Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

2_Asym/2357069263376_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 384, "out_features": 384, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/2357069263376_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c405f05da7023f3d1f4553adce02a95ed691582e2b75c738119f77f9839d3e
+size 591520

2_Asym/2357085690448_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 384, "out_features": 384, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/2357085690448_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed52545c73bc6c5808b81aea5e0210727d68d5cdfa780184e20da139a45be40c
+size 591520

2_Asym/config.json

@@ -0,0 +1,17 @@
+{
+  "types": {
+    "2357085690448_Dense": "sentence_transformers.models.Dense",
+    "2357069263376_Dense": "sentence_transformers.models.Dense"
+  },
+  "structure": {
+    "query": [
+      "2357085690448_Dense"
+    ],
+    "doc": [
+      "2357069263376_Dense"
+    ]
+  },
+  "parameters": {
+    "allow_empty_key": true
+  }
+}

README.md

@@ -0,0 +1,571 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:3012496
+- loss:MultipleNegativesRankingLoss
+base_model: nreimers/MiniLM-L6-H384-uncased
+datasets:
+- sentence-transformers/gooaq
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+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_mrr@10
+- cosine_map@100
+co2_eq_emissions:
+  emissions: 22.281960304608415
+  energy_consumed: 0.05732401763975595
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 0.212
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: MPNet base trained on AllNLI triplets
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: gooaq dev
+      type: gooaq-dev
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1588
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2785
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3457
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.4466
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1588
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09283333333333332
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06914
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04466
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1588
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2785
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3457
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.4466
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2881970902221442
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.23927892857142846
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2521367709898081
+      name: Cosine Map@100
+---
+
+# MPNet base trained on AllNLI triplets
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nreimers/MiniLM-L6-H384-uncased](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) on the [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) 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:** [nreimers/MiniLM-L6-H384-uncased](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) <!-- at revision 3276f0fac9d818781d7a1327b3ff818fc4e643c0 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq)
+- **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': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (asym): Asym(
+    (query-0): Dense({'in_features': 384, 'out_features': 384, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (doc-0): Dense({'in_features': 384, 'out_features': 384, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+  )
+)
+```
+
+## 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("tomaarsen/MiniLM-L6-H384-uncased-gooaq-asym")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+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
+
+#### Information Retrieval
+
+* Dataset: `gooaq-dev`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1588     |
+| cosine_accuracy@3   | 0.2785     |
+| cosine_accuracy@5   | 0.3457     |
+| cosine_accuracy@10  | 0.4466     |
+| cosine_precision@1  | 0.1588     |
+| cosine_precision@3  | 0.0928     |
+| cosine_precision@5  | 0.0691     |
+| cosine_precision@10 | 0.0447     |
+| cosine_recall@1     | 0.1588     |
+| cosine_recall@3     | 0.2785     |
+| cosine_recall@5     | 0.3457     |
+| cosine_recall@10    | 0.4466     |
+| **cosine_ndcg@10**  | **0.2882** |
+| cosine_mrr@10       | 0.2393     |
+| cosine_map@100      | 0.2521     |
+
+<!--
+## 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
+
+#### gooaq
+
+* Dataset: [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) at [b089f72](https://huggingface.co/datasets/sentence-transformers/gooaq/tree/b089f728748a068b7bc5234e5bcf5b25e3c8279c)
+* Size: 3,012,496 training samples
+* Columns: <code>question</code> and <code>answer</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | question           | answer             |
+  |:--------|:-------------------|:-------------------|
+  | type    | dict               | dict               |
+  | details | <ul><li></li></ul> | <ul><li></li></ul> |
+* Samples:
+  | question                                                                                        | answer                                                                                                                                                                                                                                                                                                                           |
+  |:------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>{'query': 'what is the difference between broilers and layers?'}</code>                   | <code>{'doc': 'An egg laying poultry is called egger or layer whereas broilers are reared for obtaining meat. So a layer should be able to produce more number of large sized eggs, without growing too much. On the other hand, a broiler should yield more meat and hence should be able to grow well.'}</code>                |
