README.md

---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
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.*
-->

### 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.*
-->