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": 1536,
+  "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_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1536, "out_features": 1024, "bias": true, "activation_function": "torch.nn.modules.linear.Identity"}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e2801747ecd978b3d38188615b8b06ef2e7695a41a76a7bece810e53e49b71
+size 6295712

README.md

@@ -0,0 +1,618 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:180740
+- loss:MultipleNegativesRankingLoss
+base_model: NovaSearch/stella_en_1.5B_v5
+widget:
+- source_sentence: $230 pool for outdoors not plastic
+  sentences:
+  - Wireless Outdoor Security Camera, WiFi Solar Rechargeable Battery Power IP Surveillance
+    Home Cameras, 1080P, Human Motion Detection, Night Vision, 2-Way Audio, 4dbi Antenna,
+    IP65 Waterproof, Cloud/SD
+  - Bestway SaluSpa Miami Inflatable Hot Tub, 4-Person AirJet Spa
+  - Mens Plush Robe - Fleece Robe, Mens Bathrobe - Fig -Small/Medium
+- source_sentence: (hearing aid not amplifer)
+  sentences:
+  - Hearing Aid Cleaning Wire for Sound Tubes (2 Packs of 5)
+  - Hearing Aids, Enjoyee Hearing Aids for Seniors Rechargeable Hearing Amplifier
+    with Noise Cancelling for Adults Hearing Loss, Digital Ear Hearing Assist Devices
+    with Volume Control
+  - '24 Pieces Checking Erasable Pencils Red Pencils Pre-Sharpened #2 HB with Erasable
+    Tops for Checking Map Coloring Tests Grading'
+- source_sentence: (can not use in the usa) european 220voltage hair tools
+  sentences:
+  - Umarex 2252109 Brodax Air Pistol .177 BB
+  - One-Step Hair Dryer & Volumizer Hot Air Brush, 3-in-1 Hair Dryer Brush Styler
+    for Straightening, Curling, Salon Negative Ion Ceramic Lightweight Blow Dryers
+    Straightener Curl Hair Brush
+  - Mini Portable Flat Iron Tourmaline Ceramic Dual Voltage Travel Iron for Worldwide
+    Use LED Indicator LOVANI Hair Straightener (Ceramic Mini)
+- source_sentence: '''not my circus not my monkeys my monkeys flyshirt'''
+  sentences:
+  - Dresswel Women This is My Circus These are My Monkeys T-Shirt Mom Life Graphic
+    Tee Pocket Shirt Casual Tops
+  - 'Goyunwell Nylon Black Zippers by The Yard #5 10 Yards Nylon Black Long Zipper
+    Tape for Sewing 20Pcs Gunmetal Pulls Slider Zipper by The Yard Black Zipper Roll
+    for Craft Bag Purse Sewing Black Tape'
+  - Not My Circus Not My Monkeys Party T-Shirt
+- source_sentence: '#1 small corded treadmill without remote control'
+  sentences:
+  - Goplus Under Desk Treadmill, with Touchable LED Display and Wireless Remote Control,
+    Built-in 3 Workout Modes and 12 Programs, Walking Jogging Machine, Superfit Electric
+    Treadmill for Home Office
+  - Pencil Guy Untipped white round pencil, no eraser 144 to a box
+  - SUNNY HEALTH & FITNESS ASUNA Space Saving Treadmill, Motorized with Speakers for
+    AUX Audio Connection - 8730G
+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@5
+- cosine_ndcg@10
+- cosine_mrr@1
+- cosine_mrr@5
+- cosine_mrr@10
+- cosine_map@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on NovaSearch/stella_en_1.5B_v5
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: ir evaluation
+      type: ir_evaluation
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5243984708792444
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7189116258151563
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.782325163031257
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8452889588486621
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5243984708792444
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.44764260550183643
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.4002248706993479
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.3198335956824826
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.09367303103726933
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.21358059074273028
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.2980042886250134
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.43181596262310956
+      name: Cosine Recall@10
+    - type: cosine_ndcg@5
+      value: 0.46762394517912087
+      name: Cosine Ndcg@5
+    - type: cosine_ndcg@10
+      value: 0.46811760590873697
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.5243984708792444
+      name: Cosine Mrr@1
+    - type: cosine_mrr@5
+      value: 0.625680233865528
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 0.6341315350816145
+      name: Cosine Mrr@10
+    - type: cosine_map@10
+      value: 0.34926714503106293
+      name: Cosine Map@10
+    - type: cosine_map@100
+      value: 0.4065326888005573
+      name: Cosine Map@100
+  - task:
+      type: graded-ir
+      name: Graded IR
+    dataset:
+      name: gr evaluation
+      type: gr_evaluation
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.708792444344502
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9037553406791096
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9462559028558579
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9840341803463009
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.708792444344502
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.6468780451240538
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.6044974139869574
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.5283786822577018
