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 +1,513 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:100K<n<1M
+- loss:CoSENTLoss
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+base_model: distilbert/distilbert-base-uncased
+widget:
+- source_sentence: T L 2 DUMMY CHEST LAT WIDEBAND 90 Deg Front 2020 CX482 G-S
+  sentences:
+  - T L F DUMMY CHEST LAT WIDEBAND 90 Deg Front 2020.5 U625 G-S
+  - T L F DUMMY HEAD CG LAT WIDEBAND Static Airbag OOP Test 2025 CX430 G-S
+  - T R F DUMMY PELVIS LAT WIDEBAND 90 Deg Frontal Impact Simulation 2026 P800 G-S
+- source_sentence: T L F DUMMY CHEST LONG WIDEBAND 90 Deg Front 2022 U553 G-S
+  sentences:
+  - T R F TORSO BELT AT D RING LOAD WIDEBAND 90 Deg Front 2022 U553 LBF
+  - T L F DUMMY L UP TIBIA MY LOAD WIDEBAND 90 Deg Front 2015 P552 IN-LBS
+  - T R F DUMMY R UP TIBIA FX LOAD WIDEBAND 30 Deg Front Angular Left 2022 U554 LBF
+- source_sentence: T R F DUMMY PELVIS LAT WIDEBAND 90 Deg Front 2019 D544 G-S
+  sentences:
+  - T L F DUMMY PELVIS LAT WIDEBAND 90 Deg Front 2015 P552 G-S
+  - T L LOWER CONTROL ARM VERT WIDEBAND Left Side Drop Test 2024.5 P702 G-S
+  - F BARRIER PLATE 11030 SZ D FX LOAD WIDEBAND 90 Deg Front 2015 P552 LBF
+- source_sentence: T ENGINE ENGINE TOP LAT WIDEBAND 90 Deg Front 2015 P552 G-S
+  sentences:
+  - T R ENGINE TRANS BOTTOM LAT WIDEBAND 90 Deg Front 2015 P552 G-S
+  - F BARRIER PLATE 09030 SZ D FX LOAD WIDEBAND 90 Deg Front 2015 P552 LBF
+  - T R F DUMMY NECK UPPER MX LOAD WIDEBAND 90 Deg Front 2022 U554 IN-LBS
+- source_sentence: T L F DUMMY CHEST LAT WIDEBAND 90 Deg Front 2020 CX482 G-S
+  sentences:
+  - T R F DUMMY CHEST LAT WIDEBAND 90 Deg Front 2025 V363N G-S
+  - T R F DUMMY HEAD CG VERT WIDEBAND VIA Linear Impact Test 2021 C727 G-S
+  - T L F DUMMY T1 VERT WIDEBAND 75 Deg Oblique Left Side 10 in. Pole 2026 P800 G-S
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on distilbert/distilbert-base-uncased
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.27051173706186693
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.2798593637893599
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.228702027931258
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.25353345676390787
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.23018017587211453
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.2550481010151111
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.2125353301405465
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.1902748420981738
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.27051173706186693
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.2798593637893599
+      name: Spearman Max
+    - type: pearson_cosine
+      value: 0.26319176781258086
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.2721909587247752
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.21766215319708615
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.2439514548051345
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.2195389492634635
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.24629153092425862
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.21073878591545503
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.1864889259868287
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.26319176781258086
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.2721909587247752
+      name: Spearman Max
+---
+
+# SentenceTransformer based on distilbert/distilbert-base-uncased
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased). 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:** [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) <!-- at revision 12040accade4e8a0f71eabdb258fecc2e7e948be -->
+- **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: DistilBertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'T L F DUMMY CHEST LAT WIDEBAND 90 Deg Front 2020 CX482 G-S',
+    'T R F DUMMY CHEST LAT WIDEBAND 90 Deg Front 2025 V363N G-S',
+    'T R F DUMMY HEAD CG VERT WIDEBAND VIA Linear Impact Test 2021 C727 G-S',
+]
+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-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.2705     |
+| **spearman_cosine** | **0.2799** |
+| pearson_manhattan   | 0.2287     |
+| spearman_manhattan  | 0.2535     |
+| pearson_euclidean   | 0.2302     |
+| spearman_euclidean  | 0.255      |
+| pearson_dot         | 0.2125     |
+| spearman_dot        | 0.1903     |
+| pearson_max         | 0.2705     |
+| spearman_max        | 0.2799     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.2632     |
+| **spearman_cosine** | **0.2722** |
+| pearson_manhattan   | 0.2177     |
+| spearman_manhattan  | 0.244      |
+| pearson_euclidean   | 0.2195     |
+| spearman_euclidean  | 0.2463     |
+| pearson_dot         | 0.2107     |
+| spearman_dot        | 0.1865     |
+| pearson_max         | 0.2632     |
+| spearman_max        | 0.2722     |
+
+<!--
+## 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: 481,114 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: 16 tokens</li><li>mean: 32.14 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 32.62 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                   | sentence2                                                                                                         | score                           |
+  |:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>T L C PLR SM SCS L2 HY REF 053 LAT WIDEBAND 75 Deg Oblique Left Side 10 in. Pole 2018 P558 G-S</code> | <code>T PCM PWR POWER TO PCM VOLT 2 SEC WIDEBAND 75 Deg Oblique Left Side 10 in. Pole 2020 V363N VOLTS</code>     | <code>0.5198143220305642</code> |
