Add new SentenceTransformer model

.gitattributes

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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": 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
+}

README.md

@@ -0,0 +1,628 @@
+---
+language:
+- vi
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:6066
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: splendor1811/BGE-base-banking-ONE-v0106
+widget:
+- source_sentence: HUYNHDEANHKHOA COMPANY LIMITED
+  sentences:
+  - SHYH JIUH INDUSTRIAL CO.,LTD
+  - KENG HIN ENGINEERING CO
+  - CTTNHHTHIETKE MYTHUAT VA TINHOC HUYNHDEANHKHOA
+- source_sentence: YUEQING RONGSHENG ELECTRICAL APPLIANCES LTD.
+  sentences:
+  - RAUCH FRUCHTSÄFTE GMBH & CO OG
+  - YUEQING RONGSHENG INTRODUCED ELECTRICAL APPLIANCES CO., LTD
+  - BACH MY TRADING, SERVICES AND CONSTRUCTION COMPANY LIMITED
+- source_sentence: ZHENFA TEXTILE COMPANY, LIMITED
+  sentences:
+  - DATANI LOGISTICS COMPANY LIMITED
+  - Quan Pham Electrical Equipment Co., Ltd.
+  - ZHENFA TEXTILE CO., LIMITED
+- source_sentence: CONG TY TNHH KY THUAT VSI
+  sentences:
+  - CTCAD SERVICES TRADING COMPANY LIMITED
+  - CHAKTOMUK RESOURCES SUPPLY IMPORT EXPORT CO.,LTD
+  - VSI ENGINEERING COMPANY LIMITED
+- source_sentence: VIET ANH DUONG CO., LTD
+  sentences:
+  - ROCK GRANITES
+  - CTY TNHH VIET ANH DUONG
+  - SOVAN SEUNGDEN CO.,LTD
+pipeline_tag: sentence-similarity
+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
+model-index:
+- name: BGE-mapping-tool
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 1024
+      type: dim_1024
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.844213649851632
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9169139465875371
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9540059347181009
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.983679525222552
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.844213649851632
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.8209693372898119
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.8172106824925816
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.7956973293768547
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.04068450507619647
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.11841496782149599
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.1962584728163363
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.38186014447142047
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8055555734311861
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8893975790118221
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8042214818897099
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8501483679525222
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9124629080118695
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9525222551928784
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.983679525222552
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8501483679525222
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.8199802176063304
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.8160237388724035
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.7958456973293768
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.040903524434681704
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.1182842627204645
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.1959109963561002
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.38199438214275006
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8060214331494838
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8915365503273512
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8045717264189338
+      name: Cosine Map@100
+---
+
+# BGE-mapping-tool
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [splendor1811/BGE-base-banking-ONE-v0106](https://huggingface.co/splendor1811/BGE-base-banking-ONE-v0106) on the json dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [splendor1811/BGE-base-banking-ONE-v0106](https://huggingface.co/splendor1811/BGE-base-banking-ONE-v0106) <!-- at revision 9c233176fc7eb592572824ebb465bbe59997a308 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **Language:** vi
+- **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': 8192, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
+  (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): 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("splendor1811/BGE-mapping-tool_epoch3")
+# Run inference
+sentences = [
+    'VIET ANH DUONG CO., LTD',
+    'CTY TNHH VIET ANH DUONG',
+    'ROCK GRANITES',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[ 1.0000,  0.9738, -0.0072],
+#         [ 0.9738,  1.0000,  0.0011],
+#         [-0.0072,  0.0011,  1.0000]])
+```
+
+<!--
+### 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_1024`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 1024
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.8442     |
+| cosine_accuracy@3   | 0.9169     |
+| cosine_accuracy@5   | 0.954      |
+| cosine_accuracy@10  | 0.9837     |
+| cosine_precision@1  | 0.8442     |
+| cosine_precision@3  | 0.821      |
+| cosine_precision@5  | 0.8172     |
+| cosine_precision@10 | 0.7957     |
+| cosine_recall@1     | 0.0407     |
+| cosine_recall@3     | 0.1184     |
+| cosine_recall@5     | 0.1963     |
+| cosine_recall@10    | 0.3819     |
+| **cosine_ndcg@10**  | **0.8056** |
+| cosine_mrr@10       | 0.8894     |
+| cosine_map@100      | 0.8042     |
+
+#### Information Retrieval
+
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.8501    |
+| cosine_accuracy@3   | 0.9125    |
+| cosine_accuracy@5   | 0.9525    |
+| cosine_accuracy@10  | 0.9837    |
+| cosine_precision@1  | 0.8501    |
+| cosine_precision@3  | 0.82      |
+| cosine_precision@5  | 0.816     |
+| cosine_precision@10 | 0.7958    |
+| cosine_recall@1     | 0.0409    |
+| cosine_recall@3     | 0.1183    |
+| cosine_recall@5     | 0.1959    |
+| cosine_recall@10    | 0.382     |
+| **cosine_ndcg@10**  | **0.806** |
+| cosine_mrr@10       | 0.8915    |
+| cosine_map@100      | 0.8046    |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 6,066 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: 4 tokens</li><li>mean: 15.22 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.46 tokens</li><li>max: 48 tokens</li></ul> |
+* Samples:
+  | anchor                                                       | positive                                                  |
+  |:-------------------------------------------------------------|:----------------------------------------------------------|
+  | <code>ZHONGSHAN CHINHAO MOLD HARDWARE COMPANY LIMITED</code> | <code>ZHONGSHAN CHINHAO MOLD HARDWARE CO., LTD.</code>    |
+  | <code>Changshu Longte International Trade Co., Ltd</code>    | <code>CHANGSHU LONGTE INTERNATIONAL TRADE CO., LTD</code> |
