compliance. I am currently gathering receipts and service contracts for all entries you flagged as unclear, including those labeled under 'miscellaneous services' and 'external consulting.' I will organize and forward digital copies, along with brief descriptions of each expense, by end of day tomorrow. If you need clarification on specific vendors, please let me know so I can prioritize those.<br><br>Thanks for highlighting this and ensuring we stay audit-ready. I’ll follow up shortly with all the documentation.<br><br>Best regards,<br>Maria</code> |
795
+ | <code>Identify records confirming pre-clearance and FARA registration for ASI's government liaison activities in Mexico and the United States.</code> | <code>Subject: Análisis sobre el registro FARA y obligaciones de cumplimiento en actividades gubernamentales México-EE.UU.<br>Date: 2025-08-04T06:58:00<br>From: Amanda Foster<br>Participants: Sarah Mitchell<br><br>Body:<br>Hola Sarah,<br><br>Quiero compartir contigo el análisis preliminar referente al registro bajo FARA (Foreign Agents Registration Act) y nuestras obligaciones rutinarias de cumplimiento en relación con las actividades de vinculación gubernamental en México y EE.UU. Como sabes, todas las interacciones de ASI con entidades gubernamentales, tanto en México como en EE.UU., son registradas y pre-aprobadas mediante nuestro proceso interno de pre-clearance en Government Relations; esto garantiza la trazabilidad y documentación del propósito empresarial legítimo en cada caso.<br><br>Recordando las regulaciones estadounidenses, cualquier actividad que implique representación de intereses extranjeros exige una revisión exhaustiva para determinar si corresponde el registro FARA. Hasta el momento, todas nuestras ges...</code> |
796
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
797
+ ```json
798
+ {
799
+ "scale": 20.0,
800
+ "similarity_fct": "cos_sim",
801
+ "gather_across_devices": false
802
+ }
803
+ ```
804
+
805
+ ### Training Hyperparameters
806
+ #### Non-Default Hyperparameters
807
+
808
+ - `per_device_train_batch_size`: 16
809
+ - `per_device_eval_batch_size`: 16
810
+ - `multi_dataset_batch_sampler`: round_robin
811
+
812
+ #### All Hyperparameters
813
+ <details><summary>Click to expand</summary>
814
+
815
+ - `do_predict`: False
816
+ - `eval_strategy`: no
817
+ - `prediction_loss_only`: True
818
+ - `per_device_train_batch_size`: 16
819
+ - `per_device_eval_batch_size`: 16
820
+ - `gradient_accumulation_steps`: 1
821
+ - `eval_accumulation_steps`: None
822
+ - `torch_empty_cache_steps`: None
823
+ - `learning_rate`: 5e-05
824
+ - `weight_decay`: 0.0
825
+ - `adam_beta1`: 0.9
826
+ - `adam_beta2`: 0.999
827
+ - `adam_epsilon`: 1e-08
828
+ - `max_grad_norm`: 1
829
+ - `num_train_epochs`: 3
830
+ - `max_steps`: -1
831
+ - `lr_scheduler_type`: linear
832
+ - `lr_scheduler_kwargs`: None
833
+ - `warmup_ratio`: None
834
+ - `warmup_steps`: 0
835
+ - `log_level`: passive
836
+ - `log_level_replica`: warning
837
+ - `log_on_each_node`: True
838
+ - `logging_nan_inf_filter`: True
839
+ - `enable_jit_checkpoint`: False
840
+ - `save_on_each_node`: False
841
+ - `save_only_model`: False
842
+ - `restore_callback_states_from_checkpoint`: False
843
+ - `use_cpu`: False
844
+ - `seed`: 42
845
+ - `data_seed`: None
846
+ - `bf16`: False
847
+ - `fp16`: False
848
+ - `bf16_full_eval`: False
849
+ - `fp16_full_eval`: False
850
+ - `tf32`: None
851
