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 +1,819 @@
+---
+base_model: nomic-ai/nomic-embed-text-v1.5
+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:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Chevron aims to support a diverse and inclusive supply chain that
+    reflects the communities where they operate, believing that a diverse supply chain
+    contributes to their success and growth.
+  sentences:
+  - What was the renewal rate for Costco memberships in the U.S. and Canada at the
+    end of 2023?
+  - What is Chevron's approach towards maintaining a diverse and inclusive supply
+    chain?
+  - What percentage growth did LinkedIn revenue experience?
+- source_sentence: Visa Direct is part of Visa’s strategy beyond C2B payments and
+    helps facilitate the delivery of funds to eligible cards, deposit accounts and
+    digital wallets across more than 190 countries and territories. Visa Direct supports
+    multiple use cases, such as P2P payments and account-to-account transfers, business
+    and government payouts to individuals or small businesses, merchant settlements
+    and refunds.
+  sentences:
+  - What type of situations will the company record a liability for legal proceedings?
+  - What is the purpose of Visa Direct?
+  - What benefits does Airbnb's AirCover for guests offer?
+- source_sentence: As of December 31, 2023, we had $267 million of total unrecognized
+    compensation cost related to nonvested stock-based compensation awards granted
+    under our plans.
+  sentences:
+  - How much total unrecognized compensation cost related to nonvested stock-based
+    compensation awards was reported as of December 31, 2023?
+  - What changes are planned for the company's reporting metrics starting in fiscal
+    year 202es and how does this affect the treatment of paused subscriptions?
+  - How much does HP expect to pay for benefit claims for its post-retirement benefit
+    plans in fiscal year 2024?
+- source_sentence: Discrete tax items resulted in a (benefit) provision for income
+    taxes of $(18.1) million and $(11.9) million for the years ended December 31,
+    2023 and 2022, respectively.
+  sentences:
+  - What was the total cost of TNT Express's business realignment through 2023?
+  - What is the purpose of adding research and development expenses and general and
+    administrative expenses to the loss from operations when calculating the contribution
+    margin?
+  - What impact did discrete tax items have on the tax provision in 2023 compared
+    to 2022?
+- source_sentence: 'The company may issue debt or equity securities occasionally to
+    provide additional liquidity or pursue opportunities to enhance its long-term
+    competitive position while maintaining a strong balance sheet. '
+  sentences:
+  - What might the company do to increase liquidity or pursue long-term competitive
+    advantages while managing a strong balance sheet?
+  - What types of technologies does the Mortgage Technology segment employ to enhance
+    operational efficiency?
+  - Which section of a financial document covers Financial Statements and Supplementary
+    Data?
+model-index:
+- name: Nomic Embed 1.5 Financial Matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6928571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8228571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.87
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9071428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6928571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2742857142857143
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.174
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0907142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6928571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8228571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.87
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9071428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8029973671837228
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7692715419501133
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7724352164684344
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6914285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8271428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.87
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9085714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6914285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2757142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.174
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09085714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6914285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8271428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.87
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9085714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8029523922190992
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7687732426303853
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7717841390041892
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6871428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8285714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8728571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8985714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6871428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27619047619047615
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17457142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08985714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6871428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8285714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8728571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8985714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7983704009707536
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7655901360544215
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7693376855880492
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6671428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8185714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8557142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8957142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6671428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27285714285714285
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17114285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08957142857142855
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6671428571428571
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8185714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8557142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8957142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7849638501826605
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7491031746031743
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.752516331310788
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6528571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7871428571428571
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8271428571428572
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8771428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6528571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2623809523809524
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1654285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0877142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6528571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7871428571428571
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8271428571428572
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8771428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7639694587103518
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7279750566893419
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7317631790989764
+      name: Cosine Map@100
+---
+
+# Nomic Embed 1.5 Financial Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5). 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:** [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) <!-- at revision b0753ae76394dd36bcfb912a46018088bca48be0 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 768 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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel 
+  (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("venkateshmurugadas/nomic-v1.5-financial-matryoshka")
+# Run inference
+sentences = [
+    'The company may issue debt or equity securities occasionally to provide additional liquidity or pursue opportunities to enhance its long-term competitive position while maintaining a strong balance sheet. ',
+    'What might the company do to increase liquidity or pursue long-term competitive advantages while managing a strong balance sheet?',
+    'What types of technologies does the Mortgage Technology segment employ to enhance operational efficiency?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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_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   | 0.6929     |
+| cosine_accuracy@3   | 0.8229     |
+| cosine_accuracy@5   | 0.87       |
+| cosine_accuracy@10  | 0.9071     |
+| cosine_precision@1  | 0.6929     |
+| cosine_precision@3  | 0.2743     |
+| cosine_precision@5  | 0.174      |
+| cosine_precision@10 | 0.0907     |
+| cosine_recall@1     | 0.6929     |
+| cosine_recall@3     | 0.8229     |
+| cosine_recall@5     | 0.87       |
+| cosine_recall@10    | 0.9071     |
+| cosine_ndcg@10      | 0.803      |
+| cosine_mrr@10       | 0.7693     |
+| **cosine_map@100**  | **0.7724** |
+
+#### 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   | 0.6914     |
+| cosine_accuracy@3   | 0.8271     |
+| cosine_accuracy@5   | 0.87       |
+| cosine_accuracy@10  | 0.9086     |
+| cosine_precision@1  | 0.6914     |
+| cosine_precision@3  | 0.2757     |
+| cosine_precision@5  | 0.174      |
+| cosine_precision@10 | 0.0909     |
+| cosine_recall@1     | 0.6914     |
+| cosine_recall@3     | 0.8271     |
+| cosine_recall@5     | 0.87       |
+| cosine_recall@10    | 0.9086     |
+| cosine_ndcg@10      | 0.803      |
+| cosine_mrr@10       | 0.7688     |
+| **cosine_map@100**  | **0.7718** |
+
+#### 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   | 0.6871     |
+| cosine_accuracy@3   | 0.8286     |
+| cosine_accuracy@5   | 0.8729     |
+| cosine_accuracy@10  | 0.8986     |
+| cosine_precision@1  | 0.6871     |
+| cosine_precision@3  | 0.2762     |
+| cosine_precision@5  | 0.1746     |
+| cosine_precision@10 | 0.0899     |
+| cosine_recall@1     | 0.6871     |
+| cosine_recall@3     | 0.8286     |
+| cosine_recall@5     | 0.8729     |
+| cosine_recall@10    | 0.8986     |
+| cosine_ndcg@10      | 0.7984     |
+| cosine_mrr@10       | 0.7656     |
+| **cosine_map@100**  | **0.7693** |
+
+#### 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   | 0.6671     |
+| cosine_accuracy@3   | 0.8186     |
+| cosine_accuracy@5   | 0.8557     |
+| cosine_accuracy@10  | 0.8957     |
+| cosine_precision@1  | 0.6671     |
+| cosine_precision@3  | 0.2729     |
+| cosine_precision@5  | 0.1711     |
+| cosine_precision@10 | 0.0896     |
+| cosine_recall@1     | 0.6671     |
+| cosine_recall@3     | 0.8186     |
+| cosine_recall@5     | 0.8557     |
+| cosine_recall@10    | 0.8957     |
+| cosine_ndcg@10      | 0.785      |
+| cosine_mrr@10       | 0.7491     |
+| **cosine_map@100**  | **0.7525** |
+
+#### 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   | 0.6529     |
+| cosine_accuracy@3   | 0.7871     |
+| cosine_accuracy@5   | 0.8271     |
+| cosine_accuracy@10  | 0.8771     |
+| cosine_precision@1  | 0.6529     |
+| cosine_precision@3  | 0.2624     |
+| cosine_precision@5  | 0.1654     |
+| cosine_precision@10 | 0.0877     |
+| cosine_recall@1     | 0.6529     |
+| cosine_recall@3     | 0.7871     |
+| cosine_recall@5     | 0.8271     |
+| cosine_recall@10    | 0.8771     |
+| cosine_ndcg@10      | 0.764      |
+| cosine_mrr@10       | 0.728      |
+| **cosine_map@100**  | **0.7318** |
+
+<!--
+## 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: 6,300 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: 8 tokens</li><li>mean: 46.46 tokens</li><li>max: 371 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 20.45 tokens</li><li>max: 41 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | anchor                                                                                                |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|
+  | <code>We evaluate uncertain tax positions periodically, considering changes in facts and circumstances, such as new regulations or recent judicial opinions, as well as the status of audit activities by taxing authorities.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | <code>How are changes to a company's uncertain tax positions evaluated?</code>                        |
+  | <code>During 2022 and 2023, our operating margin was impacted by increased wage rates. During 2022, our gross margin was impacted by higher air freight costs as a result of global supply chain disruption.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | <code>What effects did inflation have on the company's operating results during 2022 and 2023?</code> |
+  | <code>To mitigate these developments, we are continually working to evolve our advertising systems to improve the performance of our ad products. We are developing privacy enhancing technologies to deliver relevant ads and measurement capabilities while reducing the amount of personal information we process, including by relying more on anonymized or aggregated third-party data. In addition, we are developing tools that enable marketers to share their data into our systems, as well as ad products that generate more valuable signals within our apps. More broadly, we also continue to innovate our advertising tools to help marketers prepare campaigns and connect with consumers, including developing growing formats such as Reels ads and our business messaging ad products. Across all of these efforts, we are making significant investments in artificial intelligence (AI), including generative AI, to improve our delivery, targeting, and measurement capabilities. Further, we are focused on driving onsite conversions in our business messaging ad products by developing new features and scaling existing features.</code> | <code>What technological solutions is the company developing to improve ad delivery?</code>           |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 4
+- `per_device_eval_batch_size`: 4
+- `gradient_accumulation_steps`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `tf32`: False
+- `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`: 4
+- `per_device_eval_batch_size`: 4
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 64
+- `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`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `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_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.4063     | 10     | 0.1329        | -                      | -                      | -                      | -                     | -                      |
+| 0.8127     | 20     | 0.0567        | -                      | -                      | -                      | -                     | -                      |
+| 0.9752     | 24     | -             | 0.7416                 | 0.7604                 | 0.7678                 | 0.7249                | 0.7758                 |
+| 1.2190     | 30     | 0.0415        | -                      | -                      | -                      | -                     | -                      |
+| 1.6254     | 40     | 0.0043        | -                      | -                      | -                      | -                     | -                      |
+| 1.9911     | 49     | -             | 0.7491                 | 0.7648                 | 0.7700                 | 0.7315                | 0.7731                 |
+| 2.0317     | 50     | 0.0059        | -                      | -                      | -                      | -                     | -                      |
+| 2.4381     | 60     | 0.0045        | -                      | -                      | -                      | -                     | -                      |
+| 2.8444     | 70     | 0.0013        | -                      | -                      | -                      | -                     | -                      |
+| **2.9663** | **73** | **-**         | **0.7531**             | **0.7703**             | **0.7712**             | **0.7327**            | **0.7738**             |
+| 3.2508     | 80     | 0.0031        | -                      | -                      | -                      | -                     | -                      |
+| 3.6571     | 90     | 0.0009        | -                      | -                      | -                      | -                     | -                      |
+| 3.9010     | 96     | -             | 0.7525                 | 0.7693                 | 0.7718                 | 0.7318                | 0.7724                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.31.0
+- 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 +1,58 @@
+{
+  "_name_or_path": "nomic-ai/nomic-embed-text-v1.5",
+  "activation_function": "swiglu",
+  "architectures": [
+    "NomicBertModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",
+    "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
+    "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining"
+  },
+  "bos_token_id": null,
+  "causal": false,
+  "dense_seq_output": true,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "fused_bias_fc": true,
+  "fused_dropout_add_ln": true,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-12,
+  "max_trained_positions": 2048,
+  "mlp_fc1_bias": false,
+  "mlp_fc2_bias": false,
+  "model_type": "nomic_bert",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 8192,
+  "pad_vocab_size_multiple": 64,
+  "parallel_block": false,
+  "parallel_block_tied_norm": false,
+  "prenorm": false,
+  "qkv_proj_bias": false,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_emb_base": 1000,
+  "rotary_emb_fraction": 1.0,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "rotary_scaling_factor": null,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_flash_attn": true,
+  "use_rms_norm": false,
+  "use_xentropy": true,
+  "vocab_size": 30528
+}

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:e3ffdac84df4039824c0975c9299af8f0237edc013e2f4d27042c97e8b193f61
+size 546938168

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": 8192,
+  "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 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}