Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 384,
+    "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
+}

README.md

@@ -0,0 +1,661 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:5000
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-MiniLM-L6-v2
+widget:
+- source_sentence: (CNN) -- A third minute goal from Gonzalo Higuain gave Real Madrid
+    a 1-0 victory over Valencia, coach Juande Ramos' first Primera Liga win since
+    taking charge of the Spanish champions. Gonzalo Higuain is congratulated after
+    scoring Real Madrid's only goal against Valencia. The win ended Madrid's run of
+    three straight league defeats and moved them up to 29 points, nine behind leaders
+    Barcelona -- who visit Villarreal on Sunday. With captain Raul Gonzalez only on
+    the bench befcause of the flu, Higuain played alone in attack, and he soon made
+    his mark with the early goal -- the Argentine collecting Arjen Robben's pass to
+    fire home his 11th goal of the season. Valencia almost fell two goals behind in
+    the 16th minute when Rafael van der Vaart struck the post with a curling drive.
+    Higuain had a chance to double Madrid's tally in the second-half, but his close-range
+    shot struck the bar. The visitors' hopes were effectively ended when captain Carlos
+    Marchena was sent off  after picking up his second yellow card, for a foul on
+    Robben. The defeat, only Valencia's second of the season after also going down
+    to Barcelona, leaves them on 30 points, just one above Madrid.
+  sentences:
+  - 'California governor honors U.S. Airways pilot Capt. Chesley Sullenberger .
+
+    Schwarzenegger: "We need a great hero" in state legislature like Sullenberger
+    .
+
+    Sullenberger safely landed flight 1549 in the Hudson River in New York .
+
+    Sullenberger accepts recognition on behalf of crew members, others .'
+  - 'Gonzalo Higuain scoresd the only goal as Real Madrid defeat Valencia 1-0 .
+
+    The victory marks first success in the Primera Liga for coach Juande Ramos .
+
+    Valencia, who had Carlos Marchena sent off, were losing only second match .'
+  - 'By definition, a premature baby is born before the 37th week of pregnancy .
+
+    Premature babies cost the U.S. at least $26 billion each year .
+
+    There are risk factors, but not all premature births can be prevented .
+
+    In tough economic times, pregnant women should not cut back on health care .'
+- source_sentence: (CNN) -- The U.S. Olympic Committee and the International Olympic
+    Committee are expected to ask a federal judge Monday to shut down Web sites they
+    allege scam customers trying to buy Olympic tickets, according to court documents.
+    The Web site www.beijingticketing.com is accused in a lawsuit of scamming Olympic
+    ticket buyers. The IOC and the USOC filed lawsuits on July 22 against several
+    Web sites -- primarily www.beijingticketing.com and www.beijing-2008tickets.com
+    -- for illegally using Olympic trademarks to dupe customers into giving them credit
+    card, passport and banking information. Lawyers for the IOC and USOC are expected
+    to petition U.S. District Court Judge Jeffrey White on Monday to permanently shut
+    down several sites listed in the lawsuit. The lawsuit names the company XL & H
+    Ltd, known as Xclusive Leisure & Hospitality Ltd. and six other Web sites believed
+    to be fraudulent. Several consumers who purchased tickets from the site contacted
+    the USOC when they did not receive tickets, despite numerous calls and e-mails
+    to the Web sites founder, according to a USOC press release. The scam has hit
+    Olympic fans in the United States, Australia, New Zealand, England, Japan, China
+    and Norway, according to media reports. Australian Olympic Committee President
+    John Coates told local media that relatives of the country's softball team had
+    been victims of the site. The Sydney Morning Herald reported that the New South
+    Wales Government set up a hotline for those duped out of tickets. The hotline
+    has received hundreds of calls from around the globe with consumers detailing
+    losses as high as $57,000. The IOC and USOC successfully secured a restraining
+    order on July 23 in federal court in Phoenix, Arizona, that shut down www.beijing-2008tickets.com,
+    according to court documents. That site is now shut down and no contact information
+    is available. The site www.BeijingTicketing.com priced tickets for Friday's Olympic
+    opening ceremony at about $2,000, with events such as swimming selling for between
+    $300 and $500. The site is the first entry that comes up for a Google search for
+    "Olympic tickets," second only to the authorized dealer of Olympic tickets, www.cosport.com.
