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 +1,582 @@
+---
+language:
+- en
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:404290
+- loss:OnlineContrastiveLoss
+base_model: sentence-transformers/stsb-distilbert-base
+widget:
+- source_sentence: What does the lock symbol on my iPhone 6 means?
+  sentences:
+  - How did the Soviet Navy compare to the US Navy?
+  - What does the iPhone icon with lock and arrow mean?
+  - What is the importance of electrical engineering?
+- source_sentence: Why are blue and red neon lights illegal or restricted for commercial
+    uses in Honduras?
+  sentences:
+  - Why are blue and red neon lights illegal or restricted for commercial uses in
+    Colombia?
+  - Why would I want a Raspberry Pi?
+  - How do I see things as they are?
+- source_sentence: How will Hillary Clinton deal with russia?
+  sentences:
+  - What would have happened if Barty crouch Jr escaped the dementors and made it
+    back to the graveyard?
+  - How will Hillary Clinton deal with terrorism?
+  - I am a commercial student who wishes to study accounting, but now I wish to study
+    law. Is it possible?
+- source_sentence: What are the best managing skills?
+  sentences:
+  - What are the top skills of effective Product Managers?
+  - How do I lose weight in a short time?
+  - What are some good songs for lyrical dances?
+- source_sentence: What is the best fact checking sources that all Quorans will most
+    trust?
+  sentences:
+  - Do people still write love letters?
+  - Is working in McKinsey one of the best and surest ways to get into Harvard Business
+    School?
+  - What is the most memorable book that Quorans have read?
+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: 0.869
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.813665509223938
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.8390243902439025
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7617226243019104
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.7818181818181819
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9052631578947369
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.8852756469769394
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.7337941850587686
+      name: Cosine Mcc
+  - task:
+      type: paraphrase-mining
+      name: Paraphrase Mining
+    dataset:
+      name: quora duplicates dev
+      type: quora-duplicates-dev
+    metrics:
+    - type: average_precision
+      value: 0.5427423938771084
+      name: Average Precision
+    - type: f1
+      value: 0.5532539228607665
+      name: F1
+    - type: precision
+      value: 0.5508021390374331
+      name: Precision
+    - type: recall
+      value: 0.5557276315132138
+      name: Recall
+    - type: threshold
+      value: 0.865865558385849
+      name: Threshold
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9298
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9732
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.982
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9868
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9298
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.4154
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.26792
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1417
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8009069531416296
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9349178789609083
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9610774822138647
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9765400300287947
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9525570390902354
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9522342063492065
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9400294978560327
+      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("yahyaabd/stsb-distilbert-base-ocl")
+# Run inference
+sentences = [
+    'What is the best fact checking sources that all Quorans will most trust?',
+    'What is the most memorable book that Quorans have read?',
+    'Is working in McKinsey one of the best and surest ways to get into Harvard Business School?',
+]
+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           | 0.869      |
+| cosine_accuracy_threshold | 0.8137     |
+| cosine_f1                 | 0.839      |
+| cosine_f1_threshold       | 0.7617     |
+| cosine_precision          | 0.7818     |
+| cosine_recall             | 0.9053     |
+| **cosine_ap**             | **0.8853** |
+| cosine_mcc                | 0.7338     |
+
+#### 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)
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| **average_precision** | **0.5427** |
+| f1                    | 0.5533     |
+| precision             | 0.5508     |
+| recall                | 0.5557     |
+| threshold             | 0.8659     |
+
+#### 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   | 0.9298     |
+| cosine_accuracy@3   | 0.9732     |
+| cosine_accuracy@5   | 0.982      |
+| cosine_accuracy@10  | 0.9868     |
+| cosine_precision@1  | 0.9298     |
+| cosine_precision@3  | 0.4154     |
+| cosine_precision@5  | 0.2679     |
+| cosine_precision@10 | 0.1417     |
+| cosine_recall@1     | 0.8009     |
+| cosine_recall@3     | 0.9349     |
+| cosine_recall@5     | 0.9611     |
+| cosine_recall@10    | 0.9765     |
+| **cosine_ndcg@10**  | **0.9526** |
+| cosine_mrr@10       | 0.9522     |
+| cosine_map@100      | 0.94       |
+
+<!--
+## 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: 404,290 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: 6 tokens</li><li>mean: 16.01 tokens</li><li>max: 67 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.9 tokens</li><li>max: 72 tokens</li></ul> | <ul><li>0: ~64.40%</li><li>1: ~35.60%</li></ul> |
+* Samples:
+  | sentence1                                                                                                       | sentence2                                                                                                                     | label          |
+  |:----------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>How much worse do things need to get before the "blue" states cut off welfare to the "red" states?</code> | <code>If the red states and the blue states were separated into two countries, which country would be more successful?</code> | <code>0</code> |
+  | <code>Can you offer me any advice on how to lose weight?</code>                                                 | <code>What are the best ways to lose weight? What is the best diet plan?</code>                                               | <code>1</code> |
+  | <code>How do I break my knee?</code>                                                                            | <code>How do I break my elbow?</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: 404,290 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: 6 tokens</li><li>mean: 15.98 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.9 tokens</li><li>max: 77 tokens</li></ul> | <ul><li>0: ~62.00%</li><li>1: ~38.00%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                  | sentence2                                                                               | label          |
+  |:---------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:---------------|
+  | <code>Which is the best SAP online training centre at Hyderabad?</code>                                                    | <code>Which is the best sap workflow online training institute in Hyderabad?</code>     | <code>1</code> |
+  | <code>How did World War Two start?</code>                                                                                  | <code>What will most likely cause World War III?</code>                                 | <code>0</code> |
+  | <code>How do I find a unique string from a given string in Java without methods such as split, contain, and divide?</code> | <code>How can I split the string "[] {() <>} []" into " [,], {, (, ..." in Java?</code> | <code>0</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}
+- `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
+- `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
+- `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    | -             | -               | 0.7402                     | 0.4200                                 | 0.9413         |
+| 0.0640 | 100  | 2.481         | -               | -                          | -                                      | -              |
+| 0.1280 | 200  | 2.1466        | -               | -                          | -                                      | -              |
+| 0.1599 | 250  | -             | 1.7997          | 0.8327                     | 0.4596                                 | 0.9355         |
+| 0.1919 | 300  | 2.0354        | -               | -                          | -                                      | -              |
+| 0.2559 | 400  | 1.9342        | -               | -                          | -                                      | -              |
+| 0.3199 | 500  | 1.9132        | 1.6231          | 0.8617                     | 0.4896                                 | 0.9425         |
+| 0.3839 | 600  | 1.8015        | -               | -                          | -                                      | -              |
+| 0.4479 | 700  | 1.7407        | -               | -                          | -                                      | -              |
+| 0.4798 | 750  | -             | 1.4953          | 0.8737                     | 0.5112                                 | 0.9468         |
+| 0.5118 | 800  | 1.6454        | -               | -                          | -                                      | -              |
+| 0.5758 | 900  | 1.6568        | -               | -                          | -                                      | -              |
+| 0.6398 | 1000 | 1.6811        | 1.4678          | 0.8751                     | 0.5290                                 | 0.9457         |
+| 0.7038 | 1100 | 1.711         | -               | -                          | -                                      | -              |
+| 0.7678 | 1200 | 1.6449        | -               | -                          | -                                      | -              |
+| 0.7997 | 1250 | -             | 1.4363          | 0.8811                     | 0.5327                                 | 0.9507         |
+| 0.8317 | 1300 | 1.5921        | -               | -                          | -                                      | -              |
+| 0.8957 | 1400 | 1.5062        | -               | -                          | -                                      | -              |
+| 0.9597 | 1500 | 1.5728        | 1.4029          | 0.8853                     | 0.5427                                 | 0.9526         |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.4.0
+- Transformers: 4.48.1
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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",
+}
+```
+
+<!--
+## 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 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/stsb-distilbert-base",
+  "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": "4.48.1",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.0",
+    "transformers": "4.48.1",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f41621bacba4d0210b4ad4b3bd8bf190d1728154f739dc69f5021ed1e179b6
+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]"
+}