+ - `local_rank`: -1
852
+ - `ddp_backend`: None
853
+ - `debug`: []
854
+ - `dataloader_drop_last`: False
855
+ - `dataloader_num_workers`: 0
856
+ - `dataloader_prefetch_factor`: None
857
+ - `disable_tqdm`: False
858
+ - `remove_unused_columns`: True
859
+ - `label_names`: None
860
+ - `load_best_model_at_end`: False
861
+ - `ignore_data_skip`: False
862
+ - `fsdp`: []
863
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
864
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
865
+ - `parallelism_config`: None
866
+ - `deepspeed`: None
867
+ - `label_smoothing_factor`: 0.0
868
+ - `optim`: adamw_torch_fused
869
+ - `optim_args`: None
870
+ - `group_by_length`: False
871
+ - `length_column_name`: length
872
+ - `project`: huggingface
873
+ - `trackio_space_id`: trackio
874
+ - `ddp_find_unused_parameters`: None
875
+ - `ddp_bucket_cap_mb`: None
876
+ - `ddp_broadcast_buffers`: False
877
+ - `dataloader_pin_memory`: True
878
+ - `dataloader_persistent_workers`: False
879
+ - `skip_memory_metrics`: True
880
+ - `push_to_hub`: False
881
+ - `resume_from_checkpoint`: None
882
+ - `hub_model_id`: None
883
+ - `hub_strategy`: every_save
884
+ - `hub_private_repo`: None
885
+ - `hub_always_push`: False
886
+ - `hub_revision`: None
887
+ - `gradient_checkpointing`: False
888
+ - `gradient_checkpointing_kwargs`: None
889
+ - `include_for_metrics`: []
890
+ - `eval_do_concat_batches`: True
891
+ - `auto_find_batch_size`: False
892
+ - `full_determinism`: False
893
+ - `ddp_timeout`: 1800
894
+ - `torch_compile`: False
895
+ - `torch_compile_backend`: None
896
+ - `torch_compile_mode`: None
897
+ - `include_num_input_tokens_seen`: no
898
+ - `neftune_noise_alpha`: None
899
+ - `optim_target_modules`: None
900
+ - `batch_eval_metrics`: False
901
+ - `eval_on_start`: False
902
+ - `use_liger_kernel`: False
903
+ - `liger_kernel_config`: None
904
+ - `eval_use_gather_object`: False
905
+ - `average_tokens_across_devices`: True
906
+ - `use_cache`: False
907
+ - `prompts`: None
908
+ - `batch_sampler`: batch_sampler
909
+ - `multi_dataset_batch_sampler`: round_robin
910
+ - `router_mapping`: {}
911
+ - `learning_rate_mapping`: {}
912
+
913
+ </details>
914
+
915
+ ### Training Logs
916
+ | Epoch | Step | val_full_corpus_cosine_ndcg@10 |
917
+ |:-----:|:----:|:------------------------------:|
918
+ | 1.0 | 51 | 0.9547 |
919
+
920
+
921
+ ### Framework Versions
922
+ - Python: 3.12.12
923
+ - Sentence Transformers: 5.2.3
924
+ - Transformers: 5.0.0
925
+ - PyTorch: 2.10.0+cu128
926
+ - Accelerate: 1.12.0
927
+ - Datasets: 4.0.0
928
+ - Tokenizers: 0.22.2
929
+
930
+ ## Citation
931
+
932
+ ### BibTeX
933
+
934
+ #### Sentence Transformers
935
+ ```bibtex
936
+ @inproceedings{reimers-2019-sentence-bert,
937
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
938
+ author = "Reimers, Nils and Gurevych, Iryna",
939
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
940
+ month = "11",
941
+ year = "2019",
942
+ publisher = "Association for Computational Linguistics",
943
+ url = "https://arxiv.org/abs/1908.10084",
944
+ }
945
+ ```
946
+
947
+ #### MultipleNegativesRankingLoss
948
+ ```bibtex
949
+ @misc{henderson2017efficient,
950
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
951
+ 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},
952
+ year={2017},
953
+ eprint={1705.00652},
954
+ archivePrefix={arXiv},
955
+ primaryClass={cs.CL}
956
+ }
957
+ ```
958
+
959
