tomaarsen HF Staff commited on
Commit
1ee5c00
·
verified ·
1 Parent(s): 7bc6940

Add new SentenceTransformer model

Browse files
README.md ADDED
@@ -0,0 +1,879 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - sentence-transformers
7
+ - sentence-similarity
8
+ - feature-extraction
9
+ - dense
10
+ - generated_from_trainer
11
+ - dataset_size:99231
12
+ - loss:MultipleNegativesRankingLoss
13
+ widget:
14
+ - source_sentence: who ordered the charge of the light brigade
15
+ sentences:
16
+ - Charge of the Light Brigade The Charge of the Light Brigade was a charge of British
17
+ light cavalry led by Lord Cardigan against Russian forces during the Battle of
18
+ Balaclava on 25 October 1854 in the Crimean War. Lord Raglan, overall commander
19
+ of the British forces, had intended to send the Light Brigade to prevent the Russians
20
+ from removing captured guns from overrun Turkish positions, a task well-suited
21
+ to light cavalry.
22
+ - UNICEF The United Nations International Children's Emergency Fund was created
23
+ by the United Nations General Assembly on 11 December 1946, to provide emergency
24
+ food and healthcare to children in countries that had been devastated by World
25
+ War II. The Polish physician Ludwik Rajchman is widely regarded as the founder
26
+ of UNICEF and served as its first chairman from 1946. On Rajchman's suggestion,
27
+ the American Maurice Pate was appointed its first executive director, serving
28
+ from 1947 until his death in 1965.[5][6] In 1950, UNICEF's mandate was extended
29
+ to address the long-term needs of children and women in developing countries everywhere.
30
+ In 1953 it became a permanent part of the United Nations System, and the words
31
+ "international" and "emergency" were dropped from the organization's name, making
32
+ it simply the United Nations Children's Fund, retaining the original acronym,
33
+ "UNICEF".[3]
34
+ - Marcus Jordan Marcus James Jordan (born December 24, 1990) is an American former
35
+ college basketball player who played for the UCF Knights men's basketball team
36
+ of Conference USA.[1] He is the son of retired Hall of Fame basketball player
37
+ Michael Jordan.
38
+ - source_sentence: what part of the cow is the rib roast
39
+ sentences:
40
+ - Standing rib roast A standing rib roast, also known as prime rib, is a cut of
41
+ beef from the primal rib, one of the nine primal cuts of beef. While the entire
42
+ rib section comprises ribs six through 12, a standing rib roast may contain anywhere
43
+ from two to seven ribs.
44
+ - Blaine Anderson Kurt begins to mend their relationship in "Thanksgiving", just
45
+ before New Directions loses at Sectionals to the Warblers, and they spend Christmas
46
+ together in New York City.[29][30] Though he and Kurt continue to be on good terms,
47
+ Blaine finds himself developing a crush on his best friend, Sam, which he knows
48
+ will come to nothing as he knows Sam is not gay; the two of them team up to find
49
+ evidence that the Warblers cheated at Sectionals, which means New Directions will
50
+ be competing at Regionals. He ends up going to the Sadie Hawkins dance with Tina
51
+ Cohen-Chang (Jenna Ushkowitz), who has developed a crush on him, but as friends
52
+ only.[31] When Kurt comes to Lima for the wedding of glee club director Will (Matthew
53
+ Morrison) and Emma (Jayma Mays)—which Emma flees—he and Blaine make out beforehand,
54
+ and sleep together afterward, though they do not resume a permanent relationship.[32]
55
+ - 'Soviet Union The Soviet Union (Russian: Сове́тский Сою́з, tr. Sovétsky Soyúz,
56
+ IPA: [sɐˈvʲɛt͡skʲɪj sɐˈjus] ( listen)), officially the Union of Soviet Socialist
57
+ Republics (Russian: Сою́з Сове́тских Социалисти́ческих Респу́блик, tr. Soyúz Sovétskikh
58
+ Sotsialistícheskikh Respúblik, IPA: [sɐˈjus sɐˈvʲɛtskʲɪx sətsɨəlʲɪsˈtʲitɕɪskʲɪx
59
+ rʲɪˈspublʲɪk] ( listen)), abbreviated as the USSR (Russian: СССР, tr. SSSR), was
60
+ a socialist state in Eurasia that existed from 1922 to 1991. Nominally a union
61
+ of multiple national Soviet republics,[a] its government and economy were highly
62
+ centralized. The country was a one-party state, governed by the Communist Party
63
+ with Moscow as its capital in its largest republic, the Russian Soviet Federative
64
+ Socialist Republic. The Russian nation had constitutionally equal status among
65
+ the many nations of the union but exerted de facto dominance in various respects.[7]
66
+ Other major urban centres were Leningrad, Kiev, Minsk, Alma-Ata and Novosibirsk.
67
+ The Soviet Union was one of the five recognized nuclear weapons states and possessed
68
+ the largest stockpile of weapons of mass destruction.[8] It was a founding permanent
69
+ member of the United Nations Security Council, as well as a member of the Organization
70
+ for Security and Co-operation in Europe (OSCE) and the leading member of the Council
71
+ for Mutual Economic Assistance (CMEA) and the Warsaw Pact.'
72
+ - source_sentence: what is the current big bang theory season
73
+ sentences:
74
+ - Byzantine army From the seventh to the 12th centuries, the Byzantine army was
75
+ among the most powerful and effective military forces in the world – neither
76
+ Middle Ages Europe nor (following its early successes) the fracturing Caliphate
77
+ could match the strategies and the efficiency of the Byzantine army. Restricted
78
+ to a largely defensive role in the 7th to mid-9th centuries, the Byzantines developed
79
+ the theme-system to counter the more powerful Caliphate. From the mid-9th century,
80
+ however, they gradually went on the offensive, culminating in the great conquests
81
+ of the 10th century under a series of soldier-emperors such as Nikephoros II Phokas,
82
+ John Tzimiskes and Basil II. The army they led was less reliant on the militia
83
+ of the themes; it was by now a largely professional force, with a strong and well-drilled
84
+ infantry at its core and augmented by a revived heavy cavalry arm. With one of
85
+ the most powerful economies in the world at the time, the Empire had the resources
86
+ to put to the field a powerful host when needed, in order to reclaim its long-lost
87
+ territories.
