Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "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 +1,569 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:672
+- loss:ContrastiveLoss
+base_model: sentence-transformers/multi-qa-mpnet-base-dot-v1
+widget:
+- source_sentence: '
+
+    Animals may not be allowed onto beds or other furniture, which serves for
+
+    guests. It is not permitted to use baths, showers or washbasins for bathing or
+
+    washing animals.'
+  sentences:
+  - '
+
+    Please advise of any special needs such as high-chairs and sleeping cots.'
+  - '
+
+    Animals may not be allowed onto beds or other furniture, which serves for
+
+    guests. It is not permitted to use baths, showers or washbasins for bathing or
+
+    washing animals.'
+  - '
+
+    It is strongly advised that you arrange adequate insurance cover such as cancellation
+    due to illness,
+
+    accident or injury, personal accident and personal liability, loss of or damage
+    to baggage and sport
+
+    equipment (Note that is not an exhaustive list). We will not be responsible or
+    liable if you fail to take
+
+    adequate insurance cover or none at all.'
+- source_sentence: 'Owners are responsible for ensuring that animals are kept quiet
+    between the
+
+    hours of 10:00 pm and 06:00 am. In the case of failure to abide by this
+
+    regulation the guest may be asked to leave the hotel without a refund of the
+
+    price of the night''s accommodation.'
+  sentences:
+  - '
+
+    Visitors are not allowed in the rooms and must be entertained in the lounges and/or
+    other public areas
+
+    provided.'
+  - 'To ensure the safety and comfort of everyone in the hotel, the Management
+
+    reserves the right to terminate the accommodation of guests who fail to comply
+
+    with the following rules and regulations.'
+  - 'Owners are responsible for ensuring that animals are kept quiet between the
+
+    hours of 10:00 pm and 06:00 am. In the case of failure to abide by this
+
+    regulation the guest may be asked to leave the hotel without a refund of the
+
+    price of the night''s accommodation.'
+- source_sentence: '
+
+    We ask all guests to behave in such a way that they do not disturb other guests
+    and the neighborhood.
+
+    The hotel staff is authorized to refuse services to a person who violates this
+    rule.'
+  sentences:
+  - '
+
+    Please take note of the limitation specified for the room you have booked.
+
+    If such number is exceeded, whether temporarily or over-night, we reserve the
+    right to do one or more of
+
+    the following: cancel your booking; retain all the monies you''ve paid; request
+    you to vacate your room(s)
+
+    forthwith, charge a higher rate for the room or recover all monies due.'
+  - '
+
+    We ask all guests to behave in such a way that they do not disturb other guests
+    and the neighborhood.
+
+    The hotel staff is authorized to refuse services to a person who violates this
+    rule.'
+  - 'We will only deal with your information as indicated in the booking/reservation
+    and we will only process your
+
+    personal information (both terms as defined in the Protection of Personal Information
+    Act, act 4 of 2013 [''the
+
+    POPIA''] and the European Union General Data Protection Regulation – (''GDPR'')
+    and any Special Personal
+
+    Information (as defined in the GDPR & POPIA), which processing includes amongst
+    others the ''collecting,
+
+    storing and dissemination'' of your personal information (as defined in GDPR &
+    POPIA).'
+- source_sentence: '
+
+    All articles stored in the luggage storage room are received at the owner’s own
+    risk.'
+  sentences:
+  - "\n Unregistered visitors are not permitted to enter guest rooms or other areas\
+    \ of\nthe hotel. An additional fee for unregistered guests will be charged to\
+    \ the\naccount of the guest(s) registered to the room."
+  - 'Please advise us if you anticipate arriving late as bookings will be cancelled
+    by 17:00 on the day of arrival,
+
+    unless we have been so notified.'
+  - '
+
+    All articles stored in the luggage storage room are received at the owner’s own
+    risk.'
+- source_sentence: ' In the event of a disturbance, one polite request (warning) will
+
+    be given to reduce the noise. If our request is not followed, the guest will be
+    asked to leave
+
+    the hotel without refund and may be charged Guest Compensation Disturbance Fee.'
+  sentences:
+  - '
+
+    Without limiting the generality of the aforementioned, it applies to pay-to-view
+    TV programmes or videos, as
+
+    well as telephone calls or any other expenses of a similar nature that is made
+    from your room, you will be
+
+    deemed to be the contracting party.'
+  - 'Pets are not allowed in the restaurant during breakfast time
+
+    (7:00 – 10:30) for hygienic reasons due to the breakfast’s buffet style. An
+
+    exception is the case when the hotel terrace is open, as pets can be taken to
+
+    the terrace through the hotel''s main entrance and they can stay there during
+
+    breakfast.'
