Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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 +1,624 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:43371
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+datasets: []
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+widget:
+- source_sentence: ' New Kids on the Block: Step by Step (1990/I)  Step closer to
+    the New Kids on the Block as they share their newest songs, their hottest performances,
+    and their most personal thoughts. Join the guys as they look at where they came
+    from, where they are right now, and where they''re headed - step by step.'
+  sentences:
+  - Rare
+  - Rare
+  - thriller
+- source_sentence: ' "Vampirism Bites" (2010)  Vampire fan girl Belle always dreamed
+    of becoming a vampire, and finally got her wish on a blind date. She quickly discovers
+    the life of a vampire is not what books, movies and TV have told her, and learns
+    that Vampirism is not a 24/7 sexual and romantic fantasy. In fact, Vampirism Bites.'
+  sentences:
+  - thriller
+  - comedy
+  - Rare
+- source_sentence: ' O Candidato Vieira (2005)  A feature documentary about satirical
+    rock star Manuel Joăo Vieira who ran as a candidate for the Presidency of Portugal
+    in 2001. Altough he didn''t collect the number of signatures needed to officially
+    put him on the ballots, Vieira''s surreal campaign appearances on television talk
+    shows, radio and concerts took the country by storm and left everybody laughing.
+    A political, comedic and musical documentary!'
+  sentences:
+  - documentary
+  - short
+  - short
+- source_sentence: ' Ani DiFranco: Live at Babeville (2008)  On September 11 and 12,
+    2007, Ani DiFranco and her band (Allison Miller on drums, Todd Sickafoose on bass
+    and Mike Dillon on vibes and percussion) played two sold-out shows before a hometown
+    audience in Buffalo, New York. What made those nights so special wasn''t just
+    the music-that''s always special at an Ani show-but the fact that she was playing
+    the inaugural shows in her very own venue, "Babeville". Now the highlights of
+    the two shows are available on a single DVD featuring eighteen songs (two of which
+    have not yet appeared on studio albums), plus bonus sound check and interview
+    footage, all shot in high definition video and 5.1 surround sound. The result
+    is a must-have memento of Ani at her finest-onstage, playing her guitar and singing
+    with the passion, intensity, and joy that have made her a legend.'
+  sentences:
+  - drama
+  - Rare
+  - documentary
+- source_sentence: ' "Oliver Twist" (1985)  In a storm, in a workhouse, to a nameless
+    woman, young Oliver Twist is born into parish care where he''s overworked and
+    underfed. As he grows older his adventures take him from the countryside to London,
+    through harsh treatment, kindness, an undertaker, and a thieves'' dens, where
+    he makes friends and enemies. But all the time he is pursued by the mysterious
+    Monks, who hires Fagin to turn Oliver into a thief. Oliver is rescued by chance
+    and kind friends. But it''s a puzzle of legitimacy, inheritance, and identity
+    that Oliver''s friends must attempt to unravel before Monks can destroy Oliver.'
+  sentences:
+  - documentary
+  - drama
+  - drama
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.900683492678328
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.601991593837738
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.4642871879513101
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.520057201385498
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.4201015531660693
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.5188600940699069
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.46368250557502916
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.900683492678328
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 0.6019916534423828
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.4642871879513101
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 0.5200573205947876
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.4201015531660693
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.5188600940699069
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.4636826492476884
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.900304343816287
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 13.547416687011719
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.45818772856562373
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 15.149662017822266
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.40953003559235857
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.5199667988564051
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.45787992811626
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.900683492678328
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 0.8921977281570435
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.4642871879513101
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 0.979737401008606
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.4201015531660693
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.5188600940699069
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.46368245984449313
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.900683492678328
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 13.547416687011719
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.4642871879513101
+      name: Max F1
+    - type: max_f1_threshold
+      value: 15.149662017822266
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.4201015531660693
+      name: Max Precision
+    - type: max_recall
+      value: 0.5199667988564051
+      name: Max Recall
+    - type: max_ap
+      value: 0.4636826492476884
+      name: Max Ap
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.6381767038642442
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.3618232961357558
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 0.6227289495527069
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 0.6381767038642442
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 0.6381767038642442
+      name: Max Accuracy
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the imdb-triplet dataset. It maps sentences & paragraphs to a 384-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/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision 8b3219a92973c328a8e22fadcfa821b5dc75636a -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - imdb-triplet