+    The Web site ww.beijingticketing.com site lists a London phone number, which rang
+    unanswered. The site lists an office address in Arizona. The site boasts tickets
+    for nearly every Olympic event, with some events showing sell-outs already. The
+    site also looked to assure ticket buyers of its authenticity with a note at the
+    bottom of the site. "Beijing 2008 Ticketing is a well known tickets agent and
+    a trusted market place for buyers to find book Olympic tickets," the note stated.
+    "We assure 100% guaranteed tickets delivery."
+  sentences:
+  - 'French National Assembly backs president''s plan to rejoin NATO .
+
+    President Nicolas Sarkozy''s plan is politically sensitive .
+
+    France was a founding member of NATO but left in 1966 .
+
+    President Charles de Gaulle said in 1966 membership meant losing independence
+    .'
+  - 'Harry Nicolaides, 41, was arrested last August over his 2005 book .
+
+    The book includes a paragraph about the king and crown prince .
+
+    Authorities deemed it a violation of a law that makes it illegal to insult the
+    crown .
+
+    Man''s lawyer says he was relieved and left for Australia at about midnight .'
+  - 'USOC, IOC claim fake ticket sites have bilked customers using their trademark
+    .
+
+    Sites www.BeijingTicketing.com and www.beijing-2008tickets.com named in suit .
+
+    One site claims "We assure 100 % guaranteed tickets delivery"'
+- source_sentence: (CNN) -- Police are searching for any other alleged victims of
+    a Sunday school teacher accused of raping and killing an 8-year-old girl from
+    Tracy, California. Melissa Huckaby is charged with killing 8-year-old Sandra Cantu,
+    who was a friend of her own daughter. "We are asking the public if they have any
+    indication that any of their children may have had inappropriate contact with
+    [the suspect] to contact us," Tracy Police Sgt. Tony Sheneman said Tuesday evening.
+    "There has been no indication that this has happened. But she is a Sunday school
+    teacher and did have contact with children, so that is why we are asking." Melissa
+    Huckaby, 28, was arrested and charged with killing and raping 8-year-old Sandra
+    Cantu, a friend of her 5-year-old daughter. Huckaby, wearing red jail scrubs over
+    a white T-shirt, was in court Tuesday for an arraignment. She was charged with
+    murder, kidnapping, the performance of a lewd and lascivious act on a child under
+    14 and rape by instrument. If convicted, Huckaby would face the death penalty
+    or life in prison without parole, San Joaquin County District Attorney James Willett
+    told reporters after the hearing. A decision on whether to seek the death penalty
+    will be made later, he said. Huckaby did not enter a plea or speak during the
+    court hearing, although she flinched when Sandra Cantu's name was spoken, and
+    she cried at times. Sandra's body was found April 6, stuffed into a suitcase and
+    submerged in a pond at a dairy farm. Huckaby was arrested Friday night after questioning
+    by police. Sandra was last seen alive March 27 in the mobile home park where she
+    lived with her family -- the same mobile home park where Huckaby lives with her
+    daughter. The two children were close friends and played together frequently,
+    police said. Huckaby is the granddaughter of Clifford Lane Lawless, pastor of
+    Clover Road Baptist Church near the mobile home park, and she taught Sunday school
+    at the church, police have said. The church was searched as part of the investigation
+    into Sandra's disappearance and death. Before her arrest, Huckaby acknowledged
+    to a newspaper reporter that she owned the suitcase that contained Sandra's body.
+    But Huckaby said the suitcase had been stolen. Willett declined to comment on
+    any of the evidence or allegations in the case, saying evidence would be presented
+    in court. A memorial ceremony is scheduled for Sandra at 1 p.m. Thursday at a
+    high school in Tracy, police said. -- CNN's Ninette Sosa contributed to this report.