88
+ - The Big Bang Theory The Big Bang Theory is an American television sitcom created
89
+ by Chuck Lorre and Bill Prady, both of whom serve as executive producers on the
90
+ series, along with Steven Molaro. All three also serve as head writers. The show
91
+ premiered on CBS on September 24, 2007.[3] The series' tenth season premiered
92
+ on September 19, 2016.[4] In March 2017, the series was renewed for two additional
93
+ seasons, bringing its total to twelve, and running through the 2018–19 television
94
+ season. The eleventh season is set to premiere on September 25, 2017.[5]
95
+ - 2016 NCAA Division I Softball Tournament The 2016 NCAA Division I Softball Tournament
96
+ was held from May 20 through June 8, 2016 as the final part of the 2016 NCAA Division
97
+ I softball season. The 64 NCAA Division I college softball teams were to be selected
98
+ out of an eligible 293 teams on May 15, 2016. Thirty-two teams were awarded an
99
+ automatic bid as champions of their conference, and thirty-two teams were selected
100
+ at-large by the NCAA Division I softball selection committee. The tournament culminated
101
+ with eight teams playing in the 2016 Women's College World Series at ASA Hall
102
+ of Fame Stadium in Oklahoma City in which the Oklahoma Sooners were crowned the
103
+ champions.
104
+ - source_sentence: what happened to tates mom on days of our lives
105
+ sentences:
106
+ - 'Paige O''Hara Donna Paige Helmintoller, better known as Paige O''Hara (born May
107
+ 10, 1956),[1] is an American actress, voice actress, singer and painter. O''Hara
108
+ began her career as a Broadway actress in 1983 when she portrayed Ellie May Chipley
109
+ in the musical Showboat. In 1991, she made her motion picture debut in Disney''s
110
+ Beauty and the Beast, in which she voiced the film''s heroine, Belle. Following
111
+ the critical and commercial success of Beauty and the Beast, O''Hara reprised
112
+ her role as Belle in the film''s two direct-to-video follow-ups, Beauty and the
113
+ Beast: The Enchanted Christmas and Belle''s Magical World.'
114
+ - M. Shadows Matthew Charles Sanders (born July 31, 1981), better known as M. Shadows,
115
+ is an American singer, songwriter, and musician. He is best known as the lead
116
+ vocalist, songwriter, and a founding member of the American heavy metal band Avenged
117
+ Sevenfold. In 2017, he was voted 3rd in the list of Top 25 Greatest Modern Frontmen
118
+ by Ultimate Guitar.[1]
119
+ - Theresa Donovan In July 2013, Jeannie returns to Salem, this time going by her
120
+ middle name, Theresa. Initially, she strikes up a connection with resident bad
121
+ boy JJ Deveraux (Casey Moss) while trying to secure some pot.[28] During a confrontation
122
+ with JJ and his mother Jennifer Horton (Melissa Reeves) in her office, her aunt
123
+ Kayla confirms that Theresa is in fact Jeannie and that Jen promised to hire her
124
+ as her assistant, a promise she reluctantly agrees to. Kayla reminds Theresa it
125
+ is her last chance at a fresh start.[29] Theresa also strikes up a bad first impression
126
+ with Jennifer's daughter Abigail Deveraux (Kate Mansi) when Abigail smells pot
127
+ on Theresa in her mother's office.[30] To continue to battle against Jennifer,
128
+ she teams up with Anne Milbauer (Meredith Scott Lynn) in hopes of exacting her
129
+ perfect revenge. In a ploy, Theresa reveals her intentions to hopefully woo Dr.
130
+ Daniel Jonas (Shawn Christian). After sleeping with JJ, Theresa overdoses on marijuana
131
+ and GHB. Upon hearing of their daughter's overdose and continuing problems, Shane
132
+ and Kimberly return to town in the hopes of handling their daughter's problem,
133
+ together. After believing that Theresa has a handle on her addictions, Shane and
134
+ Kimberly leave town together. Theresa then teams up with hospital co-worker Anne
135
+ Milbauer (Meredith Scott Lynn) to conspire against Jennifer, using Daniel as a
136
+ way to hurt their relationship. In early 2014, following a Narcotics Anonymous
137
+ (NA) meeting, she begins a sexual and drugged-fused relationship with Brady Black
138
+ (Eric Martsolf). In 2015, after it is found that Kristen DiMera (Eileen Davidson)
139
+ stole Theresa's embryo and carried it to term, Brady and Melanie Jonas return
140
+ her son, Christopher, to her and Brady, and the pair rename him Tate. When Theresa
141
+ moves into the Kiriakis mansion, tensions arise between her and Victor. She eventually
142
+ expresses her interest in purchasing Basic Black and running it as her own fashion
143
+ company, with financial backing from Maggie Horton (Suzanne Rogers). In the hopes
144
+ of finding the right partner, she teams up with Kate Roberts (Lauren Koslow) and
145
+ Nicole Walker (Arianne Zucker) to achieve the goal of purchasing Basic Black,
146
+ with Kate and Nicole's business background and her own interest in fashion design.
147
+ As she and Brady share several instances of rekindling their romance, she is kicked
148
+ out of the mansion by Victor; as a result, Brady quits Titan and moves in with
149
+ Theresa and Tate, in their own penthouse.
150
+ - source_sentence: where does the last name francisco come from
151
+ sentences:
152
+ - Francisco Francisco is the Spanish and Portuguese form of the masculine given
153
+ name Franciscus (corresponding to English Francis).
