| --- |
| base_model: dunzhang/stella_en_1.5B_v5 |
| datasets: [] |
| language: [] |
| library_name: sentence-transformers |
| pipeline_tag: sentence-similarity |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - generated_from_trainer |
| - dataset_size:99000 |
| - loss:MultipleNegativesSymmetricRankingLoss |
| widget: |
| - source_sentence: 'Instruct: Given a web search query, retrieve relevant passages |
| that answer the query. |
| |
| Query: Glay' |
| sentences: |
| - The Theory of Good and Evil is a 1907 book about ethics by the English philosopher |
| Hastings Rashdall, in which the author expounds a theory he calls "ideal utilitarianism". |
| It has been seen as Rashdall's most important philosophical work. |
| - GLAY is a Japanese rock band , formed in Hakodate in 1988 . Glay primarily composes |
| songs in the rock and pop genres , but they have also arranged songs using elements |
| from a wide variety of genres , including punk , electronic , R&B , progressive |
| rock , folk , reggae , gospel , and ska . Originally a visual kei band , the group |
| slowly shifted to less dramatic attire through the years . As of 2008 , Glay had |
| sold an estimated 51 million records ; 28 million singles and 23 million albums |
| , making them one of the top ten best-selling artists of all time in Japan . |
| - Aashirwad is a 1968 Bollywood film , directed by Hrishikesh Mukherjee . The film |
| stars Ashok Kumar and Sanjeev Kumar . The film is notable for its inclusion |
| of a rap-like song performed by Ashok Kumar , `` Rail Gaadi '' . |
| - source_sentence: 'Instruct: Given a web search query, retrieve relevant passages |
| that answer the query. |
| |
| Query: Indexing does not work with index package' |
| sentences: |
| - 'I am trying to do indexing with the following code: \documentclass[a4paper]{article} \usepackage{index} \makeindex \newindex{aut}{adx}{and}{Name |
| Index} \begin{document} Hellow \index[aut]{FiRST} \printindex[aut] \end{document} Acccording |
| to documention of the `index` package it should work. But makeindex creates empty |
| `.idx` and `.ind`. If I run code like this: \documentclass[a4paper]{article} \usepackage{index} \makeindex \begin{document} Hellow |
| \index{FiRST} \printindex \end{document} It runs. But I need to have |
| user-defined index. Please help me with it. I''ve searched for several hours on |
| internet, but without success.' |
| - 'Body materials may include, but are not limited to, any of these materials:' |
| - Berberis aemulans is a shrub endemic to the region of Sichuan in southern China. |
| It grows there in thickets and on slopes at elevations of 2900-3200 m.Berberis |
| aemulans is a deciduous shrub up to 2 m tall, with spines along the branches. |
| Leaves are simple, elliptical to ovate, up to 4 cm long, lighter in color on the |
| underside because of a waxy layer. Flowers are in simple racemes of only a few |
| flowers. Berries egg-shaped, orange, up to 16 mm long. |
| - source_sentence: 'Instruct: Given a web search query, retrieve relevant passages |
| that answer the query. |
| |
| Query: Parodi''s hemispingus' |
| sentences: |
| - Another event dubbed a "Battle of the Sexes" took place during the 1998 Australian |
| Open[51] between Karsten Braasch and the Williams sisters. Venus and Serena Williams |
| had claimed that they could beat any male player ranked outside the world's top |
| 200, so Braasch, then ranked 203rd, challenged them both. Braasch was described |
| by one journalist as "a man whose training regime centered around a pack of cigarettes |
| and more than a couple bottles of ice cold lager".[52][51] The matches took place |
| on court number 12 in Melbourne Park,[53] after Braasch had finished a round of |
| golf and two shandies. He first took on Serena and after leading 5–0, beat her |
| 6–1. Venus then walked on court and again Braasch was victorious, this time winning |
| 6–2.[54] Braasch said afterwards, "500 and above, no chance". He added that he |
| had played like someone ranked 600th in order to keep the game "fun".[55] Braasch |
| said the big difference was that men can chase down shots much easier, and that |
| men put spin on the ball that the women can't handle. The Williams sisters adjusted |
| their claim to beating men outside the top 350.[51] |
