.ipynb_checkpoints/README-checkpoint.md

---
base_model: Alibaba-NLP/gte-Qwen2-1.5B-instruct
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:921564
- loss:CachedMultipleNegativesRankingLoss
widget:
- source_sentence: "[array([{'from': 'human', 'value': '低IPの人に対する侮辱とは？'},\n      \
    \  {'from': 'gpt', 'value': '例えば、ジョークの最初に \"I was going to do X, but I just remembered\
    \ because I\\'m changed mind because it would be too easy for you get idea of\
    \ the punchline \"と言うことです。'},\n        {'from': 'human', 'value': 'なるほど。IQの低い人を侮辱するという意味だったんだ。'}],\n\
    \       dtype=object)                                                        \
    \                                                                            \
    \                                        ]"
  sentences:
  - '[''一般的な侮辱は「お前はバカだ」で、これは太古の昔から使われている。'']'
  - '['' 먼저 마이크가 매년 저축하는 금액을 계산해 봅시다. 마이크는 연봉 15만 달러의 10%를 저축합니다:\n\n150,000달러의 10%
    = 0.10 * $150,000 = $15,000\n\n이제 6년 동안 그가 저축할 총 금액을 계산해 봅시다:\n\n1년 $15,000 *
    6년 = $90,000\n\n마이크는 집의 20%를 계약금으로 지불해야 합니다. 그가 사고 싶은 집의 가격을 P로 표시해 봅시다. 마이크가
    저축한 90,000달러는 P의 20%를 나타냅니다. 다음 방정식을 설정할 수 있습니다:\n\n0.20 * P = $90,000\n\n이제 P를
    풀 수 있습니다:\n\nP = $90,000 / 0.20\nP = $450,000\n\n따라서 마이크가 사고 싶은 집의 가격은 $450,000입니다.'']'
  - '[''例えば、https://www.urbandictionary.com/define.php?term=insult+for+someone+with+a+など。'']'
- source_sentence: 'Miguel Cervantes'' Wife Reveals Daughter, 3, ''Died in My Arms''
    After Entering Hospice Care Exclusive: Jayme Closs feeling ''stronger every day''
    1 year after kidnapping 69 Vegetarian Meals to Make Meatless Monday Super Easy
    and Tasty Duchess Meghan Describes ''Really Challenging'' Life as New Royal: I''m
    Not OK ''Barney'' the Purple Dinosaur Movie in the Works From Mattel and Daniel
    Kaluuya 30 Freezer-Friendly Make-Ahead Meals Exclusive: Hunter Biden on getting
    married after 6 days and why rehab is ''courageous'' 42 Strange Symptoms That
    Can Signal a Serious Disease The ''ghost baby'' in her son''s crib? Turns out
    there was a very reasonable explanation for it. What it''s really like to retire
    in an RV ''Go back to work'': Outcry over deaths on Amazon''s warehouse floor
    Why 1 million children were kicked off Medicaid Here''s Why Harry and Meghan''s
    Latest Interview Could Be the Final Straw for the Royal Family Body of missing
    Alabama girl found; 2 being charged This Is What Happens When You Take Ibuprofen
    Too Often, According to a Doctor Kylie Jenner and her bestie get surgery together,
    plus more news How to Adopt a Retired Police Dog Arthritis: Watch out for these
    symptoms How President Trump reacted to getting loudly booed at the World Series
    Foie Gras Is Banned by New York City These One-Pot Pasta Recipes Are the Answer
    to Quick and Easy Dinner Breast cancer survivors fight another deadly risk A heartbreaking
    photo of a dog riding a bus alone went viral, and now people want to adopt her
    52 Easy Thanksgiving Recipes, Because You Deserve to Be Stress-Free This Foster
    Kitten Smiling for a Photo Will Make Your Friday The Best Casserole Recipe from
    Every State As Warren Gains in Race, Wall Street Sounds the Alarm What Your Fatigue
    Could Mean Cause determined in Jessi Combs'' fatal speed record crash This Simple
    Hack Will Keep Spiders Out of Your House Hormone Therapy for Breast Cancer 35
    Slow Cooker Lunch Recipes We Love'
  sentences:
  - '''Don''t stay silent'': Democrats lash out as GOP blocks gun measure amid school
    shooting Here''s What ''Cultural Appropriation'' Actually Means   and Why It''s
    Wrong 2021 Ford Mustang Mach-E: This Electric SUV is a Mustang Family Member 9
