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 +1,524 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:10K<n<100K
+- loss:CosineSimilarityLoss
+base_model: distilbert/distilbert-base-uncased
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: The long jump pit had to be raked after every few attempts.
+  sentences:
+  - The high jumper cleared the bar on his first attempt.
+  - Chemists use quantum mechanics to predict electron behavior and molecular bonding.
+  - Eczema frequently appears as inflamed, tender spots on several parts of the body.
+- source_sentence: Street art transforms empty rural barns into lively murals.
+  sentences:
+  - Traditional folk music plays a significant role in preserving a community's history.
+  - '[SYNTAX] The saxophone offers the high-pitched, thrilling elements in a jazz
+    trio.'
+  - Atmospheric pressure decreases as you move higher above sea level.
+- source_sentence: Proteins are synthesized through the process of translation.
+  sentences:
+  - Molecular genetics studies the structure and function of genes at a molecular
+    level.
+  - The mathematics lecture is a compelling method for introducing integral equations.
+  - 'The correlation between air pollution and increased mortality rates is well-documented.  '
+- source_sentence: '[SYNTAX] A barometer is used to measure atmospheric pressure.'
+  sentences:
+  - '[SYNTAX] Colonialism is a primary subject in several political science research
+    papers.'
+  - '[SYNTAX] Ordinary urban walls are turned into vibrant masterpieces by street
+    art.'
+  - Email remains a significant device for academic and fictional correspondence.
+- source_sentence: Salinity gradients in oceans affect local wildlife habitats.
+  sentences:
+  - The distribution of wildlife in different habitats has fascinated ecologists for
+    decades.
+  - '[SYNTAX] Bioenergy plants can convert agricultural waste into valuable electricity.'
+  - Proper management of irrigation schedules is crucial for crop health.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on distilbert/distilbert-base-uncased
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: custom dev
+      type: custom-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.9117000984572255
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8442193394453843
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.9156511082976959
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8440889792296263
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9159884478218315
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8445673615230997
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.9046139794819923
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8327655787489855
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9159884478218315
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8445673615230997
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: custom test
+      type: custom-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.919801732989496
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8500534773438543
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.9282084953416339
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8493690342081703
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.9284184436823353
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.849759760833697
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.9141474471982576
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8410969822964006
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.9284184436823353
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8500534773438543
+      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 = [
+    'Salinity gradients in oceans affect local wildlife habitats.',
+    'The distribution of wildlife in different habitats has fascinated ecologists for decades.',
+    '[SYNTAX] Bioenergy plants can convert agricultural waste into valuable electricity.',
+]
+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: `custom-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9117     |
+| **spearman_cosine** | **0.8442** |
+| pearson_manhattan   | 0.9157     |
+| spearman_manhattan  | 0.8441     |
+| pearson_euclidean   | 0.916      |
+| spearman_euclidean  | 0.8446     |
+| pearson_dot         | 0.9046     |
+| spearman_dot        | 0.8328     |
+| pearson_max         | 0.916      |
+| spearman_max        | 0.8446     |
+
+#### Semantic Similarity
+* Dataset: `custom-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9198     |
+| **spearman_cosine** | **0.8501** |
+| pearson_manhattan   | 0.9282     |
+| spearman_manhattan  | 0.8494     |
+| pearson_euclidean   | 0.9284     |
+| spearman_euclidean  | 0.8498     |
+| pearson_dot         | 0.9141     |
+| spearman_dot        | 0.8411     |
+| pearson_max         | 0.9284     |
+| spearman_max        | 0.8501     |
+
+<!--
+## 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: 19,352 training samples
+* Columns: <code>s1</code>, <code>s2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | s1                                                                                 | s2                                                                                 | label                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | int                                             |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 19.92 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 20.53 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>0: ~50.50%</li><li>1: ~49.50%</li></ul> |
+* Samples:
+  | s1                                                                                                                                       | s2                                                                                                                                       | label          |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>According to labeling theory, individuals are considered deviant once society has tagged them with that label.</code>              | <code>Labeling theory posits that corporations become powerful when labeled as such by stakeholders.</code>                              | <code>0</code> |
+  | <code>Employers must classify workers correctly as either employees or independent contractors to comply with tax and labor laws.</code> | <code>Employers must classify workers correctly as either employees or independent contractors to comply with tax and labor laws.</code> | <code>1</code> |
