File size: 144,634 Bytes
c54851c ee7fda4 c54851c 6132e97 17c1f43 ee7fda4 17c1f43 c54851c 17c1f43 c54851c 17c1f43 6132e97 c54851c 6132e97 c54851c 6132e97 c54851c 6132e97 c54851c 6132e97 ee7fda4 17c1f43 ee7fda4 17c1f43 c54851c 6132e97 c54851c 17c1f43 c54851c ee7fda4 17c1f43 ee7fda4 17c1f43 6132e97 ee7fda4 c54851c 17c1f43 c54851c 17c1f43 c54851c ee7fda4 6132e97 c54851c ee7fda4 6132e97 ee7fda4 c54851c ee7fda4 c54851c 6132e97 c54851c ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 6132e97 ee7fda4 6132e97 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 6132e97 ee7fda4 6132e97 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 6132e97 ee7fda4 6132e97 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 6132e97 ee7fda4 6132e97 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 6132e97 ee7fda4 6132e97 17c1f43 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 6132e97 ee7fda4 6132e97 ee7fda4 17c1f43 ee7fda4 6132e97 ee7fda4 6132e97 ee7fda4 17c1f43 ee7fda4 6132e97 ee7fda4 6132e97 ee7fda4 17c1f43 ee7fda4 c54851c ee7fda4 c54851c 17c1f43 ee7fda4 c54851c ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 d4f93e5 ee7fda4 17c1f43 ee7fda4 d4f93e5 ee7fda4 17c1f43 ee7fda4 d4f93e5 ee7fda4 17c1f43 ee7fda4 17c1f43 ee7fda4 c54851c 17c1f43 c54851c ee7fda4 c54851c ee7fda4 c54851c ee7fda4 17c1f43 6132e97 c54851c 17c1f43 c54851c 17c1f43 c54851c db3c618 c54851c 17c1f43 c54851c 17c1f43 c54851c 17c1f43 c54851c ee7fda4 c54851c 17c1f43 c54851c 17c1f43 c54851c 17c1f43 c54851c 17c1f43 c54851c 17c1f43 c54851c 17c1f43 6132e97 c54851c 17c1f43 c54851c 17c1f43 c54851c db3c618 c54851c 17c1f43 c54851c 17c1f43 c54851c ee7fda4 17c1f43 c54851c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 |
---
language:
- en
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:7376192
- loss:AnglELoss
- loss:CoSENTLoss
- loss:CachedMultipleNegativesRankingLoss
base_model: jhu-clsp/ettin-encoder-17m
widget:
- source_sentence: what is paediatric clinical psychology
sentences:
- Pediatric neuropsychology (paediatric in the UK) is a sub-speciality within the
field of clinical neuropsychology that studies the relationship between brain
health and behaviour in children.any pediatric neuropsychologists are involved
in teaching, research, supervision, and training of undergraduate and graduate
students in the field. In the United States undergraduate and graduate psychology
programs generally do not offer a track in pediatric neuropsychology, per se.
- "â\x80\x9CRealâ\x80\x9D hummus, should contain about 175 calories, out of which\
\ 70-80 calories are contributed by fat. The average Israeli eats 8-10 kilograms\
\ (18-22 pounds) of hummus every year, so weâ\x80\x99re talking about extra 15,000\
\ calories which can make him gain about 2.5kg of body weight each year. So you\
\ can see how excessive consumption of the packaged product might be fattening\
\ over the years. The common serving size of hummus (real hummus, that is), which\
\ is around one cup (220-240g) may contain 400-450 calories. And every pita (â\x80\
\x9Cpita breadâ\x80\x9D) contains another 270, so itâ\x80\x99s not really â\x80\
\x9Cdietaryâ\x80\x9D."
- "Pediatrics (also spelled paediatrics or pædiatrics) is the branch of medicine\
\ that involves the medical care of infants, children, and adolescents. The American\
\ Academy of Pediatrics recommends people be under pediatric care up to the age\
\ of 21.[1] A medical practitioner who specializes in this area is known as a\
\ pediatrician, or paediatrician. The word pediatrics and its cognates mean healer\
\ of children; they derive from two Greek words: Ï\x80αá¿\x96Ï\x82 (pais child)\
\ and ἰαÏ\x84Ï\x81Ï\x8CÏ\x82 (iatros doctor, healer)."
- source_sentence: These TBMs used were then buried to provide an electrical mass
.
sentences:
- As a result of this success , other multinational companies such as Unilever ,
Microsoft , Digital Equipment , Schlumberger or Lazard have approached the services
of Leclercq 's company .
- These buried TBMs were then used to provide an electrical earth .
- Huge fields along the zone were discovered in 1920 at Huntington Beach Oil Field
and at Long Beach Oil Field in 1921 .
- source_sentence: Eric Gagne earned his 17th save in as many opportunities as he
struck out three in the ninth and allowed only an infield single by Greg Norton.
sentences:
- Closer Eric Gagne earned his 17th save in as many opportunities as he struck out
three of the four batters he faced in the ninth.
- Syrian soldiers killed in bomb attack
- Two puppies play with a red chew toy in a field.
- source_sentence: I think I want to learn French.
sentences:
- GOOD
- In my experience, I have observed them not achieve their goals very quickly but
I have also witnessed them succeed.
- my way of thinking I want to learn French
- source_sentence: who said better to reign in hell than serve in heaven
sentences:
- House of Cards (season 6) The sixth and final season of the American political
drama web television series House of Cards was confirmed by Netflix on December
4, 2017, and is scheduled to be released in late 2018.[1] Unlike previous seasons
that consisted of thirteen episodes each, the sixth season will consist of only
eight. The season will not include former lead actor Kevin Spacey, who was fired
from the show due to sexual misconduct allegations.
- 'Maggie Elizabeth Jones Maggie Elizabeth Jones (born October 10, 2003) is an American
child actress, best known for her roles in We Bought a Zoo, the Fox sitcom Ben
and Kate,[1] and as Lea Clark in American Girl: Lea to the Rescue. [2]'
- 'Paradise Lost Satan, formerly called Lucifer, is the first major character introduced
in the poem. He was once the most beautiful of all angels, and is a tragic figure
who famously declares: "Better to reign in Hell than serve in Heaven." Following
his failed rebellion against God, he is cast out from Heaven and condemned to
Hell. Satan''s desire to rebel against his creator stems from his unwillingness
to be subjugated by God and his Son, claiming that angels are "self-begot, self-raised,"[13]
and thereby denying God''s authority over them as their creator.'
