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 +1,552 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+datasets: []
+language:
+- en
+library_name: sentence-transformers
+license: apache-2.0
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_ndcg@100
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:10000
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Enzalutamide ( brand name Xtandi ) is a synthetic non-steroidal
+    antiandrogen ( NSAA ) which was developed by the pharmaceutical company Medivation
+    for the treatment of metastatic , castration-resistant prostate cancer . Medivation
+    has reported up to an 89 % decrease in serum prostate specific antigen ( PSA )
+    levels after a month of taking the drug . Research suggests that enzalutamide
+    may also be effective in the treatment of certain types of breast cancer . In
+    August 2012 , the United States ( U.S. ) Food and Drug Administration ( FDA )
+    approved enzalutamide for the treatment of castration-resistant prostate cancer
+    .
+  sentences:
+  - what type of cancer is enzalutamide
+  - who is simon cho
+  - who is dr william farone
+- source_sentence: Sohel Rana is a Bangladeshi footballer who plays as a midfielder
+    . He currently plays for Sheikh Jamal Dhanmondi Club .
+  sentences:
+  - who is sohel rana
+  - who is olympicos
+  - who is roberto laserna
+- source_sentence: Qarah Qayeh ( قره قيه , also Romanized as Qareh Qīyeh ) is a village
+    in Chaharduli Rural District , Keshavarz District , Shahin Dezh County , West
+    Azerbaijan Province , Iran . At the 2006 census , its population was 465 , in
+    93 families .
+  sentences:
+  - what was the knoxville riot
+  - what language is kbif
+  - where is qarah qayeh
+- source_sentence: Martin Severin Janus From ( 8 April 1828 -- 6 May 1895 ) was a
+    Danish chess master .   Born in Nakskov , From received his first education at
+    the grammar school of Nykøbing Falster . He entered the army as a volunteer during
+    the Prussian-Danish War ( Schleswig-Holstein War of Succession ) , where he served
+    in the brigade of Major-General Olaf Rye and partook in the Battle of Fredericia
+    on July 6 , 1849 .   After the war From settled in Copenhagen . He was employed
+    by the Statistical Bureau , where he met Magnus Oscar Møllerstrøm , then the strongest
+    chess player in Copenhagen . Next , he worked in the central office for prison
+    management , and in 1890 he became an inspector of the penitentiary of Christianshavn
+    . In 1891 he received the order Ridder af Dannebrog ( `` Knight of the Danish
+    cloth '' , i.e. flag of Denmark ) , which is the second highest of Danish orders
+    .   In 1895 Severin From died of cancer . He is interred at Vestre Cemetery ,
+    Copenhagen .
+  sentences:
+  - when did martin from die
+  - what is hymenoxys lemmonii
+  - where is macomb square il
+- source_sentence: The Recession of 1937 -- 1938 was an economic downturn that occurred
+    during the Great Depression in the United States .   By the spring of 1937 , production
+    , profits , and wages had regained their 1929 levels . Unemployment remained high
+    , but it was slightly lower than the 25 % rate seen in 1933 . The American economy
+    took a sharp downturn in mid-1937 , lasting for 13 months through most of 1938
+    . Industrial production declined almost 30 percent and production of durable goods
+    fell even faster .   Unemployment jumped from 14.3 % in 1937 to 19.0 % in 1938
+    . Manufacturing output fell by 37 % from the 1937 peak and was back to 1934 levels
+    .  Producers reduced their expenditures on durable goods , and inventories declined
+    , but personal income was only 15 % lower than it had been at the peak in 1937
+    . In most sectors , hourly earnings continued to rise throughout the recession
+    , which partly compensated for the reduction in the number of hours worked . As
+    unemployment rose , consumers expenditures declined , thereby leading to further
+    cutbacks in production .
+  sentences:
+  - when did the great depression peak in the u.s. economy?
+  - what is tom mount's specialty
+  - where is poulton
+model-index:
+- name: SentenceTransformer based on BAAI/bge-base-en-v1.5
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9175
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9565
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.965
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.977
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9175
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31883333333333325
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19300000000000003
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09770000000000002
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9175
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9565
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.965
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.977
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9481552613003054
+      name: Cosine Ndcg@10
+    - type: cosine_ndcg@100
+      value: 0.9518775022084042
+      name: Cosine Ndcg@100
+    - type: cosine_mrr@10
+      value: 0.938853373015873
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9396524466438041
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-base-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). 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-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### 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("MugheesAwan11/bge-base-climate_fever-dataset-10k-2k-v1")
+# Run inference
+sentences = [
+    'The Recession of 1937 -- 1938 was an economic downturn that occurred during the Great Depression in the United States .   By the spring of 1937 , production , profits , and wages had regained their 1929 levels . Unemployment remained high , but it was slightly lower than the 25 % rate seen in 1933 . The American economy took a sharp downturn in mid-1937 , lasting for 13 months through most of 1938 . Industrial production declined almost 30 percent and production of durable goods fell even faster .   Unemployment jumped from 14.3 % in 1937 to 19.0 % in 1938 . Manufacturing output fell by 37 % from the 1937 peak and was back to 1934 levels .  Producers reduced their expenditures on durable goods , and inventories declined , but personal income was only 15 % lower than it had been at the peak in 1937 . In most sectors , hourly earnings continued to rise throughout the recession , which partly compensated for the reduction in the number of hours worked . As unemployment rose , consumers expenditures declined , thereby leading to further cutbacks in production .',
+    'when did the great depression peak in the u.s. economy?',
+    'where is poulton',
+]
+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
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9175     |
+| cosine_accuracy@3   | 0.9565     |
+| cosine_accuracy@5   | 0.965      |
