Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,586 @@
+---
+language:
+- en
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:100000
+- loss:OnlineContrastiveLoss
+base_model: sentence-transformers/stsb-distilbert-base
+widget:
+- source_sentence: Why does Jimmy Wales choose to reside in London instead of the
+    US?
+  sentences:
+  - What are the challenges in RTE?
+  - Why did Jimmy Wales move to London?
+  - What are the most common barriers that affect the effective communication of a
+    family?
+- source_sentence: How I can speak English with fluency?
+  sentences:
+  - How can I improve my English Language?
+  - What are some ways to be a good storyteller?
+  - What are good ways to count your calories?
+- source_sentence: How can I come out of my depression?
+  sentences:
+  - Will I lose my Yahoo account email when I leave AT&T just because all my Yahoo
+    account email has my old AT&T (pacbell.net) name?
+  - How did you come out of depression?
+  - How can I become rich by the age of 25?
+- source_sentence: What would I get if I could somehow merge two, three or four nuclei
+    of nitrogen-15?
+  sentences:
+  - What would I get if I could merge two nuclei of argon-40?
+  - What is the historical relationship between the Mexican war and War of 1812? Any
+    thoughts?
+  - Do employees at Excel Trust have a good work-life balance? Does this differ across
+    positions and departments?
+- source_sentence: In mythologies, how do mermaids reproduce?
+  sentences:
+  - How is it possible for cops to trace a lost mobile using the IMEI number even
+    after the SIM card has been taken out?
+  - I am a best friend of a girl who rejected me twice, can I still have a chance
+    of dating her?
+  - How do mermaids in myths have babies?
+datasets:
+- sentence-transformers/quora-duplicates
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+- average_precision
+- f1
+- precision
+- recall
+- threshold
+- 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: SentenceTransformer based on sentence-transformers/stsb-distilbert-base
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: quora duplicates
+      type: quora-duplicates
+    metrics:
+    - type: cosine_accuracy
+      value: 0.873
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.815665602684021
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.8341836734693877
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.8002265691757202
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.8114143920595533
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8582677165354331
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9065066687277681
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.7281893615860209
+      name: Cosine Mcc
+  - task:
+      type: paraphrase-mining
+      name: Paraphrase Mining
+    dataset:
+      name: quora duplicates dev
+      type: quora-duplicates-dev
+    metrics:
+    - type: average_precision
+      value: 0.5364240829748219
+      name: Average Precision
+    - type: f1
+      value: 0.5459832968781071
+      name: F1
+    - type: precision
+      value: 0.5433094236952758
+      name: Precision
+    - type: recall
+      value: 0.5486836189239147
+      name: Recall
+    - type: threshold
+      value: 0.8692173957824707
+      name: Threshold
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9294
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9706
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9782
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9872
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9294
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.4145333333333334
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.26644
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.14156000000000002
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8007371472808238
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9326976956997253
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9557324145037969
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9757744890011949
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.951609899037309
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9512162698412696
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.939197562645401
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on sentence-transformers/stsb-distilbert-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) on the [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) <!-- at revision a560fa5fec90547a51a4a41a392d4aef93b49f16 -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("CalebR84/stsb-distilbert-base-ocl")
+# Run inference
+sentences = [
+    'In mythologies, how do mermaids reproduce?',
+    'How do mermaids in myths have babies?',
+    'I am a best friend of a girl who rejected me twice, can I still have a chance of dating her?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Binary Classification
+
+* Dataset: `quora-duplicates`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value      |
+|:--------------------------|:-----------|
+| cosine_accuracy           | 0.873      |
+| cosine_accuracy_threshold | 0.8157     |
+| cosine_f1                 | 0.8342     |
+| cosine_f1_threshold       | 0.8002     |
+| cosine_precision          | 0.8114     |
+| cosine_recall             | 0.8583     |
+| **cosine_ap**             | **0.9065** |
+| cosine_mcc                | 0.7282     |
+
+#### Paraphrase Mining
+
+* Dataset: `quora-duplicates-dev`
+* Evaluated with [<code>ParaphraseMiningEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator) with these parameters:
+  ```json
+  {'add_transitive_closure': <function ParaphraseMiningEvaluator.add_transitive_closure at 0x000001E7E3966700>, 'max_pairs': 500000, 'top_k': 100}
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| **average_precision** | **0.5364** |
+| f1                    | 0.546      |
+| precision             | 0.5433     |
+| recall                | 0.5487     |
+| threshold             | 0.8692     |
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9294     |
+| cosine_accuracy@3   | 0.9706     |
+| cosine_accuracy@5   | 0.9782     |
+| cosine_accuracy@10  | 0.9872     |
+| cosine_precision@1  | 0.9294     |
+| cosine_precision@3  | 0.4145     |
+| cosine_precision@5  | 0.2664     |
+| cosine_precision@10 | 0.1416     |
+| cosine_recall@1     | 0.8007     |
+| cosine_recall@3     | 0.9327     |
+| cosine_recall@5     | 0.9557     |
+| cosine_recall@10    | 0.9758     |
+| **cosine_ndcg@10**  | **0.9516** |
+| cosine_mrr@10       | 0.9512     |
+| cosine_map@100      | 0.9392     |
+
+<!--
+## 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
+
+#### quora-duplicates
+