datasets:
- google-research-datasets/paws
- nyu-mll/glue
- mwong/fever-evidence-related
- tasksource/parade
- tasksource/apt
- tasksource/sts-companion
- tasksource/zero-shot-label-nli
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on jhu-clsp/ettin-encoder-17m
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [jhu-clsp/ettin-encoder-17m](https://huggingface.co/jhu-clsp/ettin-encoder-17m) on 20 datasets. It maps sentences & paragraphs to a 256-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [jhu-clsp/ettin-encoder-17m](https://huggingface.co/jhu-clsp/ettin-encoder-17m) <!-- at revision 987607455c61e7a5bbc85f7758e0512ea6d0ae4c -->
- **Maximum Sequence Length:** 1024 tokens
- **Output Dimensionality:** 256 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Datasets:**
- [paws/labeled_final](https://huggingface.co/datasets/paws)
- [glue/mrpc](https://huggingface.co/datasets/glue)
- [fever-evidence-related](https://huggingface.co/datasets/mwong/fever-evidence-related)
- [parade](https://huggingface.co/datasets/tasksource/parade)
- [apt](https://huggingface.co/datasets/tasksource/apt)
- [glue/stsb](https://huggingface.co/datasets/glue)
- sick/relatedness
- [sts-companion](https://huggingface.co/datasets/tasksource/sts-companion)
- [zero-shot-label-nli](https://huggingface.co/datasets/tasksource/zero-shot-label-nli)
- tomaarsen/natural-questions-hard-negatives
- tomaarsen/gooaq-hard-negatives
- bclavie/msmarco-500k-triplets
- sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1
- sentence-transformers/gooaq
- sentence-transformers/natural-questions
- sentence-transformers/quora-duplicates
- sentence-transformers/s2orc
- sentence-transformers/codesearchnet
- sentence-transformers/stackexchange-duplicates
- tasksource/flan
- **Language:** en
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
(1): Pooling({'word_embedding_dimension': 256, '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})
(2): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("tasksource/ettin-17m-embed")
# Run inference
queries = [
"who said better to reign in hell than serve in heaven",
]
documents = [
'Paradise Lost Satan, formerly called Lucifer, is the first major character introduced in the poem. He was once the most beautiful of all angels, and is a tragic figure who famously declares: "Better to reign in Hell than serve in Heaven." Following his failed rebellion against God, he is cast out from Heaven and condemned to Hell. Satan\'s desire to rebel against his creator stems from his unwillingness to be subjugated by God and his Son, claiming that angels are "self-begot, self-raised,"[13] and thereby denying God\'s authority over them as their creator.',
'Maggie Elizabeth Jones Maggie Elizabeth Jones (born October 10, 2003) is an American child actress, best known for her roles in We Bought a Zoo, the Fox sitcom Ben and Kate,[1] and as Lea Clark in American Girl: Lea to the Rescue. [2]',
'House of Cards (season 6) The sixth and final season of the American political drama web television series House of Cards was confirmed by Netflix on December 4, 2017, and is scheduled to be released in late 2018.[1] Unlike previous seasons that consisted of thirteen episodes each, the sixth season will consist of only eight. The season will not include former lead actor Kevin Spacey, who was fired from the show due to sexual misconduct allegations.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 256] [3, 256]
# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.6853, -0.1319, -0.0476]])
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Datasets
<details><summary>paws/labeled_final</summary>
#### paws/labeled_final
* Dataset: [paws/labeled_final](https://huggingface.co/datasets/paws) at [161ece9](https://huggingface.co/datasets/paws/tree/161ece9501cf0a11f3e48bd356eaa82de46d6a09)
* Size: 148,203 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 11 tokens</li><li>mean: 27.89 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 27.86 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>0: ~55.30%</li><li>1: ~44.70%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
| <code>Wesley Enoch , the eldest son of Doug and Lyn Enoch from Stradbroke Island , grew up in Brisbane and is the brother of the Minister of Queensland , Leeanne Enoch .</code> | <code>Wesley Enoch , the eldest son of Doug and Lyn Enoch from Brisbane , grew up in Stradbroke Island and is the brother of the Minister of Queensland , Leeanne Enoch .</code> | <code>0</code> |
| <code>The idea of the ensemble is further discussed in the article Statistical Ensemble ( Mathematical Physics ) .</code> | <code>The idea of the ensemble is further discussed in the mathematical ensemble ( statistical physics ) article .</code> | <code>0</code> |
| <code>Clatsop County comprises the Astoria , OR Micropolitan Statistical Area and is located in the northwest - Oregon .</code> | <code>Clatsop County comprises the Astoria , OR Micropolitan Statistical Area and is located in Northwest Oregon .</code> | <code>1</code> |
* Loss: [<code>AnglELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_angle_sim"
}
```
</details>
<details><summary>glue/mrpc</summary>
#### glue/mrpc
* Dataset: [glue/mrpc](https://huggingface.co/datasets/glue) at [bcdcba7](https://huggingface.co/datasets/glue/tree/bcdcba79d07bc864c1c254ccfcedcce55bcc9a8c)
* Size: 11,004 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 10 tokens</li><li>mean: 27.03 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 27.13 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>0: ~32.90%</li><li>1: ~67.10%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
| <code>Colorado Attorney-General Ken Salazar later said his office has also filed suit against Invesco , charging it with violations of the state 's consumer protection act .</code> | <code>Colorado Attorney General Ken Salazar also filed a lawsuit Tuesday against Invesco , accusing it of violating the state 's Consumer Protection Act .</code> | <code>1</code> |
| <code>At first , the animals ’ performance declined compared to the sessions on the joystick .</code> | <code>At first , the animals ' performance declined compared with the joystick sessions .</code> | <code>1</code> |
| <code>For the first quarter , HP pulled in $ 2.94 billion and captured 27.9 percent of the market .</code> | <code>H-P came in second with nearly $ 3.32 billion in sales and 26 percent of the market 's revenue .</code> | <code>1</code> |
* Loss: [<code>AnglELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_angle_sim"
}
```
</details>
<details><summary>fever-evidence-related</summary>
#### fever-evidence-related
* Dataset: [fever-evidence-related](https://huggingface.co/datasets/mwong/fever-evidence-related) at [14aba00](https://huggingface.co/datasets/mwong/fever-evidence-related/tree/14aba009b5fcd97b1a9ee6f3e3b0da0e308cf7cb)
* Size: 800,000 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 6 tokens</li><li>mean: 13.48 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 28 tokens</li><li>mean: 331.34 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>0: ~32.20%</li><li>1: ~67.80%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
| <code>Dopamine is released by neurons.</code> | <code>Dopamine -LRB- DA , contracted from 3,4-dihydroxyphenethylamine -RRB- is an organic chemical of the catecholamine and phenethylamine families that plays several important roles in the brain and body .. organic chemical. organic compound. catecholamine. catecholamine. phenethylamine. phenethylamine. brain. brain. Dopamine. Dopamine ( medication ). It is an amine synthesized by removing a carboxyl group from a molecule of its precursor chemical L-DOPA , which is synthesized in the brain and kidneys .. L-DOPA. L-DOPA. amine. amine. carboxyl group. C-terminus. precursor chemical. precursor ( chemistry ). synthesized. biosynthesis. brain. brain. Dopamine is also synthesized in plants and most animals .. synthesized. biosynthesis. Dopamine. Dopamine ( medication ). In the brain , dopamine functions as a neurotransmitter -- a chemical released by neurons -LRB- nerve cells -RRB- to send signals to other nerve cells .. brain. brain. neurotransmitter. neurotransmitter. The brain includes several...</code> | <code>0</code> |
