Hugging Face's logo

tomaarsen
/
mpnet-base-msmarco-margin-mse

Sentence Similarity
sentence-transformers
Safetensors
English
mpnet
feature-extraction
dense
Generated from Trainer
dataset_size:10000
loss:MarginMSELoss
Eval Results
Model card Files
xet
Community
tomaarsen HF Staff commited on
Commit
98f33ba
·
verified ·
1 Parent(s): 4617e8f

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +751 -0
  3. config.json +23 -0
  4. config_sentence_transformers.json +14 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +73 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,751 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:10000
12
+ - loss:MarginMSELoss
13
+ base_model: microsoft/mpnet-base
14
+ widget:
15
+ - source_sentence: what commands can i use in netflix?
16
+ sentences:
17
+ - Netflix is a streaming service that allows our customers to watch a wide variety
18
+ of award-winning TV shows, movies, documentaries and more on thousands of Internet-connected
19
+ devices. With Netflix, you can enjoy unlimited viewing of our content without
20
+ having to watch a single commercial.
21
+ - 'Best Answer: You can check out http://instantwatcher.com to see everything they
22
+ have available. Currently there are 9,381 movies. Netflix''s API says they have
23
+ 4,505 TV shows, but their system counts individual seasons as separate titles.
24
+ The true number is probably between 1,500-2000. As far as I know, there was a
25
+ time when people thought that Netflix is the best service for watching TV shows
26
+ and movies.'
27
+ - The Cortana help section includes the recommended commands you should use for
28
+ each app. Netflix, for example, uses Netflix find [show or movie].. Cortana commands
29
+ work by either speaking or typing (if you don't have a microphone or can't bring
30
+ yourself to talk to your computer). If you do use the voice feature, don't forget
31
+ to start with Hey Cortana..
32
+ - InstantWatcher is a better way to search for Amazon Prime and Netflix videos.
33
+ The site helps you find what you want to watch. Find Ratings. Amazon Prime Instant
34
+ Video and Netflix both provide a wide variety of movies and television shows on
35
+ their video streaming services. But finding the show you want to watch can be
36
+ frustrating.
37
+ - Courageous fullmovie-youtube-Watch movies online instantly with netflix movies.
38
+ see a list of all available instant netflix movies and start your streaming at
39
+ movies.com...
40
+ - "AllFlicks is a Netflix search engine that, according to Lifehacker, â\x80\x9C\
41
+ provides much more powerful search criteriaâ\x80\x9D than Netflix. In addition\
42
+ \ to searching, you can browse Netflixâ\x80\x99s catalog and sort the list of\
43
+ \ movies and TV shows by Title, Release Year, Genre, Rating, and Netflix Availability\
44
+ \ Date. By default, the list is sorted by Netflix Availability Date, so that you\
45
+ \ can quickly see whatâ\x80\x99s new on Netflix."
46
+ - What special equipment do I need to watch Netflix. All you need is a computer
47
+ and a connection to the internet and you can watch it directly on Netflix.com.
48
+ In addition you can download the free Netflix app onto your smart TV, game console,
49
+ streaming player, phone or tablet.
50
+ - "To get Netflix on your player you need to select the Netflix App icon, or download\
51
+ \ it from your connected Blu-ray playerâ\x80\x99s store if itâ\x80\x99s not displayed.\
52
+ \ Enter your account information as normal and add the activation code to the\
53
+ \ Netflix site to activate the player on your account."
54
+ - tv The Best Streaming Netflix TV Shows. List Rules Serial TV shows that are currently
55
+ streaming on Netflix. No movies. The best streaming Netflix TV shows include some
56
+ great television dramas, sci-fi/adventure shows, sitcoms, and reality TV programs.
57
+ - source_sentence: can the new zealand citizen be a dependant child when applying
58
+ for a 461 visa
59
+ sentences:
60
+ - "The subclass 461 visa is valid for five years and it may be renewed, subject\
61
+ \ to certain conditions being met. The visa extension may be granted even if the\
62
+ \ relationship with the New Zealand citizen on the 444 visa has broken down, as\
63
+ \ long as certain conditions are met.enerally, the applicant should not be married,\
64
+ \ but a widow or divorced person is able to apply. One non-blood relationship\
65
+ \ which is acceptable is if the applicant for the 461 visa is a dependent child\
66
+ \ of the New Zealand citizenâ\x80\x99s partner or spouse."
67
+ - You can claim a boyfriend or girlfriend and their children as dependents if they
68
+ are your qualifying relatives. they are not a qualifying child of another taxpayer.
69
+ they meet all of the requirements above to be a qualifying relative.
70
+ - 'This generally would be your parent or guardian. Here are the criteria for being
71
+ claimed as a dependent as a qualifying child 1 : You are the child, stepchild,
72
+ foster child, sibling, stepsibling or descendant of another taxpayer. 2 You lived
73
+ with the taxpayer for more than half a year (there are some exceptions).'
74
+ - 1 An Australian citizen travelling on an Australian passport. 2 British citizen
75
+ and or British passport holder who can produce evidence of the right to reside
76
+ permanently in the UK (you can stay up to six months) A citizen of a country
77
+ which has a visa waiver agreement with New Zealand (you can stay up to three months).
78
+ - 'Posted. Normally, parents are not considered dependents unless the situations
79
+ in this document apply: http://www.cra-arc.g...5/lgbl-eng.html. For non-resident
80
+ dependents (such as the spouse or children of a newcomer to Canada who is still
81
+ residing in their home country), you are able to claim them as dependents.osted.
82
+ Normally, parents are not considered dependents unless the situations in this
83
+ document apply: http://www.cra-arc.g...5/lgbl-eng.html. For non-resident dependents
84
+ (such as the spouse or children of a newcomer to Canada who is still residing
85
+ in their home country), you are able to claim them as dependents.'
86
+ - 'Answer: Each child can only be claimed as a dependent by one parent (except when
87
+ married couples file taxes jointly). Typically, in the case of divorced, separated,
88
+ or never married parents, it is the custodial parent who is legally able to claim
89
+ a child as a dependent for tax purposes.'
90
+ - "Effective August 1, 2014, Citizenship and Immigration Canada has changed its\
91
+ \ definition of a dependent child for its immigration programs. A dependent child\
92
+ \ must be under 19 years of age, instead of the previous limit of under 22 years\
93
+ \ of age. Find out more about the change in the definition of a dependent child.\
94
+ \ son or daughter is considered a dependant of their parent when the child is:\
95
+ \ 1 under 19 years old, and does not have a spouse or partner, or. 2 19 years\
96
+ \ old and over, and has depended largely on the parentâ\x80\x99s financial support\
97
+ \ since before the age of 19 because of a physical or mental condition."
98
+ - "Children who qualify as dependents. If your son or daughter is your biological\
99
+ \ child, stepchild, foster child, sibling, step-sibling, or a descendant of any\
100
+ \ of these individuals, you can claim him/her as your dependent, but the child\
101
+ \ canâ\x80\x99t turn 19 at any time during the tax year (age 24 if a full-time\
102
+ \ student)."
103
+ - There is no age limit on claiming your child as a dependent if the child meets
104
+ the qualifying relative test. As long as all of the following tests are met, you
105
+ may claim a dependency exemption for your child:1 Qualifying child or qualifying
106
+ relative test, 2 Dependent taxpayer test, 3 Citizen or resident test, and.o
107
+ meet the qualifying child test, your child must be younger than you and, as of
108
+ the end of the calendar year, either be younger than 19 years old or be a student
109
+ and younger than 24 years old.
