Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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 +1,995 @@
+---
+base_model: FacebookAI/xlm-roberta-large
+datasets:
+- sentence-transformers/stsb
+language:
+- en
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:5749
+- loss:MatryoshkaLoss
+- loss:CoSENTLoss
+widget:
+- source_sentence: A chef is preparing some food.
+  sentences:
+  - Five birds stand on the snow.
+  - A chef prepared a meal.
+  - There is no 'still' that is not relative to some other object.
+- source_sentence: A woman is adding oil on fishes.
+  sentences:
+  - Large cruise ship floating on the water.
+  - It refers to the maximum f-stop (which is defined as the ratio of focal length
+    to effective aperture diameter).
+  - The woman is cutting potatoes.
+- source_sentence: The player shoots the winning points.
+  sentences:
+  - Minimum wage laws hurt the least skilled, least productive the most.
+  - The basketball player is about to score points for his team.
+  - Three televisions, on on the floor, the other two on a box.
+- source_sentence: Stars form in star-formation regions, which itself develop from
+    molecular clouds.
+  sentences:
+  - Although I believe Searle is mistaken, I don't think you have found the problem.
+  - It may be possible for a solar system like ours to exist outside of a galaxy.
+  - A blond-haired child performing on the trumpet in front of a house while his younger
+    brother watches.
+- source_sentence: While Queen may refer to both Queen regent (sovereign) or Queen
+    consort, the King has always been the sovereign.
+  sentences:
+  - At first, I thought this is a bit of a tricky question.
+  - A man plays the guitar.
+  - There is a very good reason not to refer to the Queen's spouse as "King" - because
+    they aren't the King.
+model-index:
+- name: SentenceTransformer based on FacebookAI/xlm-roberta-large
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 768
+      type: sts-dev-768
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.038123417655342585
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: -0.030855987437062582
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.0742298464837288
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: -0.016119009479880368
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: -0.053239384921975864
+      name: Pearson Dot
+    - type: spearman_dot
+      value: -0.03860610142560432
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.040766255073950965
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: -0.028106086435826655
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.076050553000047
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: -0.014573222092867504
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: -0.06110575151055097
+      name: Pearson Dot
+    - type: spearman_dot
+      value: -0.04818501881621991
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.044210895435818166
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: -0.03253407490039325
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.0529355152933442
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: -0.0338167301189937
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.0887169006335579
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.06886250477710897
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 128
+      type: sts-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.05321620243744594
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: -0.026531903856252148
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.06064347235216407
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: -0.0270947004666721
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.07199088437564892
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.05552894816506978
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 64
+      type: sts-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.046922199302745354
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: -0.027530540631984835
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.04930495975336398
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: -0.02287953412697089
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.05851507366090909
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.044913605667507114
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 768
+      type: sts-test-768
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.0005203243269627229
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.007914891421418472
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.008479099839233263
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.0002449834909380018
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.015253799995136243
+      name: Pearson Dot
+    - type: spearman_dot
+      value: -0.002544651953260673
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 512
+      type: sts-test-512
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.000985791968546407
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.009210170664121263
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.010968197464829785
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.0006366521814203481
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.030903954394043587
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.0214169911509498
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.008347426706014351
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.008133437696668973
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.01284332508912676
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.006207692348050752
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: -0.10411841010392278
+      name: Pearson Dot
+    - type: spearman_dot
+      value: -0.10441611480429308
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.007293947286825709
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.012461130559236479
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.013785631605643068
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.008355374230034162
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: -0.07790382803601184
+      name: Pearson Dot
+    - type: spearman_dot
+      value: -0.08277939304968172
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: -0.012731573411777072
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.003453137865023755
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: -0.013710254571378023
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.0028389826642085166
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: -0.04900795414419644
+      name: Pearson Dot
+    - type: spearman_dot
+      value: -0.05520642056907742
+      name: Spearman Dot
+    - type: pearson_max
+      value: .nan
+      name: Pearson Max
+    - type: spearman_max
+      value: .nan
+      name: Spearman Max
+---
+
+# SentenceTransformer based on FacebookAI/xlm-roberta-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) <!-- at revision c23d21b0620b635a76227c604d44e43a9f0ee389 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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("dipteshkanojia/xlm-roberta-large-sts-matryoshka")
+# Run inference
+sentences = [
+    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
+    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
+    'A man plays the guitar.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+* Dataset: `sts-dev-768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.0381 |
+| spearman_manhattan  | -0.0309 |
+| pearson_euclidean   | -0.0742 |
+| spearman_euclidean  | -0.0161 |
+| pearson_dot         | -0.0532 |
+| spearman_dot        | -0.0386 |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.0408 |
+| spearman_manhattan  | -0.0281 |
+| pearson_euclidean   | -0.0761 |
+| spearman_euclidean  | -0.0146 |
+| pearson_dot         | -0.0611 |
+| spearman_dot        | -0.0482 |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.0442 |
+| spearman_manhattan  | -0.0325 |
+| pearson_euclidean   | -0.0529 |
+| spearman_euclidean  | -0.0338 |
