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 +1,789 @@
+---
+base_model: intfloat/e5-base
+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:63
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: 하이브리드 자동차의 스마트 크루즈 컨트롤 기능은 운전자가 설정한 속도를 유지하는 기능입니다. 이 기능에서는 전방
+    카메라와 레이더 센서를 사용하여 도로의 제한 속도를 감지하고, 이를 기반으로 속도를 조절합니다.
+  sentences:
+  - 하이테크센터나 블루핸즈에서 점검을 받을 때는 어떤 경우에 해당합니까?
+  - 원터치 자동 유리창의 작동 원리를 설명하세요.
+  - 하이브리드 자동차의 스마트 크루즈 컨트롤 기능을 설명하세요.
+- source_sentence: 하이브리드 자동차의 지능형 속도 제한 보조의 제한 사항은 표지판이 오염 또는 훼손되거나 불명확할 경우, 주변 물체에
+    표지판 일부가 가려지거나 그림자가 표지판을 덮을 경우, 표지판 형상 또는 설치 방법이 표준과 다를 경우 등입니다.
+  sentences:
+  - 테마 모드를 설정하려면 어떻게 해야 하나요?
+  - 에어백 경고 라벨의 주의 사항은 무엇입니까?
+  - 하이브리드 자동차의 지능형 속도 제한 보조의 제한 사항은 무엇입니까?
+- source_sentence: 어린이 탑승 시에는 차에서 내릴 때 어린이를 차 안에 남겨두지 마십시오. 어린이가 차내 안전 장비를 잘못 만져 사고가
+    발생할 수 있고, 여름이나 겨울에는 차 내부 온도가 너무 높거나 낮아져 매우 위험합니다.
+  sentences:
+  - 운전자 주의 경고의 기본 기능은 무엇입니까?
+  - 하이브리드 자동차의 고전압 배터리 시스템에 대한 안전 주의 사항은 무엇입니까?
+  - 어린이 탑승 시 주의 사항을 설명하세요.
+- source_sentence: 후방 주차 충돌방지 보조의 이상 및 제한 사항은 다음과 같습니다. 기능 이상, 인식 센서 가림, 광각-후방 카메라,
+    후방 초음파센서의 이상 등이 있습니다. 이러한 이상 및 제한 사항에 따라 후방 주차 충돌방지 보조의 성능이 저하되거나 오작동 할 수 있습니다.
+  sentences:
+  - 하이브리드 자동차의 회생 제동 모드를 설명하세요.
+  - 하이빔 보조 설정 방법은 무엇입니까?
+  - 후방 주차 충돌방지 보조의 이상 및 제한 사항을 설명하세요.
+- source_sentence: 클러스터 조명 밝기 조절은 시동 'ON' 상태에서 인포테인먼트 시스템의 설정> 클러스터/HUD > 화면 밝기를 차례로
+    선택하면 클러스터의 밝기를 조절할 수 있습니다. 인포테인먼트 시스템 화면에 표시되는 조명밝기 조절 정도를 참고하여 원하는 밝기로 조절하십시오.
+  sentences:
+  - 운전자 주의 경고 시스템의 작동 원리를 설명하세요.
+  - 클러스터 조명 밝기 조절은 어떻게 하나요?
+  - 하이브리드 자동차의 저압 타이어 경고등이 켜졌을 때의 조치는 무엇입니까?