110
+ - source_sentence: how soon can i start the nuvaring
111
+ sentences:
112
+ - Nuva ring effective in 7 days? How does this work? I just started Nuva ring, actually
113
+ it's my first birth control, and my doctor said that it only takes 7 days to become
114
+ effective. I've always heard it takes a FULL Cycle...It's making me think about
115
+ how many hormones are actually in the ring... does anyone know why it only takes
116
+ 7 days opposed to a full cyle? thanks.
117
+ - Menorrhagia is not something you have to put up. with, and NovaSure may be the
118
+ solution. *The average treatment time is 90 seconds, and the entire NovaSure procedure.
119
+ typically takes less than 5 minutes to complete.
120
+ - If NuvaRing® is not started within five days after a first trimester abortion
121
+ or miscarriage, begin NuvaRing® at the time of your next menstrual period. Counting
122
+ the first day of your menstrual period as Day 1, insert NuvaRing® on or before
123
+ Day 5 of the cycle, even if you have not finished bleeding. During this first
124
+ cycle, use an extra method of birth control, such as male condoms or spermicide,
125
+ for the first seven days of ring use.
126
+ - '#1 trinidadman Junior Member. Hello, I have a female friend of mine doing 15mg
127
+ (5 morning 10mg at noon) of anavar , she has been on for about 5 days, when should
128
+ she start to see any results? Bye the way before everyone starts asking why the
129
+ morning afternoon stuff.'
130
+ - Alternatively, if the NuvaRing is outside the vagina for more than three hours
131
+ during the third week, you can start using a new ring right away. This may cause
132
+ breakthrough spotting or bleeding. Use a backup method of contraception until
133
+ you have used the new ring continuously for seven days. Or, if you used NuvaRing
134
+ continuously for at least the previous seven days prior to explusion, you can
135
+ discard the ring and wait up to seven days from the time the ring was removed
136
+ or expelled to insert a new ring.
137
+ - 'RE: do you have to store nuvaring in the refrigerator for it to be active? i
138
+ got my nuvaring about 2 weeks ago and they told me to keep it stored in the fridge,
139
+ i've had it in the side of my daughters diaper bag the whole time cause i
140
+ forgot all about it.'
141
+ - No!!! You need to keep Nuvaring in for for 3 weeks, take it out for one week,
142
+ (7 days) then replace with a new one for another 21 days! If you take it out ,
143
+ you before 21 days you can get pregnant. And on the web site they have a little
144
+ desktop app that keeps track of the in and out times.
145
+ - Just yesterday I went to the doctor to start on the NuvaRing. The doctor had me
146
+ insert the ring at the appointment even though I'm at day 15 of my cycle. When
147
+ I got home, I read that women who are starting NuvaRing who haven't been on another
148
+ form of oral contraceptive should start the ring between days 1 and 5 of their
149
+ cycle.
150
+ - Take one tablet as soon as possible after unprotected sex. The manufacturer recommends
151
+ to take within 72 hours (3 days) after unprotected sex, but studies have shown
152
+ moderate efficacy still exists if taken up to 120 hours (5 days) after unprotected
153
+ sex. Levonorgestrel 0.75 mg, two tablet regimen.
154
+ - source_sentence: who wrote the bell curve
155
+ sentences:
156
+ - First, you have to know a little about statistics. I assume that the grades are
157
+ drawn from a normal (bell-curve) distribution. These distributions have an average
158
+ (also called a mean) and a standard deviation (stdev), which measures how wide
159
+ the distribution spreads out.
160
+ - So if you want a bell curve chart, you first have to enter the right data. In
161
+ this tutorial, we select a range of numbers corresponding to a Mean average and
162
+ a Standard Deviation. After applying Excel's Normal Distribution function to those
163
+ numbers, Excel gives you a perfectly-formed bell curve.
164
+ - "With standardized IQ tests, IQ tests are designed so that their scores have a\
165
+ \ â\x80\x98bell curveâ\x80\x99 distribution in the general population with an\
166
+ \ average of 100. This curve has a peak in the middle where most people score\
167
+ \ and tapering ends where only a few people score. In statistics this is called\
168
+ \ a normal distribution."
169
+ - "Definition: The term bell curve is used to describe the mathematical concept\
170
+ \ called normal distribution, sometimes referred to as Gaussian distribution.\
171
+ \ â\x80\x98Bell curveâ\x80\x99 refers to the shape that is created when a line\
172
+ \ is plotted using the data points for an item that meets the criteria of â\x80\
173
+ \x98normal distributionâ\x80\x99.he important things to note about a normal distribution\
174
+ \ is the curve is concentrated in the center and decreases on either side. This\
175
+ \ is significant in that the data has less of a tendency to produce unusually\
176
+ \ extreme values, called outliers, as compared to other distributions."
177
+ - See normal distribution for the bell curve in statistics. The Bell Curve is a
178
+ controversial, best-selling 1994 book by Richard J. Herrnstein and Charles Murray
179
+ exploring the role of intelligence in American life. The authors became notorious
180
+ for the book's discussion of race and intelligence in Chapters 13 and 14.
181
+ - Noun. 1. Gaussian curve-a symmetrical curve representing the normal distribution.
182
+ bell-shaped curve, Gaussian shape, normal curve. statistics-a branch of applied
183
+ mathematics concerned with the collection and interpretation of quantitative data
184
+ and the use of probability theory to estimate population parameters.aussian curve-a
185
+ symmetrical curve representing the normal distribution. bell-shaped curve, Gaussian
186
+ shape, normal curve. statistics-a branch of applied mathematics concerned with
187
+ the collection and interpretation of quantitative data and the use of probability
188
+ theory to estimate population parameters.
189
+ - Chebyshev's Theorem. The Russian mathematician P. L. Chebyshev (1821- 1894) discovered
190
+ that the fraction of observations falling between two distinct values, whose differences
191
+ from the mean have the same absolute value, is related to the variance of the
192
+ population.
193
+ - A visual glossary of hat types for men, hats, mens hats, advertisement, ad, social
194
+ media ideas, infrographics, fashion, chef hat, derby hat, beret, cowboy hat. Fashion
195
+ in Infographics has a chart for every fashion thing you've ever wondered about.
196
+ So says Buzzfeed, and our followers agree.
197
+ - "Definition: The term bell curve is used to describe the mathematical concept\
198
+ \ called normal distribution, sometimes referred to as Gaussian distribution.\
199
+ \ â\x80\x98Bell curveâ\x80\x99 refers to the shape that is created when a line\
200
+ \ is plotted using the data points for an item that meets the criteria of â\x80\
201
+ \x98normal distributionâ\x80\x99."
202
+ - source_sentence: wht is tartaric acid
203
+ sentences:
204
+ - Tartaric Acid. Tartaric acid is a naturally occurring organic acid which appears
205
+ as a white crystalline solid at room temperature. Foods such as grapes, apricots,
206
+ avocados, apples and sunflower seeds have all been known to have high concentrations
207
+ of the acid.Alternatively, it has also been found in tamarinds which are a type
208
+ of tree indigenous to tropical Africa and other warms parts of the world.ses.
209
+ As mentioned above, Mexican cuisine relies heavily on the use of tartaric acid
210
+ which, when combined with baking soda, acts as a leavening agent. The acid also
211
+ plays a major role in wine-making where it is used during the fermentation process
212
+ for acidity adjustments to make for a more palate pleasing taste.