| <code>Tanzania shares borders with several landlocked countries.</code> | <code>Mah-Adhur Gushnasp , also known by the Arabicized form of Mahadharjushnas , was an Iranian nobleman who served as the wuzurg framadar -LRB- vizier or prime minister -RRB- of the Sasanian Empire during the reign of the child ruler Ardashir III -LRB- r. 628 -- 629 -RRB- .. Arabicized. Arabicized. Iranian. Iranian people. wuzurg framadar. Wuzurg framadar. vizier. vizier. prime minister. prime minister. Sasanian Empire. Sasanian Empire. Ardashir III. Ardashir III</code> | <code>1</code> |
| <code>Naga Chaitanya was in Dhada.</code> | <code>BMW 320 TC is a racing car built under Super 2000 specifications , which is currently competing in the FIA World Touring Car Championship .. World Touring Car Championship. World Touring Car Championship. BMW. BMW. Super 2000. Super 2000. FIA. FIA</code> | <code>1</code> |
* Loss: [<code>AnglELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_angle_sim"
}
```
</details>
<details><summary>parade</summary>
#### parade
* Dataset: [parade](https://huggingface.co/datasets/tasksource/parade) at [466978f](https://huggingface.co/datasets/tasksource/parade/tree/466978f31aebf4d052287f32ea3ae393f178f386)
* Size: 22,650 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 6 tokens</li><li>mean: 22.13 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 22.1 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>0: ~53.00%</li><li>1: ~47.00%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
| <code>a statistical statement of how likely it is that an obtained result occurred by chance (p value should be less than or equal to 3)</code> | <code>refers to the cutoff point (i.e., critical value); any value that exceeds the cutoff point will be noted as statistically significant</code> | <code>0</code> |
| <code>a website that finds webpages that match a word of phase of a given search expression</code> | <code>search tool that allows you to find specific documents through keyword searches and menu choices, in contrast to directories, which are lists of websites classified by topic.</code> | <code>1</code> |
| <code>explains a phenomenon using assumptions and a philosophical stance. similar to theory but more abstract, generally not testable. connects concepts</code> | <code>broadly presents an understanding of a phenomena and reflects the assumptions of he model's designer</code> | <code>1</code> |
* Loss: [<code>AnglELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_angle_sim"
}
```
</details>
<details><summary>apt</summary>
#### apt
* Dataset: [apt](https://huggingface.co/datasets/tasksource/apt) at [f6c07f6](https://huggingface.co/datasets/tasksource/apt/tree/f6c07f66d3eccebd36418885ce10aff295d436dd)
* Size: 10,047 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 4 tokens</li><li>mean: 17.38 tokens</li><li>max: 82 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 17.38 tokens</li><li>max: 143 tokens</li></ul> | <ul><li>0: ~36.60%</li><li>1: ~63.40%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
| <code>The Embraer jets are scheduled to be delivered by September 2006.</code> | <code>Joseph Biden Jr. is an American politician and the president-elect of the United States.</code> | <code>0</code> |
| <code>Attackers detonated a second roadside bomb later Sunday as a U.S. convoy was traveling near Fallujah, killing an American soldier and wounding three others.</code> | <code>ATTAACKERS DETONATED A SECOND ROADSIDE BOMB LATER SUNDAY AS A U S CONVOY WAS TRAVELING NEAR FALLUJAH, AND AMERICAN SOLDER WOUNDING OTHERS</code> | <code>0</code> |
| <code>You want something to eat?</code> | <code>Do you want to go get some food</code> | <code>0</code> |
* Loss: [<code>AnglELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_angle_sim"
}
```
</details>
<details><summary>glue/stsb</summary>
#### glue/stsb
* Dataset: [glue/stsb](https://huggingface.co/datasets/glue) at [bcdcba7](https://huggingface.co/datasets/glue/tree/bcdcba79d07bc864c1c254ccfcedcce55bcc9a8c)
* Size: 17,247 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | <ul><li>min: 6 tokens</li><li>mean: 14.85 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.79 tokens</li><li>max: 51 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.68</li><li>max: 5.0</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:-------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:-------------------------------|
| <code>New Syria opposition chief wants no-strings aid</code> | <code>Syria opposition unites as Israel fires warning shots</code> | <code>1.0</code> |
| <code>A spokesman said: "Since November, we have co-operated fully with the police.</code> | <code>It added it had "co-operated fully" with police since November.</code> | <code>4.25</code> |
| <code>A small boy in a bathrobe is sitting in a metal chair.</code> | <code>A boy in a robe sits in a chair.</code> | <code>4.199999809265137</code> |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_cos_sim"
}
```
</details>
<details><summary>sick/relatedness</summary>
#### sick/relatedness
* Dataset: sick/relatedness
* Size: 13,317 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------|
| type | string | string | float |
| details | <ul><li>min: 5 tokens</li><li>mean: 12.26 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.22 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 3.5</li><li>max: 5.0</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:----------------------------------------------------|:---------------------------------------------------------|:-------------------------------|
| <code>A woman is cooking eggs</code> | <code>The woman is cooking something</code> | <code>4.199999809265137</code> |
| <code>A great dog is climbing a steep hill</code> | <code>A great dog is wildly climbing a steep hill</code> | <code>4.5</code> |
| <code>A man is passionately playing a guitar</code> | <code>A person is singing and playing a guitar</code> | <code>4.199999809265137</code> |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_cos_sim"
}
```
</details>
<details><summary>sts-companion</summary>
#### sts-companion
* Dataset: [sts-companion](https://huggingface.co/datasets/tasksource/sts-companion) at [fd8beff](https://huggingface.co/datasets/tasksource/sts-companion/tree/fd8beffb788df5f6673bc688e6dcbe3690a3acc6)
* Size: 14,280 training samples
* Columns: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code>
* Approximate statistics based on the first 1000 samples:
| | label | sentence1 | sentence2 |
|:--------|:---------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | float | string | string |
| details | <ul><li>min: 0.0</li><li>mean: 3.13</li><li>max: 5.0</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 18.59 tokens</li><li>max: 80 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 17.19 tokens</li><li>max: 77 tokens</li></ul> |
* Samples:
| label | sentence1 | sentence2 |
|:------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>0.0</code> | <code>they "have" fox because fox news reports on newsworthy events.</code> | <code>i saved up for it because i knew i was going to need it.</code> |
| <code>4.25</code> | <code>Each time, radical improvements in technology made the threat evaporate.</code> | <code>Each time, of radical technological progress leave these threats.</code> |
| <code>3.4</code> | <code>I call on Prague to respond to this signal, this challenge, this plea for dialogue, to grant our request and to ensure, together with our House, that this legacy of a nationalist era can be consigned to the past.</code> | <code>I invite Prague to seize this, this invitation, this request for dialogue, to respond and to ensure that, together with this House, these relics of a nationalist age can be abandoned.</code> |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_cos_sim"
}
```
</details>
<details><summary>zero-shot-label-nli</summary>
#### zero-shot-label-nli
* Dataset: [zero-shot-label-nli](https://huggingface.co/datasets/tasksource/zero-shot-label-nli) at [ee693db](https://huggingface.co/datasets/tasksource/zero-shot-label-nli/tree/ee693dba923b5d5484aa9232b7357c5e45dd39b8)
