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:3362
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/multi-qa-mpnet-base-dot-v1
+widget:
+- source_sentence: '
+
+    Guests are responsible for damages caused to hotel property according to the valid
+    legal
+
+    prescriptions of Hungary.'
+  sentences:
+  - '
+
+    Guests are responsible for damages caused to hotel property according to the valid
+    legal
+
+    prescriptions of Hungary.'
+  - '
+
+    We request that guests report any complaints and defects to the hotel reception
+    or hotel
+
+    management in person. Your complaints shall be attended to immediately.'
+  - '
+
+    We do not guarantee that any special requests will be met, but we will use our
+    best endeavours to do so as
+
+    well as using our best endeavours to advise you if that is not the case.'
+- source_sentence: '
+
+    If we must cancel the reservation due to circumstances beyond our control, the
+    entire payment will be
+
+    refunded to you without any further obligation on our part and you will have no
+    further recourse against us.'
+  sentences:
+  - '
+
+    We do not guarantee that any special requests will be met, but we will use our
+    best endeavours to do so as
+
+    well as using our best endeavours to advise you if that is not the case.'
+  - '
+
+    A hotel guest may not leave the room to another person, even if the time for which
+    he or she has paid has
+
+    not expired.'
+  - '
+
+    If we must cancel the reservation due to circumstances beyond our control, the
+    entire payment will be
+
+    refunded to you without any further obligation on our part and you will have no
+    further recourse against us.'
+- source_sentence: 'For safety reasons it is not permitted to leave children under
+    12 years of age in hotel
+
+    rooms and other common areas of the hotel without adult supervision, and children
+    under
+
+    12 years of age may not use the lift without supervision.'
+  sentences:
+  - 'For safety reasons it is not permitted to leave children under 12 years of age
+    in hotel
+
+    rooms and other common areas of the hotel without adult supervision, and children
+    under
+
+    12 years of age may not use the lift without supervision.'
+  - '
+
+    I accept personal responsibility for payment of all amounts arising from my party''s
+    stay at the Hotel.
+
+    I/we are obligated to vacate my/our room/s at the designated check-out time, unless
+    I have made prior
+
+    alternative check-out arrangements with the management of the Hotel. My/our failure
+    to do so will result in
+
+    my liability for the costs of an additional night''s accommodation.'
+  - '
+
+    Elevators are to be used for the sole purpose of transporting guests and their
+    luggage to the appropriate
+
+    floor of the hotel. Misuse and horseplay will not be allowed.'
+- source_sentence: '
+
+    Accommodation in the hotel is permitted only to persons who are not carrying infectious
+
+    diseases and who are not visibly under the influence of alcohol or drugs.'
+  sentences:
+  - '
+
+    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.'
+  - '
+
+    Accommodation in the hotel is permitted only to persons who are not carrying infectious
+
+    diseases and who are not visibly under the influence of alcohol or drugs.'
+  - '
+
+    The pets can not be left without supervision if there is a risk of causing any
+
+    damage or might disturb other guests.'
+- source_sentence: '
+
+    A hotel guest may not leave the room to another person, even if the time for which
+    he or she has paid has
+
+    not expired.'
+  sentences:
+  - '
+
+    A hotel guest may not leave the room to another person, even if the time for which
+    he or she has paid has
+
+    not expired.'
+  - '
+
+    There is no running, shouting, roughhousing or horseplay accepted while on the
+    hotel property. This
+
+    includes hallways, lobby areas, stairways, elevators, food service areas and guest
+    rooms.'
+  - 'Orders for accommodation services made in writing or by other means, which have
+    been
+
+    confirmed by the hotel and have not been cancelled by the customer in a timely
+    manner, are
+
+    mutually binding. The front office manager keeps a record of all received and
+    confirmed
+
+    orders.'
