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 +1,981 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:10K<n<100K
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: l3cube-pune/indic-sentence-similarity-sbert
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Excuse me.
+  sentences:
+  - um pardon me
+  - A man is opening mail.
+  - The girls are indoors.
+- source_sentence: Double pig.
+  sentences:
+  - Ah, triple pig!
+  - a girl poses for camera
+  - Girls dance together.
+- source_sentence: People pose.
+  sentences:
+  - People are smiling.
+  - I know a few old ones.
+  - The boy fell off his bike.
+- source_sentence: A man sings.
+  sentences:
+  - People singing
+  - A man is playing golf.
+  - The women are eating bread.
+- source_sentence: Then he ran.
+  sentences:
+  - He then started to run.
+  - A man plays the flute.
+  - A couple sit on the couch
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on l3cube-pune/indic-sentence-similarity-sbert
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 768
+      type: sts-dev-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8608857207512975
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8662860178080238
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.858692209351004
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8612472945208892
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.858472048314985
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8611276457994067
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8258747949887901
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8259736371824636
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8608857207512975
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8662860178080238
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8594405198312016
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8648571300070264
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8574291650964095
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8598780673781499
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8574540367546871
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8600722932569861
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.822340474813523
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8226609928783558
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8594405198312016
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8648571300070264
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8506120561071212
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8575982860981437
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.852829777566948
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8552667517015687
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8526934293405145
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8551077930316164
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7943956137623474
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7963976287579885
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.852829777566948
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8575982860981437
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 128
+      type: sts-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8410977354989039
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.850480817077266
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8461619224798919
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8490393633313068
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8458138708136093
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.848719989437845
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7755878071062363
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7755629190322909
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8461619224798919
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.850480817077266
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 64
+      type: sts-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.8176550213032908
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8307913870285043
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8291830276998975
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8320477651805375
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8311109004860973
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8333955109708812
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7153413665605783
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7181274999679498
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8311109004860973
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8333955109708812
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 768
+      type: sts-test-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8491592809545866
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8568871215102605
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8572052385387118
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.856617432589014
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8568623186549655
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8567096295439565
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7968828934121807
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7879173370882538
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8572052385387118
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8568871215102605
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 512
+      type: sts-test-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8507070298067174
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8575370129160172
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8564033014649287
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8560352984315738
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8561906595447021
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8560701630452845
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7973312469719326
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7873345752731498
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8564033014649287
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8575370129160172
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8467375811334358
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8523459221020806
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8515524299355154
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8516309696270962
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8505975029491393
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8504082169041302
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7756647219222156
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7687165011432322
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8515524299355154
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8523459221020806
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8377317518267889
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.84715184876888
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.846568244977152
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8487991796570058
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8456229087328332
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.847227591472
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7502527212449147
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7415962106597614
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.846568244977152
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8487991796570058
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.8173604263806156
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8315612974155435
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8319781289166863
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8347311175148256
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8334921243463637
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8350960592133633
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6935445265890855
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6843746062699552
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8334921243463637
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8350960592133633
+      name: Spearman Max
+---
+
+# SentenceTransformer based on l3cube-pune/indic-sentence-similarity-sbert
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [l3cube-pune/indic-sentence-similarity-sbert](https://huggingface.co/l3cube-pune/indic-sentence-similarity-sbert) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) 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:** [l3cube-pune/indic-sentence-similarity-sbert](https://huggingface.co/l3cube-pune/indic-sentence-similarity-sbert) <!-- at revision b07ef91a96390f3e35ce94ddb42340861519bf07 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
+- **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: 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})
+)
+```
+
+## 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("ammumadhu/indic-bert-nli-matryoshka")
+# Run inference
+sentences = [
+    'Then he ran.',
+    'He then started to run.',
+    'A man plays the flute.',
+]
+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      | 0.8609     |
+| **spearman_cosine** | **0.8663** |
+| pearson_manhattan   | 0.8587     |
+| spearman_manhattan  | 0.8612     |
+| pearson_euclidean   | 0.8585     |
+| spearman_euclidean  | 0.8611     |
+| pearson_dot         | 0.8259     |
+| spearman_dot        | 0.826      |
+| pearson_max         | 0.8609     |
+| spearman_max        | 0.8663     |
+
+#### 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      | 0.8594     |
+| **spearman_cosine** | **0.8649** |
+| pearson_manhattan   | 0.8574     |
+| spearman_manhattan  | 0.8599     |
+| pearson_euclidean   | 0.8575     |
+| spearman_euclidean  | 0.8601     |
+| pearson_dot         | 0.8223     |
+| spearman_dot        | 0.8227     |
+| pearson_max         | 0.8594     |
+| spearman_max        | 0.8649     |
+
+#### 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      | 0.8506     |
+| **spearman_cosine** | **0.8576** |
+| pearson_manhattan   | 0.8528     |
+| spearman_manhattan  | 0.8553     |
+| pearson_euclidean   | 0.8527     |
+| spearman_euclidean  | 0.8551     |
+| pearson_dot         | 0.7944     |
+| spearman_dot        | 0.7964     |
+| pearson_max         | 0.8528     |
+| spearman_max        | 0.8576     |
+
+#### 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      | 0.8411     |
+| **spearman_cosine** | **0.8505** |
+| pearson_manhattan   | 0.8462     |
+| spearman_manhattan  | 0.849      |
+| pearson_euclidean   | 0.8458     |
+| spearman_euclidean  | 0.8487     |
+| pearson_dot         | 0.7756     |
+| spearman_dot        | 0.7756     |
+| pearson_max         | 0.8462     |
+| spearman_max        | 0.8505     |
+
+#### 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      | 0.8177     |
+| **spearman_cosine** | **0.8308** |
+| pearson_manhattan   | 0.8292     |
+| spearman_manhattan  | 0.832      |
+| pearson_euclidean   | 0.8311     |
+| spearman_euclidean  | 0.8334     |
+| pearson_dot         | 0.7153     |
+| spearman_dot        | 0.7181     |
+| pearson_max         | 0.8311     |
+| spearman_max        | 0.8334     |
+
+#### 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      | 0.8492     |
+| **spearman_cosine** | **0.8569** |
+| pearson_manhattan   | 0.8572     |
+| spearman_manhattan  | 0.8566     |
+| pearson_euclidean   | 0.8569     |
+| spearman_euclidean  | 0.8567     |
+| pearson_dot         | 0.7969     |
+| spearman_dot        | 0.7879     |
+| pearson_max         | 0.8572     |
+| spearman_max        | 0.8569     |
+
+#### 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      | 0.8507     |
+| **spearman_cosine** | **0.8575** |
+| pearson_manhattan   | 0.8564     |
+| spearman_manhattan  | 0.856      |
+| pearson_euclidean   | 0.8562     |
+| spearman_euclidean  | 0.8561     |
+| pearson_dot         | 0.7973     |
+| spearman_dot        | 0.7873     |
+| pearson_max         | 0.8564     |
+| spearman_max        | 0.8575     |
+
+#### 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      | 0.8467     |
+| **spearman_cosine** | **0.8523** |
+| pearson_manhattan   | 0.8516     |
+| spearman_manhattan  | 0.8516     |
+| pearson_euclidean   | 0.8506     |
+| spearman_euclidean  | 0.8504     |
+| pearson_dot         | 0.7757     |
+| spearman_dot        | 0.7687     |
+| pearson_max         | 0.8516     |
+| spearman_max        | 0.8523     |
+
+#### 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      | 0.8377     |
+| **spearman_cosine** | **0.8472** |
+| pearson_manhattan   | 0.8466     |
+| spearman_manhattan  | 0.8488     |
+| pearson_euclidean   | 0.8456     |
+| spearman_euclidean  | 0.8472     |
+| pearson_dot         | 0.7503     |
+| spearman_dot        | 0.7416     |
+| pearson_max         | 0.8466     |
+| spearman_max        | 0.8488     |
+
+#### 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      | 0.8174     |
+| **spearman_cosine** | **0.8316** |
+| pearson_manhattan   | 0.832      |
+| spearman_manhattan  | 0.8347     |
+| pearson_euclidean   | 0.8335     |
+| spearman_euclidean  | 0.8351     |
+| pearson_dot         | 0.6935     |
+| spearman_dot        | 0.6844     |
+| pearson_max         | 0.8335     |
+| spearman_max        | 0.8351     |
+
+<!--
+## 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/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 10,000 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                          | negative                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 18.8 tokens</li><li>max: 89 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.84 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 12.39 tokens</li><li>max: 38 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                    | positive                                          | negative                                               |
+  |:----------------------------------------------------------------------------------------------------------|:--------------------------------------------------|:-------------------------------------------------------|
+  | <code>Side view of a female triathlete during the run.</code>                                             | <code>A woman runs</code>                         | <code>A man sits</code>                                |
+  | <code>Confused person standing in the middle of the trolley tracks trying to figure out the signs.</code> | <code>A person is on the tracks.</code>           | <code>A man sits in an airplane.</code>                |
+  | <code>A woman in a black shirt, jean shorts and white tennis shoes is bowling.</code>                     | <code>A woman is bowling in casual clothes</code> | <code>A woman bowling wins an outfit of clothes</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
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 6,584 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                         | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 18.54 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.97 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.59 tokens</li><li>max: 29 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                         | positive                                                    | negative                                                |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:--------------------------------------------------------|
+  | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>Two woman are holding packages.</code>                | <code>The men are fighting outside a deli.</code>       |
+  | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code>        |
+  | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code>                                                                    | <code>A man selling donuts to a customer.</code>            | <code>A woman drinks her coffee in a small cafe.</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`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### 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`: 128
+- `per_device_eval_batch_size`: 128
+- `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`: 1
+- `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`: no_duplicates
+- `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 |
+|:------:|:----:|:-------------:|:------:|:---------------------------:|:---------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
+| 0.3797 | 30   | 7.9432        | 4.2806 | 0.8509                      | 0.8570                      | 0.8633                      | 0.8311                     | 0.8644                      | -                            | -                            | -                            | -                           | -                            |
+| 0.7595 | 60   | 6.1701        | 3.9498 | 0.8505                      | 0.8576                      | 0.8649                      | 0.8308                     | 0.8663                      | -                            | -                            | -                            | -                           | -                            |
+| 1.0    | 79   | -             | -      | -                           | -                           | -                           | -                          | -                           | 0.8472                       | 0.8523                       | 0.8575                       | 0.8316                      | 0.8569                       |
+
+
+### 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: 2.19.2
+- 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": "l3cube-pune/indic-sentence-similarity-sbert",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "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": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 197285
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.26.1",
+    "pytorch": "1.13.1+cu116"
+  },
+  "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:b7b82af46f5399f2103276c545b9b2cdcd1249f4b411f9d2ec45221df28bd93b
+size 950247272

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 +1,37 @@
+{
+  "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 +1,65 @@
+{
+  "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
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "lowercase": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}