| - The Parodi 's hemispingus ( Hemispingus parodii ) is a species of bird in the |
| family Thraupidae that is endemic to Peru . Its natural habitat is subtropical |
| or tropical moist montane forests . |
| - 'I need help because my Minecraft launcher doesn''t work... It''s been a long |
| time I haven''t played Minecraft and until now it worked nicely. But now that |
| I want to play on it again and I run the launcher, this appears (click images |
| to enlarge):  |
| At the bottom left of the screen the profile names keep loading (normally my username |
| appears in the box) and as you can see I am unable to click on the "Play" button. |
| I tried creating another profile but it doesn''t work because soon after they |
| ask to enter my Minecraft username and password. The password I entered disappears |
| and it keeps loading (I''ve tried waiting like, 30 minutes and it still doesn''t |
| work) so this is definitely not normal.  |
|   So basically I can''t play |
| on Minecraft anymore (version 1.7.9)... P.S. I use Windows 7.' |
| - source_sentence: 'Instruct: Given a web search query, retrieve relevant passages |
| that answer the query. |
| |
| Query: Mahabharata' |
| sentences: |
| - The epic employs the story within a story structure, otherwise known as frametales, |
| popular in many Indian religious and non-religious works. It is first recited |
| at Takshashila by the sage Vaiśampāyana,[12][13] a disciple of Vyāsa, to the King |
| Janamejaya who is the great-grandson of the Pāṇḍava prince Arjuna. The story is |
| then recited again by a professional storyteller named Ugraśrava Sauti, many years |
| later, to an assemblage of sages performing the 12-year sacrifice for the king |
| Saunaka Kulapati in the Naimiśa Forest. |
| - 'Guncati (Serbian Cyrillic: Гунцати) is a suburban settlement of Belgrade, the |
| capital of Serbia. It is located in the municipality of Barajevo.Guncati is located |
| west of the municipal seat of Barajevo, halfway between the Belgrade-Bar railway |
| and Ibarska magistrala (Highway of Ibar).It is a rural settlement with a steady |
| population growth: from 1,718 (Census 1991) to 2,102 (Census 2002).' |
| - Beck 's Brewery , also known as Brauerei Beck & Co. , is a brewery in the northern |
| German city of Bremen . In 2001 , Interbrew agreed to buy Brauerei Beck for 1.8 |
| billion euro ; at that time it was the fourth largest brewer in Germany . US manufacture |
| of Beck 's Brew has been based in St. Louis , Missouri , since early 2012 but |
| some customers have rebelled against the US market version . Since 2008 , it |
| has been owned by the Interbrew subsidiary of Anheuser-Busch InBev SA/NV . The |
| Beck 's Art Label Campaign has offered artists the opportunity to provide designs |
| to replace the brand 's label . It started in London in 1987 with Gilbert and |
| George . The artists created an art label , because Beck 's sponsored their retrospective |
| at the Hayward Gallery . The labels of the 2000 limited edition Beck 's bottles |
| were matching their exhibition poster . Other participants of the Art Label Campaign |
| are members of the loose group `` Young British Artists '' and nominees or winners |
| of the Turner Prize . Damien Hirst for example , designed a label for Beck 's |
| in 1995 , showing his famous spots . In 2000 , Tracey Emin created a label , which |
| shows herself , posing in a bathtub . Furthermore , Rachel Whiteread designed |
| a label in 1993 , presenting her artwork `` house '' , which was also financed |
| by Beck 's . The Art Label Campaign has also been parodied by Matthew Higgs , |
| who is a member of the British art collective `` Bank '' . In the Bank exhibition |
| `` The Charge of the Light Brigade '' in 1995 , he brewed a beer , called `` Kunstlerbrau |
| '' . In 2012 , Beck 's started giving young and independent musicians the opportunity |
| to design a label for the Beck 's bottle . Beck 's summer 2009 limited-edition |
| labels were designed by the musical groups Hard-Fi and Ladyhawke . |
| - source_sentence: 'Instruct: Given a web search query, retrieve relevant passages |
| that answer the query. |
|
|
| Query: Ahu A Umi Heiau' |
| sentences: |
| - The 1967 All-Ireland Intermediate Hurling Championship was the seventh staging |
| of the All-Ireland hurling championship. The championship ended on 17 September |
