Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,879 @@
+---
+base_model: WhereIsAI/UAE-Large-V1
+datasets: []
+language:
+- en
+library_name: sentence-transformers
+license: apache-2.0
+metrics:
+- 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
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:3474
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Microsoft Corporation believes that its success is based upon its
+    ability to transform to meet the needs of customers. Its growth strategy includes
+    innovation across its cloud platforms and services, as well as investing in complementary
+    businesses, products, services, and technologies to extend and grow its product
+    offerings.
+  sentences:
+  - What factors caused the surge in Tesla’s stock prices in the first half of 2023?
+  - What's Microsoft growth strategy in the cloud computing sector?
+  - How has Microsoft Corporation performed in terms of stock prices over the past
+    five years?
+- source_sentence: Amazon reported the Q3 2023 earnings revealing a 21% year-over-year
+    increase in the revenue, which stood at $116.38 billion. Net income increased
+    57% to $6.66 billion, or $13.21 per diluted share, compared to $4.23 billion,
+    or $8.42 per diluted share, in third quarter 2022. Amazon Web Services (AWS) revenue
+    grew 32% in the quarter to $15 billion.
+  sentences:
+  - Can you tell about Amazon's Q3 2023 earnings?
+  - What was the net income of Microsoft in Fiscal Year 2024?
+  - What is the significance of EBITDA in financial analysis?
+- source_sentence: For the fiscal year 2024, Walmart had an operating profit margin
+    of 20%.
+  sentences:
+  - What is Pfizer's dividend yield for the financial year 2022?
+  - What was Exxon Mobil Corporation's net income for the fourth quarter of 2023?
+  - What is the operating profit margin for Walmart for the fiscal year 2024?
+- source_sentence: The slowdown in construction, particularly in developing markets,
+    resulted in a decrease in demand for Caterpillar's machinery and equipment, which
+    negatively impacted the revenue for the year 2022.
+  sentences:
+  - How did the slow down in construction in 2022 affect Caterpillar's revenues?
+  - What is JP Morgan's strategy when it comes to sustainability?
+  - What was the debt-to-equity ratio for Tesla Inc in Q4 of 2022?
+- source_sentence: According to Johnson & Johnson’s 2024 guidance report, their pharmaceutical
+    sector was projected to grow by 7% in 2023 after considering crucial factors like
+    the overall market demand, introduction of new drugs and potential impact of patent
+    expirations.
+  sentences:
+  - What are Caterpillar's initiatives for enhancing its product sustainability?
+  - How is JPMorgan Chase & Co. improving its cybersecurity measures?
+  - What was the projected growth of Johnson & Johnson’s pharmaceutical sector in
+    2023?
+model-index:
+- name: UAE-Large-V1-financial-embeddings-matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 1024
+      type: dim_1024
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8316062176165803
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9326424870466321
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.966321243523316
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9896373056994818
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8316062176165803
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31088082901554404
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1932642487046632
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09896373056994817
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8316062176165803
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9326424870466321
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.966321243523316
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9896373056994818
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9113990251008172
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8860854099843737
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.886565872062324
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8290155440414507
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9326424870466321
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.966321243523316
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9844559585492227
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8290155440414507
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31088082901554404
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1932642487046632
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09844559585492228
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8290155440414507
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9326424870466321
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.966321243523316
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9844559585492227
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9098442107332023
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8854439098610082
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8863342112694444
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8238341968911918
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9378238341968912
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9637305699481865
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9844559585492227
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8238341968911918
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3126079447322971
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19274611398963729
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09844559585492228
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8238341968911918
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9378238341968912
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9637305699481865
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9844559585492227
