Add new SparseEncoder model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

2_CSRSparsity/config.json

@@ -0,0 +1,8 @@
+{
+    "input_dim": 1024,
+    "hidden_dim": 4096,
+    "k": 256,
+    "k_aux": 512,
+    "normalize": false,
+    "dead_threshold": 30
+}

2_CSRSparsity/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ed77a15b6965493fc2ae4d0a83652288489db8886582a4bf444162be347187
+size 16830864

README.md

@@ -0,0 +1,1150 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sparse-encoder
+- sparse
+- csr
+- generated_from_trainer
+- dataset_size:99000
+- loss:CSRLoss
+- loss:SparseMultipleNegativesRankingLoss
+base_model: mixedbread-ai/mxbai-embed-large-v1
+widget:
+- text: Saudi Arabia–United Arab Emirates relations However, the UAE and Saudi Arabia
+    continue to take somewhat differing stances on regional conflicts such the Yemeni
+    Civil War, where the UAE opposes Al-Islah, and supports the Southern Movement,
+    which has fought against Saudi-backed forces, and the Syrian Civil War, where
+    the UAE has disagreed with Saudi support for Islamist movements.[4]
+- text: Economy of New Zealand New Zealand's diverse market economy has a sizable
+    service sector, accounting for 63% of all GDP activity in 2013.[17] Large scale
+    manufacturing industries include aluminium production, food processing, metal
+    fabrication, wood and paper products. Mining, manufacturing, electricity, gas,
+    water, and waste services accounted for 16.5% of GDP in 2013.[17] The primary
+    sector continues to dominate New Zealand's exports, despite accounting for 6.5%
+    of GDP in 2013.[17]
+- text: who was the first president of indian science congress meeting held in kolkata
+    in 1914
+- text: Get Over It (Eagles song) "Get Over It" is a song by the Eagles released as
+    a single after a fourteen-year breakup. It was also the first song written by
+    bandmates Don Henley and Glenn Frey when the band reunited. "Get Over It" was
+    played live for the first time during their Hell Freezes Over tour in 1994. It
+    returned the band to the U.S. Top 40 after a fourteen-year absence, peaking at
+    No. 31 on the Billboard Hot 100 chart. It also hit No. 4 on the Billboard Mainstream
+    Rock Tracks chart. The song was not played live by the Eagles after the "Hell
+    Freezes Over" tour in 1994. It remains the group's last Top 40 hit in the U.S.
+- text: 'Cornelius the Centurion Cornelius (Greek: Κορνήλιος) was a Roman centurion
+    who is considered by Christians to be one of the first Gentiles to convert to
+    the faith, as related in Acts of the Apostles.'
+datasets:
+- sentence-transformers/natural-questions
+pipeline_tag: feature-extraction
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+- query_active_dims
+- query_sparsity_ratio
+- corpus_active_dims
+- corpus_sparsity_ratio
+co2_eq_emissions:
+  emissions: 40.554498153266884
+  energy_consumed: 0.10433313477488382
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 0.265
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: Sparse CSR model trained on Natural Questions
+  results:
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: nq eval 4
+      type: nq_eval_4
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.305
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.442
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.501
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.61
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.305
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.14733333333333332
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1002
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.061
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.305
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.442
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.501
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.61
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.44361734950305676
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.39226865079365053
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.4023289651029423
+      name: Cosine Map@100
+    - type: query_active_dims
+      value: 4.0
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.9990234375
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 4.0
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.9990234375
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: nq eval 8
+      type: nq_eval_8
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.509
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.696
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.758
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.831
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.509
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.232
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.15159999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0831
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.509
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.696
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.758
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.831
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6667307022062331
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6143956349206346
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6199605197356874