154
+ - 'Book of Esther The Book of Esther, also known in Hebrew as "the Scroll" (Megillah),
155
+ is a book in the third section (Ketuvim, "Writings") of the Jewish Tanakh (the
156
+ Hebrew Bible) and in the Christian Old Testament. It is one of the five Scrolls
157
+ (Megillot) in the Hebrew Bible. It relates the story of a Hebrew woman in Persia,
158
+ born as Hadassah but known as Esther, who becomes queen of Persia and thwarts
159
+ a genocide of her people. The story forms the core of the Jewish festival of Purim,
160
+ during which it is read aloud twice: once in the evening and again the following
161
+ morning. The books of Esther and Song of Songs are the only books in the Hebrew
162
+ Bible that do not explicitly mention God.[2]'
163
+ - Times Square Times Square is a major commercial intersection, tourist destination,
164
+ entertainment center and neighborhood in the Midtown Manhattan section of New
165
+ York City at the junction of Broadway and Seventh Avenue. It stretches from West
166
+ 42nd to West 47th Streets.[1] Brightly adorned with billboards and advertisements,
167
+ Times Square is sometimes referred to as "The Crossroads of the World",[2] "The
168
+ Center of the Universe",[3] "the heart of The Great White Way",[4][5][6] and the
169
+ "heart of the world".[7] One of the world's busiest pedestrian areas,[8] it is
170
+ also the hub of the Broadway Theater District[9] and a major center of the world's
171
+ entertainment industry.[10] Times Square is one of the world's most visited tourist
172
+ attractions, drawing an estimated 50 million visitors annually.[11] Approximately
173
+ 330,000 people pass through Times Square daily,[12] many of them tourists,[13]
174
+ while over 460,000 pedestrians walk through Times Square on its busiest days.[7]
175
+ datasets:
176
+ - sentence-transformers/natural-questions
177
+ pipeline_tag: sentence-similarity
178
+ library_name: sentence-transformers
179
+ metrics:
180
+ - cosine_accuracy@1
181
+ - cosine_accuracy@3
182
+ - cosine_accuracy@5
183
+ - cosine_accuracy@10
184
+ - cosine_precision@1
185
+ - cosine_precision@3
186
+ - cosine_precision@5
187
+ - cosine_precision@10
188
+ - cosine_recall@1
189
+ - cosine_recall@3
190
+ - cosine_recall@5
191
+ - cosine_recall@10
192
+ - cosine_ndcg@10
193
+ - cosine_mrr@10
194
+ - cosine_map@100
195
+ co2_eq_emissions:
196
+ emissions: 53.173500692008666
197
+ energy_consumed: 0.13679759994033647
198
+ source: codecarbon
199
+ training_type: fine-tuning
200
+ on_cloud: false
201
+ cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
202
+ ram_total_size: 31.777088165283203
203
+ hours_used: 0.344
204
+ hardware_used: 1 x NVIDIA GeForce RTX 3090
205
+ model-index:
206
+ - name: mxbai-embed-large-v1 with static query embeddings trained on Natural Questions
207
+ pairs
208
+ results:
209
+ - task:
210
+ type: information-retrieval
211
+ name: Information Retrieval
212
+ dataset:
213
+ name: NanoMSMARCO
214
+ type: NanoMSMARCO
215
+ metrics:
216
+ - type: cosine_accuracy@1
217
+ value: 0.16
218
+ name: Cosine Accuracy@1
219
+ - type: cosine_accuracy@3
220
+ value: 0.24
221
+ name: Cosine Accuracy@3
222
+ - type: cosine_accuracy@5
223
+ value: 0.28
224
+ name: Cosine Accuracy@5
225
+ - type: cosine_accuracy@10
226
+ value: 0.34
227
+ name: Cosine Accuracy@10
228
+ - type: cosine_precision@1
229
+ value: 0.16
230
+ name: Cosine Precision@1
231
+ - type: cosine_precision@3
232
+ value: 0.08
233
+ name: Cosine Precision@3
234
+ - type: cosine_precision@5
235
+ value: 0.05600000000000001
236
+ name: Cosine Precision@5
237
+ - type: cosine_precision@10
238
+ value: 0.034
239
+ name: Cosine Precision@10
240
+ - type: cosine_recall@1
241
+ value: 0.16
242
+ name: Cosine Recall@1
243
+ - type: cosine_recall@3
244
+ value: 0.24
245
+ name: Cosine Recall@3
246
+ - type: cosine_recall@5
247
+ value: 0.28
248
+ name: Cosine Recall@5
249
+ - type: cosine_recall@10
250
+ value: 0.34
251
+ name: Cosine Recall@10
252
+ - type: cosine_ndcg@10
253
+ value: 0.23725805092953053
254
+ name: Cosine Ndcg@10
255
+ - type: cosine_mrr@10
256
+ value: 0.20577777777777775
257
+ name: Cosine Mrr@10
258
+ - type: cosine_map@100
259
+ value: 0.22671842216621577
260
+ name: Cosine Map@100
261
+ - task:
262
+ type: information-retrieval
263
+ name: Information Retrieval
264
+ dataset:
265
+ name: NanoNFCorpus
266
+ type: NanoNFCorpus
267
+ metrics:
268
+ - type: cosine_accuracy@1
269
+ value: 0.08
270
+ name: Cosine Accuracy@1
271
+ - type: cosine_accuracy@3
272
+ value: 0.2
273
+ name: Cosine Accuracy@3
274
+ - type: cosine_accuracy@5
275
+ value: 0.28
276
+ name: Cosine Accuracy@5
277
+ - type: cosine_accuracy@10
278
+ value: 0.36
279
+ name: Cosine Accuracy@10
280
+ - type: cosine_precision@1
281
+ value: 0.08
282
+ name: Cosine Precision@1
283
+ - type: cosine_precision@3
284
+ value: 0.09333333333333332
285
+ name: Cosine Precision@3
286
+ - type: cosine_precision@5
287
+ value: 0.09200000000000001
288
+ name: Cosine Precision@5
289
+ - type: cosine_precision@10
290
+ value: 0.08399999999999999
291
+ name: Cosine Precision@10
292
+ - type: cosine_recall@1
293
+ value: 0.003567099567099567
294
+ name: Cosine Recall@1
295
+ - type: cosine_recall@3
296