+  sentences:
+  - 'President Bush continues a Christmas tradition by issuing pardons .
+
+    Convicted Cheney aide Lewis "Scooter" Libby is not among those pardoned .
+
+    Posthumous pardon issued for man who ran guns to Israeli Jews in late 1940s .
+
+    Life sentence of man convicted of methamphetamine commuted .'
+  - 'Police comb community for other possible victims .
+
+    Melissa Huckaby was arrested and charged with killing and raping Sandra Cantu
+    .
+
+    Sandra, 8, was friends with Huckaby''s 5-year-old daughter .'
+  - 'San Antonio, Texas, 12-year-old wins "Doodle for Google" national contest .
+
+    Christin Engelberth''s work will grace Google''s main site for 24 hours Thursday
+    .
+
+    Other prizes: $25,000 college scholarship, laptop, tech grant for her school .
+
+    When she grows up, she said, she hopes to do "anything to do with art"'
+- source_sentence: 'Editor''s note: Fawaz A. Gerges holds the Christian A. Johnson
+    Chair in Middle Eastern Studies and International Affairs at Sarah Lawrence College.
+    His most recent book is "The Far Enemy: Why Jihad Went Global." Fawaz Gerges says
+    the elite running Iran has lost the support of two key groups -- women and young
+    voters. (CNN) -- With an apparent political coup in Iran by President Mahmoud
+    Ahmadinejad and his supporters over the weekend, the ruling mullahs have dispensed
+    with all democratic pretense and joined the ranks of traditional dictators in
+    the Middle East. The hardliners in Tehran, led by the Revolutionary Guards and
+    ultraconservatives, have won the first round against reformist conservatives but
+    at an extravagant cost: loss of public support. Widespread accusations of fraud
+    and manipulation are calling into question the very legitimacy and authority of
+    the mullahs'' Islamic-based regime. The electoral crisis has exposed a deepening
+    divide between female and young voters, who represent about 70 percent of the
+    population, and a radical conservative ruling elite out of touch with the hopes,
+    fears and aspirations of young Iranians. The consensus in Iran, particularly among
+    young voters, is that the election was stolen from reformist candidate, Mir Hossein
+    Moussavi, and that the outcome did not reflect the electorate''s genuine will.
+    After the Interior Ministry announced the final election results showing a nearly
+    2-to-1 landslide for Ahmadinejad (62.63 to 33.75 percent), thousands of young
+    protesters took to the streets and clashed with police and set trash bins and
+    tires ablaze. Shock and disbelief turned to anger and rage. What poured gasoline
+    on a simmering fire among the youth was a belief of widespread fraud. "It''s like
+    taking 10 million votes away from Moussavi and giving them to Ahmadinejad," said
+    Tehran-based analyst Saeed Leilaz. That is equivalent to more than 30 million
+    votes in the American electorate. "Death to the dictatorship" and "down with the
+    dictator" shouted the demonstrators while being clubbed by police and anti-riot
+    squads. For the first time, young Iranians showed defiance against their tormentors
+    and overcame their fear. Many young men reportedly roamed Tehran streets looking
+    for a fight with the police. The ruling mullahs face an unprecedentedly serious
+    crisis at home. While it does not threaten their existence, the crisis risks undermining
+    their ability to govern effectively and pursue a successful foreign policy. In
+    his first response to the results of the election, Moussavi nailed it on the head.
+    "I won''t surrender to this manipulation," he wrote on his Web site. "The result
+    of such performance by some officials will jeopardize the pillars of the Islamic
+    Republic and will establish tyranny." Moussavi''s warning to the mullahs that
+    stealing the election would weaken the very foundation of their regime and ultimately
+    bring about its collapse carries weight because he has been part of the political
+    inner circle of the Islamic Republic, not an outsider. Moussavi is a former prime
+    minister admired for the way he managed the country''s economy during the prolonged
+    and bloody Iran-Iraq war in the 1980s, a conflict which cost Iran over $500 billion.
