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 +1,443 @@
+---
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:7999
+- loss:MultipleNegativesRankingLoss
+base_model: medicalai/ClinicalBERT
+metrics:
+- cosine_accuracy
+widget:
+- source_sentence: pt,dressing,pi,surgery,2 weeks,o,ozing,regular,dressing,weight,111.
+    800,height,179. 000,temperature,97. 700,pulse,88. 000,res,19. 000 bp,sy,sto,145.
+    000 bp,dia,sto,82. 000 spo,2,:,99,cap,blood sugar,ja,undice,ec,no past medical
+    history,no past medical history,no past medical history,no past medical history,no
+    past medical history,no past medical history,no past,no,no,no past,no,past,no,no,no,no,no,no,no,no,no,no,no,stable,stable,stable,stable,stable,stable,stable,stable,stable,stable,normal,no,surgical
+    history,no,surgical history,no,surgical history,no,no
+  sentences:
+  - Acne vulgaris
+  - Encounter for change or removal of surgical wound dressing
+  - Irritant contact dermatitis due to detergents
+- source_sentence: 'fa,dubai,arab emirates,cardiac assessment,chest,pain,nausea,mild,dizzy,sleep,clinic,pulse,70,res,18,res,normal,sao,:,98,air
+    time,00 : 39 : 00,bp,140 / 100,cap,< 2 sec,temperature,36,>,3 reacts,right,>,3
+    reacts,total,gcs,15,car,mild'
+  sentences:
+  - Dizziness and giddiness
+  - Pruritus, unspecified
+  - Acute gastritis without bleeding
+- source_sentence: low,back,pain,1,no,sp,fine,lower back,moderate,1 month,no,diseases,no,no,no,no,no,no,single,normal,no,no,no,normal,normal,normal,normal,cvs,cv,normal,abnormal,-
+    genito - urinary,normal,systems _ cns - cns,normal,musc,mu,normal,ps,normal,systems,endo
+    - end,normal,normal,haemo,haem,normal,low,back,pain,1 month
+  sentences:
+  - Headache
+  - Muscle spasm of back
+  - Other chest pain
+- source_sentence: 'fa,ap,arab,mobility,knee assessment,ambula,tory,c,/,o,pain,swelling,right,cold
+    pack,crepebanda,v,pt,transfer,pulse,68r,16,res,normal,sao,: 100,air time,07 :
+    29 : 00,bp,112 / 78,cap,< 2 sec,4 reacts,right,-,>,3,reacts,gcs,15,pain,4,blood,car
+    accident,twisted,right ankle'
+  sentences:
+  - Unspecified injury of right ankle, initial encounter
+  - Other spondylosis with radiculopathy, lumbosacral region
+  - Right upper quadrant pain
+- source_sentence: irregular,period,few months,moderate,few months ago,none,weight,90.
+    000,height,163. 000,temperature,98. 600,pulse,82. 000,respiration,19. 000 bp,systolic,110.
