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 +1,1103 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:1K<n<10K
+- loss:MatryoshkaLoss
+- loss:CoSENTLoss
+base_model: distilbert/distilbert-base-uncased
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: A woman is dancing.
+  sentences:
+  - Women are dancing.
+  - A toddler walks down a hallway.
+  - Shinzo Abe is Japan's prime minister
+- source_sentence: A man is spitting.
+  sentences:
+  - A man is crying.
+  - The girl is playing the guitar.
+  - A slow loris hanging on a cord.
+- source_sentence: A man is speaking.
+  sentences:
+  - A man is talking.
+  - A man plays an acoustic guitar.
+  - The dogs are chasing a cat.
+- source_sentence: A plane in the sky.
+  sentences:
+  - Two airplanes in the sky.
+  - A slow loris hanging on a cord.
+  - Turkey's PM Warns Against Protests
+- source_sentence: A baby is laughing.
+  sentences:
+  - The baby laughed in his car seat.
+  - A brown horse in a green field.
+  - Bangladesh Islamist leader executed
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on distilbert/distilbert-base-uncased
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 768
+      type: sts-dev-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8597256789475689
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8704890959686488
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8577087236028236
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8613364457717408
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8573646665610765
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8611053939518858
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7230928823966007
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7292814320710974
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8597256789475689
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8704890959686488
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8565849984058084
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8690380994355429
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8560989283234569
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8602048185493963
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8560319360006069
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8598344132114529
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7250593470322173
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7324935808414036
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8565849984058084
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8690380994355429
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8508677416837496
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8655671620679589
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8516296649395021
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8576372447474295
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8512958746883122
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8567348597207523
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.691266333570308
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6983564197469347
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8516296649395021
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8655671620679589
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 128
+      type: sts-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8416379040782492
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8625866345174488
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8410105415496507
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8496221523132089
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8431760561066126
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8505697779445824
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.677560950193549
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6864851260895027
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8431760561066126
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8625866345174488
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 64
+      type: sts-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.823170809036498
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8523184158399918
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8255414664543136
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8358413125165197
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8292011526410756
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8385242101250404
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.641639319620455
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6564088055361835
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8292011526410756
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8523184158399918
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 32
+      type: sts-dev-32
+    metrics:
+    - type: pearson_cosine
+      value: 0.7903418859430655
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8327625705936669
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8031537655331857
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8168069966906343
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8078549989079483
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8195679102426064
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5951512690504269
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5992430550243973
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8078549989079483
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8327625705936669
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 768
+      type: sts-test-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8259116102299048
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8420103291660583
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8417036739734224
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.839403978426242
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8416944892693242
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8392814362849023
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6531059298507882
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6395643411764597
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8417036739734224
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8420103291660583
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 512
+      type: sts-test-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8243325623482549
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8417788357334501
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8405895269265039
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8387513037939833
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8405749756794761
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8386191956000736
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6577547074460394
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6453398362527448
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8405895269265039
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8417788357334501
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8128490933340125