+ value: 0.00780253787262505
297
+ name: Cosine Recall@3
298
+ - type: cosine_recall@5
299
+ value: 0.032721284486266905
300
+ name: Cosine Recall@5
301
+ - type: cosine_recall@10
302
+ value: 0.04284774158371686
303
+ name: Cosine Recall@10
304
+ - type: cosine_ndcg@10
305
+ value: 0.09353788666049406
306
+ name: Cosine Ndcg@10
307
+ - type: cosine_mrr@10
308
+ value: 0.16635714285714287
309
+ name: Cosine Mrr@10
310
+ - type: cosine_map@100
311
+ value: 0.03350285958868042
312
+ name: Cosine Map@100
313
+ - task:
314
+ type: information-retrieval
315
+ name: Information Retrieval
316
+ dataset:
317
+ name: NanoNQ
318
+ type: NanoNQ
319
+ metrics:
320
+ - type: cosine_accuracy@1
321
+ value: 0.2
322
+ name: Cosine Accuracy@1
323
+ - type: cosine_accuracy@3
324
+ value: 0.42
325
+ name: Cosine Accuracy@3
326
+ - type: cosine_accuracy@5
327
+ value: 0.48
328
+ name: Cosine Accuracy@5
329
+ - type: cosine_accuracy@10
330
+ value: 0.56
331
+ name: Cosine Accuracy@10
332
+ - type: cosine_precision@1
333
+ value: 0.2
334
+ name: Cosine Precision@1
335
+ - type: cosine_precision@3
336
+ value: 0.13999999999999999
337
+ name: Cosine Precision@3
338
+ - type: cosine_precision@5
339
+ value: 0.1
340
+ name: Cosine Precision@5
341
+ - type: cosine_precision@10
342
+ value: 0.05800000000000001
343
+ name: Cosine Precision@10
344
+ - type: cosine_recall@1
345
+ value: 0.18
346
+ name: Cosine Recall@1
347
+ - type: cosine_recall@3
348
+ value: 0.38
349
+ name: Cosine Recall@3
350
+ - type: cosine_recall@5
351
+ value: 0.45
352
+ name: Cosine Recall@5
353
+ - type: cosine_recall@10
354
+ value: 0.53
355
+ name: Cosine Recall@10
356
+ - type: cosine_ndcg@10
357
+ value: 0.3613956797522054
358
+ name: Cosine Ndcg@10
359
+ - type: cosine_mrr@10
360
+ value: 0.32304761904761903
361
+ name: Cosine Mrr@10
362
+ - type: cosine_map@100
363
+ value: 0.31800623900654096
364
+ name: Cosine Map@100
365
+ - task:
366
+ type: nano-beir
367
+ name: Nano BEIR
368
+ dataset:
369
+ name: NanoBEIR mean
370
+ type: NanoBEIR_mean
371
+ metrics:
372
+ - type: cosine_accuracy@1
373
+ value: 0.14666666666666667
374
+ name: Cosine Accuracy@1
375
+ - type: cosine_accuracy@3
376
+ value: 0.2866666666666667
377
+ name: Cosine Accuracy@3
378
+ - type: cosine_accuracy@5
379
+ value: 0.3466666666666667
380
+ name: Cosine Accuracy@5
381
+ - type: cosine_accuracy@10
382
+ value: 0.42
383
+ name: Cosine Accuracy@10
384
+ - type: cosine_precision@1
385
+ value: 0.14666666666666667
386
+ name: Cosine Precision@1
387
+ - type: cosine_precision@3
388
+ value: 0.10444444444444445
389
+ name: Cosine Precision@3
390
+ - type: cosine_precision@5
391
+ value: 0.08266666666666668
392
+ name: Cosine Precision@5
393
+ - type: cosine_precision@10
394
+ value: 0.058666666666666666
395
+ name: Cosine Precision@10
396
+ - type: cosine_recall@1
397
+ value: 0.11452236652236653
398
+ name: Cosine Recall@1
399
+ - type: cosine_recall@3
400
+ value: 0.20926751262420837
401
+ name: Cosine Recall@3
402
+ - type: cosine_recall@5
403
+ value: 0.25424042816208897
404
+ name: Cosine Recall@5
405
+ - type: cosine_recall@10
406
+ value: 0.30428258052790563
407
+ name: Cosine Recall@10
408
+ - type: cosine_ndcg@10
409
+ value: 0.23073053911407668
410
+ name: Cosine Ndcg@10
411
+ - type: cosine_mrr@10
412
+ value: 0.2317275132275132
413
+ name: Cosine Mrr@10
414
+ - type: cosine_map@100
415
+ value: 0.19274250692047903
416
+ name: Cosine Map@100
417
+ ---
418
+
419
+ # mxbai-embed-large-v1 with static query embeddings trained on Natural Questions pairs
420
+
421
+ This is a [sentence-transformers](https://www.SBERT.net) model trained on the [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) dataset. 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.
422
+
423
+ ## Model Details
424
+
425
+ ### Model Description
426
+ - **Model Type:** Sentence Transformer
427
+ <!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
428
+ - **Maximum Sequence Length:** inf tokens
429
+ - **Output Dimensionality:** 1024 dimensions
430
+ - **Similarity Function:** Cosine Similarity
431
+ - **Training Dataset:**
432
+ - [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions)
433
+ - **Language:** en
434
+ - **License:** apache-2.0
435
+
436
+ ### Model Sources
437
+
438
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
439
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
440
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
441
+
442
+ ### Full Model Architecture
443
+
444
+ ```
445
+ SentenceTransformer(
446
+ (0): Router(
447
+ (query_0_StaticEmbedding): StaticEmbedding(
448
+ (embedding): EmbeddingBag(30522, 1024, mode='mean')
449
+ )
450
+ (document_0_Transformer): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
451
+ (document_1_Pooling): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, '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': False, 'include_prompt': True})
452
+ )
453
+ (1): Normalize()
454
+ )
455
+ ```
456
+
457
+ ## Usage
458
+
459
+ ### Direct Usage (Sentence Transformers)
460
+
461
+ First install the Sentence Transformers library:
462
+
463
+ ```bash
464
+ pip install -U sentence-transformers
465
+ ```
466
+
467
+ Then you can load this model and run inference.
