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 +1,576 @@
+---
+language:
+- en
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:404290
+- loss:OnlineContrastiveLoss
+base_model: sentence-transformers/stsb-distilbert-base
+widget:
+- source_sentence: Why Modi is putting a ban on 500 and 1000 notes?
+  sentences:
+  - Why making multiple fake accounts on Quora is illegal?
+  - What are the advantages of the decision taken by the Government of India to scrap
+    out 500 and 1000 rupees notes?
+  - Why should I go for internships?
+- source_sentence: Where can I buy cheap t-shirts?
+  sentences:
+  - Where can I buy cheap wholesale t-shirts?
+  - How can I make money from a blog?
+  - What are the best places to shop in Charleston, SC?
+- source_sentence: What are the most important mobile applications?
+  sentences:
+  - How can I tell if my wife's vagina had a bigger penis inside?
+  - What is the most important apps in your phone?
+  - What do you think Ned Stark would have done or said to Jon Snow if he was able
+    to join the Night’s Watch or escaped his beheading?
+- source_sentence: What is the whole process for making Android games with high graphics?
+  sentences:
+  - What lf I don't accept Jesus as God?
+  - I have to masturbate3 times to feel an orgasm sometimes only2 times what is wrong
+    with me I went to the doctor and they do not believe meWhat's wrong?
+  - What does a healthy diet consist of?
+- source_sentence: Why do so many religious people believe in healing miracles?
+  sentences:
+  - Is Warframe better than Destiny?
+  - What do you like about China?
+  - Is believing in God a bad thing?
+datasets:
+- sentence-transformers/quora-duplicates
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+- average_precision
+- f1
+- precision
+- recall
+- threshold
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on sentence-transformers/stsb-distilbert-base
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: quora duplicates
+      type: quora-duplicates
+    metrics:
+    - type: cosine_accuracy
+      value: 0.877
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7857047319412231
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.8516284680337757
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.774639368057251
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.8209302325581396
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8847117794486216
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.8988328505183655
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.7483655051498526
+      name: Cosine Mcc
+  - task:
+      type: paraphrase-mining
+      name: Paraphrase Mining
+    dataset:
+      name: quora duplicates dev
+      type: quora-duplicates-dev
+    metrics:
+    - type: average_precision
+      value: 0.5483042026376685
+      name: Average Precision
+    - type: f1
+      value: 0.5606415792720543
+      name: F1
+    - type: precision
+      value: 0.5539301735907939
+      name: Precision
+    - type: recall
+      value: 0.5675176100314733
+      name: Recall
+    - type: threshold
+      value: 0.8631762564182281
+      name: Threshold
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9308
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.969
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9778
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9854
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9308
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.4145333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.26696000000000003
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.14144
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8008592901379665
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9314231047351341
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9558165998609235
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9743579383296442
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9511384841680516
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9511976190476192
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.939071878001028
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on sentence-transformers/stsb-distilbert-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) on the [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) dataset. 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/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) <!-- at revision 8ea752b88e5f7239f96bdde0bc62e265c3999eec -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
+- **Language:** en
+<!-- - **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': 128, '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("omega5505/stsb-distilbert-base-ocl")
+# Run inference
+sentences = [
+    'Why do so many religious people believe in healing miracles?',
+    'Is believing in God a bad thing?',
+    'What do you like about China?',
+]
+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
+
+* Dataset: `quora-duplicates`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value      |
+|:--------------------------|:-----------|
+| cosine_accuracy           | 0.877      |
+| cosine_accuracy_threshold | 0.7857     |
+| cosine_f1                 | 0.8516     |
+| cosine_f1_threshold       | 0.7746     |
+| cosine_precision          | 0.8209     |
+| cosine_recall             | 0.8847     |
+| **cosine_ap**             | **0.8988** |
+| cosine_mcc                | 0.7484     |
+
+#### Paraphrase Mining
+
+* Dataset: `quora-duplicates-dev`
+* Evaluated with [<code>ParaphraseMiningEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator)
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| **average_precision** | **0.5483** |
+| f1                    | 0.5606     |
+| precision             | 0.5539     |
+| recall                | 0.5675     |
+| threshold             | 0.8632     |
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9308     |
+| cosine_accuracy@3   | 0.969      |
+| cosine_accuracy@5   | 0.9778     |
+| cosine_accuracy@10  | 0.9854     |
+| cosine_precision@1  | 0.9308     |
+| cosine_precision@3  | 0.4145     |
+| cosine_precision@5  | 0.267      |
+| cosine_precision@10 | 0.1414     |
+| cosine_recall@1     | 0.8009     |
+| cosine_recall@3     | 0.9314     |
+| cosine_recall@5     | 0.9558     |
+| cosine_recall@10    | 0.9744     |
+| **cosine_ndcg@10**  | **0.9511** |
+| cosine_mrr@10       | 0.9512     |
+| cosine_map@100      | 0.9391     |
+
+<!--