* Size: 1,090,333 training samples
* Columns: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code>
* Approximate statistics based on the first 1000 samples:
| | label | sentence1 | sentence2 |
|:--------|:------------------------------------------------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
| type | int | string | string |
| details | <ul><li>0: ~50.70%</li><li>1: ~49.30%</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 68.51 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 7.95 tokens</li><li>max: 17 tokens</li></ul> |
* Samples:
| label | sentence1 | sentence2 |
|:---------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------|
| <code>0</code> | <code>Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .<br>Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .</code> | <code>This example is not_equivalent.</code> |
| <code>1</code> | <code>Do science and religion conflict with each other?<br>Does science conflict with the Bible?</code> | <code>This example is not_duplicate.</code> |
| <code>0</code> | <code>do iran and afghanistan speak the same language</code> | <code>This example is False.</code> |
* Loss: [<code>AnglELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_angle_sim"
}
```
</details>
<details><summary>tomaarsen/natural-questions-hard-negatives</summary>
#### tomaarsen/natural-questions-hard-negatives
* Dataset: tomaarsen/natural-questions-hard-negatives
* Size: 96,658 training samples
* Columns: <code>query</code>, <code>answer</code>, <code>negative_1</code>, <code>negative_2</code>, <code>negative_3</code>, <code>negative_4</code>, and <code>negative_5</code>
* Approximate statistics based on the first 1000 samples:
| | query | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
|:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string | string | string | string | string | string |
| details | <ul><li>min: 10 tokens</li><li>mean: 12.52 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 137.85 tokens</li><li>max: 556 tokens</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 144.1 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 142.73 tokens</li><li>max: 832 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 146.37 tokens</li><li>max: 649 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 145.79 tokens</li><li>max: 549 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 142.01 tokens</li><li>max: 574 tokens</li></ul> |
* Samples:
| query | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
|:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>when did richmond last play in a preliminary final</code> | <code>Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tig...</code> | <code>Brisbane Bears However, the club was still struggling off-field. One of the Bears' biggest problems was its lack of support (both on and off the field) in Melbourne, the location of most of its away matches. In mid-1996, the struggling Fitzroy Football Club collapsed due to financial pressures and was seeking to merge its assets with another club. When a merger with North Melbourne in forming the North Fitzroy Kangaroos failed to win the support of the other AFL clubs, a deal for a merger was done between Fitzroy and the Bears. The new team was known as the Brisbane Lions, based at the Gabba, with Northey as the coach of the merged club. As such, the history of the Brisbane Bears as an individual entity ended after the 1996 season, with ten seasons of competition and the third-place finish in 1996 as its best performance. The Bears last match as a separate entity was a preliminary final on Saturday 21 September 1996 at the Melbourne Cricket Ground (where the Bears played their first VF...</code> | <code>Virginia Tech–West Virginia football rivalry Virginia Tech held the trophy in six of the nine years in which it was contested, but West Virginia leads the all-time series 28–23–1. The last game was played on September 3, 2017 at FedEx Field in Landover, MD; Virginia Tech won 31–24.</code> | <code>Martin Truex Jr. To start off the Round of 12, Truex scored his 6th win of the season at Charlotte after leading 91 out of 334 laps to secure a spot for the Round of 8. Just two weeks later, he scored another win at Kansas despite having a restart violation early in the race.</code> | <code>Adelaide Football Club Star midfielder for many years Patrick Dangerfield left the club at the end of the 2015 season (a season in which he won the club's best and fairest) and Don Pyke, a former premiership player and assistant coach with West Coast who had also been an assistant coach at Adelaide from 2005 to 2006, was appointed Adelaide's senior coach for at least three years.[9] Adelaide was widely tipped to slide out of the finals in 2016[27][28][29] but the Crows proved to be one of the successes of the season, comfortably qualifying for a home elimination final and defeating North Melbourne by 62 points, before being eliminated the next week by eventual beaten grand finalists, Sydney in the semi-finals. The club had a dominant 2017 season, winning their opening six games and never falling below second place for the entire season. Adelaide claimed their second McClelland Trophy as minor premiers.[30] The Adelaide Crows entered the 2017 finals series as favourites for the premiers...</code> | <code>Battle of Appomattox Court House The Battle of Appomattox Court House (Virginia, U.S.), fought on the morning of April 9, 1865, was one of the last battles of the American Civil War (1861–1865). It was the final engagement of Confederate States Army General-in-Chief, Robert E. Lee, and his Army of Northern Virginia before it surrendered to the Union Army of the Potomac under the Commanding General of the United States, Ulysses S. Grant. Lee, having abandoned the Confederate capital of Richmond, Virginia, after the nine and one-half month Siege of Petersburg and Richmond, retreated west, hoping to join his army with the remaining Confederate forces in North Carolina, the Army of Tennessee under Gen. Joseph E. Johnston. Union infantry and cavalry forces under Gen. Philip Sheridan pursued and cut off the Confederates' retreat at the central Virginia village of Appomattox Court House. Lee launched a last-ditch attack to break through the Union forces to his front, assuming the Union forc...</code> |
| <code>who sang what in the world's come over you</code> | <code>Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.</code> | <code>Lover, You Should've Come Over "Lover, You Should've Come Over" is the seventh track on Jeff Buckley's album Grace. Inspired by the ending of the relationship between Buckley and Rebecca Moore,[1] it concerns the despondency of a young man growing older, finding that his actions represent a perspective he feels that he should have outgrown. Biographer and critic David Browne describes the lyrics as "confused and confusing" and the music as "a languid beauty."[1]</code> | <code>It's Christmas (All Over The World) "It's Christmas (All Over The World)" is a song recorded by Scottish singer Sheena Easton. It was released in November 1985 as the theme song from the soundtrack of Santa Claus: The Movie. The song was written by Bill House and John Hobbs.</code> | <code>The End of the World (Skeeter Davis song) "The End of the World" is a country pop song written by Arthur Kent and Sylvia Dee, for American singer Skeeter Davis. It had success in the 1960s and spawned many covers.</code> | <code>Israel Kamakawiwoʻole His voice became famous outside Hawaii when his album Facing Future was released in 1993. His medley of "Somewhere Over the Rainbow/What a Wonderful World" was released on his albums Ka ʻAnoʻi and Facing Future. It was subsequently featured in several films, television programs, and television commercials.</code> | <code>Make the World Go Away "Make the World Go Away'" is a country-popular music song composed by Hank Cochran. It has become a Top 40 popular success three times: for Timi Yuro (during 1963), for Eddy Arnold (1965), and for the brother-sister duo Donny and Marie Osmond (1975). The original version of the song was recorded by Ray Price during 1963. It has remained a country crooner standard ever since.</code> |