468
+ ```python
469
+ from sentence_transformers import SentenceTransformer
470
+
471
+ # Download from the 🤗 Hub
472
+ model = SentenceTransformer("tomaarsen/mxbai-embed-large-v1-static-queries-nq")
473
+ # Run inference
474
+ sentences = [
475
+ 'where does the last name francisco come from',
476
+ 'Francisco Francisco is the Spanish and Portuguese form of the masculine given name Franciscus (corresponding to English Francis).',
477
+ 'Book of Esther The Book of Esther, also known in Hebrew as "the Scroll" (Megillah), is a book in the third section (Ketuvim, "Writings") of the Jewish Tanakh (the Hebrew Bible) and in the Christian Old Testament. It is one of the five Scrolls (Megillot) in the Hebrew Bible. It relates the story of a Hebrew woman in Persia, born as Hadassah but known as Esther, who becomes queen of Persia and thwarts a genocide of her people. The story forms the core of the Jewish festival of Purim, during which it is read aloud twice: once in the evening and again the following morning. The books of Esther and Song of Songs are the only books in the Hebrew Bible that do not explicitly mention God.[2]',
478
+ ]
479
+ embeddings = model.encode(sentences)
480
+ print(embeddings.shape)
481
+ # [3, 1024]
482
+
483
+ # Get the similarity scores for the embeddings
484
+ similarities = model.similarity(embeddings, embeddings)
485
+ print(similarities.shape)
486
+ # [3, 3]
487
+ ```
488
+
489
+ <!--
490
+ ### Direct Usage (Transformers)
491
+
492
+ <details><summary>Click to see the direct usage in Transformers</summary>
493
+
494
+ </details>
495
+ -->
496
+
497
+ <!--
498
+ ### Downstream Usage (Sentence Transformers)
499
+
500
+ You can finetune this model on your own dataset.
501
+
502
+ <details><summary>Click to expand</summary>
503
+
504
+ </details>
505
+ -->
506
+
507
+ <!--
508
+ ### Out-of-Scope Use
509
+
510
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
511
+ -->
512
+
513
+ ## Evaluation
514
+
515
+ ### Metrics
516
+
517
+ #### Information Retrieval
518
+
519
+ * Datasets: `NanoMSMARCO`, `NanoNFCorpus` and `NanoNQ`
520
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
521
+
522
+ | Metric | NanoMSMARCO | NanoNFCorpus | NanoNQ |
523
+ |:--------------------|:------------|:-------------|:-----------|
524
+ | cosine_accuracy@1 | 0.16 | 0.08 | 0.2 |
525
+ | cosine_accuracy@3 | 0.24 | 0.2 | 0.42 |
526
+ | cosine_accuracy@5 | 0.28 | 0.28 | 0.48 |
527
+ | cosine_accuracy@10 | 0.34 | 0.36 | 0.56 |
528
+ | cosine_precision@1 | 0.16 | 0.08 | 0.2 |
529
+ | cosine_precision@3 | 0.08 | 0.0933 | 0.14 |
530
+ | cosine_precision@5 | 0.056 | 0.092 | 0.1 |
531
+ | cosine_precision@10 | 0.034 | 0.084 | 0.058 |
532
+ | cosine_recall@1 | 0.16 | 0.0036 | 0.18 |
533
+ | cosine_recall@3 | 0.24 | 0.0078 | 0.38 |
534
+ | cosine_recall@5 | 0.28 | 0.0327 | 0.45 |
535
+ | cosine_recall@10 | 0.34 | 0.0428 | 0.53 |
536
+ | **cosine_ndcg@10** | **0.2373** | **0.0935** | **0.3614** |
537
+ | cosine_mrr@10 | 0.2058 | 0.1664 | 0.323 |
538
+ | cosine_map@100 | 0.2267 | 0.0335 | 0.318 |
539
+
540
+ #### Nano BEIR
541
+
542
+ * Dataset: `NanoBEIR_mean`
543
+ * Evaluated with [<code>NanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.NanoBEIREvaluator) with these parameters:
544
+ ```json
545
+ {
546
+ "dataset_names": [
547
+ "msmarco",
548
+ "nfcorpus",
549
+ "nq"
550
+ ]
551
+ }
552
+ ```
553
+
554
+ | Metric | Value |
555
+ |:--------------------|:-----------|
556
+ | cosine_accuracy@1 | 0.1467 |
557
+ | cosine_accuracy@3 | 0.2867 |
558
+ | cosine_accuracy@5 | 0.3467 |
559
+ | cosine_accuracy@10 | 0.42 |
560
+ | cosine_precision@1 | 0.1467 |
561
+ | cosine_precision@3 | 0.1044 |
562
+ | cosine_precision@5 | 0.0827 |
563
+ | cosine_precision@10 | 0.0587 |
564
+ | cosine_recall@1 | 0.1145 |
565
+ | cosine_recall@3 | 0.2093 |
566
+ | cosine_recall@5 | 0.2542 |
567
+ | cosine_recall@10 | 0.3043 |
568
+ | **cosine_ndcg@10** | **0.2307** |
569
+ | cosine_mrr@10 | 0.2317 |
570
+ | cosine_map@100 | 0.1927 |
571
+
572
+ <!--
573
+ ## Bias, Risks and Limitations
574
+
575
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
576
+ -->
577
+
578
+ <!--
579
+ ### Recommendations
580
+
581
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
582
+ -->
583
+
584
+ ## Training Details
585
+
586
+ ### Training Dataset
587
+
588
+ #### natural-questions
589
+
590
+ * Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
591
+ * Size: 99,231 training samples
592
+ * Columns: <code>query</code> and <code>answer</code>
593
+ * Approximate statistics based on the first 1000 samples:
594
+ | | query | answer |
595
+ |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
596
+ | type | string | string |
597
+ | details | <ul><li>min: 10 tokens</li><li>mean: 11.74 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 137.2 tokens</li><li>max: 508 tokens</li></ul> |
598
+ * Samples:
599
+ | query | answer |
600
+ |:------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
601
+ | <code>who is required to report according to the hmda</code> | <code>Home Mortgage Disclosure Act US financial institutions must report HMDA data to their regulator if they meet certain criteria, such as having assets above a specific threshold. The criteria is different for depository and non-depository institutions and are available on the FFIEC website.[4] In 2012, there were 7,400 institutions that reported a total of 18.7 million HMDA records.[5]</code> |
