Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,773 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- loss:MultipleNegativesRankingLoss
+base_model: distilbert/distilroberta-base
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: She was buried in Breda .
+  sentences:
+  - Anna was buried in Breda .
+  - Jackson Township is a township found in Will County , Illinois .
+  - Saint-Genis-Pouilly is a commune in the Ain department in eastern France .
+- source_sentence: Have you never been mellow? No, I'm just a grumpy sumbitch
+  sentences:
+  - How many of you retards have ever had wooopi.? Not me... I'm saving myself...
+  - Has anyone heard of the marketing company Vector? If so what is the company about
+    and is it a good place to work?
+  - I want to make hearts on the computer too?!? How do i do it!!!!i tried doing alt
+    3 but i couldn't see my heart!!!Is that normal!!
+- source_sentence: Are there UFOs?
+  sentences:
+  - Who has seen aliens or UFOs?
+  - How do people become famous?
+  - How do I learn math?
+- source_sentence: The dog runs.
+  sentences:
+  - A dog running.
+  - A man eats a sandwich.
+  - The people are sitting.
+- source_sentence: guy on a bike
+  sentences:
+  - Man riding a bike
+  - A man cooks on a grill.
+  - The woman is indoors.
+pipeline_tag: sentence-similarity
+co2_eq_emissions:
+  emissions: 78.69029495412121
+  energy_consumed: 0.2024437614268031
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 0.601
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: SentenceTransformer based on distilbert/distilroberta-base
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8415424335219892
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.845236449663091
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8502275215819475
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.851659983857617
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8534543309306831
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8555429338051269
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6505488321872611
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6489555708500816
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8534543309306831
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8555429338051269
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.8105817065758533
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8144723448926713
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8225264118038157
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8131121443026537
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.825469313508584
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8164637881262432
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5910799174044387
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5760606722387962
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.825469313508584
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8164637881262432
+      name: Spearman Max
+---
+
+# SentenceTransformer based on distilbert/distilroberta-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli), [sentence-compression](https://huggingface.co/datasets/sentence-transformers/sentence-compression), [simple-wiki](https://huggingface.co/datasets/sentence-transformers/simple-wiki), [altlex](https://huggingface.co/datasets/sentence-transformers/altlex), [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates), [coco-captions](https://huggingface.co/datasets/sentence-transformers/coco-captions), [flickr30k-captions](https://huggingface.co/datasets/sentence-transformers/flickr30k-captions), [yahoo-answers](https://huggingface.co/datasets/sentence-transformers/yahoo-answers) and [stack-exchange](https://huggingface.co/datasets/sentence-transformers/stackexchange-duplicates) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) <!-- at revision fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
+    - [sentence-compression](https://huggingface.co/datasets/sentence-transformers/sentence-compression)
+    - [simple-wiki](https://huggingface.co/datasets/sentence-transformers/simple-wiki)
+    - [altlex](https://huggingface.co/datasets/sentence-transformers/altlex)
+    - [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
+    - [coco-captions](https://huggingface.co/datasets/sentence-transformers/coco-captions)
+    - [flickr30k-captions](https://huggingface.co/datasets/sentence-transformers/flickr30k-captions)
+    - [yahoo-answers](https://huggingface.co/datasets/sentence-transformers/yahoo-answers)
+    - [stack-exchange](https://huggingface.co/datasets/sentence-transformers/stackexchange-duplicates)
+- **Language:** en
+<!-- - **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': 128, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## 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("tomaarsen/distilroberta-base-paraphrases-multi")
+# Run inference
+sentences = [
+    'guy on a bike',
+    'Man riding a bike',
+    'A man cooks on a grill.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(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.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+* Dataset: `sts-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8415     |
+| **spearman_cosine** | **0.8452** |
+| pearson_manhattan   | 0.8502     |
+| spearman_manhattan  | 0.8517     |
+| pearson_euclidean   | 0.8535     |
+| spearman_euclidean  | 0.8555     |
+| pearson_dot         | 0.6505     |
+| spearman_dot        | 0.649      |
+| pearson_max         | 0.8535     |
+| spearman_max        | 0.8555     |
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8106     |
+| **spearman_cosine** | **0.8145** |
+| pearson_manhattan   | 0.8225     |
+| spearman_manhattan  | 0.8131     |
+| pearson_euclidean   | 0.8255     |
+| spearman_euclidean  | 0.8165     |
+| pearson_dot         | 0.5911     |
+| spearman_dot        | 0.5761     |
+| pearson_max         | 0.8255     |
+| spearman_max        | 0.8165     |
+
+<!--
+## 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
+
+#### all-nli
+
+* Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [cc6c526](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/cc6c526380e29912b5c6fa03682da4daf773c013)