213
+ - Send Enquiry. Tartaric Acid. Tartaric acid is a white crystalline diprotic organic
214
+ acid. It occurs naturally in many plants, particularly grapes, bananas, and tamarinds,
215
+ and is one of the main acids found in wine.It is added to other foods to give
216
+ a sour taste, and is used as anantioxidant. Salts of tartaric acid are known as
217
+ tartrates.end Enquiry. Tartaric Acid. Tartaric acid is a white crystalline diprotic
218
+ organic acid. It occurs naturally in many plants, particularly grapes, bananas,
219
+ and tamarinds, and is one of the main acids found in wine.
220
+ - Acids are used as additives to drinks and foods, as they alter their taste and
221
+ serve as preservatives. Phosphoric acid, for example, is a component of cola drinks.
222
+ Acetic acid is used in day-to-day life as vinegar. Carbonic acid is an important
223
+ part of some cola drinks and soda.Citric acid is used as a preservative in sauces
224
+ and pickles. Tartaric acid is an important component of some commonly used foods
225
+ like unripened mangoes and tamarind.cids are used as additives to drinks and foods,
226
+ as they alter their taste and serve as preservatives. Phosphoric acid, for example,
227
+ is a component of cola drinks. Acetic acid is used in day-to-day life as vinegar.
228
+ Carbonic acid is an important part of some cola drinks and soda.
229
+ - Sour salt is actually citric acid, a white crystalline compound with an acidic,
230
+ tart taste; it is often used to furnish the sour taste element in sweet/sour dishes
231
+ such as cabbage soup.
232
+ - Cream of tartar, which is actually a byproduct of the winemaking process, is an
233
+ acidic powder that is typically used in baking to stabilize eggs and creams, as
234
+ well as adding volume and thickness to the final product.
235
+ - Fumaric acid or trans-butenedioic acid is the chemical compound with the formula
236
+ HO 2 CCH=CHCO 2 H. This white crystalline compound is one of two isomeric unsaturated
237
+ dicarboxylic acids, the other being maleic acid.umaric acid has been used a food
238
+ acidulant since 1946. It is approved for use as a food additive in the EU, USA
239
+ and Australia and New Zealand. As a food additive, it is used as an acidity regulator
240
+ and can be denoted by the E number E297.
241
+ - July 1, 2008 in Baking, How-To's and Tips, Ingredients 72 Comments. Cream of tartar,
242
+ more technically known as potassium hydrogen tartrate, is a fine white powder
243
+ with many culinary applications. It is a byproduct of the winemaking process as
244
+ the powder forms inside wine barrels during fermentation.
245
+ - Tartaric acid is a white crystalline organic acid that occurs naturally in many
246
+ plants, most notably in grapes.he acid itself is added to foods as an antioxidant
247
+ and to impart its distinctive sour taste. Tartaric is an alpha-hydroxy-carboxylic
248
+ acid, is diprotic and aldaric in acid characteristics, and is a dihydroxyl derivative
249
+ of succinic acid.
250
+ - Citric acid is found naturally in several fruits and berries, and is commonly
251
+ added to many foods and beverages as a preservative or for flavor. It has a tart
252
+ taste, and is also known as lemon salt or sour salt. Many of our customers use
253
+ our citric acid to clean dishwashers and dishes, or to make fizzy bath bombs (fun!).
254
+ Citric acid is completely natural, produced by cells during the Krebs cycle.
255
+ datasets:
256
+ - tomaarsen/msmarco-Qwen3-Reranker-0.6B
257
+ pipeline_tag: sentence-similarity
258
+ library_name: sentence-transformers
259
+ metrics:
260
+ - cosine_accuracy@1
261
+ - cosine_accuracy@3
262
+ - cosine_accuracy@5
263
+ - cosine_accuracy@10
264
+ - cosine_precision@1
265
+ - cosine_precision@3
266
+ - cosine_precision@5
267
+ - cosine_precision@10
268
+ - cosine_recall@1
269
+ - cosine_recall@3
270
+ - cosine_recall@5
271
+ - cosine_recall@10
272
+ - cosine_ndcg@10
273
+ - cosine_mrr@10
274
+ - cosine_map@100
275
+ co2_eq_emissions:
276
+ emissions: 25.734910258179127
277
+ energy_consumed: 0.06620730085818732
278
+ source: codecarbon
279
+ training_type: fine-tuning
280
+ on_cloud: false
281
+ cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
282
+ ram_total_size: 31.777088165283203
283
+ hours_used: 0.199
284
+ hardware_used: 1 x NVIDIA GeForce RTX 3090
285
+ model-index:
286
+ - name: mpnet-base finetuned on MSMARCO via distillation
287
+ results:
288
+ - task:
289
+ type: information-retrieval
290
+ name: Information Retrieval
291
+ dataset:
292
+ name: msmarco eval 1kq 1kd
293
+ type: msmarco-eval-1kq-1kd
294
+ metrics:
295
+ - type: cosine_accuracy@1
296
+ value: 0.875
297
+ name: Cosine Accuracy@1
298
+ - type: cosine_accuracy@3
299
+ value: 0.931
300
+ name: Cosine Accuracy@3
301
+ - type: cosine_accuracy@5
302
+ value: 0.94
303
+ name: Cosine Accuracy@5
304
+ - type: cosine_accuracy@10
305
+ value: 0.95
306
+ name: Cosine Accuracy@10
307
+ - type: cosine_precision@1
308
+ value: 0.875
309
+ name: Cosine Precision@1
310
+ - type: cosine_precision@3
311
+ value: 0.31033333333333324
312
+ name: Cosine Precision@3
313
+ - type: cosine_precision@5
314
+ value: 0.188
315
+ name: Cosine Precision@5
316
+ - type: cosine_precision@10
317
+ value: 0.09500000000000001
318
+ name: Cosine Precision@10
319
+ - type: cosine_recall@1
320
+ value: 0.875
321
+ name: Cosine Recall@1
322
+ - type: cosine_recall@3
323
+ value: 0.931
324
+ name: Cosine Recall@3
325
+ - type: cosine_recall@5
326
+ value: 0.94
327
+ name: Cosine Recall@5
328
+ - type: cosine_recall@10
329
+ value: 0.95
330
+ name: Cosine Recall@10
331
+ - type: cosine_ndcg@10
332
+ value: 0.9160765514570743
333
+ name: Cosine Ndcg@10
334
+ - type: cosine_mrr@10
335
+ value: 0.904880158730159
336
+ name: Cosine Mrr@10
337
+ - type: cosine_map@100
338
+ value: 0.9062235162428945
339
+ name: Cosine Map@100
340
+ ---
341
+
342
+ # mpnet-base finetuned on MSMARCO via distillation
343
+
344
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [msmarco-qwen3-reranker-0.6_b](https://huggingface.co/datasets/tomaarsen/msmarco-Qwen3-Reranker-0.6B) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
345
+
346
+ ## Model Details
347
+
348
+ ### Model Description
349
+ - **Model Type:** Sentence Transformer
350
+ - **Base model:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
351
+ - **Maximum Sequence Length:** 512 tokens
352
+ - **Output Dimensionality:** 768 dimensions
353
+ - **Similarity Function:** Cosine Similarity
354
+ - **Training Dataset:**
355
+ - [msmarco-qwen3-reranker-0.6_b](https://huggingface.co/datasets/tomaarsen/msmarco-Qwen3-Reranker-0.6B)
356
+ - **Language:** en
357
+ - **License:** apache-2.0
358
+
359
+ ### Model Sources
360
+
361
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
362
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
363
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
364
+
365
+ ### Full Model Architecture
366
+
367
+ ```
368
+ SentenceTransformer(
369
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'MPNetModel'})
370
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
371
+ )
372
+ ```
373
+
374
+ ## Usage
375
+
376
+ ### Direct Usage (Sentence Transformers)
377
+
378
+ First install the Sentence Transformers library:
379
+
380
+ ```bash
381
+ pip install -U sentence-transformers
382
+ ```
383
+
384
+ Then you can load this model and run inference.