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.12721101888273206
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.30930165915538804
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.4489712213025254
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7098551817763595
+      name: Cosine Recall@10
+    - type: cosine_ndcg@5
+      value: 0.7127144186187505
+      name: Cosine Ndcg@5
+    - type: cosine_ndcg@10
+      value: 0.7543447490248549
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.708792444344502
+      name: Cosine Mrr@1
+    - type: cosine_mrr@5
+      value: 0.8065999550258622
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 0.8118267710352285
+      name: Cosine Mrr@10
+    - type: cosine_map@10
+      value: 0.6051494969120079
+      name: Cosine Map@10
+    - type: cosine_map@100
+      value: 0.6944358205631005
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on NovaSearch/stella_en_1.5B_v5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [NovaSearch/stella_en_1.5B_v5](https://huggingface.co/NovaSearch/stella_en_1.5B_v5). 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:** [NovaSearch/stella_en_1.5B_v5](https://huggingface.co/NovaSearch/stella_en_1.5B_v5) <!-- at revision b467445fc9c39af69fdb1bda9e18416df4d19f3c -->
+- **Maximum Sequence Length:** 512 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': 512, 'do_lower_case': False}) with Transformer model: Qwen2Model 
+  (1): Pooling({'word_embedding_dimension': 1536, '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): Dense({'in_features': 1536, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'})
+)
+```
+
+## 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("bod9/fulldshardneg")
+# Run inference
+sentences = [
+    '#1 small corded treadmill without remote control',
+    'SUNNY HEALTH & FITNESS ASUNA Space Saving Treadmill, Motorized with Speakers for AUX Audio Connection - 8730G',
+    'Goplus Under Desk Treadmill, with Touchable LED Display and Wireless Remote Control, Built-in 3 Workout Modes and 12 Programs, Walking Jogging Machine, Superfit Electric Treadmill for Home Office',
+]
+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.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Dataset: `ir_evaluation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.5244     |
+| cosine_accuracy@3   | 0.7189     |
+| cosine_accuracy@5   | 0.7823     |
+| cosine_accuracy@10  | 0.8453     |
+| cosine_precision@1  | 0.5244     |
+| cosine_precision@3  | 0.4476     |
+| cosine_precision@5  | 0.4002     |
+| cosine_precision@10 | 0.3198     |
+| cosine_recall@1     | 0.0937     |
+| cosine_recall@3     | 0.2136     |
+| cosine_recall@5     | 0.298      |
+| cosine_recall@10    | 0.4318     |
+| cosine_ndcg@5       | 0.4676     |
+| **cosine_ndcg@10**  | **0.4681** |
+| cosine_mrr@1        | 0.5244     |
+| cosine_mrr@5        | 0.6257     |
+| cosine_mrr@10       | 0.6341     |
+| cosine_map@10       | 0.3493     |
+| cosine_map@100      | 0.4065     |
+
+#### Graded IR
+
+* Dataset: `gr_evaluation`
+* Evaluated with <code>GradedIREvaluator.GradedIREvaluator</code>
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7088     |
+| cosine_accuracy@3   | 0.9038     |
+| cosine_accuracy@5   | 0.9463     |
+| cosine_accuracy@10  | 0.984      |
+| cosine_precision@1  | 0.7088     |
+| cosine_precision@3  | 0.6469     |
+| cosine_precision@5  | 0.6045     |
+| cosine_precision@10 | 0.5284     |
+| cosine_recall@1     | 0.1272     |
+| cosine_recall@3     | 0.3093     |
+| cosine_recall@5     | 0.449      |
+| cosine_recall@10    | 0.7099     |
+| cosine_ndcg@5       | 0.7127     |
+| **cosine_ndcg@10**  | **0.7543** |
+| cosine_mrr@1        | 0.7088     |
+| cosine_mrr@5        | 0.8066     |
+| cosine_mrr@10       | 0.8118     |
+| cosine_map@10       | 0.6051     |
+| cosine_map@100      | 0.6944     |
+
+<!--
+## 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: 180,740 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: 3 tokens</li><li>mean: 9.83 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 34.7 tokens</li><li>max: 107 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 34.66 tokens</li><li>max: 70 tokens</li></ul> |
+* Samples:
+  | anchor                                    | positive                                                                                                              | negative                                                                                      |
+  |:------------------------------------------|:----------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|
+  | <code>!awnmower tires without rims</code> | <code>MaxAuto 2-Pack 13x5.00-6 2PLY Turf Mower Tractor Tire with Yellow Rim, (3" Centered Hub, 3/4" Bushings )</code> | <code>Honda 44710-VG3-010 Front Wheels, (Set of 2)</code>                                     |
+  | <code>!awnmower tires without rims</code> | <code>(Set of 2) 15x6.00-6 Husqvarna/Poulan Tire Wheel Assy .75" Bearing</code>                                       | <code>Honda 44710-VG3-010 Front Wheels, (Set of 2)</code>                                     |
+  | <code>!awnmower tires without rims</code> | <code>MaxAuto 2 Pcs 16x6.50-8 Lawn Mower Tire for Garden Tractors Ridings, 4PR, Tubeless</code>                       | <code>2PK 13x5.00-6 13x5.00x6 13x5x6 13x5-6 2PLY Turf Mower Tractor Tire with Gray Rim</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`: epoch