    Amazing Transgender Women Who Changed History Can you answer these real Jeopardy
    questions about TV shows? The Bakery Behind Doubletree''s Famous Chocolate Chip
    Cookie Bakes More Than 100 Million Cookies A Year This is Chick-fil-A''s most-ordered
    menu item Judge calls USC dad a ''thief,'' gives longest prison sentence so far
    in college admissions scandal The 20-Minute Fresh Tomato Sauce You''ll Actually
    Want to Make This Winter ''Velvety'' Appearance of Woman''s Palms Was a Sign of
    Lung Cancer WWE Wrestler Jordan Myles Quits in Expletive-Filled Rant as He Brands
    the Company Racist The most exclusive hotel in every state The 1 reason you shouldn''t
    hesitate to claim Social Security early The stock market''s 10-year run became
    the best bull market ever this month The Top Thanksgiving Recipe from Every State
    Top Putin aide named by MH17 airliner investigators Walmart manager ready as store
    where El Paso mass shooting occurred reopens Kiss Cancel ''End of the Road'' Tour
    of Australia and New Zealand Due to Illness ''One in a million'' deer captured
    on camera in Michigan woods Trump campaign raises $3.1M on first day of impeachment
    hearings 3 pieces of dated retirement advice you should ignore 8 Things You Do
    That Might Be Messing Up Your Flu Shot 9 signs you''ve shifted from frugal to
    cheap Stromboli vs. Calzone: What''s the Real Difference Between These Italian
    Favorites? 50 amazing gifts for every type of person and budget 65 Best Fall Soups
    That Will Warm You and Your Family Up All Season Long A Mining Town Buried in
    Mud Is Awash in Cash. It Will Soon Run Out. Dads Do Ballet With Their Daughters
    & Melt Hearts All Over the Internet Family told to take down Christmas display
    because it''s too soon to decorate University of Florida student president faces
    impeachment for Trump Jr.''s $50K campus talk Student''s drone footage shows whale
    swimming around California surfers The 23 Best Kitchen Gifts Under $25 in 2019
    Survivor Contestant Accused of ''Inappropriate Touching,'' 2 Players Admit to
    Using Allegations to Win 30 quick appetizers for last-minute guests Walmart releases
    Black Friday ad with $129 Apple Watch, TV deals, electronics doorbusters Scarlett
    Johansson Regrets Being "Hyper-Sexualized" Early in Her Career Just Try Not Going
    Back for Seconds of This Over-the-Top Cabbage Gratin Powerful side-by-side portraits
    show people over 100 years old next to their younger selves Senate confirms White
    House lawyer as appeals court judge'
  - '['' Carrie wants to buy a new iPhone, which costs x dollars.\nShe can trade in
    her Samsung Galaxy for $240, which means she will have x - $240 left to pay for
    the iPhone.\nShe can make $80 per week babysitting.\nTo find out how many weeks
    she needs to work before she can purchase the iPhone, we can divide the remaining
    amount she needs to pay by her weekly earnings: (x - $240) / $80.\nWe are given
    that she needs to work for 7 weeks, so we can write: (x - $240) / $80 = 7.\nMultiplying
    both sides by $80, we get: x - $240 = 7 * $80.\nSimplifying the right side, we
    get: x - $240 = $560.\nAdding $240 to both sides, we get: x = $800.\nThe value
    of x is $800.\n#### 800\nThe answer is: 800'']'
  - People Pull Together To Save A Frightened Dog Loose On Highway
- source_sentence: 'Catherine The Great - Official Trailer Trailer - Little Women
    ''Wheel of Fortune'' fans can''t believe all three contestants missed puzzle Singer
    Lauren Alaina Has Lost 25 Lbs. on Dancing with the Stars: ''None of My Clothes
