Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,583 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:498970
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-m3
+widget:
+- source_sentence: how long does engine take to cool down
+  sentences:
+  - "Turn off the engine. If you can pop the hood from the driverâ\x80\x99s seat,\
+    \ do so â\x80\x94 but donâ\x80\x99t risk opening it by hand until the engine has\
+    \ cooled, especially if you see steam wafting off the engine. It typically takes\
+    \ a solid 30 minutes for an engine to cool down enough for it to be safe to handle."
+  - Realism as an art movement was led by Gustave Courbet in France. It spread across
+    Europe and was influential for the rest of the century and beyond, but as it became
+    adopted into the mainstream of painting it becomes less common and useful as a
+    term to define artistic style.
+  - As the engine cools when shut off, the contracting coolant in the radiator sucks
+    back coolant from the recovery tank. Fluid in the recovery tank should never be
+    below the full hot or full cold marks, lest air be sucked in. -- BETTER ANSWER
+    ==. Your cooling fans are not turning on.It is not normal for your overflow tank
+    to boil like that. It is true that your radiator is overflowing into the reserve
+    tank, but that means yourr adiaotor is boiling. Check for blown fuses or relays
+    for your cooling fans.IF theya re fine. run your engine for about 15 minutes and
+    drive.s the engine cools when shut off, the contracting coolant in the radiator
+    sucks back coolant from the recovery tank. Fluid in the recovery tank should never
+    be below the full hot or full cold marks, lest air be sucked in. -- BETTER ANSWER
+    ==. Your cooling fans are not turning on.
+- source_sentence: what is the tax rate for food in missouri
+  sentences:
+  - 'MINIMUM WAGE RATE Missouri: $7.65. All employers must pay the minimum wage, except
+    employers engaged in retail or service businesses whose annual gross income is
+    less than $500,000. There are also certain classes of employees exempt.Missouri''s
+    minimum wage is recalculated yearly based on the Consumer Price Index. St. Louis
+    restaurant owner isn''t waiting for Congress or the Missouri Legislature to raise
+    the minimum wage to boost his own workers'' pay. Pi Pizzeria owner Chris Sommers
+    says he will pay all of his employees $10.10 an hour starting on April 1, instead
+    of the Missouri state''s minimum of $7.50.'
+  - Rating Newest Oldest. 1  MO probably has the most insanely complex sales tax in
+    the country. Not only is there a state level tax (4.225% for most items and 1.225%
+    for grocery foods) but city and county level sales taxes. 2  The sales tax is
+    set by county. Go to Missouri Sales Tax website and look up your county.
+  - 'Arthritis: The health benefits of copper relate to its anti-inflammatory actions
+    that assist in reducing the symptoms of arthritis. The consumer market is also
+    flooded with copper bracelets as well as other accessories for curing this condition.'
+- source_sentence: is woolwich london safe
+  sentences:
+  - SE18 has four train stations Plumstead, Woolwich Arsenal and Woolwich Dockyard.
+    Plumstead and Woolwich Arsenal are situated in Zone 4, Woolwich Dockyard in Zone
+    3.Approximately just under 30 minutes to Charing Cross from all Stations.Trains
+    are operated buy South-eastern. Train timetables are available at southeasternrailway.co.uk.here
+    is no shortage of schools, libraries and colleges in SE18. A short walk from Plumstead
+    station is Greenwich Community College offering a wide range of courses from cookery
+    to languages. Notable schools include the newly re-built Foxfield Primary, Saint
+    Pauls and Plumstead Mannor.
+  - Karine Adria, Gamer. Views. If you mean will Mount Everest ever erupt lava like
+    a volcano then no. It is a mountain part of the Himalayan range which is an orogenic
+    mountain belt formed as a result of a continental collision along the convergent
+    plate boundary between the Indo-Australian Plate and the Eurasian Plate. The process
+    of how volcanoes are formed is totally different.
+  - "In its heyday Woolwich was known better known as the home of Arsenal Football\
+    \ Club, the first McDonalds in the UK and the base for the British Armyâ\x80\x99\
+    s artillery. At present, it is safe to say the town would not be found in any\
+    \ London travel guide."
+- source_sentence: what ocean is around hawaii
+  sentences:
+  - 'Hawaii: Aloha! Whether you are hoping to travel to Hawaii for a tropical green
+    Christmas or you are hoping to make this island paradise your home, we can help
+    you find the information you need! The state of Hawaii, located in the middle
+    of the Pacific Ocean, is farther away from any other landmass than any other island
+    on the earth.'
+  - Deadband is also known as hysteresis and is the amount of a measured variable
+    (pressure, temperature, etc.) between the point where a switch closes and then
+    re-opens. It can be implemented is software if you have an analog input (i.e.,
+    open at 1.02 PSI, close at 0.98 PSI) or designed into a switching mechanism. Often
+    the deadband of a switch is fixed and cannot be adjusted. A typical example is
+    in a wall thermostat in your house.
+  - Under the Sea, On the Stage. Enter a world where the ocean floor is full of fish
+    and Ariel longs to stroll and dance with humans. Read More. Enter a world where
+    the ocean floor is full of fish and Ariel longs to stroll and dance with humans.
+- source_sentence: who is christopher kyle
+  sentences:
+  - '''American Sniper'' Chris Kyle''s wife thanks audiences for ''watching the hard
+    stuff''. Taya Kyle has told of her gratitude to audiences for supporting the film
+    about her dead husband Chris Kyle, a Navy Seal played by Bradley Cooper.'
+  - Chris Kyle American Sniper. Christopher Scott Kyle was born and raised in Texas
+    and was a United States Navy SEAL from 1999 to 2009. He is currently known as
+    the most successful sniper in American military history. According to his book
+    American Sniper, he had 160 confirmed kills (which was from 255 claimed kills).
+  - A passport card is valid for travel to and from Canada, Mexico, the Caribbean
+    and Bermuda at land border crossings and sea ports-of-entry. It is not valid for
+    air travel. It is valid for 10 years for adults and 5 years for minors under 16.
+    A first passport book costs $135 for adults and $105 for minors under the age
+    of 16. It costs $110 to renew. A first passport card costs $55 for adults and
+    $40 for minors under the age of 16. It costs $30 to renew. The cost when applying
+    for both is $165 for adults and $120 for minors.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on BAAI/bge-m3
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3). It maps sentences & paragraphs to a 1024-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-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## 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("BlackBeenie/bge-m3-msmarco-v3-sbert")
+# Run inference
+sentences = [
+    'who is christopher kyle',
+    'Chris Kyle American Sniper. Christopher Scott Kyle was born and raised in Texas and was a United States Navy SEAL from 1999 to 2009. He is currently known as the most successful sniper in American military history. According to his book American Sniper, he had 160 confirmed kills (which was from 255 claimed kills).',
+    "'American Sniper' Chris Kyle's wife thanks audiences for 'watching the hard stuff'. Taya Kyle has told of her gratitude to audiences for supporting the film about her dead husband Chris Kyle, a Navy Seal played by Bradley Cooper.",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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.*
+-->
+
+<!--
+## 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: 498,970 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                       | sentence_1                                                                          | sentence_2                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                              | string                                                                              |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 9.93 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 90.01 tokens</li><li>max: 239 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 86.47 tokens</li><li>max: 229 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                   | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | sentence_2                                                                                                                                                                                                                                                                                                                                                                                                                                              |
+  |:-------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>how much does it cost to paint a interior house</code> | <code>Interior House Painting Cost Factors. Generally, it will take a minimum of two gallons of paint to cover a room. At the highest end, paint will cost anywhere between $30 and $60 per gallon and come in three different finishes: flat, semi-gloss or high-gloss.Flat finishes are the least shiny and are best suited for areas requiring frequent cleaning.rovide a few details about your project and receive competitive quotes from local pros. The average national cost to paint a home interior is $1,671, with most homeowners spending between $966 and $2,426.</code>                                      | <code>Question DetailsAsked on 3/12/2014. Guest_... How much does it cost per square foot to paint the interior of a house? We just bought roughly a 1500 sg ft townhouse and want to get the entire house, including ceilings painted (including a roughly 400 sq ft finished basement not included in square footage).</code>                                                                                                                         |