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8343525276981816
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8349925426973063
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8339373046648948
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8349685334828352
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8342389147888624
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6010530472572276
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5827176472260001
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8349925426973063
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8343525276981816
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8037074044935162
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8297484250803338
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8282523311738189
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8292579770469635
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.828555014804415
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8294547431431344
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.579341375708575
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5659659830073487
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.828555014804415
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8297484250803338
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.7861572380387101
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8221344542757412
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8179044736790866
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8218843830925717
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8199399298670013
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8240682904452457
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5115276911122266
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5024074247877125
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8199399298670013
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8240682904452457
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 32
+      type: sts-test-32
+    metrics:
+    - type: pearson_cosine
+      value: 0.7616404560065974
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8126281001961144
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7995560120404742
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8084393007868024
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8024415842761214
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8115677983458126
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.4646775610104062
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.451018702626726
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8024415842761214
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8126281001961144
+      name: Spearman Max
+---
+
+# SentenceTransformer based on distilbert/distilbert-base-uncased
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) 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:** [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) <!-- at revision 12040accade4e8a0f71eabdb258fecc2e7e948be -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 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: DistilBertModel 
+  (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("mrm8488/distilbert-base-matryoshka-sts")
+# Run inference
+sentences = [
+    'A baby is laughing.',
+    'The baby laughed in his car seat.',
+    'A brown horse in a green field.',
+]
+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
+
+#### 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      | 0.8597     |
+| **spearman_cosine** | **0.8705** |
+| pearson_manhattan   | 0.8577     |
+| spearman_manhattan  | 0.8613     |
+| pearson_euclidean   | 0.8574     |
+| spearman_euclidean  | 0.8611     |
+| pearson_dot         | 0.7231     |
+| spearman_dot        | 0.7293     |
+| pearson_max         | 0.8597     |
+| spearman_max        | 0.8705     |
+
+#### 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      | 0.8566    |
+| **spearman_cosine** | **0.869** |
+| pearson_manhattan   | 0.8561    |
+| spearman_manhattan  | 0.8602    |
+| pearson_euclidean   | 0.856     |
+| spearman_euclidean  | 0.8598    |
+| pearson_dot         | 0.7251    |
+| spearman_dot        | 0.7325    |
+| pearson_max         | 0.8566    |
+| spearman_max        | 0.869     |
+
+#### 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      | 0.8509     |
+| **spearman_cosine** | **0.8656** |
+| pearson_manhattan   | 0.8516     |
+| spearman_manhattan  | 0.8576     |
+| pearson_euclidean   | 0.8513     |
+| spearman_euclidean  | 0.8567     |
+| pearson_dot         | 0.6913     |
+| spearman_dot        | 0.6984     |
+| pearson_max         | 0.8516     |
+| spearman_max        | 0.8656     |
+
+#### 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      | 0.8416     |
+| **spearman_cosine** | **0.8626** |
+| pearson_manhattan   | 0.841      |
+| spearman_manhattan  | 0.8496     |
+| pearson_euclidean   | 0.8432     |
+| spearman_euclidean  | 0.8506     |
+| pearson_dot         | 0.6776     |
+| spearman_dot        | 0.6865     |
+| pearson_max         | 0.8432     |
+| spearman_max        | 0.8626     |
+
+#### 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      | 0.8232     |
+| **spearman_cosine** | **0.8523** |
+| pearson_manhattan   | 0.8255     |
+| spearman_manhattan  | 0.8358     |
+| pearson_euclidean   | 0.8292     |
+| spearman_euclidean  | 0.8385     |
+| pearson_dot         | 0.6416     |
+| spearman_dot        | 0.6564     |
+| pearson_max         | 0.8292     |
+| spearman_max        | 0.8523     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-32`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7903     |
+| **spearman_cosine** | **0.8328** |
+| pearson_manhattan   | 0.8032     |
+| spearman_manhattan  | 0.8168     |
+| pearson_euclidean   | 0.8079     |
+| spearman_euclidean  | 0.8196     |
+| pearson_dot         | 0.5952     |
+| spearman_dot        | 0.5992     |
+| pearson_max         | 0.8079     |
+| spearman_max        | 0.8328     |
+
+#### 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      | 0.8259    |
+| **spearman_cosine** | **0.842** |
+| pearson_manhattan   | 0.8417    |
+| spearman_manhattan  | 0.8394    |
+| pearson_euclidean   | 0.8417    |
+| spearman_euclidean  | 0.8393    |
+| pearson_dot         | 0.6531    |
+| spearman_dot        | 0.6396    |
+| pearson_max         | 0.8417    |
+| spearman_max        | 0.842     |
+
+#### 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      | 0.8243     |
+| **spearman_cosine** | **0.8418** |
+| pearson_manhattan   | 0.8406     |
+| spearman_manhattan  | 0.8388     |
+| pearson_euclidean   | 0.8406     |
+| spearman_euclidean  | 0.8386     |
+| pearson_dot         | 0.6578     |
+| spearman_dot        | 0.6453     |
+| pearson_max         | 0.8406     |
+| spearman_max        | 0.8418     |
+
+#### 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      | 0.8128     |
+| **spearman_cosine** | **0.8344** |
+| pearson_manhattan   | 0.835      |
+| spearman_manhattan  | 0.8339     |
+| pearson_euclidean   | 0.835      |
+| spearman_euclidean  | 0.8342     |