+model-index:
+- name: BGE base Financial Matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5555555555555556
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8148148148148148
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8518518518518519
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9259259259259259
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5555555555555556
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27160493827160487
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1703703703703704
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09259259259259262
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.5555555555555556
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8148148148148148
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8518518518518519
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9259259259259259
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7435849530374239
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6849206349206348
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6889906389906391
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5555555555555556
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7777777777777778
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8518518518518519
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8888888888888888
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5555555555555556
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.25925925925925924
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1703703703703704
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0888888888888889
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.5555555555555556
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7777777777777778
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8518518518518519
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8888888888888888
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7335374617221688
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6824514991181657
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6896593804001211
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5925925925925926
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7777777777777778
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8148148148148148
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8888888888888888
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5925925925925926
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.25925925925925924
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16296296296296298
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0888888888888889
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.5925925925925926
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7777777777777778
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8148148148148148
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8888888888888888
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7460717071407622
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6997354497354498
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7073543740210406
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5925925925925926
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7407407407407407
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8518518518518519
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8888888888888888
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5925925925925926
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.24691358024691354
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1703703703703704
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0888888888888889
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.5925925925925926
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7407407407407407
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8518518518518519
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8888888888888888
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7391281504030159
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6910493827160493
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6993265993265992
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5925925925925926
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7407407407407407
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8518518518518519
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9259259259259259
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5925925925925926
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.24691358024691354
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1703703703703704
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09259259259259262
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.5925925925925926
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7407407407407407
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8518518518518519
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9259259259259259
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7456467996361283
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6892416225749558
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6932539682539682
+      name: Cosine Map@100
+---
+
+# BGE base Financial Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/e5-base](https://huggingface.co/intfloat/e5-base). 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:** [intfloat/e5-base](https://huggingface.co/intfloat/e5-base) <!-- at revision b533fe4636f4a2507c08ddab40644d20b0006d6a -->
+- **Maximum Sequence Length:** 512 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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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})
+  (2): Normalize()
+)
+```
+
+## 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("ValentinaKim/bge-base-automobile-matryoshka")
+# Run inference
+sentences = [