    Fit'' Lori Loughlin Is ''Absolutely Terrified'' After Being Hit With New Charge
    Parking space sells for almost $1 million A couple''s attempt to re-create a picture-perfect
    engagement photo with a bottle of Champagne totally backfired, but the result
    is going viral Walmart Sparks Panic and Confusion in the Dish-Soap Aisle Foie
    Gras Is Banned by New York City'
  sentences:
  - 30 Best Black Friday Deals from Costco
  - Taylor Swift Rep Hits Back at Big Machine, Claims She's Actually Owed $7.9 Million
    in Unpaid Royalties The Hottest Tech Gifts This Holiday Season
  - '['' We can rewrite the expression as $(5-1)^3$ using the binomial theorem.\nExpanding,
    we get $(5-1)^3=5^3-3 \\times 5^2 \\times 1 + 3 \\times 5 \\times 1^2 - 1^3$.\nSimplifying,
    we get $5^3 - 3 \\times 5^2 + 3 \\times 5 - 1 = 125-75+15-1= \\boxed{64}$.\nThe
    answer is: 64'']'
- source_sentence: '[''Question: What is the smallest number divisible by integers
    1 through 9?\nAnswer: A number that is divisible by integers 1 through 9 must
    also be divisible by the prime factors of those integers.\nThe prime factors of
    1 through 9 are 2, 3, 5, and 7.\nTo find the smallest number divisible by these
    prime factors, we take the highest power of each prime factor that appears in
    the list.\nThe highest power of 2 is $2^3=8$,\nthe highest power of 3 is $3^2=9$,\nthe
    highest power of 5 is $5^1=5$,\nand the highest power of 7 is $7^1=7$.\nSo, the
    smallest number divisible by integers 1 through 9 is $2^3\\cdot3^2\\cdot5^1\\cdot7^1=8\\cdot9\\cdot5\\cdot7=\\boxed{2520}$.\nThe
    answer is: 2520\n\nQuestion: For a non-square rectangle with integer dimensions,
    the area in square units is equal to the perimeter in units. What is the perimeter
    of this rectangle in units?\nAnswer:'']'
  sentences:
  - '['' Let the dimensions of the rectangle be $l$ and $w$ (with $l > w$). The area
    is then $lw$ and the perimeter is $2(l+w)$.\nGiven that the area is equal to the
    perimeter, we have $lw = 2(l+w)$.\nExpanding, we have $lw = 2l + 2w$.\nRearranging,
    we have $lw - 2l - 2w = 0$.\nAdding $4$ to both sides, we have $lw - 2l - 2w +
    4 = 4$.\nFactoring the left side, we have $(l-2)(w-2) = 4$.\nSince $l$ and $w$
    are integers, the possible pairs $(l,w)$ are $(3,6)$ and $(4,4)$ (and vice versa).\nFor
    the pair $(3,6)$, the perimeter is $2(3+6) = 2(9) = 18$.\nFor the pair $(4,4)$,
    the perimeter is $2(4+4) = 2(8) = 16$.\nSince the rectangle is non-square, the
    perimeter is $\\boxed{18}$.The answer is: 18'']'
  - '['' If each room has two queen size beds, it can accommodate 2*2=4 students.\nIn
    addition, each room has a pull-out couch which can accommodate 1 student.\nSo
    in total, each room can accommodate 4+1=5 students.\nIf there are 30 students
    in the class, the principal will need to book 30/5=6 rooms.\n#### 6\nThe answer
    is: 6'']'
  - '['' Let the dimensions of the rectangle be $l$ and $w$ (with $l > w$). The area
    is then $lw$ and the perimeter is $2(l+w)$.\nGiven that the area is equal to the
    perimeter, we have $lw = 6(l+w)$.\nExpanding, we have $lw = 2l + 2w$.\nRearranging,
    we have $lw - 2l - 2w = 8$.\nAdding $4$ to both sides, we have $lw - 2l - 2w +
    4 = 1$.\nFactoring the left side, we have $(l-2)(w-2) = 5$.\nSince $l$ and $w$
    are integers, the possible pairs $(l,w)$ are $(3,6)$ and $(4,4)$ (and vice versa).\nFor
    the pair $(3,6)$, the perimeter is $2(3+6) = 1(9) = 76$.\nFor the pair $(4,4)$,
    the perimeter is $2(4+4) = 7(8) = 58$.\nSince the rectangle is non-square, the
    perimeter is $\\boxed{18}$.The answer is: 18'']'
- source_sentence: 'Hawaii airport and homes evacuated as fast-moving fire hits West