602
+ | <code>what is the definition of endoplasmic reticulum in biology</code> | <code>Endoplasmic reticulum The endoplasmic reticulum (ER) is a type of organelle in eukaryotic cells that forms an interconnected network of flattened, membrane-enclosed sacs or tube-like structures known as cisternae. The membranes of the ER are continuous with the outer nuclear membrane. The endoplasmic reticulum occurs in most types of eukaryotic cells, but is absent from red blood cells and spermatozoa. There are two types of endoplasmic reticulum: rough and smooth. The outer (cytosolic) face of the rough endoplasmic reticulum is studded with ribosomes that are the sites of protein synthesis. The rough endoplasmic reticulum is especially prominent in cells such as hepatocytes. The smooth endoplasmic reticulum lacks ribosomes and functions in lipid manufacture and metabolism, the production of steroid hormones, and detoxification.[1] The smooth ER is especially abundant in mammalian liver and gonad cells. The lacy membranes of the endoplasmic reticulum were first seen in 1945 using elect...</code> |
603
+ | <code>what does the ski mean in polish names</code> | <code>Polish name Since the High Middle Ages, Polish-sounding surnames ending with the masculine -ski suffix, including -cki and -dzki, and the corresponding feminine suffix -ska/-cka/-dzka were associated with the nobility (Polish szlachta), which alone, in the early years, had such suffix distinctions.[1] They are widely popular today.</code> |
604
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
605
+ ```json
606
+ {
607
+ "scale": 20.0,
608
+ "similarity_fct": "cos_sim"
609
+ }
610
+ ```
611
+
612
+ ### Evaluation Dataset
613
+
614
+ #### natural-questions
615
+
616
+ * Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
617
+ * Size: 1,000 evaluation samples
618
+ * Columns: <code>query</code> and <code>answer</code>
619
+ * Approximate statistics based on the first 1000 samples:
620
+ | | query | answer |
621
+ |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
622
+ | type | string | string |
623
+ | details | <ul><li>min: 10 tokens</li><li>mean: 11.78 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 135.64 tokens</li><li>max: 512 tokens</li></ul> |
624
+ * Samples:
625
+ | query | answer |
626
+ |:------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
627
+ | <code>difference between russian blue and british blue cat</code> | <code>Russian Blue The coat is known as a "double coat", with the undercoat being soft, downy and equal in length to the guard hairs, which are an even blue with silver tips. However, the tail may have a few very dull, almost unnoticeable stripes. The coat is described as thick, plush and soft to the touch. The feeling is softer than the softest silk. The silver tips give the coat a shimmering appearance. Its eyes are almost always a dark and vivid green. Any white patches of fur or yellow eyes in adulthood are seen as flaws in show cats.[3] Russian Blues should not be confused with British Blues (which are not a distinct breed, but rather a British Shorthair with a blue coat as the British Shorthair breed itself comes in a wide variety of colors and patterns), nor the Chartreux or Korat which are two other naturally occurring breeds of blue cats, although they have similar traits.</code> |
628
+ | <code>who played the little girl on mrs doubtfire</code> | <code>Mara Wilson Mara Elizabeth Wilson[2] (born July 24, 1987) is an American writer and former child actress. She is known for playing Natalie Hillard in Mrs. Doubtfire (1993), Susan Walker in Miracle on 34th Street (1994), Matilda Wormwood in Matilda (1996) and Lily Stone in Thomas and the Magic Railroad (2000). Since retiring from film acting, Wilson has focused on writing.</code> |
629
+ | <code>what year did the movie the sound of music come out</code> | <code>The Sound of Music (film) The film was released on March 2, 1965 in the United States, initially as a limited roadshow theatrical release. Although critical response to the film was widely mixed, the film was a major commercial success, becoming the number one box office movie after four weeks, and the highest-grossing film of 1965. By November 1966, The Sound of Music had become the highest-grossing film of all-time—surpassing Gone with the Wind—and held that distinction for five years. The film was just as popular throughout the world, breaking previous box-office records in twenty-nine countries. Following an initial theatrical release that lasted four and a half years, and two successful re-releases, the film sold 283 million admissions worldwide and earned a total worldwide gross of $286,000,000.</code> |
630
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
631
+ ```json
632
+ {
633
+ "scale": 20.0,
634
+ "similarity_fct": "cos_sim"
635
+ }
636
+ ```
637
+
638
+ ### Training Hyperparameters
639
+ #### Non-Default Hyperparameters
640
+
641
+ - `eval_strategy`: steps
642
+ - `per_device_train_batch_size`: 16
643
+ - `per_device_eval_batch_size`: 16
644
+ - `learning_rate`: 2e-05
645
+ - `num_train_epochs`: 1
646
+ - `warmup_ratio`: 0.1
647
+ - `seed`: 12
648
+ - `bf16`: True
649
+ - `batch_sampler`: no_duplicates
650
