Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "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 +1,775 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:685
+- loss:BatchSemiHardTripletLoss
+base_model: BAAI/bge-base-en
+widget:
+- source_sentence: '
+
+    Name : TRAVEL HORIZON CONSULTANCY
+
+    Category: Travel, Consulting & Professional Fees
+
+    Department: Corporate Affairs
+
+    Location: Amsterdam, Netherlands
+
+    Amount: 874.99
+
+    Card: Global Strategy Meetings
+
+    Trip Name: Annual Stakeholders Retreat
+
+    '
+  sentences:
+  - '
+
+    Name : INTERNATIONAL CLOUD CONNECT
+
+    Category: Telecommunications, Cloud Services & Hosting
+
+    Department: IT Services
+
+    Location: New York, NY
+
+    Amount: 1875.45
+
+    Card: IT Infrastructure
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : GLOBAL CONNECTIVITY SERVICES
+
+    Category: Telecommunications, Cloud Services & Hosting
+
+    Department: IT Infrastructure
+
+    Location: London, UK
+
+    Amount: 895.63
+
+    Card: Global IT Operations Fund
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : TECHIE HOMES INNOVATIONS
+
+    Category: Office Supplies, Smart Home Technology
+
+    Department: Facilities Management
+
+    Location: Chicago, IL
+
+    Amount: 498.75
+
+    Card: Office Modernization
+
+    Trip Name: unknown
+
+    '
+- source_sentence: '
+
+    Name : Café Cultura
+
+    Category: Meals & Entertainment, Consulting & Professional Fees
+
+    Department: Client Relations
+
+    Location: Barcelona, Spain
+
+    Amount: 654.75
+
+    Card: Client Catch-Up Meeting
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : Telelink Solutions
+
+    Category: Telecommunications, Cloud Services & Hosting
+
+    Department: IT Services
+
+    Location: Dublin, Ireland
+
+    Amount: 602.77
+
+    Card: Voice and Data Integration Project
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Cafe Artisan Revue
+
+    Category: Meals & Entertainment, Consulting & Professional Fees
+
+    Department: Corporate Events
+
+    Location: Barcelona, Spain
+
+    Amount: 862.45
+
+    Card: Team Building Lunch
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Aether Travel & Logistics
+
+    Category: Travel, Meals & Entertainment
+
+    Department: Business Development
+
+    Location: London, UK
+
+    Amount: 947.68
+
+    Card: Vendor Relationship Management
+
+    Trip Name: Annual Partnership Conference 2023
+
+    '
+- source_sentence: '
+
+    Name : ASEA TOUCH SERVICES
+
+    Category: Shipping & Postage, Consulting & Professional Fees
+
+    Department: International Logistics
+
+    Location: Osaka, Japan
+
+    Amount: 1229.49
+
+    Card: Global Shipping Optimization
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : Apex Courier Services
+
+    Category: Shipping & Postage, Cloud Services & Hosting
+
+    Department: Logistics & IT
+
+    Location: Toronto, Canada
+
+    Amount: 1142.78
+
+    Card: Global Operations Fund
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Wellness Hub Global
+
+    Category: Employee Perks & Benefits, Subscriptions & Memberships
+
+    Department: Human Resources
+
+    Location: New York, NY
+
+    Amount: 612.34
+
+    Card: Employee Wellness Initiative
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Global Skill Development Ltd.