+| pearson_dot         | 0.0887  |
+| spearman_dot        | 0.0689  |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.0532 |
+| spearman_manhattan  | -0.0265 |
+| pearson_euclidean   | -0.0606 |
+| spearman_euclidean  | -0.0271 |
+| pearson_dot         | 0.072   |
+| spearman_dot        | 0.0555  |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.0469 |
+| spearman_manhattan  | -0.0275 |
+| pearson_euclidean   | -0.0493 |
+| spearman_euclidean  | -0.0229 |
+| pearson_dot         | 0.0585  |
+| spearman_dot        | 0.0449  |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | 0.0005  |
+| spearman_manhattan  | 0.0079  |
+| pearson_euclidean   | -0.0085 |
+| spearman_euclidean  | 0.0002  |
+| pearson_dot         | 0.0153  |
+| spearman_dot        | -0.0025 |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.001  |
+| spearman_manhattan  | 0.0092  |
+| pearson_euclidean   | -0.011  |
+| spearman_euclidean  | 0.0006  |
+| pearson_dot         | 0.0309  |
+| spearman_dot        | 0.0214  |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.0083 |
+| spearman_manhattan  | 0.0081  |
+| pearson_euclidean   | -0.0128 |
+| spearman_euclidean  | 0.0062  |
+| pearson_dot         | -0.1041 |
+| spearman_dot        | -0.1044 |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.0073 |
+| spearman_manhattan  | 0.0125  |
+| pearson_euclidean   | -0.0138 |
+| spearman_euclidean  | 0.0084  |
+| pearson_dot         | -0.0779 |
+| spearman_dot        | -0.0828 |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+| pearson_manhattan   | -0.0127 |
+| spearman_manhattan  | 0.0035  |
+| pearson_euclidean   | -0.0137 |
+| spearman_euclidean  | 0.0028  |
+| pearson_dot         | -0.049  |
+| spearman_dot        | -0.0552 |
+| pearson_max         | nan     |
+| spearman_max        | nan     |
+
+<!--
+## 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
+
+#### sentence-transformers/stsb
+
+* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 11.08 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 11.05 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                  | sentence2                                                             | score             |
+  |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
+  | <code>A plane is taking off.</code>                        | <code>An air plane is taking off.</code>                              | <code>1.0</code>  |
+  | <code>A man is playing a large flute.</code>               | <code>A man is playing a flute.</code>                                | <code>0.76</code> |
+  | <code>A man is spreading shreded cheese on a pizza.</code> | <code>A man is spreading shredded cheese on an uncooked pizza.</code> | <code>0.76</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "CoSENTLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/stsb
+
+* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                        | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 16.55 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.5 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                         | sentence2                                             | score             |
+  |:--------------------------------------------------|:------------------------------------------------------|:------------------|
+  | <code>A man with a hard hat is dancing.</code>    | <code>A man wearing a hard hat is dancing.</code>     | <code>1.0</code>  |
+  | <code>A young child is riding a horse.</code>     | <code>A child is riding a horse.</code>               | <code>0.95</code> |
+  | <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code>  |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "CoSENTLoss",
+      "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`: steps
+- `per_device_train_batch_size`: 6
+- `per_device_eval_batch_size`: 6
+- `num_train_epochs`: 8
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 6
+- `per_device_eval_batch_size`: 6
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 8
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `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`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: 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
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss    | sts-dev-128_spearman_cosine | sts-dev-256_spearman_cosine | sts-dev-512_spearman_cosine | sts-dev-64_spearman_cosine | sts-dev-768_spearman_cosine | sts-test-128_spearman_cosine | sts-test-256_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
+|:------:|:----:|:-------------:|:-------:|:---------------------------:|:---------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
+| 1.0417 | 500  | 21.1353       | 20.8565 | nan                         | nan                         | nan                         | nan                        | nan                         | -                            | -                            | -                            | -                           | -                            |
+| 2.0833 | 1000 | 20.7941       | 20.8565 | nan                         | nan                         | nan                         | nan                        | nan                         | -                            | -                            | -                            | -                           | -                            |
+| 3.125  | 1500 | 20.7823       | 20.8565 | nan                         | nan                         | nan                         | nan                        | nan                         | -                            | -                            | -                            | -                           | -                            |
+| 4.1667 | 2000 | 20.781        | 20.8565 | nan                         | nan                         | nan                         | nan                        | nan                         | -                            | -                            | -                            | -                           | -                            |
+| 5.2083 | 2500 | 20.7707       | 20.8565 | nan                         | nan                         | nan                         | nan                        | nan                         | -                            | -                            | -                            | -                           | -                            |
+| 6.25   | 3000 | 20.7661       | 20.8565 | nan                         | nan                         | nan                         | nan                        | nan                         | -                            | -                            | -                            | -                           | -                            |
+| 7.2917 | 3500 | 20.7719       | 20.8565 | nan                         | nan                         | nan                         | nan                        | nan                         | -                            | -                            | -                            | -                           | -                            |
+| 8.0    | 3840 | -             | -       | -                           | -                           | -                           | -                          | -                           | nan                          | nan                          | nan                          | nan                         | nan                          |
+
+
+### Framework Versions
+- Python: 3.9.19
+- Sentence Transformers: 3.1.0.dev0
+- Transformers: 4.44.2
+- PyTorch: 2.4.1+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.21.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### 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}
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## 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 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.0.dev0",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.1+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 sha256:60f5c9a0442025429e327c478b39b65da049485680fb689cc497ec710002388c
+size 2239607176

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}