+ <!--
960
+ ## Glossary
961
+
962
+ *Clearly define terms in order to be accessible across audiences.*
963
+ -->
964
+
965
+ <!--
966
+ ## Model Card Authors
967
+
968
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
969
+ -->
970
+
971
+ <!--
972
+ ## Model Card Contact
973
+
974
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
975
+ -->
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3Model"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": null,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.0.0",
60
+ "use_cache": true,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151669
63
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "prompts": {
3
+ "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
4
+ "document": ""
5
+ },
6
+ "default_prompt_name": null,
7
+ "similarity_fn_name": "cosine",
8
+ "model_type": "SentenceTransformer",
9
+ "__version__": {
10
+ "sentence_transformers": "5.2.3",
11
+ "transformers": "5.0.0",
12
+ "pytorch": "2.10.0+cu128"
13
+ }
14
+ }
eval/Information-Retrieval_evaluation_val_full_corpus_results.csv ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
2
+ 1.0,37,0.8585365853658536,0.9560975609756097,0.975609756097561,0.9902439024390244,0.8585365853658536,0.8585365853658536,0.31869918699186994,0.9560975609756097,0.19512195121951217,0.975609756097561,0.09902439024390243,0.9902439024390244,0.9074119241192412,0.9279158126042436,0.9079858122110633
3
+ 2.0,74,0.8585365853658536,0.9463414634146341,0.9658536585365853,0.9902439024390244,0.8585365853658536,0.8585365853658536,0.3154471544715448,0.9463414634146341,0.19317073170731705,0.9658536585365853,0.09902439024390243,0.9902439024390244,0.9057026713124273,0.9264301726415258,0.9061916987590929
4
+ 3.0,111,0.8536585365853658,0.9512195121951219,0.9658536585365853,0.9902439024390244,0.8536585365853658,0.8536585365853658,0.3170731707317073,0.9512195121951219,0.19317073170731705,0.9658536585365853,0.09902439024390243,0.9902439024390244,0.9045373596593108,0.9256650415118459,0.9050508384783096
5
+ 1.0,37,0.8585365853658536,0.9512195121951219,0.975609756097561,0.9902439024390244,0.8585365853658536,0.8585365853658536,0.3170731707317074,0.9512195121951219,0.1951219512195122,0.975609756097561,0.09902439024390243,0.9902439024390244,0.9082171893147504,0.9284712920737884,0.9088804327892903
6
+ 2.0,74,0.8585365853658536,0.9560975609756097,0.975609756097561,0.9853658536585366,0.8585365853658536,0.8585365853658536,0.31869918699186994,0.9560975609756097,0.1951219512195122,0.975609756097561,0.09853658536585364,0.9853658536585366,0.9087049941927992,0.9278242902120388,0.9097804271039188
7
+ 3.0,111,0.8536585365853658,0.9560975609756097,0.975609756097561,0.9853658536585366,0.8536585365853658,0.8536585365853658,0.31869918699186994,0.9560975609756097,0.1951219512195122,0.975609756097561,0.09853658536585364,0.9853658536585366,0.906265969802555,0.9260239475465335,0.9073414027136749
8
+ 1.0,37,0.8536585365853658,0.9512195121951219,0.9658536585365853,0.9902439024390244,0.8536585365853658,0.8536585365853658,0.3170731707317073,0.9512195121951219,0.19317073170731705,0.9658536585365853,0.09902439024390243,0.9902439024390244,0.903786295005807,0.9250795728818809,0.9043321718931475
9
+ 2.0,74,0.8634146341463415,0.9512195121951219,0.9707317073170731,0.9902439024390244,0.8634146341463415,0.8634146341463415,0.3170731707317074,0.9512195121951219,0.1941463414634146,0.9707317073170731,0.09902439024390243,0.9902439024390244,0.9097560975609754,0.929580010542026,0.9102296077905835
