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 +1,902 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- loss:MultipleNegativesRankingLoss
+- loss:ContrastiveLoss
+base_model: sentence-transformers/stsb-distilbert-base
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+- average_precision
+- f1
+- precision
+- recall
+- threshold
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+- dot_accuracy@1
+- dot_accuracy@3
+- dot_accuracy@5
+- dot_accuracy@10
+- dot_precision@1
+- dot_precision@3
+- dot_precision@5
+- dot_precision@10
+- dot_recall@1
+- dot_recall@3
+- dot_recall@5
+- dot_recall@10
+- dot_ndcg@10
+- dot_mrr@10
+- dot_map@100
+widget:
+- source_sentence: What is Mindset?
+  sentences:
+  - What is a mindset?
+  - Can you eat only once a day?
+  - Is law a good career choice?
+- source_sentence: Is a queef real?
+  sentences:
+  - Is "G" based on real events?
+  - What is the entire court process?
+  - How do I reduce my weight?
+- source_sentence: Is Cicret a scam?
+  sentences:
+  - Is the Cicret Bracelet a scam?
+  - Was World War II Inevitable?
+  - What are some of the best photos?
+- source_sentence: What is Planet X?
+  sentences:
+  - Do planet X exist?
+  - What are the best C++ books?
+  - How can I lose my weight fast?
+- source_sentence: How fast is fast?
+  sentences:
+  - How does light travel so fast?
+  - How do I copyright my books?
+  - What is a black hole made of?
+pipeline_tag: sentence-similarity
+co2_eq_emissions:
+  emissions: 32.724475965905576
+  energy_consumed: 0.08418911136527617
+  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: 0.399
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: SentenceTransformer based on sentence-transformers/stsb-distilbert-base
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: quora duplicates
+      type: quora-duplicates
+    metrics:
+    - type: cosine_accuracy
+      value: 0.846
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7969297170639038
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.7791495198902607
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7139598727226257
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.6977886977886978
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8819875776397516
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.8230449963294564
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.843
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 151.2908477783203
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.7660818713450294
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 143.77838134765625
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.7237569060773481
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.8136645962732919
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.7946044629726107
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.838
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 194.99119567871094
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.7704081632653061
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 247.49777221679688
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.6536796536796536
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.937888198757764
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.8149715271935773
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.841
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 9.02225112915039
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.7703889585947302
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 11.385245323181152
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.6463157894736842
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.953416149068323
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.8152967320117391
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.846
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 194.99119567871094
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.7791495198902607
+      name: Max F1
+    - type: max_f1_threshold
+      value: 247.49777221679688
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.7237569060773481
+      name: Max Precision
+    - type: max_recall
+      value: 0.953416149068323
+      name: Max Recall
+    - type: max_ap
+      value: 0.8230449963294564
+      name: Max Ap
+  - task:
+      type: paraphrase-mining
+      name: Paraphrase Mining
+    dataset:
+      name: quora duplicates dev
+      type: quora-duplicates-dev
+    metrics:
+    - type: average_precision
+      value: 0.5888649029434471
+      name: Average Precision
+    - type: f1
+      value: 0.5761652140962487
+      name: F1
+    - type: precision
+      value: 0.5477552123204396
+      name: Precision
+    - type: recall
+      value: 0.6076834690513064
+      name: Recall
+    - type: threshold
+      value: 0.7728720009326935
+      name: Threshold
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.963
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9906
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9944
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9982
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.963
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.4285333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.27568000000000004
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.14494
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8299562338609103
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9590366552956846
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9806221849555673
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9925738410935468