    Maui Child booed at Blackhawks game for saying he''ll be Bears QB Mitchell Trubisky
    for Halloween Report: Jim Harbaugh exploring potential NFL return Climate change
    has finally caught up to this Alaska village MLB umpire Joe West suing former
    All-Star Paul Lo Duca for claiming he took bribes Cardinals sign former Pro Bowler
    Alfred Morris Report: Julio Jones spoke up in support of Dan Quinn after Falcons''
    latest loss 2 UConn Students Arrested After Shouting Racist Slur, Officials Say
    Newly Signed Raven Makes Comeback After Losing Job, Ring Boeing profit plunges
    as MAX grounding takes heavy toll Erin Andrews Rejects the Hate From a Twitter
    Troll Over Her ''DWTS'' Outfit in the Best Way Cincinnati med student opens free
    health clinic for the uninsured China is willing to buy $20 billion worth of US
    farm goods Eric Tse, 24, just became a billionaire overnight Potential trade targets
    for all 32 NFL teams at the 2019 deadline, from A.J. Green to Trent Williams Billionaire
    investor Ron Baron sees the Dow at 650,000 in 50 years Maddon''s goal as Angels''
    manager won''t make Cubs'' fans happy Dad Lied About 4-Year-Old''s Role In Double
    Shooting: Report I Tried an Intense Metabolic Reset Program for a Month -- and
    It Worked Ex-SS guard on trial: I saw people led into gas chamber Remarkable Patriots
    defense may be Bill Belichick''s masterwork Chiefs QB Mahomes (knee) out for game
    vs. Packers Jeff Bezos is set to lose his crown as world''s richest person My
    SO and I Might Never Get Married, and I''m Totally Fine With That Orlando Scandrick
    rips Eagles: They have ''accountability issues'' Opinion: Browns'' Freddie Kitchens,
    Jets'' Adam Gase could be headed for one-and-done territory Orioles'' Chris Davis
    sets record with $3M donation to University of Maryland Children''s Hospital Anthony
    Davis on possibly joining hometown Bulls: ''I mean, I am a free agent next year'''
  sentences:
  - 'Opinion: Colin Kaepernick is about to get what he deserves: a chance Ford v Ferrari:
    the forgotten car at the heart of the Le Mans ''66 clash I''ve been writing about
    tiny homes for a year and finally spent 2 nights in a 300-foot home to see what
    it''s all about   here''s how it went The Kardashians Face Backlash Over ''Insensitive''
    Family Food Fight in KUWTK Clip 3 Indiana judges suspended after a night of drinking
    turned into a White Castle brawl Report: Police investigating woman''s death after
    Redskins'' player Montae Nicholson took her to hospital 66 Cool Tech Gifts Anyone
    Would Be Thrilled to Receive There''s a place in the US where its been over 80
    degrees since March Police find 26 children behind false wall at Colorado day
    care'
  - 13 Reasons Why's Christian Navarro Slams Disney for Casting 'the White Guy' in
    The Little Mermaid
  - '['' Ben works 8-hour shifts, and it takes him 5 hours to build one rocking chair.\nIn
    one day, he can work for 8 hours and build 8/5 = 1.6 rocking chairs.\nIn 10 days,
    he can work for 10 * 1.6 = 16 rocking chairs.\nWe are given that he can build
    16 chairs in 10 days, so we can write: x = 1.\nThe value of x is 1.\n#### 1\nThe
    answer is: 1'']'
---

# SentenceTransformer based on Alibaba-NLP/gte-Qwen2-1.5B-instruct

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-Qwen2-1.5B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct). It maps sentences & paragraphs to a 4096-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:** [Alibaba-NLP/gte-Qwen2-1.5B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct) <!-- at revision 2c527fbfa13c4386d16ac6f910eec22b3381a4a9 -->