+* Size: 557,850 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: 7 tokens</li><li>mean: 10.38 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.8 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.4 tokens</li><li>max: 50 tokens</li></ul> |
+* Samples:
+  | anchor                                                                     | positive                                         | negative                                                   |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>A person is at a diner, ordering an omelette.</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>The kids are frowning</code>                         |
+  | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code>             |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### sentence-compression
+
+* Dataset: [sentence-compression](https://huggingface.co/datasets/sentence-transformers/sentence-compression) at [605bc91](https://huggingface.co/datasets/sentence-transformers/sentence-compression/tree/605bc91d95631895ba25b6eda51a3cb596976c90)
+* Size: 180,000 training samples
+* Columns: <code>text</code> and <code>simplified</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text                                                                                | simplified                                                                        |
+  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                            |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 33.13 tokens</li><li>max: 126 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.13 tokens</li><li>max: 29 tokens</li></ul> |
+* Samples:
+  | text                                                                                                                                                                                                                                               | simplified                                             |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------|
+  | <code>The USHL completed an expansion draft on Monday as 10 players who were on the rosters of USHL teams during the 2009-10 season were selected by the League's two newest entries, the Muskegon Lumberjacks and Dubuque Fighting Saints.</code> | <code>USHL completes expansion draft</code>            |
+  | <code>Major League Baseball Commissioner Bud Selig will be speaking at St. Norbert College next month.</code>                                                                                                                                      | <code>Bud Selig to speak at St. Norbert College</code> |
+  | <code>It's fresh cherry time in Michigan and the best time to enjoy this delicious and nutritious fruit.</code>                                                                                                                                    | <code>It's cherry time</code>                          |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### simple-wiki
+
+* Dataset: [simple-wiki](https://huggingface.co/datasets/sentence-transformers/simple-wiki) at [60fd9b4](https://huggingface.co/datasets/sentence-transformers/simple-wiki/tree/60fd9b4680642ace0e2604cc2de44d376df419a7)
+* Size: 102,225 training samples
+* Columns: <code>text</code> and <code>simplified</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text                                                                               | simplified                                                                        |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 35.19 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 29.1 tokens</li><li>max: 128 tokens</li></ul> |
+* Samples:
+  | text                                                                                                                                                                                                                                                                                                                                                                                                                      | simplified                                                                                                                                                                                                                                                                                                                             |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>The greatest example has been in his present job ( then , Minister for Foreign Affairs ) , where he has perforce concentrated on Anglo-Irish relations and , in particular the North ( i.e. , Northern Ireland ) .</code>                                                                                                                                                                                           | <code>The greatest example has been in his present job ( then , Minister for Foreign Affairs ) , where he has perforce concentrated on Anglo-Irish relations and , in particular Northern Ireland ( .</code>                                                                                                                           |
+  | <code>His reputation rose further when opposition leaders under parliamentary privilege alleged that Taoiseach Charles Haughey , who in January 1982 had been Leader of the Opposition , had not merely rung the President 's Office but threatened to end the career of the army officer who took the call and who , on Hillery 's explicit instructions , had refused to put through the call to the President .</code> | <code>President Hillery refused to speak to any opposition party politicians , but when Charles Haughey , who was Leader of the Opposition , had rang the President 's Office he threatened to end the career of the army officer answered and refused on Hillery 's explicit orders to put the call through to the President .</code> |
+  | <code>He considered returning to medicine , perhaps moving with his wife , Maeve ( also a doctor ) to Africa .</code>                                                                                                                                                                                                                                                                                                     | <code>He thought about returning to medicine , perhaps moving with his wife , Maeve ( also a doctor ) to Africa .</code>                                                                                                                                                                                                               |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### altlex
