Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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 +1,685 @@
+---
+language: []
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:1115700
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-small-en-v1.5
+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: Ndege mwenye mdomo mrefu katikati ya ndege.
+  sentences:
+  - Panya anayekimbia juu ya gurudumu.
+  - Mtu anashindana katika mashindano ya mbio.
+  - Ndege anayeruka.
+- source_sentence: Msichana mchanga mwenye nywele nyeusi anakabili kamera na kushikilia
+    mfuko wa karatasi wakati amevaa shati la machungwa na mabawa ya kipepeo yenye
+    rangi nyingi.
+  sentences:
+  - Mwanamke mzee anakataa kupigwa picha.
+  - mtu akila na mvulana mdogo kwenye kijia cha jiji
+  - Msichana mchanga anakabili kamera.
+- source_sentence: Wanawake na watoto wameketi nje katika kivuli wakati kikundi cha
+    watoto wadogo wameketi ndani katika kivuli.
+  sentences:
+  - Mwanamke na watoto na kukaa chini.
+  - Mwanamke huyo anakimbia.
+  - Watu wanasafiri kwa baiskeli.
+- source_sentence: Mtoto mdogo anaruka mikononi mwa mwanamke aliyevalia suti nyeusi
+    ya kuogelea akiwa kwenye dimbwi.
+  sentences:
+  - Mtoto akiruka mikononi mwa mwanamke aliyevalia suti ya kuogelea kwenye dimbwi.
+  - Someone is holding oranges and walking
+  - Mama na binti wakinunua viatu.
+- source_sentence: Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa
+    kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi
+    nyuma.
+  sentences:
+  - tai huruka
+  - mwanamume na mwanamke wenye mikoba
+  - Wanaume wawili wameketi karibu na mwanamke.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on BAAI/bge-small-en-v1.5
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.6831671531193453
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.677143022633225
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.6891948944875336
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6892226446007472
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.6916897298195501
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6916850273924392
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.6418376172951465
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.628581703082033
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.6916897298195501
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6916850273924392
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.6753009254241098
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6731049071307844
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.6906782473185179
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6927883369656496
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.6933649652149252
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.694111832507592
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.600449101550258
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5857671058687308
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.6933649652149252
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.694111832507592
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.6546200020168988
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6523958945855459
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.6837289470688535
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.6796775815725002
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.6861328219241016
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.6815842202083926
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5120576666695955
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.49141347385563683
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.6861328219241016
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.6815842202083926
+      name: Spearman Max
+---
+
+# SentenceTransformer based on BAAI/bge-small-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) on the Mollel/swahili-n_li-triplet-swh-eng 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:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) <!-- at revision 5c38ec7c405ec4b44b94cc5a9bb96e735b38267a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - Mollel/swahili-n_li-triplet-swh-eng
+<!-- - **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': 384, '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("Mollel/MultiLinguSwahili-bge-small-en-v1.5-nli-matryoshka")
+# Run inference
+sentences = [
+    'Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi nyuma.',
+    'mwanamume na mwanamke wenye mikoba',
+    'tai huruka',
+]
+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      | 0.6832     |
+| **spearman_cosine** | **0.6771** |
+| pearson_manhattan   | 0.6892     |
+| spearman_manhattan  | 0.6892     |
+| pearson_euclidean   | 0.6917     |
+| spearman_euclidean  | 0.6917     |
+| pearson_dot         | 0.6418     |
+| spearman_dot        | 0.6286     |
+| pearson_max         | 0.6917     |
+| spearman_max        | 0.6917     |
+
+#### 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      | 0.6753     |
+| **spearman_cosine** | **0.6731** |
+| pearson_manhattan   | 0.6907     |
+| spearman_manhattan  | 0.6928     |
+| pearson_euclidean   | 0.6934     |
+| spearman_euclidean  | 0.6941     |
+| pearson_dot         | 0.6004     |
+| spearman_dot        | 0.5858     |
+| pearson_max         | 0.6934     |
+| spearman_max        | 0.6941     |
+
+#### 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      | 0.6546     |
+| **spearman_cosine** | **0.6524** |
+| pearson_manhattan   | 0.6837     |
+| spearman_manhattan  | 0.6797     |
+| pearson_euclidean   | 0.6861     |
+| spearman_euclidean  | 0.6816     |
+| pearson_dot         | 0.5121     |
+| spearman_dot        | 0.4914     |
+| pearson_max         | 0.6861     |
+| spearman_max        | 0.6816     |
+
+<!--
+## 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
+
+#### Mollel/swahili-n_li-triplet-swh-eng
+
+* Dataset: Mollel/swahili-n_li-triplet-swh-eng
+* Size: 1,115,700 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                           |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 15.18 tokens</li><li>max: 80 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 18.53 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 17.8 tokens</li><li>max: 53 tokens</li></ul> |
+* Samples:
+  | anchor                                                                | positive                                       | negative                                                   |
+  |:----------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>   | <code>A person is outdoors, on a horse.</code> | <code>A person is at a diner, ordering an omelette.</code> |