+
+    Category: Training & Development, Subscriptions & Memberships
+
+    Department: Human Resources
+
+    Location: Montreal, Canada
+
+    Amount: 875.45
+
+    Card: Professional Upskilling Initiative
+
+    Trip Name: unknown
+
+    '
+- source_sentence: '
+
+    Name : Expedited Services International
+
+    Category: Shipping & Postage, Consulting & Professional Fees
+
+    Department: Global Logistics
+
+    Location: London, UK
+
+    Amount: 764.92
+
+    Card: Cross-Border Client Solutions
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : Café Cielo
+
+    Category: Meals & Entertainment, Consulting & Professional Fees
+
+    Department: Client Relations
+
+    Location: Barcelona, Spain
+
+    Amount: 873.45
+
+    Card: Client Engagement Initiative
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Pinnacle Operational Strategies
+
+    Category: Consulting & Professional Fees, Training & Development
+
+    Department: Business Analysis
+
+    Location: Toronto, Canada
+
+    Amount: 949.29
+
+    Card: Operational Efficiency Program
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Nestle Wellness Center
+
+    Category: Employee Perks & Benefits, Meals & Entertainment
+
+    Department: Human Resources
+
+    Location: Zurich, Switzerland
+
+    Amount: 589.67
+
+    Card: Company Health Initiative
+
+    Trip Name: unknown
+
+    '
+- source_sentence: '
+
+    Name : Innovative Design Systems GmbH
+
+    Category: Consulting & Professional Fees, Computer Hardware & Software
+
+    Department: Product Development
+
+    Location: Berlin, Germany
+
+    Amount: 1423.77
+
+    Card: Tech Innovation Fund
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : Cultural Cafe & Event Space
+
+    Category: Meals & Entertainment, Consulting & Professional Fees
+
+    Department: Cultural Initiatives
+
+    Location: Paris, France
+
+    Amount: 764.32
+
+    Card: Art Networking Event
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : TechVista Innovations
+
+    Category: Computer Hardware & Software, Subscriptions & Memberships
+
+    Department: IT Support
+
+    Location: Amsterdam, Netherlands
+
+    Amount: 1183.49
+
+    Card: Annual Software Licensing
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Learning Innovators Group
+
+    Category: Consulting & Professional Fees, Training & Development
+
+    Department: Human Resources
+
+    Location: Chicago, IL
+
+    Amount: 359.99
+
+    Card: Skills Enhancement Program
+
+    Trip Name: unknown
+
+    '
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- dot_accuracy
+- manhattan_accuracy
+- euclidean_accuracy
+- max_accuracy
+model-index:
+- name: SentenceTransformer based on BAAI/bge-base-en
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: bge base en train
+      type: bge-base-en-train
+    metrics:
+    - type: cosine_accuracy
+      value: 0.997080291970803
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.00291970802919708
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 0.997080291970803
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 0.997080291970803
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 0.997080291970803
+      name: Max Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: bge base en eval
+      type: bge-base-en-eval
+    metrics:
+    - type: cosine_accuracy
+      value: 1.0
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.0
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 1.0
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 1.0
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 1.0
+      name: Max Accuracy
+---
+
+# SentenceTransformer based on BAAI/bge-base-en
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en). 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:** [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) <!-- at revision b737bf5dcc6ee8bdc530531266b4804a5d77b5d8 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("vijay-delete/finetuned-transaction-classification-bge-base-en")
+# Run inference
+sentences = [
+    '\nName : Innovative Design Systems GmbH\nCategory: Consulting & Professional Fees, Computer Hardware & Software\nDepartment: Product Development\nLocation: Berlin, Germany\nAmount: 1423.77\nCard: Tech Innovation Fund\nTrip Name: unknown\n',
+    '\nName : Learning Innovators Group\nCategory: Consulting & Professional Fees, Training & Development\nDepartment: Human Resources\nLocation: Chicago, IL\nAmount: 359.99\nCard: Skills Enhancement Program\nTrip Name: unknown\n',
+    '\nName : Cultural Cafe & Event Space\nCategory: Meals & Entertainment, Consulting & Professional Fees\nDepartment: Cultural Initiatives\nLocation: Paris, France\nAmount: 764.32\nCard: Art Networking Event\nTrip Name: unknown\n',
+]
+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
+* Dataset: `bge-base-en-train`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| cosine_accuracy    | 0.9971     |
+| dot_accuracy       | 0.0029     |
+| manhattan_accuracy | 0.9971     |
+| euclidean_accuracy | 0.9971     |
+| **max_accuracy**   | **0.9971** |
+
+#### Triplet
+* Dataset: `bge-base-en-eval`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value   |
+|:-------------------|:--------|
+| cosine_accuracy    | 1.0     |
+| dot_accuracy       | 0.0     |
+| manhattan_accuracy | 1.0     |
+| euclidean_accuracy | 1.0     |
+| **max_accuracy**   | **1.0** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 685 training samples
+* Columns: <code>sentence</code> and <code>label</code>
+* Approximate statistics based on the first 685 samples:
+  |         | sentence                                                                           | label                                                                                                                                                                                                                                                                     |
+  |:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | type    | string                                                                             | int                                                                                                                                                                                                                                                                       |