+  | <code>{'query': 'what is the difference between chronological order and spatial order?'}</code> | <code>{'doc': 'As a writer, you should always remember that unlike chronological order and the other organizational methods for data, spatial order does not take into account the time. Spatial order is primarily focused on the location. All it does is take into account the location of objects and not the time.'}</code> |
+  | <code>{'query': 'is kamagra same as viagra?'}</code>                                            | <code>{'doc': 'Kamagra is thought to contain the same active ingredient as Viagra, sildenafil citrate. In theory, it should work in much the same way as Viagra, taking about 45 minutes to take effect, and lasting for around 4-6 hours. However, this will vary from person to person.'}</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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### gooaq
+
+* Dataset: [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) at [b089f72](https://huggingface.co/datasets/sentence-transformers/gooaq/tree/b089f728748a068b7bc5234e5bcf5b25e3c8279c)
+* Size: 3,012,496 evaluation samples
+* Columns: <code>question</code> and <code>answer</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | question           | answer             |
+  |:--------|:-------------------|:-------------------|
+  | type    | dict               | dict               |
+  | details | <ul><li></li></ul> | <ul><li></li></ul> |
+* Samples:
+  | question                                                                                  | answer                                                                                                                                                                                                                                                                                                                                                |
+  |:------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>{'query': 'how do i program my directv remote with my tv?'}</code>                  | <code>{'doc': "['Press MENU on your remote.', 'Select Settings & Help > Settings > Remote Control > Program Remote.', 'Choose the device (TV, audio, DVD) you wish to program. ... ', 'Follow the on-screen prompts to complete programming.']"}</code>                                                                                               |
+  | <code>{'query': 'are rodrigues fruit bats nocturnal?'}</code>                             | <code>{'doc': 'Before its numbers were threatened by habitat destruction, storms, and hunting, some of those groups could number 500 or more members. Sunrise, sunset. Rodrigues fruit bats are most active at dawn, at dusk, and at night.'}</code>                                                                                                  |
+  | <code>{'query': 'why does your heart rate increase during exercise bbc bitesize?'}</code> | <code>{'doc': 'During exercise there is an increase in physical activity and muscle cells respire more than they do when the body is at rest. The heart rate increases during exercise. The rate and depth of breathing increases - this makes sure that more oxygen is absorbed into the blood, and more carbon dioxide is removed from it.'}</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`: 128
+- `per_device_eval_batch_size`: 128
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `seed`: 24
+- `bf16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 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
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 24
+- `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, '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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | gooaq-dev_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:------------------------:|
+| -1     | -1   | -             | -               | 0.0000                   |
+| 0.0003 | 1    | 4.9236        | -               | -                        |
+| 0.0128 | 50   | 4.8759        | -               | -                        |
+| 0.0256 | 100  | 4.7225        | -               | -                        |
+| 0.0384 | 150  | 4.0357        | -               | -                        |
+| 0.0512 | 200  | 3.0877        | -               | -                        |
+| 0.0640 | 250  | 2.5094        | -               | -                        |
+| 0.0768 | 300  | 2.0771        | -               | -                        |
+| 0.0896 | 350  | 1.734         | -               | -                        |
+| 0.1024 | 400  | 1.4959        | -               | -                        |
+| 0.1152 | 450  | 1.308         | -               | -                        |
+| 0.1280 | 500  | 1.1529        | 0.8984          | 0.0796                   |
+| 0.1408 | 550  | 1.0101        | -               | -                        |
+| 0.1536 | 600  | 0.9601        | -               | -                        |
+| 0.1664 | 650  | 0.8845        | -               | -                        |
+| 0.1792 | 700  | 0.8348        | -               | -                        |
+| 0.1920 | 750  | 0.7838        | -               | -                        |
+| 0.2048 | 800  | 0.7457        | -               | -                        |
+| 0.2176 | 850  | 0.6879        | -               | -                        |
+| 0.2304 | 900  | 0.6778        | -               | -                        |
