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 +1,569 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:557850
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+datasets: []
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Mwanamume aliyepangwa vizuri anasimama kwa mguu mmoja karibu na
+    pwani safi ya bahari.
+  sentences:
+  - mtu anacheka wakati wa kufua nguo
+  - Mwanamume fulani yuko nje karibu na ufuo wa bahari.
+  - Mwanamume fulani ameketi kwenye sofa yake.
+- source_sentence: Mwanamume mwenye ngozi nyeusi akivuta sigareti karibu na chombo
+    cha taka cha kijani.
+  sentences:
+  - Karibu na chombo cha taka mwanamume huyo alisimama na kuvuta sigareti
+  - Kitanda ni chafu.
+  - Alipokuwa kwenye dimbwi la kuogelea mvulana huyo mwenye ugonjwa wa albino alijihadhari
+    na jua kupita kiasi
+- source_sentence: Mwanamume kijana mwenye nywele nyekundu anaketi ukutani akisoma
+    gazeti huku mwanamke na msichana mchanga wakipita.
+  sentences:
+  - Mwanamume aliyevalia shati la bluu amegonga ukuta kando ya barabara na gari la
+    bluu na gari nyekundu lenye maji nyuma.
+  - Mwanamume mchanga anatazama gazeti huku wanawake wawili wakipita karibu naye.
+  - Mwanamume huyo mchanga analala huku Mama akimwongoza binti yake kwenye bustani.
+- source_sentence: Wasichana wako nje.
+  sentences:
+  - Wasichana wawili wakisafiri kwenye sehemu ya kusisimua.
+  - Kuna watu watatu wakiongoza gari linaloweza kugeuzwa-geuzwa wakipita watu wengine.
+  - Wasichana watatu wamesimama pamoja katika chumba, mmoja anasikiliza, mwingine
+    anaandika ukutani na wa tatu anaongea nao.
+- source_sentence: Mwanamume aliyevalia koti la bluu la kuzuia upepo, amelala uso
+    chini kwenye benchi ya bustani, akiwa na chupa ya pombe iliyofungwa kwenye mojawapo
+    ya miguu ya benchi.
+  sentences:
+  - Mwanamume amelala uso chini kwenye benchi ya bustani.
+  - Mwanamke anaunganisha uzi katika mipira kando ya rundo la mipira
+  - Mwanamume fulani anacheza dansi kwenye klabu hiyo akifungua chupa.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.6942864389866223
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6856061049537777
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.6885375818451587
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6872214410233022
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.6914785578290242
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6905722127311041
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6799233396985102
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.667743621858275
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.6942864389866223
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6905722127311041
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.6891584502617563
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6814103986417178
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.6968187377070036
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6920002958564649
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7000628001426884
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6960243670969477
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6364862920838279
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6189765115954626
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7000628001426884
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6960243670969477
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.6782226699898293
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6755345411699644
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.6962074727926596
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.689094339218281
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.6996133052307816
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6937517032138506
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.58122590177631
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5606971476688047
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.6996133052307816
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6937517032138506
+      name: Spearman Max
+---
+
+# 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). 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:** 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': 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("sartifyllc/swahili-all-MiniLM-L6-v2-nli-matryoshka")
+# Run inference
+sentences = [
+    'Mwanamume aliyevalia koti la bluu la kuzuia upepo, amelala uso chini kwenye benchi ya bustani, akiwa na chupa ya pombe iliyofungwa kwenye mojawapo ya miguu ya benchi.',
+    'Mwanamume amelala uso chini kwenye benchi ya bustani.',
+    'Mwanamume fulani anacheza dansi kwenye klabu hiyo akifungua chupa.',
+]
+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
+
+#### Semantic Similarity
+* Dataset: `sts-test-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6943     |
+| **spearman_cosine** | **0.6856** |
+| pearson_manhattan   | 0.6885     |
+| spearman_manhattan  | 0.6872     |
+| pearson_euclidean   | 0.6915     |
+| spearman_euclidean  | 0.6906     |
+| pearson_dot         | 0.6799     |
+| spearman_dot        | 0.6677     |
+| pearson_max         | 0.6943     |
+| spearman_max        | 0.6906     |
+
+#### Semantic Similarity
+* Dataset: `sts-test-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6892     |
+| **spearman_cosine** | **0.6814** |
+| pearson_manhattan   | 0.6968     |
+| spearman_manhattan  | 0.692      |
+| pearson_euclidean   | 0.7001     |
+| spearman_euclidean  | 0.696      |
+| pearson_dot         | 0.6365     |
+| spearman_dot        | 0.619      |
+| pearson_max         | 0.7001     |
+| spearman_max        | 0.696      |
+
+#### Semantic Similarity
+* Dataset: `sts-test-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6782     |
+| **spearman_cosine** | **0.6755** |
+| pearson_manhattan   | 0.6962     |
+| spearman_manhattan  | 0.6891     |
+| pearson_euclidean   | 0.6996     |
+| spearman_euclidean  | 0.6938     |
+| pearson_dot         | 0.5812     |
+| spearman_dot        | 0.5607     |
+| pearson_max         | 0.6996     |
+| spearman_max        | 0.6938     |
+
+<!--
+## 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 Hyperparameters
+#### Non-Default Hyperparameters
+
+- `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
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 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