385
+ ```python
386
+ from sentence_transformers import SentenceTransformer
387
+
388
+ # Download from the 🤗 Hub
389
+ model = SentenceTransformer("tomaarsen/mpnet-base-msmarco-margin-mse")
390
+ # Run inference
391
+ queries = [
392
+ "wht is tartaric acid",
393
+ ]
394
+ documents = [
395
+ 'Tartaric Acid. Tartaric acid is a naturally occurring organic acid which appears as a white crystalline solid at room temperature. Foods such as grapes, apricots, avocados, apples and sunflower seeds have all been known to have high concentrations of the acid.Alternatively, it has also been found in tamarinds which are a type of tree indigenous to tropical Africa and other warms parts of the world.ses. As mentioned above, Mexican cuisine relies heavily on the use of tartaric acid which, when combined with baking soda, acts as a leavening agent. The acid also plays a major role in wine-making where it is used during the fermentation process for acidity adjustments to make for a more palate pleasing taste.',
396
+ 'Tartaric acid is a white crystalline organic acid that occurs naturally in many plants, most notably in grapes.he acid itself is added to foods as an antioxidant and to impart its distinctive sour taste. Tartaric is an alpha-hydroxy-carboxylic acid, is diprotic and aldaric in acid characteristics, and is a dihydroxyl derivative of succinic acid.',
397
+ 'Send Enquiry. Tartaric Acid. Tartaric acid is a white crystalline diprotic organic acid. It occurs naturally in many plants, particularly grapes, bananas, and tamarinds, and is one of the main acids found in wine.It is added to other foods to give a sour taste, and is used as anantioxidant. Salts of tartaric acid are known as tartrates.end Enquiry. Tartaric Acid. Tartaric acid is a white crystalline diprotic organic acid. It occurs naturally in many plants, particularly grapes, bananas, and tamarinds, and is one of the main acids found in wine.',
398
+ ]
399
+ query_embeddings = model.encode_query(queries)
400
+ document_embeddings = model.encode_document(documents)
401
+ print(query_embeddings.shape, document_embeddings.shape)
402
+ # [1, 768] [3, 768]
403
+
404
+ # Get the similarity scores for the embeddings
405
+ similarities = model.similarity(query_embeddings, document_embeddings)
406
+ print(similarities)
407
+ # tensor([[0.7287, 0.7477, 0.7356]])
408
+ ```
409
+
410
+ <!--
411
+ ### Direct Usage (Transformers)
412
+
413
+ <details><summary>Click to see the direct usage in Transformers</summary>
414
+
415
+ </details>
416
+ -->
417
+
418
+ <!--
419
+ ### Downstream Usage (Sentence Transformers)
420
+
421
+ You can finetune this model on your own dataset.
422
+
423
+ <details><summary>Click to expand</summary>
424
+
425
+ </details>
426
+ -->
427
+
428
+ <!--
429
+ ### Out-of-Scope Use
430
+
431
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
432
+ -->
433
+
434
+ ## Evaluation
435
+
436
+ ### Metrics
437
+
438
+ #### Information Retrieval
439
+
440
+ * Dataset: `msmarco-eval-1kq-1kd`
441
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
442
+
443
+ | Metric | Value |
444
+ |:--------------------|:-----------|
445
+ | cosine_accuracy@1 | 0.875 |
446
+ | cosine_accuracy@3 | 0.931 |
447
+ | cosine_accuracy@5 | 0.94 |
448
+ | cosine_accuracy@10 | 0.95 |
449
+ | cosine_precision@1 | 0.875 |
450
+ | cosine_precision@3 | 0.3103 |
451
+ | cosine_precision@5 | 0.188 |
452
+ | cosine_precision@10 | 0.095 |
453
+ | cosine_recall@1 | 0.875 |
454
+ | cosine_recall@3 | 0.931 |
455
+ | cosine_recall@5 | 0.94 |
456
+ | cosine_recall@10 | 0.95 |
457
+ | **cosine_ndcg@10** | **0.9161** |
458
+ | cosine_mrr@10 | 0.9049 |
459
+ | cosine_map@100 | 0.9062 |
460
+
461
+ <!--
462
+ ## Bias, Risks and Limitations
463
+
464
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
465
+ -->
466
+
467
+ <!--
468
+ ### Recommendations
469
+
470
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
471
+ -->
472
+
473
+ ## Training Details
474
+
475
+ ### Training Dataset
476
+
477
+ #### msmarco-qwen3-reranker-0.6_b
478
+
479
+ * Dataset: [msmarco-qwen3-reranker-0.6_b](https://huggingface.co/datasets/tomaarsen/msmarco-Qwen3-Reranker-0.6B) at [20c25c8](https://huggingface.co/datasets/tomaarsen/msmarco-Qwen3-Reranker-0.6B/tree/20c25c858f80ba96bdb58f1558746e077001303a)
480
+ * Size: 10,000 training samples
481
+ * Columns: <code>query</code>, <code>positive</code>, <code>negative_1</code>, <code>negative_2</code>, <code>negative_3</code>, <code>negative_4</code>, <code>negative_5</code>, <code>negative_6</code>, <code>negative_7</code>, <code>negative_8</code>, and <code>score</code>
482
+ * Approximate statistics based on the first 1000 samples:
483
+ | | query | positive | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | score |
484
+ |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------|
485
+ | type | string | string | string | string | string | string | string | string | string | string | list |
486
+ | details | <ul><li>min: 4 tokens</li><li>mean: 9.18 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 80.35 tokens</li><li>max: 298 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 68.3 tokens</li><li>max: 197 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 70.27 tokens</li><li>max: 209 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 70.16 tokens</li><li>max: 241 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 71.17 tokens</li><li>max: 211 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 71.8 tokens</li><li>max: 190 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 72.04 tokens</li><li>max: 194 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 73.0 tokens</li><li>max: 203 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 71.02 tokens</li><li>max: 206 tokens</li></ul> | <ul><li>size: 9 elements</li></ul> |
487
+ * Samples:
488
+ | query | positive | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | score |
489
+ |:-------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|
490
+ | <code>what is clomiphene</code> | <code>Uses of This Medicine. Clomiphene is used as a fertility medicine in some women who are unable to become pregnant. Clomiphene probably works by changing the hormone balance of the body. In women, this causes ovulation to occur and prepares the body for pregnancy.ses of This Medicine. Clomiphene is used as a fertility medicine in some women who are unable to become pregnant. Clomiphene probably works by changing the hormone balance of the body. In women, this causes ovulation to occur and prepares the body for pregnancy.</code> | <code>Clomiphene citrate, a synthetic hormone commonly used to induce or regulate ovulation, is the most often prescribed fertility pill. Brand names for clomiphene citrate include Clomid and Serophene. Clomiphene works indirectly to stimulate ovulation.</code> | <code>Occasionally, clomiphene can stimulate the ovaries too much, causing multiple eggs to be released, which can result in multiple births, such as twins or triplets (see Clomid and Twins) . Clomiphene is one of the least expensive and easiest-to-use fertility drugs. However, it will not work for all types of infertility. Your healthcare provider needs to try to find your cause of infertility before you try clomiphene.</code> | <code>Clomiphene Citrate offers two benefits to the performance enhancing athlete with one being primary. Most commonly, this SERM is used for post cycle recovery purposes; specifically to stimulate natural testosterone production that has been suppressed due to the use of anabolic steroids.