+ - `router_mapping`: {'query': 'query', 'answer': 'document'}
651
+ - `learning_rate_mapping`: {'StaticEmbedding\\.embedding': 0.2}
652
+
653
+ #### All Hyperparameters
654
+ <details><summary>Click to expand</summary>
655
+
656
+ - `overwrite_output_dir`: False
657
+ - `do_predict`: False
658
+ - `eval_strategy`: steps
659
+ - `prediction_loss_only`: True
660
+ - `per_device_train_batch_size`: 16
661
+ - `per_device_eval_batch_size`: 16
662
+ - `per_gpu_train_batch_size`: None
663
+ - `per_gpu_eval_batch_size`: None
664
+ - `gradient_accumulation_steps`: 1
665
+ - `eval_accumulation_steps`: None
666
+ - `torch_empty_cache_steps`: None
667
+ - `learning_rate`: 2e-05
668
+ - `weight_decay`: 0.0
669
+ - `adam_beta1`: 0.9
670
+ - `adam_beta2`: 0.999
671
+ - `adam_epsilon`: 1e-08
672
+ - `max_grad_norm`: 1.0
673
+ - `num_train_epochs`: 1
674
+ - `max_steps`: -1
675
+ - `lr_scheduler_type`: linear
676
+ - `lr_scheduler_kwargs`: {}
677
+ - `warmup_ratio`: 0.1
678
+ - `warmup_steps`: 0
679
+ - `log_level`: passive
680
+ - `log_level_replica`: warning
681
+ - `log_on_each_node`: True
682
+ - `logging_nan_inf_filter`: True
683
+ - `save_safetensors`: True
684
+ - `save_on_each_node`: False
685
+ - `save_only_model`: False
686
+ - `restore_callback_states_from_checkpoint`: False
687
+ - `no_cuda`: False
688
+ - `use_cpu`: False
689
+ - `use_mps_device`: False
690
+ - `seed`: 12
691
+ - `data_seed`: None
692
+ - `jit_mode_eval`: False
693
+ - `use_ipex`: False
694
+ - `bf16`: True
695
+ - `fp16`: False
696
+ - `fp16_opt_level`: O1
697
+ - `half_precision_backend`: auto
698
+ - `bf16_full_eval`: False
699
+ - `fp16_full_eval`: False
700
+ - `tf32`: None
701
+ - `local_rank`: 0
702
+ - `ddp_backend`: None
703
+ - `tpu_num_cores`: None
704
+ - `tpu_metrics_debug`: False
705
+ - `debug`: []
706
+ - `dataloader_drop_last`: False
707
+ - `dataloader_num_workers`: 0
708
+ - `dataloader_prefetch_factor`: None
709
+ - `past_index`: -1
710
+ - `disable_tqdm`: False
711
+ - `remove_unused_columns`: True
712
+ - `label_names`: None
713
+ - `load_best_model_at_end`: False
714
+ - `ignore_data_skip`: False
715
+ - `fsdp`: []
716
+ - `fsdp_min_num_params`: 0
717
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
718
+ - `fsdp_transformer_layer_cls_to_wrap`: None
719
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
720
+ - `deepspeed`: None
721
+ - `label_smoothing_factor`: 0.0
722
+ - `optim`: adamw_torch
723
+ - `optim_args`: None
724
+ - `adafactor`: False
725
+ - `group_by_length`: False
726
+ - `length_column_name`: length
727
+ - `ddp_find_unused_parameters`: None
728
+ - `ddp_bucket_cap_mb`: None
729
+ - `ddp_broadcast_buffers`: False
730
+ - `dataloader_pin_memory`: True
731
+ - `dataloader_persistent_workers`: False
732
+ - `skip_memory_metrics`: True
733
+ - `use_legacy_prediction_loop`: False
734
+ - `push_to_hub`: False
735
+ - `resume_from_checkpoint`: None
736
+ - `hub_model_id`: None
737
+ - `hub_strategy`: every_save
738
+ - `hub_private_repo`: None
739
+ - `hub_always_push`: False
740
+ - `gradient_checkpointing`: False
741
+ - `gradient_checkpointing_kwargs`: None
742
+ - `include_inputs_for_metrics`: False
743
+ - `include_for_metrics`: []
744
+ - `eval_do_concat_batches`: True
745
+ - `fp16_backend`: auto
746
+ - `push_to_hub_model_id`: None
747
+ - `push_to_hub_organization`: None
748
+ - `mp_parameters`:
749
+ - `auto_find_batch_size`: False
750
+ - `full_determinism`: False
751
+ - `torchdynamo`: None
752
+ - `ray_scope`: last
753
+ - `ddp_timeout`: 1800
754
+ - `torch_compile`: False
755
+ - `torch_compile_backend`: None
756
+ - `torch_compile_mode`: None
757
+ - `include_tokens_per_second`: False
758
+ - `include_num_input_tokens_seen`: False
759
+ - `neftune_noise_alpha`: None
760
+ - `optim_target_modules`: None
761
+ - `batch_eval_metrics`: False
762
+ - `eval_on_start`: False
763
+ - `use_liger_kernel`: False
764
+ - `eval_use_gather_object`: False
765
+ - `average_tokens_across_devices`: False
766
+ - `prompts`: None
767
+ - `batch_sampler`: no_duplicates
768
+ - `multi_dataset_batch_sampler`: proportional
769
+ - `router_mapping`: {'query': 'query', 'answer': 'document'}
770
+ - `learning_rate_mapping`: {'StaticEmbedding\\.embedding': 0.2}
771
+
772
+ </details>
773
+
774
+ ### Training Logs
775
+ | Epoch | Step | Training Loss | Validation Loss | NanoMSMARCO_cosine_ndcg@10 | NanoNFCorpus_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
776
+ |:------:|:----:|:-------------:|:---------------:|:--------------------------:|:---------------------------:|:---------------------:|:----------------------------:|
777
+ | -1 | -1 | - | - | 0.0 | 0.0195 | 0.0 | 0.0065 |
778
+ | 0.0002 | 1 | 2.9289 | - | - | - | - | - |
779
+ | 0.0322 | 200 | 2.7795 | - | - | - | - | - |
780
+ | 0.0645 | 400 | 2.137 | - | - | - | - | - |
781
+ | 0.0967 | 600 | 1.5211 | 1.1857 | 0.0440 | 0.0317 | 0.1087 | 0.0615 |
782
+ | 0.1290 | 800 | 1.0909 | - | - | - | - | - |
783
+ | 0.1612 | 1000 | 0.8669 | - | - | - | - | - |
784
+ | 0.1935 | 1200 | 0.7003 | 0.5961 | 0.0990 | 0.0503 | 0.2530 | 0.1341 |
785
+ | 0.2257 | 1400 | 0.5979 | - | - | - | - | - |
786
+ | 0.2580 | 1600 | 0.5242 | - | - | - | - | - |
787
+ | 0.2902 | 1800 | 0.4695 | 0.4039 | 0.1633 | 0.0596 | 0.2845 | 0.1691 |
788
+ | 0.3225 | 2000 | 0.4223 | - | - | - | - | - |
789
+ | 0.3547 | 2200 | 0.4145 | - | - | - | - | - |