| <code>who produces the most wool in the world</code> | <code>Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.</code> | <code>Baa, Baa, Black Sheep As with many nursery rhymes, attempts have been made to find origins and meanings for the rhyme, most which have no corroborating evidence.[1] Katherine Elwes Thomas in The Real Personages of Mother Goose (1930) suggested that the rhyme referred to resentment at the heavy taxation on wool.[5] This has particularly been taken to refer to the medieval English "Great" or "Old Custom" wool tax of 1275, which survived until the fifteenth century.[1] More recently the rhyme has been connected to the slave trade, particularly in the southern United States.[6] This explanation was advanced during debates over political correctness and the use and reform of nursery rhymes in the 1980s, but has no supporting historical evidence.[7] Rather than being negative, the wool of black sheep may have been prized as it could be made into dark cloth without dyeing.[6]</code> | <code>Raymond Group Raymond Group is an Indian branded fabric and fashion retailer, incorporated in 1925. It produces suiting fabric, with a capacity of producing 31 million meters of wool and wool-blended fabrics. Gautam Singhania is the chairman and managing director of the Raymond group.[3]</code> | <code>Silk in the Indian subcontinent Silk in the Indian subcontinent is a luxury good. In India, about 97% of the raw mulberry silk is produced in the five Indian states of Karnataka, Andhra Pradesh, Tamil Nadu, West Bengal and Jammu and Kashmir.[1] Mysore and North Bangalore, the upcoming site of a US$20 million "Silk City", contribute to a majority of silk production.[2] Another emerging silk producer is Tamil Nadu where mulberry cultivation is concentrated in Salem, Erode and Dharmapuri districts. Hyderabad, Andhra Pradesh and Gobichettipalayam, Tamil Nadu were the first locations to have automated silk reeling units.[3] yoyo quantity:::</code> | <code>F. W. Woolworth Company The two Woolworth brothers pioneered and developed merchandising, direct purchasing, sales, and customer service practices commonly used today. Despite its growing to be one of the largest retail chains in the world through most of the 20th century, increased competition led to its decline beginning in the 1980s, while its sporting goods division grew. The chain went out of business in July 1997, when the company decided to focus primarily on sporting goods and renamed itself Venator Group. By 2001, the company focused exclusively on the sporting goods market, changing its name to the present Foot Locker, Inc., changing its ticker symbol from its familiar Z in 2003 to its present ticker (NYSE:Â FL).</code> | <code>Silk Silk's absorbency makes it comfortable to wear in warm weather and while active. Its low conductivity keeps warm air close to the skin during cold weather. It is often used for clothing such as shirts, ties, blouses, formal dresses, high fashion clothes, lining, lingerie, pajamas, robes, dress suits, sun dresses and Eastern folk costumes. For practical use, silk is excellent as clothing that protects from many biting insects that would ordinarily pierce clothing, such as mosquitoes and horseflies.</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>tomaarsen/gooaq-hard-negatives</summary>
#### tomaarsen/gooaq-hard-negatives
* Dataset: tomaarsen/gooaq-hard-negatives
* Size: 800,000 training samples
* Columns: <code>question</code>, <code>answer</code>, <code>negative_1</code>, <code>negative_2</code>, <code>negative_3</code>, <code>negative_4</code>, and <code>negative_5</code>
* Approximate statistics based on the first 1000 samples:
| | question | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string | string | string | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 11.99 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 57.82 tokens</li><li>max: 138 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 57.42 tokens</li><li>max: 125 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 56.84 tokens</li><li>max: 120 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 57.08 tokens</li><li>max: 155 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 57.54 tokens</li><li>max: 129 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 58.23 tokens</li><li>max: 195 tokens</li></ul> |
* Samples:
| question | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
|:---------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>is toprol xl the same as metoprolol?</code> | <code>Metoprolol succinate is also known by the brand name Toprol XL. It is the extended-release form of metoprolol. Metoprolol succinate is approved to treat high blood pressure, chronic chest pain, and congestive heart failure.</code> | <code>Secondly, metoprolol and metoprolol ER have different brand-name equivalents: Brand version of metoprolol: Lopressor. Brand version of metoprolol ER: Toprol XL.</code> | <code>Pill with imprint 1 is White, Round and has been identified as Metoprolol Tartrate 25 mg.</code> | <code>Interactions between your drugs No interactions were found between Allergy Relief and metoprolol. This does not necessarily mean no interactions exist. Always consult your healthcare provider.</code> | <code>Metoprolol is a type of medication called a beta blocker. It works by relaxing blood vessels and slowing heart rate, which improves blood flow and lowers blood pressure. Metoprolol can also improve the likelihood of survival after a heart attack.</code> | <code>Metoprolol starts to work after about 2 hours, but it can take up to 1 week to fully take effect. You may not feel any different when you take metoprolol, but this doesn't mean it's not working. It's important to keep taking your medicine.</code> |
| <code>are you experienced cd steve hoffman?</code> | <code>The Are You Experienced album was apparently mastered from the original stereo UK master tapes (according to Steve Hoffman - one of the very few who has heard both the master tapes and the CDs produced over the years). ... The CD booklets were a little sparse, but at least they stayed true to the album's original design.</code> | <code>I Saw the Light. Showcasing the unique talent and musical influence of country-western artist Hank Williams, this candid biography also sheds light on the legacy of drug abuse and tormented relationships that contributes to the singer's legend.</code> | <code>(Read our ranking of his top 10.) And while Howard dresses the part of director, any notion of him as a tortured auteur or dictatorial taskmasker — the clichés of the Hollywood director — are tossed aside. He's very nice.</code> | <code>He was a music star too. Where're you people born and brought up? We 're born and brought up here in Anambra State at Nkpor town, near Onitsha.</code> | <code>At the age of 87 he has now retired from his live shows and all the traveling involved. And although he still picks up his Martin Guitar and does a show now and then, his life is now devoted to writing his memoirs.</code> | <code>The owner of the mysterious voice behind all these videos is a man who's seen a lot, visiting a total of 56 intimate celebrity spaces over the course of five years. His name is Joe Sabia — that's him in the photo — and he's currently the VP of creative development at Condé Nast Entertainment.</code> |
| <code>how are babushka dolls made?</code> | <code>Matryoshka dolls are made of wood from lime, balsa, alder, aspen, and birch trees; lime is probably the most common wood type. ... After cutting, the trees are stripped of most of their bark, although a few inner rings of bark are left to bind the wood and keep it from splitting.</code> | <code>A quick scan of the auction and buy-it-now listings on eBay finds porcelain doll values ranging from around $5 and $10 to several thousand dollars or more but no dolls listed above $10,000.</code> | <code>Japanese dolls are called as ningyō in Japanese and literally translates to 'human form'.</code> | <code>Matyoo: All Fresno Girl dolls come just as real children are born.</code> | <code>As of September 2016, there are over 100 characters. The main toy line includes 13-inch Dolls, the mini-series, and a variety of mini play-sets and plush dolls as well as Lalaloopsy Littles, smaller siblings of the 13-inch dolls. A spin-off known as "Lala-Oopsies" came out in late 2012.</code> | <code>LOL dolls are little baby dolls that come wrapped inside a surprise toy ball. Each ball has layers that contain stickers, secret messages, mix and match accessories–and finally–a doll. ... The doll on the ball is almost never the doll inside. Dolls are released in series, so not every doll is available all the time.</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>bclavie/msmarco-500k-triplets</summary>