</code> | <code>PCOS and ovulation problems and Clomid treatment. Clomid (clomiphene citrate or Serophene) is an oral medication that is commonly used for the treatment of infertility. It is often given to try to induce ovulation in women that do not develop and release an egg (ovulate) on their own.</code> | <code>Indication: Clomid (clomiphene citrate) is often the first choice for treating infertility, because it's effective and been used for more than 40 years.</code> | <code>Clomid Description. 1 Clomid (clomiphene citrate tablets USP) is an orally administered, nonsteroidal, ovulatory stimulant designated chemically as 2-[p-(2-chloro-1,2-diphenylvinyl)phenoxy] triethylamine citrate (1:1). It has the molecular formula of C26H28ClNO • C6H8O7 and a molecular weight of 598.09.</code> | <code>PCOS and ovulation problems and Clomid treatment. Clomid (clomiphene citrate or Serophene) is an oral medication that is commonly used for the treatment of infertility. 1 It is often given to try to induce ovulation in women that do not develop and release an egg (ovulate) on their own. Clomid is started early in the menstrual cycle and is taken for five days either from cycle days 3 through 7, or from day 5 through 9. 2 Clomid is usually started at a dose of one tablet (50mg) daily-taken any time of day.</code> | <code>Clomid is taken as a pill. This is unlike the stronger fertility drugs, which require injection. Clomid is also very effective, stimulating ovulation 80 percent of the time. Clomid may also be marketed under the name Serophene, or you may see it sold under its generic name, clomiphene citrate. Note: Clomid can also be used as a treatment for male infertility. This article focuses on Clomid treatment in women.</code> | <code>[4.75390625, 6.9375, 3.92578125, 1.0400390625, 5.61328125, ...]</code> |
491
+ | <code>typical accountant cost for it contractor</code> | <code>In the current market, we’ve seen rates as low as £50 +VAT, and as high as £180 +VAT for dedicated contractor accountants. Interestingly, the average cost of contractor accounting has not risen in line with inflation over the past decade.</code> | <code>So, how much does a contractor cost, anywhere from 5% to 25% of the total project cost, with the average ranging 10-15%.ypically the contractor' s crew will be general carpentry trades people, some who may have more specialized skills. Exactly how a general contractor charges for a project depends on the type of contract you agree to. There are three common types of cost contracts, fixed price, time & materials and cost plus a fee.</code> | <code>1 Accountants charge $150-$400 or more an hour, depending on the type of work, the size of the firm and its location. 2 You'll pay lower rates for routine work done by a less-experienced associate or lesser-trained employee, such as $30-$50 for bookkeeping services. 3 An accountant's total fee depends on the project. For a simple start-up, expect a minimum of 0.5-1.5 hours of consultation ($75-$600) to go over your business structure and basic tax issues.</code> | <code>So, how much does a contractor cost, anywhere from 5% to 25% of the total project cost, with the average ranging 10-15%.xactly how a general contractor charges for a project depends on the type of contract you agree to. There are three common types of cost contracts, fixed price, time & materials and cost plus a fee. Each contract type has pros and cons for both the consumer and for the contractor.</code> | <code>1 Accountants charge $150-$400 or more an hour, depending on the type of work, the size of the firm and its location. 2 You'll pay lower rates for routine work done by a less-experienced associate or lesser-trained employee, such as $30-$50 for bookkeeping services. 3 An accountant's total fee depends on the project.</code> | <code>average data entry keystrokes per hour salaries the average salary for data entry keystrokes per hour jobs is $ 20000</code> | <code>Accounting services are typically $250 to $400 per month, or $350 to $500 per quarter. Sales tax and bank recs included. We do all the processing, filing and tax deposits. 5 employees, bi-weekly payroll, direct deposit, $135 per month.</code> | <code>The less that is outsourced, the cheaper it will be for you. A bookkeeper should be paid between $15 and $18 per hour. An accountant with a undergraduate degree (4-years) should be paid somewhere around $20/hour but that still depends on what you're having them do. An accountant with a graduate degree (masters) should be paid between $25 and $30 per hour.</code> | <code>Pay by Experience Level for Intelligence Analyst. Median of all compensation (including tips, bonus, and overtime) by years of experience. Intelligence Analysts with a lot of experience tend to enjoy higher earnings.</code> | <code>[7.44921875, 3.271484375, 5.859375, 3.234375, 5.421875, ...]</code> |
492
+ | <code>what is mch on a blood test</code> | <code>What High Levels Mean. MCH levels in blood tests are considered high if they are 35 or higher. A normal hemoglobin level is considered to be in the range between 26 and 33 picograms per red blood cell. High MCH levels can indicate macrocytic anemia, which can be caused by insufficient vitamin B12.acrocytic RBCs are large so tend to have a higher MCH, while microcytic red cells would have a lower value.”. MCH is one of three red blood cell indices (MCHC and MCV are the other two). The measurements are done by machine and can help with diagnosis of medical problems.</code> | <code>MCH stands for mean corpuscular hemoglobin. It estimates the average amount of hemoglobin in each red blood cell, measured in picograms (a trillionth of a gram). Automated cell counters calculate the MCH, which is reported as part of a complete blood count (CBC) test. MCH may be low in iron-deficiency anemia, and may be high in anemia due to vitamin B12 or folate deficiency. Other forms of anemia can also cause MCH to be abnormal. Doctors only use the MCH as supporting information, not to make a diagnosis.</code> | <code>A. MCH stands for mean corpuscular hemoglobin. It estimates the average amount of hemoglobin in each red blood cell, measured in picograms (a trillionth of a gram). Automated cell counters calculate the MCH, which is reported as part of a complete blood count (CBC) test. MCH may be low in iron-deficiency anemia, and may be high in anemia due to vitamin B12 or folate deficiency. Other forms of anemia can also cause MCH to be abnormal.</code> | <code>The test used to determine the quantity of hemoglobin in the blood is known as the MCH blood test. The full form of MCH is Mean Corpuscular Hemoglobin. This test is therefore used to determine the average amount of hemoglobin per red blood cell in the body. The results of the MCH blood test are therefore reported in picograms, a tiny measure of weight.</code> | <code>MCH blood test high indicates that there is a poor supply of oxygen to the blood where as MCH blood test low mean that hemoglobin is too little in the cells indicating a lack of iron. It is important that iron is maintained at a certain level as too much or too little iron can be dangerous to your body.</code> | <code>slide 1 of 7. What Is MCH? MCH is the initialism for Mean Corpuscular Hemoglobin. Taken from Latin, the term refers to the average amount of hemoglobin found in red blood cells. A CBC (complete blood count) blood test can be used to monitor MCH levels in the blood. Lab Tests Online explains that the MCH aspect of a CBC test “is a measurement of the average amount of oxygen-carrying hemoglobin inside a red blood cell. Macrocytic RBCs are large so tend to have a higher MCH, while microcytic red cells would have a lower value..