+    000 bp,diastolic,70. 000,sp,o,2,:,99,cap,blood sugar,ja,und,ice,ec,abd,an,l,girth,head,chest,ch
+    ida ch vitamin d deficiency,polycystic ovary syndrome,ch ida ch vitamin d deficiency,polycystic
+    ovary syndrome,ch,ida ch vitamin d deficiency,polycystic ovary syndrome,ch,ida
+    ch vitamin d deficiency,polycystic ovary syndrome,no,no family,no,no,nation,grade
+    11,grade 11,grade 11,grade 11,no,no,no,no,normal,normal,normal,normal,_ cvs,cv,normal,normal,irregular
+    period,cns,cn,normal,mu,normal,normal,normal,normal,normal,normal,irregular period
+  sentences:
+  - Pain in right hip
+  - Radial styloid tenosynovitis [de Quervain]
+  - Irregular menstruation, unspecified
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on medicalai/ClinicalBERT
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: ai job validation
+      type: ai-job-validation
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9429429173469543
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: ai job test
+      type: ai-job-test
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9290709495544434
+      name: Cosine Accuracy
+---
+
+# SentenceTransformer based on medicalai/ClinicalBERT
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [medicalai/ClinicalBERT](https://huggingface.co/medicalai/ClinicalBERT) on the parquet 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:** [medicalai/ClinicalBERT](https://huggingface.co/medicalai/ClinicalBERT) <!-- at revision 3bb5faa9f33458dd7801549e88767c3b23264942 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - parquet
+<!-- - **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("khaled-omar/distilroberta-ai-job-embeddings")
+# Run inference
+sentences = [
+    'irregular,period,few months,moderate,few months ago,none,weight,90. 000,height,163. 000,temperature,98. 600,pulse,82. 000,respiration,19. 000 bp,systolic,110. 000 bp,diastolic,70. 000,sp,o,2,:,99,cap,blood sugar,ja,und,ice,ec,abd,an,l,girth,head,chest,ch ida ch vitamin d deficiency,polycystic ovary syndrome,ch ida ch vitamin d deficiency,polycystic ovary syndrome,ch,ida ch vitamin d deficiency,polycystic ovary syndrome,ch,ida ch vitamin d deficiency,polycystic ovary syndrome,no,no family,no,no,nation,grade 11,grade 11,grade 11,grade 11,no,no,no,no,normal,normal,normal,normal,_ cvs,cv,normal,normal,irregular period,cns,cn,normal,mu,normal,normal,normal,normal,normal,normal,irregular period',
+    'Irregular menstruation, unspecified',
+    'Radial styloid tenosynovitis [de Quervain]',
+]
+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
+
+#### Triplet
+
+* Datasets: `ai-job-validation` and `ai-job-test`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric              | ai-job-validation | ai-job-test |
+|:--------------------|:------------------|:------------|
+| **cosine_accuracy** | **0.9429**        | **0.9291**  |
+
+<!--
+## 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
+
+#### parquet
+
+* Dataset: parquet
+* Size: 7,999 training samples
+* Columns: <code>Entities</code>, <code>PosLongDesc</code>, and <code>NegLongDesc</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | Entities                                                                            | PosLongDesc                                                                       | NegLongDesc                                                                       |
+  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 155.39 tokens</li><li>max: 485 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.62 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 10.35 tokens</li><li>max: 31 tokens</li></ul> |
+* Samples:
+  | Entities                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | PosLongDesc                                                                                             | NegLongDesc                                                                                        |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|
+  | <code>it,chiness,since 3 months,it,chiness,since,3 months,weight,90. 100,height,178. 000,temperature,98. 060,pulse,84. 000,respiration,0. 000 bp,sy,sto,122. 000 bp,dia,69. 000,sp,o,:,99,cap,blood sugar,ja,undice,ec,abd,an,rth,nonsignificant,nonsignificant,nonsignifican,t,no family,nonsignificant family,nonsignificant family,nonsignificant,no relevant family history,yes,married, smoker, carpenter,married, smoker, carpenter social,married, smoker, carpenter social history,nonsignificant,nonsignificant,nonsignificant,it,chiness,3 months,treatment</code> | <code>Rash and other nonspecific skin eruption</code>                                                   | <code>Acute nasopharyngitis [common cold]</code>                                                   |
+  | <code>amc,dubai,united arab emirates,uma,pa,gut,hari,val,electrocard,gram,pt,amc,sitting,coherent,w /,can,nula,bra,chia,vital,85,18,res,normal,sao,100,air time,17,: 51 : 34,bp,120 / 81,cap,<,2,sec,temperature,> 4 reacts,>,4,reacts,total,gcs,15,pain,0,blood glucose,102,car,accident,drug overdose,intentional</code>                                                                                                                                                                                                                                                   | <code>Epileptic seizures related to external causes, not intractable, without status epilepticus</code> | <code>COVID-19</code>                                                                              |