+    He worked closely with Ali Khamenei, then Iran''s president and today supreme
+    leader, and clashed with him over political authority and powers. Moussavi is
+    a member of Iran''s Expediency Council, which mediates between the parliament
+    and the non-elected Guardian Council led by Ayatollah Khamenei. Initially, many
+    reformists were skeptical about Moussavi''s reform credentials and feared that
+    he was too conservative for their taste. Throughout the presidential campaign,
+    Moussavi labored hard to portray his proposals on social policy and foreign affairs
+    as an extension of the Islamic system in order to disarm conservative critics,
+    even denying that he is a mainstream reformist candidate in the hope of winning
+    the support of reformers and moderate conservatives. Indeed, as the presidential
+    campaign progressed, Moussavi won the backing not only of an important conservative
+    segment of the electorate but also the formidable youth constituency. His charismatic
+    wife, Zahra Rahnavard, electrified the female vote and won the hearts and minds
+    of women voters who flooded their campaign rallies. In the past two weeks, Moussavi''s
+    campaign gained momentum. There was increasing evidence that the tide was turning
+    and that women and young voters would tip the balance of power his way, if they
+    turned out to vote in large numbers. Some important facts: There are 46 million
+    eligible voters in Iran, half of whom are women. In 1997, more than 60 percent
+    of the votes that brought moderate Mohammad Khatami to power were cast by women,
+    and in 2000, women voters were instrumental in giving reformists a sweeping majority
+    in the Parliament. Promising greater individual freedoms to youths was instrumental
+    in the two landslide victories by Khatami in 1997 and 2001. Surely, if the turnout
+    was 85 percent as the Interior Ministry said, Moussavi should have done much better
+    than the mere 33.8 percent he supposedly received. According to many independent
+    media reports from all over Iran, women and young voters turned out in record
+    numbers, especially in cities where Moussavi is very popular. That should have
+    given Moussavi a comfortable lead over the incumbent. Multiple irregularities
+    were reported, including the fact that Moussavi supposedly lost the vote in his
+    home province. There is an alarming discrepancy between the final results and
+    the voting patterns of the Iranian electorate over more than a decade. Lack of
+    transparency in the vote count has reinforced Iranians'' suspicion. The weight
+    of evidence is at odds with the final outcome given by the Interior Ministry.
+    Before Moussavi formally appealed the election result, supreme leader Khamenei
+    closed the door for any possible compromise. In a message on state TV, he urged
+    the nation to unite behind Ahmadinejad, calling the result a "divine assessment."
+    Yet the Guardian Council, not Khamenei, is the authority that either ratifies
+    or annuls the results. It is refreshing that Khamenei has finally ordered an investigation
+    into allegations of ballot fraud. It is a good start. A more reassuring intiative
+    would be for the Guardian Council to order a full recount with the presence of
+    independent observers. That would go a long way to putting to rest Iranians''
+    concerns. In the meantime, trying to divert attention from the mess at home, Khamenei
+    and Ahmadinejad have blamed external "enemies" and "foreign media" for instigating
+    a "full-fledged fight against our people." The truth is that the crisis is internal
+    and has nothing to do with foreign media or the West. The Obama administration
+    has done the right thing by keeping a low profile and not actively interfering
+    in Iran''s unfolding domestic crisis. Unlike his predecessor, Obama has defused
+    the minefield of relations between Washington and Tehran, shifting the focus of
+    Iranians to their own society. But the disputed result shows that the ultraconservative
+    mullahs are not only out of touch with a plurality of their citizens but also
+    with reality. Their conduct reflects a deeper crisis of self-confidence and fear
+    of the future. Has the Islamic revolution run out of ideological steam? If the
+    mullahs fear Moussavi, a loyalist, they must be scared of their shadows and uncertain
+    about their authority and power. That speaks volumes about where the Islamic Republic
+    is and where it is heading. The mullahs are swimming against the dominant current
+    of Iranian society. In the next four years, Iran will likely be engulfed in social
+    and political turmoil unless the electoral crisis is resolved in a transparent
+    manner. The opinions expressed in this commentary are solely those of Fawaz Gerges.'