+    "클러스터 조명 밝기 조절은 시동 'ON' 상태에서 인포테인먼트 시스템의 설정> 클러스터/HUD > 화면 밝기를 차례로 선택하면 클러스터의 밝기를 조절할 수 있습니다. 인포테인먼트 시스템 화면에 표시되는 조명밝기 조절 정도를 참고하여 원하는 밝기로 조절하십시오.",
+    '클러스터 조명 밝기 조절은 어떻게 하나요?',
+    '하이브리드 자동차의 저압 타이어 경고등이 켜졌을 때의 조치는 무엇입니까?',
+]
+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   | 0.5556    |
+| cosine_accuracy@3   | 0.8148    |
+| cosine_accuracy@5   | 0.8519    |
+| cosine_accuracy@10  | 0.9259    |
+| cosine_precision@1  | 0.5556    |
+| cosine_precision@3  | 0.2716    |
+| cosine_precision@5  | 0.1704    |
+| cosine_precision@10 | 0.0926    |
+| cosine_recall@1     | 0.5556    |
+| cosine_recall@3     | 0.8148    |
+| cosine_recall@5     | 0.8519    |
+| cosine_recall@10    | 0.9259    |
+| cosine_ndcg@10      | 0.7436    |
+| cosine_mrr@10       | 0.6849    |
+| **cosine_map@100**  | **0.689** |
+
+#### 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   | 0.5556     |
+| cosine_accuracy@3   | 0.7778     |
+| cosine_accuracy@5   | 0.8519     |
+| cosine_accuracy@10  | 0.8889     |
+| cosine_precision@1  | 0.5556     |
+| cosine_precision@3  | 0.2593     |
+| cosine_precision@5  | 0.1704     |
+| cosine_precision@10 | 0.0889     |
+| cosine_recall@1     | 0.5556     |
+| cosine_recall@3     | 0.7778     |
+| cosine_recall@5     | 0.8519     |
+| cosine_recall@10    | 0.8889     |
+| cosine_ndcg@10      | 0.7335     |
+| cosine_mrr@10       | 0.6825     |
+| **cosine_map@100**  | **0.6897** |
+
+#### 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   | 0.5926     |
+| cosine_accuracy@3   | 0.7778     |
+| cosine_accuracy@5   | 0.8148     |
+| cosine_accuracy@10  | 0.8889     |
+| cosine_precision@1  | 0.5926     |
+| cosine_precision@3  | 0.2593     |
+| cosine_precision@5  | 0.163      |
+| cosine_precision@10 | 0.0889     |
+| cosine_recall@1     | 0.5926     |
+| cosine_recall@3     | 0.7778     |
+| cosine_recall@5     | 0.8148     |
+| cosine_recall@10    | 0.8889     |
+| cosine_ndcg@10      | 0.7461     |
+| cosine_mrr@10       | 0.6997     |
+| **cosine_map@100**  | **0.7074** |
+
+#### 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   | 0.5926     |
+| cosine_accuracy@3   | 0.7407     |
+| cosine_accuracy@5   | 0.8519     |
+| cosine_accuracy@10  | 0.8889     |
+| cosine_precision@1  | 0.5926     |
+| cosine_precision@3  | 0.2469     |
+| cosine_precision@5  | 0.1704     |
+| cosine_precision@10 | 0.0889     |
+| cosine_recall@1     | 0.5926     |
+| cosine_recall@3     | 0.7407     |
+| cosine_recall@5     | 0.8519     |
+| cosine_recall@10    | 0.8889     |
+| cosine_ndcg@10      | 0.7391     |
+| cosine_mrr@10       | 0.691      |
+| **cosine_map@100**  | **0.6993** |
+
+#### 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   | 0.5926     |
+| cosine_accuracy@3   | 0.7407     |
+| cosine_accuracy@5   | 0.8519     |
+| cosine_accuracy@10  | 0.9259     |
+| cosine_precision@1  | 0.5926     |
+| cosine_precision@3  | 0.2469     |
+| cosine_precision@5  | 0.1704     |
+| cosine_precision@10 | 0.0926     |
+| cosine_recall@1     | 0.5926     |
+| cosine_recall@3     | 0.7407     |
+| cosine_recall@5     | 0.8519     |
+| cosine_recall@10    | 0.9259     |
+| cosine_ndcg@10      | 0.7456     |
+| cosine_mrr@10       | 0.6892     |
+| **cosine_map@100**  | **0.6933** |
+
+<!--
+## 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: 63 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: 89 tokens</li><li>mean: 181.76 tokens</li><li>max: 365 tokens</li></ul> | <ul><li>min: 22 tokens</li><li>mean: 46.21 tokens</li><li>max: 72 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                | anchor                                                |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------|
+  | <code>하이브리드 자동차의 전방 차량 출발 알림 기능의 제한 사항은 과격하게 운전할 경우, 빈번하게 차선을 침범할 경우, 차로 이탈방지 보조 등 다른 운전자 보조에 의해 차량이 제어될 경우 등입니다.</code>                                                | <code>하이브리드 자동차의 전방 차량 출발 알림 기능의 제한 사항은 무엇입니까?</code> |
+  | <code>파워 트렁크가 정상적으로 작동하지 않으면 무리한 힘을 가하지 마십시오. 파워 트렁크가 손상될 수 있습니다. 반드시 당사 직영 하이테크센터나 블루핸즈에서 점검을 받으십시오.</code>                                                            | <code>파워 트렁크가 정상적으로 작동하지 않으면 어떻게 해야 하나요?</code>       |
+  | <code>에어백 경고 라벨의 주의 사항은 13세 미만의 어린이는 에어백의 팽창 충격으로 다칠 수 있습니다. 어린이에게는 뒷좌석이 안전할 수 있습니다. 유아용 보조 좌석은 동승석에 설치하지 마십시오. 에어백에서 가능한 떨어져 앉으십시오. 좌석 안전벨트와 어린이 보호 장치를 사용하십시오.</code> | <code>에어백 경고 라벨의 주의 사항은 무엇입니까?</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
+- `gradient_accumulation_steps`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `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`: 8
+- `per_device_eval_batch_size`: 8
+- `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`: False
+- `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  | 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 |
+|:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 1.0     | 1     | 0.4923                 | 0.5456                 | 0.5549                 | 0.4722                | 0.5450                 |
+| 2.0     | 2     | 0.6184                 | 0.6751                 | 0.7085                 | 0.6313                | 0.7072                 |
+| 3.0     | 3     | 0.6810                 | 0.6825                 | 0.6916                 | 0.6933                | 0.6840                 |
+| **4.0** | **4** | **0.6993**             | **0.7074**             | **0.6897**             | **0.6933**            | **0.689**              |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.33.0
+- 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 +1,26 @@
+{
+  "_name_or_path": "intfloat/e5-base",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "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 sha256:5d242b90da3320782fe9fef77af20ca3482ec4696ca61fd229f3b890fd659373
+size 437951328

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

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 +1,55 @@
+{
+  "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": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}