+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: 0.667063020214031
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 48.93047332763672
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.49865951742627346
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 33.95234298706055
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.33253873659118
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9964285714285714
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.31258772254817324
+      name: Dot Ap
+    - type: dot_mcc
+      value: 0.0
+      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/Base_Test1_")
+# Run inference
+sentences = [
+    '\nA hotel guest may not leave the room to another person, even if the time for which he or she has paid has\nnot expired.',
+    '\nA hotel guest may not leave the room to another person, even if the time for which he or she has paid has\nnot expired.',
+    'Orders for accommodation services made in writing or by other means, which have been\nconfirmed by the hotel and have not been cancelled by the customer in a timely manner, are\nmutually binding. The front office manager keeps a record of all received and confirmed\norders.',
+]
+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           | 0.6671     |
+| dot_accuracy_threshold | 48.9305    |
+| dot_f1                 | 0.4987     |
+| dot_f1_threshold       | 33.9523    |
+| dot_precision          | 0.3325     |
+| dot_recall             | 0.9964     |
+| **dot_ap**             | **0.3126** |
+| dot_mcc                | 0.0        |
+
+<!--
+## 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: 3,362 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: 11 tokens</li><li>mean: 48.75 tokens</li><li>max: 156 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 48.75 tokens</li><li>max: 156 tokens</li></ul> | <ul><li>0: ~69.20%</li><li>1: ~30.80%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                                                                              | sentence2                                                                                                                                                                                                                                                                                              | label          |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Hotel guests may receive visits in their hotel rooms from guests not staying in the hotel.<br>Visitors must present a personal document at the hotel reception and register in the visitors'<br>book. These visits can last for only a maximum of 2 hours and must finish until 10:00 pm.</code> | <code>Hotel guests may receive visits in their hotel rooms from guests not staying in the hotel.<br>Visitors must present a personal document at the hotel reception and register in the visitors'<br>book. These visits can last for only a maximum of 2 hours and must finish until 10:00 pm.</code> | <code>0</code> |
+  | <code><br>We do not guarantee that any special requests will be met, but we will use our best endeavours to do so as<br>well as using our best endeavours to advise you if that is not the case.</code>                                                                                                | <code><br>We do not guarantee that any special requests will be met, but we will use our best endeavours to do so as<br>well as using our best endeavours to advise you if that is not the case.</code>                                                                                                | <code>0</code> |
+  | <code><br>Pool and Fitness Room hours and guidelines are provided at check in. All rules and times will be enforced to<br>allow efficient operation of the hotel and for the comfort and safety of all guests.</code>                                                                                  | <code><br>Pool and Fitness Room hours and guidelines are provided at check in. All rules and times will be enforced to<br>allow efficient operation of the hotel and for the comfort and safety of all guests.</code>                                                                                  | <code>1</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 841 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 841 samples:
+  |         | sentence1                                                                          | sentence2                                                                          | label                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | int                                             |
+  | details | <ul><li>min: 11 tokens</li><li>mean: 48.1 tokens</li><li>max: 156 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 48.1 tokens</li><li>max: 156 tokens</li></ul> | <ul><li>0: ~66.71%</li><li>1: ~33.29%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                                                                                    | sentence2                                                                                                                                                                                                                                                                                                    | label          |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>In the case of fire, guests are obliged to notify the reception without hesitation, either<br>directly, or on the phone (0) and may use a portable fire extinguisher located at the corridors<br>of each floor to extinguish the flames. The use of the elevator in case of fire is prohibited!</code> | <code>In the case of fire, guests are obliged to notify the reception without hesitation, either<br>directly, or on the phone (0) and may use a portable fire extinguisher located at the corridors<br>of each floor to extinguish the flames. The use of the elevator in case of fire is prohibited!</code> | <code>0</code> |
+  | <code><br>Children should be accompanied in locations such as stairways etc.<br> The rooms are for accommodation service. Each individual staying in a room<br>must be registered at the reception.</code>                                                                                                   | <code><br>Children should be accompanied in locations such as stairways etc.<br> The rooms are for accommodation service. Each individual staying in a room<br>must be registered at the reception.</code>                                                                                                   | <code>0</code> |
+  | <code><br>Towels for the Fitness Room and Pool are located in those areas. Towels from guest rooms are not to be<br>taken to the Pool or Fitness Room.</code>                                                                                                                                                | <code><br>Towels for the Fitness Room and Pool are located in those areas. Towels from guest rooms are not to be<br>taken to the Pool or Fitness Room.</code>                                                                                                                                                | <code>0</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `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`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: 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 | dot_ap |
+|:------:|:----:|:-------------:|:---------------:|:------:|
+| -1     | -1   | -             | -               | 0.3126 |
+| 0.4739 | 100  | 0.0011        | 0.0001          | -      |
+| 0.9479 | 200  | 0.0002        | 0.0000          | -      |
+| 1.4218 | 300  | 0.0           | 0.0000          | -      |
+| 1.8957 | 400  | 0.0001        | 0.0000          | -      |
+| 2.3697 | 500  | 0.0           | 0.0000          | -      |
+| 2.8436 | 600  | 0.0           | 0.0000          | -      |
+| 3.3175 | 700  | 0.0           | 0.0000          | -      |
+| 3.7915 | 800  | 0.0           | 0.0000          | -      |
+| 4.2654 | 900  | 0.0           | 0.0000          | -      |
+| 4.7393 | 1000 | 0.0           | 0.0000          | -      |
+
+
+### 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,24 @@
+{
+  "_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:fd0d91289f33955eb9fd0d649fced0a1477fc32687dd5a2746aadbf6af795ac9
+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]"
+}