+- `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, '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_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | sts-test-128_spearman_cosine | sts-test-256_spearman_cosine | sts-test-64_spearman_cosine |
+|:------:|:----:|:-------------:|:----------------------------:|:----------------------------:|:---------------------------:|
+| 0.0229 | 100  | 12.9498       | -                            | -                            | -                           |
+| 0.0459 | 200  | 9.9003        | -                            | -                            | -                           |
+| 0.0688 | 300  | 8.6333        | -                            | -                            | -                           |
+| 0.0918 | 400  | 8.0124        | -                            | -                            | -                           |
+| 0.1147 | 500  | 7.2322        | -                            | -                            | -                           |
+| 0.1376 | 600  | 6.936         | -                            | -                            | -                           |
+| 0.1606 | 700  | 7.2855        | -                            | -                            | -                           |
+| 0.1835 | 800  | 6.5985        | -                            | -                            | -                           |
+| 0.2065 | 900  | 6.4369        | -                            | -                            | -                           |
+| 0.2294 | 1000 | 6.2767        | -                            | -                            | -                           |
+| 0.2524 | 1100 | 6.4011        | -                            | -                            | -                           |
+| 0.2753 | 1200 | 6.1288        | -                            | -                            | -                           |
+| 0.2982 | 1300 | 6.1466        | -                            | -                            | -                           |
+| 0.3212 | 1400 | 5.9279        | -                            | -                            | -                           |
+| 0.3441 | 1500 | 5.8959        | -                            | -                            | -                           |
+| 0.3671 | 1600 | 5.5911        | -                            | -                            | -                           |
+| 0.3900 | 1700 | 5.5258        | -                            | -                            | -                           |
+| 0.4129 | 1800 | 5.5835        | -                            | -                            | -                           |
+| 0.4359 | 1900 | 5.4701        | -                            | -                            | -                           |
+| 0.4588 | 2000 | 5.3888        | -                            | -                            | -                           |
+| 0.4818 | 2100 | 5.4474        | -                            | -                            | -                           |
+| 0.5047 | 2200 | 5.1465        | -                            | -                            | -                           |
+| 0.5276 | 2300 | 5.28          | -                            | -                            | -                           |
+| 0.5506 | 2400 | 5.4184        | -                            | -                            | -                           |
+| 0.5735 | 2500 | 5.3811        | -                            | -                            | -                           |
+| 0.5965 | 2600 | 5.2171        | -                            | -                            | -                           |
+| 0.6194 | 2700 | 5.3212        | -                            | -                            | -                           |
+| 0.6423 | 2800 | 5.2493        | -                            | -                            | -                           |
+| 0.6653 | 2900 | 5.459         | -                            | -                            | -                           |
+| 0.6882 | 3000 | 5.068         | -                            | -                            | -                           |
+| 0.7112 | 3100 | 5.1415        | -                            | -                            | -                           |
+| 0.7341 | 3200 | 5.0764        | -                            | -                            | -                           |
+| 0.7571 | 3300 | 6.1606        | -                            | -                            | -                           |
+| 0.7800 | 3400 | 6.1028        | -                            | -                            | -                           |
+| 0.8029 | 3500 | 5.7441        | -                            | -                            | -                           |
+| 0.8259 | 3600 | 5.7148        | -                            | -                            | -                           |
+| 0.8488 | 3700 | 5.4799        | -                            | -                            | -                           |
+| 0.8718 | 3800 | 5.4396        | -                            | -                            | -                           |
+| 0.8947 | 3900 | 5.3519        | -                            | -                            | -                           |
+| 0.9176 | 4000 | 5.2394        | -                            | -                            | -                           |
+| 0.9406 | 4100 | 5.2311        | -                            | -                            | -                           |
+| 0.9635 | 4200 | 5.3486        | -                            | -                            | -                           |
+| 0.9865 | 4300 | 5.215         | -                            | -                            | -                           |
+| 1.0    | 4359 | -             | 0.6814                       | 0.6856                       | 0.6755                      |
+
+
+### Framework Versions
+- Python: 3.11.9
+- Sentence Transformers: 3.0.1
+- Transformers: 4.40.1
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.29.3
+- 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### 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": "4.40.1",
+  "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": "4.40.1",
+    "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 sha256:64199796093dcf298a92deced68231b013454440c2ea684c9c12e453e91b5b7f
+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]"
+}