+## 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
+
+#### quora-duplicates
+
+* Dataset: [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 404,290 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: 6 tokens</li><li>mean: 15.73 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.93 tokens</li><li>max: 85 tokens</li></ul> | <ul><li>0: ~61.60%</li><li>1: ~38.40%</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                     | sentence2                                                                                                  | label          |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>How can Trump supporters claim he didn't mock a disabled reporter when there is live footage of him mocking a disabled reporter?</code> | <code>Why don't people actually watch the Trump video of him allegedly mocking a disabled reporter?</code> | <code>0</code> |
+  | <code>Where can I get the best digital marketing course (online & offline) in India?</code>                                                   | <code>Which is the best digital marketing institute for professionals in India?</code>                     | <code>1</code> |
+  | <code>What best two liner shayri?</code>                                                                                                      | <code>What does "senile dementia, uncomplicated" mean in medical terms?</code>                             | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Evaluation Dataset
+
+#### quora-duplicates
+
+* Dataset: [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 404,290 evaluation 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: 6 tokens</li><li>mean: 16.14 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.92 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>0: ~60.10%</li><li>1: ~39.90%</li></ul> |
+* Samples:
+  | sentence1                                               | sentence2                                                  | label          |
+  |:--------------------------------------------------------|:-----------------------------------------------------------|:---------------|
+  | <code>What are some must subscribe RSS feeds?</code>    | <code>What are RSS feeds?</code>                           | <code>0</code> |
+  | <code>How close are Madonna and Hillary Clinton?</code> | <code>Why do people say Hillary Clinton is a crook?</code> | <code>0</code> |
+  | <code>Can you share best day of your life?</code>       | <code>What is the Best Day of your life till date?</code>  | <code>1</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 1
+- `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`: 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
+- `torch_empty_cache_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`: 1
+- `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
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | quora-duplicates_cosine_ap | quora-duplicates-dev_average_precision | cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:--------------------------:|:--------------------------------------:|:--------------:|
+| 0      | 0    | -             | -               | 0.7458                     | 0.4200                                 | 0.9390         |
+| 0.0640 | 100  | 2.5263        | -               | -                          | -                                      | -              |
+| 0.1280 | 200  | 2.1489        | -               | -                          | -                                      | -              |
+| 0.1599 | 250  | -             | 1.8621          | 0.8433                     | 0.3907                                 | 0.9329         |
+| 0.1919 | 300  | 2.0353        | -               | -                          | -                                      | -              |
+| 0.2559 | 400  | 1.7831        | -               | -                          | -                                      | -              |
+| 0.3199 | 500  | 1.8887        | 1.7744          | 0.8662                     | 0.4924                                 | 0.9379         |
+| 0.3839 | 600  | 1.7814        | -               | -                          | -                                      | -              |
+| 0.4479 | 700  | 1.7775        | -               | -                          | -                                      | -              |
+| 0.4798 | 750  | -             | 1.6468          | 0.8766                     | 0.4945                                 | 0.9399         |
+| 0.5118 | 800  | 1.6835        | -               | -                          | -                                      | -              |
+| 0.5758 | 900  | 1.6974        | -               | -                          | -                                      | -              |
+| 0.6398 | 1000 | 1.5704        | 1.4925          | 0.8895                     | 0.5283                                 | 0.9460         |
+| 0.7038 | 1100 | 1.6771        | -               | -                          | -                                      | -              |
+| 0.7678 | 1200 | 1.619         | -               | -                          | -                                      | -              |
+| 0.7997 | 1250 | -             | 1.4311          | 0.8982                     | 0.5252                                 | 0.9466         |
+| 0.8317 | 1300 | 1.6119        | -               | -                          | -                                      | -              |
+| 0.8957 | 1400 | 1.6043        | -               | -                          | -                                      | -              |
+| 0.9597 | 1500 | 1.6848        | 1.4070          | 0.8988                     | 0.5483                                 | 0.9511         |
+
+
+### Framework Versions
+- Python: 3.9.18
+- Sentence Transformers: 3.4.1
+- Transformers: 4.44.2
+- PyTorch: 2.2.1+cu121
+- Accelerate: 1.3.0
+- Datasets: 2.19.0
+- 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": "sentence-transformers/stsb-distilbert-base",
+  "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": "4.44.2",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.2.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a371751d04ac0eed530b1805d1f4e91a98f64f5d08992e5533eff73184e687e6
+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": 128,
+  "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 +1,58 @@
+{
+  "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,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}