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9784033087450696
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9771579365079368
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9709189650394419
+      name: Cosine Map@100
+    - type: dot_accuracy@1
+      value: 0.9514
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.9852
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.991
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 0.9968
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.9514
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.4247333333333334
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.27364
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.14458000000000001
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.8194380520427287
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.9520212390452685
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.9755502441186265
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 0.9910547306614953
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.9715023430522326
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.9692583333333334
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.961739772177385
+      name: Dot Map@100
+---
+
+# SentenceTransformer based on sentence-transformers/stsb-distilbert-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) on the [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) and [cl](https://huggingface.co/datasets/sentence-transformers/quora-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:** [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) <!-- at revision 82ad392c08f81be9be9bf065339670b23f2e1493 -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
+    - [cl](https://huggingface.co/datasets/sentence-transformers/quora-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: DistilBertModel 
+  (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/stsb-distilbert-base-mnrl-cl-multi")
+# Run inference
+sentences = [
+    'How fast is fast?',
+    'How does light travel so fast?',
+    'How do I copyright my books?',
+]
+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
+
+#### Binary Classification
+* Dataset: `quora-duplicates`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value     |
+|:-----------------------------|:----------|
+| cosine_accuracy              | 0.846     |
+| cosine_accuracy_threshold    | 0.7969    |
+| cosine_f1                    | 0.7791    |
+| cosine_f1_threshold          | 0.714     |
+| cosine_precision             | 0.6978    |
+| cosine_recall                | 0.882     |
+| cosine_ap                    | 0.823     |
+| dot_accuracy                 | 0.843     |
+| dot_accuracy_threshold       | 151.2908  |
+| dot_f1                       | 0.7661    |
+| dot_f1_threshold             | 143.7784  |
+| dot_precision                | 0.7238    |
+| dot_recall                   | 0.8137    |
+| dot_ap                       | 0.7946    |
+| manhattan_accuracy           | 0.838     |
+| manhattan_accuracy_threshold | 194.9912  |
+| manhattan_f1                 | 0.7704    |
+| manhattan_f1_threshold       | 247.4978  |
+| manhattan_precision          | 0.6537    |
+| manhattan_recall             | 0.9379    |
+| manhattan_ap                 | 0.815     |
+| euclidean_accuracy           | 0.841     |
+| euclidean_accuracy_threshold | 9.0223    |
+| euclidean_f1                 | 0.7704    |
+| euclidean_f1_threshold       | 11.3852   |
+| euclidean_precision          | 0.6463    |
+| euclidean_recall             | 0.9534    |
+| euclidean_ap                 | 0.8153    |
+| max_accuracy                 | 0.846     |
+| max_accuracy_threshold       | 194.9912  |
+| max_f1                       | 0.7791    |
+| max_f1_threshold             | 247.4978  |
+| max_precision                | 0.7238    |
+| max_recall                   | 0.9534    |
+| **max_ap**                   | **0.823** |
+
+#### Paraphrase Mining
+* Dataset: `quora-duplicates-dev`
+* Evaluated with [<code>ParaphraseMiningEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator)
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| **average_precision** | **0.5889** |
+| f1                    | 0.5762     |
+| precision             | 0.5478     |
+| recall                | 0.6077     |
+| threshold             | 0.7729     |
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.963      |
+| cosine_accuracy@3   | 0.9906     |
+| cosine_accuracy@5   | 0.9944     |
+| cosine_accuracy@10  | 0.9982     |
+| cosine_precision@1  | 0.963      |
+| cosine_precision@3  | 0.4285     |
+| cosine_precision@5  | 0.2757     |
+| cosine_precision@10 | 0.1449     |
+| cosine_recall@1     | 0.83       |
+| cosine_recall@3     | 0.959      |
+| cosine_recall@5     | 0.9806     |
+| cosine_recall@10    | 0.9926     |
+| cosine_ndcg@10      | 0.9784     |
+| cosine_mrr@10       | 0.9772     |
+| **cosine_map@100**  | **0.9709** |
+| dot_accuracy@1      | 0.9514     |
+| dot_accuracy@3      | 0.9852     |
+| dot_accuracy@5      | 0.991      |
+| dot_accuracy@10     | 0.9968     |
+| dot_precision@1     | 0.9514     |
+| dot_precision@3     | 0.4247     |
+| dot_precision@5     | 0.2736     |
+| dot_precision@10    | 0.1446     |
+| dot_recall@1        | 0.8194     |
+| dot_recall@3        | 0.952      |
+| dot_recall@5        | 0.9756     |
+| dot_recall@10       | 0.9911     |
+| dot_ndcg@10         | 0.9715     |
+| dot_mrr@10          | 0.9693     |
+| dot_map@100         | 0.9617     |
+
+<!--
+## 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
+
+#### mnrl
+
+* Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 100,000 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 13.85 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.65 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.76 tokens</li><li>max: 64 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"
+  }
+  ```
+
+#### cl
+
+* Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 100,000 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                         | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | int                                             |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.3 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.66 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>0: ~62.00%</li><li>1: ~38.00%</li></ul> |
+* Samples:
+  | sentence1                                                                              | sentence2                                                                                             | label          |
+  |:---------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>What is the step by step guide to invest in share market in india?</code>        | <code>What is the step by step guide to invest in share market?</code>                                | <code>0</code> |
+  | <code>What is the story of Kohinoor (Koh-i-Noor) Diamond?</code>                       | <code>What would happen if the Indian government stole the Kohinoor (Koh-i-Noor) diamond back?</code> | <code>0</code> |
+  | <code>How can I increase the speed of my internet connection while using a VPN?</code> | <code>How can Internet speed be increased by hacking through DNS?</code>                              | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Datasets
+
+#### mnrl
+
+* Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 1,000 evaluation 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: 13.84 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.8 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.71 tokens</li><li>max: 56 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                   | positive                                                                         | negative                                                                                                                                                                                                                                                                          |
+  |:---------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Which programming language is best for developing low-end games?</code>                            | <code>What coding language should I learn first for making games?</code>         | <code>I am entering the world of video game programming and want to know what language I should learn? Because there are so many languages ​​I do not know which one to start with. Can you recommend a language that's easy to learn and can be used with many platforms?</code> |
+  | <code>Was it appropriate for Meryl Streep to use her Golden Globes speech to attack Donald Trump?</code> | <code>Should Meryl Streep be using her position to attack the president?</code>  | <code>Why did Kelly Ann Conway say that Meryl Streep incited peoples worst feelings?</code>                                                                                                                                                                                       |
+  | <code>Where can I found excellent commercial fridges in Sydney?</code>                                   | <code>Where can I found impressive range of commercial fridges in Sydney?</code> | <code>What is the best grocery delivery service in Sydney?</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"
+  }
+  ```
+
+#### cl
+
+* Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 1,000 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 15.59 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.65 tokens</li><li>max: 76 tokens</li></ul> | <ul><li>0: ~63.40%</li><li>1: ~36.60%</li></ul> |
+* Samples:
+  | sentence1                                                                 | sentence2                                                                                                | label          |
+  |:--------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>What should I ask my friend to get from UK to India?</code>         | <code>What is the process of getting a surgical residency in UK after completing MBBS from India?</code> | <code>0</code> |
+  | <code>How can I learn hacking for free?</code>                            | <code>How can I learn to hack seriously?</code>                                                          | <code>1</code> |
+  | <code>Which is the best website to learn programming language C++?</code> | <code>Which is the best website to learn C++ Programming language for free?</code>                       | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### 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`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | cl loss | mnrl loss | cosine_map@100 | quora-duplicates-dev_average_precision | quora-duplicates_max_ap |
+|:------:|:----:|:-------------:|:-------:|:---------:|:--------------:|:--------------------------------------:|:-----------------------:|
+| 0      | 0    | -             | -       | -         | 0.9245         | 0.4200                                 | 0.6890                  |
+| 0.0320 | 100  | 0.1634        | -       | -         | -              | -                                      | -                       |