#### bclavie/msmarco-500k-triplets
* Dataset: bclavie/msmarco-500k-triplets
* Size: 500,000 training samples
* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | query | positive | negative |
|:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 9.31 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 82.19 tokens</li><li>max: 216 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 78.99 tokens</li><li>max: 209 tokens</li></ul> |
* Samples:
| query | positive | negative |
|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>the most important factor that influences k+ secretion is __________.</code> | <code>The regulation of K+ distribution between the intracellular and extracellular space is referred to as internal K+ balance. The most important factors regulating this movement under normal conditions are insulin and catecholamines (1).</code> | <code>They are both also important for secretion and flow of bile: 1 Cholecystokinin: The name of this hormone describes its effect on the biliary system-cholecysto = gallbladder and kinin = movement. 2 Secretin: This hormone is secreted in response to acid in the duodenum.</code> |
| <code>how much did the mackinac bridge cost to build</code> | <code>The cost to design the project was $3,500,000 (Steinman Company). The cost to construct the bridge was $70, 268,500. Two primary contractors were hired to build the bridge: American Bridge for superstructure - $44,532,900; and Merritt-Chapman and Scott of New York for the foundations - $25,735,600.</code> | <code>When your child needs a dental tooth bridge, you need to know the average cost so you can factor the price into your budget. Several factors affect the price of a bridge, which can run between $700 to $1,500 per tooth. If you have insurance or your child is covered by Medicaid, part of the cost may be covered.</code> |
| <code>when do concussion symptoms appear</code> | <code>Then you can get advice on what to do next. For milder symptoms, the doctor may recommend rest and ask you to watch your child closely for changes, such as a headache that gets worse. Symptoms of a concussion don't always show up right away, and can develop within 24 to 72 hours after an injury.</code> | <code>Concussion: A traumatic injury to soft tissue, usually the brain, as a result of a violent blow, shaking, or spinning. A brain concussion can cause immediate but temporary impairment of brain functions, such as thinking, vision, equilibrium, and consciousness. After a person has had a concussion, he or she is at increased risk for recurrence. Moreover, after a person has several concussions, less of a blow can cause injury, and the person can require more time to recover.</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1</summary>
#### sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1
* Dataset: sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1
* Size: 800,000 training samples
* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | query | positive | negative |
|:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 5 tokens</li><li>mean: 9.87 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 44 tokens</li><li>mean: 85.25 tokens</li><li>max: 211 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 81.18 tokens</li><li>max: 227 tokens</li></ul> |
* Samples:
| query | positive | negative |
|:----------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>what are the liberal arts?</code> | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>Rather than preparing students for a specific career, liberal arts programs focus on cultural literacy and hone communication and analytical skills. They often cover various disciplines, ranging from the humanities to social sciences. 1 Program Levels in Liberal Arts: Associate degree, Bachelor's degree, Master's degree.</code> |
| <code>what are the liberal arts?</code> | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>Artes Liberales: The historical basis for the modern liberal arts, consisting of the trivium (grammar, logic, and rhetoric) and the quadrivium (arithmetic, geometry, astronomy, and music). General Education: That part of a liberal education curriculum that is shared by all students.</code> |
| <code>what are the liberal arts?</code> | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>Liberal Arts. Upon completion of the Liberal Arts degree, students will be able to express ideas in coherent, creative, and appropriate forms, orally and in writing. Students will be able to apply their reading abilities in order to interconnect an understanding of resources to academic, professional, and personal interests.</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>sentence-transformers/gooaq</summary>
#### sentence-transformers/gooaq
* Dataset: sentence-transformers/gooaq
* Size: 800,000 training samples
* Columns: <code>question</code> and <code>answer</code>
* Approximate statistics based on the first 1000 samples:
| | question | answer |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 12.19 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 58.34 tokens</li><li>max: 124 tokens</li></ul> |
* Samples:
| question | answer |
|:---------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>is toprol xl the same as metoprolol?</code> | <code>Metoprolol succinate is also known by the brand name Toprol XL. It is the extended-release form of metoprolol. Metoprolol succinate is approved to treat high blood pressure, chronic chest pain, and congestive heart failure.</code> |
| <code>are you experienced cd steve hoffman?</code> | <code>The Are You Experienced album was apparently mastered from the original stereo UK master tapes (according to Steve Hoffman - one of the very few who has heard both the master tapes and the CDs produced over the years). ... The CD booklets were a little sparse, but at least they stayed true to the album's original design.</code> |
| <code>how are babushka dolls made?</code> | <code>Matryoshka dolls are made of wood from lime, balsa, alder, aspen, and birch trees; lime is probably the most common wood type. ... After cutting, the trees are stripped of most of their bark, although a few inner rings of bark are left to bind the wood and keep it from splitting.</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>sentence-transformers/natural-questions</summary>
#### sentence-transformers/natural-questions
* Dataset: sentence-transformers/natural-questions
* Size: 100,231 training samples
* Columns: <code>query</code> and <code>answer</code>
* Approximate statistics based on the first 1000 samples:
| | query | answer |
|:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 10 tokens</li><li>mean: 12.47 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 138.32 tokens</li><li>max: 556 tokens</li></ul> |
* Samples:
| query | answer |
|:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>when did richmond last play in a preliminary final</code> | <code>Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tig...</code> |
| <code>who sang what in the world's come over you</code> | <code>Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.</code> |
| <code>who produces the most wool in the world</code> | <code>Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>sentence-transformers/quora-duplicates</summary>
#### sentence-transformers/quora-duplicates
* Dataset: sentence-transformers/quora-duplicates
* Size: 101,762 training samples