+      name: Cosine Map@100
+    - type: query_active_dims
+      value: 8.0
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.998046875
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 8.0
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.998046875
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: nq eval 16
+      type: nq_eval_16
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.686
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.837
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.88
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.925
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.686
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.279
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.176
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09250000000000001
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.686
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.837
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.88
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.925
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8078628031678144
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7699809523809527
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7734418631171641
+      name: Cosine Map@100
+    - type: query_active_dims
+      value: 16.0
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.99609375
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 16.0
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.99609375
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: nq eval 32
+      type: nq_eval_32
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.82
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.916
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.941
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.965
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.82
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.30533333333333323
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18820000000000003
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09650000000000003
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.82
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.916
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.941
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.965
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8959815252151966
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8735440476190476
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8753779462223106
+      name: Cosine Map@100
+    - type: query_active_dims
+      value: 32.0
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.9921875
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 32.0
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.9921875
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: nq eval 64
+      type: nq_eval_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.884
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.963
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.976
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.986
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.884
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.32099999999999995
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19520000000000004
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09860000000000002
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.884
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.963
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.976
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.986
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9404409421950981
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9252813492063495
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.92604431847803
+      name: Cosine Map@100
+    - type: query_active_dims
+      value: 64.0
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.984375
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 64.0
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.984375
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: nq eval 128
+      type: nq_eval_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.921
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.981
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.988
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.993
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.921
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.32699999999999996
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19760000000000003
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09930000000000001
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.921
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.981
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.988
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.993
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9613681085985268
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.950713492063492
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9509802020874972
+      name: Cosine Map@100
+    - type: query_active_dims
+      value: 128.0
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.96875
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 128.0
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.96875
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: nq eval 256
+      type: nq_eval_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.94
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.983
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.989
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.994
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.94
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3276666666666666
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19780000000000003
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0994
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.94
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.983
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.989
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.994
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9701540897990301
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9621623015873015
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9622774531024532
+      name: Cosine Map@100
+    - type: query_active_dims
+      value: 256.0
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.9375
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 256.0
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.9375
+      name: Corpus Sparsity Ratio
+---
+
+# Sparse CSR model trained on Natural Questions
+
+This is a [CSR Sparse Encoder](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) model finetuned from [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) on the [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) dataset using the [sentence-transformers](https://www.SBERT.net) library. It maps sentences & paragraphs to a 4096-dimensional sparse vector space  with 256 maximum active dimensions  and can be used for semantic search and sparse retrieval.
+## Model Details
+
+### Model Description
+- **Model Type:** CSR Sparse Encoder
+- **Base model:** [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) <!-- at revision db9d1fe0f31addb4978201b2bf3e577f3f8900d2 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 4096 dimensions (trained with 256 maximum active dimensions)
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions)
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Documentation:** [Sparse Encoder Documentation](https://www.sbert.net/docs/sparse_encoder/usage/usage.html)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sparse Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=sparse-encoder)
+
+### Full Model Architecture
+
+```
+SparseEncoder(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): CSRSparsity({'input_dim': 1024, 'hidden_dim': 4096, 'k': 256, 'k_aux': 512, 'normalize': False, 'dead_threshold': 30})
+)
+```
+
+## 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 SparseEncoder
+
+# Download from the 🤗 Hub
+model = SparseEncoder("tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-20-gamma-0.5-detach-2")
+# Run inference
+queries = [
+    "who is cornelius in the book of acts",
+]
+documents = [
+    'Cornelius the Centurion Cornelius (Greek: Κορνήλιος) was a Roman centurion who is considered by Christians to be one of the first Gentiles to convert to the faith, as related in Acts of the Apostles.',
+    "Joe Ranft Ranft reunited with Lasseter when he was hired by Pixar in 1991 as their head of story.[1] There he worked on all of their films produced up to 2006; this included Toy Story (for which he received an Academy Award nomination) and A Bug's Life, as the co-story writer and others as story supervisor. His final film was Cars. He also voiced characters in many of the films, including Heimlich the caterpillar in A Bug's Life, Wheezy the penguin in Toy Story 2, and Jacques the shrimp in Finding Nemo.[1]",
+    'Wonderful Tonight "Wonderful Tonight" is a ballad written by Eric Clapton. It was included on Clapton\'s 1977 album Slowhand. Clapton wrote the song about Pattie Boyd.[1] The female vocal harmonies on the song are provided by Marcella Detroit (then Marcy Levy) and Yvonne Elliman.',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 4096] [3, 4096]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[0.7220, 0.2012, 0.1931]])
+```
+
+<!--
+### 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
+
+#### Sparse Information Retrieval
+
+* Dataset: `nq_eval_4`
+* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "max_active_dims": 4
+  }
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| cosine_accuracy@1     | 0.305      |
+| cosine_accuracy@3     | 0.442      |
+| cosine_accuracy@5     | 0.501      |
+| cosine_accuracy@10    | 0.61       |
+| cosine_precision@1    | 0.305      |
+| cosine_precision@3    | 0.1473     |
+| cosine_precision@5    | 0.1002     |
+| cosine_precision@10   | 0.061      |
+| cosine_recall@1       | 0.305      |
+| cosine_recall@3       | 0.442      |
+| cosine_recall@5       | 0.501      |
+| cosine_recall@10      | 0.61       |
+| **cosine_ndcg@10**    | **0.4436** |
+| cosine_mrr@10         | 0.3923     |
+| cosine_map@100        | 0.4023     |
+| query_active_dims     | 4.0        |
+| query_sparsity_ratio  | 0.999      |
+| corpus_active_dims    | 4.0        |
+| corpus_sparsity_ratio | 0.999      |
+
+#### Sparse Information Retrieval
+
+* Dataset: `nq_eval_8`
+* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "max_active_dims": 8
+  }
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| cosine_accuracy@1     | 0.509      |
+| cosine_accuracy@3     | 0.696      |
+| cosine_accuracy@5     | 0.758      |
+| cosine_accuracy@10    | 0.831      |
+| cosine_precision@1    | 0.509      |
+| cosine_precision@3    | 0.232      |
+| cosine_precision@5    | 0.1516     |
+| cosine_precision@10   | 0.0831     |
+| cosine_recall@1       | 0.509      |
+| cosine_recall@3       | 0.696      |
+| cosine_recall@5       | 0.758      |
+| cosine_recall@10      | 0.831      |
+| **cosine_ndcg@10**    | **0.6667** |
+| cosine_mrr@10         | 0.6144     |
+| cosine_map@100        | 0.62       |
+| query_active_dims     | 8.0        |
+| query_sparsity_ratio  | 0.998      |
+| corpus_active_dims    | 8.0        |
+| corpus_sparsity_ratio | 0.998      |
+
+#### Sparse Information Retrieval
+
+* Dataset: `nq_eval_16`
+* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "max_active_dims": 16
+  }
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| cosine_accuracy@1     | 0.686      |
+| cosine_accuracy@3     | 0.837      |
+| cosine_accuracy@5     | 0.88       |
+| cosine_accuracy@10    | 0.925      |
+| cosine_precision@1    | 0.686      |
+| cosine_precision@3    | 0.279      |
+| cosine_precision@5    | 0.176      |
+| cosine_precision@10   | 0.0925     |
+| cosine_recall@1       | 0.686      |
+| cosine_recall@3       | 0.837      |
+| cosine_recall@5       | 0.88       |
+| cosine_recall@10      | 0.925      |
+| **cosine_ndcg@10**    | **0.8079** |
+| cosine_mrr@10         | 0.77       |
+| cosine_map@100        | 0.7734     |
+| query_active_dims     | 16.0       |
+| query_sparsity_ratio  | 0.9961     |
+| corpus_active_dims    | 16.0       |
+| corpus_sparsity_ratio | 0.9961     |
+
+#### Sparse Information Retrieval
+
+* Dataset: `nq_eval_32`
+* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "max_active_dims": 32
+  }
+  ```
+
+| Metric                | Value     |
+|:----------------------|:----------|
+| cosine_accuracy@1     | 0.82      |
+| cosine_accuracy@3     | 0.916     |
+| cosine_accuracy@5     | 0.941     |
+| cosine_accuracy@10    | 0.965     |
+| cosine_precision@1    | 0.82      |
+| cosine_precision@3    | 0.3053    |
+| cosine_precision@5    | 0.1882    |
+| cosine_precision@10   | 0.0965    |
+| cosine_recall@1       | 0.82      |
+| cosine_recall@3       | 0.916     |
+| cosine_recall@5       | 0.941     |
+| cosine_recall@10      | 0.965     |
+| **cosine_ndcg@10**    | **0.896** |
+| cosine_mrr@10         | 0.8735    |
+| cosine_map@100        | 0.8754    |
+| query_active_dims     | 32.0      |
+| query_sparsity_ratio  | 0.9922    |
+| corpus_active_dims    | 32.0      |
+| corpus_sparsity_ratio | 0.9922    |
+
+#### Sparse Information Retrieval
+
+* Dataset: `nq_eval_64`
+* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "max_active_dims": 64
+  }
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| cosine_accuracy@1     | 0.884      |
+| cosine_accuracy@3     | 0.963      |
+| cosine_accuracy@5     | 0.976      |
+| cosine_accuracy@10    | 0.986      |
+| cosine_precision@1    | 0.884      |
+| cosine_precision@3    | 0.321      |
+| cosine_precision@5    | 0.1952     |
+| cosine_precision@10   | 0.0986     |
+| cosine_recall@1       | 0.884      |
+| cosine_recall@3       | 0.963      |
+| cosine_recall@5       | 0.976      |
+| cosine_recall@10      | 0.986      |
+| **cosine_ndcg@10**    | **0.9404** |
+| cosine_mrr@10         | 0.9253     |
+| cosine_map@100        | 0.926      |
+| query_active_dims     | 64.0       |
+| query_sparsity_ratio  | 0.9844     |
+| corpus_active_dims    | 64.0       |
+| corpus_sparsity_ratio | 0.9844     |
+
+#### Sparse Information Retrieval
+
+* Dataset: `nq_eval_128`
+* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "max_active_dims": 128
+  }
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| cosine_accuracy@1     | 0.921      |
+| cosine_accuracy@3     | 0.981      |
+| cosine_accuracy@5     | 0.988      |
+| cosine_accuracy@10    | 0.993      |
+| cosine_precision@1    | 0.921      |
+| cosine_precision@3    | 0.327      |
+| cosine_precision@5    | 0.1976     |
+| cosine_precision@10   | 0.0993     |
+| cosine_recall@1       | 0.921      |
+| cosine_recall@3       | 0.981      |
+| cosine_recall@5       | 0.988      |
+| cosine_recall@10      | 0.993      |
+| **cosine_ndcg@10**    | **0.9614** |
+| cosine_mrr@10         | 0.9507     |
+| cosine_map@100        | 0.951      |
+| query_active_dims     | 128.0      |
+| query_sparsity_ratio  | 0.9688     |
+| corpus_active_dims    | 128.0      |
+| corpus_sparsity_ratio | 0.9688     |
+
+#### Sparse Information Retrieval
+
+* Dataset: `nq_eval_256`
+* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "max_active_dims": 256
+  }
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| cosine_accuracy@1     | 0.94       |
+| cosine_accuracy@3     | 0.983      |
+| cosine_accuracy@5     | 0.989      |
+| cosine_accuracy@10    | 0.994      |
+| cosine_precision@1    | 0.94       |
+| cosine_precision@3    | 0.3277     |
+| cosine_precision@5    | 0.1978     |
+| cosine_precision@10   | 0.0994     |
+| cosine_recall@1       | 0.94       |
+| cosine_recall@3       | 0.983      |
+| cosine_recall@5       | 0.989      |
+| cosine_recall@10      | 0.994      |
+| **cosine_ndcg@10**    | **0.9702** |
+| cosine_mrr@10         | 0.9622     |
+| cosine_map@100        | 0.9623     |
+| query_active_dims     | 256.0      |
+| query_sparsity_ratio  | 0.9375     |
+| corpus_active_dims    | 256.0      |
+| corpus_sparsity_ratio | 0.9375     |
+
+<!--
+## 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
+
+#### natural-questions
+
+* Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
+* Size: 99,000 training samples
+* Columns: <code>query</code> and <code>answer</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | answer                                                                              |
+  |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                              |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 11.71 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 131.81 tokens</li><li>max: 450 tokens</li></ul> |
+* Samples:
+  | query                                                         | answer                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+  |:--------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>who played the father in papa don't preach</code>       | <code>Alex McArthur Alex McArthur (born March 6, 1957) is an American actor.</code>                                                                                                                                                                                                                                                                                                                                                     |
+  | <code>where was the location of the battle of hastings</code> | <code>Battle of Hastings The Battle of Hastings[a] was fought on 14 October 1066 between the Norman-French army of William, the Duke of Normandy, and an English army under the Anglo-Saxon King Harold Godwinson, beginning the Norman conquest of England. It took place approximately 7 miles (11 kilometres) northwest of Hastings, close to the present-day town of Battle, East Sussex, and was a decisive Norman victory.</code> |
+  | <code>how many puppies can a dog give birth to</code>         | <code>Canine reproduction The largest litter size to date was set by a Neapolitan Mastiff in Manea, Cambridgeshire, UK on November 29, 2004; the litter was 24 puppies.[22]</code>                                                                                                                                                                                                                                                      |
+* Loss: [<code>CSRLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#csrloss) with these parameters:
+  ```json
+  {
+      "beta": 0.1,
+      "gamma": 0.5,
+      "loss": "SparseMultipleNegativesRankingLoss(scale=20.0, similarity_fct='cos_sim')"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### natural-questions
+
+* Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
+* Size: 1,000 evaluation samples
+* Columns: <code>query</code> and <code>answer</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | answer                                                                               |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                               |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 11.69 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 134.01 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | query                                                  | answer                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+  |:-------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>where is the tiber river located in italy</code> | <code>Tiber The Tiber (/ˈtaɪbər/, Latin: Tiberis,[1] Italian: Tevere [ˈteːvere])[2] is the third-longest river in Italy, rising in the Apennine Mountains in Emilia-Romagna and flowing 406 kilometres (252 mi) through Tuscany, Umbria and Lazio, where it is joined by the river Aniene, to the Tyrrhenian Sea, between Ostia and Fiumicino.[3] It drains a basin estimated at 17,375 square kilometres (6,709 sq mi). The river has achieved lasting fame as the main watercourse of the city of Rome, founded on its eastern banks.</code> |
+  | <code>what kind of car does jay gatsby drive</code>    | <code>Jay Gatsby At the Buchanan home, Jordan Baker, Nick, Jay, and the Buchanans decide to visit New York City. Tom borrows Gatsby's yellow Rolls Royce to drive up to the city. On the way to New York City, Tom makes a detour at a gas station in "the Valley of Ashes", a run-down part of Long Island. The owner, George Wilson, shares his concern that his wife, Myrtle, may be having an affair. This unnerves Tom, who has been having an affair with Myrtle, and he leaves in a hurry.</code>                                       |
+  | <code>who sings if i can dream about you</code>        | <code>I Can Dream About You "I Can Dream About You" is a song performed by American singer Dan Hartman on the soundtrack album of the film Streets of Fire. Released in 1984 as a single from the soundtrack, and included on Hartman's album I Can Dream About You, it reached number 6 on the Billboard Hot 100.[1]</code>                                                                                                                                                                                                                   |
+* Loss: [<code>CSRLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#csrloss) with these parameters:
+  ```json
+  {
+      "beta": 0.1,
+      "gamma": 0.5,
+      "loss": "SparseMultipleNegativesRankingLoss(scale=20.0, similarity_fct='cos_sim')"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 4e-05
+- `num_train_epochs`: 1
+- `bf16`: 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`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: 4e-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`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: 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`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | nq_eval_4_cosine_ndcg@10 | nq_eval_8_cosine_ndcg@10 | nq_eval_16_cosine_ndcg@10 | nq_eval_32_cosine_ndcg@10 | nq_eval_64_cosine_ndcg@10 | nq_eval_128_cosine_ndcg@10 | nq_eval_256_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:------------------------:|:------------------------:|:-------------------------:|:-------------------------:|:-------------------------:|:--------------------------:|:--------------------------:|
+| -1     | -1   | -             | -               | 0.2777                   | 0.4704                   | 0.6864                    | 0.8601                    | 0.9349                    | 0.9649                     | 0.9767                     |
+| 0.0646 | 100  | 0.4911        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.1293 | 200  | 0.4186        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.1939 | 300  | 0.3902        | 0.3351          | 0.3779                   | 0.5968                   | 0.7846                    | 0.8949                    | 0.9390                    | 0.9646                     | 0.9688                     |
+| 0.2586 | 400  | 0.3749        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.3232 | 500  | 0.3655        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.3878 | 600  | 0.3589        | 0.3161          | 0.4119                   | 0.6464                   | 0.7897                    | 0.8984                    | 0.9380                    | 0.9643                     | 0.9680                     |
+| 0.4525 | 700  | 0.3509        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.5171 | 800  | 0.3457        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.5818 | 900  | 0.3431        | 0.3065          | 0.4460                   | 0.6674                   | 0.8094                    | 0.8942                    | 0.9381                    | 0.9613                     | 0.9691                     |
+| 0.6464 | 1000 | 0.3403        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.7111 | 1100 | 0.3344        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.7757 | 1200 | 0.3341        | 0.3015          | 0.4458                   | 0.6664                   | 0.8050                    | 0.8976                    | 0.9414                    | 0.9586                     | 0.9659                     |
+| 0.8403 | 1300 | 0.3362        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.9050 | 1400 | 0.3303        | -               | -                        | -                        | -                         | -                         | -                         | -                          | -                          |
+| 0.9696 | 1500 | 0.3316        | 0.2991          | 0.4417                   | 0.6641                   | 0.8096                    | 0.8958                    | 0.9399                    | 0.9631                     | 0.9698                     |
+| -1     | -1   | -             | -               | 0.4436                   | 0.6667                   | 0.8079                    | 0.8960                    | 0.9404                    | 0.9614                     | 0.9702                     |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.104 kWh
+- **Carbon Emitted**: 0.041 kg of CO2
+- **Hours Used**: 0.264 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 4.2.0.dev0
+- Transformers: 4.52.4
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.5.1
+- Datasets: 2.21.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### CSRLoss
+```bibtex
+@misc{wen2025matryoshkarevisitingsparsecoding,
+      title={Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation},
+      author={Tiansheng Wen and Yifei Wang and Zequn Zeng and Zhong Peng and Yudi Su and Xinyang Liu and Bo Chen and Hongwei Liu and Stefanie Jegelka and Chenyu You},
+      year={2025},
+      eprint={2503.01776},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2503.01776},
+}
+```
+
+#### SparseMultipleNegativesRankingLoss
+```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 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,15 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.2.0.dev0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "query": "Represent this sentence for searching relevant passages: ",
+    "document": "",
+    "passage": ""
+  },
+  "default_prompt_name": null,
+  "model_type": "SparseEncoder",
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86b2a89f7f8933cf7bd90586cdf69d0012140e412818234b234f807e51ee574
+size 1340612432

modules.json

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

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 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}