+* Dataset: [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 100,000 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 15.28 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.86 tokens</li><li>max: 81 tokens</li></ul> | <ul><li>0: ~59.90%</li><li>1: ~40.10%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                              | sentence2                                                                                                                                                                                                         | label          |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>How can I change my profile name in Facebook?</code>                                                                                             | <code>How do I change my Facebook profile name?</code>                                                                                                                                                            | <code>1</code> |
+  | <code>How is the LNMIIT, Jaipur?</code>                                                                                                                | <code>Where is LNMIIT located in Jaipur?</code>                                                                                                                                                                   | <code>0</code> |
+  | <code>I moved to the U.S. on my senior year and have aprox. 2 months to get ready for the SAT (or ACT). What would be the best strategy for me?</code> | <code>I have been living abroad for almost 10 years and am about to move back to the U.S. (Bay Area to be exact). What advice would you give me regarding a job search, a place to live, healthcare, etc.?</code> | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Evaluation Dataset
+
+#### quora-duplicates
+
+* Dataset: [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 1,000 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 15.27 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.94 tokens</li><li>max: 76 tokens</li></ul> | <ul><li>0: ~61.90%</li><li>1: ~38.10%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                   | sentence2                                                                                                           | label          |
+  |:----------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>What is utility?</code>                                                                                               | <code>What is utility programs?</code>                                                                              | <code>0</code> |
+  | <code>Can you describe the process from the time you type in a website's URL to it finishing loading on your screen?</code> | <code>What are the series of steps that happen when an URL is requested from the address field of a browser?</code> | <code>0</code> |
+  | <code>What were the motives behind the 2016 Orlando nightclub shooting?</code>                                              | <code>What motivated the shooter in the June 2016 Orlando nightclub shooting?</code>                                | <code>1</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 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`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `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
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | quora-duplicates_cosine_ap | quora-duplicates-dev_average_precision | cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:--------------------------:|:--------------------------------------:|:--------------:|
+| 0      | 0    | -             | -               | 0.7503                     | 0.4200                                 | 0.9401         |
+| 0.0640 | 100  | 2.4538        | -               | -                          | -                                      | -              |
+| 0.1280 | 200  | 2.1419        | -               | -                          | -                                      | -              |
+| 0.1599 | 250  | -             | 1.9259          | 0.8580                     | 0.4437                                 | 0.9350         |
+| 0.1919 | 300  | 2.0272        | -               | -                          | -                                      | -              |
+| 0.2559 | 400  | 1.9581        | -               | -                          | -                                      | -              |
+| 0.3199 | 500  | 1.7846        | 1.8828          | 0.8845                     | 0.4698                                 | 0.9431         |
+| 0.3839 | 600  | 1.8462        | -               | -                          | -                                      | -              |
+| 0.4479 | 700  | 1.8053        | -               | -                          | -                                      | -              |
+| 0.4798 | 750  | -             | 1.6727          | 0.8933                     | 0.5039                                 | 0.9468         |
+| 0.5118 | 800  | 1.7161        | -               | -                          | -                                      | -              |
+| 0.5758 | 900  | 1.6574        | -               | -                          | -                                      | -              |
+| 0.6398 | 1000 | 1.6719        | 1.5868          | 0.9009                     | 0.5152                                 | 0.9471         |
+| 0.7038 | 1100 | 1.693         | -               | -                          | -                                      | -              |
+| 0.7678 | 1200 | 1.6622        | -               | -                          | -                                      | -              |
+| 0.7997 | 1250 | -             | 1.5453          | 0.9047                     | 0.5257                                 | 0.9462         |
+| 0.8317 | 1300 | 1.6129        | -               | -                          | -                                      | -              |
+| 0.8957 | 1400 | 1.5736        | -               | -                          | -                                      | -              |
+| 0.9597 | 1500 | 1.6402        | 1.5463          | 0.9065                     | 0.5364                                 | 0.9516         |
+
+
+### Framework Versions
+- Python: 3.12.9
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.7.0
+- Datasets: 3.6.0
+- 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",
+}
+```
+
+<!--
+## 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 +1,23 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc141f489bcb457d59f9a97f3271f6df9fda7b32f4ffef45ea9c559a72f4fc83
+size 265462608

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "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 +1,59 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}