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 13.85 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.63 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.68 tokens</li><li>max: 61 tokens</li></ul> |
* Samples:
| anchor | positive | negative |
|:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------|
| <code>Why in India do we not have one on one political debate as in USA?</code> | <code>Why cant we have a public debate between politicians in India like the one in US?</code> | <code>Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk?</code> |
| <code>What is OnePlus One?</code> | <code>How is oneplus one?</code> | <code>Why is OnePlus One so good?</code> |
| <code>Does our mind control our emotions?</code> | <code>How do smart and successful people control their emotions?</code> | <code>How can I control my positive emotions for the people whom I love but they don't care about me?</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>sentence-transformers/s2orc</summary>
#### sentence-transformers/s2orc
* Dataset: sentence-transformers/s2orc
* Size: 800,000 training samples
* Columns: <code>title</code> and <code>abstract</code>
* Approximate statistics based on the first 1000 samples:
| | title | abstract |
|:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 20.08 tokens</li><li>max: 83 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 131.03 tokens</li><li>max: 332 tokens</li></ul> |
* Samples:
| title | abstract |
|:----------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>Syntheses, Structures and Properties of Two Transition Metal-Flexible Ligand Coordination Polymers</code> | <code>Two coordination polymers based on 3,5-bis(4-carboxyphenylmethyloxy) benzoic acid (H3L), [M(HL)]·2H2O M = Mn(1), Co(2), have been synthesized under hydrothermal conditions. Their structures have been determined by single-crystal X-ray diffraction and further characterized by elemental analysis, IR spectra and TGA. The two complexes possess 3D framework with diamond channels resulting from the trans-configuration of the flexible ligand and three coordination modes, 3(η2, η1), 2(η1, η1), η1, of carboxyl groups in the ligand. The framework can be represented with Schlafli symbol of (48·66)(47·66). The wall of the channel consists of left- or right-handed helical polymeric chains. UV–visible–NIR and photoluminescence spectra, magnetic properties of 1 and 2 have also been discussed.</code> |
| <code>Discussion on the Influence and Development of Technical Aesthetics in Modern Landscape Design</code> | <code>The source of technical aesthetics was introduced and its meaning was explained.The relations between technical aesthetics and modern landscpae design were discussed.The embodiment of technical aesthetics in landscpae design was discussed in the aspects of new material,new technology,new structureand new apparatus.It was put forward that the the development direction of technical aesthetics were tending to sensibility, native land and zoology.</code> |
| <code>GRIN optics for dual-band IR sensors (Conference Presentation)</code> | <code>Graded index (GRIN) optics offer potential for both weight savings and increased performance but have until recently been limited to visible and NIR bands (wavelengths shorter than about 0.9 µm). NRL has developed glass-based IR-GRIN lenses compatible with SWIR-LWIR wavebands. Recent designs show the potential for significant SWaP reduction benefits and improved performance using IR-GRIN lens elements in dual-band, MWIR-LWIR sensors. The SWaP and performance advantages of IR-GRIN lenses in platform-relevant dual-band imagers will be presented.</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>sentence-transformers/codesearchnet</summary>
#### sentence-transformers/codesearchnet
* Dataset: sentence-transformers/codesearchnet
* Size: 800,000 training samples
* Columns: <code>comment</code> and <code>code</code>
* Approximate statistics based on the first 1000 samples:
| | comment | code |
|:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 3 tokens</li><li>mean: 28.98 tokens</li><li>max: 142 tokens</li></ul> | <ul><li>min: 30 tokens</li><li>mean: 166.72 tokens</li><li>max: 1024 tokens</li></ul> |
* Samples:
| comment | code |
|:-----------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>Computes the new parent id for the node being moved.<br><br>@return int</code> | <code>protected function parentId()<br> {<br> switch ( $this->position )<br> {<br> case 'root':<br> return null;<br><br> case 'child':<br> return $this->target->getKey();<br><br> default:<br> return $this->target->getParentId();<br> }<br> }</code> |
| <code>// SetWinSize overwrites the playlist's window size.</code> | <code>func (p *MediaPlaylist) SetWinSize(winsize uint) error {<br> if winsize > p.capacity {<br> return errors.New("capacity must be greater than winsize or equal")<br> }<br> p.winsize = winsize<br> return nil<br>}</code> |
| <code>Show the sidebar and squish the container to make room for the sidebar.<br>If hideOthers is true, hide other open sidebars.</code> | <code>function() {<br> var options = this.options;<br><br> if (options.hideOthers) {<br> this.secondary.each(function() {<br> var sidebar = $(this);<br><br> if (sidebar.hasClass('is-expanded')) {<br> sidebar.toolkit('offCanvas', 'hide');<br> }<br> });<br> }<br><br> this.fireEvent('showing');<br><br> this.container.addClass('move-' + this.opposite);<br><br> this.element<br> .reveal()<br> .addClass('is-expanded')<br> .aria('expanded', true);<br><br> if (options.stopScroll) {<br> $('body').addClass('no-scroll');<br> }<br><br> this.fireEvent('shown');<br> }</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>sentence-transformers/stackexchange-duplicates</summary>
#### sentence-transformers/stackexchange-duplicates
* Dataset: sentence-transformers/stackexchange-duplicates
* Size: 250,460 training samples
* Columns: <code>body1</code> and <code>body2</code>
* Approximate statistics based on the first 1000 samples:
| | body1 | body2 |
|:--------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 13 tokens</li><li>mean: 174.01 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 156.88 tokens</li><li>max: 1024 tokens</li></ul> |
* Samples:
| body1 | body2 |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>I've been wondering about this for years. It seems like a pretty obvious question, so I'm surprised not to have found it addressed among the other Tolkien minutiae on this site. Hopefully I haven't missed it, but anyway, here goes... In Tolkien's Middle-Earth writings, Evil cannot create things, only twist and warp what already exists. Thus, Orcs are twisted Elves, Trolls are twisted Ents, etc. So then, what's the original source for Dragons? They look pretty original to me! The only template that seems even remotely possible is the Eagles, as they're both powerful fliers, but the connection seems very remote indeed. Also, as twisted copies Orcs and Trolls are markedly inferior to Elves and Ents respectively, but I'm not aware of any text describing Dragons as inferior to Eagles.</code> | <code>All that I know of Smaug is that he (she?) came out of nowhere to attack and conquer Erebor. Where exactly did he come from? In fact, what are the origins of dragons? Did Ilúvatar create them or did they come from somewhere else?</code> |
| <code>Hi i have some data which coming out from database in form of table like this, first i match some data with searching and then display it on page now i need to download it as csv file format please help me check my code and i'm new in php. please check image too for the reference and please please help me //import.php // echo "<pre>"; //print_r($_POST);die(); $keyword = $_POST['keyword']; $csvname = $_POST['csv_file']; ?> <table border ="1"> <thead> <tr> <th>id</th> <th>title</th> <th>count</th> </tr> </thead> <?php $row = 0; if (($handle = fopen("idata.csv", "r",)) !== FALSE) { while (($data = fgetcsv($handle, 1000, ",")) !== FALSE) { $num = count($data); // echo "<p> $num fields in line $row: <br /></p>\n"; $row++; for ($c=0; $c < $num; $c++) { // echo $data[$c] . "<br...</code> | <code>What is the most efficient way to convert a MySQL query to CSV in PHP please? It would be best to avoid temp files as this reduces portability (dir paths and setting file-system permissions required). The CSV should also include one top line of field names.</code> |
