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 +1,644 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:1625
+- loss:CosineSimilarityLoss
+base_model: BAAI/bge-base-en-v1.5
+datasets: []
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Boron Steel
+  sentences:
+  - Rock Bit
+  - Spalling Test
+  - Excavator Bucket
+- source_sentence: Friction Wear
+  sentences:
+  - Tool Steel
+  - Medium Carbon Steel
+  - Diffusion Bonding
+- source_sentence: Delamination
+  sentences:
+  - Subsea Christmas Tree
+  - Low Alloyed Steel
+  - Screw Conveyors
+- source_sentence: Nitriding
+  sentences:
+  - Subsea Manifold
+  - Trencher Chain
+  - Cylinder
+- source_sentence: Corrosion Resistant Coatings
+  sentences:
+  - Mower Blade
+  - Gas Metal Arc Welding (GMAW)
+  - Corrosion Resistant Coatings
+pipeline_tag: sentence-similarity
+model-index:
+- name: BGE base Financial Matryoshka
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: pearson_cosine
+      value: 0.9548051644723275
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6620048542679903
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.985909077336812
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6620048542679903
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9863519709955113
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6620048542679903
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.9548051701614557
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6610658947764548
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9863519709955113
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6620048542679903
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: pearson_cosine
+      value: 0.9544417196413574
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6620048542679903
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.9855825558550574
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6620048542679903
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9862004412296757
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6620048542679903
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.9501184326722917
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6607798700248341
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9862004412296757
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6620048542679903
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: pearson_cosine
+      value: 0.9494511778471465
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6620048542679903
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.9830259644213172
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6620048542679903
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9835562939431381
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6620048542679903
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.9469313992827345
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6607798700248341
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9835562939431381
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6620048542679903
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: pearson_cosine
+      value: 0.9397052405386266
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6620048542679903
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.9762184586055923
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6620048542679903
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9781975526221939
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6620048542679903
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.9271211389022183
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6607798700248341
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9781975526221939
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6620048542679903
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: pearson_cosine
+      value: 0.9149032642312528
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6620048542679903
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.968215524939354
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6620048542679903
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9708485057392984
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6620048542679903
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8940456314300972
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6602255244962898
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9708485057392984
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6620048542679903
+      name: Spearman Max
+---
+
+# BGE base Financial Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### 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': True}) with Transformer model: BertModel 
+  (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})
+  (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("thetayne/finetuned_model_0613")
+# Run inference
+sentences = [
+    'Corrosion Resistant Coatings',
+    'Corrosion Resistant Coatings',
+    'Mower Blade',
+]
+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: `dim_768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.9548    |
+| **spearman_cosine** | **0.662** |
+| pearson_manhattan   | 0.9859    |
+| spearman_manhattan  | 0.662     |
+| pearson_euclidean   | 0.9864    |
+| spearman_euclidean  | 0.662     |
+| pearson_dot         | 0.9548    |
+| spearman_dot        | 0.6611    |
+| pearson_max         | 0.9864    |
+| spearman_max        | 0.662     |
+
+#### Semantic Similarity
+* Dataset: `dim_512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.9544    |
+| **spearman_cosine** | **0.662** |
+| pearson_manhattan   | 0.9856    |
+| spearman_manhattan  | 0.662     |
+| pearson_euclidean   | 0.9862    |
+| spearman_euclidean  | 0.662     |
+| pearson_dot         | 0.9501    |
+| spearman_dot        | 0.6608    |
+| pearson_max         | 0.9862    |
+| spearman_max        | 0.662     |
+
+#### Semantic Similarity
+* Dataset: `dim_256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.9495    |
+| **spearman_cosine** | **0.662** |
+| pearson_manhattan   | 0.983     |
+| spearman_manhattan  | 0.662     |
+| pearson_euclidean   | 0.9836    |
+| spearman_euclidean  | 0.662     |
+| pearson_dot         | 0.9469    |
+| spearman_dot        | 0.6608    |
+| pearson_max         | 0.9836    |
+| spearman_max        | 0.662     |
+
+#### Semantic Similarity
+* Dataset: `dim_128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.9397    |
+| **spearman_cosine** | **0.662** |
+| pearson_manhattan   | 0.9762    |
+| spearman_manhattan  | 0.662     |
+| pearson_euclidean   | 0.9782    |
+| spearman_euclidean  | 0.662     |
+| pearson_dot         | 0.9271    |
+| spearman_dot        | 0.6608    |
+| pearson_max         | 0.9782    |
+| spearman_max        | 0.662     |
+
+#### Semantic Similarity
+* Dataset: `dim_64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.9149    |
+| **spearman_cosine** | **0.662** |
+| pearson_manhattan   | 0.9682    |
+| spearman_manhattan  | 0.662     |
+| pearson_euclidean   | 0.9708    |
+| spearman_euclidean  | 0.662     |
+| pearson_dot         | 0.894     |
+| spearman_dot        | 0.6602    |
+| pearson_max         | 0.9708    |
+| spearman_max        | 0.662     |
+
+<!--
+## 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: 1,625 training samples
+* Columns: <code>sentence_A</code>, <code>sentence_B</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_A                                                                       | sentence_B                                                                       | score                                           |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.68 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.73 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>0: ~83.30%</li><li>1: ~16.70%</li></ul> |
+* Samples:
+  | sentence_A                         | sentence_B                            | score          |
+  |:-----------------------------------|:--------------------------------------|:---------------|
+  | <code>Thermal Fatigue</code>       | <code>Ferritic Stainless Steel</code> | <code>0</code> |
+  | <code>High Temperature Wear</code> | <code>Drill String</code>             | <code>0</code> |
+  | <code>Carbide Coatings</code>      | <code>Carbide Coatings</code>         | <code>1</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`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `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`: True
+- `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`: True
+- `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_fused
+- `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
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_128_spearman_cosine | dim_256_spearman_cosine | dim_512_spearman_cosine | dim_64_spearman_cosine | dim_768_spearman_cosine |
+|:----------:|:------:|:-------------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|:-----------------------:|
+| 0          | 0      | -             | 0.6626                  | 0.6626                  | 0.6626                  | 0.6626                 | 0.6626                  |
+| 0.9412     | 3      | -             | 0.6620                  | 0.6620                  | 0.6620                  | 0.6620                 | 0.6620                  |
+| 1.8627     | 6      | -             | 0.6620                  | 0.6620                  | 0.6620                  | 0.6620                 | 0.6620                  |
+| 2.7843     | 9      | -             | 0.6620                  | 0.6620                  | 0.6620                  | 0.6620                 | 0.6620                  |
+| 3.0784     | 10     | 0.156         | -                       | -                       | -                       | -                      | -                       |
+| **3.7059** | **12** | **-**         | **0.662**               | **0.662**               | **0.662**               | **0.662**              | **0.662**               |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.31.0
+- Datasets: 2.19.1
+- 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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+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:a914a7f6770ec2aa31953dd18e4f7590d1fd79343c31efdb73b46647a5c67f87
+size 437951328

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": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}