+  sentences:
+  - 'Celtic defeat rivals Rangers 2-0 to win Scottish League Cup final at Hampden
+    .
+
+    Extra-time goals by Darren O''Dea and Aiden McGeady secure cup for Celtic .
+
+    The result will give Celtic a boost as they battle with Rangers for Scottish title
+    .'
+  - 'Rare species of freshwater dolphins found in Bangladesh''s waterlogged jungles
+    .
+
+    Fears Irrawaddy had dwindled in number to just a few hundred .
+
+    However, researchers have now counted almost 6,000 .'
+  - 'Fawaz Gerges: Iran''s ruling mullahs forfeited their public support in the election
+    .
+
+    Gerges: Ruling mullahs are out of step with women and young voters .
+
+    He says hardliners are swimming against the current of Iranian society .'
+- source_sentence: '(CNN) -- Eight Florida teenagers -- six of them girls -- will
+    be tried as adults and could be sentenced to life in prison for their alleged
+    roles in the videotaped beating of another teen, the state attorney''s office
+    said Thursday. The teenagers seen in a video assaulting a 16-year-old could face
+    life in prison. The suspects, who range in age from 14 to 18, all face charges
+    of kidnapping, which is a first-degree felony, and battery, said Chip Thullbery,
+    a spokesman for the Polk County state attorney. Three of them are also charged
+    with tampering with a witness. Everyone involved in the case was under a gag order
+    imposed by a judge. The only attorney for the teens who has been publicly identified
+    did not return calls from CNN, and his assistant cited the gag order as the reason.
+    The teens are scheduled for their first appearance in court Friday. The video
+    shows a brutal scene: The 16-year-old victim is punched, kneed and slapped by
+    other girls. She huddles in the fetal position, or stands and screams at her attackers,
+    but the assault continues. Authorities say the eight teens said they were retaliating
+    for insults posted on the Internet by the attack victim. Polk County Sheriff Grady
+    Judd called the March 30 attack "animalistic." "I''ve been involved in law enforcement
+    for 35 years, and I''ve seen a lot of extremely violent events, but I''ve never
+    seen children, 14 to 18 years of age, engage in this conduct for a 30-minute period
+    of time and then make these video clips," he said. Police say the teens planned
+    to post the video on YouTube.  Watch the disturbing video » . The victim, a 16-year-old
+    from Lakeland, Florida, was hospitalized, and still has blurred vision, hearing
+    loss, and a swollen face, her mother told CNN on Wednesday. The video shows only
+    girls doing the beating; Judd said the boys acted as lookouts. The idea of girls
+    administering a vicious beating so they can post the video online may seem shocking,
+    but it''s becoming an increasingly common scenario, according to experts and news
+    reports.  Watch why more teens are putting fights online » . A search for "girl
+    fight" on YouTube gets thousands of results, and a suggestion to also try "girl
+    fight at school, boy girl fight" and other search terms. There''s at least one
+    Web site devoted exclusively to videos of girls fighting. In 2003, 25 percent
+    of high school girls said they had been in a physical fight in the past year,
+    according to a survey by the Centers for Disease Control and Prevention. (The
+    figure for boys was 40.5 percent.) A Justice Department report released in 2006
+    showed that by age 17, 21 percent of girls said they had assaulted someone with
+    the intent to cause serious harm. Frank Green is executive director of Keys to
+    Safer Schools, a group that studies and tries to prevent school violence. He said
+    he''s not sure whether girls have actually become more violent, or whether there''s
+    just more awareness of their fights. "In one respect, girls have always been more
+    vicious than boys," Green said. "Their violence is of a personal nature." He said
+    boys usually have some focus and a concrete goal when they fight. "But girls want
+    to cause pain and make the other girl feel bad," he said. Judd, the Polk County
+    sheriff, said an important part of the plan in the Lakeland attack was to post
+    the video of the beating on YouTube to humiliate and embarrass the victim. "It''s
+    the next stage of cyberbullying," psychologist Susan Lipkins said. "They want
+    to show what they''re doing." "Our kids are being peer pressured, in another sense
+    of a trend, to put these shock videos out there at other peoples'' expense," said
+    Talisa Lindsay, the victim''s mother. "And I hope that it doesn''t come to the
+    point where there''s more people''s lives that are being affected by having to
+    take a beating for entertainment, or possibly being killed."  Watch mother describe
+    how the victim is doing » . The suspects didn''t have a chance to post the video
+    online before police moved in and seized it, Judd said. The Sheriff''s Department
+    made it public, and it wound up on YouTube anyway. Judd recognizes the irony.