| 1967.Tipperary were the defending champions, however, they were defeated in the |
| provincial championship. London won the title after defeating Cork by 1-9 to 1-5 |
| in the final. |
| - 'The digit ratio is the ratio of the lengths of different digits or fingers typically |
| measured from the midpoint of bottom crease ( where the finger joins the hand |
| ) to the tip of the finger . It has been suggested by some scientists that the |
| ratio of two digits in particular , the 2nd ( index finger ) and 4th ( ring finger |
| ) , is affected by exposure to androgens , e.g. , testosterone while in the uterus |
| and that this 2D :4 D ratio can be considered a crude measure for prenatal androgen |
| exposure , with lower 2D :4 D ratios pointing to higher prenatal androgen exposure |
| . The 2D :4 D ratio is calculated by dividing the length of the index finger of |
| a given hand by the length of the ring finger of the same hand . A longer index |
| finger will result in a ratio higher than 1 , while a longer ring finger will |
| result in a ratio lower than 1 . The 2D :4 D digit ratio is sexually dimorphic |
| : although the second digit is typically shorter in both females and males , the |
| difference between the lengths of the two digits is greater in males than in females |
| . A number of studies have shown a correlation between the 2D :4 D digit ratio |
| and various physical and behavioral traits .' |
| - Ahu A ʻ Umi Heiau means "shrine at the temple of ʻ Umi" in the Hawaiian Language. |
| --- |
| |
| # SentenceTransformer based on dunzhang/stella_en_1.5B_v5 |
| |
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [dunzhang/stella_en_1.5B_v5](https://huggingface.co/dunzhang/stella_en_1.5B_v5). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. |
| |
| ## Model Details |
| |
| ### Model Description |
| - **Model Type:** Sentence Transformer |
| - **Base model:** [dunzhang/stella_en_1.5B_v5](https://huggingface.co/dunzhang/stella_en_1.5B_v5) <!-- at revision 129dc50d3ca5f0f5ee0ce8944f65a8553c0f26e0 --> |
| - **Maximum Sequence Length:** 8096 tokens |
| - **Output Dimensionality:** 1024 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': 8096, 'do_lower_case': False}) with Transformer model: Qwen2Model |
| (1): Pooling({'word_embedding_dimension': 1536, '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): Dense({'in_features': 1536, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'}) |
| ) |
| ``` |
| |
| ## 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 = [ |
| 'Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: Ahu A Umi Heiau', |
| 'Ahu A ʻ Umi Heiau means "shrine at the temple of ʻ Umi" in the Hawaiian Language.', |
| 'The digit ratio is the ratio of the lengths of different digits or fingers typically measured from the midpoint of bottom crease ( where the finger joins the hand ) to the tip of the finger . It has been suggested by some scientists that the ratio of two digits in particular , the 2nd ( index finger ) and 4th ( ring finger ) , is affected by exposure to androgens , e.g. , testosterone while in the uterus and that this 2D :4 D ratio can be considered a crude measure for prenatal androgen exposure , with lower 2D :4 D ratios pointing to higher prenatal androgen exposure . The 2D :4 D ratio is calculated by dividing the length of the index finger of a given hand by the length of the ring finger of the same hand . A longer index finger will result in a ratio higher than 1 , while a longer ring finger will result in a ratio lower than 1 . The 2D :4 D digit ratio is sexually dimorphic : although the second digit is typically shorter in both females and males , the difference between the lengths of the two digits is greater in males than in females . A number of studies have shown a correlation between the 2D :4 D digit ratio and various physical and behavioral traits .', |
| ] |
| embeddings = model.encode(sentences) |
| print(embeddings.shape) |
| # [3, 1024] |
| |
| # 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 Logs |
| | Epoch | Step | Training Loss | retrival loss | |
| |:------:|:----:|:-------------:|:-------------:| |
| | 0.6466 | 500 | 0.0424 | 0.0060 | |
| | 1.2932 | 1000 | 0.0073 | 0.0040 | |
| |
| |
| |
| <!-- |
| ## 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.* |
| --> |