+  | <code>T L F DUMMY L_FEMUR MX LOAD WIDEBAND 90 Deg Frontal Impact Simulation MY2025 U717 IN-LBS</code>       | <code>B L FRAME AT No 1 X MEM LAT WIDEBAND Inline 25% Left Front Offset Vehicle to Vehicle 2021 P702 G-S</code>   | <code>0.5214072221695696</code> |
+  | <code>T R F DOOR REAR OF SEAT H PT LAT WIDEBAND 75 Deg Oblique Right Side 10 in. Pole 2015 P552 G-S</code>  | <code>T SCS R2 HY BOS A12 008 TAP RIGHT C PILLAR VOLT WIDEBAND 30 Deg Front Angular Right 2021 CX727 VOLTS</code> | <code>0.322173496575591</code>  |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 103,097 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: 17 tokens</li><li>mean: 31.98 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 31.96 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                 | sentence2                                                                                                                      | score                            |
+  |:----------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------|:---------------------------------|
+  | <code>T R F DUMMY NECK UPPER MZ LOAD WIDEBAND 90 Deg Frontal Impact Simulation 2026 GENERIC IN-LBS</code> | <code>T R ROCKER AT C PILLAR LAT WIDEBAND 90 Deg Front 2021 P702 G-S</code>                                                    | <code>0.5234504780172093</code>  |
+  | <code>T L ROCKER AT B_PILLAR VERT WIDEBAND 90 Deg Front 2024.5 P702 G-S</code>                            | <code>T RCM BTWN SEATS LOW G Z RCM C1 LZ ALV RC7 003 VOLT WIDEBAND 75 Deg Oblique Left Side 10 in. Pole 2018 P558 VOLTS</code> | <code>0.36805699821563936</code> |
+  | <code>T R FRAME AT C_PILLAR LONG WIDEBAND 90 Deg Left Side IIHS MDB to Vehicle 2024.5 P702 G-S</code>     | <code>T L F LAP BELT AT ANCHOR LOAD WIDEBAND 90 DEG / LEFT SIDE DECEL-3G 2021 P702 LBF</code>                                  | <code>0.5309750606095435</code>  |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 32
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `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`: 32
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `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
+- `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`: 7
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 0
+- `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_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: 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
+- `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
+- `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`: False
+- `include_tokens_per_second`: False
+- `neftune_noise_alpha`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step  | Training Loss | loss   | sts-dev_spearman_cosine |
+|:-------:|:-----:|:-------------:|:------:|:-----------------------:|
+| 1.0650  | 1000  | 7.6111        | 7.5503 | 0.4087                  |
+| 2.1299  | 2000  | 7.5359        | 7.5420 | 0.4448                  |
+| 3.1949  | 3000  | 7.5232        | 7.5292 | 0.4622                  |
+| 4.2599  | 4000  | 7.5146        | 7.5218 | 0.4779                  |
+| 5.3248  | 5000  | 7.5045        | 7.5200 | 0.4880                  |
+| 6.3898  | 6000  | 7.4956        | 7.5191 | 0.4934                  |
+| 7.4547  | 7000  | 7.4873        | 7.5170 | 0.4967                  |
+| 8.5197  | 8000  | 7.4781        | 7.5218 | 0.4931                  |
+| 9.5847  | 9000  | 7.4686        | 7.5257 | 0.4961                  |
+| 10.6496 | 10000 | 7.4596        | 7.5327 | 0.4884                  |
+| 11.7146 | 11000 | 7.4498        | 7.5403 | 0.4860                  |
+| 12.7796 | 12000 | 7.4386        | 7.5507 | 0.4735                  |
+| 13.8445 | 13000 | 7.4253        | 7.5651 | 0.4660                  |
+| 14.9095 | 14000 | 7.4124        | 7.5927 | 0.4467                  |
+| 15.9744 | 15000 | 7.3989        | 7.6054 | 0.4314                  |
+| 17.0394 | 16000 | 7.3833        | 7.6654 | 0.4163                  |
+| 18.1044 | 17000 | 7.3669        | 7.7186 | 0.3967                  |
+| 19.1693 | 18000 | 7.3519        | 7.7653 | 0.3779                  |
+| 20.2343 | 19000 | 7.3349        | 7.8356 | 0.3651                  |
+| 21.2993 | 20000 | 7.3191        | 7.8772 | 0.3495                  |
+| 22.3642 | 21000 | 7.3032        | 7.9346 | 0.3412                  |
+| 23.4292 | 22000 | 7.2873        | 7.9624 | 0.3231                  |
+| 24.4941 | 23000 | 7.2718        | 8.0169 | 0.3161                  |
+| 25.5591 | 24000 | 7.2556        | 8.0633 | 0.3050                  |
+| 26.6241 | 25000 | 7.2425        | 8.1021 | 0.2958                  |
+| 27.6890 | 26000 | 7.2278        | 8.1563 | 0.2954                  |
+| 28.7540 | 27000 | 7.2124        | 8.1955 | 0.2882                  |
+| 29.8190 | 28000 | 7.2014        | 8.2234 | 0.2821                  |
+| 30.8839 | 29000 | 7.1938        | 8.2447 | 0.2792                  |
+| 31.9489 | 30000 | 7.1811        | 8.2609 | 0.2799                  |
+| 32.0    | 30048 | -             | -      | 0.2722                  |
+
+
+### Framework Versions
+- Python: 3.10.6
+- Sentence Transformers: 3.0.0
+- Transformers: 4.35.0
+- PyTorch: 2.1.0a0+4136153
+- Accelerate: 0.30.1
+- Datasets: 2.14.1
+- Tokenizers: 0.14.1
+
+## 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",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## 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": "./encoder/training_stsbenchmark_distilbert-base-uncased-2024-06-08_01-23-53/final",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.35.0",
+    "pytorch": "2.1.0a0+4136153"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861fdc3f9bf4c0aa14f6ccaa4a04312452eee70b76823a8faf03c02ddac515a8
+size 265462608

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}