+
+* Dataset: [altlex](https://huggingface.co/datasets/sentence-transformers/altlex) at [97eb209](https://huggingface.co/datasets/sentence-transformers/altlex/tree/97eb20963455c361d5a81c107c3596cff9e0cd82)
+* Size: 112,696 training samples
+* Columns: <code>text</code> and <code>simplified</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text                                                                              | simplified                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 31.8 tokens</li><li>max: 121 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 26.49 tokens</li><li>max: 114 tokens</li></ul> |
+* Samples:
+  | text                                                                                                                                                                                                                                                         | simplified                                                                                                                                                                                                                                                              |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>A set of 31 guns , cast 1729-1749 by the first master founder at the Royal Foundry , later the Royal Arsenal , Woolwich , were used to fire salutes until 1907 , often for Queen Victoria , who was a frequent visitor .</code>                        | <code>A set of 31 guns , cast 1729-1749 by the first master founder at the Royal Foundry , later the Royal Arsenal , Woolwich , were used to fire salutes until 1907 , often for Queen Victoria who was a frequent visitor .</code>                                     |
+  | <code>In 1929 , the building became vacant , and was given to Prince Edward , Prince of Wales , by his father , King George V . This became the Prince 's chief residence and was used extensively by him for entertaining and as a country retreat .</code> | <code>In 1929 , the building became vacant , and was given to Prince Edward , the Prince of Wales by his father , King George V . This became the Prince 's chief residence , and was used extensively by the Prince for entertaining and as a country retreat .</code> |
+  | <code>Additions included an octagon room in the north-east side , in which the King regularly had dinner .</code>                                                                                                                                            | <code>Additions included an octagon room in the North-East side , where the King regularly had dinner .</code>                                                                                                                                                          |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### quora-duplicates
+
+* Dataset: [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* 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: 13.72 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.5 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.56 tokens</li><li>max: 62 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>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### coco-captions
+
+* Dataset: [coco-captions](https://huggingface.co/datasets/sentence-transformers/coco-captions) at [bd26018](https://huggingface.co/datasets/sentence-transformers/coco-captions/tree/bd2601822b9af9a41656d678ffbd5c80d81e276a)
+* Size: 414,010 training samples
+* Columns: <code>caption1</code> and <code>caption2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | caption1                                                                           | caption2                                                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 13.65 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 13.65 tokens</li><li>max: 25 tokens</li></ul> |
+* Samples:
+  | caption1                                                                                   | caption2                                                                                   |
+  |:-------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------|
+  | <code>A clock that blends in with the wall hangs in a bathroom. </code>                    | <code>A very clean and well decorated empty bathroom</code>                                |
+  | <code>A very clean and well decorated empty bathroom</code>                                | <code>A bathroom with a border of butterflies and blue paint on the walls above it.</code> |
+  | <code>A bathroom with a border of butterflies and blue paint on the walls above it.</code> | <code>An angled view of a beautifully decorated bathroom.</code>                           |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### flickr30k-captions
+
+* Dataset: [flickr30k-captions](https://huggingface.co/datasets/sentence-transformers/flickr30k-captions) at [0ef0ce3](https://huggingface.co/datasets/sentence-transformers/flickr30k-captions/tree/0ef0ce31492fd8dc161ed483a40d3c4894f9a8c1)
+* Size: 158,881 training samples
+* Columns: <code>caption1</code> and <code>caption2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | caption1                                                                          | caption2                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 16.22 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.22 tokens</li><li>max: 60 tokens</li></ul> |
+* Samples:
+  | caption1                                                                                        | caption2                                                                                        |
+  |:------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|
+  | <code>Two men in green shirts are standing in a yard.</code>                                    | <code>Two young, White males are outside near many bushes.</code>                               |