| <code>Following along in tutorials I see the blur filter being used. I am using Blender 2.69 and I can't locate it visually or even with a search. Actually, there is no "Filters" category at all. Do I have to download something to get it?</code> | <code>I have been following tutorial until I started adding nodes. The problem is that he has completely different nodes than I have. Even nodes that are created at start are different (I have Material and Output and he has Render Layers and Composite). Have I missed something or should I use different nodes than he?</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
<details><summary>tasksource/flan</summary>
#### tasksource/flan
* Dataset: tasksource/flan
* Size: 200,000 training samples
* Columns: <code>anchor</code>, <code>positive</code>, <code>rejected</code>, <code>task</code>, and <code>template_type</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | rejected | task | template_type |
|:--------|:--------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
| type | string | string | string | string | string |
| details | <ul><li>min: 72 tokens</li><li>mean: 513.33 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.69 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.59 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 16.38 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 5.97 tokens</li><li>max: 7 tokens</li></ul> |
* Samples:
| anchor | positive | rejected | task | template_type |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------|:------------------------------------------|:---------------------------------------------------------|:--------------------|
| <code>Please answer the following question: Given the following passage "A healthy, and legal, publishing industry existed throughout Europe, although established publishers and book sellers occasionally ran afoul of the law. The Encyclopédie, for example, condemned not only by the King but also by Clement XII, nevertheless found its way into print with the help of the aforementioned Malesherbes and creative use of French censorship law. But many works were sold without running into any legal trouble at all. Borrowing records from libraries in England, Germany and North America indicate that more than 70 percent of books borrowed were novels. Less than 1 percent of the books were of a religious nature, indicating the general trend of declining religiosity.", answer the following question. Note that the answer is present within the text. Question: What country was omitted from the borrowing records?<br>Answer:</code> | <code>French</code> | <code>US</code> | <code>adversarial_qa_dbert_answer_the_following_q</code> | <code>zs_opt</code> |
| <code>Problem: Given the question: Given the following passage "On 3 December, Chopin complained about his bad health and the incompetence of the doctors in Majorca: "Three doctors have visited me ... The first said I was dead; the second said I was dying; and the third said I was about to die." He also had problems having his Pleyel piano sent to him. It finally arrived from Paris in December. Chopin wrote to Pleyel in January 1839: "I am sending you my Preludes [(Op. 28)]. I finished them on your little piano, which arrived in the best possible condition in spite of the sea, the bad weather and the Palma customs." Chopin was also able to undertake work on his Ballade No. 2, Op. 38; two Polonaises, Op. 40; and the Scherzo No. 3, Op. 39.", answer the following question. Note that the answer is present within the text. Question: Which doctor did not think Chopin was dead?<br>++++++++++++++++++++++++++++++++<br>The answer is:<br>the third<br><br><br>Problem: Given the question: Given the following passage "...</code> | <code>Jehovah</code> | <code>Ashkenazi and Sephardic Jews</code> | <code>adversarial_qa_dbert_answer_the_following_q</code> | <code>fs_opt</code> |
| <code>input: Please answer the following: Given the following passage "Jehovah's Witnesses are perhaps best known for their efforts to spread their beliefs, most notably by visiting people from house to house, distributing literature published by the Watch Tower Society in 700 languages. The objective is to start a regular "Bible study" with any person who is not already a member, with the intention that the student be baptized as a member of the group; Witnesses are advised to consider discontinuing Bible studies with students who show no interest in becoming members. Witnesses are taught they are under a biblical command to engage in public preaching. They are instructed to devote as much time as possible to their ministry and are required to submit an individual monthly "Field Service Report". Baptized members who fail to report a month of preaching are termed "irregular" and may be counseled by elders; those who do not submit reports for six consecutive months are termed "inactive".", ...</code> | <code>reformed</code> | <code>The Verge</code> | <code>adversarial_qa_dbert_answer_the_following_q</code> | <code>fs_opt</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"mini_batch_size": 32,
"gather_across_devices": false
}
```
</details>
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 512
- `learning_rate`: 1.0
- `weight_decay`: 6e-05
- `num_train_epochs`: 1.0
- `fp16`: True
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: no
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 512
- `per_device_eval_batch_size`: 8
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 1.0
- `weight_decay`: 6e-05
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1.0
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `parallelism_config`: None
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `project`: huggingface
- `trackio_space_id`: trackio
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `hub_revision`: None
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: no
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `liger_kernel_config`: None
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: True
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}
</details>
### Training Logs
| Epoch | Step | Training Loss |
|:------:|:-----:|:-------------:|
| 0.0347 | 500 | 5.015 |
| 0.0694 | 1000 | 3.6072 |
| 0.1041 | 1500 | 3.6206 |
| 0.1387 | 2000 | 3.5205 |
| 0.1734 | 2500 | 3.8717 |
| 0.2081 | 3000 | 3.2363 |
| 0.2428 | 3500 | 3.0776 |
| 0.2775 | 4000 | 3.1094 |
| 0.3122 | 4500 | 3.3586 |
| 0.3468 | 5000 | 3.2504 |
| 0.3815 | 5500 | 2.9393 |
| 0.4162 | 6000 | 2.8626 |
| 0.4509 | 6500 | 3.1186 |
| 0.4856 | 7000 | 2.9852 |
| 0.5203 | 7500 | 2.8228 |
| 0.5549 | 8000 | 2.9656 |
| 0.5896 | 8500 | 2.6737 |
| 0.6243 | 9000 | 2.6191 |
| 0.6590 | 9500 | 2.7254 |
| 0.6937 | 10000 | 2.6937 |
| 0.7284 | 10500 | 2.8813 |
| 0.7630 | 11000 | 2.8221 |
| 0.7977 | 11500 | 2.9132 |
| 0.8324 | 12000 | 2.4675 |
| 0.8671 | 12500 | 2.9528 |
| 0.9018 | 13000 | 2.4298 |
| 0.9365 | 13500 | 2.3748 |
| 0.9711 | 14000 | 2.6557 |
### Framework Versions
- Python: 3.12.10
- Sentence Transformers: 5.1.2
- Transformers: 4.57.3
- PyTorch: 2.7.1+cu126
- Accelerate: 1.7.0
- Datasets: 3.6.0
- Tokenizers: 0.22.1
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### AnglELoss
```bibtex
@inproceedings{li-li-2024-aoe,
title = "{A}o{E}: Angle-optimized Embeddings for Semantic Textual Similarity",
author = "Li, Xianming and Li, Jing",
year = "2024",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.101/",
doi = "10.18653/v1/2024.acl-long.101"
}
```
#### CoSENTLoss
```bibtex
@article{10531646,
author={Huang, Xiang and Peng, Hao and Zou, Dongcheng and Liu, Zhiwei and Li, Jianxin and Liu, Kay and Wu, Jia and Su, Jianlin and Yu, Philip S.},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
title={CoSENT: Consistent Sentence Embedding via Similarity Ranking},
year={2024},
doi={10.1109/TASLP.2024.3402087}
}
```
#### CachedMultipleNegativesRankingLoss
```bibtex
@misc{gao2021scaling,
title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
year={2021},
eprint={2101.06983},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> |