+| cosine_accuracy@10  | 0.977      |
+| cosine_precision@1  | 0.9175     |
+| cosine_precision@3  | 0.3188     |
+| cosine_precision@5  | 0.193      |
+| cosine_precision@10 | 0.0977     |
+| cosine_recall@1     | 0.9175     |
+| cosine_recall@3     | 0.9565     |
+| cosine_recall@5     | 0.965      |
+| cosine_recall@10    | 0.977      |
+| cosine_ndcg@10      | 0.9482     |
+| cosine_ndcg@100     | 0.9519     |
+| cosine_mrr@10       | 0.9389     |
+| **cosine_map@100**  | **0.9397** |
+
+<!--
+## 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: 10,000 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                            | anchor                                                                          |
+  |:--------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                          |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 116.45 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.6 tokens</li><li>max: 19 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | anchor                                   |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------|
+  | <code>Professor Maurice Cockrill , RA , FBA ( 8 October 1936 -- 1 December 2013 ) was a British painter and poet .   Born in Hartlepool , County Durham , he studied at Wrexham School of Art , north east Wales , then Denbigh Technical College and later the University of Reading from 1960 -- 64 .  In Liverpool , where he lived for nearly twenty years from 1964 , he taught at Liverpool College of Art and Liverpool Polytechnic . He was a central figure in Liverpool 's artistic life , regularly exhibiting at the Walker Art Gallery , before his departure for London in 1982 .  Cockrill 's Liverpool work was in line with that of John Baum , Sam Walsh and Adrian Henri , employing Pop and Photo-Realist styles , but later he moved towards Romantic Expressionism , as it was shown in his retrospective at the Walker Art Gallery , Liverpool in 1995 .  His poetry was published in magazines such as `` Ambit '' and `` Poetry Review '' .   He was formerly the Keeper of the Royal Academy , and as such managed the RA Schools of the Establishment as well as being a member of the Board and Executive Committee .</code> | <code>who was maurice cockrill</code>    |
+  | <code>Nowa Dąbrowa -LSB- ` nowa-dom ` browa -RSB- is a village in the administrative district of Gmina Kwilcz , within Międzychód County , Greater Poland Voivodeship , in west-central Poland . It lies approximately 16 km south-east of Międzychód and 59 km west of the regional capital Poznań .   The village has a population of 40 .</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | <code>where is nowa dbrowa poland</code> |
+  | <code>Hymenoxys lemmonii is a species of flowering plant in the daisy family known by the common names Lemmon 's rubberweed , Lemmon 's bitterweed , and alkali hymenoxys . It is native to the western United States in and around the Great Basin in Utah , Nevada , northern California , and southeastern Oregon .   Hymenoxys lemmonii is a biennial or perennial herb with one or more branching stems growing erect to a maximum height near 50 centimeters ( 20 inches ) . It produces straight , dark green leaves up to 9 centimeters ( 3.6 inches ) long and divided into a number of narrow , pointed lobes . The foliage and stem may be hairless to quite woolly . The daisy-like flower head is generally at least 1.5 centimeters ( 0.6 inches ) wide , with a center of 50 -- 125 thick golden disc florets and a shaggy fringe of 9 -- 12 golden ray florets .   The species is named for John Gill Lemmon , husband of prominent American botanist Sarah Plummer Lemmon .</code>                                                                                                                                                      | <code>what is hymenoxys lemmonii</code>  |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768
+      ],
+      "matryoshka_weights": [
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `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`: cosine
+- `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`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `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`: True
+- `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_fused
+- `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`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step    | Training Loss | dim_768_cosine_map@100 |
+|:-------:|:-------:|:-------------:|:----------------------:|
+| 0.0319  | 10      | 0.1626        | -                      |
+| 0.0639  | 20      | 0.1168        | -                      |
+| 0.0958  | 30      | 0.0543        | -                      |
+| 0.1278  | 40      | 0.1227        | -                      |
+| 0.1597  | 50      | 0.061         | -                      |
+| 0.1917  | 60      | 0.0537        | -                      |
+| 0.2236  | 70      | 0.0693        | -                      |
+| 0.2556  | 80      | 0.1115        | -                      |
+| 0.2875  | 90      | 0.0541        | -                      |
+| 0.3195  | 100     | 0.0774        | -                      |
+| 0.3514  | 110     | 0.0639        | -                      |
+| 0.3834  | 120     | 0.0639        | -                      |
+| 0.4153  | 130     | 0.0567        | -                      |
+| 0.4473  | 140     | 0.0385        | -                      |
+| 0.4792  | 150     | 0.0452        | -                      |
+| 0.5112  | 160     | 0.0641        | -                      |
+| 0.5431  | 170     | 0.042         | -                      |
+| 0.5751  | 180     | 0.0243        | -                      |
+| 0.6070  | 190     | 0.0405        | -                      |
+| 0.6390  | 200     | 0.062         | -                      |
+| 0.6709  | 210     | 0.0366        | -                      |
+| 0.7029  | 220     | 0.0399        | -                      |
+| 0.7348  | 230     | 0.0382        | -                      |
+| 0.7668  | 240     | 0.0387        | -                      |
+| 0.7987  | 250     | 0.0575        | -                      |
+| 0.8307  | 260     | 0.0391        | -                      |
+| 0.8626  | 270     | 0.0776        | -                      |
+| 0.8946  | 280     | 0.0258        | -                      |
+| 0.9265  | 290     | 0.0493        | -                      |
+| 0.9585  | 300     | 0.037         | -                      |
+| 0.9904  | 310     | 0.0499        | -                      |
+| **1.0** | **313** | **-**         | **0.9397**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.31.0
+- Datasets: 2.19.1
+- 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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "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": "4.41.2",
+  "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+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:a54982f7acdc147c0047daca5d30d6df47423896f724ce4aceddb9fb70c3999d
+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]"
+}