</code> | <code>The test used to determine the quantity of hemoglobin in the blood is known as the MCH blood test. The full form of MCH is Mean Corpuscular Hemoglobin. This test is therefore used to determine the average amount of hemoglobin per red blood cell in the body. The results of the MCH blood test are therefore reported in picograms, a tiny measure of weight. The normal range of the MCH blood test is between 26 and 33 pg per cell.</code> | <code>A MCHC test is a test that is carried out to test a person for anemia. The MCHC in a MCHC test stands for Mean Corpuscular Hemoglobin Concentration. MCHC is the calculation of the average hemoglobin inside a red blood cell. A MCHC test can be performed along with a MCV test (Mean Corpuscular Volume).Both levels are used to test people for anemia.The MCHC test is also known as the MCH blood test which tests the levels of hemoglobin in the blood. The MCHC test can be ordered as part of a complete blood count (CBC) test.CHC is measured in grams per deciliter. Normal readings for MCHC are 31 grams per deciliter to 35 grams per deciliter. A MCHC blood test may be ordered when a person is showing signs of fatigue or weakness, when there is an infection, is bleeding or bruising easily or when there is an inflammation.</code> | <code>The test looks at the average amount of hemoglobin per red cell. So MCHC = the amount of hemoglobin present in each red blood cell. A MCHC blood test could be ordered for someone who has signs of fatigue or weakness, when there is an infection, is bleeding or bruising easily or when there is noticeable inflammation.</code> | <code>[6.44921875, 7.05078125, 7.2109375, 8.40625, 6.53515625, ...]</code> |
493
+ * Loss: [<code>MarginMSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#marginmseloss)
494
+
495
+ ### Evaluation Dataset
496
+
497
+ #### msmarco-qwen3-reranker-0.6_b
498
+
499
+ * Dataset: [msmarco-qwen3-reranker-0.6_b](https://huggingface.co/datasets/tomaarsen/msmarco-Qwen3-Reranker-0.6B) at [20c25c8](https://huggingface.co/datasets/tomaarsen/msmarco-Qwen3-Reranker-0.6B/tree/20c25c858f80ba96bdb58f1558746e077001303a)
500
+ * Size: 1,000 evaluation samples
501
+ * Columns: <code>query</code>, <code>positive</code>, <code>negative_1</code>, <code>negative_2</code>, <code>negative_3</code>, <code>negative_4</code>, <code>negative_5</code>, <code>negative_6</code>, <code>negative_7</code>, <code>negative_8</code>, and <code>score</code>
502
+ * Approximate statistics based on the first 1000 samples:
503
+ | | query | positive | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | score |
504
+ |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------|
505
+ | type | string | string | string | string | string | string | string | string | string | string | list |
506
+ | details | <ul><li>min: 4 tokens</li><li>mean: 9.05 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 81.61 tokens</li><li>max: 244 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 69.2 tokens</li><li>max: 231 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 68.76 tokens</li><li>max: 198 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 70.99 tokens</li><li>max: 225 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 70.7 tokens</li><li>max: 236 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 72.57 tokens</li><li>max: 315 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 68.95 tokens</li><li>max: 203 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 71.68 tokens</li><li>max: 220 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 70.18 tokens</li><li>max: 213 tokens</li></ul> | <ul><li>size: 9 elements</li></ul> |
507
+ * Samples:
508
+ | query | positive | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | score |
509
+ |:-------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|
510
+ | <code>how many people employed by shell</code> | <code>Shell worldwide. Royal Dutch Shell was formed in 1907, although our history dates back to the early 19th century, to a small shop in London where the Samuel family sold sea shells. Today, Shell is one of the world’s major energy companies, employing an average of 93,000 people and operating in more than 70 countries. Our headquarters are in The Hague, the Netherlands, and our Chief Executive Officer is Ben van Beurden.</code> | <code>Show sources information. This statistic shows the number of employees at SeaWorld Entertainment, Inc. in the United States, by type. As of December 2016, SeaWorld employed 5,000 full-time employees and counted approximately 13,000 seasonal employees during their peak operating season.</code> | <code>Jobs, companies, people, and articles for LinkedIn’s Payroll Specialist - Addus Homecare, Inc. members. Insights about Payroll Specialist - Addus Homecare, Inc. members on LinkedIn. Median salary $31,300.</code> | <code>As of July 2014, there are 139 million people employed in the United States. This number is up by 209,000 employees from June and by 1.47 million from the beginning of 2014.</code> | <code>average data entry keystrokes per hour salaries the average salary for data entry keystrokes per hour jobs is $ 20000</code> | <code>Research and review Plano Synergy jobs. Learn more about a career with Plano Synergy including all recent jobs, hiring trends, salaries, work environment and more. Find Jobs Company Reviews Find Salaries Find Resumes Employers / Post Job Upload your resume Sign in</code> | <code>From millions of real job salary data. 13 Customer Support Specialist salary data. Average Customer Support Specialist salary is $59,032 Detailed Customer Support Specialist starting salary, median salary, pay scale, bonus data report Register & Know how much $ you can earn \| Sign In</code> | <code>From millions of real job salary data. 1 Ceo Ally salary data. Average Ceo Ally salary is $55,000 Detailed Ceo Ally starting salary, median salary, pay scale, bonus data report</code> | <code>HelpSystems benefits and perks, including insurance benefits, retirement benefits, and vacation policy. Reported anonymously by HelpSystems employees. Glassdoor uses cookies to improve your site experience.</code> | <code>[6.265625, -1.3671875, -6.91796875, 1.111328125, -7.96875, ...]</code> |
511
+ | <code>what is a lcsw</code> | <code>LCSW is an acronym for licensed clinical social worker, and people with this title are skilled professionals who meet certain requirements and work in a variety of fields. The term social worker is not always synonymous with licensed clinical social worker.</code> | <code>LISW means the person is a Licensed Independent Social Worker. LCSW means the person is a Licensed Clinical Social Worker. Source(s): Introduction to Social Work 101 at University of Nevada, Las Vega (UNLV) Dorothy K. · 1 decade ago.</code> | <code>An LCSW is a licensed clinical social worker. A LMHC is the newest addition to the field of mental health. They are highly similar and can do most of the same things with few exceptions. One thing to keep in mind is that because the LMHC lincense is so new, there are fewer in number in the field.n LCSW is a licensed clinical social worker. A LMHC is the newest addition to the field of mental health. They are highly similar and can do most of the same things with few exceptions. One thing to keep in mind is that because the LMHC lincense is so new, there are fewer in number in the field.</code> | <code>The Licensed Clinical Social Worker or LCSW, is a sub-sector within the field of Social Work. They work with clients in order to help them deal with issues involving their mental and emotional health. This could be related to substance abuse, past trauma or mental illness.