+  | <code>when is s corp taxes due</code>                        | <code>If you form a corporate entity for your small business, regardless of whether it's taxed as a C or S corporation, a tax return must be filed with the Internal Revenue Service on its due date each year. Corporate tax returns are always due on the 15th day of the third month following the close of the tax year. The actual day that the tax return filing deadline falls on, however, isn't the same for every corporation.</code>                                                                                                                                                                              | <code>But if you haven’t, don’t panic: the majority of forms aren’t due quite yet. Most tax forms have an annual January 31 due date. Your tax forms are considered on time if the form is properly addressed and mailed on or before that date. If the regular due date falls on a Saturday, Sunday, or legal holiday – which is the case in 2015 for both January and February due dates – issuers have until the next business day.</code> |
+  | <code>what are disaccharides</code>                          | <code>Disaccharides are formed when two monosaccharides are joined together and a molecule of water is removed, a process known as dehydration reaction. For example; milk sugar (lactose) is made from glucose and galactose whereas the sugar from sugar cane and sugar beets (sucrose) is made from glucose and fructose.altose, another notable disaccharide, is made up of two glucose molecules. The two monosaccharides are bonded via a dehydration reaction (also called a condensation reaction or dehydration synthesis) that leads to the loss of a molecule of water and formation of a glycosidic bond.</code> | <code>Other disaccharides include (diagrams p. 364): Sucrose, common table sugar, has a glycosidic bond linking the anomeric hydroxyls of glucose and fructose. Because the configuration at the anomeric carbon of glucose is a (O points down from the ring), the linkage is designated a(12).</code>                                                                                                                                                 |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `num_train_epochs`: 5
+- `fp16`: True
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `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`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `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
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step  | Training Loss |
+|:------:|:-----:|:-------------:|
+| 0.0321 | 500   | 0.3086        |
+| 0.0641 | 1000  | 0.2339        |
+| 0.0962 | 1500  | 0.2289        |
+| 0.1283 | 2000  | 0.2262        |
+| 0.1603 | 2500  | 0.2213        |
+| 0.1924 | 3000  | 0.2158        |
+| 0.2245 | 3500  | 0.2101        |
+| 0.2565 | 4000  | 0.2082        |
+| 0.2886 | 4500  | 0.2107        |
+| 0.3207 | 5000  | 0.2015        |
+| 0.3527 | 5500  | 0.2023        |
+| 0.3848 | 6000  | 0.201         |
+| 0.4169 | 6500  | 0.1974        |
+| 0.4489 | 7000  | 0.191         |
+| 0.4810 | 7500  | 0.1956        |
+| 0.5131 | 8000  | 0.2           |
+| 0.5451 | 8500  | 0.191         |
+| 0.5772 | 9000  | 0.1888        |
+| 0.6092 | 9500  | 0.1885        |
+| 0.6413 | 10000 | 0.1936        |
+| 0.6734 | 10500 | 0.1944        |
+| 0.7054 | 11000 | 0.1806        |
+| 0.7375 | 11500 | 0.1834        |
+| 0.7696 | 12000 | 0.1853        |
+| 0.8016 | 12500 | 0.1823        |
+| 0.8337 | 13000 | 0.1827        |
+| 0.8658 | 13500 | 0.1821        |
+| 0.8978 | 14000 | 0.1724        |
+| 0.9299 | 14500 | 0.1745        |
+| 0.9620 | 15000 | 0.1776        |
+| 0.9940 | 15500 | 0.1781        |
+| 1.0    | 15593 | -             |
+| 1.0261 | 16000 | 0.1133        |
+| 1.0582 | 16500 | 0.0964        |
+| 1.0902 | 17000 | 0.0931        |
+| 1.1223 | 17500 | 0.0947        |
+| 1.1544 | 18000 | 0.097         |
+| 1.1864 | 18500 | 0.0977        |
+| 1.2185 | 19000 | 0.096         |
+| 1.2506 | 19500 | 0.1005        |
+| 1.2826 | 20000 | 0.1008        |