10
+ 3.0,111,0.8634146341463415,0.9560975609756097,0.975609756097561,0.9902439024390244,0.8634146341463415,0.8634146341463415,0.31869918699186994,0.9560975609756097,0.1951219512195122,0.975609756097561,0.09902439024390243,0.9902439024390244,0.910379403794038,0.9301260311829979,0.9108329767508201
11
+ 1.0,51,0.8439024390243902,0.9365853658536586,0.975609756097561,0.9853658536585366,0.8439024390243902,0.8439024390243902,0.3121951219512195,0.9365853658536586,0.1951219512195122,0.975609756097561,0.09853658536585364,0.9853658536585366,0.8982113821138211,0.9198897945980052,0.8994735345954858
12
+ 2.0,102,0.8682926829268293,0.9512195121951219,0.9853658536585366,1.0,0.8682926829268293,0.8682926829268293,0.3170731707317074,0.9512195121951219,0.19707317073170727,0.9853658536585366,0.1,1.0,0.915338753387534,0.9361010912485102,0.9153387533875339
13
+ 3.0,153,0.8634146341463415,0.9560975609756097,0.9853658536585366,1.0,0.8634146341463415,0.8634146341463415,0.31869918699186994,0.9560975609756097,0.19707317073170727,0.9853658536585366,0.1,1.0,0.9134610917537747,0.9347964889712779,0.9134610917537747
14
+ 1.0,51,0.8682926829268293,0.9512195121951219,0.975609756097561,1.0,0.8682926829268293,0.8682926829268293,0.3170731707317074,0.9512195121951219,0.1951219512195122,0.975609756097561,0.1,1.0,0.9131358885017422,0.9341684466667171,0.9131358885017421
15
+ 2.0,102,0.8731707317073171,0.9609756097560975,0.9853658536585366,1.0,0.8731707317073171,0.8731707317073171,0.3203252032520326,0.9609756097560975,0.19707317073170727,0.9853658536585366,0.1,1.0,0.9206562137049942,0.9402415066946049,0.9206562137049942
16
+ 3.0,153,0.8731707317073171,0.9560975609756097,0.9853658536585366,0.9951219512195122,0.8731707317073171,0.8731707317073171,0.31869918699186994,0.9560975609756097,0.19707317073170727,0.9853658536585366,0.09951219512195121,0.9951219512195122,0.9174912891986065,0.9366617478099398,0.9179347481786505
17
+ 1.0,51,0.9029126213592233,0.9854368932038835,0.9902912621359223,0.9951456310679612,0.9029126213592233,0.9029126213592233,0.3284789644012946,0.9854368932038835,0.19805825242718444,0.9902912621359223,0.09951456310679611,0.9951456310679612,0.9410194174757281,0.9546600421052297,0.9410877888691372
18
+ 2.0,102,0.8932038834951457,0.9902912621359223,0.9902912621359223,0.9951456310679612,0.8932038834951457,0.8932038834951457,0.33009708737864085,0.9902912621359223,0.19805825242718444,0.9902912621359223,0.09951456310679611,0.9951456310679612,0.9383957466481737,0.9528994157131321,0.9384780240877
19
+ 3.0,153,0.8932038834951457,0.9902912621359223,0.9902912621359223,0.9951456310679612,0.8932038834951457,0.8932038834951457,0.33009708737864085,0.9902912621359223,0.19805825242718444,0.9902912621359223,0.09951456310679611,0.9951456310679612,0.9385113268608415,0.9530104538382519,0.9385871763754046
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217d2fe9ca4aba5f2e6b511d3e571abd47d3e37ebf64b3f6fd4d95eee75dad31
3
+ size 1191586416
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": 32768,
3
+ "do_lower_case": false
4
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf519278622d854311452949ee197ff7afb0fbb1e0fa16cc307a959d8e61764
3
+ size 11423969
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "model_max_length": 131072,
25
+ "model_specific_special_tokens": {},
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }