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 +1,850 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:5822
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: nomic-ai/nomic-embed-text-v1.5
+widget:
+- source_sentence: "submitted to the CIA for each year.”  Id. at 1–2.  On July 22,\
+    \ 2010, the CIA responded to this \nrequest, stating “[w]e . . . have determined\
+    \ that our record systems are not configured in a way \nthat would allow us to\
+    \ perform a search reasonably calculated to lead to the responsive record \nwithout\
+    \ an unreasonable effort.”  First Lutz Decl. Ex. L at 1, No. 11-444, ECF No. 20-3.\
+    \  As a"
+  sentences:
+  - How many instances of individual's names does the plaintiff point to?
+  - What date did the CIA respond to the request?
+  - What phrase does the Bar propose to delete references to in the Preamble to Chapter
+    4?
+- source_sentence: "City Department of Education, the self-represented plaintiff \n\
+    submitted a filing containing hallucinations.  No. 24-cv-04232, \n \n20 \n2024\
+    \ WL 3460049, at *7 (S.D.N.Y. July 18, 2024) (unpublished \nopinion).  The court\
+    \ noted that “[s]anctions may be imposed for \nsubmitting false and nonexistent\
+    \ legal authority to the [c]ourt.”  Id.  \nHowever, the court declined to impose\
+    \ sanctions due to the"
+  sentences:
+  - In which sections of their opposition does the plaintiff discuss the deliberative-process
+    privilege?
+  - Who submitted the filing containing hallucinations?
+  - When did the plaintiff file a motion?
+- source_sentence: "§ 424 and Exemption 3; Exemption 5; and/or Exemption 6.  See Second\
+    \ Williams Decl. Ex. A. \n120 \n \nTherefore, the Court need not decide whether\
+    \ the DIA has the independent authority to invoke \nthe National Security Act\
+    \ as an Exemption 3 withholding statute. \n3. \nODNI \nFinally, the plaintiff\
+    \ challenges the ODNI’s decision to withhold certain portions of e-"
+  sentences:
+  - How many counts did EPIC bring related to the APA?
+  - Which organization's decision is being challenged by the plaintiff?
+  - Does the Government agree with EPIC's claim about their Answer?
+- source_sentence: "confidentiality agreement/order, that remain following those discussions.\
+    \  This is a \nfinal report and notice of exceptions shall be filed within three\
+    \ days of the date of \nthis report, pursuant to Court of Chancery Rule 144(d)(2),\
+    \ given the expedited and \nsummary nature of Section 220 proceedings.  \n \n\
+    \ \n \n \n \n \n \nRespectfully, \n \n \n \n \n \n \n \n \n/s/ Patricia W. Griffin"
+  sentences:
+  - Who signed this document?
+  - Did Mr. Mooney allege that the video was altered or tampered with?
+  - Did the plaintiff report the defendant at that time?
+- source_sentence: "such an argument, and she does not offer any case law, cites to\
+    \ secondary sources, dictionaries \nor grammatical texts, arguments by analogy,\
+    \ or other citations, except for the mere assertion \nthat defendant failed to\
+    \ move in a timely fashion after he was “on notice” of the ex parte order. \n\
+    A reviewing court is entitled to have issues clearly defined with relevant authority\
+    \ cited."
+  sentences:
+  - What page is Cross-MJAR's emphasis mentioned on?
+  - What mere assertion does she make?
+  - On what dates did the Commission meet in 2019?