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 0.0001
+- `weight_decay`: 0.01
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `bf16_full_eval`: True
+- `gradient_checkpointing`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 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
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 0.0001
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: True
+- `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}
+- `tp_size`: 0
+- `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`: True
+- `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
+- `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 | ir_evaluation_cosine_ndcg@10 | gr_evaluation_cosine_ndcg@10 |
+|:------:|:-----:|:-------------:|:----------------------------:|:----------------------------:|
+| 0.0004 | 1     | 8.8035        | -                            | -                            |
+| 0.1770 | 500   | 3.9262        | -                            | -                            |
+| 0.3540 | 1000  | 1.292         | -                            | -                            |
+| 0.5310 | 1500  | 1.069         | -                            | -                            |
+| 0.7080 | 2000  | 0.9684        | -                            | -                            |
+| 0.8850 | 2500  | 0.9254        | -                            | -                            |
+| 1.0    | 2825  | -             | 0.4565                       | 0.7494                       |
+| 1.0619 | 3000  | 0.8566        | -                            | -                            |
+| 1.2389 | 3500  | 0.7997        | -                            | -                            |
+| 1.4159 | 4000  | 0.7695        | -                            | -                            |
+| 1.5929 | 4500  | 0.7489        | -                            | -                            |
+| 1.7699 | 5000  | 0.7555        | -                            | -                            |
+| 1.9469 | 5500  | 0.7279        | -                            | -                            |
+| 2.0    | 5650  | -             | 0.4591                       | 0.7489                       |
+| 2.1239 | 6000  | 0.6673        | -                            | -                            |
+| 2.3009 | 6500  | 0.6388        | -                            | -                            |
+| 2.4779 | 7000  | 0.6286        | -                            | -                            |
+| 2.6549 | 7500  | 0.6168        | -                            | -                            |
+| 2.8319 | 8000  | 0.614         | -                            | -                            |
+| 3.0    | 8475  | -             | 0.4710                       | 0.7542                       |
+| 3.0088 | 8500  | 0.602         | -                            | -                            |
+| 3.1858 | 9000  | 0.5355        | -                            | -                            |
+| 3.3628 | 9500  | 0.5322        | -                            | -                            |
+| 3.5398 | 10000 | 0.5274        | -                            | -                            |
+| 3.7168 | 10500 | 0.5434        | -                            | -                            |
+| 3.8938 | 11000 | 0.5362        | -                            | -                            |
+| 4.0    | 11300 | -             | 0.4697                       | 0.7550                       |
+| 4.0708 | 11500 | 0.5085        | -                            | -                            |
+| 4.2478 | 12000 | 0.48          | -                            | -                            |
+| 4.4248 | 12500 | 0.4871        | -                            | -                            |
+| 4.6018 | 13000 | 0.4845        | -                            | -                            |
+| 4.7788 | 13500 | 0.4879        | -                            | -                            |
+| 4.9558 | 14000 | 0.484         | -                            | -                            |
+| 5.0    | 14125 | -             | 0.4681                       | 0.7543                       |
+
+
+### Framework Versions
+- Python: 3.11.12
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### 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.*
+-->

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NovaSearch/stella_en_1.5B_v5",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330f2950cfd8096da9bfa44bc7d77db80a15b6a6d8393604780f04955cb48f89
+size 4372168

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config_sentence_transformers.json

@@ -0,0 +1,13 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "s2p_query": "Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: ",
+    "s2s_query": "Instruct: Retrieve semantically similar text.\nQuery: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "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:f9f198d74f8167446195840e984e047a0336be641303805c5bb11e25d9ffbe90
+size 11419303

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "NovaSearch/stella_en_1.5B_v5--tokenization_qwen.Qwen2Tokenizer",
+      "NovaSearch/stella_en_1.5B_v5--tokenization_qwen.Qwen2TokenizerFast"
+    ]
+  },
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}