+  - ' In the event of a disturbance, one polite request (warning) will
+
+    be given to reduce the noise. If our request is not followed, the guest will be
+    asked to leave
+
+    the hotel without refund and may be charged Guest Compensation Disturbance Fee.'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- dot_mcc
+model-index:
+- name: SentenceTransformer based on sentence-transformers/multi-qa-mpnet-base-dot-v1
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: dot_accuracy
+      value: 0.6745562130177515
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 49.0201301574707
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.4932735426008969
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 35.02415466308594
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.32934131736526945
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9821428571428571
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.3294144882113245
+      name: Dot Ap
+    - type: dot_mcc
+      value: -0.03920743101752848
+      name: Dot Mcc
+---
+
+# SentenceTransformer based on sentence-transformers/multi-qa-mpnet-base-dot-v1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/multi-qa-mpnet-base-dot-v1](https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-dot-v1). 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/multi-qa-mpnet-base-dot-v1](https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-dot-v1) <!-- at revision 4633e80e17ea975bc090c97b049da26062b054d3 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Dot Product
+<!-- - **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': 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})
+)
+```
+
+## 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("Marco127/Argu_T3")
+# Run inference
+sentences = [
+    ' In the event of a disturbance, one polite request (warning) will\nbe given to reduce the noise. If our request is not followed, the guest will be asked to leave\nthe hotel without refund and may be charged Guest Compensation Disturbance Fee.',
+    ' In the event of a disturbance, one polite request (warning) will\nbe given to reduce the noise. If our request is not followed, the guest will be asked to leave\nthe hotel without refund and may be charged Guest Compensation Disturbance Fee.',
+    '\nWithout limiting the generality of the aforementioned, it applies to pay-to-view TV programmes or videos, as\nwell as telephone calls or any other expenses of a similar nature that is made from your room, you will be\ndeemed to be the contracting party.',
+]
+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
+
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                 | Value      |
+|:-----------------------|:-----------|
+| dot_accuracy           | 0.6746     |
+| dot_accuracy_threshold | 49.0201    |
+| dot_f1                 | 0.4933     |
+| dot_f1_threshold       | 35.0242    |
+| dot_precision          | 0.3293     |
+| dot_recall             | 0.9821     |
+| **dot_ap**             | **0.3294** |
+| dot_mcc                | -0.0392    |
+
+<!--
+## 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: 672 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 672 samples:
+  |         | sentence1                                                                           | sentence2                                                                           | label                                           |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                              | string                                                                              | int                                             |
+  | details | <ul><li>min: 11 tokens</li><li>mean: 48.63 tokens</li><li>max: 156 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 48.63 tokens</li><li>max: 156 tokens</li></ul> | <ul><li>0: ~66.67%</li><li>1: ~33.33%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                           | sentence2                                                                                                                                                                           | label          |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code><br>The pets can not be left without supervision if there is a risk of causing any<br>damage or might disturb other guests.</code>                                            | <code><br>The pets can not be left without supervision if there is a risk of causing any<br>damage or might disturb other guests.</code>                                            | <code>0</code> |
+  | <code><br>Any guest in violation of these rules may be asked to leave the hotel with no refund. Extra copies of these<br>rules are available at the Front Desk upon request.</code> | <code><br>Any guest in violation of these rules may be asked to leave the hotel with no refund. Extra copies of these<br>rules are available at the Front Desk upon request.</code> | <code>0</code> |
+  | <code><br>Consuming the products from the minibar involves additional costs. You can find the<br>prices in the kitchen area.</code>                                                 | <code><br>Consuming the products from the minibar involves additional costs. You can find the<br>prices in the kitchen area.</code>                                                 | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 169 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 169 samples:
+  |         | sentence1                                                                           | sentence2                                                                           | label                                           |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                              | string                                                                              | int                                             |
+  | details | <ul><li>min: 13 tokens</li><li>mean: 46.01 tokens</li><li>max: 156 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 46.01 tokens</li><li>max: 156 tokens</li></ul> | <ul><li>0: ~66.86%</li><li>1: ~33.14%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | sentence2                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | label          |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code><br>I understand and accept that the BON Hotels Group collects the personal information ("personal<br>information") of all persons in my party for purposes of loyalty programmes and special offers. I, on behalf of<br>all in my party, expressly consent and grant permission to the BON Hotels Group to: -<br>collect, collate, process, study and use the personal information; and<br>communicate directly with me/us from time to time, unless I have stated to the contrary below.</code> | <code><br>I understand and accept that the BON Hotels Group collects the personal information ("personal<br>information") of all persons in my party for purposes of loyalty programmes and special offers. I, on behalf of<br>all in my party, expressly consent and grant permission to the BON Hotels Group to: -<br>collect, collate, process, study and use the personal information; and<br>communicate directly with me/us from time to time, unless I have stated to the contrary below.</code> | <code>0</code> |
+  | <code>However, in lieu of the above, any such goods will only be kept by us for 6 (six) months. At the end of which<br>period, we reserve the right in our sole discretion to dispose thereof and you will have no right of recourse<br>against us.</code>                                                                                                                                                                                                                                              | <code>However, in lieu of the above, any such goods will only be kept by us for 6 (six) months. At the end of which<br>period, we reserve the right in our sole discretion to dispose thereof and you will have no right of recourse<br>against us.</code>                                                                                                                                                                                                                                              | <code>0</code> |
+  | <code> In cases where the hotel<br>suffers damage (either physical, or moral) due to the guests’ violation of the above rules, it<br>may charge a compensation fee in proportion to the damage. Moral damage may be for<br>example disturbing other guests, thus ruining the reputation of the hotel.</code>                                                                                                                                                                                            | <code> In cases where the hotel<br>suffers damage (either physical, or moral) due to the guests’ violation of the above rules, it<br>may charge a compensation fee in proportion to the damage. Moral damage may be for<br>example disturbing other guests, thus ruining the reputation of the hotel.</code>                                                                                                                                                                                            | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 1e-05
+- `num_train_epochs`: 2
+- `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`: 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`: 1e-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`: 2
+- `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 | dot_ap |
+|:-----:|:----:|:------:|
+| -1    | -1   | 0.3294 |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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/multi-qa-mpnet-base-dot-v1",
+  "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": "4.48.3",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "dot"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d8061cc6b0f1e79d939b97790c41c637b6141ed3a398eeb8f5d841d78a93b0
+size 437967672

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": 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 +1,73 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 250,
+  "model_max_length": 512,
+  "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]"
+}