790
+ | 0.3870 | 2400 | 0.3736 | 0.3128 | 0.1958 | 0.0717 | 0.2990 | 0.1888 |
791
+ | 0.4192 | 2600 | 0.3325 | - | - | - | - | - |
792
+ | 0.4515 | 2800 | 0.3172 | - | - | - | - | - |
793
+ | 0.4837 | 3000 | 0.2966 | 0.2590 | 0.1948 | 0.0744 | 0.3058 | 0.1917 |
794
+ | 0.5160 | 3200 | 0.2741 | - | - | - | - | - |
795
+ | 0.5482 | 3400 | 0.281 | - | - | - | - | - |
796
+ | 0.5805 | 3600 | 0.2533 | 0.2269 | 0.2113 | 0.0805 | 0.3407 | 0.2108 |
797
+ | 0.6127 | 3800 | 0.248 | - | - | - | - | - |
798
+ | 0.6450 | 4000 | 0.2402 | - | - | - | - | - |
799
+ | 0.6772 | 4200 | 0.2267 | 0.2044 | 0.2188 | 0.0810 | 0.3396 | 0.2131 |
800
+ | 0.7094 | 4400 | 0.2172 | - | - | - | - | - |
801
+ | 0.7417 | 4600 | 0.2277 | - | - | - | - | - |
802
+ | 0.7739 | 4800 | 0.2047 | 0.1905 | 0.2276 | 0.0893 | 0.3352 | 0.2173 |
803
+ | 0.8062 | 5000 | 0.2011 | - | - | - | - | - |
804
+ | 0.8384 | 5200 | 0.198 | - | - | - | - | - |
805
+ | 0.8707 | 5400 | 0.2025 | 0.1826 | 0.2439 | 0.0939 | 0.3443 | 0.2274 |
806
+ | 0.9029 | 5600 | 0.2018 | - | - | - | - | - |
807
+ | 0.9352 | 5800 | 0.1896 | - | - | - | - | - |
808
+ | 0.9674 | 6000 | 0.1973 | 0.1783 | 0.2373 | 0.0919 | 0.3614 | 0.2302 |
809
+ | 0.9997 | 6200 | 0.1924 | - | - | - | - | - |
810
+ | -1 | -1 | - | - | 0.2373 | 0.0935 | 0.3614 | 0.2307 |
811
+
812
+
813
+ ### Environmental Impact
814
+ Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
815
+ - **Energy Consumed**: 0.137 kWh
816
+ - **Carbon Emitted**: 0.053 kg of CO2
817
+ - **Hours Used**: 0.344 hours
818
+
819
+ ### Training Hardware
820
+ - **On Cloud**: No
821
+ - **GPU Model**: 1 x NVIDIA GeForce RTX 3090
822
+ - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
823
+ - **RAM Size**: 31.78 GB
824
+
825
+ ### Framework Versions
826
+ - Python: 3.11.6
827
+ - Sentence Transformers: 4.2.0.dev0
828
+ - Transformers: 4.52.3
829
+ - PyTorch: 2.6.0+cu124
830
+ - Accelerate: 1.5.1
831
+ - Datasets: 2.21.0
832
+ - Tokenizers: 0.21.1
833
+
834
+ ## Citation
835
+
836
+ ### BibTeX
837
+
838
+ #### Sentence Transformers
839
+ ```bibtex
840
+ @inproceedings{reimers-2019-sentence-bert,
841
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
842
+ author = "Reimers, Nils and Gurevych, Iryna",
843
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
844
+ month = "11",
845
+ year = "2019",
846
+ publisher = "Association for Computational Linguistics",
847
+ url = "https://arxiv.org/abs/1908.10084",
848
+ }
849
+ ```
850
+
851
+ #### MultipleNegativesRankingLoss
852
+ ```bibtex
853
+ @misc{henderson2017efficient,
854
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
855
+ 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},
856
+ year={2017},
857
+ eprint={1705.00652},
858
+ archivePrefix={arXiv},
859
+ primaryClass={cs.CL}
860
+ }
861
+ ```
862
+
863
+ <!--
864
+ ## Glossary
865
+
866
+ *Clearly define terms in order to be accessible across audiences.*
867
+ -->
868
+
869
+ <!--
870
+ ## Model Card Authors
871
+
872
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
873
+ -->
874
+
875
+ <!--
876
+ ## Model Card Contact
877
+
878
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
879
+ -->
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "SentenceTransformer",
3
+ "__version__": {
4
+ "sentence_transformers": "4.2.0.dev0",
5
+ "transformers": "4.52.3",
6
+ "pytorch": "2.6.0+cu124"
7
+ },
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
document_0_Transformer/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.52.3",
22
+ "type_vocab_size": 2,
23
+ "use_cache": false,
24
+ "vocab_size": 30522
25
+ }
document_0_Transformer/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e86b2a89f7f8933cf7bd90586cdf69d0012140e412818234b234f807e51ee574
3
+ size 1340612432
document_0_Transformer/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
document_0_Transformer/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
document_0_Transformer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
document_0_Transformer/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
document_0_Transformer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
document_1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": true,
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": false,
9
+ "include_prompt": true
10
+ }
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Router"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Normalize",
12
+ "type": "sentence_transformers.models.Normalize"
13
+ }
14
+ ]
query_0_StaticEmbedding/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c5907e6d0ac47451d74219076ab420a33c703a41de49072c6e39ea4fc089b4b
3
+ size 125018208
query_0_StaticEmbedding/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
router_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "types": {
3
+ "query_0_StaticEmbedding": "sentence_transformers.models.StaticEmbedding.StaticEmbedding",
4
+ "document_0_Transformer": "sentence_transformers.models.Transformer.Transformer",
5
+ "document_1_Pooling": "sentence_transformers.models.Pooling.Pooling"
6
+ },
7
+ "structure": {
8
+ "query": [
9
+ "query_0_StaticEmbedding"
10
+ ],
11
+ "document": [
12
+ "document_0_Transformer",
13
+ "document_1_Pooling"
14
+ ]
15
+ },
16
+ "parameters": {
17
+ "default_route": "document",
18
+ "allow_empty_key": true
19
+ }
20
+ }