</code> | <code>Licensed Clinical Social Worker \| LCSW. The Licensed Clinical Social Worker or LCSW, is a sub-sector within the field of Social Work. LCSW's work with clients in order to help deal with issues involving mental and emotional health. There are a wide variety of specializations the Licensed Clinical Social Worker can focus on.</code> | <code>The LMSW exam is a computer-based test containing 170 multiple-choice questions designed to measure minimum competencies in four categories of social work practice: Human development, diversity, and behavior in the environment. Assessment and intervention planning.</code> | <code>The Licensed Clinical Social Worker, also known as the LCSW, is a branch of social work that specializes in mental health therapy in a counseling format. Becoming an LCSW requires a significant degree of training, including having earned a Master of Social Work (MSW) degree from a Council on Social Work Education (CSWE) accredited program.</code> | <code>a. The examination requirements for licensure as an LCSW include passing the Clinical Examination of the ASWB or the Clinical Social Workers Examination of the State of California. Scope of practice-Limitations. a.To the extent they are prepared through education and training, an LCSW can engage in all acts and practices defined as the practice of clinical social work. Certified Social Work (CSW): CSW means a licensed certified social worker. A CSW must have a master s degree.</code> | <code>The LTCM Client is a way for companies to stay in touch with you, their customers, in a way that is unobtrusive and completely under the users' control. It's an application that runs quietly on the computer. Users can and should customize the client to match their desired preferences.</code> | <code>[7.34375, 6.046875, 7.09765625, 6.46484375, 7.28515625, ...]</code> |
512
+ | <code>does oolong tea have much caffeine?</code> | <code>At a given weight, tea contains more caffeine than coffee, but this doesn’t mean that a usual portion of tea contains more caffeine than coffee because tea is usually brewed in a weak way. Some kinds of tea, such as oolong and black tea, contain higher level of caffeine than most other teas. Among six basic teas (green, black, yellow, white, oolong, dark), green tea contains less caffeine than black tea and white tea contains less than green tea. But many studies found that the caffeine content varies more among individual teas than it does among broad categories.</code> | <code>Actually, oolong tea has less caffeine than coffee and black tea. A cup of oolong tea only has about 1/3 of caffeine of a cup of coffee. According to a research conducted by HICKS M.B, the caffeine decreases whenever the tea leaves go through the process of brewing.</code> | <code>Oolong tea contains caffeine. Caffeine works by stimulating the central nervous system (CNS), heart, and muscles. Oolong tea also contains theophylline and theobromine, which are chemicals similar to caffeine. Too much oolong tea, more than five cups per day, can cause side effects because of the caffeine.</code> | <code>Oolong tea, made from more mature leaves, usually have less caffeine than green tea. On the flip side, mature leaves contain less theanine, a sweet, natural relaxant that makes a tea much less caffeinated than it actually is. That is the theory, anyway.</code> | <code>Oolong tea is a product made from the leaves, buds, and stems of the Camellia sinensis plant. This is the same plant that is also used to make black tea and green tea. The difference is in the processing.Oolong tea is partially fermented, black tea is fully fermented, and green tea is unfermented. Oolong tea is used to sharpen thinking skills and improve mental alertness. It is also used to prevent cancer, tooth decay, osteoporosis, and heart disease.owever, do not drink more than 2 cups a day of oolong tea. That amount of tea contains about 200 mg of caffeine. Too much caffeine during pregnancy might cause premature delivery, low birth weight, and harm to the baby.</code> | <code>A Department of Nutritional Services report provides the following ranges of caffeine content for a cup of tea made with loose leaves: 1 Black Tea: 23 - 110 mg. 2 Oolong Tea: 12 - 55 mg. Green Tea: 8 - 36 mg.</code> | <code>Oolong tea is a product made from the leaves, buds, and stems of the Camellia sinensis plant. This is the same plant that is also used to make black tea and green tea. The difference is in the processing. Oolong tea is partially fermented, black tea is fully fermented, and green tea is unfermented. Oolong tea is used to sharpen thinking skills and improve mental alertness. It is also used to prevent cancer, tooth decay, osteoporosis, and heart disease.</code> | <code>Health Effects of Tea – Caffeine. In dry form, a kilogram of black tea has twice the caffeine as a kilogram of coffee…. But one kilogram of black tea makes about 450 cups of tea and one kilogram of coffee makes about 100 cups of coffee, so…. There is less caffeine in a cup of tea than in a cup of coffee. Green teas have less caffeine than black teas, and white teas have even less caffeine than green teas. Oolong teas fall between black and green teas. Herbal tea, because it is not made from the same tea plant, is caffeine-free, naturally. Here is a graphical representation of their respective caffeine content.</code> | <code>The average 8-ounce serving of brewed black tea contains 14 to 70 mg of caffeine. This compares to 24 to 45 mg of caffeine found in green tea. An 8-ounce glass of instant iced tea prepared with water contains 11 to 47 mg of caffeine. Most ready-to-drink bottled teas contain 5 to 40 mg of caffeine. Just as with coffee, decaffeinated tea still contains 5 to 10 mg of caffeine per cup.</code> | <code>[7.60546875, 8.78125, 9.109375, 8.609375, 7.984375, ...]</code> |
513
+ * Loss: [<code>MarginMSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#marginmseloss)
514
+
515
+ ### Training Hyperparameters
516
+ #### Non-Default Hyperparameters
517
+
518
+ - `eval_strategy`: steps
519
+ - `per_device_train_batch_size`: 16
520
+ - `per_device_eval_batch_size`: 16
521
+ - `learning_rate`: 4e-05
522
+ - `num_train_epochs`: 1
523
+ - `warmup_ratio`: 0.1
524
+ - `bf16`: True
525
+
526
+ #### All Hyperparameters
527
+ <details><summary>Click to expand</summary>
528
+
529
+ - `overwrite_output_dir`: False
530
+ - `do_predict`: False
531
+ - `eval_strategy`: steps
532
+ - `prediction_loss_only`: True
533
+ - `per_device_train_batch_size`: 16
534
+ - `per_device_eval_batch_size`: 16
535
+ - `per_gpu_train_batch_size`: None
536
+ - `per_gpu_eval_batch_size`: None
537
+ - `gradient_accumulation_steps`: 1
538
+ - `eval_accumulation_steps`: None
539
+ - `torch_empty_cache_steps`: None
540
+ - `learning_rate`: 4e-05
541
+ - `weight_decay`: 0.0
542
+ - `adam_beta1`: 0.9
543
+ - `adam_beta2`: 0.999
544
+ - `adam_epsilon`: 1e-08
545
+ - `max_grad_norm`: 1.0
546
+ - `num_train_epochs`: 1
547
+ - `max_steps`: -1
548
+ - `lr_scheduler_type`: linear
549
+ - `lr_scheduler_kwargs`: {}
550
+ - `warmup_ratio`: 0.1
551
+ - `warmup_steps`: 0
552
+ - `log_level`: passive
553
+ - `log_level_replica`: warning
554
+ - `log_on_each_node`: True
555
+ - `logging_nan_inf_filter`: True
556
+ - `save_safetensors`: True
557
+ - `save_on_each_node`: False
558
+ - `save_only_model`: False
559
+ - `restore_callback_states_from_checkpoint`: False
560
+ - `no_cuda`: False
561
