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 +1,545 @@
+---
+base_model: sentence-transformers/all-mpnet-base-v2
+datasets: []
+language: []
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:17093
+- loss:CosineSimilarityLoss
+widget:
+- source_sentence: In the realm of genetics , it is far better to be safe than sorry
+    .
+  sentences:
+  - Marijuana use harms the brain, and legalization will increase mental health problems.
+  - We are god now !
+  - Likewise , the proposal that addictive drugs should be legalized , regulated and
+    opened to " free market dynamics " is immediately belied by the recognition that
+    the drug market for an addict is no longer a free market – it is clear that they
+    will pay any price when needing their drug .
+- source_sentence: The worldwide anti-nuclear power movement has provided enormous
+    stimulation to the Australian movement , and the decline in nuclear power expansion
+    since the late 1970s - due substantially to worldwide citizen opposition - has
+    been a great setback for Australian uranium mining interests .
+  sentences:
+  - Just as the state has the authority ( and duty ) to act justly in allocating scarce
+    resources , in meeting minimal needs of its ( deserving ) citizens , in defending
+    its citizens from violence and crime , and in not waging unjust wars ; so too
+    does it have the authority , flowing from its mission to promote justice and the
+    good of its people , to punish the criminal .
+  - The long lead times for construction that invalidate nuclear power as a way of
+    mitigating climate change was a point recognized in 2009 by the body whose mission
+    is to promote the use of nuclear power , the International Atomic Energy Agency
+    ( IAEA ) .
+  - Gun control laws would reduce the societal costs associated with gun violence.
+- source_sentence: Requiring uniforms enhances school security by permitting identification
+    of non-students who try to enter the campus .
+  sentences:
+  - Many students who are against school uniforms argue that they lose their â € ‹
+    self identity when they lose their right to express themselves through fashion
+    .
+  - If reproductive cloning is perfected , a quadriplegic can also choose to have
+    himself cloned , so someone can take his place .
+  - A higher minimum wage might also decrease turnover and thus keep training costs
+    down , supporters say .
+- source_sentence: Minimum wage has long been a minimum standard of living .
+  sentences:
+  - A minimum wage job is suppose to be an entry level stepping stone – not a career
+    goal .
+  - It is argued that just as it would be permissible to " unplug " and thereby cause
+    the death of the person who is using one 's kidneys , so it is permissible to
+    abort the fetus ( who similarly , it is said , has no right to use one 's body
+    's life-support functions against one 's will ) .
+  - Abortion reduces welfare costs to taxpayers .
+- source_sentence: Fanatics of the pro – life argument are sometimes so focused on
+    the fetus that they put no value to the mother ’s life and do not even consider
+    the viability of the fetus .
+  sentences:
+  - Life is life , whether it s outside the womb or not .
+  - Legalization of marijuana is phasing out black markets and taking money away from
+    drug cartels, organized crime, and street gangs.
+  - 'Response 2 : A child is not replaceable .'
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.7294675022492696
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7234943835496113
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7104391963353577
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.7118078150763045
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7212412855224142
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.7234943835496113
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7294674862347428
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7234943835496113
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7294675022492696
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.7234943835496113
+      name: Spearman Max
+    - type: pearson_cosine
+      value: 0.7146126101962849
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6886131469202397
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7069653659670995
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6837201725651982
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7115078495768724
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6886131469202397
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7146126206763159
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6886131469202397
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7146126206763159
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6886131469202397
+      name: Spearman Max
+---
+
+# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). 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/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **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': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (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})
+  (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("armaniii/all-mpnet-base-v2-augmentation-indomain-bm25-sts")
+# Run inference
+sentences = [
+    'Fanatics of the pro – life argument are sometimes so focused on the fetus that they put no value to the mother ’s life and do not even consider the viability of the fetus .',
+    'Life is life , whether it s outside the womb or not .',
+    'Legalization of marijuana is phasing out black markets and taking money away from drug cartels, organized crime, and street gangs.',
+]
+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
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7295     |
+| **spearman_cosine** | **0.7235** |
+| pearson_manhattan   | 0.7104     |
+| spearman_manhattan  | 0.7118     |
+| pearson_euclidean   | 0.7212     |
+| spearman_euclidean  | 0.7235     |
+| pearson_dot         | 0.7295     |
+| spearman_dot        | 0.7235     |
+| pearson_max         | 0.7295     |
+| spearman_max        | 0.7235     |
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7146     |
+| **spearman_cosine** | **0.6886** |
+| pearson_manhattan   | 0.707      |
+| spearman_manhattan  | 0.6837     |
+| pearson_euclidean   | 0.7115     |
+| spearman_euclidean  | 0.6886     |
+| pearson_dot         | 0.7146     |
+| spearman_dot        | 0.6886     |
+| pearson_max         | 0.7146     |
+| spearman_max        | 0.6886     |
+
+<!--
+## 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: 17,093 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                            |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 33.23 tokens</li><li>max: 97 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 30.75 tokens</li><li>max: 96 tokens</li></ul> | <ul><li>min: 0.09</li><li>mean: 0.55</li><li>max: 0.95</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                               | sentence2                                                                                                                                                                                                                                                                                                                         | score                           |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>It is true that a Colorado study found a post-legalization increase in youths being treated for marijuana exposure .</code>                                       | <code>In Colorado , recent figures correlate with the years since marijuana legalization to show a dramatic decrease in overall highway fatalities – and a two-fold increase in the frequency of marijuana-positive drivers in fatal auto crashes .</code>                                                                        | <code>0.4642857142857143</code> |