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9085199240883707
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8836016530964717
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8844289493397997
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8212435233160622
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9326424870466321
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.961139896373057
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9792746113989638
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8212435233160622
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31088082901554404
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19222797927461138
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09792746113989637
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8212435233160622
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9326424870466321
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.961139896373057
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9792746113989638
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9050964679750835
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8807097623159799
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8817273654804927
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8186528497409327
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9352331606217616
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.961139896373057
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9792746113989638
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8186528497409327
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3117443868739206
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19222797927461138
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09792746113989637
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8186528497409327
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9352331606217616
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.961139896373057
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9792746113989638
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9031436826413919
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8781797433999506
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8793080516202277
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7979274611398963
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9222797927461139
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9585492227979274
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9792746113989638
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7979274611398963
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.307426597582038
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19170984455958548
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09792746113989637
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7979274611398963
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9222797927461139
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9585492227979274
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9792746113989638
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8935743388819871
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8654926391973025
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8667278930244052
+      name: Cosine Map@100
+---
+
+# UAE-Large-V1-financial-embeddings-matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [WhereIsAI/UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [WhereIsAI/UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1) <!-- at revision 52d9e291d9fc7fc7f5276ff077b26fd1880c7c4f -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### 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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': 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("rbhatia46/UAE-Large-V1-financial-rag-matryoshka")
+# Run inference
+sentences = [
+    'According to Johnson & Johnson’s 2024 guidance report, their pharmaceutical sector was projected to grow by 7% in 2023 after considering crucial factors like the overall market demand, introduction of new drugs and potential impact of patent expirations.',
+    'What was the projected growth of Johnson & Johnson’s pharmaceutical sector in 2023?',
+    'How is JPMorgan Chase & Co. improving its cybersecurity measures?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+* Dataset: `dim_1024`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.8316     |
+| cosine_accuracy@3   | 0.9326     |
+| cosine_accuracy@5   | 0.9663     |
+| cosine_accuracy@10  | 0.9896     |
+| cosine_precision@1  | 0.8316     |
+| cosine_precision@3  | 0.3109     |
+| cosine_precision@5  | 0.1933     |
+| cosine_precision@10 | 0.099      |
+| cosine_recall@1     | 0.8316     |
+| cosine_recall@3     | 0.9326     |
+| cosine_recall@5     | 0.9663     |
+| cosine_recall@10    | 0.9896     |
+| cosine_ndcg@10      | 0.9114     |
+| cosine_mrr@10       | 0.8861     |
+| **cosine_map@100**  | **0.8866** |
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.829      |
+| cosine_accuracy@3   | 0.9326     |
+| cosine_accuracy@5   | 0.9663     |
+| cosine_accuracy@10  | 0.9845     |
+| cosine_precision@1  | 0.829      |
+| cosine_precision@3  | 0.3109     |
+| cosine_precision@5  | 0.1933     |
+| cosine_precision@10 | 0.0984     |
+| cosine_recall@1     | 0.829      |
+| cosine_recall@3     | 0.9326     |
+| cosine_recall@5     | 0.9663     |
+| cosine_recall@10    | 0.9845     |
+| cosine_ndcg@10      | 0.9098     |
+| cosine_mrr@10       | 0.8854     |
+| **cosine_map@100**  | **0.8863** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.8238     |
+| cosine_accuracy@3   | 0.9378     |
+| cosine_accuracy@5   | 0.9637     |
+| cosine_accuracy@10  | 0.9845     |
+| cosine_precision@1  | 0.8238     |
+| cosine_precision@3  | 0.3126     |
+| cosine_precision@5  | 0.1927     |