+| 0.0640 | 200  | 0.1206        | -       | -         | -              | -                                      | -                       |
+| 0.0800 | 250  | -             | 0.0190  | 0.1469    | 0.9530         | 0.5068                                 | 0.7354                  |
+| 0.0960 | 300  | 0.1036        | -       | -         | -              | -                                      | -                       |
+| 0.1280 | 400  | 0.0836        | -       | -         | -              | -                                      | -                       |
+| 0.1599 | 500  | 0.0918        | 0.0180  | 0.1008    | 0.9553         | 0.5259                                 | 0.7643                  |
+| 0.1919 | 600  | 0.0784        | -       | -         | -              | -                                      | -                       |
+| 0.2239 | 700  | 0.0656        | -       | -         | -              | -                                      | -                       |
+| 0.2399 | 750  | -             | 0.0177  | 0.0905    | 0.9593         | 0.5305                                 | 0.7686                  |
+| 0.2559 | 800  | 0.0593        | -       | -         | -              | -                                      | -                       |
+| 0.2879 | 900  | 0.0534        | -       | -         | -              | -                                      | -                       |
+| 0.3199 | 1000 | 0.0612        | 0.0161  | 0.0736    | 0.9642         | 0.5512                                 | 0.7881                  |
+| 0.3519 | 1100 | 0.0572        | -       | -         | -              | -                                      | -                       |
+| 0.3839 | 1200 | 0.06          | -       | -         | -              | -                                      | -                       |
+| 0.3999 | 1250 | -             | 0.0158  | 0.0641    | 0.9649         | 0.5567                                 | 0.7983                  |
+| 0.4159 | 1300 | 0.0565        | -       | -         | -              | -                                      | -                       |
+| 0.4479 | 1400 | 0.0565        | -       | -         | -              | -                                      | -                       |
+| 0.4798 | 1500 | 0.0475        | 0.0154  | 0.0578    | 0.9645         | 0.5614                                 | 0.8062                  |
+| 0.5118 | 1600 | 0.0596        | -       | -         | -              | -                                      | -                       |
+| 0.5438 | 1700 | 0.0509        | -       | -         | -              | -                                      | -                       |
+| 0.5598 | 1750 | -             | 0.0150  | 0.0525    | 0.9674         | 0.5762                                 | 0.8092                  |
+| 0.5758 | 1800 | 0.0403        | -       | -         | -              | -                                      | -                       |
+| 0.6078 | 1900 | 0.0431        | -       | -         | -              | -                                      | -                       |
+| 0.6398 | 2000 | 0.0481        | 0.0150  | 0.0531    | 0.9689         | 0.5824                                 | 0.8128                  |
+| 0.6718 | 2100 | 0.05          | -       | -         | -              | -                                      | -                       |
+| 0.7038 | 2200 | 0.0468        | -       | -         | -              | -                                      | -                       |
+| 0.7198 | 2250 | -             | 0.0146  | 0.0486    | 0.9684         | 0.5756                                 | 0.8195                  |
+| 0.7358 | 2300 | 0.0436        | -       | -         | -              | -                                      | -                       |
+| 0.7678 | 2400 | 0.0409        | -       | -         | -              | -                                      | -                       |
+| 0.7997 | 2500 | 0.0391        | 0.0145  | 0.0454    | 0.9705         | 0.5822                                 | 0.8190                  |
+| 0.8317 | 2600 | 0.0412        | -       | -         | -              | -                                      | -                       |
+| 0.8637 | 2700 | 0.0373        | -       | -         | -              | -                                      | -                       |
+| 0.8797 | 2750 | -             | 0.0143  | 0.0451    | 0.9705         | 0.5889                                 | 0.8229                  |
+| 0.8957 | 2800 | 0.0428        | -       | -         | -              | -                                      | -                       |
+| 0.9277 | 2900 | 0.0419        | -       | -         | -              | -                                      | -                       |
+| 0.9597 | 3000 | 0.0376        | 0.0143  | 0.0435    | 0.9709         | 0.5889                                 | 0.8230                  |
+| 0.9917 | 3100 | 0.0366        | -       | -         | -              | -                                      | -                       |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.084 kWh
+- **Carbon Emitted**: 0.033 kg of CO2
+- **Hours Used**: 0.399 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}
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, 
+    title={Dimensionality Reduction by Learning an Invariant Mapping}, 
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/stsb-distilbert-base",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5fff731121df51b321267ac7bbc9c4add62099b0c93b84f7f14645c56fef5c
+size 265462608

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 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}