+  | <code>The idea of a school uniform is that students wear the uniform at school , but do not wear the uniform , say , at a disco or other events outside school .</code> | <code>If it means that the schoolrooms will be more orderly , more disciplined , and that our young people will learn to evaluate themselves by what they are on the inside instead of what they 're wearing on the outside , then our public schools should be able to require their students to wear school uniforms . "</code> | <code>0.5714285714285714</code> |
+  | <code>The resulting embryonic stem cells could then theoretically be grown into adult cells to replace the ailing person 's mutated cells .</code>                      | <code>However , there is a more serious , less cartoonish objection to turning procreation into manufacturing .</code>                                                                                                                                                                                                            | <code>0.4464285714285714</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 340 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                          | sentence2                                                                          | score                                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                           |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 33.76 tokens</li><li>max: 105 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 31.86 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 0.09</li><li>mean: 0.5</li><li>max: 0.89</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                 | sentence2                                                                                                                                                                                                                          | score                           |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>[ quoting himself from Furman v. Georgia , 408 U.S. 238 , 257 ( 1972 ) ] As such it is a penalty that ' subjects the individual to a fate forbidden by the principle of civilized treatment guaranteed by the [ Clause ] . '</code> | <code>It provides a deterrent for prisoners already serving a life sentence .</code>                                                                                                                                               | <code>0.3214285714285714</code> |
+  | <code>Of those savings , $ 25.7 billion would accrue to state and local governments , while $ 15.6 billion would accrue to the federal government .</code>                                                                                | <code>Jaime Smith , deputy communications director for the governor ’s office , said , “ The legalization initiative was not driven by a desire for a revenue , but it has provided a small assist for our state budget . ”</code> | <code>0.5357142857142857</code> |
+  | <code>If the uterus is designed to sustain an unborn child ’s life , do n’t unborn children have a right to receive nutrition and shelter through the one organ designed to provide them with that ordinary care ?</code>                 | <code>We as parents are supposed to protect our children at all costs whether they are in the womb or not .</code>                                                                                                                 | <code>0.7678571428571428</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `warmup_ratio`: 0.1
+- `bf16`: True
+
+#### 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`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 3
+- `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`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: 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
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:------------------------:|
+| 0.0935 | 100  | 0.0151        | 0.0098 | 0.7013                   |
+| 0.1871 | 200  | 0.0069        | 0.0112 | 0.6857                   |
+| 0.2806 | 300  | 0.0058        | 0.0106 | 0.6860                   |
+| 0.3742 | 400  | 0.0059        | 0.0102 | 0.6915                   |
+| 0.4677 | 500  | 0.0057        | 0.0097 | 0.6903                   |
+| 0.5613 | 600  | 0.0049        | 0.0100 | 0.6797                   |
+| 0.6548 | 700  | 0.0055        | 0.0101 | 0.6766                   |
+| 0.7484 | 800  | 0.0049        | 0.0116 | 0.6529                   |
+| 0.8419 | 900  | 0.0049        | 0.0105 | 0.6572                   |
+| 0.9355 | 1000 | 0.0051        | 0.0115 | 0.6842                   |
+| 1.0290 | 1100 | 0.0038        | 0.0094 | 0.7000                   |
+| 1.1225 | 1200 | 0.0029        | 0.0091 | 0.7027                   |
+| 1.2161 | 1300 | 0.0026        | 0.0093 | 0.7016                   |
+| 1.3096 | 1400 | 0.0027        | 0.0088 | 0.7192                   |
+| 1.4032 | 1500 | 0.0027        | 0.0097 | 0.7065                   |
+| 1.4967 | 1600 | 0.0028        | 0.0091 | 0.7011                   |
+| 1.5903 | 1700 | 0.0027        | 0.0095 | 0.7186                   |
+| 1.6838 | 1800 | 0.0026        | 0.0087 | 0.7277                   |
+| 1.7774 | 1900 | 0.0024        | 0.0085 | 0.7227                   |
+| 1.8709 | 2000 | 0.0025        | 0.0086 | 0.7179                   |
+| 1.9645 | 2100 | 0.0022        | 0.0086 | 0.7195                   |
+| 2.0580 | 2200 | 0.0017        | 0.0088 | 0.7183                   |
+| 2.1515 | 2300 | 0.0014        | 0.0088 | 0.7229                   |
+| 2.2451 | 2400 | 0.0014        | 0.0086 | 0.7200                   |
+| 2.3386 | 2500 | 0.0013        | 0.0088 | 0.7248                   |
+| 2.4322 | 2600 | 0.0014        | 0.0085 | 0.7286                   |
+| 2.5257 | 2700 | 0.0015        | 0.0085 | 0.7283                   |
+| 2.6193 | 2800 | 0.0014        | 0.0085 | 0.7263                   |
+| 2.7128 | 2900 | 0.0014        | 0.0085 | 0.7248                   |
+| 2.8064 | 3000 | 0.0013        | 0.0087 | 0.7191                   |
+| 2.8999 | 3100 | 0.0011        | 0.0086 | 0.7225                   |
+| 2.9935 | 3200 | 0.0012        | 0.0085 | 0.7235                   |
+| 3.0    | 3207 | -             | -      | 0.6886                   |
+
+
+### Framework Versions
+- Python: 3.9.2
+- Sentence Transformers: 3.0.1
+- Transformers: 4.43.1
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.14.7
+- 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",
+}
+```
+
+<!--
+## 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/all-mpnet-base-v2",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.43.1",
+    "pytorch": "2.3.1+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:ff9b9e6201722cd4c5c86607f3b10ac76089f23af114e9b40bb647e866be05ae
+size 437967672

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": 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_config.json

@@ -0,0 +1,72 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}