+  | <code>Two young, White males are outside near many bushes.</code>                               | <code>Two young guys with shaggy hair look at their hands while hanging out in the yard.</code> |
+  | <code>Two young guys with shaggy hair look at their hands while hanging out in the yard.</code> | <code>A man in a blue shirt standing in a garden.</code>                                        |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### yahoo-answers
+
+* Dataset: [yahoo-answers](https://huggingface.co/datasets/sentence-transformers/yahoo-answers) at [93b3605](https://huggingface.co/datasets/sentence-transformers/yahoo-answers/tree/93b3605c508cf93e3666c9d3e34640b5fe62b507)
+* Size: 599,417 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: 12 tokens</li><li>mean: 52.48 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 83.5 tokens</li><li>max: 128 tokens</li></ul> |
+* Samples:
+  | question                                                                                                                                             | answer                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>why doesn't an optical mouse work on a glass table? or even on some surfaces?</code>                                                           | <code>why doesn't an optical mouse work on a glass table? Optical mice use an LED and a camera to rapidly capture images of the surface beneath the mouse.  The infomation from the camera is analyzed by a DSP (Digital Signal Processor) and used to detect imperfections in the underlying surface and determine motion. Some materials, such as glass, mirrors or other very shiny, uniform surfaces interfere with the ability of the DSP to accurately analyze the surface beneath the mouse.  \nSince glass is transparent and very uniform, the mouse is unable to pick up enough imperfections in the underlying surface to determine motion.  Mirrored surfaces are also a problem, since they constantly reflect back the same image, causing the DSP not to recognize motion properly. When the system is unable to see surface changes associated with movement, the mouse will not work properly.</code> |
+  | <code>What is the best off-road motorcycle trail ? long-distance trail throughout CA</code>                                                          | <code>What is the best off-road motorcycle trail ? i hear that the mojave road is amazing!<br />\nsearch for it online.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+  | <code>What is Trans Fat? How to reduce that? I heard that tras fat is bad for the body.  Why is that? Where can we find it in our daily food?</code> | <code>What is Trans Fat? How to reduce that? Trans fats occur in manufactured foods during the process of partial hydrogenation, when hydrogen gas is bubbled through vegetable oil to increase shelf life and stabilize the original polyunsatured oil. The resulting fat is similar to saturated fat, which raises "bad" LDL cholesterol and can lead to clogged arteries and heart disease. \nUntil very recently, food labels were not required to list trans fats, and this health risk remained hidden to consumers. In early July, FDA regulations changed, and food labels will soon begin identifying trans fat content in processed foods.</code>                                                                                                                                                                                                                                                            |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### stack-exchange
+
+* Dataset: [stack-exchange](https://huggingface.co/datasets/sentence-transformers/stackexchange-duplicates) at [1c9657a](https://huggingface.co/datasets/sentence-transformers/stackexchange-duplicates/tree/1c9657aec12d9e101667bb9593efcc623c4a68ff)
+* Size: 304,525 training samples
+* Columns: <code>title1</code> and <code>title2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | title1                                                                            | title2                                                                            |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 15.04 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.91 tokens</li><li>max: 80 tokens</li></ul> |
+* Samples:
+  | title1                                                                            | title2                                                       |
+  |:----------------------------------------------------------------------------------|:-------------------------------------------------------------|
+  | <code>what is the advantage of using the GPU rendering options in Android?</code> | <code>Can anyone explain all these Developer Options?</code> |
+  | <code>Blank video when converting uncompressed AVI files with ffmpeg</code>       | <code>FFmpeg lossy compression problems</code>               |
+  | <code>URL Rewriting of a query string in php</code>                               | <code>How to create friendly URL in php?</code>              |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: False
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_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`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `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
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: 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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: None
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:-----------------------:|:------------------------:|
+| 0.0140 | 100  | 3.739         | -                       | -                        |
+| 0.0279 | 200  | 1.1317        | -                       | -                        |
+| 0.0419 | 300  | 0.9645        | -                       | -                        |
+| 0.0558 | 400  | 0.9053        | -                       | -                        |
+| 0.0698 | 500  | 0.8889        | -                       | -                        |
+| 0.0838 | 600  | 0.8741        | -                       | -                        |
+| 0.0977 | 700  | 0.8329        | -                       | -                        |
+| 0.1117 | 800  | 0.8331        | -                       | -                        |