+  | <code>Mtu aliyepanda farasi anaruka juu ya ndege iliyovunjika.</code> | <code>Mtu yuko nje, juu ya farasi.</code>      | <code>Mtu yuko kwenye mkahawa, akiagiza omelette.</code>   |
+  | <code>Children smiling and waving at camera</code>                    | <code>There are children present</code>        | <code>The kids are frowning</code>                         |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Mollel/swahili-n_li-triplet-swh-eng
+
+* Dataset: Mollel/swahili-n_li-triplet-swh-eng
+* Size: 13,168 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                           |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 26.43 tokens</li><li>max: 94 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.37 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.7 tokens</li><li>max: 54 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                         | positive                                                    | negative                                                           |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:-------------------------------------------------------------------|
+  | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>Two woman are holding packages.</code>                | <code>The men are fighting outside a deli.</code>                  |
+  | <code>Wanawake wawili wanakumbatiana huku wakishikilia vifurushi vya kwenda.</code>                                                                                            | <code>Wanawake wawili wanashikilia vifurushi.</code>        | <code>Wanaume hao wanapigana nje ya duka la vyakula vitamu.</code> |
+  | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code>                   |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `bf16`: 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`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `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`: 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 |
+|:------:|:----:|:-------------:|:----------------------------:|:----------------------------:|:---------------------------:|
+| 0.0115 | 100  | 9.6847        | -                            | -                            | -                           |
+| 0.0229 | 200  | 8.5336        | -                            | -                            | -                           |
+| 0.0344 | 300  | 7.768         | -                            | -                            | -                           |
+| 0.0459 | 400  | 7.2049        | -                            | -                            | -                           |
+| 0.0574 | 500  | 6.9425        | -                            | -                            | -                           |
+| 0.0688 | 600  | 7.029         | -                            | -                            | -                           |
+| 0.0803 | 700  | 6.259         | -                            | -                            | -                           |
+| 0.0918 | 800  | 6.0939        | -                            | -                            | -                           |
+| 0.1032 | 900  | 5.991         | -                            | -                            | -                           |
+| 0.1147 | 1000 | 5.39          | -                            | -                            | -                           |
+| 0.1262 | 1100 | 5.3214        | -                            | -                            | -                           |
+| 0.1377 | 1200 | 5.1469        | -                            | -                            | -                           |
+| 0.1491 | 1300 | 4.901         | -                            | -                            | -                           |
+| 0.1606 | 1400 | 5.2725        | -                            | -                            | -                           |
+| 0.1721 | 1500 | 5.077         | -                            | -                            | -                           |
+| 0.1835 | 1600 | 4.8006        | -                            | -                            | -                           |
+| 0.1950 | 1700 | 4.5318        | -                            | -                            | -                           |
+| 0.2065 | 1800 | 4.48          | -                            | -                            | -                           |
+| 0.2180 | 1900 | 4.5752        | -                            | -                            | -                           |
+| 0.2294 | 2000 | 4.427         | -                            | -                            | -                           |
+| 0.2409 | 2100 | 4.4021        | -                            | -                            | -                           |
+| 0.2524 | 2200 | 4.5903        | -                            | -                            | -                           |
+| 0.2639 | 2300 | 4.4561        | -                            | -                            | -                           |
+| 0.2753 | 2400 | 4.372         | -                            | -                            | -                           |
+| 0.2868 | 2500 | 4.2698        | -                            | -                            | -                           |
+| 0.2983 | 2600 | 4.3954        | -                            | -                            | -                           |
+| 0.3097 | 2700 | 4.2697        | -                            | -                            | -                           |
+| 0.3212 | 2800 | 4.125         | -                            | -                            | -                           |
+| 0.3327 | 2900 | 4.3611        | -                            | -                            | -                           |
+| 0.3442 | 3000 | 4.2527        | -                            | -                            | -                           |
+| 0.3556 | 3100 | 4.1892        | -                            | -                            | -                           |
+| 0.3671 | 3200 | 4.0417        | -                            | -                            | -                           |
+| 0.3786 | 3300 | 3.9434        | -                            | -                            | -                           |
+| 0.3900 | 3400 | 3.9797        | -                            | -                            | -                           |
+| 0.4015 | 3500 | 3.9611        | -                            | -                            | -                           |
+| 0.4130 | 3600 | 4.04          | -                            | -                            | -                           |
+| 0.4245 | 3700 | 3.965         | -                            | -                            | -                           |