+    "In a perverted sense, we were feeding into exactly what the kids wanted," he
+    said. "But according to Florida law, [the video] is public record, and it''s going
+    to be in the public domain whether we agree with that or not." Judd said the suspects
+    showed no remorse when they were arrested and booked. "They were laughing and
+    joking about, ''I guess we won''t get to go to the beach during spring break.''
+    And one ... asked whether she could go to cheerleading practice," he said. Lipkins,
+    the psychologist, says there''s a "disconnect between their actions and their
+    thoughts." "They think the entire society is doing it, and they think it''s funny.
+    So they put it on YouTube. And I don''t think they expect kids to get really hurt,
+    and they also don''t expect to get really caught." E-mail to a friend . CNN''s
+    Rich Phillips contributed to this report.'
+  sentences:
+  - 'Between 4 and 6 percent of the U.S. population suffers from SAD .
+
+    Light therapy, psychotherapy, and medications are treatment options .
+
+    Recent research indicates genetic component to the condition .'
+  - 'Cornelia Wallace was in her late 60s .
+
+    She was with Wallace when would-be assassin shot him in 1972 .
+
+    "She served as first lady during a very turbulent time," Gov. Bob Riley says .'
+  - 'Eight Florida teens to be tried as adults in videotaped beating case .
+
+    Video shows 16-year-old girl punched by other girls .
+
+    21 percent of girls age 17 say they''ve assaulted someone, the Justice Dept. reports
+    .
+
+    The teens have "disconnect" between thoughts and actions, psychologist says .'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/paraphrase-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L6-v2) <!-- at revision c9a2bfebc254878aee8c3aca9e6844d5bbb102d1 -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **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': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 384, '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})
+)
+```
+
+## 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("aasifali4813/bert-summarizer")
+# Run inference
+sentences = [
+    '(CNN) -- Eight Florida teenagers -- six of them girls -- will be tried as adults and could be sentenced to life in prison for their alleged roles in the videotaped beating of another teen, the state attorney\'s office said Thursday. The teenagers seen in a video assaulting a 16-year-old could face life in prison. The suspects, who range in age from 14 to 18, all face charges of kidnapping, which is a first-degree felony, and battery, said Chip Thullbery, a spokesman for the Polk County state attorney. Three of them are also charged with tampering with a witness. Everyone involved in the case was under a gag order imposed by a judge. The only attorney for the teens who has been publicly identified did not return calls from CNN, and his assistant cited the gag order as the reason. The teens are scheduled for their first appearance in court Friday. The video shows a brutal scene: The 16-year-old victim is punched, kneed and slapped by other girls. She huddles in the fetal position, or stands and screams at her attackers, but the assault continues. Authorities say the eight teens said they were retaliating for insults posted on the Internet by the attack victim. Polk County Sheriff Grady Judd called the March 30 attack "animalistic." "I\'ve been involved in law enforcement for 35 years, and I\'ve seen a lot of extremely violent events, but I\'ve never seen children, 14 to 18 years of age, engage in this conduct for a 30-minute period of time and then make these video clips," he said. Police say the teens planned to post the video on YouTube.  Watch the disturbing video » . The victim, a 16-year-old from Lakeland, Florida, was hospitalized, and still has blurred vision, hearing loss, and a swollen face, her mother told CNN on Wednesday. The video shows only girls doing the beating; Judd said the boys acted as lookouts. The idea of girls administering a vicious beating so they can post the video online may seem shocking, but it\'s becoming an increasingly common scenario, according to experts and news reports.  