+| cosine_precision@10 | 0.0984     |
+| cosine_recall@1     | 0.8238     |
+| cosine_recall@3     | 0.9378     |
+| cosine_recall@5     | 0.9637     |
+| cosine_recall@10    | 0.9845     |
+| cosine_ndcg@10      | 0.9085     |
+| cosine_mrr@10       | 0.8836     |
+| **cosine_map@100**  | **0.8844** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.8212     |
+| cosine_accuracy@3   | 0.9326     |
+| cosine_accuracy@5   | 0.9611     |
+| cosine_accuracy@10  | 0.9793     |
+| cosine_precision@1  | 0.8212     |
+| cosine_precision@3  | 0.3109     |
+| cosine_precision@5  | 0.1922     |
+| cosine_precision@10 | 0.0979     |
+| cosine_recall@1     | 0.8212     |
+| cosine_recall@3     | 0.9326     |
+| cosine_recall@5     | 0.9611     |
+| cosine_recall@10    | 0.9793     |
+| cosine_ndcg@10      | 0.9051     |
+| cosine_mrr@10       | 0.8807     |
+| **cosine_map@100**  | **0.8817** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.8187     |
+| cosine_accuracy@3   | 0.9352     |
+| cosine_accuracy@5   | 0.9611     |
+| cosine_accuracy@10  | 0.9793     |
+| cosine_precision@1  | 0.8187     |
+| cosine_precision@3  | 0.3117     |
+| cosine_precision@5  | 0.1922     |
+| cosine_precision@10 | 0.0979     |
+| cosine_recall@1     | 0.8187     |
+| cosine_recall@3     | 0.9352     |
+| cosine_recall@5     | 0.9611     |
+| cosine_recall@10    | 0.9793     |
+| cosine_ndcg@10      | 0.9031     |
+| cosine_mrr@10       | 0.8782     |
+| **cosine_map@100**  | **0.8793** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7979     |
+| cosine_accuracy@3   | 0.9223     |
+| cosine_accuracy@5   | 0.9585     |
+| cosine_accuracy@10  | 0.9793     |
+| cosine_precision@1  | 0.7979     |
+| cosine_precision@3  | 0.3074     |
+| cosine_precision@5  | 0.1917     |
+| cosine_precision@10 | 0.0979     |
+| cosine_recall@1     | 0.7979     |
+| cosine_recall@3     | 0.9223     |
+| cosine_recall@5     | 0.9585     |
+| cosine_recall@10    | 0.9793     |
+| cosine_ndcg@10      | 0.8936     |
+| cosine_mrr@10       | 0.8655     |
+| **cosine_map@100**  | **0.8667** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 3,474 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                            | anchor                                                                            |
+  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                            |
+  | details | <ul><li>min: 15 tokens</li><li>mean: 44.84 tokens</li><li>max: 112 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 18.34 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                     | anchor                                                                                 |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|
+  | <code>Exxon Mobil faces substantial risk factors including fluctuating market prices for oil and gas, regulatory environment changes and the potential for catastrophic accidents such as oil spills.</code>                                                                 | <code>What is the key risk factor faced by Exxon Mobil in the energy sector?</code>    |
+  | <code>Tesla’s remarkable revenue growth in 2023 is largely driven by its robust electric vehicle sales in China and the strong demand for its energy storage products.</code>                                                                                                | <code>What is the main reason behind Tesla’s revenue growth in 2023?</code>            |
+  | <code>Amazon is expected to see a sales growth of 23% in the next financial year, driven by the increased demand for their ecommerce business and strong growth in AWS. This projection is subject to changes in the market condition and customer spending patterns.</code> | <code>What is the projected sales growth for Amazon in the next financial year?</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          1024,
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `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
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `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`: True
+- `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_fused
+- `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`: False
+- `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_eval_metrics`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_1024_cosine_map@100 | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.8807     | 6      | -             | 0.8708                  | 0.8499                 | 0.8647                 | 0.8705                 | 0.8307                | 0.8700                 |
+| 1.4679     | 10     | 0.7358        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.9083     | 13     | -             | 0.8848                  | 0.8724                 | 0.8782                 | 0.8861                 | 0.8617                | 0.8855                 |
+| **2.9358** | **20** | **0.1483**    | **0.8865**              | **0.8793**             | **0.8814**             | **0.8857**             | **0.8667**            | **0.8863**             |
+| 3.5229     | 24     | -             | 0.8866                  | 0.8793                 | 0.8817                 | 0.8844                 | 0.8667                | 0.8863                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.6
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.19.1
+- 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### 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 +1,26 @@
+{
+  "_name_or_path": "WhereIsAI/UAE-Large-V1",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+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 sha256:21cc373f00100e294aa091d1f585dd25d8ee0a5d84af30b84c5af39bea829392
+size 1340612432

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": 512,
+  "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 +1,57 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}