+<!-- - **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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("celik-muhammed/all-MiniLM-L6-v2-finetuned-imdb")
+# Run inference
+sentences = [
+    ' "Oliver Twist" (1985)  In a storm, in a workhouse, to a nameless woman, young Oliver Twist is born into parish care where he\'s overworked and underfed. As he grows older his adventures take him from the countryside to London, through harsh treatment, kindness, an undertaker, and a thieves\' dens, where he makes friends and enemies. But all the time he is pursued by the mysterious Monks, who hires Fagin to turn Oliver into a thief. Oliver is rescued by chance and kind friends. But it\'s a puzzle of legitimacy, inheritance, and identity that Oliver\'s friends must attempt to unravel before Monks can destroy Oliver.',
+    'drama',
+    'documentary',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.9007     |
+| cosine_accuracy_threshold    | 0.602      |
+| cosine_f1                    | 0.4643     |
+| cosine_f1_threshold          | 0.5201     |
+| cosine_precision             | 0.4201     |
+| cosine_recall                | 0.5189     |
+| cosine_ap                    | 0.4637     |
+| dot_accuracy                 | 0.9007     |
+| dot_accuracy_threshold       | 0.602      |
+| dot_f1                       | 0.4643     |
+| dot_f1_threshold             | 0.5201     |
+| dot_precision                | 0.4201     |
+| dot_recall                   | 0.5189     |
+| dot_ap                       | 0.4637     |
+| manhattan_accuracy           | 0.9003     |
+| manhattan_accuracy_threshold | 13.5474    |
+| manhattan_f1                 | 0.4582     |
+| manhattan_f1_threshold       | 15.1497    |
+| manhattan_precision          | 0.4095     |
+| manhattan_recall             | 0.52       |
+| manhattan_ap                 | 0.4579     |
+| euclidean_accuracy           | 0.9007     |
+| euclidean_accuracy_threshold | 0.8922     |
+| euclidean_f1                 | 0.4643     |
+| euclidean_f1_threshold       | 0.9797     |
+| euclidean_precision          | 0.4201     |
+| euclidean_recall             | 0.5189     |
+| euclidean_ap                 | 0.4637     |
+| max_accuracy                 | 0.9007     |
+| max_accuracy_threshold       | 13.5474    |
+| max_f1                       | 0.4643     |
+| max_f1_threshold             | 15.1497    |
+| max_precision                | 0.4201     |
+| max_recall                   | 0.52       |
+| **max_ap**                   | **0.4637** |
+
+#### Triplet
+
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| cosine_accuracy    | 0.6382     |
+| dot_accuracy       | 0.3618     |
+| manhattan_accuracy | 0.6227     |
+| euclidean_accuracy | 0.6382     |
+| **max_accuracy**   | **0.6382** |
+
+<!--
+## 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
+
+#### imdb-triplet
+
+* Dataset: imdb-triplet
+* Size: 43,371 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                               | positive                                                                       |
+  |:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                         |
+  | details | <ul><li>min: 31 tokens</li><li>mean: 129.65 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.0 tokens</li><li>max: 3 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                                              | positive           |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------|
+  | <code> A Metafísica dos Chocolates (1967)  Beautiful girls (pre-teens, adolescents, and young women) in street scenes and one of them visiting a chocolate factory, where all the workers are young women, too. A poetic text and an extract from a major Portuguese poet, convey to us the sensual feeling of choosing, unwrapping, and munching chocolate.</code> | <code>short</code> |
+  | <code> Thai Jashe! (2016)  Thai Jashe! is an upcoming Gujarati film written and directed by Nirav Barot. It is about the struggles of a middle class man to achieve his goals in the metro-city Ahmedabad. The film stars Manoj Joshi, Malhar Thakar and Monal Gajjar.</code>                                                                                       | <code>drama</code> |
+  | <code> Vuelco (2005)  A teenage boy rides out of town to meet a a girl in the countryside. She is deaf, and he explains the different means he uses to get her attention when she has not seen him. Then they say goodbye, with one poignant hug and a desperate yell punctuating their final farewell.</code>                                                      | <code>short</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`: 256
+- `per_device_eval_batch_size`: 256
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: round_robin
+
+#### 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`: 256
+- `per_device_eval_batch_size`: 256
+- `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`: 5
+- `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`: no_duplicates
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | max_accuracy | max_ap |
+|:------:|:----:|:-------------:|:------------:|:------:|
+| 0      | 0    | -             | 0.6382       | 0.2004 |
+| 0.5882 | 100  | 1.7867        | -            | 0.3542 |
+| 1.1765 | 200  | 1.3073        | -            | 0.4564 |
+| 1.7647 | 300  | 1.266         | -            | 0.3862 |
+| 2.3529 | 400  | 1.1889        | -            | 0.4011 |
+| 2.9412 | 500  | 1.1554        | -            | 0.4398 |
+| 3.5294 | 600  | 1.1558        | -            | 0.4386 |
+| 4.1176 | 700  | 1.1555        | -            | 0.4566 |
+| 4.7059 | 800  | 1.0835        | -            | 0.4637 |
+
+
+### Framework Versions
+- Python: 3.10.13
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2
+- Accelerate: 0.30.1
+- Datasets: 2.19.2
+- 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 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd9ffe053c5acb0d586d8437beae28cfeb0a4d5401dfafb98e67a434d16b04d
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "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 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "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": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}