+ - `use_cpu`: False
562
+ - `use_mps_device`: False
563
+ - `seed`: 42
564
+ - `data_seed`: None
565
+ - `jit_mode_eval`: False
566
+ - `use_ipex`: False
567
+ - `bf16`: True
568
+ - `fp16`: False
569
+ - `fp16_opt_level`: O1
570
+ - `half_precision_backend`: auto
571
+ - `bf16_full_eval`: False
572
+ - `fp16_full_eval`: False
573
+ - `tf32`: None
574
+ - `local_rank`: 0
575
+ - `ddp_backend`: None
576
+ - `tpu_num_cores`: None
577
+ - `tpu_metrics_debug`: False
578
+ - `debug`: []
579
+ - `dataloader_drop_last`: False
580
+ - `dataloader_num_workers`: 0
581
+ - `dataloader_prefetch_factor`: None
582
+ - `past_index`: -1
583
+ - `disable_tqdm`: False
584
+ - `remove_unused_columns`: True
585
+ - `label_names`: None
586
+ - `load_best_model_at_end`: False
587
+ - `ignore_data_skip`: False
588
+ - `fsdp`: []
589
+ - `fsdp_min_num_params`: 0
590
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
591
+ - `tp_size`: 0
592
+ - `fsdp_transformer_layer_cls_to_wrap`: None
593
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
594
+ - `deepspeed`: None
595
+ - `label_smoothing_factor`: 0.0
596
+ - `optim`: adamw_torch
597
+ - `optim_args`: None
598
+ - `adafactor`: False
599
+ - `group_by_length`: False
600
+ - `length_column_name`: length
601
+ - `ddp_find_unused_parameters`: None
602
+ - `ddp_bucket_cap_mb`: None
603
+ - `ddp_broadcast_buffers`: False
604
+ - `dataloader_pin_memory`: True
605
+ - `dataloader_persistent_workers`: False
606
+ - `skip_memory_metrics`: True
607
+ - `use_legacy_prediction_loop`: False
608
+ - `push_to_hub`: False
609
+ - `resume_from_checkpoint`: None
610
+ - `hub_model_id`: None
611
+ - `hub_strategy`: every_save
612
+ - `hub_private_repo`: None
613
+ - `hub_always_push`: False
614
+ - `gradient_checkpointing`: False
615
+ - `gradient_checkpointing_kwargs`: None
616
+ - `include_inputs_for_metrics`: False
617
+ - `include_for_metrics`: []
618
+ - `eval_do_concat_batches`: True
619
+ - `fp16_backend`: auto
620
+ - `push_to_hub_model_id`: None
621
+ - `push_to_hub_organization`: None
622
+ - `mp_parameters`:
623
+ - `auto_find_batch_size`: False
624
+ - `full_determinism`: False
625
+ - `torchdynamo`: None
626
+ - `ray_scope`: last
627
+ - `ddp_timeout`: 1800
628
+ - `torch_compile`: False
629
+ - `torch_compile_backend`: None
630
+ - `torch_compile_mode`: None
631
+ - `include_tokens_per_second`: False
632
+ - `include_num_input_tokens_seen`: False
633
+ - `neftune_noise_alpha`: None
634
+ - `optim_target_modules`: None
635
+ - `batch_eval_metrics`: False
636
+ - `eval_on_start`: False
637
+ - `use_liger_kernel`: False
638
+ - `eval_use_gather_object`: False
639
+ - `average_tokens_across_devices`: False
640
+ - `prompts`: None
641
+ - `batch_sampler`: batch_sampler
642
+ - `multi_dataset_batch_sampler`: proportional
643
+ - `router_mapping`: {}
644
+ - `learning_rate_mapping`: {}
645
+
646
+ </details>
647
+
648
+ ### Training Logs
649
+ | Epoch | Step | Training Loss | Validation Loss | msmarco-eval-1kq-1kd_cosine_ndcg@10 |
650
+ |:-----:|:----:|:-------------:|:---------------:|:-----------------------------------:|
651
+ | 0.032 | 20 | 63.0051 | - | - |
652
+ | 0.064 | 40 | 50.9263 | - | - |
653
+ | 0.096 | 60 | 32.2675 | - | - |
654
+ | 0.128 | 80 | 29.6631 | - | - |
655
+ | 0.16 | 100 | 27.4689 | 23.1813 | 0.8913 |
656
+ | 0.192 | 120 | 23.3088 | - | - |
657
+ | 0.224 | 140 | 22.3476 | - | - |
658
+ | 0.256 | 160 | 20.5504 | - | - |
659
+ | 0.288 | 180 | 24.3006 | - | - |
660
+ | 0.32 | 200 | 22.5171 | 20.1510 | 0.8825 |
661
+ | 0.352 | 220 | 20.6006 | - | - |
662
+ | 0.384 | 240 | 22.0129 | - | - |
663
+ | 0.416 | 260 | 20.5189 | - | - |
664
+ | 0.448 | 280 | 21.0449 | - | - |
665
+ | 0.48 | 300 | 19.5734 | 17.6009 | 0.8993 |
666
+ | 0.512 | 320 | 20.5288 | - | - |
667
+ | 0.544 | 340 | 20.7801 | - | - |
668
+ | 0.576 | 360 | 20.6489 | - | - |
669
+ | 0.608 | 380 | 16.5201 | - | - |
670
+ | 0.64 | 400 | 20.2228 | 16.7519 | 0.9050 |
671
+ | 0.672 | 420 | 18.9227 | - | - |
672
+ | 0.704 | 440 | 18.0528 | - | - |
673
+ | 0.736 | 460 | 16.4477 | - | - |
674
+ | 0.768 | 480 | 16.6701 | - | - |
675
+ | 0.8 | 500 | 16.6258 | 17.4570 | 0.9119 |
676
+ | 0.832 | 520 | 15.7178 | - | - |
677
+ | 0.864 | 540 | 18.2512 | - | - |
678
+ | 0.896 | 560 | 17.2619 | - | - |
679
+ | 0.928 | 580 | 15.2639 | - | - |
680
+ | 0.96 | 600 | 18.8847 | 16.1425 | 0.9149 |
681
+ | 0.992 | 620 | 17.6204 | - | - |
682
+ | -1 | -1 | - | - | 0.9161 |
683
+
684
+
685
+ ### Environmental Impact
686
+ Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
687
+ - **Energy Consumed**: 0.066 kWh
688
+ - **Carbon Emitted**: 0.026 kg of CO2
689
+ - **Hours Used**: 0.199 hours
690
+
691
+ ### Training Hardware
692
+ - **On Cloud**: No
693
+ - **GPU Model**: 1 x NVIDIA GeForce RTX 3090
694
+ - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
695
+ - **RAM Size**: 31.78 GB
696
+
697
+ ### Framework Versions
698
+ - Python: 3.11.6
699
+ - Sentence Transformers: 5.1.0.dev0
700
+ - Transformers: 4.51.3
701
+ - PyTorch: 2.7.1+cu126
702
+ - Accelerate: 1.5.1
703
+ - Datasets: 2.21.0
704
+ - Tokenizers: 0.21.1
705
+
706
+ ## Citation
707
+
708
+ ### BibTeX
709
+
710
+ #### Sentence Transformers
711
+ ```bibtex
712
+ @inproceedings{reimers-2019-sentence-bert,
713
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
714
+ author = "Reimers, Nils and Gurevych, Iryna",
715
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
716
+ month = "11",
717
+ year = "2019",
718
+ publisher = "Association for Computational Linguistics",
719
+ url = "https://arxiv.org/abs/1908.10084",
720
+ }
721
+ ```
722
+
723
+ #### MarginMSELoss
724
+ ```bibtex
725
+ @misc{hofstätter2021improving,
726
+ title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
727
+ author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury},
728
+ year={2021},
729
+ eprint={2010.02666},
730
+ archivePrefix={arXiv},
731
+ primaryClass={cs.IR}
732
+ }
733
+ ```
734
+
735
+ <!--
736
+ ## Glossary
737
+
738
+ *Clearly define terms in order to be accessible across audiences.*
739
+ -->
740
+
741
+ <!--
742
+ ## Model Card Authors
743
+
744
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
745
+ -->
746
+
747
+ <!--
748
+ ## Model Card Contact
749
+
750
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
751
+ -->
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MPNetModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 514,
15
+ "model_type": "mpnet",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 1,
19
+ "relative_attention_num_buckets": 32,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.51.3",
22
+ "vocab_size": 30527
23
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "SentenceTransformer",
3
+ "__version__": {
4
+ "sentence_transformers": "5.1.0.dev0",
5
+ "transformers": "4.51.3",
6
+ "pytorch": "2.7.1+cu126"
7
+ },
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a790d0dac4fe8fd0c68cb932c1afb5dc84c45cc1882c3d4098d37d318116a7
3
+ size 437967672
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": false,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "extra_special_tokens": {},
58
+ "mask_token": "<mask>",
59
+ "max_length": 512,
60
+ "model_max_length": 512,
61
+ "pad_to_multiple_of": null,
62
+ "pad_token": "<pad>",
63
+ "pad_token_type_id": 0,
64
+ "padding_side": "right",
65
+ "sep_token": "</s>",
66
+ "stride": 0,
67
+ "strip_accents": null,
68
+ "tokenize_chinese_chars": true,
69
+ "tokenizer_class": "MPNetTokenizer",
70
+ "truncation_side": "right",
71
+ "truncation_strategy": "longest_first",
72
+ "unk_token": "[UNK]"
73
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff