Add new SentenceTransformer model.

.gitattributes

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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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 +1,659 @@
+---
+base_model: intfloat/multilingual-e5-small
+language:
+- multilingual
+library_name: sentence-transformers
+license: apache-2.0
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2320
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: 'MVGO; medium vacuum
+
+    gas oil'
+  sentences:
+  - 과분해
+  - Medium Vacuum Gas Oil(MVGO) ;
+  - '선적 전 또는 양하 후에 화물창에 잔존하는 소량의 액체화물 양을 결정하는 수학
+
+    적인 계산 수식'
+- source_sentence: PLE; plain large end
+  sentences:
+  - Plain Large End ;
+  - '부하중 변압기 Tap 변환기 ;
+
+    변압기 권선의 Tap을 무정전으로 변경하는 장치'
+  - Cone Roof Tank에서 Tank내의 Vapor가 외부로 나갈 수 있도록 만들어 놓은 구멍
+- source_sentence: Fluidization
+  sentences:
+  - '핵심성과지표;
+
+    어떤 계획이나 목표가 성공하였는지 또는 성공하고 있는지를 확인하려면 그 성공
+
+    을 구성하는 요소들을 측정하는 지표를 찾아 측정하여야 하는데, 이들 지표 중 성
+
+    공을 확인할 수 있는 가장 결정적인 지표를 KPI라고 부릅니다.'
+  - '전압변동에 영향을 주는 무효전력을 줄이기 위한 조상설비의 일종으로 정지형 무
+
+    효전력 보상장치'
+  - 고체층을 액체나 기체로 확대시키거나 현탁시켜 유통하도록 하는 것
+- source_sentence: 'SH; surface hardened
+
+    steel body'
+  sentences:
+  - Surface Hardened Steel Body ;
+  - 분산제 ; 슬러지 생성을 방지하기 위하여 Oil에 넣어주는 약품
+  - '작업위험성평가;
+
+    현장에서 수행되는 작업을 포함한 전반적인 직무 활동에 대하여 위험요인을 분석
+
+    하여 현재 안전조치를 검토하고 안전대책을 마련하는 기법'
+- source_sentence: U-205200
+  sentences:
+  - 물속의 (-)ion을 OH-로 치환해 주는 이온교환수지탑
+  - 차단기, 스위치류 , 스위치
+  - 올레핀 송유/동력 Nitrogen Section
+model-index:
+- name: Multilingual base soil embedding model (quantized)
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2441860465116279
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.31007751937984496
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3643410852713178
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.4108527131782946
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.2441860465116279
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.10335917312661498
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.07286821705426358
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.041085271317829464
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.2441860465116279
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.31007751937984496
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3643410852713178
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.4108527131782946
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.3172493867293268
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.28840746893072483
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.3003133446683658
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.2054263565891473
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.28294573643410853
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3178294573643411
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.38372093023255816
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.2054263565891473
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09431524547803617
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06356589147286822
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03837209302325582
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.2054263565891473
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.28294573643410853
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3178294573643411
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.38372093023255816
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2850988708112555
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.25465270087363123
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.26532412971784447
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1937984496124031
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2713178294573643
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.29844961240310075
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3488372093023256
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1937984496124031
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0904392764857881
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.059689922480620154
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03488372093023256
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1937984496124031
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2713178294573643
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.29844961240310075
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3488372093023256
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.26467320016495083
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.2385474344776671
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2482312240959752
+      name: Cosine Map@100
+---
+
+# Multilingual base soil embedding model (quantized)
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) <!-- at revision fd1525a9fd15316a2d503bf26ab031a61d056e98 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** multilingual
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("ValentinaKim/Multilingual-base-soil-embedding")
+# Run inference
+sentences = [
+    'U-205200',
+    '올레핀 송유/동력 Nitrogen Section',
+    '차단기, 스위치류 , 스위치',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.2442     |
+| cosine_accuracy@3   | 0.3101     |
+| cosine_accuracy@5   | 0.3643     |
+| cosine_accuracy@10  | 0.4109     |
+| cosine_precision@1  | 0.2442     |
+| cosine_precision@3  | 0.1034     |
+| cosine_precision@5  | 0.0729     |
+| cosine_precision@10 | 0.0411     |
+| cosine_recall@1     | 0.2442     |
+| cosine_recall@3     | 0.3101     |
+| cosine_recall@5     | 0.3643     |
+| cosine_recall@10    | 0.4109     |
+| cosine_ndcg@10      | 0.3172     |
+| cosine_mrr@10       | 0.2884     |
+| **cosine_map@100**  | **0.3003** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.2054     |
+| cosine_accuracy@3   | 0.2829     |
+| cosine_accuracy@5   | 0.3178     |
+| cosine_accuracy@10  | 0.3837     |
+| cosine_precision@1  | 0.2054     |
+| cosine_precision@3  | 0.0943     |
+| cosine_precision@5  | 0.0636     |
+| cosine_precision@10 | 0.0384     |
+| cosine_recall@1     | 0.2054     |
+| cosine_recall@3     | 0.2829     |
+| cosine_recall@5     | 0.3178     |
+| cosine_recall@10    | 0.3837     |
+| cosine_ndcg@10      | 0.2851     |
+| cosine_mrr@10       | 0.2547     |
+| **cosine_map@100**  | **0.2653** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1938     |
+| cosine_accuracy@3   | 0.2713     |
+| cosine_accuracy@5   | 0.2984     |
+| cosine_accuracy@10  | 0.3488     |
+| cosine_precision@1  | 0.1938     |
+| cosine_precision@3  | 0.0904     |
+| cosine_precision@5  | 0.0597     |
+| cosine_precision@10 | 0.0349     |
+| cosine_recall@1     | 0.1938     |
+| cosine_recall@3     | 0.2713     |
+| cosine_recall@5     | 0.2984     |
+| cosine_recall@10    | 0.3488     |
+| cosine_ndcg@10      | 0.2647     |
+| cosine_mrr@10       | 0.2385     |
+| **cosine_map@100**  | **0.2482** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 2,320 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                           |
+  |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 6.72 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 35.77 tokens</li><li>max: 408 tokens</li></ul> |
+* Samples:
+  | anchor                                            | positive                                                                                                            |
+  |:--------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------|
+  | <code>Deionizer</code>                            | <code>탈이온장치 ; Demineralizer와 동일</code>                                                                              |
+  | <code>Sub-CC; sub-contracting<br>committee</code> | <code>외주 계약의 투명성과 공정성을 확보하기 위한 Sub-계약위원회로서 위원 및 위원<br>장은 CEO가 임명한다. CC이원원 부문장 이상 임원으로 하고 간사는 구매관리팀<br>장이 한다.</code> |
+  | <code>In-line Sampler</code>                      | <code>원유 속의 물과 침전물의 함량을 측정하기 위하여 원유하역 Line에 설치해 놓은<br>시료채취기</code>                                                  |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 10
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `tf32`: False
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 10
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: 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_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_64_cosine_map@100 |
+|:------:|:----:|:-------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.8767 | 4    | -             | 0.2156                 | 0.2448                 | 0.1831                |
+| 1.9726 | 9    | -             | 0.2511                 | 0.2765                 | 0.2154                |
+| 2.1918 | 10   | 7.6309        | -                      | -                      | -                     |
+| 2.8493 | 13   | -             | 0.2531                 | 0.2852                 | 0.2345                |
+| 3.9452 | 18   | -             | 0.2617                 | 0.2914                 | 0.2353                |
+| 4.3836 | 20   | 5.3042        | -                      | -                      | -                     |
+| 4.8219 | 22   | -             | 0.2626                 | 0.2946                 | 0.2422                |
+| 5.9178 | 27   | -             | 0.2629                 | 0.2987                 | 0.2481                |
+| 6.5753 | 30   | 4.2433        | -                      | -                      | -                     |
+| 6.7945 | 31   | -             | 0.2684                 | 0.2988                 | 0.2495                |
+| 7.8904 | 36   | -             | 0.2652                 | 0.3003                 | 0.2488                |
+| 8.7671 | 40   | 3.9117        | 0.2653                 | 0.3003                 | 0.2482                |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.1.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 1.0.0
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-small",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fefd3648885dbef088f6d9e5c87d488742493440adabea90311199a5a13ffef
+size 470637416

modules.json

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

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef04f2b385d1514f500e779207ace0f53e30895ce37563179e29f4022d28ca38
+size 17083053

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}