+| 0.2432 | 950  | 0.6783        | -               | -                        |
+| 0.2560 | 1000 | 0.6351        | 0.4814          | 0.2080                   |
+| 0.2687 | 1050 | 0.6221        | -               | -                        |
+| 0.2815 | 1100 | 0.6015        | -               | -                        |
+| 0.2943 | 1150 | 0.5738        | -               | -                        |
+| 0.3071 | 1200 | 0.5745        | -               | -                        |
+| 0.3199 | 1250 | 0.574         | -               | -                        |
+| 0.3327 | 1300 | 0.5464        | -               | -                        |
+| 0.3455 | 1350 | 0.5257        | -               | -                        |
+| 0.3583 | 1400 | 0.5074        | -               | -                        |
+| 0.3711 | 1450 | 0.4905        | -               | -                        |
+| 0.3839 | 1500 | 0.4633        | 0.3643          | 0.2435                   |
+| 0.3967 | 1550 | 0.4853        | -               | -                        |
+| 0.4095 | 1600 | 0.4587        | -               | -                        |
+| 0.4223 | 1650 | 0.4561        | -               | -                        |
+| 0.4351 | 1700 | 0.4442        | -               | -                        |
+| 0.4479 | 1750 | 0.4399        | -               | -                        |
+| 0.4607 | 1800 | 0.4448        | -               | -                        |
+| 0.4735 | 1850 | 0.4159        | -               | -                        |
+| 0.4863 | 1900 | 0.424         | -               | -                        |
+| 0.4991 | 1950 | 0.419         | -               | -                        |
+| 0.5119 | 2000 | 0.4049        | 0.3047          | 0.2713                   |
+| 0.5247 | 2050 | 0.3897        | -               | -                        |
+| 0.5375 | 2100 | 0.3873        | -               | -                        |
+| 0.5503 | 2150 | 0.3892        | -               | -                        |
+| 0.5631 | 2200 | 0.3777        | -               | -                        |
+| 0.5759 | 2250 | 0.382         | -               | -                        |
+| 0.5887 | 2300 | 0.3703        | -               | -                        |
+| 0.6015 | 2350 | 0.3703        | -               | -                        |
+| 0.6143 | 2400 | 0.3809        | -               | -                        |
+| 0.6271 | 2450 | 0.3576        | -               | -                        |
+| 0.6399 | 2500 | 0.3486        | 0.2686          | 0.2837                   |
+| 0.6527 | 2550 | 0.3395        | -               | -                        |
+| 0.6655 | 2600 | 0.3687        | -               | -                        |
+| 0.6783 | 2650 | 0.365         | -               | -                        |
+| 0.6911 | 2700 | 0.3553        | -               | -                        |
+| 0.7039 | 2750 | 0.3446        | -               | -                        |
+| 0.7167 | 2800 | 0.3396        | -               | -                        |
+| 0.7295 | 2850 | 0.3505        | -               | -                        |
+| 0.7423 | 2900 | 0.359         | -               | -                        |
+| 0.7551 | 2950 | 0.3239        | -               | -                        |
+| 0.7679 | 3000 | 0.3408        | 0.2474          | 0.2440                   |
+| 0.7807 | 3050 | 0.3217        | -               | -                        |
+| 0.7934 | 3100 | 0.3367        | -               | -                        |
+| 0.8062 | 3150 | 0.3479        | -               | -                        |
+| 0.8190 | 3200 | 0.3278        | -               | -                        |
+| 0.8318 | 3250 | 0.3203        | -               | -                        |
+| 0.8446 | 3300 | 0.2966        | -               | -                        |
+| 0.8574 | 3350 | 0.3298        | -               | -                        |
+| 0.8702 | 3400 | 0.3291        | -               | -                        |
+| 0.8830 | 3450 | 0.3199        | -               | -                        |
+| 0.8958 | 3500 | 0.3302        | 0.2363          | 0.2783                   |
+| 0.9086 | 3550 | 0.3124        | -               | -                        |
+| 0.9214 | 3600 | 0.3136        | -               | -                        |
+| 0.9342 | 3650 | 0.3327        | -               | -                        |
+| 0.9470 | 3700 | 0.3214        | -               | -                        |
+| 0.9598 | 3750 | 0.3214        | -               | -                        |
+| 0.9726 | 3800 | 0.3123        | -               | -                        |
+| 0.9854 | 3850 | 0.3185        | -               | -                        |
+| 0.9982 | 3900 | 0.2999        | -               | -                        |
+| -1     | -1   | -             | -               | 0.2882                   |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.057 kWh
+- **Carbon Emitted**: 0.022 kg of CO2
+- **Hours Used**: 0.212 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 3.5.0.dev0
+- Transformers: 4.49.0.dev0
+- PyTorch: 2.5.0+cu121
+- Accelerate: 1.3.0
+- Datasets: 2.20.0
+- 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 +1,26 @@
+{
+  "_name_or_path": "nreimers/MiniLM-L6-H384-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.5.0.dev0",
+    "transformers": "4.49.0.dev0",
+    "pytorch": "2.5.0+cu121"
+  },
+  "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:c009e6e393571ca9bb3d9bdf1b91ecd257dcc507c5105afd8c9d046311c0a7d6
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "asym",
+    "path": "2_Asym",
+    "type": "sentence_transformers.models.Asym"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}