+  | <code>amc gate,dubai,united arab emirates,ssi,test,airports,dubai,concourse,ent assessment,throat,transported,endorsed,pulse :,77r,14,res,normal %,sao,2 :,100,air time,05 :,26,:,00,bp,118 / 69,cap,<,2,sec,temperature,36. 7,pupil,left,>,4,reacts,right,>,4,reacts,gcs,15,pain,2,blood glucose,96,car,accident,no,throatpain</code>                                                                                                                                                                                                                                       | <code>Pain in throat</code>                                                                             | <code>Encounter for observation for suspected exposure to other biological agents ruled out</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### parquet
+
+* Dataset: parquet
+* Size: 999 evaluation samples
+* Columns: <code>Entities</code>, <code>PosLongDesc</code>, and <code>NegLongDesc</code>
+* Approximate statistics based on the first 999 samples:
+  |         | Entities                                                                            | PosLongDesc                                                                       | NegLongDesc                                                                       |
+  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 154.58 tokens</li><li>max: 470 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.61 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.12 tokens</li><li>max: 35 tokens</li></ul> |
+* Samples:
+  | Entities                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | PosLongDesc                                                                   | NegLongDesc                                                 |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------|:------------------------------------------------------------|
+  | <code>it,chy,redness,3 days,both,it,ching,mild,moderate,3 days,weight,50. 200,height,143. 000,temperature,98. 240,pulse,78. 000,respiration,0. 000 bp,systolic,0. 000 bp,dia,sto,lic,0. 000,sp,o,2,:,99,cap,blood sugar,ja,undice,ec,abd,no past medical history,no past medical history,unknown family medical history,negative family,chronic disease,no diabetic mellitus,no hypertention,negative family,chronic disease,no diabetic mellitus,no hypertention,no,7 years and,7 months,7 years,7 months,no,removal,int,removal,int,red,it,chy,it,chy,redness,3 days</code> | <code>Acute atopic conjunctivitis, bilateral</code>                           | <code>Deficiency of other specified B group vitamins</code> |
+  | <code>pi,mples,pustules,plus,minus,cyst,both side,of the face,too,it,ching,skin,4,pi,notice,increase,laser removal,facial,expose,sun,pust,cyst,it,weight,52,.,800,height,159. 000,temperature,98. 100,pulse,93. 000,res,0. 000 bp,sy,sto,99. 000 bp,sto,60. 000,sp,o,98,cap,blood sugar,ja,undice,ec,no,no,ro,course,ro,not,course,no diabetic mellitus,no,les,no diabetic,mellit,us,no,les,basic,nation,nation,13,years,months,15 years,11 months,old,pu,ules,plus,cyst,side</code>                                                                                          | <code>Local infection of the skin and subcutaneous tissue, unspecified</code> | <code>Inflammatory polyarthropathy</code>                   |
+  | <code>respiratory rate,sp,pain,sy,lic,bp,mm,dia,bp,mm,height,weight,00 kg,repeat,prescription</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | <code>Menopausal and female climacteric states</code>                         | <code>COVID-19</code>                                       |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `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`: 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`: False
+- `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
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | Training Loss | Validation Loss | ai-job-validation_cosine_accuracy | ai-job-test_cosine_accuracy |
+|:-----:|:----:|:-------------:|:---------------:|:---------------------------------:|:---------------------------:|
+| -1    | -1   | -             | -               | 0.5495                            | -                           |
+| 0.2   | 100  | 2.8729        | 1.8172          | 0.8789                            | -                           |
+| 0.4   | 200  | 2.085         | 1.4398          | 0.9259                            | -                           |
+| 0.6   | 300  | 1.8233        | 1.3448          | 0.9339                            | -                           |
+| 0.8   | 400  | 1.6871        | 1.2579          | 0.9409                            | -                           |
+| 1.0   | 500  | 1.4881        | 1.2327          | 0.9429                            | -                           |
+| -1    | -1   | -             | -               | 0.9429                            | 0.9291                      |
+
+
+### Framework Versions
+- Python: 3.11.4
+- Sentence Transformers: 3.4.1
+- Transformers: 4.41.2
+- PyTorch: 2.3.1+cpu
+- Accelerate: 1.3.0
+- Datasets: 3.2.0
+- 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "medicalai/ClinicalBERT",
+  "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,
+  "output_past": true,
+  "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": "4.41.2",
+  "vocab_size": 119547
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.1+cpu"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7280c630189118252ab9c92eb1c50ee4c1fd243dc1c41f068e700c33f0664e97
+size 538947416

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 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

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": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}