+  | details | <ul><li>min: 36 tokens</li><li>mean: 42.06 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>0: ~6.57%</li><li>1: ~7.88%</li><li>2: ~6.72%</li><li>3: ~7.01%</li><li>4: ~7.74%</li><li>5: ~7.45%</li><li>6: ~6.42%</li><li>7: ~7.01%</li><li>8: ~7.15%</li><li>9: ~7.15%</li><li>10: ~7.74%</li><li>11: ~7.15%</li><li>12: ~8.18%</li><li>13: ~5.84%</li></ul> |
+* Samples:
+  | sentence                                                                                                                                                                                                                                                             | label          |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code><br>Name : Summit Advisory Partners<br>Category: Consulting & Professional Fees, Training & Development<br>Department: Strategic Insights<br>Location: New York, NY<br>Amount: 985.45<br>Card: Leadership Development Program<br>Trip Name: unknown<br></code> | <code>0</code> |
+  | <code><br>Name : CloudWave Enterprises<br>Category: Telecommunications, Cloud Services & Hosting<br>Department: Infrastructure Management<br>Location: London, UK<br>Amount: 1450.95<br>Card: Network Optimization Project<br>Trip Name: unknown<br></code>          | <code>1</code> |
+  | <code><br>Name : AeroTech Communication Solutions<br>Category: Telecommunications, Cloud Services & Hosting<br>Department: IT Operations<br>Location: Singapore<br>Amount: 915.45<br>Card: Networking Infrastructure Upgrade<br>Trip Name: unknown<br></code>        | <code>1</code> |
+* Loss: [<code>BatchSemiHardTripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#batchsemihardtripletloss)
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 171 evaluation samples
+* Columns: <code>sentence</code> and <code>label</code>
+* Approximate statistics based on the first 171 samples:
+  |         | sentence                                                                           | label                                                                                                                                                                                                                                                                     |
+  |:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | type    | string                                                                             | int                                                                                                                                                                                                                                                                       |
+  | details | <ul><li>min: 37 tokens</li><li>mean: 42.08 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>0: ~8.77%</li><li>1: ~7.02%</li><li>2: ~5.26%</li><li>3: ~7.60%</li><li>4: ~7.02%</li><li>5: ~8.77%</li><li>6: ~5.85%</li><li>7: ~4.09%</li><li>8: ~9.36%</li><li>9: ~7.60%</li><li>10: ~7.60%</li><li>11: ~5.26%</li><li>12: ~7.60%</li><li>13: ~8.19%</li></ul> |
+* Samples:
+  | sentence                                                                                                                                                                                                                                                      | label          |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code><br>Name : YOLOSTREAM MEDIA<br>Category: Subscriptions & Memberships, Cloud Services & Hosting<br>Department: Marketing & IT<br>Location: New York, NY<br>Amount: 927.4<br>Card: Digital Strategy Fund<br>Trip Name: unknown<br></code>                 | <code>9</code> |
+  | <code><br>Name : Learning Innovators Group<br>Category: Consulting & Professional Fees, Training & Development<br>Department: Human Resources<br>Location: Chicago, IL<br>Amount: 359.99<br>Card: Skills Enhancement Program<br>Trip Name: unknown<br></code> | <code>6</code> |
+  | <code><br>Name : Globetraining Solutions<br>Category: Subscriptions & Memberships, Training & Development<br>Department: Human Resources<br>Location: Newark, NJ<br>Amount: 523.47<br>Card: Employee Skill Enhancement<br>Trip Name: unknown<br></code>       | <code>6</code> |
+* Loss: [<code>BatchSemiHardTripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#batchsemihardtripletloss)
+
+### 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`: 5
+- `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
+- `torch_empty_cache_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`: 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`: 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
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | bge-base-en-eval_max_accuracy | bge-base-en-train_max_accuracy |
+|:------:|:----:|:-------------:|:------:|:-----------------------------:|:------------------------------:|
+| 0      | 0    | -             | -      | -                             | 0.9650                         |
+| 2.3256 | 100  | 4.6242        | 4.0409 | -                             | 0.9956                         |
+| 4.6512 | 200  | 4.2332        | 3.9329 | -                             | 0.9971                         |
+| 5.0    | 215  | -             | -      | 1.0                           | -                              |
+
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 3.1.1
+- Transformers: 4.45.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.8.1
+- Datasets: 2.14.4
+- Tokenizers: 0.20.3
+
+## 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",
+}
+```
+
+#### BatchSemiHardTripletLoss
+```bibtex
+@misc{hermans2017defense,
+    title={In Defense of the Triplet Loss for Person Re-Identification},
+    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
+    year={2017},
+    eprint={1703.07737},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+<!--
+## 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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.45.2",
+    "pytorch": "2.6.0+cu124"
+  },
+  "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:c65d2d63b52cd48636902722b74bd950dd5ee71aa73145cd8fed463aece759cd
+size 437951328

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": 512,
+  "do_lower_case": true
+}

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 +1,57 @@
+{
+  "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]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}