+| 0.4359 | 3800 | 3.778         | -                            | -                            | -                           |
+| 0.4474 | 3900 | 4.0624        | -                            | -                            | -                           |
+| 0.4589 | 4000 | 3.8972        | -                            | -                            | -                           |
+| 0.4703 | 4100 | 3.7882        | -                            | -                            | -                           |
+| 0.4818 | 4200 | 3.8048        | -                            | -                            | -                           |
+| 0.4933 | 4300 | 3.9253        | -                            | -                            | -                           |
+| 0.5048 | 4400 | 3.9832        | -                            | -                            | -                           |
+| 0.5162 | 4500 | 3.6644        | -                            | -                            | -                           |
+| 0.5277 | 4600 | 3.7353        | -                            | -                            | -                           |
+| 0.5392 | 4700 | 3.7768        | -                            | -                            | -                           |
+| 0.5506 | 4800 | 3.796         | -                            | -                            | -                           |
+| 0.5621 | 4900 | 3.875         | -                            | -                            | -                           |
+| 0.5736 | 5000 | 3.7856        | -                            | -                            | -                           |
+| 0.5851 | 5100 | 3.8898        | -                            | -                            | -                           |
+| 0.5965 | 5200 | 3.6327        | -                            | -                            | -                           |
+| 0.6080 | 5300 | 3.7727        | -                            | -                            | -                           |
+| 0.6195 | 5400 | 3.8582        | -                            | -                            | -                           |
+| 0.6310 | 5500 | 3.729         | -                            | -                            | -                           |
+| 0.6424 | 5600 | 3.7088        | -                            | -                            | -                           |
+| 0.6539 | 5700 | 3.8414        | -                            | -                            | -                           |
+| 0.6654 | 5800 | 3.7624        | -                            | -                            | -                           |
+| 0.6768 | 5900 | 3.8816        | -                            | -                            | -                           |
+| 0.6883 | 6000 | 3.7483        | -                            | -                            | -                           |
+| 0.6998 | 6100 | 3.7759        | -                            | -                            | -                           |
+| 0.7113 | 6200 | 3.6674        | -                            | -                            | -                           |
+| 0.7227 | 6300 | 3.6441        | -                            | -                            | -                           |
+| 0.7342 | 6400 | 3.7779        | -                            | -                            | -                           |
+| 0.7457 | 6500 | 3.6691        | -                            | -                            | -                           |
+| 0.7571 | 6600 | 3.7636        | -                            | -                            | -                           |
+| 0.7686 | 6700 | 3.7424        | -                            | -                            | -                           |
+| 0.7801 | 6800 | 3.4943        | -                            | -                            | -                           |
+| 0.7916 | 6900 | 3.5399        | -                            | -                            | -                           |
+| 0.8030 | 7000 | 3.3658        | -                            | -                            | -                           |
+| 0.8145 | 7100 | 3.2856        | -                            | -                            | -                           |
+| 0.8260 | 7200 | 3.3702        | -                            | -                            | -                           |
+| 0.8374 | 7300 | 3.3121        | -                            | -                            | -                           |
+| 0.8489 | 7400 | 3.2322        | -                            | -                            | -                           |
+| 0.8604 | 7500 | 3.1577        | -                            | -                            | -                           |
+| 0.8719 | 7600 | 3.1873        | -                            | -                            | -                           |
+| 0.8833 | 7700 | 3.1492        | -                            | -                            | -                           |
+| 0.8948 | 7800 | 3.2035        | -                            | -                            | -                           |
+| 0.9063 | 7900 | 3.1607        | -                            | -                            | -                           |
+| 0.9177 | 8000 | 3.1557        | -                            | -                            | -                           |
+| 0.9292 | 8100 | 3.0915        | -                            | -                            | -                           |
+| 0.9407 | 8200 | 3.1335        | -                            | -                            | -                           |
+| 0.9522 | 8300 | 3.14          | -                            | -                            | -                           |
+| 0.9636 | 8400 | 3.1422        | -                            | -                            | -                           |
+| 0.9751 | 8500 | 3.1923        | -                            | -                            | -                           |
+| 0.9866 | 8600 | 3.1085        | -                            | -                            | -                           |
+| 0.9980 | 8700 | 3.089         | -                            | -                            | -                           |
+| 1.0    | 8717 | -             | 0.6731                       | 0.6771                       | 0.6524                      |
+
+
+### 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 +1,31 @@
+{
+  "_name_or_path": "BAAI/bge-small-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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": "4.40.1",
+  "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 sha256:441f88cb9681ef618d77170e1e56b32a4ba852e80a7fd23ee39c78a257629c60
+size 133462128

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]"
+}