+| pearson_dot         | 0.6011     |
+| spearman_dot        | 0.5827     |
+| pearson_max         | 0.835      |
+| spearman_max        | 0.8344     |
+
+#### 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      | 0.8037     |
+| **spearman_cosine** | **0.8297** |
+| pearson_manhattan   | 0.8283     |
+| spearman_manhattan  | 0.8293     |
+| pearson_euclidean   | 0.8286     |
+| spearman_euclidean  | 0.8295     |
+| pearson_dot         | 0.5793     |
+| spearman_dot        | 0.566      |
+| pearson_max         | 0.8286     |
+| spearman_max        | 0.8297     |
+
+#### 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      | 0.7862     |
+| **spearman_cosine** | **0.8221** |
+| pearson_manhattan   | 0.8179     |
+| spearman_manhattan  | 0.8219     |
+| pearson_euclidean   | 0.8199     |
+| spearman_euclidean  | 0.8241     |
+| pearson_dot         | 0.5115     |
+| spearman_dot        | 0.5024     |
+| pearson_max         | 0.8199     |
+| spearman_max        | 0.8241     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-32`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7616     |
+| **spearman_cosine** | **0.8126** |
+| pearson_manhattan   | 0.7996     |
+| spearman_manhattan  | 0.8084     |
+| pearson_euclidean   | 0.8024     |
+| spearman_euclidean  | 0.8116     |
+| pearson_dot         | 0.4647     |
+| spearman_dot        | 0.451      |
+| pearson_max         | 0.8024     |
+| spearman_max        | 0.8126     |
+
+<!--
+## 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: 10.0 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 9.95 tokens</li><li>max: 25 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,
+          32
+      ],
+      "matryoshka_weights": [
+          1,
+          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: 15.1 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.11 tokens</li><li>max: 53 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,
+          32
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 4
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_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`: 4
+- `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
+- `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-32_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-32_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
+|:------:|:----:|:-------------:|:-------:|:---------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
+| 0.2778 | 100  | 28.2763       | 26.3514 | 0.8250                      | 0.8306                      | 0.7893                     | 0.8308                      | 0.8094                     | 0.8314                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 0.5556 | 200  | 26.3731       | 26.0000 | 0.8373                      | 0.8412                      | 0.8026                     | 0.8463                      | 0.8267                     | 0.8467                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 0.8333 | 300  | 26.0243       | 26.5062 | 0.8434                      | 0.8495                      | 0.8073                     | 0.8534                      | 0.8297                     | 0.8556                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 1.1111 | 400  | 25.3448       | 28.1742 | 0.8496                      | 0.8544                      | 0.8157                     | 0.8593                      | 0.8361                     | 0.8611                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 1.3889 | 500  | 24.7922       | 27.0245 | 0.8488                      | 0.8529                      | 0.8149                     | 0.8574                      | 0.8352                     | 0.8589                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 1.6667 | 600  | 24.7596       | 26.9771 | 0.8516                      | 0.8558                      | 0.8199                     | 0.8601                      | 0.8389                     | 0.8619                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 1.9444 | 700  | 24.7165       | 26.2923 | 0.8602                      | 0.8634                      | 0.8277                     | 0.8665                      | 0.8476                     | 0.8681                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 2.2222 | 800  | 23.7934       | 27.9207 | 0.8570                      | 0.8608                      | 0.8263                     | 0.8640                      | 0.8460                     | 0.8656                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 2.5    | 900  | 23.4618       | 27.5855 | 0.8583                      | 0.8618                      | 0.8257                     | 0.8657                      | 0.8456                     | 0.8675                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 2.7778 | 1000 | 23.1831       | 29.9791 | 0.8533                      | 0.8557                      | 0.8232                     | 0.8599                      | 0.8411                     | 0.8612                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 3.0556 | 1100 | 23.1935       | 28.7866 | 0.8612                      | 0.8636                      | 0.8329                     | 0.8677                      | 0.8504                     | 0.8689                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 3.3333 | 1200 | 22.1447       | 30.0641 | 0.8597                      | 0.8630                      | 0.8285                     | 0.8661                      | 0.8488                     | 0.8676                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 3.6111 | 1300 | 21.9271       | 30.9347 | 0.8613                      | 0.8648                      | 0.8309                     | 0.8679                      | 0.8509                     | 0.8697                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 3.8889 | 1400 | 21.973        | 30.9209 | 0.8626                      | 0.8656                      | 0.8328                     | 0.8690                      | 0.8523                     | 0.8705                      | -                            | -                            | -                           | -                            | -                           | -                            |
+| 4.0    | 1440 | -             | -       | -                           | -                           | -                          | -                           | -                          | -                           | 0.8297                       | 0.8344                       | 0.8126                      | 0.8418                       | 0.8221                      | 0.8420                       |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.1
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### 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 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.1",
+    "pytorch": "2.3.0+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 sha256:55378706b1488589936650f2a54a73ba783faa33b67fa354d08c87ed0e055942
+size 265462608

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 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}