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+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
+model-index:
+- name: nomic-embed-text-v1.5
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5486862442040186
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5965996908809892
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7017001545595054
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7697063369397218
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5486862442040186
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.5239567233384853
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.40989180834621336
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.24142194744976814
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.19049459041731065
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5101751674394642
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6503091190108191
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7595311695002576
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6615339195276682
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6004440519123668
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6427552042140723
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5409582689335394
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.58887171561051
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6924265842349304
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7743431221020093
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5409582689335394
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.5172591447707368
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.4034003091190108
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.24188562596599691
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.18740340030911898
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5054095826893354
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6411643482740855
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7622359608449253
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6576404555647709
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.5934416476533937
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6355153178607286
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.508500772797527
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5564142194744977
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6707882534775889
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7449768160741885
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.508500772797527
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.4873776403915508
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.38639876352395675
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.23122102009273574
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.17671303451828954
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.47707367336424517
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6141164348274084
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7257856774858321
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6257588263652936
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.562961531856431
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6091899586876254
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.45131375579598143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5054095826893354
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.58887171561051
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.6862442040185471
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.45131375579598143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.437403400309119
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.3415765069551777
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.21298299845440496
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.15700669757856775
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.4282586295723854
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.5426326635754766
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.6720762493560021
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5679548352076085
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.503881160913618
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.5511797935827811
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.35239567233384855
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3894899536321484
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.47295208655332305
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5641421947449768
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.35239567233384855
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.33900051519835134
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.26955177743431225
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1723338485316847
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.12171561051004637
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.33217413704276144
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.4310922205048943
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5446934569809376
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.45200452556542003
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.39659662422413555
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.44614347894124107
+      name: Cosine Map@100
+---
+
+# nomic-embed-text-v1.5
+
+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) on the json dataset. 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 a03db6748c80237063eb0546ac6b627eca2318cb -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **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("Thejina/nomic-embed-text-finetuned")
+# Run inference
+sentences = [
+    'such an argument, and she does not offer any case law, cites to secondary sources, dictionaries \nor grammatical texts, arguments by analogy, or other citations, except for the mere assertion \nthat defendant failed to move in a timely fashion after he was “on notice” of the ex parte order. \nA reviewing court is entitled to have issues clearly defined with relevant authority cited.',
+    'What mere assertion does she make?',
+    "What page is Cross-MJAR's emphasis mentioned on?",
+]
+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) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.5487     |
+| cosine_accuracy@3   | 0.5966     |
+| cosine_accuracy@5   | 0.7017     |
+| cosine_accuracy@10  | 0.7697     |
+| cosine_precision@1  | 0.5487     |
+| cosine_precision@3  | 0.524      |
+| cosine_precision@5  | 0.4099     |
+| cosine_precision@10 | 0.2414     |
+| cosine_recall@1     | 0.1905     |
+| cosine_recall@3     | 0.5102     |
+| cosine_recall@5     | 0.6503     |
+| cosine_recall@10    | 0.7595     |
+| **cosine_ndcg@10**  | **0.6615** |
+| cosine_mrr@10       | 0.6004     |
+| cosine_map@100      | 0.6428     |
+
+#### Information Retrieval
+