+  | <code>ACT CHEMICAL AND THERAPEUTIC LABORATORIES SARL</code>  | <code>MEDICAL SUPPLIES PHARMACEUTICALS & EQUIPMENT</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          1024,
+          768
+      ],
+      "matryoshka_weights": [
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `gradient_accumulation_steps`: 8
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `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`: 8
+- `per_device_eval_batch_size`: 8
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 8
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_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`: 5
+- `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`: True
+- `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`: True
+- `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}
+- `parallelism_config`: 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`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `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
+- `liger_kernel_config`: None
+- `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 | dim_1024_cosine_ndcg@10 | dim_768_cosine_ndcg@10 |
+|:-------:|:-------:|:-------------:|:-----------------------:|:----------------------:|
+| 0.1054  | 10      | 0.4225        | -                       | -                      |
+| 0.2108  | 20      | 0.2415        | -                       | -                      |
+| 0.3162  | 30      | 0.1252        | -                       | -                      |
+| 0.4216  | 40      | 0.0765        | -                       | -                      |
+| 0.5270  | 50      | 0.0573        | -                       | -                      |
+| 0.6324  | 60      | 0.0345        | -                       | -                      |
+| 0.7378  | 70      | 0.0448        | -                       | -                      |
+| 0.8432  | 80      | 0.0355        | -                       | -                      |
+| 0.9486  | 90      | 0.0996        | -                       | -                      |
+| 1.0     | 95      | -             | 0.7994                  | 0.7994                 |
+| 1.0527  | 100     | 0.0194        | -                       | -                      |
+| 1.1581  | 110     | 0.0418        | -                       | -                      |
+| 1.2635  | 120     | 0.0339        | -                       | -                      |
+| 1.3689  | 130     | 0.0427        | -                       | -                      |
+| 1.4743  | 140     | 0.0339        | -                       | -                      |
+| 1.5797  | 150     | 0.0333        | -                       | -                      |
+| 1.6851  | 160     | 0.0396        | -                       | -                      |
+| 1.7905  | 170     | 0.0877        | -                       | -                      |
+| 1.8959  | 180     | 0.0608        | -                       | -                      |
+| 2.0     | 190     | 0.0352        | 0.8037                  | 0.8031                 |
+| 2.1054  | 200     | 0.023         | -                       | -                      |
+| 2.2108  | 210     | 0.0638        | -                       | -                      |
+| 2.3162  | 220     | 0.0401        | -                       | -                      |
+| 2.4216  | 230     | 0.0274        | -                       | -                      |
+| 2.5270  | 240     | 0.0405        | -                       | -                      |
+| 2.6324  | 250     | 0.0305        | -                       | -                      |
+| 2.7378  | 260     | 0.0414        | -                       | -                      |
+| 2.8432  | 270     | 0.0178        | -                       | -                      |
+| 2.9486  | 280     | 0.0535        | -                       | -                      |
+| 3.0     | 285     | -             | 0.8008                  | 0.8012                 |
+| 3.0527  | 290     | 0.0629        | -                       | -                      |
+| 3.1581  | 300     | 0.0283        | -                       | -                      |
+| 3.2635  | 310     | 0.0567        | -                       | -                      |
+| 3.3689  | 320     | 0.0167        | -                       | -                      |
+| 3.4743  | 330     | 0.0349        | -                       | -                      |
+| 3.5797  | 340     | 0.053         | -                       | -                      |
+| 3.6851  | 350     | 0.0517        | -                       | -                      |
+| 3.7905  | 360     | 0.0603        | -                       | -                      |
+| 3.8959  | 370     | 0.0323        | -                       | -                      |
+| 4.0     | 380     | 0.0229        | 0.8042                  | 0.8055                 |
+| 4.1054  | 390     | 0.0476        | -                       | -                      |
+| 4.2108  | 400     | 0.06          | -                       | -                      |
+| 4.3162  | 410     | 0.0412        | -                       | -                      |
+| 4.4216  | 420     | 0.0553        | -                       | -                      |
+| 4.5270  | 430     | 0.0446        | -                       | -                      |
+| 4.6324  | 440     | 0.016         | -                       | -                      |
+| 4.7378  | 450     | 0.0302        | -                       | -                      |
+| 4.8432  | 460     | 0.0223        | -                       | -                      |
+| 4.9486  | 470     | 0.0649        | -                       | -                      |
+| **5.0** | **475** | **-**         | **0.8056**              | **0.806**              |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 5.1.0
+- Transformers: 4.56.1
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.8.1
+- Datasets: 3.6.0
+- Tokenizers: 0.22.0
+
+## 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 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.0",
+    "transformers": "4.56.1",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine",
+  "model_type": "SentenceTransformer"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e0c03a836c0d6dbcae499e84979940eb3e86a092174782ed56c5fad8a6fe37
+size 2271064456

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": 8192,
+    "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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": true,
+    "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 sha256:222975faa02f5257c6e8c734e85973e48c8d42d7d37d90b894c73efa1841d76a
+size 17083154

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 8192,
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}