Watch why more teens are putting fights online » . A search for "girl fight" on YouTube gets thousands of results, and a suggestion to also try "girl fight at school, boy girl fight" and other search terms. There\'s at least one Web site devoted exclusively to videos of girls fighting. In 2003, 25 percent of high school girls said they had been in a physical fight in the past year, according to a survey by the Centers for Disease Control and Prevention. (The figure for boys was 40.5 percent.) A Justice Department report released in 2006 showed that by age 17, 21 percent of girls said they had assaulted someone with the intent to cause serious harm. Frank Green is executive director of Keys to Safer Schools, a group that studies and tries to prevent school violence. He said he\'s not sure whether girls have actually become more violent, or whether there\'s just more awareness of their fights. "In one respect, girls have always been more vicious than boys," Green said. "Their violence is of a personal nature." He said boys usually have some focus and a concrete goal when they fight. "But girls want to cause pain and make the other girl feel bad," he said. Judd, the Polk County sheriff, said an important part of the plan in the Lakeland attack was to post the video of the beating on YouTube to humiliate and embarrass the victim. "It\'s the next stage of cyberbullying," psychologist Susan Lipkins said. "They want to show what they\'re doing." "Our kids are being peer pressured, in another sense of a trend, to put these shock videos out there at other peoples\' expense," said Talisa Lindsay, the victim\'s mother. "And I hope that it doesn\'t come to the point where there\'s more people\'s lives that are being affected by having to take a beating for entertainment, or possibly being killed."  Watch mother describe how the victim is doing » . The suspects didn\'t have a chance to post the video online before police moved in and seized it, Judd said. The Sheriff\'s Department made it public, and it wound up on YouTube anyway. Judd recognizes the irony. "In a perverted sense, we were feeding into exactly what the kids wanted," he said. "But according to Florida law, [the video] is public record, and it\'s going to be in the public domain whether we agree with that or not." Judd said the suspects showed no remorse when they were arrested and booked. "They were laughing and joking about, \'I guess we won\'t get to go to the beach during spring break.\' And one ... asked whether she could go to cheerleading practice," he said. Lipkins, the psychologist, says there\'s a "disconnect between their actions and their thoughts." "They think the entire society is doing it, and they think it\'s funny. So they put it on YouTube. And I don\'t think they expect kids to get really hurt, and they also don\'t expect to get really caught." E-mail to a friend . CNN\'s Rich Phillips contributed to this report.',
+    'Eight Florida teens to be tried as adults in videotaped beating case .\nVideo shows 16-year-old girl punched by other girls .\n21 percent of girls age 17 say they\'ve assaulted someone, the Justice Dept. reports .\nThe teens have "disconnect" between thoughts and actions, psychologist says .',
+    'Cornelia Wallace was in her late 60s .\nShe was with Wallace when would-be assassin shot him in 1972 .\n"She served as first lady during a very turbulent time," Gov. Bob Riley says .',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.7511, 0.1292],
+#         [0.7511, 1.0000, 0.1549],
+#         [0.1292, 0.1549, 1.0000]])
+```
+
+<!--
+### 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 Dataset
+
+#### Unnamed Dataset
+
+* Size: 5,000 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                           | sentence_1                                                                         |
+  |:--------|:-------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                             |
+  | details | <ul><li>min: 29 tokens</li><li>mean: 127.89 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 26 tokens</li><li>mean: 56.37 tokens</li><li>max: 93 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | sentence_1                                                                                                                                                                                                                                                                                                               |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>(CNN) -- It may take a lot of frequent-flier miles, a penchant for cold places, a tolerance of taxes and regular doses of chocolate, but happiness could be within reach. However, it's not where most people might expect. Journalist Eric Weiner says he wanted to explore the relationship between place and happiness. Just ask Eric Weiner, who made it his mission to find the most content places around the globe, uncovering lots of surprises along the way. Hungering for a tropical paradise? A warm climate doesn't necessarily make a happy nation, Weiner said. Thinking of moving to a wealthy state? Money can degrade happiness, he found. Weiner, who wrote the book, "The Geography of Bliss: One Grump's Search for the Happiest Places in the World," began his quest for very personal reasons. "I'm an unhappy person, so it's kind of what prompts a hungry person to search for food," he said. Weiner spent 10 years as a foreign correspondent for National Public Radio, a job that took him to some of the...</code> | <code>Journalist spent a year looking for the world's happiest countries .<br>Eric Weiner: Bhutan is probably the closest thing on Earth to Shangri-La .<br>He marvels at the creativity and "coziness" of Iceland .<br>Self-described "grump:" chocolate contributes to happiness in Switzerland .</code>               |