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 512
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.541      |
+| cosine_accuracy@3   | 0.5889     |
+| cosine_accuracy@5   | 0.6924     |
+| cosine_accuracy@10  | 0.7743     |
+| cosine_precision@1  | 0.541      |
+| cosine_precision@3  | 0.5173     |
+| cosine_precision@5  | 0.4034     |
+| cosine_precision@10 | 0.2419     |
+| cosine_recall@1     | 0.1874     |
+| cosine_recall@3     | 0.5054     |
+| cosine_recall@5     | 0.6412     |
+| cosine_recall@10    | 0.7622     |
+| **cosine_ndcg@10**  | **0.6576** |
+| cosine_mrr@10       | 0.5934     |
+| cosine_map@100      | 0.6355     |
+
+#### Information Retrieval
+
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.5085     |
+| cosine_accuracy@3   | 0.5564     |
+| cosine_accuracy@5   | 0.6708     |
+| cosine_accuracy@10  | 0.745      |
+| cosine_precision@1  | 0.5085     |
+| cosine_precision@3  | 0.4874     |
+| cosine_precision@5  | 0.3864     |
+| cosine_precision@10 | 0.2312     |
+| cosine_recall@1     | 0.1767     |
+| cosine_recall@3     | 0.4771     |
+| cosine_recall@5     | 0.6141     |
+| cosine_recall@10    | 0.7258     |
+| **cosine_ndcg@10**  | **0.6258** |
+| cosine_mrr@10       | 0.563      |
+| cosine_map@100      | 0.6092     |
+
+#### Information Retrieval
+
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 128
+  }
+  ```
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.4513    |
+| cosine_accuracy@3   | 0.5054    |
+| cosine_accuracy@5   | 0.5889    |
+| cosine_accuracy@10  | 0.6862    |
+| cosine_precision@1  | 0.4513    |
+| cosine_precision@3  | 0.4374    |
+| cosine_precision@5  | 0.3416    |
+| cosine_precision@10 | 0.213     |
+| cosine_recall@1     | 0.157     |
+| cosine_recall@3     | 0.4283    |
+| cosine_recall@5     | 0.5426    |
+| cosine_recall@10    | 0.6721    |
+| **cosine_ndcg@10**  | **0.568** |
+| cosine_mrr@10       | 0.5039    |
+| cosine_map@100      | 0.5512    |
+
+#### Information Retrieval
+
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 64
+  }
+  ```
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.3524    |
+| cosine_accuracy@3   | 0.3895    |
+| cosine_accuracy@5   | 0.473     |
+| cosine_accuracy@10  | 0.5641    |
+| cosine_precision@1  | 0.3524    |
+| cosine_precision@3  | 0.339     |
+| cosine_precision@5  | 0.2696    |
+| cosine_precision@10 | 0.1723    |
+| cosine_recall@1     | 0.1217    |
+| cosine_recall@3     | 0.3322    |
+| cosine_recall@5     | 0.4311    |
+| cosine_recall@10    | 0.5447    |
+| **cosine_ndcg@10**  | **0.452** |
+| cosine_mrr@10       | 0.3966    |
+| cosine_map@100      | 0.4461    |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 5,822 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: 46 tokens</li><li>mean: 91.09 tokens</li><li>max: 324 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.89 tokens</li><li>max: 43 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                               | anchor                                                                       |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|
+  | <code>functional test, too.  Id. at 89–90.  Still, the Court made clear that this functional test was “not <br>relevant.”  Id. at 90.  So, just as in Energy Research, its application of the functional test was <br>dicta.  And because this discussion relied on the dicta from Energy Research, this was dicta <br>upon dicta. <br> <br> The Government is thus imprecise when it asserts as the “law of the case” that the</code> | <code>What page is the functional test mentioned as 'not relevant'?</code>   |
+  | <code>authenticated through his testimony under Maryland Rule 5-901(b)(1) as a witness with <br>personal knowledge of the events. <br>- 6 - <br>The part of the video depicting the shooting was properly authenticated through <br>circumstantial evidence under Maryland Rule 5-901(b)(4), as there was sufficient <br>circumstantial evidence from which a reasonable juror could have inferred that the video</code>               | <code>Which part of the video was authenticated?</code>                      |
+  | <code>KLAN202300916 <br> <br> <br> <br> <br>9<br>Los derechos morales, a su vez, están fundamentalmente <br>protegidos por la legislación estatal. Esta reconoce los derechos de <br>los autores como exclusivos de estos y los protege no solo en <br>beneficio propio, sino también de la sociedad por la contribución <br>social y cultural que históricamente se le ha reconocido a la</code>                                      | <code>¿En beneficio de quién se protegen los derechos de los autores?</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`: 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
+- `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
+- `torch_empty_cache_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`: 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`: 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}
+- `tp_size`: 0
+- `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`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `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
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.8791     | 10     | 69.7578       | -                      | -                      | -                      | -                      | -                     |
+| 1.0        | 12     | -             | 0.6178                 | 0.6069                 | 0.5742                 | 0.5088                 | 0.4115                |
+| 1.7033     | 20     | 28.4334       | -                      | -                      | -                      | -                      | -                     |
+| 2.0        | 24     | -             | 0.6589                 | 0.6509                 | 0.6268                 | 0.5616                 | 0.4494                |
+| 2.5275     | 30     | 20.1123       | -                      | -                      | -                      | -                      | -                     |
+| 3.0        | 36     | -             | 0.6621                 | 0.6573                 | 0.6263                 | 0.5677                 | 0.4508                |
+| 3.3516     | 40     | 16.5444       | -                      | -                      | -                      | -                      | -                     |
+| **3.7033** | **44** | **-**         | **0.6615**             | **0.6576**             | **0.6258**             | **0.568**              | **0.452**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.12
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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 +1,57 @@
+{
+  "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": "4.51.3",
+  "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": "4.1.0",
+    "transformers": "4.51.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:188b92cd53a4b5eeabb440a861943b7964db7f341518be40857cc4346fbb3f3d
+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 +1,56 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}