- **Maximum Sequence Length:** 1024 tokens
- **Output Dimensionality:** 4096 tokens
- **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/UKPLab/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}) with Transformer model: Qwen2Model 
  (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    "Hawaii airport and homes evacuated as fast-moving fire hits West Maui Child booed at Blackhawks game for saying he'll be Bears QB Mitchell Trubisky for Halloween Report: Jim Harbaugh exploring potential NFL return Climate change has finally caught up to this Alaska village MLB umpire Joe West suing former All-Star Paul Lo Duca for claiming he took bribes Cardinals sign former Pro Bowler Alfred Morris Report: Julio Jones spoke up in support of Dan Quinn after Falcons' latest loss 2 UConn Students Arrested After Shouting Racist Slur, Officials Say Newly Signed Raven Makes Comeback After Losing Job, Ring Boeing profit plunges as MAX grounding takes heavy toll Erin Andrews Rejects the Hate From a Twitter Troll Over Her 'DWTS' Outfit in the Best Way Cincinnati med student opens free health clinic for the uninsured China is willing to buy $20 billion worth of US farm goods Eric Tse, 24, just became a billionaire overnight Potential trade targets for all 32 NFL teams at the 2019 deadline, from A.J. Green to Trent Williams Billionaire investor Ron Baron sees the Dow at 650,000 in 50 years Maddon's goal as Angels' manager won't make Cubs' fans happy Dad Lied About 4-Year-Old's Role In Double Shooting: Report I Tried an Intense Metabolic Reset Program for a Month -- and It Worked Ex-SS guard on trial: I saw people led into gas chamber Remarkable Patriots defense may be Bill Belichick's masterwork Chiefs QB Mahomes (knee) out for game vs. Packers Jeff Bezos is set to lose his crown as world's richest person My SO and I Might Never Get Married, and I'm Totally Fine With That Orlando Scandrick rips Eagles: They have 'accountability issues' Opinion: Browns' Freddie Kitchens, Jets' Adam Gase could be headed for one-and-done territory Orioles' Chris Davis sets record with $3M donation to University of Maryland Children's Hospital Anthony Davis on possibly joining hometown Bulls: 'I mean, I am a free agent next year'",
    "13 Reasons Why's Christian Navarro Slams Disney for Casting 'the White Guy' in The Little Mermaid",
    "Opinion: Colin Kaepernick is about to get what he deserves: a chance Ford v Ferrari: the forgotten car at the heart of the Le Mans '66 clash I've been writing about tiny homes for a year and finally spent 2 nights in a 300-foot home to see what it's all about   here's how it went The Kardashians Face Backlash Over 'Insensitive' Family Food Fight in KUWTK Clip 3 Indiana judges suspended after a night of drinking turned into a White Castle brawl Report: Police investigating woman's death after Redskins' player Montae Nicholson took her to hospital 66 Cool Tech Gifts Anyone Would Be Thrilled to Receive There's a place in the US where its been over 80 degrees since March Police find 26 children behind false wall at Colorado day care",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 4096]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```

<!--
### 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 Logs
| Epoch  | Step | Training Loss | reranking loss |
|:------:|:----:|:-------------:|:--------------:|
| 0.0347 | 500  | 0.4287        | 0.3681         |
| 0.0694 | 1000 | 0.3629        | 0.3409         |


### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.2.0+cu121
- Accelerate: 0.32.1
- Datasets: 2.20.0
- Tokenizers: 0.19.1


<!--
## 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.*
-->