+  | <code>Higher education institutions play a critical role in advancing research and innovation.</code>                                    | <code>Advancement in research and innovation is significantly driven by the contributions of higher education institutions.</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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 2,419 evaluation samples
+* Columns: <code>s1</code>, <code>s2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | s1                                                                                 | s2                                                                                 | label                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | int                                             |
+  | details | <ul><li>min: 11 tokens</li><li>mean: 19.91 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 20.46 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>0: ~49.70%</li><li>1: ~50.30%</li></ul> |
+* Samples:
+  | s1                                                                                                                          | s2                                                                                                                          | label          |
+  |:----------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Acoustic tomography is an innovative geophysical technique used to image the Earth's interior.</code>                 | <code>Acoustic tomography is an innovative geophysical technique used to image the Earth's interior.</code>                 | <code>1</code> |
+  | <code>Urban areas frequently exhibit a different age distribution pattern compared to rural areas.</code>                   | <code>Urban areas frequently exhibit a different age distribution pattern compared to rural areas.</code>                   | <code>1</code> |
+  | <code>Radiocarbon dating is a critical tool for assessing the duration of battery life in modern electronic devices.</code> | <code>Radiocarbon dating is a critical tool for assessing the duration of battery life in modern electronic devices.</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`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 10
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `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`: 10
+- `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`: 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`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | custom-dev_spearman_cosine | custom-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:--------------------------:|:---------------------------:|
+| 0.3300 | 100  | 0.2961        | 0.1185 | 0.8063                     | -                           |
+| 0.6601 | 200  | 0.0772        | 0.0504 | 0.8461                     | -                           |
+| 0.9901 | 300  | 0.0502        | 0.0454 | 0.8486                     | -                           |
+| 1.3201 | 400  | 0.0376        | 0.0402 | 0.8481                     | -                           |
+| 1.6502 | 500  | 0.0344        | 0.0400 | 0.8501                     | -                           |
+| 1.9802 | 600  | 0.0329        | 0.0390 | 0.8518                     | -                           |
+| 2.3102 | 700  | 0.0185        | 0.0387 | 0.8496                     | -                           |
+| 2.6403 | 800  | 0.0164        | 0.0371 | 0.8492                     | -                           |
+| 2.9703 | 900  | 0.0179        | 0.0393 | 0.8428                     | -                           |
+| 3.3003 | 1000 | 0.0099        | 0.0389 | 0.8466                     | -                           |
+| 3.6304 | 1100 | 0.0092        | 0.0395 | 0.8480                     | -                           |
+| 3.9604 | 1200 | 0.0101        | 0.0368 | 0.8492                     | -                           |
+| 4.2904 | 1300 | 0.0067        | 0.0385 | 0.8474                     | -                           |
+| 4.6205 | 1400 | 0.0056        | 0.0393 | 0.8456                     | -                           |
+| 4.9505 | 1500 | 0.0068        | 0.0401 | 0.8466                     | -                           |
+| 5.2805 | 1600 | 0.0041        | 0.0410 | 0.8462                     | -                           |
+| 5.6106 | 1700 | 0.0043        | 0.0399 | 0.8469                     | -                           |
+| 5.9406 | 1800 | 0.0039        | 0.0406 | 0.8463                     | -                           |
+| 6.2706 | 1900 | 0.003         | 0.0400 | 0.8456                     | -                           |
+| 6.6007 | 2000 | 0.0026        | 0.0416 | 0.8438                     | -                           |
+| 6.9307 | 2100 | 0.0027        | 0.0420 | 0.8437                     | -                           |
+| 7.2607 | 2200 | 0.0028        | 0.0424 | 0.8449                     | -                           |
+| 7.5908 | 2300 | 0.0021        | 0.0422 | 0.8458                     | -                           |
+| 7.9208 | 2400 | 0.002         | 0.0414 | 0.8451                     | -                           |
+| 8.2508 | 2500 | 0.0015        | 0.0421 | 0.8451                     | -                           |
+| 8.5809 | 2600 | 0.0015        | 0.0427 | 0.8451                     | -                           |
+| 8.9109 | 2700 | 0.0016        | 0.0429 | 0.8444                     | -                           |
+| 9.2409 | 2800 | 0.0011        | 0.0432 | 0.8442                     | -                           |
+| 9.5710 | 2900 | 0.0014        | 0.0432 | 0.8444                     | -                           |
+| 9.9010 | 3000 | 0.0011        | 0.0432 | 0.8442                     | -                           |
+| 10.0   | 3030 | -             | -      | -                          | 0.8501                      |
+
+
+### Framework Versions
+- Python: 3.11.9
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- 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 +1,24 @@
+{
+  "_name_or_path": "./output/training_stsbenchmark_distilbert-base-uncased-2024-06-18_11-20-16/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": "4.41.1",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.0+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 sha256:35a557849989bbc9a9bf27fba43bd3d80ed2def89605f38b8ab1d2cdf648ea4f
+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]"
+}