+  | <code>(CNN) -- Hamburg have put one foot in the UEFA Cup final after a header from Germany winger Piotr Trochowski proved enough to give them a 1-0 win at Bundesliga rivals Werder Bremen in the first leg of their semifinal. Piotr Trochowski celebrates the only goal as Hamburg took a major step towards the UEFA Cup final. Martin Jol's side scored the only goal of a pulsating match in the 38th minute when Trochowski, the smallest player on the pitch, rose superbly at the back post to head Guy Demel's right-wing cross past goalkeeper Tim Wiese. Both side had countless half-chances to score but Hamburg wasted the best of them on the hour mark when Bayern Munich-bound striker Ivica Olic broke through in acres of space, but fired his shot straight at Wiese. Hamburg's victory puts them on line for their first European final since 1983, when they beat Juventus 1-0 to win the European Cup. This was the second of four matches in quick succession between the north Germany neighbors -- who met each othe...</code> | <code>Hamburg in line for first European final since 1983 after defeating Werder 1-0 .<br>Winger Piotr Trochowski heads in the only goal of their UEFA Cup semifinal .<br>Eventual winners will face Shakhtar Donetsk or Dynamo Kiev in Istanbul final .</code>                                                          |
+  | <code>(CNET) -- Suleman Ali cashed out just in time. Suleman Ali sold Esgut, his portfolio of Facebook applications, for seven figures in April. The 26-year-old, a former Microsoft employee who helped put together the Windows Home Server product, founded a company called Esgut within months of the debut of Facebook's developer platform in May 2007. Esgut is a portfolio of Facebook applications, and a few of them, like Superlatives and Entourage, became genuine viral hits. In April, Ali sold the 12-employee Esgut to the Social Gaming Network, a Silicon Valley company backed by the likes of Bezos Expeditions, the Founders Fund, and Greylock Partners. He said the price was in the seven figures. But Ali is the first to acknowledge that for upstart social-platform developers, hailed just months ago as the Valley's hottest breed of bright young things, the condition has taken a significant turn for the worse. "Most people are not counting on anything," the lanky and bespectacled Ali said over lunc...</code> | <code>Suleman Ali sold Esgut, his tech startup, for seven figures in April .<br>Esgut is a portfolio of Facebook applications; a few of them became big viral hits .<br>Suleman "started building Facebook apps just out of restlessness"<br>He sold his company just before the social-platform craze subsided .</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 1
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: None
+- `warmup_ratio`: None
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `enable_jit_checkpoint`: False
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `use_cpu`: False
+- `seed`: 42
+- `data_seed`: None
+- `bf16`: False
+- `fp16`: False
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: -1
+- `ddp_backend`: None
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `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_fused
+- `optim_args`: None
+- `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
+- `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_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `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
+- `use_cache`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Framework Versions
+- Python: 3.12.13
+- Sentence Transformers: 5.3.0
+- Transformers: 5.0.0
+- PyTorch: 2.10.0+cu128
+- Accelerate: 1.13.0
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{oord2019representationlearningcontrastivepredictive,
+      title={Representation Learning with Contrastive Predictive Coding},
+      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
+      year={2019},
+      eprint={1807.03748},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/1807.03748},
+}
+```
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "5.0.0",
+    "pytorch": "2.10.0+cu128"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cdf86a4d878f88e6f568ff78dc5e6254912494d0d04265d09bfc83c33fef65
+size 90864176

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 128,
+    "do_lower_case": false
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}