+| 1.3147 | 20500 | 0.0998        |
+| 1.3468 | 21000 | 0.0972        |
+| 1.3788 | 21500 | 0.0992        |
+| 1.4109 | 22000 | 0.0994        |
+| 1.4430 | 22500 | 0.1029        |
+| 1.4750 | 23000 | 0.1008        |
+| 1.5071 | 23500 | 0.0985        |
+| 1.5392 | 24000 | 0.1013        |
+| 1.5712 | 24500 | 0.1027        |
+| 1.6033 | 25000 | 0.0988        |
+| 1.6353 | 25500 | 0.0982        |
+| 1.6674 | 26000 | 0.0994        |
+| 1.6995 | 26500 | 0.0998        |
+| 1.7315 | 27000 | 0.0989        |
+| 1.7636 | 27500 | 0.101         |
+| 1.7957 | 28000 | 0.099         |
+| 1.8277 | 28500 | 0.096         |
+| 1.8598 | 29000 | 0.0989        |
+| 1.8919 | 29500 | 0.1011        |
+| 1.9239 | 30000 | 0.0974        |
+| 1.9560 | 30500 | 0.0999        |
+| 1.9881 | 31000 | 0.0976        |
+| 2.0    | 31186 | -             |
+| 2.0201 | 31500 | 0.0681        |
+| 2.0522 | 32000 | 0.0478        |
+| 2.0843 | 32500 | 0.0483        |
+| 2.1163 | 33000 | 0.0485        |
+| 2.1484 | 33500 | 0.0472        |
+| 2.1805 | 34000 | 0.0482        |
+| 2.2125 | 34500 | 0.0491        |
+| 2.2446 | 35000 | 0.0484        |
+| 2.2767 | 35500 | 0.0493        |
+| 2.3087 | 36000 | 0.0484        |
+| 2.3408 | 36500 | 0.0503        |
+| 2.3729 | 37000 | 0.0498        |
+| 2.4049 | 37500 | 0.0507        |
+| 2.4370 | 38000 | 0.0502        |
+| 2.4691 | 38500 | 0.0508        |
+| 2.5011 | 39000 | 0.0483        |
+| 2.5332 | 39500 | 0.0486        |
+| 2.5653 | 40000 | 0.0494        |
+| 2.5973 | 40500 | 0.0511        |
+| 2.6294 | 41000 | 0.0508        |
+| 2.6615 | 41500 | 0.0496        |
+| 2.6935 | 42000 | 0.0487        |
+| 2.7256 | 42500 | 0.0497        |
+| 2.7576 | 43000 | 0.0491        |
+| 2.7897 | 43500 | 0.0486        |
+| 2.8218 | 44000 | 0.0503        |
+| 2.8538 | 44500 | 0.0504        |
+| 2.8859 | 45000 | 0.0499        |
+| 2.9180 | 45500 | 0.048         |
+| 2.9500 | 46000 | 0.047         |
+| 2.9821 | 46500 | 0.0497        |
+| 3.0    | 46779 | -             |
+| 3.0142 | 47000 | 0.0395        |
+| 3.0462 | 47500 | 0.0247        |
+| 3.0783 | 48000 | 0.0256        |
+| 3.1104 | 48500 | 0.0254        |
+| 3.1424 | 49000 | 0.0247        |
+| 3.1745 | 49500 | 0.0251        |
+| 3.2066 | 50000 | 0.0253        |
+| 3.2386 | 50500 | 0.0263        |
+| 3.2707 | 51000 | 0.0261        |
+| 3.3028 | 51500 | 0.0259        |
+| 3.3348 | 52000 | 0.0256        |
+| 3.3669 | 52500 | 0.0254        |
+| 3.3990 | 53000 | 0.026         |
+| 3.4310 | 53500 | 0.0255        |
+| 3.4631 | 54000 | 0.0255        |
+| 3.4952 | 54500 | 0.0257        |
+| 3.5272 | 55000 | 0.0249        |
+| 3.5593 | 55500 | 0.0251        |
+| 3.5914 | 56000 | 0.026         |
+| 3.6234 | 56500 | 0.0246        |
+| 3.6555 | 57000 | 0.0258        |
+| 3.6876 | 57500 | 0.0266        |
+| 3.7196 | 58000 | 0.0242        |
+| 3.7517 | 58500 | 0.0251        |
+| 3.7837 | 59000 | 0.0243        |
+| 3.8158 | 59500 | 0.0249        |
+| 3.8479 | 60000 | 0.0252        |
+| 3.8799 | 60500 | 0.0251        |
+| 3.9120 | 61000 | 0.025         |
+| 3.9441 | 61500 | 0.0249        |
+| 3.9761 | 62000 | 0.0254        |
+| 4.0    | 62372 | -             |
+| 4.0082 | 62500 | 0.0221        |
+| 4.0403 | 63000 | 0.0146        |
+| 4.0723 | 63500 | 0.0146        |
+| 4.1044 | 64000 | 0.0152        |
+| 4.1365 | 64500 | 0.0153        |
+| 4.1685 | 65000 | 0.0144        |
+| 4.2006 | 65500 | 0.0154        |
+| 4.2327 | 66000 | 0.0137        |
+| 4.2647 | 66500 | 0.0145        |
+| 4.2968 | 67000 | 0.0148        |
+| 4.3289 | 67500 | 0.0148        |
+| 4.3609 | 68000 | 0.0142        |
+| 4.3930 | 68500 | 0.0148        |
+| 4.4251 | 69000 | 0.0155        |
+| 4.4571 | 69500 | 0.0148        |
+| 4.4892 | 70000 | 0.0144        |
+| 4.5213 | 70500 | 0.0144        |
+| 4.5533 | 71000 | 0.0148        |
+| 4.5854 | 71500 | 0.015         |
+| 4.6175 | 72000 | 0.0149        |
+| 4.6495 | 72500 | 0.0135        |
+| 4.6816 | 73000 | 0.0142        |
+| 4.7137 | 73500 | 0.0152        |
+| 4.7457 | 74000 | 0.0144        |
+| 4.7778 | 74500 | 0.0143        |
+| 4.8099 | 75000 | 0.0141        |
+| 4.8419 | 75500 | 0.0146        |
+| 4.8740 | 76000 | 0.0142        |
+| 4.9060 | 76500 | 0.0142        |
+| 4.9381 | 77000 | 0.0147        |
+| 4.9702 | 77500 | 0.0145        |
+| 5.0    | 77965 | -             |
+
+</details>
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "BAAI/bge-m3",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8a6dc809bf17b82c4c6766c09fb317f585d2ef87f77ed6b4ee6f5c6067764d
+size 2271064456

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}