+| 0.1256 | 900  | 0.8241        | -                       | -                        |
+| 0.1396 | 1000 | 0.7829        | 0.8460                  | -                        |
+| 0.1535 | 1100 | 0.7871        | -                       | -                        |
+| 0.1675 | 1200 | 0.7521        | -                       | -                        |
+| 0.1815 | 1300 | 0.7905        | -                       | -                        |
+| 0.1954 | 1400 | 0.7531        | -                       | -                        |
+| 0.2094 | 1500 | 0.7677        | -                       | -                        |
+| 0.2233 | 1600 | 0.7745        | -                       | -                        |
+| 0.2373 | 1700 | 0.7651        | -                       | -                        |
+| 0.2513 | 1800 | 0.7712        | -                       | -                        |
+| 0.2652 | 1900 | 0.7476        | -                       | -                        |
+| 0.2792 | 2000 | 0.7814        | 0.8370                  | -                        |
+| 0.2931 | 2100 | 0.7536        | -                       | -                        |
+| 0.3071 | 2200 | 0.7689        | -                       | -                        |
+| 0.3210 | 2300 | 0.7656        | -                       | -                        |
+| 0.3350 | 2400 | 0.7672        | -                       | -                        |
+| 0.3490 | 2500 | 0.6921        | -                       | -                        |
+| 0.3629 | 2600 | 0.6778        | -                       | -                        |
+| 0.3769 | 2700 | 0.6844        | -                       | -                        |
+| 0.3908 | 2800 | 0.6907        | -                       | -                        |
+| 0.4048 | 2900 | 0.6881        | -                       | -                        |
+| 0.4188 | 3000 | 0.6815        | 0.8372                  | -                        |
+| 0.4327 | 3100 | 0.6869        | -                       | -                        |
+| 0.4467 | 3200 | 0.698         | -                       | -                        |
+| 0.4606 | 3300 | 0.6868        | -                       | -                        |
+| 0.4746 | 3400 | 0.7174        | -                       | -                        |
+| 0.4886 | 3500 | 0.6714        | -                       | -                        |
+| 0.5025 | 3600 | 0.6698        | -                       | -                        |
+| 0.5165 | 3700 | 0.6838        | -                       | -                        |
+| 0.5304 | 3800 | 0.6927        | -                       | -                        |
+| 0.5444 | 3900 | 0.6628        | -                       | -                        |
+| 0.5583 | 4000 | 0.6647        | 0.8367                  | -                        |
+| 0.5723 | 4100 | 0.6766        | -                       | -                        |
+| 0.5863 | 4200 | 0.6987        | -                       | -                        |
+| 0.6002 | 4300 | 0.6895        | -                       | -                        |
+| 0.6142 | 4400 | 0.6571        | -                       | -                        |
+| 0.6281 | 4500 | 0.66          | -                       | -                        |
+| 0.6421 | 4600 | 0.6747        | -                       | -                        |
+| 0.6561 | 4700 | 0.6495        | -                       | -                        |
+| 0.6700 | 4800 | 0.6746        | -                       | -                        |
+| 0.6840 | 4900 | 0.6575        | -                       | -                        |
+| 0.6979 | 5000 | 0.6712        | 0.8454                  | -                        |
+| 0.7119 | 5100 | 0.6627        | -                       | -                        |
+| 0.7259 | 5200 | 0.6538        | -                       | -                        |
+| 0.7398 | 5300 | 0.6659        | -                       | -                        |
+| 0.7538 | 5400 | 0.6551        | -                       | -                        |
+| 0.7677 | 5500 | 0.6548        | -                       | -                        |
+| 0.7817 | 5600 | 0.673         | -                       | -                        |
+| 0.7956 | 5700 | 0.6805        | -                       | -                        |
+| 0.8096 | 5800 | 0.6537        | -                       | -                        |
+| 0.8236 | 5900 | 0.6826        | -                       | -                        |
+| 0.8375 | 6000 | 0.7182        | 0.8370                  | -                        |
+| 0.8515 | 6100 | 0.7391        | -                       | -                        |
+| 0.8654 | 6200 | 0.7006        | -                       | -                        |
+| 0.8794 | 6300 | 0.6774        | -                       | -                        |
+| 0.8934 | 6400 | 0.7076        | -                       | -                        |
+| 0.9073 | 6500 | 0.6893        | -                       | -                        |
+| 0.9213 | 6600 | 0.678         | -                       | -                        |
+| 0.9352 | 6700 | 0.6703        | -                       | -                        |
+| 0.9492 | 6800 | 0.675         | -                       | -                        |
+| 0.9631 | 6900 | 0.6842        | -                       | -                        |
+| 0.9771 | 7000 | 0.6909        | 0.8452                  | -                        |
+| 0.9911 | 7100 | 0.681         | -                       | -                        |
+| 1.0    | 7164 | -             | -                       | 0.8145                   |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.202 kWh
+- **Carbon Emitted**: 0.079 kg of CO2
+- **Hours Used**: 0.601 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 3.0.0.dev0
+- Transformers: 4.41.0.dev0
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.26.1
+- Datasets: 2.18.0
+- Tokenizers: 0.19.1
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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 +1,27 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0.dev0",
+    "transformers": "4.41.0.dev0",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e667a0b8fa890b166f64d5b986836cd53f82d9daba2406b2cbab3ddc1cc97d
+size 328485128

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
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}